Comparison of seven protocols to identify fecal contamination sources using Escherichia coli

USGS Publications Warehouse

Stoeckel, D.M.; Mathes, M.V.; Hyer, K.E.; Hagedorn, C.; Kator, H.; Lukasik, J.; O'Brien, T. L.; Fenger, T.W.; Samadpour, M.; Strickler, K.M.; Wiggins, B.A.

2004-01-01

Microbial source tracking (MST) uses various approaches to classify fecal-indicator microorganisms to source hosts. Reproducibility, accuracy, and robustness of seven phenotypic and genotypic MST protocols were evaluated by use of Escherichia coli from an eight-host library of known-source isolates and a separate, blinded challenge library. In reproducibility tests, measuring each protocol's ability to reclassify blinded replicates, only one (pulsed-field gel electrophoresis; PFGE) correctly classified all test replicates to host species; three protocols classified 48-62% correctly, and the remaining three classified fewer than 25% correctly. In accuracy tests, measuring each protocol's ability to correctly classify new isolates, ribotyping with EcoRI and PvuII approached 100% correct classification but only 6% of isolates were classified; four of the other six protocols (antibiotic resistance analysis, PFGE, and two repetitive-element PCR protocols) achieved better than random accuracy rates when 30-100% of challenge isolates were classified. In robustness tests, measuring each protocol's ability to recognize isolates from nonlibrary hosts, three protocols correctly classified 33-100% of isolates as "unknown origin," whereas four protocols classified all isolates to a source category. A relevance test, summarizing interpretations for a hypothetical water sample containing 30 challenge isolates, indicated that false-positive classifications would hinder interpretations for most protocols. Study results indicate that more representation in known-source libraries and better classification accuracy would be needed before field application. Thorough reliability assessment of classification results is crucial before and during application of MST protocols.

Body size and somatotype characteristics of male golfers in Japan.

PubMed

Kawashima, K; Kat, K; Miyazaki, M

2003-09-01

The aim of this investigation was to compare the physical characteristics and somatotypes of 4 Japanese male golfer groups with 2 non-golfer control groups. Sixty-three male golfers, professional golfers (PR, n=11), collegiate golfers (CO, n=24), general amateur golfers (AM, n=13), collegiate recreational golfers (RE, n=15), non-golfing college student (CG, n=45) and a senior population of non-golfers as a control group (SC, n=20), for a total n=128. They were somatotyped, according to the Heath-Carter anthropometric method. The results show that the categories of the mean somatotypes of PR (3.8-5.8-1.6), CO (4.7-5.6-2.2), AM (3.3-4.4-2.6) and RE (3.7-4.8-2.7) were endomorphic mesomorph, SC (4.7-3.9-2.1) was mesomorphic endomorph, and CG (3.8-4.3-3.3) was central, respectively. The anthropometric variables that best discriminated between skilled and unskilled golfers were body weight, calf skinfold, calf girth, and femur width, with 82% correctly classified PR and 83% correctly classified for CO. Secondly, combination of sum of 4 skinfolds, biceps girth and humerus width, with 72% correctly classified PR and 75% correctly classified for CO. Within the Japanese golfer groups, there are differences between golfers and non-golfers with respect to somatotype, body size and composition. Results suggested that PR showed significantly larger limb girth than other groups. Somatotypes in male golfers tend to increased mesomorphy, related to skill level.

Evaluation of different distortion correction methods and interpolation techniques for an automated classification of celiac disease☆

PubMed Central

Gadermayr, M.; Liedlgruber, M.; Uhl, A.; Vécsei, A.

2013-01-01

Due to the optics used in endoscopes, a typical degradation observed in endoscopic images are barrel-type distortions. In this work we investigate the impact of methods used to correct such distortions in images on the classification accuracy in the context of automated celiac disease classification. For this purpose we compare various different distortion correction methods and apply them to endoscopic images, which are subsequently classified. Since the interpolation used in such methods is also assumed to have an influence on the resulting classification accuracies, we also investigate different interpolation methods and their impact on the classification performance. In order to be able to make solid statements about the benefit of distortion correction we use various different feature extraction methods used to obtain features for the classification. Our experiments show that it is not possible to make a clear statement about the usefulness of distortion correction methods in the context of an automated diagnosis of celiac disease. This is mainly due to the fact that an eventual benefit of distortion correction highly depends on the feature extraction method used for the classification. PMID:23981585

Combining multiple decisions: applications to bioinformatics

NASA Astrophysics Data System (ADS)

Yukinawa, N.; Takenouchi, T.; Oba, S.; Ishii, S.

2008-01-01

Multi-class classification is one of the fundamental tasks in bioinformatics and typically arises in cancer diagnosis studies by gene expression profiling. This article reviews two recent approaches to multi-class classification by combining multiple binary classifiers, which are formulated based on a unified framework of error-correcting output coding (ECOC). The first approach is to construct a multi-class classifier in which each binary classifier to be aggregated has a weight value to be optimally tuned based on the observed data. In the second approach, misclassification of each binary classifier is formulated as a bit inversion error with a probabilistic model by making an analogy to the context of information transmission theory. Experimental studies using various real-world datasets including cancer classification problems reveal that both of the new methods are superior or comparable to other multi-class classification methods.

Authentication of Organically and Conventionally Grown Basils by Gas Chromatography/Mass Spectrometry Chemical Profiles

PubMed Central

Wang, Zhengfang; Chen, Pei; Yu, Liangli; Harrington, Peter de B.

2013-01-01

Basil plants cultivated by organic and conventional farming practices were accurately classified by pattern recognition of gas chromatography/mass spectrometry (GC/MS) data. A novel extraction procedure was devised to extract characteristic compounds from ground basil powders. Two in-house fuzzy classifiers, i.e., the fuzzy rule-building expert system (FuRES) and the fuzzy optimal associative memory (FOAM) for the first time, were used to build classification models. Two crisp classifiers, i.e., soft independent modeling by class analogy (SIMCA) and the partial least-squares discriminant analysis (PLS-DA), were used as control methods. Prior to data processing, baseline correction and retention time alignment were performed. Classifiers were built with the two-way data sets, the total ion chromatogram representation of data sets, and the total mass spectrum representation of data sets, separately. Bootstrapped Latin partition (BLP) was used as an unbiased evaluation of the classifiers. By using two-way data sets, average classification rates with FuRES, FOAM, SIMCA, and PLS-DA were 100 ± 0%, 94.4 ± 0.4%, 93.3 ± 0.4%, and 100 ± 0%, respectively, for 100 independent evaluations. The established classifiers were used to classify a new validation set collected 2.5 months later with no parametric changes except that the training set and validation set were individually mean-centered. For the new two-way validation set, classification rates with FuRES, FOAM, SIMCA, and PLS-DA were 100%, 83%, 97%, and 100%, respectively. Thereby, the GC/MS analysis was demonstrated as a viable approach for organic basil authentication. It is the first time that a FOAM has been applied to classification. A novel baseline correction method was used also for the first time. The FuRES and the FOAM are demonstrated as powerful tools for modeling and classifying GC/MS data of complex samples and the data pretreatments are demonstrated to be useful to improve the performance of classifiers. PMID:23398171

Human cell structure-driven model construction for predicting protein subcellular location from biological images.

PubMed

Shao, Wei; Liu, Mingxia; Zhang, Daoqiang

2016-01-01

The systematic study of subcellular location pattern is very important for fully characterizing the human proteome. Nowadays, with the great advances in automated microscopic imaging, accurate bioimage-based classification methods to predict protein subcellular locations are highly desired. All existing models were constructed on the independent parallel hypothesis, where the cellular component classes are positioned independently in a multi-class classification engine. The important structural information of cellular compartments is missed. To deal with this problem for developing more accurate models, we proposed a novel cell structure-driven classifier construction approach (SC-PSorter) by employing the prior biological structural information in the learning model. Specifically, the structural relationship among the cellular components is reflected by a new codeword matrix under the error correcting output coding framework. Then, we construct multiple SC-PSorter-based classifiers corresponding to the columns of the error correcting output coding codeword matrix using a multi-kernel support vector machine classification approach. Finally, we perform the classifier ensemble by combining those multiple SC-PSorter-based classifiers via majority voting. We evaluate our method on a collection of 1636 immunohistochemistry images from the Human Protein Atlas database. The experimental results show that our method achieves an overall accuracy of 89.0%, which is 6.4% higher than the state-of-the-art method. The dataset and code can be downloaded from https://github.com/shaoweinuaa/. dqzhang@nuaa.edu.cn Supplementary data are available at Bioinformatics online. © The Author 2015. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Fully automated macular pathology detection in retina optical coherence tomography images using sparse coding and dictionary learning

NASA Astrophysics Data System (ADS)

Sun, Yankui; Li, Shan; Sun, Zhongyang

2017-01-01

We propose a framework for automated detection of dry age-related macular degeneration (AMD) and diabetic macular edema (DME) from retina optical coherence tomography (OCT) images, based on sparse coding and dictionary learning. The study aims to improve the classification performance of state-of-the-art methods. First, our method presents a general approach to automatically align and crop retina regions; then it obtains global representations of images by using sparse coding and a spatial pyramid; finally, a multiclass linear support vector machine classifier is employed for classification. We apply two datasets for validating our algorithm: Duke spectral domain OCT (SD-OCT) dataset, consisting of volumetric scans acquired from 45 subjects-15 normal subjects, 15 AMD patients, and 15 DME patients; and clinical SD-OCT dataset, consisting of 678 OCT retina scans acquired from clinics in Beijing-168, 297, and 213 OCT images for AMD, DME, and normal retinas, respectively. For the former dataset, our classifier correctly identifies 100%, 100%, and 93.33% of the volumes with DME, AMD, and normal subjects, respectively, and thus performs much better than the conventional method; for the latter dataset, our classifier leads to a correct classification rate of 99.67%, 99.67%, and 100.00% for DME, AMD, and normal images, respectively.

Fully automated macular pathology detection in retina optical coherence tomography images using sparse coding and dictionary learning.

PubMed

Sun, Yankui; Li, Shan; Sun, Zhongyang

2017-01-01

We propose a framework for automated detection of dry age-related macular degeneration (AMD) and diabetic macular edema (DME) from retina optical coherence tomography (OCT) images, based on sparse coding and dictionary learning. The study aims to improve the classification performance of state-of-the-art methods. First, our method presents a general approach to automatically align and crop retina regions; then it obtains global representations of images by using sparse coding and a spatial pyramid; finally, a multiclass linear support vector machine classifier is employed for classification. We apply two datasets for validating our algorithm: Duke spectral domain OCT (SD-OCT) dataset, consisting of volumetric scans acquired from 45 subjects—15 normal subjects, 15 AMD patients, and 15 DME patients; and clinical SD-OCT dataset, consisting of 678 OCT retina scans acquired from clinics in Beijing—168, 297, and 213 OCT images for AMD, DME, and normal retinas, respectively. For the former dataset, our classifier correctly identifies 100%, 100%, and 93.33% of the volumes with DME, AMD, and normal subjects, respectively, and thus performs much better than the conventional method; for the latter dataset, our classifier leads to a correct classification rate of 99.67%, 99.67%, and 100.00% for DME, AMD, and normal images, respectively.

Validation of a questionnaire method for estimating extent of menstrual blood loss in young adult women.

PubMed

Heath, A L; Skeaff, C M; Gibson, R S

1999-04-01

The objective of this study was to validate two indirect methods for estimating the extent of menstrual blood loss against a reference method to determine which method would be most appropriate for use in a population of young adult women. Thirty-two women aged 18 to 29 years (mean +/- SD; 22.4 +/- 2.8) were recruited by poster in Dunedin (New Zealand). Data are presented for 29 women. A recall method and a record method for estimating extent of menstrual loss were validated against a weighed reference method. Spearman rank correlation coefficients between blood loss assessed by Weighed Menstrual Loss and Menstrual Record was rs = 0.47 (p = 0.012), and between Weighed Menstrual Loss and Menstrual Recall, was rs = 0.61 (p = 0.001). The Record method correctly classified 66% of participants into the same tertile, grossly misclassifying 14%. The Recall method correctly classified 59% of participants, grossly misclassifying 7%. Reference method menstrual loss calculated for surrogate categories demonstrated a significant difference between the second and third tertiles for the Record method, and between the first and third tertiles for the Recall method. The Menstrual Recall method can differentiate between low and high levels of menstrual blood loss in young adult women, is quick to complete and analyse, and has a low participant burden.

Study design in high-dimensional classification analysis.

PubMed

Sánchez, Brisa N; Wu, Meihua; Song, Peter X K; Wang, Wen

2016-10-01

Advances in high throughput technology have accelerated the use of hundreds to millions of biomarkers to construct classifiers that partition patients into different clinical conditions. Prior to classifier development in actual studies, a critical need is to determine the sample size required to reach a specified classification precision. We develop a systematic approach for sample size determination in high-dimensional (large [Formula: see text] small [Formula: see text]) classification analysis. Our method utilizes the probability of correct classification (PCC) as the optimization objective function and incorporates the higher criticism thresholding procedure for classifier development. Further, we derive the theoretical bound of maximal PCC gain from feature augmentation (e.g. when molecular and clinical predictors are combined in classifier development). Our methods are motivated and illustrated by a study using proteomics markers to classify post-kidney transplantation patients into stable and rejecting classes. © The Author 2016. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Application of machine learning on brain cancer multiclass classification

NASA Astrophysics Data System (ADS)

Panca, V.; Rustam, Z.

2017-07-01

Classification of brain cancer is a problem of multiclass classification. One approach to solve this problem is by first transforming it into several binary problems. The microarray gene expression dataset has the two main characteristics of medical data: extremely many features (genes) and only a few number of samples. The application of machine learning on microarray gene expression dataset mainly consists of two steps: feature selection and classification. In this paper, the features are selected using a method based on support vector machine recursive feature elimination (SVM-RFE) principle which is improved to solve multiclass classification, called multiple multiclass SVM-RFE. Instead of using only the selected features on a single classifier, this method combines the result of multiple classifiers. The features are divided into subsets and SVM-RFE is used on each subset. Then, the selected features on each subset are put on separate classifiers. This method enhances the feature selection ability of each single SVM-RFE. Twin support vector machine (TWSVM) is used as the method of the classifier to reduce computational complexity. While ordinary SVM finds single optimum hyperplane, the main objective Twin SVM is to find two non-parallel optimum hyperplanes. The experiment on the brain cancer microarray gene expression dataset shows this method could classify 71,4% of the overall test data correctly, using 100 and 1000 genes selected from multiple multiclass SVM-RFE feature selection method. Furthermore, the per class results show that this method could classify data of normal and MD class with 100% accuracy.

Peculiarities of use of ECOC and AdaBoost based classifiers for thematic processing of hyperspectral data

NASA Astrophysics Data System (ADS)

Dementev, A. O.; Dmitriev, E. V.; Kozoderov, V. V.; Egorov, V. D.

2017-10-01

Hyperspectral imaging is up-to-date promising technology widely applied for the accurate thematic mapping. The presence of a large number of narrow survey channels allows us to use subtle differences in spectral characteristics of objects and to make a more detailed classification than in the case of using standard multispectral data. The difficulties encountered in the processing of hyperspectral images are usually associated with the redundancy of spectral information which leads to the problem of the curse of dimensionality. Methods currently used for recognizing objects on multispectral and hyperspectral images are usually based on standard base supervised classification algorithms of various complexity. Accuracy of these algorithms can be significantly different depending on considered classification tasks. In this paper we study the performance of ensemble classification methods for the problem of classification of the forest vegetation. Error correcting output codes and boosting are tested on artificial data and real hyperspectral images. It is demonstrates, that boosting gives more significant improvement when used with simple base classifiers. The accuracy in this case in comparable the error correcting output code (ECOC) classifier with Gaussian kernel SVM base algorithm. However the necessity of boosting ECOC with Gaussian kernel SVM is questionable. It is demonstrated, that selected ensemble classifiers allow us to recognize forest species with high enough accuracy which can be compared with ground-based forest inventory data.

An Evaluation of Information Criteria Use for Correct Cross-Classified Random Effects Model Selection

ERIC Educational Resources Information Center

Beretvas, S. Natasha; Murphy, Daniel L.

2013-01-01

The authors assessed correct model identification rates of Akaike's information criterion (AIC), corrected criterion (AICC), consistent AIC (CAIC), Hannon and Quinn's information criterion (HQIC), and Bayesian information criterion (BIC) for selecting among cross-classified random effects models. Performance of default values for the 5…

Consensus Classification Using Non-Optimized Classifiers.

PubMed

Brownfield, Brett; Lemos, Tony; Kalivas, John H

2018-04-03

Classifying samples into categories is a common problem in analytical chemistry and other fields. Classification is usually based on only one method, but numerous classifiers are available with some being complex, such as neural networks, and others are simple, such as k nearest neighbors. Regardless, most classification schemes require optimization of one or more tuning parameters for best classification accuracy, sensitivity, and specificity. A process not requiring exact selection of tuning parameter values would be useful. To improve classification, several ensemble approaches have been used in past work to combine classification results from multiple optimized single classifiers. The collection of classifications for a particular sample are then combined by a fusion process such as majority vote to form the final classification. Presented in this Article is a method to classify a sample by combining multiple classification methods without specifically classifying the sample by each method, that is, the classification methods are not optimized. The approach is demonstrated on three analytical data sets. The first is a beer authentication set with samples measured on five instruments, allowing fusion of multiple instruments by three ways. The second data set is composed of textile samples from three classes based on Raman spectra. This data set is used to demonstrate the ability to classify simultaneously with different data preprocessing strategies, thereby reducing the need to determine the ideal preprocessing method, a common prerequisite for accurate classification. The third data set contains three wine cultivars for three classes measured at 13 unique chemical and physical variables. In all cases, fusion of nonoptimized classifiers improves classification. Also presented are atypical uses of Procrustes analysis and extended inverted signal correction (EISC) for distinguishing sample similarities to respective classes.

Improvement of training set structure in fusion data cleaning using Time-Domain Global Similarity method

NASA Astrophysics Data System (ADS)

Liu, J.; Lan, T.; Qin, H.

2017-10-01

Traditional data cleaning identifies dirty data by classifying original data sequences, which is a class-imbalanced problem since the proportion of incorrect data is much less than the proportion of correct ones for most diagnostic systems in Magnetic Confinement Fusion (MCF) devices. When using machine learning algorithms to classify diagnostic data based on class-imbalanced training set, most classifiers are biased towards the major class and show very poor classification rates on the minor class. By transforming the direct classification problem about original data sequences into a classification problem about the physical similarity between data sequences, the class-balanced effect of Time-Domain Global Similarity (TDGS) method on training set structure is investigated in this paper. Meanwhile, the impact of improved training set structure on data cleaning performance of TDGS method is demonstrated with an application example in EAST POlarimetry-INTerferometry (POINT) system.

Identifying areas with vitamin A deficiency: the validity of a semiquantitative food frequency method.

PubMed

Sloan, N L; Rosen, D; de la Paz, T; Arita, M; Temalilwa, C; Solomons, N W

1997-02-01

The prevalence of vitamin A deficiency has traditionally been assessed through xerophthalmia or biochemical surveys. The cost and complexity of implementing these methods limits the ability of nonresearch organizations to identify vitamin A deficiency. This study examined the validity of a simple, inexpensive food frequency method to identify areas with a high prevalence of vitamin A deficiency. The validity of the method was tested in 15 communities, 5 each from the Philippines, Guatemala, and Tanzania. Serum retinol concentrations of less than 20 micrograms/dL defined vitamin A deficiency. Weighted measures of vitamin A intake six or fewer times per week and unweighted measures of consumption of animal sources of vitamin A four or fewer times per week correctly classified seven of eight communities as having a high prevalence of vitamin A deficiency (i.e., 15% or more preschool-aged children in the community had the deficiency) (sensitivity = 87.5%) and four of seven communities as having a low prevalence (specificity = 57.1%). This method correctly classified the vitamin A deficiency status of 73.3% of the communities but demonstrated a high false-positive rate (42.9%).

Bioimage informatics approach to automated meibomian gland analysis in infrared images of meibography

PubMed Central

Celik, Turgay; Lee, Hwee Kuan; Petznick, Andrea; Tong, Louis

2013-01-01

Background Infrared (IR) meibography is an imaging technique to capture the Meibomian glands in the eyelids. These ocular surface structures are responsible for producing the lipid layer of the tear film which helps to reduce tear evaporation. In a normal healthy eye, the glands have similar morphological features in terms of spatial width, in-plane elongation, length. On the other hand, eyes with Meibomian gland dysfunction show visible structural irregularities that help in the diagnosis and prognosis of the disease. However, currently there is no universally accepted algorithm for detection of these image features which will be clinically useful. We aim to develop a method of automated gland segmentation which allows images to be classified. Methods A set of 131 meibography images were acquired from patients from the Singapore National Eye Center. We used a method of automated gland segmentation using Gabor wavelets. Features of the imaged glands including orientation, width, length and curvature were extracted and the IR images enhanced. The images were classified as ‘healthy’, ‘intermediate’ or ‘unhealthy’, through the use of a support vector machine classifier (SVM). Half the images were used for training the SVM and the other half for validation. Independently of this procedure, the meibographs were classified by an expert clinician into the same 3 grades. Results The algorithm correctly detected 94% and 98% of mid-line pixels of gland and inter-gland regions, respectively, on healthy images. On intermediate images, correct detection rates of 92% and 97% of mid-line pixels of gland and inter-gland regions were achieved respectively. The true positive rate of detecting healthy images was 86%, and for intermediate images, 74%. The corresponding false positive rates were 15% and 31% respectively. Using the SVM, the proposed method has 88% accuracy in classifying images into the 3 classes. The classification of images into healthy and unhealthy classes achieved a 100% accuracy, but 7/38 intermediate images were incorrectly classified. Conclusions This technique of image analysis in meibography can help clinicians to interpret the degree of gland destruction in patients with dry eye and meibomian gland dysfunction.

Influence of different topographic correction strategies on mountain vegetation classification accuracy in the Lancang Watershed, China

NASA Astrophysics Data System (ADS)

Zhang, Zhiming; de Wulf, Robert R.; van Coillie, Frieke M. B.; Verbeke, Lieven P. C.; de Clercq, Eva M.; Ou, Xiaokun

2011-01-01

Mapping of vegetation using remote sensing in mountainous areas is considerably hampered by topographic effects on the spectral response pattern. A variety of topographic normalization techniques have been proposed to correct these illumination effects due to topography. The purpose of this study was to compare six different topographic normalization methods (Cosine correction, Minnaert correction, C-correction, Sun-canopy-sensor correction, two-stage topographic normalization, and slope matching technique) for their effectiveness in enhancing vegetation classification in mountainous environments. Since most of the vegetation classes in the rugged terrain of the Lancang Watershed (China) did not feature a normal distribution, artificial neural networks (ANNs) were employed as a classifier. Comparing the ANN classifications, none of the topographic correction methods could significantly improve ETM+ image classification overall accuracy. Nevertheless, at the class level, the accuracy of pine forest could be increased by using topographically corrected images. On the contrary, oak forest and mixed forest accuracies were significantly decreased by using corrected images. The results also showed that none of the topographic normalization strategies was satisfactorily able to correct for the topographic effects in severely shadowed areas.

A method for classification of transient events in EEG recordings: application to epilepsy diagnosis.

PubMed

Tzallas, A T; Karvelis, P S; Katsis, C D; Fotiadis, D I; Giannopoulos, S; Konitsiotis, S

2006-01-01

The aim of the paper is to analyze transient events in inter-ictal EEG recordings, and classify epileptic activity into focal or generalized epilepsy using an automated method. A two-stage approach is proposed. In the first stage the observed transient events of a single channel are classified into four categories: epileptic spike (ES), muscle activity (EMG), eye blinking activity (EOG), and sharp alpha activity (SAA). The process is based on an artificial neural network. Different artificial neural network architectures have been tried and the network having the lowest error has been selected using the hold out approach. In the second stage a knowledge-based system is used to produce diagnosis for focal or generalized epileptic activity. The classification of transient events reported high overall accuracy (84.48%), while the knowledge-based system for epilepsy diagnosis correctly classified nine out of ten cases. The proposed method is advantageous since it effectively detects and classifies the undesirable activity into appropriate categories and produces a final outcome related to the existence of epilepsy.

Using multiple classifiers for predicting the risk of endovascular aortic aneurysm repair re-intervention through hybrid feature selection.

PubMed

Attallah, Omneya; Karthikesalingam, Alan; Holt, Peter Je; Thompson, Matthew M; Sayers, Rob; Bown, Matthew J; Choke, Eddie C; Ma, Xianghong

2017-11-01

Feature selection is essential in medical area; however, its process becomes complicated with the presence of censoring which is the unique character of survival analysis. Most survival feature selection methods are based on Cox's proportional hazard model, though machine learning classifiers are preferred. They are less employed in survival analysis due to censoring which prevents them from directly being used to survival data. Among the few work that employed machine learning classifiers, partial logistic artificial neural network with auto-relevance determination is a well-known method that deals with censoring and perform feature selection for survival data. However, it depends on data replication to handle censoring which leads to unbalanced and biased prediction results especially in highly censored data. Other methods cannot deal with high censoring. Therefore, in this article, a new hybrid feature selection method is proposed which presents a solution to high level censoring. It combines support vector machine, neural network, and K-nearest neighbor classifiers using simple majority voting and a new weighted majority voting method based on survival metric to construct a multiple classifier system. The new hybrid feature selection process uses multiple classifier system as a wrapper method and merges it with iterated feature ranking filter method to further reduce features. Two endovascular aortic repair datasets containing 91% censored patients collected from two centers were used to construct a multicenter study to evaluate the performance of the proposed approach. The results showed the proposed technique outperformed individual classifiers and variable selection methods based on Cox's model such as Akaike and Bayesian information criterions and least absolute shrinkage and selector operator in p values of the log-rank test, sensitivity, and concordance index. This indicates that the proposed classifier is more powerful in correctly predicting the risk of re-intervention enabling doctor in selecting patients' future follow-up plan.

Enhancing atlas based segmentation with multiclass linear classifiers

DOE Office of Scientific and Technical Information (OSTI.GOV)

Sdika, Michaël, E-mail: michael.sdika@creatis.insa-lyon.fr

Purpose: To present a method to enrich atlases for atlas based segmentation. Such enriched atlases can then be used as a single atlas or within a multiatlas framework. Methods: In this paper, machine learning techniques have been used to enhance the atlas based segmentation approach. The enhanced atlas defined in this work is a pair composed of a gray level image alongside an image of multiclass classifiers with one classifier per voxel. Each classifier embeds local information from the whole training dataset that allows for the correction of some systematic errors in the segmentation and accounts for the possible localmore » registration errors. The authors also propose to use these images of classifiers within a multiatlas framework: results produced by a set of such local classifier atlases can be combined using a label fusion method. Results: Experiments have been made on the in vivo images of the IBSR dataset and a comparison has been made with several state-of-the-art methods such as FreeSurfer and the multiatlas nonlocal patch based method of Coupé or Rousseau. These experiments show that their method is competitive with state-of-the-art methods while having a low computational cost. Further enhancement has also been obtained with a multiatlas version of their method. It is also shown that, in this case, nonlocal fusion is unnecessary. The multiatlas fusion can therefore be done efficiently. Conclusions: The single atlas version has similar quality as state-of-the-arts multiatlas methods but with the computational cost of a naive single atlas segmentation. The multiatlas version offers a improvement in quality and can be done efficiently without a nonlocal strategy.« less

An expert support system for breast cancer diagnosis using color wavelet features.

PubMed

Issac Niwas, S; Palanisamy, P; Chibbar, Rajni; Zhang, W J

2012-10-01

Breast cancer diagnosis can be done through the pathologic assessments of breast tissue samples such as core needle biopsy technique. The result of analysis on this sample by pathologist is crucial for breast cancer patient. In this paper, nucleus of tissue samples are investigated after decomposition by means of the Log-Gabor wavelet on HSV color domain and an algorithm is developed to compute the color wavelet features. These features are used for breast cancer diagnosis using Support Vector Machine (SVM) classifier algorithm. The ability of properly trained SVM is to correctly classify patterns and make them particularly suitable for use in an expert system that aids in the diagnosis of cancer tissue samples. The results are compared with other multivariate classifiers such as Naïves Bayes classifier and Artificial Neural Network. The overall accuracy of the proposed method using SVM classifier will be further useful for automation in cancer diagnosis.

TRAFIC: fiber tract classification using deep learning

NASA Astrophysics Data System (ADS)

Ngattai Lam, Prince D.; Belhomme, Gaetan; Ferrall, Jessica; Patterson, Billie; Styner, Martin; Prieto, Juan C.

2018-03-01

We present TRAFIC, a fully automated tool for the labeling and classification of brain fiber tracts. TRAFIC classifies new fibers using a neural network trained using shape features computed from previously traced and manually corrected fiber tracts. It is independent from a DTI Atlas as it is applied to already traced fibers. This work is motivated by medical applications where the process of extracting fibers from a DTI atlas, or classifying fibers manually is time consuming and requires knowledge about brain anatomy. With this new approach we were able to classify traced fiber tracts obtaining encouraging results. In this report we will present in detail the methods used and the results achieved with our approach.

Artificial neural network EMG classifier for functional hand grasp movements prediction.

PubMed

Gandolla, Marta; Ferrante, Simona; Ferrigno, Giancarlo; Baldassini, Davide; Molteni, Franco; Guanziroli, Eleonora; Cotti Cottini, Michele; Seneci, Carlo; Pedrocchi, Alessandra

2017-12-01

Objective To design and implement an electromyography (EMG)-based controller for a hand robotic assistive device, which is able to classify the user's motion intention before the effective kinematic movement execution. Methods Multiple degrees-of-freedom hand grasp movements (i.e. pinching, grasp an object, grasping) were predicted by means of surface EMG signals, recorded from 10 bipolar EMG electrodes arranged in a circular configuration around the forearm 2-3 cm from the elbow. Two cascaded artificial neural networks were then exploited to detect the patient's motion intention from the EMG signal window starting from the electrical activity onset to movement onset (i.e. electromechanical delay). Results The proposed approach was tested on eight healthy control subjects (4 females; age range 25-26 years) and it demonstrated a mean ± SD testing performance of 76% ± 14% for correctly predicting healthy users' motion intention. Two post-stroke patients tested the controller and obtained 79% and 100% of correctly classified movements under testing conditions. Conclusion A task-selection controller was developed to estimate the intended movement from the EMG measured during the electromechanical delay.

Comparison of ring artifact removal methods using flat panel detector based CT images

PubMed Central

2011-01-01

Background Ring artifacts are the concentric rings superimposed on the tomographic images often caused by the defective and insufficient calibrated detector elements as well as by the damaged scintillator crystals of the flat panel detector. It may be also generated by objects attenuating X-rays very differently in different projection direction. Ring artifact reduction techniques so far reported in the literature can be broadly classified into two groups. One category of the approaches is based on the sinogram processing also known as the pre-processing techniques and the other category of techniques perform processing on the 2-D reconstructed images, recognized as the post-processing techniques in the literature. The strength and weakness of these categories of approaches are yet to be explored from a common platform. Method In this paper, a comparative study of the two categories of ring artifact reduction techniques basically designed for the multi-slice CT instruments is presented from a common platform. For comparison, two representative algorithms from each of the two categories are selected from the published literature. A very recently reported state-of-the-art sinogram domain ring artifact correction method that classifies the ring artifacts according to their strength and then corrects the artifacts using class adaptive correction schemes is also included in this comparative study. The first sinogram domain correction method uses a wavelet based technique to detect the corrupted pixels and then using a simple linear interpolation technique estimates the responses of the bad pixels. The second sinogram based correction method performs all the filtering operations in the transform domain, i.e., in the wavelet and Fourier domain. On the other hand, the two post-processing based correction techniques actually operate on the polar transform domain of the reconstructed CT images. The first method extracts the ring artifact template vector using a homogeneity test and then corrects the CT images by subtracting the artifact template vector from the uncorrected images. The second post-processing based correction technique performs median and mean filtering on the reconstructed images to produce the corrected images. Results The performances of the comparing algorithms have been tested by using both quantitative and perceptual measures. For quantitative analysis, two different numerical performance indices are chosen. On the other hand, different types of artifact patterns, e.g., single/band ring, artifacts from defective and mis-calibrated detector elements, rings in highly structural object and also in hard object, rings from different flat-panel detectors are analyzed to perceptually investigate the strength and weakness of the five methods. An investigation has been also carried out to compare the efficacy of these algorithms in correcting the volume images from a cone beam CT with the parameters determined from one particular slice. Finally, the capability of each correction technique in retaining the image information (e.g., small object at the iso-center) accurately in the corrected CT image has been also tested. Conclusions The results show that the performances of the algorithms are limited and none is fully suitable for correcting different types of ring artifacts without introducing processing distortion to the image structure. To achieve the diagnostic quality of the corrected slices a combination of the two approaches (sinogram- and post-processing) can be used. Also the comparing methods are not suitable for correcting the volume images from a cone beam flat-panel detector based CT. PMID:21846411

Are traditional methods of determining nest predators and nest fates reliable? An experiment with Wood Thrushes (Hylocichla mustelina) using miniature video cameras

USGS Publications Warehouse

Williams, Gary E.; Wood, P.B.

2002-01-01

We used miniature infrared video cameras to monitor Wood Thrush (Hylocichla mustelina) nests during 1998–2000. We documented nest predators and examined whether evidence at nests can be used to predict predator identities and nest fates. Fifty-six nests were monitored; 26 failed, with 3 abandoned and 23 depredated. We predicted predator class (avian, mammalian, snake) prior to review of video footage and were incorrect 57% of the time. Birds and mammals were underrepresented whereas snakes were over-represented in our predictions. We documented ≥9 nest-predator species, with the southern flying squirrel (Glaucomys volans) taking the most nests (n = 8). During 2000, we predicted fate (fledge or fail) of 27 nests; 23 were classified correctly. Traditional methods of monitoring nests appear to be effective for classifying success or failure of nests, but ineffective at classifying nest predators.

Egg embryo development detection with hyperspectral imaging

NASA Astrophysics Data System (ADS)

Lawrence, Kurt C.; Smith, Douglas P.; Windham, William R.; Heitschmidt, Gerald W.; Park, Bosoon

2006-10-01

In the U. S. egg industry, anywhere from 130 million to over one billion infertile eggs are incubated each year. Some of these infertile eggs explode in the hatching cabinet and can potentially spread molds or bacteria to all the eggs in the cabinet. A method to detect the embryo development of incubated eggs was developed. Twelve brown-shell hatching eggs from two replicates (n=24) were incubated and imaged to identify embryo development. A hyperspectral imaging system was used to collect transmission images from 420 to 840 nm of brown-shell eggs positioned with the air cell vertical and normal to the camera lens. Raw transmission images from about 400 to 900 nm were collected for every egg on days 0, 1, 2, and 3 of incubation. A total of 96 images were collected and eggs were broken out on day 6 to determine fertility. After breakout, all eggs were found to be fertile. Therefore, this paper presents results for egg embryo development, not fertility. The original hyperspectral data and spectral means for each egg were both used to create embryo development models. With the hyperspectral data range reduced to about 500 to 700 nm, a minimum noise fraction transformation was used, along with a Mahalanobis Distance classification model, to predict development. Days 2 and 3 were all correctly classified (100%), while day 0 and day 1 were classified at 95.8% and 91.7%, respectively. Alternatively, the mean spectra from each egg were used to develop a partial least squares regression (PLSR) model. First, a PLSR model was developed with all eggs and all days. The data were multiplicative scatter corrected, spectrally smoothed, and the wavelength range was reduced to 539 - 770 nm. With a one-out cross validation, all eggs for all days were correctly classified (100%). Second, a PLSR model was developed with data from day 0 and day 3, and the model was validated with data from day 1 and 2. For day 1, 22 of 24 eggs were correctly classified (91.7%) and for day 2, all eggs were correctly classified (100%). Although the results are based on relatively small sample sizes, they are encouraging. However, larger sample sizes, from multiple flocks, will be needed to fully validate and verify these models. Additionally, future experiments must also include non-fertile eggs so the fertile / non-fertile effect can be determined.

A random forest model based classification scheme for neonatal amplitude-integrated EEG.

PubMed

Chen, Weiting; Wang, Yu; Cao, Guitao; Chen, Guoqiang; Gu, Qiufang

2014-01-01

Modern medical advances have greatly increased the survival rate of infants, while they remain in the higher risk group for neurological problems later in life. For the infants with encephalopathy or seizures, identification of the extent of brain injury is clinically challenging. Continuous amplitude-integrated electroencephalography (aEEG) monitoring offers a possibility to directly monitor the brain functional state of the newborns over hours, and has seen an increasing application in neonatal intensive care units (NICUs). This paper presents a novel combined feature set of aEEG and applies random forest (RF) method to classify aEEG tracings. To that end, a series of experiments were conducted on 282 aEEG tracing cases (209 normal and 73 abnormal ones). Basic features, statistic features and segmentation features were extracted from both the tracing as a whole and the segmented recordings, and then form a combined feature set. All the features were sent to a classifier afterwards. The significance of feature, the data segmentation, the optimization of RF parameters, and the problem of imbalanced datasets were examined through experiments. Experiments were also done to evaluate the performance of RF on aEEG signal classifying, compared with several other widely used classifiers including SVM-Linear, SVM-RBF, ANN, Decision Tree (DT), Logistic Regression(LR), ML, and LDA. The combined feature set can better characterize aEEG signals, compared with basic features, statistic features and segmentation features respectively. With the combined feature set, the proposed RF-based aEEG classification system achieved a correct rate of 92.52% and a high F1-score of 95.26%. Among all of the seven classifiers examined in our work, the RF method got the highest correct rate, sensitivity, specificity, and F1-score, which means that RF outperforms all of the other classifiers considered here. The results show that the proposed RF-based aEEG classification system with the combined feature set is efficient and helpful to better detect the brain disorders in newborns.

A Novel Acoustic Sensor Approach to Classify Seeds Based on Sound Absorption Spectra

PubMed Central

Gasso-Tortajada, Vicent; Ward, Alastair J.; Mansur, Hasib; Brøchner, Torben; Sørensen, Claus G.; Green, Ole

2010-01-01

A non-destructive and novel in situ acoustic sensor approach based on the sound absorption spectra was developed for identifying and classifying different seed types. The absorption coefficient spectra were determined by using the impedance tube measurement method. Subsequently, a multivariate statistical analysis, i.e., principal component analysis (PCA), was performed as a way to generate a classification of the seeds based on the soft independent modelling of class analogy (SIMCA) method. The results show that the sound absorption coefficient spectra of different seed types present characteristic patterns which are highly dependent on seed size and shape. In general, seed particle size and sphericity were inversely related with the absorption coefficient. PCA presented reliable grouping capabilities within the diverse seed types, since the 95% of the total spectral variance was described by the first two principal components. Furthermore, the SIMCA classification model based on the absorption spectra achieved optimal results as 100% of the evaluation samples were correctly classified. This study contains the initial structuring of an innovative method that will present new possibilities in agriculture and industry for classifying and determining physical properties of seeds and other materials. PMID:22163455

Sample size, library composition, and genotypic diversity among natural populations of Escherichia coli from different animals influence accuracy of determining sources of fecal pollution.

PubMed

Johnson, LeeAnn K; Brown, Mary B; Carruthers, Ethan A; Ferguson, John A; Dombek, Priscilla E; Sadowsky, Michael J

2004-08-01

A horizontal, fluorophore-enhanced, repetitive extragenic palindromic-PCR (rep-PCR) DNA fingerprinting technique (HFERP) was developed and evaluated as a means to differentiate human from animal sources of Escherichia coli. Box A1R primers and PCR were used to generate 2,466 rep-PCR and 1,531 HFERP DNA fingerprints from E. coli strains isolated from fecal material from known human and 12 animal sources: dogs, cats, horses, deer, geese, ducks, chickens, turkeys, cows, pigs, goats, and sheep. HFERP DNA fingerprinting reduced within-gel grouping of DNA fingerprints and improved alignment of DNA fingerprints between gels, relative to that achieved using rep-PCR DNA fingerprinting. Jackknife analysis of the complete rep-PCR DNA fingerprint library, done using Pearson's product-moment correlation coefficient, indicated that animal and human isolates were assigned to the correct source groups with an 82.2% average rate of correct classification. However, when only unique isolates were examined, isolates from a single animal having a unique DNA fingerprint, Jackknife analysis showed that isolates were assigned to the correct source groups with a 60.5% average rate of correct classification. The percentages of correctly classified isolates were about 15 and 17% greater for rep-PCR and HFERP, respectively, when analyses were done using the curve-based Pearson's product-moment correlation coefficient, rather than the band-based Jaccard algorithm. Rarefaction analysis indicated that, despite the relatively large size of the known-source database, genetic diversity in E. coli was very great and is most likely accounting for our inability to correctly classify many environmental E. coli isolates. Our data indicate that removal of duplicate genotypes within DNA fingerprint libraries, increased database size, proper methods of statistical analysis, and correct alignment of band data within and between gels improve the accuracy of microbial source tracking methods.

A new method for correcting type I and type II constricted (cup and lop) ears.

PubMed

Xiaogeng, Hu; Hongxing, Zhuang; Qinghua, Yang; Haiyue, Jiang; Yanyong, Zhao

2006-01-01

Tanzer suggested the term "constricted ear," denoting a spectrum of deformities limited to the superior third of the ear. Tanzer classified the constricted ear into three types. Type I ears have involvement of the helix, which usually is flattened. Type II ears show involvement of both the helix and the scapha. With type III ears, the auricle is rolled into a nearly tubular form that some authors regard as a form of microtia. The authors' new method for correcting the constricted ear varies in accordance with the diverse degree of deformity. The new method was used to correct constricted ears through a one-stage operation in eight type I cases. For the remaining six type 2 cases, the methods were combined with composite grafting. Most of the patients were satisfied with the final results. Therefore, the authors conclude that their approach is suitable for the treatment of type I and type II constricted ears.

A CONCISE PANEL OF BIOMARKERS IDENTIFIES NEUROCOGNITIVE FUNCTIONING CHANGES IN HIV-INFECTED INDIVIDUALS

PubMed Central

Marcotte, Thomas D.; Deutsch, Reena; Michael, Benedict Daniel; Franklin, Donald; Cookson, Debra Rosario; Bharti, Ajay R.; Grant, Igor; Letendre, Scott L.

2013-01-01

Background Neurocognitive (NC) impairment (NCI) occurs commonly in people living with HIV. Despite substantial effort, no biomarkers have been sufficiently validated for diagnosis and prognosis of NCI in the clinic. The goal of this project was to identify diagnostic or prognostic biomarkers for NCI in a comprehensively characterized HIV cohort. Methods Multidisciplinary case review selected 98 HIV-infected individuals and categorized them into four NC groups using normative data: stably normal (SN), stably impaired (SI), worsening (Wo), or improving (Im). All subjects underwent comprehensive NC testing, phlebotomy, and lumbar puncture at two timepoints separated by a median of 6.2 months. Eight biomarkers were measured in CSF and blood by immunoassay. Results were analyzed using mixed model linear regression and staged recursive partitioning. Results At the first visit, subjects were mostly middle-aged (median 45) white (58%) men (84%) who had AIDS (70%). Of the 73% who took antiretroviral therapy (ART), 54% had HIV RNA levels below 50 c/mL in plasma. Mixed model linear regression identified that only MCP-1 in CSF was associated with neurocognitive change group. Recursive partitioning models aimed at diagnosis (i.e., correctly classifying neurocognitive status at the first visit) were complex and required most biomarkers to achieve misclassification limits. In contrast, prognostic models were more efficient. A combination of three biomarkers (sCD14, MCP-1, SDF-1α) correctly classified 82% of Wo and SN subjects, including 88% of SN subjects. A combination of two biomarkers (MCP-1, TNF-α) correctly classified 81% of Im and SI subjects, including 100% of SI subjects. Conclusions This analysis of well-characterized individuals identified concise panels of biomarkers associated with NC change. Across all analyses, the two most frequently identified biomarkers were sCD14 and MCP-1, indicators of monocyte/macrophage activation. While the panels differed depending on the outcome and on the degree of misclassification, nearly all stable patients were correctly classified. PMID:24101401

A Random Forest-based ensemble method for activity recognition.

PubMed

Feng, Zengtao; Mo, Lingfei; Li, Meng

2015-01-01

This paper presents a multi-sensor ensemble approach to human physical activity (PA) recognition, using random forest. We designed an ensemble learning algorithm, which integrates several independent Random Forest classifiers based on different sensor feature sets to build a more stable, more accurate and faster classifier for human activity recognition. To evaluate the algorithm, PA data collected from the PAMAP (Physical Activity Monitoring for Aging People), which is a standard, publicly available database, was utilized to train and test. The experimental results show that the algorithm is able to correctly recognize 19 PA types with an accuracy of 93.44%, while the training is faster than others. The ensemble classifier system based on the RF (Random Forest) algorithm can achieve high recognition accuracy and fast calculation.

Comparison of four approaches to a rock facies classification problem

USGS Publications Warehouse

Dubois, M.K.; Bohling, Geoffrey C.; Chakrabarti, S.

2007-01-01

In this study, seven classifiers based on four different approaches were tested in a rock facies classification problem: classical parametric methods using Bayes' rule, and non-parametric methods using fuzzy logic, k-nearest neighbor, and feed forward-back propagating artificial neural network. Determining the most effective classifier for geologic facies prediction in wells without cores in the Panoma gas field, in Southwest Kansas, was the objective. Study data include 3600 samples with known rock facies class (from core) with each sample having either four or five measured properties (wire-line log curves), and two derived geologic properties (geologic constraining variables). The sample set was divided into two subsets, one for training and one for testing the ability of the trained classifier to correctly assign classes. Artificial neural networks clearly outperformed all other classifiers and are effective tools for this particular classification problem. Classical parametric models were inadequate due to the nature of the predictor variables (high dimensional and not linearly correlated), and feature space of the classes (overlapping). The other non-parametric methods tested, k-nearest neighbor and fuzzy logic, would need considerable improvement to match the neural network effectiveness, but further work, possibly combining certain aspects of the three non-parametric methods, may be justified. ?? 2006 Elsevier Ltd. All rights reserved.

Neurons from the adult human dentate nucleus: neural networks in the neuron classification.

PubMed

Grbatinić, Ivan; Marić, Dušica L; Milošević, Nebojša T

2015-04-07

Topological (central vs. border neuron type) and morphological classification of adult human dentate nucleus neurons according to their quantified histomorphological properties using neural networks on real and virtual neuron samples. In the real sample 53.1% and 14.1% of central and border neurons, respectively, are classified correctly with total of 32.8% of misclassified neurons. The most important result present 62.2% of misclassified neurons in border neurons group which is even greater than number of correctly classified neurons (37.8%) in that group, showing obvious failure of network to classify neurons correctly based on computational parameters used in our study. On the virtual sample 97.3% of misclassified neurons in border neurons group which is much greater than number of correctly classified neurons (2.7%) in that group, again confirms obvious failure of network to classify neurons correctly. Statistical analysis shows that there is no statistically significant difference in between central and border neurons for each measured parameter (p>0.05). Total of 96.74% neurons are morphologically classified correctly by neural networks and each one belongs to one of the four histomorphological types: (a) neurons with small soma and short dendrites, (b) neurons with small soma and long dendrites, (c) neuron with large soma and short dendrites, (d) neurons with large soma and long dendrites. Statistical analysis supports these results (p<0.05). Human dentate nucleus neurons can be classified in four neuron types according to their quantitative histomorphological properties. These neuron types consist of two neuron sets, small and large ones with respect to their perykarions with subtypes differing in dendrite length i.e. neurons with short vs. long dendrites. Besides confirmation of neuron classification on small and large ones, already shown in literature, we found two new subtypes i.e. neurons with small soma and long dendrites and with large soma and short dendrites. These neurons are most probably equally distributed throughout the dentate nucleus as no significant difference in their topological distribution is observed. Copyright © 2015 Elsevier Ltd. All rights reserved.

Improved motion correction in PROPELLER by using grouped blades as reference.

PubMed

Liu, Zhe; Zhang, Zhe; Ying, Kui; Yuan, Chun; Guo, Hua

2014-03-01

To develop a robust reference generation method for improving PROPELLER (Periodically Rotated Overlapping ParallEL Lines with Enhanced Reconstruction) reconstruction. A new reference generation method, grouped-blade reference (GBR), is proposed for calculating rotation angle and translation shift in PROPELLER. Instead of using a single-blade reference (SBR) or combined-blade reference (CBR), our method classifies blades by their relative correlations and groups similar blades together as the reference to prevent inconsistent data from interfering the correction process. Numerical simulations and in vivo experiments were used to evaluate the performance of GBR for PROPELLER, which was further compared with SBR and CBR in terms of error level and computation cost. Both simulation and in vivo experiments demonstrate that GBR-based PROPELLER provides better correction for random motion or bipolar motion comparing with SBR or CBR. It not only produces images with lower error level but also needs less iteration steps to converge. A grouped-blade for reference selection was investigated for PROPELLER MRI. It helps to improve the accuracy and robustness of motion correction for various motion patterns. Copyright © 2013 Wiley Periodicals, Inc.

A Signal Detection Theory Approach to Evaluating Oculometer Data Quality

NASA Technical Reports Server (NTRS)

Latorella, Kara; Lynn, William, III; Barry, John S.; Kelly, Lon; Shih, Ming-Yun

2013-01-01

Currently, data quality is described in terms of spatial and temporal accuracy and precision [Holmqvist et al. in press]. While this approach provides precise errors in pixels, or visual angle, often experiments are more concerned with whether subjects'points of gaze can be said to be reliable with respect to experimentally-relevant areas of interest. This paper proposes a method to characterize oculometer data quality using Signal Detection Theory (SDT) [Marcum 1947]. SDT classification results in four cases: Hit (correct report of a signal), Miss (failure to report a ), False Alarm (a signal falsely reported), Correct Reject (absence of a signal correctly reported). A technique is proposed where subjects' are directed to look at points in and outside of an AOI, and the resulting Points of Gaze (POG) are classified as Hits (points known to be internal to an AOI are classified as such), Misses (AOI points are not indicated as such), False Alarms (points external to AOIs are indicated as in the AOI), or Correct Rejects (points external to the AOI are indicated as such). SDT metrics describe performance in terms of discriminability, sensitivity, and specificity. This paper presentation will provide the procedure for conducting this assessment and an example of data collected for AOIs in a simulated flightdeck environment.

Accuracy of automated classification of major depressive disorder as a function of symptom severity.

PubMed

Ramasubbu, Rajamannar; Brown, Matthew R G; Cortese, Filmeno; Gaxiola, Ismael; Goodyear, Bradley; Greenshaw, Andrew J; Dursun, Serdar M; Greiner, Russell

2016-01-01

Growing evidence documents the potential of machine learning for developing brain based diagnostic methods for major depressive disorder (MDD). As symptom severity may influence brain activity, we investigated whether the severity of MDD affected the accuracies of machine learned MDD-vs-Control diagnostic classifiers. Forty-five medication-free patients with DSM-IV defined MDD and 19 healthy controls participated in the study. Based on depression severity as determined by the Hamilton Rating Scale for Depression (HRSD), MDD patients were sorted into three groups: mild to moderate depression (HRSD 14-19), severe depression (HRSD 20-23), and very severe depression (HRSD ≥ 24). We collected functional magnetic resonance imaging (fMRI) data during both resting-state and an emotional-face matching task. Patients in each of the three severity groups were compared against controls in separate analyses, using either the resting-state or task-based fMRI data. We use each of these six datasets with linear support vector machine (SVM) binary classifiers for identifying individuals as patients or controls. The resting-state fMRI data showed statistically significant classification accuracy only for the very severe depression group (accuracy 66%, p = 0.012 corrected), while mild to moderate (accuracy 58%, p = 1.0 corrected) and severe depression (accuracy 52%, p = 1.0 corrected) were only at chance. With task-based fMRI data, the automated classifier performed at chance in all three severity groups. Binary linear SVM classifiers achieved significant classification of very severe depression with resting-state fMRI, but the contribution of brain measurements may have limited potential in differentiating patients with less severe depression from healthy controls.

Cost-effectiveness of different strategies for diagnosis of uncomplicated urinary tract infections in women presenting in primary care.

PubMed

Bosmans, Judith E; Coupé, Veerle M H; Knottnerus, Bart J; Geerlings, Suzanne E; Moll van Charante, Eric P; Ter Riet, Gerben

2017-01-01

Uncomplicated Urinary Tract Infections (UTIs) are common in primary care resulting in substantial costs. Since antimicrobial resistance against antibiotics for UTIs is rising, accurate diagnosis is needed in settings with low rates of multidrug-resistant bacteria. To compare the cost-effectiveness of different strategies to diagnose UTIs in women who contacted their general practitioner (GP) with painful and/or frequent micturition between 2006 and 2008 in and around Amsterdam, The Netherlands. This is a model-based cost-effectiveness analysis using data from 196 women who underwent four tests: history, urine stick, sediment, dipslide, and the gold standard, a urine culture. Decision trees were constructed reflecting 15 diagnostic strategies comprising different parallel and sequential combinations of the four tests. Using the decision trees, for each strategy the costs and the proportion of women with a correct positive or negative diagnosis were estimated. Probabilistic sensitivity analysis was used to estimate uncertainty surrounding costs and effects. Uncertainty was presented using cost-effectiveness planes and acceptability curves. Most sequential testing strategies resulted in higher proportions of correctly classified women and lower costs than parallel testing strategies. For different willingness to pay thresholds, the most cost-effective strategies were: 1) performing a dipstick after a positive history for thresholds below €10 per additional correctly classified patient, 2) performing both a history and dipstick for thresholds between €10 and €17 per additional correctly classified patient, 3) performing a dipstick if history was negative, followed by a sediment if the dipstick was negative for thresholds between €17 and €118 per additional correctly classified patient, 4) performing a dipstick if history was negative, followed by a dipslide if the dipstick was negative for thresholds above €118 per additional correctly classified patient. Depending on decision makers' willingness to pay for one additional correctly classified woman, the strategy consisting of performing a history and dipstick simultaneously (ceiling ratios between €10 and €17) or performing a sediment if history and subsequent dipstick are negative (ceiling ratios between €17 and €118) are the most cost-effective strategies to diagnose a UTI.

Age and gender classification of Merriam's turkeys from foot measurements

Treesearch

Mark A. Rumble; Todd R. Mills; Brian F. Wakeling; Richard W. Hoffman

1996-01-01

Wild turkey sex and age information is needed to define population structure but is difficult to obtain. We classified age and gender of Merriam’s turkeys (Meleagris gallopavo merriami) accurately based on measurements of two foot characteristics. Gender of birds was correctly classified 93% of the time from measurements of middle toe pads; correct...

Predicting Rotator Cuff Tears Using Data Mining and Bayesian Likelihood Ratios

PubMed Central

Lu, Hsueh-Yi; Huang, Chen-Yuan; Su, Chwen-Tzeng; Lin, Chen-Chiang

2014-01-01

Objectives Rotator cuff tear is a common cause of shoulder diseases. Correct diagnosis of rotator cuff tears can save patients from further invasive, costly and painful tests. This study used predictive data mining and Bayesian theory to improve the accuracy of diagnosing rotator cuff tears by clinical examination alone. Methods In this retrospective study, 169 patients who had a preliminary diagnosis of rotator cuff tear on the basis of clinical evaluation followed by confirmatory MRI between 2007 and 2011 were identified. MRI was used as a reference standard to classify rotator cuff tears. The predictor variable was the clinical assessment results, which consisted of 16 attributes. This study employed 2 data mining methods (ANN and the decision tree) and a statistical method (logistic regression) to classify the rotator cuff diagnosis into “tear” and “no tear” groups. Likelihood ratio and Bayesian theory were applied to estimate the probability of rotator cuff tears based on the results of the prediction models. Results Our proposed data mining procedures outperformed the classic statistical method. The correction rate, sensitivity, specificity and area under the ROC curve of predicting a rotator cuff tear were statistical better in the ANN and decision tree models compared to logistic regression. Based on likelihood ratios derived from our prediction models, Fagan's nomogram could be constructed to assess the probability of a patient who has a rotator cuff tear using a pretest probability and a prediction result (tear or no tear). Conclusions Our predictive data mining models, combined with likelihood ratios and Bayesian theory, appear to be good tools to classify rotator cuff tears as well as determine the probability of the presence of the disease to enhance diagnostic decision making for rotator cuff tears. PMID:24733553

Artificial neural network EMG classifier for functional hand grasp movements prediction

PubMed Central

Ferrante, Simona; Ferrigno, Giancarlo; Baldassini, Davide; Molteni, Franco; Guanziroli, Eleonora; Cotti Cottini, Michele; Seneci, Carlo; Pedrocchi, Alessandra

2016-01-01

Objective To design and implement an electromyography (EMG)-based controller for a hand robotic assistive device, which is able to classify the user's motion intention before the effective kinematic movement execution. Methods Multiple degrees-of-freedom hand grasp movements (i.e. pinching, grasp an object, grasping) were predicted by means of surface EMG signals, recorded from 10 bipolar EMG electrodes arranged in a circular configuration around the forearm 2–3 cm from the elbow. Two cascaded artificial neural networks were then exploited to detect the patient's motion intention from the EMG signal window starting from the electrical activity onset to movement onset (i.e. electromechanical delay). Results The proposed approach was tested on eight healthy control subjects (4 females; age range 25–26 years) and it demonstrated a mean ± SD testing performance of 76% ± 14% for correctly predicting healthy users' motion intention. Two post-stroke patients tested the controller and obtained 79% and 100% of correctly classified movements under testing conditions. Conclusion A task-selection controller was developed to estimate the intended movement from the EMG measured during the electromechanical delay. PMID:27677300

Mutual Information Item Selection Method in Cognitive Diagnostic Computerized Adaptive Testing with Short Test Length

ERIC Educational Resources Information Center

Wang, Chun

2013-01-01

Cognitive diagnostic computerized adaptive testing (CD-CAT) purports to combine the strengths of both CAT and cognitive diagnosis. Cognitive diagnosis models aim at classifying examinees into the correct mastery profile group so as to pinpoint the strengths and weakness of each examinee whereas CAT algorithms choose items to determine those…

Use of Machine Learning to Identify Children with Autism and Their Motor Abnormalities

ERIC Educational Resources Information Center

Crippa, Alessandro; Salvatore, Christian; Perego, Paolo; Forti, Sara; Nobile, Maria; Molteni, Massimo; Castiglioni, Isabella

2015-01-01

In the present work, we have undertaken a proof-of-concept study to determine whether a simple upper-limb movement could be useful to accurately classify low-functioning children with autism spectrum disorder (ASD) aged 2-4. To answer this question, we developed a supervised machine-learning method to correctly discriminate 15 preschool children…

Urine flow cytometry can rule out urinary tract infection, but cannot identify bacterial morphologies correctly.

PubMed

Geerts, N; Jansz, A R; Boonen, K J M; Wijn, R P W F; Koldewijn, E L; Boer, A K; Scharnhorst, V

2015-08-25

The diagnosis of urinary tract infection (UTI) by urine culture is a time-consuming and costly procedure. Usage of a screening method, to identify negative samples, would therefore affect time-to-diagnosis and laboratory cost positively. Urine flow cytometers are able to identify particles in urine. Together with the introduction of a cut-off value, which determines if a urine sample is subsequently cultured or not, the number of cultures can be reduced, while maintaining a low level of false negatives and a high negative predictive value. Recently, Sysmex developed additional software for their urine flow cytometers. Besides measuring the number of bacteria present in urine, information is given on bacterial morphology, which may guide the physician in the choice of antibiotic. In this study, we evaluated this software update. The UF1000i classifies bacteria into two categories: 'rods' and 'cocci/mixed'. Compared to the actual morphology of the bacterial pathogen found, the 'rods' category scores reasonably well with 91% chance of classifying rod-shaped bacteria correctly. The 'cocci/mixed' category underperforms, with only 29% of spherical-shaped bacteria (cocci) classified as such. In its current version, the bacterial morphology software does not classify bacteria, according to their morphology, well enough to be of clinical use in this study population. Copyright © 2015 Elsevier B.V. All rights reserved.

[Discrimination of donkey meat by NIR and chemometrics].

PubMed

Niu, Xiao-Ying; Shao, Li-Min; Dong, Fang; Zhao, Zhi-Lei; Zhu, Yan

2014-10-01

Donkey meat samples (n = 167) from different parts of donkey body (neck, costalia, rump, and tendon), beef (n = 47), pork (n = 51) and mutton (n = 32) samples were used to establish near-infrared reflectance spectroscopy (NIR) classification models in the spectra range of 4,000~12,500 cm(-1). The accuracies of classification models constructed by Mahalanobis distances analysis, soft independent modeling of class analogy (SIMCA) and least squares-support vector machine (LS-SVM), respectively combined with pretreatment of Savitzky-Golay smooth (5, 15 and 25 points) and derivative (first and second), multiplicative scatter correction and standard normal variate, were compared. The optimal models for intact samples were obtained by Mahalanobis distances analysis with the first 11 principal components (PCs) from original spectra as inputs and by LS-SVM with the first 6 PCs as inputs, and correctly classified 100% of calibration set and 98. 96% of prediction set. For minced samples of 7 mm diameter the optimal result was attained by LS-SVM with the first 5 PCs from original spectra as inputs, which gained an accuracy of 100% for calibration and 97.53% for prediction. For minced diameter of 5 mm SIMCA model with the first 8 PCs from original spectra as inputs correctly classified 100% of calibration and prediction. And for minced diameter of 3 mm Mahalanobis distances analysis and SIMCA models both achieved 100% accuracy for calibration and prediction respectively with the first 7 and 9 PCs from original spectra as inputs. And in these models, donkey meat samples were all correctly classified with 100% either in calibration or prediction. The results show that it is feasible that NIR with chemometrics methods is used to discriminate donkey meat from the else meat.

A method of measuring and correcting tilt of anti - vibration wind turbines based on screening algorithm

NASA Astrophysics Data System (ADS)

Xiao, Zhongxiu

2018-04-01

A Method of Measuring and Correcting Tilt of Anti - vibration Wind Turbines Based on Screening Algorithm is proposed in this paper. First of all, we design a device which the core is the acceleration sensor ADXL203, the inclination is measured by installing it on the tower of the wind turbine as well as the engine room. Next using the Kalman filter algorithm to filter effectively by establishing a state space model for signal and noise. Then we use matlab for simulation. Considering the impact of the tower and nacelle vibration on the collected data, the original data and the filtering data are classified and stored by the Screening algorithm, then filter the filtering data to make the output data more accurate. Finally, we eliminate installation errors by using algorithm to achieve the tilt correction. The device based on this method has high precision, low cost and anti-vibration advantages. It has a wide range of application and promotion value.

Centralized automated quality assurance for large scale health care systems. A pilot method for some aspects of dental radiography.

PubMed

Benn, D K; Minden, N J; Pettigrew, J C; Shim, M

1994-08-01

President Clinton's Health Security Act proposes the formation of large scale health plans with improved quality assurance. Dental radiography consumes 4% ($1.2 billion in 1990) of total dental expenditure yet regular systematic office quality assurance is not performed. A pilot automated method is described for assessing density of exposed film and fogging of unexposed processed film. A workstation and camera were used to input intraoral radiographs. Test images were produced from a phantom jaw with increasing exposure times. Two radiologists subjectively classified the images as too light, acceptable, or too dark. A computer program automatically classified global grey level histograms from the test images as too light, acceptable, or too dark. The program correctly classified 95% of 88 clinical films. Optical density of unexposed film in the range 0.15 to 0.52 measured by computer was reliable to better than 0.01. Further work is needed to see if comprehensive centralized automated radiographic quality assurance systems with feedback to dentists are feasible, are able to improve quality, and are significantly cheaper than conventional clerical methods.

Differentiation of Candida albicans, Candida glabrata, and Candida krusei by FT-IR and chemometrics by CHROMagar™ Candida.

PubMed

Wohlmeister, Denise; Vianna, Débora Renz Barreto; Helfer, Virginia Etges; Calil, Luciane Noal; Buffon, Andréia; Fuentefria, Alexandre Meneghello; Corbellini, Valeriano Antonio; Pilger, Diogo André

2017-10-01

Pathogenic Candida species are detected in clinical infections. CHROMagar™ is a phenotypical method used to identify Candida species, although it has limitations, which indicates the need for more sensitive and specific techniques. Infrared Spectroscopy (FT-IR) is an analytical vibrational technique used to identify patterns of metabolic fingerprint of biological matrixes, particularly whole microbial cell systems as Candida sp. in association of classificatory chemometrics algorithms. On the other hand, Soft Independent Modeling by Class Analogy (SIMCA) is one of the typical algorithms still little employed in microbiological classification. This study demonstrates the applicability of the FT-IR-technique by specular reflectance associated with SIMCA to discriminate Candida species isolated from vaginal discharges and grown on CHROMagar™. The differences in spectra of C. albicans, C. glabrata and C. krusei were suitable for use in the discrimination of these species, which was observed by PCA. Then, a SIMCA model was constructed with standard samples of three species and using the spectral region of 1792-1561cm -1 . All samples (n=48) were properly classified based on the chromogenic method using CHROMagar™ Candida. In total, 93.4% (n=45) of the samples were correctly and unambiguously classified (Class I). Two samples of C. albicans were classified correctly, though these could have been C. glabrata (Class II). Also, one C. glabrata sample could have been classified as C. krusei (Class II). Concerning these three samples, one triplicate of each was included in Class II and two in Class I. Therefore, FT-IR associated with SIMCA can be used to identify samples of C. albicans, C. glabrata, and C. krusei grown in CHROMagar™ Candida aiming to improve clinical applications of this technique. Copyright © 2017 Elsevier B.V. All rights reserved.

Human Actions Analysis: Templates Generation, Matching and Visualization Applied to Motion Capture of Highly-Skilled Karate Athletes

PubMed Central

Piekarczyk, Marcin; Ogiela, Marek R.

2017-01-01

The aim of this paper is to propose and evaluate the novel method of template generation, matching, comparing and visualization applied to motion capture (kinematic) analysis. To evaluate our approach, we have used motion capture recordings (MoCap) of two highly-skilled black belt karate athletes consisting of 560 recordings of various karate techniques acquired with wearable sensors. We have evaluated the quality of generated templates; we have validated the matching algorithm that calculates similarities and differences between various MoCap data; and we have examined visualizations of important differences and similarities between MoCap data. We have concluded that our algorithms works the best when we are dealing with relatively short (2–4 s) actions that might be averaged and aligned with the dynamic time warping framework. In practice, the methodology is designed to optimize the performance of some full body techniques performed in various sport disciplines, for example combat sports and martial arts. We can also use this approach to generate templates or to compare the correct performance of techniques between various top sportsmen in order to generate a knowledge base of reference MoCap videos. The motion template generated by our method can be used for action recognition purposes. We have used the DTW classifier with angle-based features to classify various karate kicks. We have performed leave-one-out action recognition for the Shorin-ryu and Oyama karate master separately. In this case, 100% actions were correctly classified. In another experiment, we used templates generated from Oyama master recordings to classify Shorin-ryu master recordings and vice versa. In this experiment, the overall recognition rate was 94.2%, which is a very good result for this type of complex action. PMID:29125560

Laboratory techniques for human embryos.

PubMed

Geber, Selmo; Sales, Liana; Sampaio, Marcos A C

2002-01-01

This review is concerned with laboratory techniques needed for assisted conception, particularly the handling of gametes and embryos. Such methods are being increasingly refined. Successive stages of fertilization and embryogenesis require especial care, and often involve the use of micromanipulative methods for intracytoplasmic sperm injection (ICSI) or preimplantation genetic diagnosis. Embryologists must take responsibility for gamete collection and preparation, and for deciding on the means of insemination or ICSI. Embryos must be assessed in culture, during the 1-cell, cleaving and morula/blastocyst stages, and classified according to quality. Co-culture methods may be necessary. The best embryos for transfer must be selected and loaded into the transfer catheter. Embryos not transferred must be cryopreserved, which demands the correct application of current methods of media preparation, seeding and the correct speed for cooling and warming. Before too long, methods of detecting abnormal embryos and avoiding their transfer may become widespread.

Gustaf: Detecting and correctly classifying SVs in the NGS twilight zone.

PubMed

Trappe, Kathrin; Emde, Anne-Katrin; Ehrlich, Hans-Christian; Reinert, Knut

2014-12-15

The landscape of structural variation (SV) including complex duplication and translocation patterns is far from resolved. SV detection tools usually exhibit low agreement, are often geared toward certain types or size ranges of variation and struggle to correctly classify the type and exact size of SVs. We present Gustaf (Generic mUlti-SpliT Alignment Finder), a sound generic multi-split SV detection tool that detects and classifies deletions, inversions, dispersed duplications and translocations of ≥ 30 bp. Our approach is based on a generic multi-split alignment strategy that can identify SV breakpoints with base pair resolution. We show that Gustaf correctly identifies SVs, especially in the range from 30 to 100 bp, which we call the next-generation sequencing (NGS) twilight zone of SVs, as well as larger SVs >500 bp. Gustaf performs better than similar tools in our benchmark and is furthermore able to correctly identify size and location of dispersed duplications and translocations, which otherwise might be wrongly classified, for example, as large deletions. © The Author 2014. Published by Oxford University Press. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Automated anatomical labeling of bronchial branches using multiple classifiers and its application to bronchoscopy guidance based on fusion of virtual and real bronchoscopy

NASA Astrophysics Data System (ADS)

Ota, Shunsuke; Deguchi, Daisuke; Kitasaka, Takayuki; Mori, Kensaku; Suenaga, Yasuhito; Hasegawa, Yoshinori; Imaizumi, Kazuyoshi; Takabatake, Hirotsugu; Mori, Masaki; Natori, Hiroshi

2008-03-01

This paper presents a method for automated anatomical labeling of bronchial branches (ALBB) extracted from 3D CT datasets. The proposed method constructs classifiers that output anatomical names of bronchial branches by employing the machine-learning approach. We also present its application to a bronchoscopy guidance system. Since the bronchus has a complex tree structure, bronchoscopists easily tend to get disoriented and lose the way to a target location. A bronchoscopy guidance system is strongly expected to be developed to assist bronchoscopists. In such guidance system, automated presentation of anatomical names is quite useful information for bronchoscopy. Although several methods for automated ALBB were reported, most of them constructed models taking only variations of branching patterns into account and did not consider those of running directions. Since the running directions of bronchial branches differ greatly in individuals, they could not perform ALBB accurately when running directions of bronchial branches were different from those of models. Our method tries to solve such problems by utilizing the machine-learning approach. Actual procedure consists of three steps: (a) extraction of bronchial tree structures from 3D CT datasets, (b) construction of classifiers using the multi-class AdaBoost technique, and (c) automated classification of bronchial branches by using the constructed classifiers. We applied the proposed method to 51 cases of 3D CT datasets. The constructed classifiers were evaluated by leave-one-out scheme. The experimental results showed that the proposed method could assign correct anatomical names to bronchial branches of 89.1% up to segmental lobe branches. Also, we confirmed that it was quite useful to assist the bronchoscopy by presenting anatomical names of bronchial branches on real bronchoscopic views.

Investigations in adaptive processing of multispectral data

NASA Technical Reports Server (NTRS)

Kriegler, F. J.; Horwitz, H. M.

1973-01-01

Adaptive data processing procedures are applied to the problem of classifying objects in a scene scanned by multispectral sensor. These procedures show a performance improvement over standard nonadaptive techniques. Some sources of error in classification are identified and those correctable by adaptive processing are discussed. Experiments in adaptation of signature means by decision-directed methods are described. Some of these methods assume correlation between the trajectories of different signature means; for others this assumption is not made.

Establishing glucose- and ABA-regulated transcription networks in Arabidopsis by microarray analysis and promoter classification using a Relevance Vector Machine.

PubMed

Li, Yunhai; Lee, Kee Khoon; Walsh, Sean; Smith, Caroline; Hadingham, Sophie; Sorefan, Karim; Cawley, Gavin; Bevan, Michael W

2006-03-01

Establishing transcriptional regulatory networks by analysis of gene expression data and promoter sequences shows great promise. We developed a novel promoter classification method using a Relevance Vector Machine (RVM) and Bayesian statistical principles to identify discriminatory features in the promoter sequences of genes that can correctly classify transcriptional responses. The method was applied to microarray data obtained from Arabidopsis seedlings treated with glucose or abscisic acid (ABA). Of those genes showing >2.5-fold changes in expression level, approximately 70% were correctly predicted as being up- or down-regulated (under 10-fold cross-validation), based on the presence or absence of a small set of discriminative promoter motifs. Many of these motifs have known regulatory functions in sugar- and ABA-mediated gene expression. One promoter motif that was not known to be involved in glucose-responsive gene expression was identified as the strongest classifier of glucose-up-regulated gene expression. We show it confers glucose-responsive gene expression in conjunction with another promoter motif, thus validating the classification method. We were able to establish a detailed model of glucose and ABA transcriptional regulatory networks and their interactions, which will help us to understand the mechanisms linking metabolism with growth in Arabidopsis. This study shows that machine learning strategies coupled to Bayesian statistical methods hold significant promise for identifying functionally significant promoter sequences.

Customized versus population-based growth curves: prediction of low body fat percent at term corrected gestational age following preterm birth.

PubMed

Law, Tameeka L; Katikaneni, Lakshmi D; Taylor, Sarah N; Korte, Jeffrey E; Ebeling, Myla D; Wagner, Carol L; Newman, Roger B

2012-07-01

Compare customized versus population-based growth curves for identification of small-for-gestational-age (SGA) and body fat percent (BF%) among preterm infants. Prospective cohort study of 204 preterm infants classified as SGA or appropriate-for-gestational-age (AGA) by population-based and customized growth curves. BF% was determined by air-displacement plethysmography. Differences between groups were compared using bivariable and multivariable linear and logistic regression analyses. Customized curves reclassified 30% of the preterm infants as SGA. SGA infants identified by customized method only had significantly lower BF% (13.8 ± 6.0) than the AGA (16.2 ± 6.3, p = 0.02) infants and similar to the SGA infants classified by both methods (14.6 ± 6.7, p = 0.51). Customized growth curves were a significant predictor of BF% (p = 0.02), whereas population-based growth curves were not a significant independent predictor of BF% (p = 0.50) at term corrected gestational age. Customized growth potential improves the differentiation of SGA infants and low BF% compared with a standard population-based growth curve among a cohort of preterm infants.

Classification of the Correct Quranic Letters Pronunciation of Male and Female Reciters

NASA Astrophysics Data System (ADS)

Khairuddin, Safiah; Ahmad, Salmiah; Embong, Abdul Halim; Nur Wahidah Nik Hashim, Nik; Altamas, Tareq M. K.; Nuratikah Syd Badaruddin, Syarifah; Shahbudin Hassan, Surul

2017-11-01

Recitation of the Holy Quran with the correct Tajweed is essential for every Muslim. Islam has encouraged Quranic education since early age as the recitation of the Quran correctly will represent the correct meaning of the words of Allah. It is important to recite the Quranic verses according to its characteristics (sifaat) and from its point of articulations (makhraj). This paper presents the identification and classification analysis of Quranic letters pronunciation for both male and female reciters, to obtain the unique representation of each letter by male as compared to female expert reciters. Linear Discriminant Analysis (LDA) was used as the classifier to classify the data with Formants and Power Spectral Density (PSD) as the acoustic features. The result shows that linear classifier of PSD with band 1 and band 2 power spectral combinations gives a high percentage of classification accuracy for most of the Quranic letters. It is also shown that the pronunciation by male reciters gives better result in the classification of the Quranic letters.

Meat mixture detection in Iberian pork sausages.

PubMed

Ortiz-Somovilla, V; España-España, F; De Pedro-Sanz, E J; Gaitán-Jurado, A J

2005-11-01

Five homogenized meat mixture treatments of Iberian (I) and/or Standard (S) pork were set up. Each treatment was analyzed by NIRS as a fresh product (N=75) and as dry-cured sausage (N=75). Spectra acquisition was carried out using DA 7000 equipment (Perten Instruments), obtaining a total of 750 spectra. Several absorption peaks and bands were selected as the most representative for homogenized dry-cured and fresh sausages. Discriminant analysis and mixture prediction equations were carried out based on the spectral data gathered. The best results using discriminant models were for fresh products, with 98.3% (calibration) and 60% (validation) correct classification. For dry-cured sausages 91.7% (calibration) and 80% (validation) of the samples were correctly classified. Models developed using mixture prediction equations showed SECV=4.7, r(2)=0.98 (calibration) and 73.3% of validation set were correctly classified for the fresh product. These values for dry-cured sausages were SECV=5.9, r(2)=0.99 (calibration) and 93.3% correctly classified for validation.

SVM based colon polyps classifier in a wireless active stereo endoscope.

PubMed

Ayoub, J; Granado, B; Mhanna, Y; Romain, O

2010-01-01

This work focuses on the recognition of three-dimensional colon polyps captured by an active stereo vision sensor. The detection algorithm consists of SVM classifier trained on robust feature descriptors. The study is related to Cyclope, this prototype sensor allows real time 3D object reconstruction and continues to be optimized technically to improve its classification task by differentiation between hyperplastic and adenomatous polyps. Experimental results were encouraging and show correct classification rate of approximately 97%. The work contains detailed statistics about the detection rate and the computing complexity. Inspired by intensity histogram, the work shows a new approach that extracts a set of features based on depth histogram and combines stereo measurement with SVM classifiers to correctly classify benign and malignant polyps.

Wide-field spectral imaging of human ovary autofluorescence and oncologic diagnosis via previously collected probe data

NASA Astrophysics Data System (ADS)

Renkoski, Timothy E.; Hatch, Kenneth D.; Utzinger, Urs

2012-03-01

With no sufficient screening test for ovarian cancer, a method to evaluate the ovarian disease state quickly and nondestructively is needed. The authors have applied a wide-field spectral imager to freshly resected ovaries of 30 human patients in a study believed to be the first of its magnitude. Endogenous fluorescence was excited with 365-nm light and imaged in eight emission bands collectively covering the 400- to 640-nm range. Linear discriminant analysis was used to classify all image pixels and generate diagnostic maps of the ovaries. Training the classifier with previously collected single-point autofluorescence measurements of a spectroscopic probe enabled this novel classification. The process by which probe-collected spectra were transformed for comparison with imager spectra is described. Sensitivity of 100% and specificity of 51% were obtained in classifying normal and cancerous ovaries using autofluorescence data alone. Specificity increased to 69% when autofluorescence data were divided by green reflectance data to correct for spatial variation in tissue absorption properties. Benign neoplasm ovaries were also found to classify as nonmalignant using the same algorithm. Although applied ex vivo, the method described here appears useful for quick assessment of cancer presence in the human ovary.

Multiclass Classification of Cardiac Arrhythmia Using Improved Feature Selection and SVM Invariants.

PubMed

Mustaqeem, Anam; Anwar, Syed Muhammad; Majid, Muahammad

2018-01-01

Arrhythmia is considered a life-threatening disease causing serious health issues in patients, when left untreated. An early diagnosis of arrhythmias would be helpful in saving lives. This study is conducted to classify patients into one of the sixteen subclasses, among which one class represents absence of disease and the other fifteen classes represent electrocardiogram records of various subtypes of arrhythmias. The research is carried out on the dataset taken from the University of California at Irvine Machine Learning Data Repository. The dataset contains a large volume of feature dimensions which are reduced using wrapper based feature selection technique. For multiclass classification, support vector machine (SVM) based approaches including one-against-one (OAO), one-against-all (OAA), and error-correction code (ECC) are employed to detect the presence and absence of arrhythmias. The SVM method results are compared with other standard machine learning classifiers using varying parameters and the performance of the classifiers is evaluated using accuracy, kappa statistics, and root mean square error. The results show that OAO method of SVM outperforms all other classifiers by achieving an accuracy rate of 81.11% when used with 80/20 data split and 92.07% using 90/10 data split option.

Realistic Subsurface Anomaly Discrimination Using Electromagnetic Induction and an SVM Classifier

NASA Astrophysics Data System (ADS)

Pablo Fernández, Juan; Shubitidze, Fridon; Shamatava, Irma; Barrowes, Benjamin E.; O'Neill, Kevin

2010-12-01

The environmental research program of the United States military has set up blind tests for detection and discrimination of unexploded ordnance. One such test consists of measurements taken with the EM-63 sensor at Camp Sibert, AL. We review the performance on the test of a procedure that combines a field-potential (HAP) method to locate targets, the normalized surface magnetic source (NSMS) model to characterize them, and a support vector machine (SVM) to classify them. The HAP method infers location from the scattered magnetic field and its associated scalar potential, the latter reconstructed using equivalent sources. NSMS replaces the target with an enclosing spheroid of equivalent radial magnetization whose integral it uses as a discriminator. SVM generalizes from empirical evidence and can be adapted for multiclass discrimination using a voting system. Our method identifies all potentially dangerous targets correctly and has a false-alarm rate of about 5%.

Classification of 'Chemlali' accessions according to the geographical area using chemometric methods of phenolic profiles analysed by HPLC-ESI-TOF-MS.

PubMed

Taamalli, Amani; Arráez Román, David; Zarrouk, Mokhtar; Segura-Carretero, Antonio; Fernández-Gutiérrez, Alberto

2012-05-01

The present work describes a classification method of Tunisian 'Chemlali' olive oils based on their phenolic composition and geographical area. For this purpose, the data obtained by HPLC-ESI-TOF-MS from 13 samples of extra virgin olive oils, obtained from different production area throughout the country, were used for this study focusing in 23 phenolics compounds detected. The quantitative results showed a significant variability among the analysed oil samples. Factor analysis method using principal component was applied to the data in order to reduce the number of factors which explain the variability of the selected compounds. The data matrix constructed was subjected to a canonical discriminant analysis (CDA) in order to classify the oil samples. These results showed that 100% of cross-validated original group cases were correctly classified, which proves the usefulness of the selected variables. Copyright © 2011 Elsevier Ltd. All rights reserved.

Classifying with confidence from incomplete information.

DOE PAGES

Parrish, Nathan; Anderson, Hyrum S.; Gupta, Maya R.; ...

2013-12-01

For this paper, we consider the problem of classifying a test sample given incomplete information. This problem arises naturally when data about a test sample is collected over time, or when costs must be incurred to compute the classification features. For example, in a distributed sensor network only a fraction of the sensors may have reported measurements at a certain time, and additional time, power, and bandwidth is needed to collect the complete data to classify. A practical goal is to assign a class label as soon as enough data is available to make a good decision. We formalize thismore » goal through the notion of reliability—the probability that a label assigned given incomplete data would be the same as the label assigned given the complete data, and we propose a method to classify incomplete data only if some reliability threshold is met. Our approach models the complete data as a random variable whose distribution is dependent on the current incomplete data and the (complete) training data. The method differs from standard imputation strategies in that our focus is on determining the reliability of the classification decision, rather than just the class label. We show that the method provides useful reliability estimates of the correctness of the imputed class labels on a set of experiments on time-series data sets, where the goal is to classify the time-series as early as possible while still guaranteeing that the reliability threshold is met.« less

Remote sensing change detection methods to track deforestation and growth in threatened rainforests in Madre de Dios, Peru

USGS Publications Warehouse

Shermeyer, Jacob S.; Haack, Barry N.

2015-01-01

Two forestry-change detection methods are described, compared, and contrasted for estimating deforestation and growth in threatened forests in southern Peru from 2000 to 2010. The methods used in this study rely on freely available data, including atmospherically corrected Landsat 5 Thematic Mapper and Moderate Resolution Imaging Spectroradiometer (MODIS) vegetation continuous fields (VCF). The two methods include a conventional supervised signature extraction method and a unique self-calibrating method called MODIS VCF guided forest/nonforest (FNF) masking. The process chain for each of these methods includes a threshold classification of MODIS VCF, training data or signature extraction, signature evaluation, k-nearest neighbor classification, analyst-guided reclassification, and postclassification image differencing to generate forest change maps. Comparisons of all methods were based on an accuracy assessment using 500 validation pixels. Results of this accuracy assessment indicate that FNF masking had a 5% higher overall accuracy and was superior to conventional supervised classification when estimating forest change. Both methods succeeded in classifying persistently forested and nonforested areas, and both had limitations when classifying forest change.

Effective classification of the prevalence of Schistosoma mansoni.

PubMed

Mitchell, Shira A; Pagano, Marcello

2012-12-01

To present an effective classification method based on the prevalence of Schistosoma mansoni in the community. We created decision rules (defined by cut-offs for number of positive slides), which account for imperfect sensitivity, both with a simple adjustment of fixed sensitivity and with a more complex adjustment of changing sensitivity with prevalence. To reduce screening costs while maintaining accuracy, we propose a pooled classification method. To estimate sensitivity, we use the De Vlas model for worm and egg distributions. We compare the proposed method with the standard method to investigate differences in efficiency, measured by number of slides read, and accuracy, measured by probability of correct classification. Modelling varying sensitivity lowers the lower cut-off more significantly than the upper cut-off, correctly classifying regions as moderate rather than lower, thus receiving life-saving treatment. The classification method goes directly to classification on the basis of positive pools, avoiding having to know sensitivity to estimate prevalence. For model parameter values describing worm and egg distributions among children, the pooled method with 25 slides achieves an expected 89.9% probability of correct classification, whereas the standard method with 50 slides achieves 88.7%. Among children, it is more efficient and more accurate to use the pooled method for classification of S. mansoni prevalence than the current standard method. © 2012 Blackwell Publishing Ltd.

Pavement type and wear condition classification from tire cavity acoustic measurements with artificial neural networks.

PubMed

Masino, Johannes; Foitzik, Michael-Jan; Frey, Michael; Gauterin, Frank

2017-06-01

Tire road noise is the major contributor to traffic noise, which leads to general annoyance, speech interference, and sleep disturbances. Standardized methods to measure tire road noise are expensive, sophisticated to use, and they cannot be applied comprehensively. This paper presents a method to automatically classify different types of pavement and the wear condition to identify noisy road surfaces. The methods are based on spectra of time series data of the tire cavity sound, acquired under normal vehicle operation. The classifier, an artificial neural network, correctly predicts three pavement types, whereas there are few bidirectional mis-classifications for two pavements, which have similar physical characteristics. The performance measures of the classifier to predict a new or worn out condition are over 94.6%. One could create a digital map with the output of the presented method. On the basis of these digital maps, road segments with a strong impact on tire road noise could be automatically identified. Furthermore, the method can estimate the road macro-texture, which has an impact on the tire road friction especially on wet conditions. Overall, this digital map would have a great benefit for civil engineering departments, road infrastructure operators, and for advanced driver assistance systems.

Probabilistic atlas-based segmentation of combined T1-weighted and DUTE MRI for calculation of head attenuation maps in integrated PET/MRI scanners.

PubMed

Poynton, Clare B; Chen, Kevin T; Chonde, Daniel B; Izquierdo-Garcia, David; Gollub, Randy L; Gerstner, Elizabeth R; Batchelor, Tracy T; Catana, Ciprian

2014-01-01

We present a new MRI-based attenuation correction (AC) approach for integrated PET/MRI systems that combines both segmentation- and atlas-based methods by incorporating dual-echo ultra-short echo-time (DUTE) and T1-weighted (T1w) MRI data and a probabilistic atlas. Segmented atlases were constructed from CT training data using a leave-one-out framework and combined with T1w, DUTE, and CT data to train a classifier that computes the probability of air/soft tissue/bone at each voxel. This classifier was applied to segment the MRI of the subject of interest and attenuation maps (μ-maps) were generated by assigning specific linear attenuation coefficients (LACs) to each tissue class. The μ-maps generated with this "Atlas-T1w-DUTE" approach were compared to those obtained from DUTE data using a previously proposed method. For validation of the segmentation results, segmented CT μ-maps were considered to the "silver standard"; the segmentation accuracy was assessed qualitatively and quantitatively through calculation of the Dice similarity coefficient (DSC). Relative change (RC) maps between the CT and MRI-based attenuation corrected PET volumes were also calculated for a global voxel-wise assessment of the reconstruction results. The μ-maps obtained using the Atlas-T1w-DUTE classifier agreed well with those derived from CT; the mean DSCs for the Atlas-T1w-DUTE-based μ-maps across all subjects were higher than those for DUTE-based μ-maps; the atlas-based μ-maps also showed a lower percentage of misclassified voxels across all subjects. RC maps from the atlas-based technique also demonstrated improvement in the PET data compared to the DUTE method, both globally as well as regionally.

The expected results method for data verification

NASA Astrophysics Data System (ADS)

Monday, Paul

2016-05-01

The credibility of United States Army analytical experiments using distributed simulation depends on the quality of the simulation, the pedigree of the input data, and the appropriateness of the simulation system to the problem. The second of these factors is best met by using classified performance data from the Army Materiel Systems Analysis Activity (AMSAA) for essential battlefield behaviors, like sensors, weapon fire, and damage assessment. Until recently, using classified data has been a time-consuming and expensive endeavor: it requires significant technical expertise to load, and it is difficult to verify that it works correctly. Fortunately, new capabilities, tools, and processes are available that greatly reduce these costs. This paper will discuss these developments, a new method to verify that all of the components are configured and operate properly, and the application to recent Army Capabilities Integration Center (ARCIC) experiments. Recent developments have focused improving the process to load the data. OneSAF has redesigned their input data file formats and structures so that they correspond exactly with the Standard File Format (SFF) defined by AMSAA, ARCIC developed a library of supporting configurations that correlate directly to the AMSAA nomenclature, and the Entity Validation Tool was designed to quickly execute the essential models with a test-jig approach to identify problems with the loaded data. The missing part of the process is provided by the new Expected Results Method. Instead of the usual subjective assessment of quality, e.g., "It looks about right to me", this new approach compares the performance of a combat model with authoritative expectations to quickly verify that the model, data, and simulation are all working correctly. Integrated together, these developments now make it possible to use AMSAA classified performance data with minimal time and maximum assurance that the experiment's analytical results will be of the highest quality possible.

Comprehensive combinatory standard correction: a calibration method for handling instrumental drifts of gas chromatography-mass spectrometry systems.

PubMed

Deport, Coralie; Ratel, Jérémy; Berdagué, Jean-Louis; Engel, Erwan

2006-05-26

The current work describes a new method, the comprehensive combinatory standard correction (CCSC), for the correction of instrumental signal drifts in GC-MS systems. The method consists in analyzing together with the products of interest a mixture of n selected internal standards, and in normalizing the peak area of each analyte by the sum of standard areas and then, select among the summation operator sigma(p = 1)(n)C(n)p possible sums, the sum that enables the best product discrimination. The CCSC method was compared with classical techniques of data pre-processing like internal normalization (IN) or single standard correction (SSC) on their ability to correct raw data from the main drifts occurring in a dynamic headspace-gas chromatography-mass spectrometry system. Three edible oils with closely similar compositions in volatile compounds were analysed using a device which performance was modulated by using new or used dynamic headspace traps and GC-columns, and by modifying the tuning of the mass spectrometer. According to one-way ANOVA, the CCSC method increased the number of analytes discriminating the products (31 after CCSC versus 25 with raw data or after IN and 26 after SSC). Moreover, CCSC enabled a satisfactory discrimination of the products irrespective of the drifts. In a factorial discriminant analysis, 100% of the samples (n = 121) were well-classified after CCSC versus 45% for raw data, 90 and 93%, respectively after IN and SSC.

A neural network for the identification of measured helicopter noise

NASA Technical Reports Server (NTRS)

Cabell, R. H.; Fuller, C. R.; O'Brien, W. F.

1991-01-01

The results of a preliminary study of the components of a novel acoustic helicopter identification system are described. The identification system uses the relationship between the amplitudes of the first eight harmonics in the main rotor noise spectrum to distinguish between helicopter types. Two classification algorithms are tested; a statistically optimal Bayes classifier, and a neural network adaptive classifier. The performance of these classifiers is tested using measured noise of three helicopters. The statistical classifier can correctly identify the helicopter an average of 67 percent of the time, while the neural network is correct an average of 65 percent of the time. These results indicate the need for additional study of the envelope of harmonic amplitudes as a component of a helicopter identification system. Issues concerning the implementation of the neural network classifier, such as training time and structure of the network, are discussed.

Improved Correction of Atmospheric Pressure Data Obtained by Smartphones through Machine Learning

PubMed Central

Kim, Yong-Hyuk; Ha, Ji-Hun; Kim, Na-Young; Im, Hyo-Hyuc; Sim, Sangjin; Choi, Reno K. Y.

2016-01-01

A correction method using machine learning aims to improve the conventional linear regression (LR) based method for correction of atmospheric pressure data obtained by smartphones. The method proposed in this study conducts clustering and regression analysis with time domain classification. Data obtained in Gyeonggi-do, one of the most populous provinces in South Korea surrounding Seoul with the size of 10,000 km2, from July 2014 through December 2014, using smartphones were classified with respect to time of day (daytime or nighttime) as well as day of the week (weekday or weekend) and the user's mobility, prior to the expectation-maximization (EM) clustering. Subsequently, the results were analyzed for comparison by applying machine learning methods such as multilayer perceptron (MLP) and support vector regression (SVR). The results showed a mean absolute error (MAE) 26% lower on average when regression analysis was performed through EM clustering compared to that obtained without EM clustering. For machine learning methods, the MAE for SVR was around 31% lower for LR and about 19% lower for MLP. It is concluded that pressure data from smartphones are as good as the ones from national automatic weather station (AWS) network. PMID:27524999

Development, validity and reproducibility of a food frequency questionnaire in pregnancy for the Universiti Sains Malaysia birth cohort study.

PubMed

Loy, S L; Marhazlina, M; Nor, Azwany Y; Hamid, Jan J M

2011-04-01

This study aimed to develop and examine the validity and reproducibility of a semi-quantitative food frequency questionnaire (FFQ) among Malay pregnant women in Kelantan, Malaysia. A total of 177 Malay pregnant women participated in the validation study while 85 of them participated in the reproducibility study which was carried out in the antenatal clinic of Universiti Sains Malaysia Hospital. The newly developed FFQ was validated against two 24-hour dietary recalls (DR). The FFQ was repeated 20 to 28 days apart. Results showed that the FFQ moderately over-estimated the nutrient and food intakes compared to the DR. Spearman correlation coefficients for nutrients ranged from 0.24 (fat) to 0.61 (calcium) and for foods, ranged from 0.13 (organ meats, onion and garlic) to 0.57 (malt drink). For nutrients, 72 to 85% of women were classified into the correct quartiles from the FFQ and the DR while for foods, 67 to 85% of women were classified correctly. Bland-Altman plot showed relatively good agreement between these two dietary methods. The intra-class correlation (ICC) was used to estimate reproducibility. It ranged from 0.75 (vitamin C) to 0.94 (phosphorus) for nutrients while it ranged from 0.73 (confectionary) to 0.96 (coffee) for foods. On average, at least 90% of pregnant women were correctly classified into the quartiles for nutrients and foods from the two sets of the FFQ. The FFQ presented acceptable reproducibility and appears to be a valid tool for categorising pregnant women according to dietary intake.

Accurate determination of imaging modality using an ensemble of text- and image-based classifiers.

PubMed

Kahn, Charles E; Kalpathy-Cramer, Jayashree; Lam, Cesar A; Eldredge, Christina E

2012-02-01

Imaging modality can aid retrieval of medical images for clinical practice, research, and education. We evaluated whether an ensemble classifier could outperform its constituent individual classifiers in determining the modality of figures from radiology journals. Seventeen automated classifiers analyzed 77,495 images from two radiology journals. Each classifier assigned one of eight imaging modalities--computed tomography, graphic, magnetic resonance imaging, nuclear medicine, positron emission tomography, photograph, ultrasound, or radiograph-to each image based on visual and/or textual information. Three physicians determined the modality of 5,000 randomly selected images as a reference standard. A "Simple Vote" ensemble classifier assigned each image to the modality that received the greatest number of individual classifiers' votes. A "Weighted Vote" classifier weighted each individual classifier's vote based on performance over a training set. For each image, this classifier's output was the imaging modality that received the greatest weighted vote score. We measured precision, recall, and F score (the harmonic mean of precision and recall) for each classifier. Individual classifiers' F scores ranged from 0.184 to 0.892. The simple vote and weighted vote classifiers correctly assigned 4,565 images (F score, 0.913; 95% confidence interval, 0.905-0.921) and 4,672 images (F score, 0.934; 95% confidence interval, 0.927-0.941), respectively. The weighted vote classifier performed significantly better than all individual classifiers. An ensemble classifier correctly determined the imaging modality of 93% of figures in our sample. The imaging modality of figures published in radiology journals can be determined with high accuracy, which will improve systems for image retrieval.

A cardiorespiratory classifier of voluntary and involuntary electrodermal activity

PubMed Central

2010-01-01

Background Electrodermal reactions (EDRs) can be attributed to many origins, including spontaneous fluctuations of electrodermal activity (EDA) and stimuli such as deep inspirations, voluntary mental activity and startling events. In fields that use EDA as a measure of psychophysiological state, the fact that EDRs may be elicited from many different stimuli is often ignored. This study attempts to classify observed EDRs as voluntary (i.e., generated from intentional respiratory or mental activity) or involuntary (i.e., generated from startling events or spontaneous electrodermal fluctuations). Methods Eight able-bodied participants were subjected to conditions that would cause a change in EDA: music imagery, startling noises, and deep inspirations. A user-centered cardiorespiratory classifier consisting of 1) an EDR detector, 2) a respiratory filter and 3) a cardiorespiratory filter was developed to automatically detect a participant's EDRs and to classify the origin of their stimulation as voluntary or involuntary. Results Detected EDRs were classified with a positive predictive value of 78%, a negative predictive value of 81% and an overall accuracy of 78%. Without the classifier, EDRs could only be correctly attributed as voluntary or involuntary with an accuracy of 50%. Conclusions The proposed classifier may enable investigators to form more accurate interpretations of electrodermal activity as a measure of an individual's psychophysiological state. PMID:20184746

Pattern classifier for health monitoring of helicopter gearboxes

NASA Technical Reports Server (NTRS)

Chin, Hsinyung; Danai, Kourosh; Lewicki, David G.

1993-01-01

The application of a newly developed diagnostic method to a helicopter gearbox is demonstrated. This method is a pattern classifier which uses a multi-valued influence matrix (MVIM) as its diagnostic model. The method benefits from a fast learning algorithm, based on error feedback, that enables it to estimate gearbox health from a small set of measurement-fault data. The MVIM method can also assess the diagnosability of the system and variability of the fault signatures as the basis to improve fault signatures. This method was tested on vibration signals reflecting various faults in an OH-58A main rotor transmission gearbox. The vibration signals were then digitized and processed by a vibration signal analyzer to enhance and extract various features of the vibration data. The parameters obtained from this analyzer were utilized to train and test the performance of the MVIM method in both detection and diagnosis. The results indicate that the MVIM method provided excellent detection results when the full range of faults effects on the measurements were included in training, and it had a correct diagnostic rate of 95 percent when the faults were included in training.

Method of Menu Selection by Gaze Movement Using AC EOG Signals

NASA Astrophysics Data System (ADS)

Kanoh, Shin'ichiro; Futami, Ryoko; Yoshinobu, Tatsuo; Hoshimiya, Nozomu

A method to detect the direction and the distance of voluntary eye gaze movement from EOG (electrooculogram) signals was proposed and tested. In this method, AC-amplified vertical and horizontal transient EOG signals were classified into 8-class directions and 2-class distances of voluntary eye gaze movements. A horizontal and a vertical EOGs during eye gaze movement at each sampling time were treated as a two-dimensional vector, and the center of gravity of the sample vectors whose norms were more than 80% of the maximum norm was used as a feature vector to be classified. By the classification using the k-nearest neighbor algorithm, it was shown that the averaged correct detection rates on each subject were 98.9%, 98.7%, 94.4%, respectively. This method can avoid strict EOG-based eye tracking which requires DC amplification of very small signal. It would be useful to develop robust human interfacing systems based on menu selection for severely paralyzed patients.

[A Feature Extraction Method for Brain Computer Interface Based on Multivariate Empirical Mode Decomposition].

PubMed

Wang, Jinjia; Liu, Yuan

2015-04-01

This paper presents a feature extraction method based on multivariate empirical mode decomposition (MEMD) combining with the power spectrum feature, and the method aims at the non-stationary electroencephalogram (EEG) or magnetoencephalogram (MEG) signal in brain-computer interface (BCI) system. Firstly, we utilized MEMD algorithm to decompose multichannel brain signals into a series of multiple intrinsic mode function (IMF), which was proximate stationary and with multi-scale. Then we extracted and reduced the power characteristic from each IMF to a lower dimensions using principal component analysis (PCA). Finally, we classified the motor imagery tasks by linear discriminant analysis classifier. The experimental verification showed that the correct recognition rates of the two-class and four-class tasks of the BCI competition III and competition IV reached 92.0% and 46.2%, respectively, which were superior to the winner of the BCI competition. The experimental proved that the proposed method was reasonably effective and stable and it would provide a new way for feature extraction.

A new responder criterion (relative effect per patient (REPP) > 0.2) externally validated in a large total hip replacement multicenter cohort (EUROHIP).

PubMed

Huber, J; Hüsler, J; Dieppe, P; Günther, K P; Dreinhöfer, K; Judge, A

2016-03-01

To validate a new method to identify responders (relative effect per patient (REPP) >0.2) using the OMERACT-OARSI criteria as gold standard in a large multicentre sample. The REPP ([score before - after treatment]/score before treatment) was calculated for 845 patients of a large multicenter European cohort study for THR. The patients with a REPP >0.2 were defined as responders. The responder rate was compared to the gold standard (OMERACT-OARSI criteria) using receiver operator characteristic (ROC) curve analysis for sensitivity, specificity and percentage of appropriately classified patients. With the criterion REPP>0.2 85.4% of the patients were classified as responders, applying the OARSI-OMERACT criteria 85.7%. The new method had 98.8% sensitivity, 94.2% specificity and 98.1% of the patients were correctly classified compared to the gold standard. The external validation showed a high sensitivity and also specificity of a new criterion to identify a responder compared to the gold standard method. It is simple and has no uncertainties due to a single classification criterion. Copyright © 2015 The Authors. Published by Elsevier Ltd.. All rights reserved.

Toward automatic phenotyping of retinal images from genetically determined mono- and dizygotic twins using amplitude modulation-frequency modulation methods

NASA Astrophysics Data System (ADS)

Soliz, P.; Davis, B.; Murray, V.; Pattichis, M.; Barriga, S.; Russell, S.

2010-03-01

This paper presents an image processing technique for automatically categorize age-related macular degeneration (AMD) phenotypes from retinal images. Ultimately, an automated approach will be much more precise and consistent in phenotyping of retinal diseases, such as AMD. We have applied the automated phenotyping to retina images from a cohort of mono- and dizygotic twins. The application of this technology will allow one to perform more quantitative studies that will lead to a better understanding of the genetic and environmental factors associated with diseases such as AMD. A method for classifying retinal images based on features derived from the application of amplitude-modulation frequency-modulation (AM-FM) methods is presented. Retinal images from identical and fraternal twins who presented with AMD were processed to determine whether AM-FM could be used to differentiate between the two types of twins. Results of the automatic classifier agreed with the findings of other researchers in explaining the variation of the disease between the related twins. AM-FM features classified 72% of the twins correctly. Visual grading found that genetics could explain between 46% and 71% of the variance.

Disambiguating ambiguous biomedical terms in biomedical narrative text: an unsupervised method.

PubMed

Liu, H; Lussier, Y A; Friedman, C

2001-08-01

With the growing use of Natural Language Processing (NLP) techniques for information extraction and concept indexing in the biomedical domain, a method that quickly and efficiently assigns the correct sense of an ambiguous biomedical term in a given context is needed concurrently. The current status of word sense disambiguation (WSD) in the biomedical domain is that handcrafted rules are used based on contextual material. The disadvantages of this approach are (i) generating WSD rules manually is a time-consuming and tedious task, (ii) maintenance of rule sets becomes increasingly difficult over time, and (iii) handcrafted rules are often incomplete and perform poorly in new domains comprised of specialized vocabularies and different genres of text. This paper presents a two-phase unsupervised method to build a WSD classifier for an ambiguous biomedical term W. The first phase automatically creates a sense-tagged corpus for W, and the second phase derives a classifier for W using the derived sense-tagged corpus as a training set. A formative experiment was performed, which demonstrated that classifiers trained on the derived sense-tagged corpora achieved an overall accuracy of about 97%, with greater than 90% accuracy for each individual ambiguous term.

Quality grading of Atlantic salmon (Salmo salar) by computer vision.

PubMed

Misimi, E; Erikson, U; Skavhaug, A

2008-06-01

In this study, we present a promising method of computer vision-based quality grading of whole Atlantic salmon (Salmo salar). Using computer vision, it was possible to differentiate among different quality grades of Atlantic salmon based on the external geometrical information contained in the fish images. Initially, before the image acquisition, the fish were subjectively graded and labeled into grading classes by a qualified human inspector in the processing plant. Prior to classification, the salmon images were segmented into binary images, and then feature extraction was performed on the geometrical parameters of the fish from the grading classes. The classification algorithm was a threshold-based classifier, which was designed using linear discriminant analysis. The performance of the classifier was tested by using the leave-one-out cross-validation method, and the classification results showed a good agreement between the classification done by human inspectors and by the computer vision. The computer vision-based method classified correctly 90% of the salmon from the data set as compared with the classification by human inspector. Overall, it was shown that computer vision can be used as a powerful tool to grade Atlantic salmon into quality grades in a fast and nondestructive manner by a relatively simple classifier algorithm. The low cost of implementation of today's advanced computer vision solutions makes this method feasible for industrial purposes in fish plants as it can replace manual labor, on which grading tasks still rely.

MR/PET quantification tools: Registration, segmentation, classification, and MR-based attenuation correction

PubMed Central

Fei, Baowei; Yang, Xiaofeng; Nye, Jonathon A.; Aarsvold, John N.; Raghunath, Nivedita; Cervo, Morgan; Stark, Rebecca; Meltzer, Carolyn C.; Votaw, John R.

2012-01-01

Purpose: Combined MR/PET is a relatively new, hybrid imaging modality. A human MR/PET prototype system consisting of a Siemens 3T Trio MR and brain PET insert was installed and tested at our institution. Its present design does not offer measured attenuation correction (AC) using traditional transmission imaging. This study is the development of quantification tools including MR-based AC for quantification in combined MR/PET for brain imaging. Methods: The developed quantification tools include image registration, segmentation, classification, and MR-based AC. These components were integrated into a single scheme for processing MR/PET data. The segmentation method is multiscale and based on the Radon transform of brain MR images. It was developed to segment the skull on T1-weighted MR images. A modified fuzzy C-means classification scheme was developed to classify brain tissue into gray matter, white matter, and cerebrospinal fluid. Classified tissue is assigned an attenuation coefficient so that AC factors can be generated. PET emission data are then reconstructed using a three-dimensional ordered sets expectation maximization method with the MR-based AC map. Ten subjects had separate MR and PET scans. The PET with [11C]PIB was acquired using a high-resolution research tomography (HRRT) PET. MR-based AC was compared with transmission (TX)-based AC on the HRRT. Seventeen volumes of interest were drawn manually on each subject image to compare the PET activities between the MR-based and TX-based AC methods. Results: For skull segmentation, the overlap ratio between our segmented results and the ground truth is 85.2 ± 2.6%. Attenuation correction results from the ten subjects show that the difference between the MR and TX-based methods was <6.5%. Conclusions: MR-based AC compared favorably with conventional transmission-based AC. Quantitative tools including registration, segmentation, classification, and MR-based AC have been developed for use in combined MR/PET. PMID:23039679

Rock images classification by using deep convolution neural network

NASA Astrophysics Data System (ADS)

Cheng, Guojian; Guo, Wenhui

2017-08-01

Granularity analysis is one of the most essential issues in authenticate under microscope. To improve the efficiency and accuracy of traditional manual work, an convolutional neural network based method is proposed for granularity analysis from thin section image, which chooses and extracts features from image samples while build classifier to recognize granularity of input image samples. 4800 samples from Ordos basin are used for experiments under colour spaces of HSV, YCbCr and RGB respectively. On the test dataset, the correct rate in RGB colour space is 98.5%, and it is believable in HSV and YCbCr colour space. The results show that the convolution neural network can classify the rock images with high reliability.

Multiclassifier system with hybrid learning applied to the control of bioprosthetic hand.

PubMed

Kurzynski, Marek; Krysmann, Maciej; Trajdos, Pawel; Wolczowski, Andrzej

2016-02-01

In this paper the problem of recognition of the intended hand movements for the control of bio-prosthetic hand is addressed. The proposed method is based on recognition of electromiographic (EMG) and mechanomiographic (MMG) biosignals using a multiclassifier system (MCS) working in a two-level structure with a dynamic ensemble selection (DES) scheme and original concepts of competence function. Additionally, feedback information coming from bioprosthesis sensors on the correct/incorrect classification is applied to the adjustment of the combining mechanism during MCS operation through adaptive tuning competences of base classifiers depending on their decisions. Three MCS systems operating in decision tree structure and with different tuning algorithms are developed. In the MCS1 system, competence is uniformly allocated to each class belonging to the group indicated by the feedback signal. In the MCS2 system, the modification of competence depends on the node of decision tree at which a correct/incorrect classification is made. In the MCS3 system, the randomized model of classifier and the concept of cross-competence are used in the tuning procedure. Experimental investigations on the real data and computer-simulated procedure of generating feedback signals are performed. In these investigations classification accuracy of the MCS systems developed is compared and furthermore, the MCS systems are evaluated with respect to the effectiveness of the procedure of tuning competence. The results obtained indicate that modification of competence of base classifiers during the working phase essentially improves performance of the MCS system and that this improvement depends on the MCS system and tuning method used. Copyright © 2015 Elsevier Ltd. All rights reserved.

Rapid Pupil-Based Assessment of Glaucomatous Damage

PubMed Central

Chen, Yanjun; Wyatt, Harry J.; Swanson, William H.; Dul, Mitchell W.

2010-01-01

Purpose To investigate the ability of a technique employing pupillometry and functionally-shaped stimuli to assess loss of visual function due to glaucomatous optic neuropathy. Methods Pairs of large stimuli, mirror images about the horizontal meridian, were displayed alternately in the upper and lower visual field. Pupil diameter was recorded and analyzed in terms of the “contrast balance” (relative sensitivity to the upper and lower stimuli), and the pupil constriction amplitude to upper and lower stimuli separately. A group of 40 patients with glaucoma was tested twice in a first session, and twice more in a second session, 1 to 3 weeks later. A group of 40 normal subjects was tested with the same protocol. Results Results for the normal subjects indicated functional symmetry in upper/lower retina, on average. Contrast balance results for the patients with glaucoma differed from normal: half the normal subjects had contrast balance within 0.06 log unit of equality and 80% had contrast balance within 0.1 log unit. Half the patients had contrast balances more than 0.1 log unit from equality. Patient contrast balances were moderately correlated with predictions from perimetric data (r = 0.37, p < 0.00001). Contrast balances correctly classified visual field damage in 28 patients (70%), and response amplitudes correctly classified 24 patients (60%). When contrast balance and response amplitude were combined, receiver operating characteristic area for discriminating glaucoma from normal was 0.83. Conclusions Pupillary evaluation of retinal asymmetry provides a rapid method for detecting and classifying visual field defects. In this patient population, classification agreed with perimetry in 70% of eyes. PMID:18521026

Development of a Metabolic Biosignature for Detection of Early Lyme Disease

PubMed Central

Molins, Claudia R.; Ashton, Laura V.; Wormser, Gary P.; Hess, Ann M.; Delorey, Mark J.; Mahapatra, Sebabrata; Schriefer, Martin E.; Belisle, John T.

2015-01-01

Background. Early Lyme disease patients often present to the clinic prior to developing a detectable antibody response to Borrelia burgdorferi, the etiologic agent. Thus, existing 2-tier serology-based assays yield low sensitivities (29%–40%) for early infection. The lack of an accurate laboratory test for early Lyme disease contributes to misconceptions about diagnosis and treatment, and underscores the need for new diagnostic approaches. Methods. Retrospective serum samples from patients with early Lyme disease, other diseases, and healthy controls were analyzed for small molecule metabolites by liquid chromatography-mass spectrometry (LC-MS). A metabolomics data workflow was applied to select a biosignature for classifying early Lyme disease and non-Lyme disease patients. A statistical model of the biosignature was trained using the patients' LC-MS data, and subsequently applied as an experimental diagnostic tool with LC-MS data from additional patient sera. The accuracy of this method was compared with standard 2-tier serology. Results. Metabolic biosignature development selected 95 molecular features that distinguished early Lyme disease patients from healthy controls. Statistical modeling reduced the biosignature to 44 molecular features, and correctly classified early Lyme disease patients and healthy controls with a sensitivity of 88% (84%–95%), and a specificity of 95% (90%–100%). Importantly, the metabolic biosignature correctly classified 77%–95% of the of serology negative Lyme disease patients. Conclusions. The data provide proof-of-concept that metabolic profiling for early Lyme disease can achieve significantly greater (P < .0001) diagnostic sensitivity than current 2-tier serology, while retaining high specificity. PMID:25761869

Estimation of human emotions using thermal facial information

NASA Astrophysics Data System (ADS)

Nguyen, Hung; Kotani, Kazunori; Chen, Fan; Le, Bac

2014-01-01

In recent years, research on human emotion estimation using thermal infrared (IR) imagery has appealed to many researchers due to its invariance to visible illumination changes. Although infrared imagery is superior to visible imagery in its invariance to illumination changes and appearance differences, it has difficulties in handling transparent glasses in the thermal infrared spectrum. As a result, when using infrared imagery for the analysis of human facial information, the regions of eyeglasses are dark and eyes' thermal information is not given. We propose a temperature space method to correct eyeglasses' effect using the thermal facial information in the neighboring facial regions, and then use Principal Component Analysis (PCA), Eigen-space Method based on class-features (EMC), and PCA-EMC method to classify human emotions from the corrected thermal images. We collected the Kotani Thermal Facial Emotion (KTFE) database and performed the experiments, which show the improved accuracy rate in estimating human emotions.

Prediction of lysine ubiquitylation with ensemble classifier and feature selection.

PubMed

Zhao, Xiaowei; Li, Xiangtao; Ma, Zhiqiang; Yin, Minghao

2011-01-01

Ubiquitylation is an important process of post-translational modification. Correct identification of protein lysine ubiquitylation sites is of fundamental importance to understand the molecular mechanism of lysine ubiquitylation in biological systems. This paper develops a novel computational method to effectively identify the lysine ubiquitylation sites based on the ensemble approach. In the proposed method, 468 ubiquitylation sites from 323 proteins retrieved from the Swiss-Prot database were encoded into feature vectors by using four kinds of protein sequences information. An effective feature selection method was then applied to extract informative feature subsets. After different feature subsets were obtained by setting different starting points in the search procedure, they were used to train multiple random forests classifiers and then aggregated into a consensus classifier by majority voting. Evaluated by jackknife tests and independent tests respectively, the accuracy of the proposed predictor reached 76.82% for the training dataset and 79.16% for the test dataset, indicating that this predictor is a useful tool to predict lysine ubiquitylation sites. Furthermore, site-specific feature analysis was performed and it was shown that ubiquitylation is intimately correlated with the features of its surrounding sites in addition to features derived from the lysine site itself. The feature selection method is available upon request.

ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction.

PubMed

Hajiloo, Mohsen; Sapkota, Yadav; Mackey, John R; Robson, Paula; Greiner, Russell; Damaraju, Sambasivarao

2013-02-22

Population stratification is a systematic difference in allele frequencies between subpopulations. This can lead to spurious association findings in the case-control genome wide association studies (GWASs) used to identify single nucleotide polymorphisms (SNPs) associated with disease-linked phenotypes. Methods such as self-declared ancestry, ancestry informative markers, genomic control, structured association, and principal component analysis are used to assess and correct population stratification but each has limitations. We provide an alternative technique to address population stratification. We propose a novel machine learning method, ETHNOPRED, which uses the genotype and ethnicity data from the HapMap project to learn ensembles of disjoint decision trees, capable of accurately predicting an individual's continental and sub-continental ancestry. To predict an individual's continental ancestry, ETHNOPRED produced an ensemble of 3 decision trees involving a total of 10 SNPs, with 10-fold cross validation accuracy of 100% using HapMap II dataset. We extended this model to involve 29 disjoint decision trees over 149 SNPs, and showed that this ensemble has an accuracy of ≥ 99.9%, even if some of those 149 SNP values were missing. On an independent dataset, predominantly of Caucasian origin, our continental classifier showed 96.8% accuracy and improved genomic control's λ from 1.22 to 1.11. We next used the HapMap III dataset to learn classifiers to distinguish European subpopulations (North-Western vs. Southern), East Asian subpopulations (Chinese vs. Japanese), African subpopulations (Eastern vs. Western), North American subpopulations (European vs. Chinese vs. African vs. Mexican vs. Indian), and Kenyan subpopulations (Luhya vs. Maasai). In these cases, ETHNOPRED produced ensembles of 3, 39, 21, 11, and 25 disjoint decision trees, respectively involving 31, 502, 526, 242 and 271 SNPs, with 10-fold cross validation accuracy of 86.5% ± 2.4%, 95.6% ± 3.9%, 95.6% ± 2.1%, 98.3% ± 2.0%, and 95.9% ± 1.5%. However, ETHNOPRED was unable to produce a classifier that can accurately distinguish Chinese in Beijing vs. Chinese in Denver. ETHNOPRED is a novel technique for producing classifiers that can identify an individual's continental and sub-continental heritage, based on a small number of SNPs. We show that its learned classifiers are simple, cost-efficient, accurate, transparent, flexible, fast, applicable to large scale GWASs, and robust to missing values.

Comparison of wheat classification accuracy using different classifiers of the image-100 system

NASA Technical Reports Server (NTRS)

Dejesusparada, N. (Principal Investigator); Chen, S. C.; Moreira, M. A.; Delima, A. M.

1981-01-01

Classification results using single-cell and multi-cell signature acquisition options, a point-by-point Gaussian maximum-likelihood classifier, and K-means clustering of the Image-100 system are presented. Conclusions reached are that: a better indication of correct classification can be provided by using a test area which contains various cover types of the study area; classification accuracy should be evaluated considering both the percentages of correct classification and error of commission; supervised classification approaches are better than K-means clustering; Gaussian distribution maximum likelihood classifier is better than Single-cell and Multi-cell Signature Acquisition Options of the Image-100 system; and in order to obtain a high classification accuracy in a large and heterogeneous crop area, using Gaussian maximum-likelihood classifier, homogeneous spectral subclasses of the study crop should be created to derive training statistics.

An easy method to differentiate retinal arteries from veins by spectral domain optical coherence tomography: retrospective, observational case series

PubMed Central

2014-01-01

Background Recently it was shown that retinal vessel diameters could be measured using spectral domain optical coherence tomography (OCT). It has also been suggested that retinal vessels manifest different features on spectral domain OCT (SD-OCT) depending on whether they are arteries or veins. Our study was aimed to present a reliable SD-OCT assisted method of differentiating retinal arteries from veins. Methods Patients who underwent circular OCT scans centred at the optic disc using a Spectralis OCT (Heidelberg Engineering, Heidelberg, Germany) were retrospectively reviewed. Individual retinal vessels were identified on infrared reflectance (IR) images and given unique labels for subsequent grading. Vessel types (artery, vein or uncertain) assessed by IR and/or fluorescein angiography (FA) were referenced as ground truth. From OCT, presence/absence of the hyperreflective lower border reflectivity feature was assessed. Presence of this feature was considered indicative for retinal arteries and compared with the ground truth. Results A total of 452 vessels from 26 eyes of 18 patients were labelled and 398 with documented vessel type (302 by IR and 96 by FA only) were included in the study. Using SD-OCT, 338 vessels were assigned a final grade, of which, 86.4% (292 vessels) were classified correctly. Forty three vessels (15 arteries and 28 veins) that IR failed to differentiate were correctly classified by SD-OCT. When using only IR based ground truth for vessel type the SD-OCT based classification approach reached a sensitivity of 0.8758/0.9297, and a specificity of 0.9297/0.8758 for arteries/veins, respectively. Conclusion Our method was able to classify retinal arteries and veins with a commercially available SD-OCT alone, and achieved high classification performance. Paired with OCT based vessel measurements, our study has expanded the potential clinical implication of SD-OCT in evaluation of a variety of retinal and systemic vascular diseases. PMID:24884611

Wide-field spectral imaging of human ovary autofluorescence and oncologic diagnosis via previously collected probe data

PubMed Central

Hatch, Kenneth D.

2012-01-01

Abstract. With no sufficient screening test for ovarian cancer, a method to evaluate the ovarian disease state quickly and nondestructively is needed. The authors have applied a wide-field spectral imager to freshly resected ovaries of 30 human patients in a study believed to be the first of its magnitude. Endogenous fluorescence was excited with 365-nm light and imaged in eight emission bands collectively covering the 400- to 640-nm range. Linear discriminant analysis was used to classify all image pixels and generate diagnostic maps of the ovaries. Training the classifier with previously collected single-point autofluorescence measurements of a spectroscopic probe enabled this novel classification. The process by which probe-collected spectra were transformed for comparison with imager spectra is described. Sensitivity of 100% and specificity of 51% were obtained in classifying normal and cancerous ovaries using autofluorescence data alone. Specificity increased to 69% when autofluorescence data were divided by green reflectance data to correct for spatial variation in tissue absorption properties. Benign neoplasm ovaries were also found to classify as nonmalignant using the same algorithm. Although applied ex vivo, the method described here appears useful for quick assessment of cancer presence in the human ovary. PMID:22502561

Exploring the effects of transducer models when training convolutional neural networks to eliminate reflection artifacts in experimental photoacoustic images

NASA Astrophysics Data System (ADS)

Allman, Derek; Reiter, Austin; Bell, Muyinatu

2018-02-01

We previously proposed a method of removing reflection artifacts in photoacoustic images that uses deep learning. Our approach generally relies on using simulated photoacoustic channel data to train a convolutional neural network (CNN) that is capable of distinguishing sources from artifacts based on unique differences in their spatial impulse responses (manifested as depth-based differences in wavefront shapes). In this paper, we directly compare a CNN trained with our previous continuous transducer model to a CNN trained with an updated discrete acoustic receiver model that more closely matches an experimental ultrasound transducer. These two CNNs were trained with simulated data and tested on experimental data. The CNN trained using the continuous receiver model correctly classified 100% of sources and 70.3% of artifacts in the experimental data. In contrast, the CNN trained using the discrete receiver model correctly classified 100% of sources and 89.7% of artifacts in the experimental images. The 19.4% increase in artifact classification accuracy indicates that an acoustic receiver model that closely mimics the experimental transducer plays an important role in improving the classification of artifacts in experimental photoacoustic data. Results are promising for developing a method to display CNN-based images that remove artifacts in addition to only displaying network-identified sources as previously proposed.

Reduction of Topographic Effect for Curve Number Estimated from Remotely Sensed Imagery

NASA Astrophysics Data System (ADS)

Zhang, Wen-Yan; Lin, Chao-Yuan

2016-04-01

The Soil Conservation Service Curve Number (SCS-CN) method is commonly used in hydrology to estimate direct runoff volume. The CN is the empirical parameter which corresponding to land use/land cover, hydrologic soil group and antecedent soil moisture condition. In large watersheds with complex topography, satellite remote sensing is the appropriate approach to acquire the land use change information. However, the topographic effect have been usually found in the remotely sensed imageries and resulted in land use classification. This research selected summer and winter scenes of Landsat-5 TM during 2008 to classified land use in Chen-You-Lan Watershed, Taiwan. The b-correction, the empirical topographic correction method, was applied to Landsat-5 TM data. Land use were categorized using K-mean classification into 4 groups i.e. forest, grassland, agriculture and river. Accuracy assessment of image classification was performed with national land use map. The results showed that after topographic correction, the overall accuracy of classification was increased from 68.0% to 74.5%. The average CN estimated from remotely sensed imagery decreased from 48.69 to 45.35 where the average CN estimated from national LULC map was 44.11. Therefore, the topographic correction method was recommended to normalize the topographic effect from the satellite remote sensing data before estimating the CN.

The application of artificial intelligence for the identification of the maceral groups and mineral components of coal

NASA Astrophysics Data System (ADS)

Mlynarczuk, Mariusz; Skiba, Marta

2017-06-01

The correct and consistent identification of the petrographic properties of coal is an important issue for researchers in the fields of mining and geology. As part of the study described in this paper, investigations concerning the application of artificial intelligence methods for the identification of the aforementioned characteristics were carried out. The methods in question were used to identify the maceral groups of coal, i.e. vitrinite, inertinite, and liptinite. Additionally, an attempt was made to identify some non-organic minerals. The analyses were performed using pattern recognition techniques (NN, kNN), as well as artificial neural network techniques (a multilayer perceptron - MLP). The classification process was carried out using microscopy images of polished sections of coals. A multidimensional feature space was defined, which made it possible to classify the discussed structures automatically, based on the methods of pattern recognition and algorithms of the artificial neural networks. Also, from the study we assessed the impact of the parameters for which the applied methods proved effective upon the final outcome of the classification procedure. The result of the analyses was a high percentage (over 97%) of correct classifications of maceral groups and mineral components. The paper discusses also an attempt to analyze particular macerals of the inertinite group. It was demonstrated that using artificial neural networks to this end makes it possible to classify the macerals properly in over 91% of cases. Thus, it was proved that artificial intelligence methods can be successfully applied for the identification of selected petrographic features of coal.

Investigation of Super Learner Methodology on HIV-1 Small Sample: Application on Jaguar Trial Data.

PubMed

Houssaïni, Allal; Assoumou, Lambert; Marcelin, Anne Geneviève; Molina, Jean Michel; Calvez, Vincent; Flandre, Philippe

2012-01-01

Background. Many statistical models have been tested to predict phenotypic or virological response from genotypic data. A statistical framework called Super Learner has been introduced either to compare different methods/learners (discrete Super Learner) or to combine them in a Super Learner prediction method. Methods. The Jaguar trial is used to apply the Super Learner framework. The Jaguar study is an "add-on" trial comparing the efficacy of adding didanosine to an on-going failing regimen. Our aim was also to investigate the impact on the use of different cross-validation strategies and different loss functions. Four different repartitions between training set and validations set were tested through two loss functions. Six statistical methods were compared. We assess performance by evaluating R(2) values and accuracy by calculating the rates of patients being correctly classified. Results. Our results indicated that the more recent Super Learner methodology of building a new predictor based on a weighted combination of different methods/learners provided good performance. A simple linear model provided similar results to those of this new predictor. Slight discrepancy arises between the two loss functions investigated, and slight difference arises also between results based on cross-validated risks and results from full dataset. The Super Learner methodology and linear model provided around 80% of patients correctly classified. The difference between the lower and higher rates is around 10 percent. The number of mutations retained in different learners also varys from one to 41. Conclusions. The more recent Super Learner methodology combining the prediction of many learners provided good performance on our small dataset.

Differentiation of Chemical Components in a Binary Solvent Vapor Mixture Using Carbon/Polymer Composite-Based Chemiresistors

DOE Office of Scientific and Technical Information (OSTI.GOV)

Patel, Sanjay V.; Jenkins, Mark W.; Hughes, Robert C.

1999-07-19

We demonstrate a ''universal solvent sensor'' constructed from a small array of carbon/polymer composite chemiresistors that respond to solvents spanning a wide range of Hildebrand volubility parameters. Conductive carbon particles provide electrical continuity in these composite films. When the polymer matrix absorbs solvent vapors, the composite film swells, the average separation between carbon particles increases, and an increase in film resistance results, as some of the conduction pathways are broken. The adverse effects of contact resistance at high solvent concentrations are reported. Solvent vapors including isooctane, ethanol, dlisopropyhnethylphosphonate (DIMP), and water are correctly identified (''classified'') using three chemiresistors, their compositemore » coatings chosen to span the full range of volubility parameters. With the same three sensors, binary mixtures of solvent vapor and water vapor are correctly classified, following classification, two sensors suffice to determine the concentrations of both vapor components. Polyethylene vinylacetate and polyvinyl alcohol (PVA) are two such polymers that are used to classify binary mixtures of DIMP with water vapor; the PVA/carbon-particle-composite films are sensitive to less than 0.25{degree}A relative humidity. The Sandia-developed VERI (Visual-Empirical Region of Influence) technique is used as a method of pattern recognition to classify the solvents and mixtures and to distinguish them from water vapor. In many cases, the response of a given composite sensing film to a binary mixture deviates significantly from the sum of the responses to the isolated vapor components at the same concentrations. While these nonlinearities pose significant difficulty for (primarily) linear methods such as principal components analysis, VERI handles both linear and nonlinear data with equal ease. In the present study the maximum speciation accuracy is achieved by an array containing three or four sensor elements, with the addition of more sensors resulting in a measurable accuracy decrease.« less

A two-step automatic sleep stage classification method with dubious range detection.

PubMed

Sousa, Teresa; Cruz, Aniana; Khalighi, Sirvan; Pires, Gabriel; Nunes, Urbano

2015-04-01

The limitations of the current systems of automatic sleep stage classification (ASSC) are essentially related to the similarities between epochs from different sleep stages and the subjects' variability. Several studies have already identified the situations with the highest likelihood of misclassification in sleep scoring. Here, we took advantage of such information to develop an ASSC system based on knowledge of subjects' variability of some indicators that characterize sleep stages and on the American Academy of Sleep Medicine (AASM) rules. An ASSC system consisting of a two-step classifier is proposed. In the first step, epochs are classified using support vector machines (SVMs) spread into different nodes of a decision tree. In the post-processing step, the epochs suspected of misclassification (dubious classification) are tagged, and a new classification is suggested. Identification and correction are based on the AASM rules, and on misclassifications most commonly found/reported in automatic sleep staging. Six electroencephalographic and two electrooculographic channels were used to classify wake, non-rapid eye movement (NREM) sleep--N1, N2 and N3, and rapid eye movement (REM) sleep. The proposed system was tested in a dataset of 14 clinical polysomnographic records of subjects suspected of apnea disorders. Wake and REM epochs not falling in the dubious range, are classified with accuracy levels compatible with the requirements for clinical applications. The suggested correction assigned to the epochs that are tagged as dubious enhances the global results of all sleep stages. This approach provides reliable sleep staging results for non-dubious epochs. Copyright © 2015 Elsevier Ltd. All rights reserved.

A minimum spanning forest based classification method for dedicated breast CT images

DOE Office of Scientific and Technical Information (OSTI.GOV)

Pike, Robert; Sechopoulos, Ioannis; Fei, Baowei, E-mail: bfei@emory.edu

Purpose: To develop and test an automated algorithm to classify different types of tissue in dedicated breast CT images. Methods: Images of a single breast of five different patients were acquired with a dedicated breast CT clinical prototype. The breast CT images were processed by a multiscale bilateral filter to reduce noise while keeping edge information and were corrected to overcome cupping artifacts. As skin and glandular tissue have similar CT values on breast CT images, morphologic processing is used to identify the skin based on its position information. A support vector machine (SVM) is trained and the resulting modelmore » used to create a pixelwise classification map of fat and glandular tissue. By combining the results of the skin mask with the SVM results, the breast tissue is classified as skin, fat, and glandular tissue. This map is then used to identify markers for a minimum spanning forest that is grown to segment the image using spatial and intensity information. To evaluate the authors’ classification method, they use DICE overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on five patient images. Results: Comparison between the automatic and the manual segmentation shows that the minimum spanning forest based classification method was able to successfully classify dedicated breast CT image with average DICE ratios of 96.9%, 89.8%, and 89.5% for fat, glandular, and skin tissue, respectively. Conclusions: A 2D minimum spanning forest based classification method was proposed and evaluated for classifying the fat, skin, and glandular tissue in dedicated breast CT images. The classification method can be used for dense breast tissue quantification, radiation dose assessment, and other applications in breast imaging.« less

Mining sequential patterns for protein fold recognition.

PubMed

Exarchos, Themis P; Papaloukas, Costas; Lampros, Christos; Fotiadis, Dimitrios I

2008-02-01

Protein data contain discriminative patterns that can be used in many beneficial applications if they are defined correctly. In this work sequential pattern mining (SPM) is utilized for sequence-based fold recognition. Protein classification in terms of fold recognition plays an important role in computational protein analysis, since it can contribute to the determination of the function of a protein whose structure is unknown. Specifically, one of the most efficient SPM algorithms, cSPADE, is employed for the analysis of protein sequence. A classifier uses the extracted sequential patterns to classify proteins in the appropriate fold category. For training and evaluating the proposed method we used the protein sequences from the Protein Data Bank and the annotation of the SCOP database. The method exhibited an overall accuracy of 25% in a classification problem with 36 candidate categories. The classification performance reaches up to 56% when the five most probable protein folds are considered.

The hospital anxiety and depression rating scale: A cross-sectional study of psychometrics and case finding abilities in general practice

PubMed Central

Olssøn, Ingrid; Mykletun, Arnstein; Dahl, Alv A

2005-01-01

Background General practitioners' (GPs) diagnostic skills lead to underidentification of generalized anxiety disorders (GAD) and major depressive episodes (MDE). Supplement of brief questionnaires could improve the diagnostic accuracy of GPs for these common mental disorders. The aims of this study were to examine the usefulness of The Hospital Anxiety and Depression Rating Scale (HADS) for GPs by: 1) Examining its psychometrics in the GPs' setting; 2) Testing its case-finding properties compared to patient-rated GAD and MDE (DSM-IV); and 3) Comparing its case finding abilities to that of the GPs using Clinical Global Impression-Severity (CGI-S) rating. Methods In a cross-sectional survey study 1,781 patients in three consecutive days in September 2001 attended 141 GPs geographically spread in Norway. Sensitivity, specificity, optimal cut off score, and Area under the curve (AUC) for the HADS and the CGI-S were calculated with Generalized Anxiety Questionnaire (GAS-Q) as reference standard for GAD, and Depression Screening Questionnaire (DSQ) for MDE. Results The HADS-A had optimal cut off ≥8 (sensitivity 0.89, specificity 0.75), AUC 0.88 and 76% of patients were correctly classified in relation to GAD. The HADS-D had by optimal cut off ≥8 (sensitivity 0.80 and specificity 0.88) AUC 0.93 and 87% of the patients were correctly classified in relation to MDE. Proportions of the total correctly classified at the CGI-S optimal cut-off ≥3 were 83% of patients for GAD and 81% for MDE. Conclusion The results indicate that addition of the patients' HADS scores to GPs' information could improve their diagnostic accuracy of GAD and MDE. PMID:16351733

Memory Alteration Test to Detect Amnestic Mild Cognitive Impairment and Early Alzheimer's Dementia in Population with Low Educational Level.

PubMed

Custodio, Nilton; Lira, David; Herrera-Perez, Eder; Montesinos, Rosa; Castro-Suarez, Sheila; Cuenca-Alfaro, José; Valeriano-Lorenzo, Lucía

2017-01-01

Background/Aims : Short tests to early detection of the cognitive impairment are necessary in primary care setting, particularly in populations with low educational level. The aim of this study was to assess the performance of Memory Alteration Test (M@T) to discriminate controls, patients with amnestic Mild Cognitive Impairment (aMCI) and patients with early Alzheimer's Dementia (AD) in a sample of individuals with low level of education. Methods : Cross-sectional study to assess the performance of the M@T (study test), compared to the neuropsychological evaluation (gold standard test) scores in 247 elderly subjects with low education level from Lima-Peru. The cognitive evaluation included three sequential stages: (1) screening (to detect cases with cognitive impairment); (2) nosological diagnosis (to determinate specific disease); and (3) classification (to differentiate disease subtypes). The subjects with negative results for all stages were considered as cognitively normal (controls). The test performance was assessed by means of area under the receiver operating characteristic (ROC) curve. We calculated validity measures (sensitivity, specificity and correctly classified percentage), the internal consistency (Cronbach's alpha coefficient), and concurrent validity (Pearson's ratio coefficient between the M@T and Clinical Dementia Rating (CDR) scores). Results : The Cronbach's alpha coefficient was 0.79 and Pearson's ratio coefficient was 0.79 ( p < 0.01). The AUC of M@T to discriminate between early AD and aMCI was 99.60% (sensitivity = 100.00%, specificity = 97.53% and correctly classified = 98.41%) and to discriminate between aMCI and controls was 99.56% (sensitivity = 99.17%, specificity = 91.11%, and correctly classified = 96.99%). Conclusions : The M@T is a short test with a good performance to discriminate controls, aMCI and early AD in individuals with low level of education from urban settings.

Prospective Evaluation of Multimodal Optical Imaging with Automated Image Analysis to Detect Oral Neoplasia In Vivo.

PubMed

Quang, Timothy; Tran, Emily Q; Schwarz, Richard A; Williams, Michelle D; Vigneswaran, Nadarajah; Gillenwater, Ann M; Richards-Kortum, Rebecca

2017-10-01

The 5-year survival rate for patients with oral cancer remains low, in part because diagnosis often occurs at a late stage. Early and accurate identification of oral high-grade dysplasia and cancer can help improve patient outcomes. Multimodal optical imaging is an adjunctive diagnostic technique in which autofluorescence imaging is used to identify high-risk regions within the oral cavity, followed by high-resolution microendoscopy to confirm or rule out the presence of neoplasia. Multimodal optical images were obtained from 206 sites in 100 patients. Histologic diagnosis, either from a punch biopsy or an excised surgical specimen, was used as the gold standard for all sites. Histopathologic diagnoses of moderate dysplasia or worse were considered neoplastic. Images from 92 sites in the first 30 patients were used as a training set to develop automated image analysis methods for identification of neoplasia. Diagnostic performance was evaluated prospectively using images from 114 sites in the remaining 70 patients as a test set. In the training set, multimodal optical imaging with automated image analysis correctly classified 95% of nonneoplastic sites and 94% of neoplastic sites. Among the 56 sites in the test set that were biopsied, multimodal optical imaging correctly classified 100% of nonneoplastic sites and 85% of neoplastic sites. Among the 58 sites in the test set that corresponded to a surgical specimen, multimodal imaging correctly classified 100% of nonneoplastic sites and 61% of neoplastic sites. These findings support the potential of multimodal optical imaging to aid in the early detection of oral cancer. Cancer Prev Res; 10(10); 563-70. ©2017 AACR . ©2017 American Association for Cancer Research.

Utilization of spectral-spatial characteristics in shortwave infrared hyperspectral images to classify and identify fungi-contaminated peanuts.

PubMed

Qiao, Xiaojun; Jiang, Jinbao; Qi, Xiaotong; Guo, Haiqiang; Yuan, Deshuai

2017-04-01

It's well-known fungi-contaminated peanuts contain potent carcinogen. Efficiently identifying and separating the contaminated can help prevent aflatoxin entering in food chain. In this study, shortwave infrared (SWIR) hyperspectral images for identifying the prepared contaminated kernels. Feature selection method of analysis of variance (ANOVA) and feature extraction method of nonparametric weighted feature extraction (NWFE) were used to concentrate spectral information into a subspace where contaminated and healthy peanuts can have favorable separability. Then, peanut pixels were classified using SVM. Moreover, image segmentation method of region growing was applied to segment the image as kernel-scale patches and meanwhile to number the kernels. The result shows that pixel-wise classification accuracies are 99.13% for breed A, 96.72% for B and 99.73% for C in learning images, and are 96.32%, 94.2% and 97.51% in validation images. Contaminated peanuts were correctly marked as aberrant kernels in both learning images and validation images. Copyright © 2016 Elsevier Ltd. All rights reserved.

Automated anatomical labeling of bronchial branches extracted from CT datasets based on machine learning and combination optimization and its application to bronchoscope guidance.

PubMed

Mori, Kensaku; Ota, Shunsuke; Deguchi, Daisuke; Kitasaka, Takayuki; Suenaga, Yasuhito; Iwano, Shingo; Hasegawa, Yosihnori; Takabatake, Hirotsugu; Mori, Masaki; Natori, Hiroshi

2009-01-01

This paper presents a method for the automated anatomical labeling of bronchial branches extracted from 3D CT images based on machine learning and combination optimization. We also show applications of anatomical labeling on a bronchoscopy guidance system. This paper performs automated labeling by using machine learning and combination optimization. The actual procedure consists of four steps: (a) extraction of tree structures of the bronchus regions extracted from CT images, (b) construction of AdaBoost classifiers, (c) computation of candidate names for all branches by using the classifiers, (d) selection of best combination of anatomical names. We applied the proposed method to 90 cases of 3D CT datasets. The experimental results showed that the proposed method can assign correct anatomical names to 86.9% of the bronchial branches up to the sub-segmental lobe branches. Also, we overlaid the anatomical names of bronchial branches on real bronchoscopic views to guide real bronchoscopy.

A robust method using propensity score stratification for correcting verification bias for binary tests

PubMed Central

He, Hua; McDermott, Michael P.

2012-01-01

Sensitivity and specificity are common measures of the accuracy of a diagnostic test. The usual estimators of these quantities are unbiased if data on the diagnostic test result and the true disease status are obtained from all subjects in an appropriately selected sample. In some studies, verification of the true disease status is performed only for a subset of subjects, possibly depending on the result of the diagnostic test and other characteristics of the subjects. Estimators of sensitivity and specificity based on this subset of subjects are typically biased; this is known as verification bias. Methods have been proposed to correct verification bias under the assumption that the missing data on disease status are missing at random (MAR), that is, the probability of missingness depends on the true (missing) disease status only through the test result and observed covariate information. When some of the covariates are continuous, or the number of covariates is relatively large, the existing methods require parametric models for the probability of disease or the probability of verification (given the test result and covariates), and hence are subject to model misspecification. We propose a new method for correcting verification bias based on the propensity score, defined as the predicted probability of verification given the test result and observed covariates. This is estimated separately for those with positive and negative test results. The new method classifies the verified sample into several subsamples that have homogeneous propensity scores and allows correction for verification bias. Simulation studies demonstrate that the new estimators are more robust to model misspecification than existing methods, but still perform well when the models for the probability of disease and probability of verification are correctly specified. PMID:21856650

Automatic identification of inertial sensor placement on human body segments during walking

PubMed Central

2013-01-01

Background Current inertial motion capture systems are rarely used in biomedical applications. The attachment and connection of the sensors with cables is often a complex and time consuming task. Moreover, it is prone to errors, because each sensor has to be attached to a predefined body segment. By using wireless inertial sensors and automatic identification of their positions on the human body, the complexity of the set-up can be reduced and incorrect attachments are avoided. We present a novel method for the automatic identification of inertial sensors on human body segments during walking. This method allows the user to place (wireless) inertial sensors on arbitrary body segments. Next, the user walks for just a few seconds and the segment to which each sensor is attached is identified automatically. Methods Walking data was recorded from ten healthy subjects using an Xsens MVN Biomech system with full-body configuration (17 inertial sensors). Subjects were asked to walk for about 6 seconds at normal walking speed (about 5 km/h). After rotating the sensor data to a global coordinate frame with x-axis in walking direction, y-axis pointing left and z-axis vertical, RMS, mean, and correlation coefficient features were extracted from x-, y- and z-components and magnitudes of the accelerations, angular velocities and angular accelerations. As a classifier, a decision tree based on the C4.5 algorithm was developed using Weka (Waikato Environment for Knowledge Analysis). Results and conclusions After testing the algorithm with 10-fold cross-validation using 31 walking trials (involving 527 sensors), 514 sensors were correctly classified (97.5%). When a decision tree for a lower body plus trunk configuration (8 inertial sensors) was trained and tested using 10-fold cross-validation, 100% of the sensors were correctly identified. This decision tree was also tested on walking trials of 7 patients (17 walking trials) after anterior cruciate ligament reconstruction, which also resulted in 100% correct identification, thus illustrating the robustness of the method. PMID:23517757

Rules based process window OPC

NASA Astrophysics Data System (ADS)

O'Brien, Sean; Soper, Robert; Best, Shane; Mason, Mark

2008-03-01

As a preliminary step towards Model-Based Process Window OPC we have analyzed the impact of correcting post-OPC layouts using rules based methods. Image processing on the Brion Tachyon was used to identify sites where the OPC model/recipe failed to generate an acceptable solution. A set of rules for 65nm active and poly were generated by classifying these failure sites. The rules were based upon segment runlengths, figure spaces, and adjacent figure widths. 2.1 million sites for active were corrected in a small chip (comparing the pre and post rules based operations), and 59 million were found at poly. Tachyon analysis of the final reticle layout found weak margin sites distinct from those sites repaired by rules-based corrections. For the active layer more than 75% of the sites corrected by rules would have printed without a defect indicating that most rulesbased cleanups degrade the lithographic pattern. Some sites were missed by the rules based cleanups due to either bugs in the DRC software or gaps in the rules table. In the end dramatic changes to the reticle prevented catastrophic lithography errors, but this method is far too blunt. A more subtle model-based procedure is needed changing only those sites which have unsatisfactory lithographic margin.

Discrimination of almonds (Prunus dulcis) geographical origin by minerals and fatty acids profiling.

PubMed

Amorello, Diana; Orecchio, Santino; Pace, Andrea; Barreca, Salvatore

2016-09-01

Twenty-one almond samples from three different geographical origins (Sicily, Spain and California) were investigated by determining minerals and fatty acids compositions. Data were used to discriminate by chemometry almond origin by linear discriminant analysis. With respect to previous PCA profiling studies, this work provides a simpler analytical protocol for the identification of almonds geographical origin. Classification by using mineral contents data only was correct in 77% of the samples, while, by using fatty acid profiles, the percentages of samples correctly classified reached 82%. The coupling of mineral contents and fatty acid profiles lead to an increased efficiency of the classification with 87% of samples correctly classified.

Improving Hospital-Wide Early Resource Allocation through Machine Learning.

PubMed

Gartner, Daniel; Padman, Rema

2015-01-01

The objective of this paper is to evaluate the extent to which early determination of diagnosis-related groups (DRGs) can be used for better allocation of scarce hospital resources. When elective patients seek admission, the true DRG, currently determined only at discharge, is unknown. We approach the problem of early DRG determination in three stages: (1) test how much a Naïve Bayes classifier can improve classification accuracy as compared to a hospital's current approach; (2) develop a statistical program that makes admission and scheduling decisions based on the patients' clincial pathways and scarce hospital resources; and (3) feed the DRG as classified by the Naïve Bayes classifier and the hospitals' baseline approach into the model (which we evaluate in simulation). Our results reveal that the DRG grouper performs poorly in classifying the DRG correctly before admission while the Naïve Bayes approach substantially improves the classification task. The results from the connection of the classification method with the mathematical program also reveal that resource allocation decisions can be more effective and efficient with the hybrid approach.

Comparing supervised learning methods for classifying sex, age, context and individual Mudi dogs from barking.

PubMed

Larrañaga, Ana; Bielza, Concha; Pongrácz, Péter; Faragó, Tamás; Bálint, Anna; Larrañaga, Pedro

2015-03-01

Barking is perhaps the most characteristic form of vocalization in dogs; however, very little is known about its role in the intraspecific communication of this species. Besides the obvious need for ethological research, both in the field and in the laboratory, the possible information content of barks can also be explored by computerized acoustic analyses. This study compares four different supervised learning methods (naive Bayes, classification trees, [Formula: see text]-nearest neighbors and logistic regression) combined with three strategies for selecting variables (all variables, filter and wrapper feature subset selections) to classify Mudi dogs by sex, age, context and individual from their barks. The classification accuracy of the models obtained was estimated by means of [Formula: see text]-fold cross-validation. Percentages of correct classifications were 85.13 % for determining sex, 80.25 % for predicting age (recodified as young, adult and old), 55.50 % for classifying contexts (seven situations) and 67.63 % for recognizing individuals (8 dogs), so the results are encouraging. The best-performing method was [Formula: see text]-nearest neighbors following a wrapper feature selection approach. The results for classifying contexts and recognizing individual dogs were better with this method than they were for other approaches reported in the specialized literature. This is the first time that the sex and age of domestic dogs have been predicted with the help of sound analysis. This study shows that dog barks carry ample information regarding the caller's indexical features. Our computerized analysis provides indirect proof that barks may serve as an important source of information for dogs as well.

Planning schistosomiasis control: investigation of alternative sampling strategies for Schistosoma mansoni to target mass drug administration of praziquantel in East Africa.

PubMed

Sturrock, Hugh J W; Gething, Pete W; Ashton, Ruth A; Kolaczinski, Jan H; Kabatereine, Narcis B; Brooker, Simon

2011-09-01

In schistosomiasis control, there is a need to geographically target treatment to populations at high risk of morbidity. This paper evaluates alternative sampling strategies for surveys of Schistosoma mansoni to target mass drug administration in Kenya and Ethiopia. Two main designs are considered: lot quality assurance sampling (LQAS) of children from all schools; and a geostatistical design that samples a subset of schools and uses semi-variogram analysis and spatial interpolation to predict prevalence in the remaining unsurveyed schools. Computerized simulations are used to investigate the performance of sampling strategies in correctly classifying schools according to treatment needs and their cost-effectiveness in identifying high prevalence schools. LQAS performs better than geostatistical sampling in correctly classifying schools, but at a cost with a higher cost per high prevalence school correctly classified. It is suggested that the optimal surveying strategy for S. mansoni needs to take into account the goals of the control programme and the financial and drug resources available.

Identification of DNA-Binding Proteins Using Structural, Electrostatic and Evolutionary Features

PubMed Central

Nimrod, Guy; Szilágyi, András; Leslie, Christina; Ben-Tal, Nir

2009-01-01

Summary DNA binding proteins (DBPs) often take part in various crucial processes of the cell's life cycle. Therefore, the identification and characterization of these proteins are of great importance. We present here a random forests classifier for identifying DBPs among proteins with known three-dimensional structures. First, clusters of evolutionarily conserved regions (patches) on the protein's surface are detected using the PatchFinder algorithm; previous studies showed that these regions are typically the proteins' functionally important regions. Next, we train a classifier using features like the electrostatic potential, cluster-based amino acid conservation patterns and the secondary structure content of the patches, as well as features of the whole protein including its dipole moment. Using 10-fold cross validation on a dataset of 138 DNA-binding proteins and 110 proteins which do not bind DNA, the classifier achieved a sensitivity and a specificity of 0.90, which is overall better than the performance of previously published methods. Furthermore, when we tested 5 different methods on 11 new DBPs which did not appear in the original dataset, only our method annotated all correctly. The resulting classifier was applied to a collection of 757 proteins of known structure and unknown function. Of these proteins, 218 were predicted to bind DNA, and we anticipate that some of them interact with DNA using new structural motifs. The use of complementary computational tools supports the notion that at least some of them do bind DNA. PMID:19233205

Identification of DNA-binding proteins using structural, electrostatic and evolutionary features.

PubMed

Nimrod, Guy; Szilágyi, András; Leslie, Christina; Ben-Tal, Nir

2009-04-10

DNA-binding proteins (DBPs) participate in various crucial processes in the life-cycle of the cells, and the identification and characterization of these proteins is of great importance. We present here a random forests classifier for identifying DBPs among proteins with known 3D structures. First, clusters of evolutionarily conserved regions (patches) on the surface of proteins were detected using the PatchFinder algorithm; earlier studies showed that these regions are typically the functionally important regions of proteins. Next, we trained a classifier using features like the electrostatic potential, cluster-based amino acid conservation patterns and the secondary structure content of the patches, as well as features of the whole protein, including its dipole moment. Using 10-fold cross-validation on a dataset of 138 DBPs and 110 proteins that do not bind DNA, the classifier achieved a sensitivity and a specificity of 0.90, which is overall better than the performance of published methods. Furthermore, when we tested five different methods on 11 new DBPs that did not appear in the original dataset, only our method annotated all correctly. The resulting classifier was applied to a collection of 757 proteins of known structure and unknown function. Of these proteins, 218 were predicted to bind DNA, and we anticipate that some of them interact with DNA using new structural motifs. The use of complementary computational tools supports the notion that at least some of them do bind DNA.

[Prediction of the efficacy of the non-medicamental treatment with the use of the ensemble of classifiers].

PubMed

Zaĭtsev, A A; Khodashinskiĭ, I A; Plotnikov, O O

2011-01-01

The importance to have the most efficacious tools and methods for the prevention and treatment of various diseases and rehabilitation of the patients dictates the necessity of search for new means of optimal correction of individual reserves of the organism. One of the approaches to addressing this problem is simulation of prognostication of curative effects of non-medicamental therapy. It is proposed to choose the therapeutic program using an ensemble of classifiers. Two types of them are considered, one based on the solution trees, the other based on the fuzzy rule basis. The software was developed that ensures high accuracy of th e prognosis of the efficiency of the two programs of the spa and resort treatment.

Prediction of Ionizing Radiation Resistance in Bacteria Using a Multiple Instance Learning Model.

PubMed

Aridhi, Sabeur; Sghaier, Haïtham; Zoghlami, Manel; Maddouri, Mondher; Nguifo, Engelbert Mephu

2016-01-01

Ionizing-radiation-resistant bacteria (IRRB) are important in biotechnology. In this context, in silico methods of phenotypic prediction and genotype-phenotype relationship discovery are limited. In this work, we analyzed basal DNA repair proteins of most known proteome sequences of IRRB and ionizing-radiation-sensitive bacteria (IRSB) in order to learn a classifier that correctly predicts this bacterial phenotype. We formulated the problem of predicting bacterial ionizing radiation resistance (IRR) as a multiple-instance learning (MIL) problem, and we proposed a novel approach for this purpose. We provide a MIL-based prediction system that classifies a bacterium to either IRRB or IRSB. The experimental results of the proposed system are satisfactory with 91.5% of successful predictions.

Integrating language models into classifiers for BCI communication: a review

NASA Astrophysics Data System (ADS)

Speier, W.; Arnold, C.; Pouratian, N.

2016-06-01

Objective. The present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication systems. Approach. The domain of natural language has been studied extensively in linguistics and has been used in the natural language processing field in applications including information extraction, machine translation, and speech recognition. While these methods have been used for years in traditional augmentative and assistive communication devices, information about the output domain has largely been ignored in BCI communication systems. Over the last few years, BCI communication systems have started to leverage this information through the inclusion of language models. Main results. Although this movement began only recently, studies have already shown the potential of language integration in BCI communication and it has become a growing field in BCI research. BCI communication systems using language models in their classifiers have progressed down several parallel paths, including: word completion; signal classification; integration of process models; dynamic stopping; unsupervised learning; error correction; and evaluation. Significance. Each of these methods have shown significant progress, but have largely been addressed separately. Combining these methods could use the full potential of language model, yielding further performance improvements. This integration should be a priority as the field works to create a BCI system that meets the needs of the amyotrophic lateral sclerosis population.

Integrating language models into classifiers for BCI communication: a review.

PubMed

Speier, W; Arnold, C; Pouratian, N

2016-06-01

The present review systematically examines the integration of language models to improve classifier performance in brain-computer interface (BCI) communication systems. The domain of natural language has been studied extensively in linguistics and has been used in the natural language processing field in applications including information extraction, machine translation, and speech recognition. While these methods have been used for years in traditional augmentative and assistive communication devices, information about the output domain has largely been ignored in BCI communication systems. Over the last few years, BCI communication systems have started to leverage this information through the inclusion of language models. Although this movement began only recently, studies have already shown the potential of language integration in BCI communication and it has become a growing field in BCI research. BCI communication systems using language models in their classifiers have progressed down several parallel paths, including: word completion; signal classification; integration of process models; dynamic stopping; unsupervised learning; error correction; and evaluation. Each of these methods have shown significant progress, but have largely been addressed separately. Combining these methods could use the full potential of language model, yielding further performance improvements. This integration should be a priority as the field works to create a BCI system that meets the needs of the amyotrophic lateral sclerosis population.

Supervised retinal vessel segmentation from color fundus images based on matched filtering and AdaBoost classifier.

PubMed

Memari, Nogol; Ramli, Abd Rahman; Bin Saripan, M Iqbal; Mashohor, Syamsiah; Moghbel, Mehrdad

2017-01-01

The structure and appearance of the blood vessel network in retinal fundus images is an essential part of diagnosing various problems associated with the eyes, such as diabetes and hypertension. In this paper, an automatic retinal vessel segmentation method utilizing matched filter techniques coupled with an AdaBoost classifier is proposed. The fundus image is enhanced using morphological operations, the contrast is increased using contrast limited adaptive histogram equalization (CLAHE) method and the inhomogeneity is corrected using Retinex approach. Then, the blood vessels are enhanced using a combination of B-COSFIRE and Frangi matched filters. From this preprocessed image, different statistical features are computed on a pixel-wise basis and used in an AdaBoost classifier to extract the blood vessel network inside the image. Finally, the segmented images are postprocessed to remove the misclassified pixels and regions. The proposed method was validated using publicly accessible Digital Retinal Images for Vessel Extraction (DRIVE), Structured Analysis of the Retina (STARE) and Child Heart and Health Study in England (CHASE_DB1) datasets commonly used for determining the accuracy of retinal vessel segmentation methods. The accuracy of the proposed segmentation method was comparable to other state of the art methods while being very close to the manual segmentation provided by the second human observer with an average accuracy of 0.972, 0.951 and 0.948 in DRIVE, STARE and CHASE_DB1 datasets, respectively.

Use of machine-learning classifiers to predict requests for preoperative acute pain service consultation.

PubMed

Tighe, Patrick J; Lucas, Stephen D; Edwards, David A; Boezaart, André P; Aytug, Haldun; Bihorac, Azra

2012-10-01

  The purpose of this project was to determine whether machine-learning classifiers could predict which patients would require a preoperative acute pain service (APS) consultation.   Retrospective cohort.   University teaching hospital.   The records of 9,860 surgical patients posted between January 1 and June 30, 2010 were reviewed.   Request for APS consultation. A cohort of machine-learning classifiers was compared according to its ability or inability to classify surgical cases as requiring a request for a preoperative APS consultation. Classifiers were then optimized utilizing ensemble techniques. Computational efficiency was measured with the central processing unit processing times required for model training. Classifiers were tested using the full feature set, as well as the reduced feature set that was optimized using a merit-based dimensional reduction strategy.   Machine-learning classifiers correctly predicted preoperative requests for APS consultations in 92.3% (95% confidence intervals [CI], 91.8-92.8) of all surgical cases. Bayesian methods yielded the highest area under the receiver operating curve (0.87, 95% CI 0.84-0.89) and lowest training times (0.0018 seconds, 95% CI, 0.0017-0.0019 for the NaiveBayesUpdateable algorithm). An ensemble of high-performing machine-learning classifiers did not yield a higher area under the receiver operating curve than its component classifiers. Dimensional reduction decreased the computational requirements for multiple classifiers, but did not adversely affect classification performance.   Using historical data, machine-learning classifiers can predict which surgical cases should prompt a preoperative request for an APS consultation. Dimensional reduction improved computational efficiency and preserved predictive performance. Wiley Periodicals, Inc.

A theory of fine structure image models with an application to detection and classification of dementia.

PubMed

O'Neill, William; Penn, Richard; Werner, Michael; Thomas, Justin

2015-06-01

Estimation of stochastic process models from data is a common application of time series analysis methods. Such system identification processes are often cast as hypothesis testing exercises whose intent is to estimate model parameters and test them for statistical significance. Ordinary least squares (OLS) regression and the Levenberg-Marquardt algorithm (LMA) have proven invaluable computational tools for models being described by non-homogeneous, linear, stationary, ordinary differential equations. In this paper we extend stochastic model identification to linear, stationary, partial differential equations in two independent variables (2D) and show that OLS and LMA apply equally well to these systems. The method employs an original nonparametric statistic as a test for the significance of estimated parameters. We show gray scale and color images are special cases of 2D systems satisfying a particular autoregressive partial difference equation which estimates an analogous partial differential equation. Several applications to medical image modeling and classification illustrate the method by correctly classifying demented and normal OLS models of axial magnetic resonance brain scans according to subject Mini Mental State Exam (MMSE) scores. Comparison with 13 image classifiers from the literature indicates our classifier is at least 14 times faster than any of them and has a classification accuracy better than all but one. Our modeling method applies to any linear, stationary, partial differential equation and the method is readily extended to 3D whole-organ systems. Further, in addition to being a robust image classifier, estimated image models offer insights into which parameters carry the most diagnostic image information and thereby suggest finer divisions could be made within a class. Image models can be estimated in milliseconds which translate to whole-organ models in seconds; such runtimes could make real-time medicine and surgery modeling possible.

Estimating Occupancy of Gopher Tortoise (Gorpherus polyphemus) Burrows in Coastal Scrub and Slash Pine Flatwoods

NASA Technical Reports Server (NTRS)

Breininger, David R.; Schmalzer, Paul A.; Hinkle, C. Ross

1991-01-01

One hundred twelve plots were established in coastal scrub and slash pine flatwoods habitats on the John F. Kennedy Space Center (KSC) to evaluate relationships between the number of burrows and gopher tortoise (Gopherus polyphemus) density. All burrows were located within these plots and were classified according to tortoise activity. Depending on season, bucket trapping, a stick method, a gopher tortoise pulling device, and a camera system were used to estimate tortoise occupancy. Correction factors (% of burrows occupied) were calculated by season and habitat type. Our data suggest that less than 20% of the active and inactive burrows combined were occupied during seasons when gopher tortoises were active. Correction factors were higher in poorly-drained areas and lower in well-drained areas during the winter, when gopher tortoise activity was low. Correction factors differed from studies elsewhere, indicating that population estimates require correction factors specific to the site and season to accurately estimate population size.

Correction of hypermobile flatfoot in children by molded insert.

PubMed

Bordelon, R L

1980-11-01

One hundred feet in 50 children between the ages of 3 and 9 years with a diagnosis of idiopathic hypermobile flatfoot had a custom-molded insert ordered. A specific method of casting, correcting the various components of the deformity was utilized. An 1/8-inch polypropolene insert was fabricated from the positive cast. The insert was worn in leather shoes with a long counter, steel shank, and Thomas heel. The flatfoot was evaluated and classified by measurement of the talometatarsal angle on a standing lateral X-ray. The insert was fabricated so that the standing lateral talometatarsal angle was corrected to neutral with the insert on the foot and the foot in the shoe. The preliminary reports indicate that a correction can be obtained at the rate of 0.41 degrees per month or approximately 5 degrees per year. There was no significant loss of motion of the foot or the ankle. Perhaps this regimen may be utilized in those children with a hypermobile flatfoot for whom treatment is advised.

Integration of metabolic activation with a predictive toxicogenomics signature to classify genotoxic versus nongenotoxic chemicals in human TK6 cells

PubMed Central

Buick, Julie K.; Moffat, Ivy; Williams, Andrew; Swartz, Carol D.; Recio, Leslie; Hyduke, Daniel R.; Li, Heng‐Hong; Fornace, Albert J.; Aubrecht, Jiri

2015-01-01

The use of integrated approaches in genetic toxicology, including the incorporation of gene expression data to determine the molecular pathways involved in the response, is becoming more common. In a companion article, a genomic biomarker was developed in human TK6 cells to classify chemicals as genotoxic or nongenotoxic. Because TK6 cells are not metabolically competent, we set out to broaden the utility of the biomarker for use with chemicals requiring metabolic activation. Specifically, chemical exposures were conducted in the presence of rat liver S9. The ability of the biomarker to classify genotoxic (benzo[a]pyrene, BaP; aflatoxin B1, AFB1) and nongenotoxic (dexamethasone, DEX; phenobarbital, PB) agents correctly was evaluated. Cells were exposed to increasing chemical concentrations for 4 hr and collected 0 hr, 4 hr, and 20 hr postexposure. Relative survival, apoptosis, and micronucleus frequency were measured at 24 hr. Transcriptome profiles were measured with Agilent microarrays. Statistical modeling and bioinformatics tools were applied to classify each chemical using the genomic biomarker. BaP and AFB1 were correctly classified as genotoxic at the mid‐ and high concentrations at all three time points, whereas DEX was correctly classified as nongenotoxic at all concentrations and time points. The high concentration of PB was misclassified at 24 hr, suggesting that cytotoxicity at later time points may cause misclassification. The data suggest that the use of S9 does not impair the ability of the biomarker to classify genotoxicity in TK6 cells. Finally, we demonstrate that the biomarker is also able to accurately classify genotoxicity using a publicly available dataset derived from human HepaRG cells. Environ. Mol. Mutagen. 56:520–534, 2015. © 2015 The Authors. Environmental and Molecular Mutagenesis Published by Wiley Periodicals, Inc. PMID:25733247

A Dirichlet process model for classifying and forecasting epidemic curves.

PubMed

Nsoesie, Elaine O; Leman, Scotland C; Marathe, Madhav V

2014-01-09

A forecast can be defined as an endeavor to quantitatively estimate a future event or probabilities assigned to a future occurrence. Forecasting stochastic processes such as epidemics is challenging since there are several biological, behavioral, and environmental factors that influence the number of cases observed at each point during an epidemic. However, accurate forecasts of epidemics would impact timely and effective implementation of public health interventions. In this study, we introduce a Dirichlet process (DP) model for classifying and forecasting influenza epidemic curves. The DP model is a nonparametric Bayesian approach that enables the matching of current influenza activity to simulated and historical patterns, identifies epidemic curves different from those observed in the past and enables prediction of the expected epidemic peak time. The method was validated using simulated influenza epidemics from an individual-based model and the accuracy was compared to that of the tree-based classification technique, Random Forest (RF), which has been shown to achieve high accuracy in the early prediction of epidemic curves using a classification approach. We also applied the method to forecasting influenza outbreaks in the United States from 1997-2013 using influenza-like illness (ILI) data from the Centers for Disease Control and Prevention (CDC). We made the following observations. First, the DP model performed as well as RF in identifying several of the simulated epidemics. Second, the DP model correctly forecasted the peak time several days in advance for most of the simulated epidemics. Third, the accuracy of identifying epidemics different from those already observed improved with additional data, as expected. Fourth, both methods correctly classified epidemics with higher reproduction numbers (R) with a higher accuracy compared to epidemics with lower R values. Lastly, in the classification of seasonal influenza epidemics based on ILI data from the CDC, the methods' performance was comparable. Although RF requires less computational time compared to the DP model, the algorithm is fully supervised implying that epidemic curves different from those previously observed will always be misclassified. In contrast, the DP model can be unsupervised, semi-supervised or fully supervised. Since both methods have their relative merits, an approach that uses both RF and the DP model could be beneficial.

Prediction of aortic valvular area and gradient by noninvasive techniques.

PubMed

Cousins, A L; Eddleman, E E; Reeves, T J

1978-03-01

Sixty-two patients with isolated aortic valvular stenosis were analyzed by a series of common noninvasive procedures and by cardiac catheterization. The data from 50 of these were evaluated in a retrospective fashion by multiple regression methods to determine significant objectively obtained predictors of aortic-left ventricular gradient and valvular area. Formulae were derived from these analyses and an additional 12 patients were then studied prospectively to evaluate the validity of the predictive formulae. Forty-three of 50 patients (86 per cent) were correctly identified as to a gradient of greater or less than 50 mm. Hg in the initial group, and all those in the prospectively studied sample were correctly classified. Thiry-five of 43 patients (82 per cent) of those with valve area data in the first application were correctly classified as to valve area or greater or less than 0.8 cm.2, and all patients in the prospectively studied group were appropriately identified as to the same area. The combined application of the observations of calcification of the aortic valve, shudder waves on the anacrotic limb, prolonged time to peak of the percussion wave and alteration of the dicrotic notch of the carotid pulse tracing, left ventricular hypertrophy by electrocardiogram, and the altered duration of ventricular ejection time were reliable predictors of elevated aortic-left ventricular gradient and decreased aortic valvular size.

Feature extraction using convolutional neural network for classifying breast density in mammographic images

NASA Astrophysics Data System (ADS)

Thomaz, Ricardo L.; Carneiro, Pedro C.; Patrocinio, Ana C.

2017-03-01

Breast cancer is the leading cause of death for women in most countries. The high levels of mortality relate mostly to late diagnosis and to the direct proportionally relationship between breast density and breast cancer development. Therefore, the correct assessment of breast density is important to provide better screening for higher risk patients. However, in modern digital mammography the discrimination among breast densities is highly complex due to increased contrast and visual information for all densities. Thus, a computational system for classifying breast density might be a useful tool for aiding medical staff. Several machine-learning algorithms are already capable of classifying small number of classes with good accuracy. However, machinelearning algorithms main constraint relates to the set of features extracted and used for classification. Although well-known feature extraction techniques might provide a good set of features, it is a complex task to select an initial set during design of a classifier. Thus, we propose feature extraction using a Convolutional Neural Network (CNN) for classifying breast density by a usual machine-learning classifier. We used 307 mammographic images downsampled to 260x200 pixels to train a CNN and extract features from a deep layer. After training, the activation of 8 neurons from a deep fully connected layer are extracted and used as features. Then, these features are feedforward to a single hidden layer neural network that is cross-validated using 10-folds to classify among four classes of breast density. The global accuracy of this method is 98.4%, presenting only 1.6% of misclassification. However, the small set of samples and memory constraints required the reuse of data in both CNN and MLP-NN, therefore overfitting might have influenced the results even though we cross-validated the network. Thus, although we presented a promising method for extracting features and classifying breast density, a greater database is still required for evaluating the results.

Probabilistic atlas-based segmentation of combined T1-weighted and DUTE MRI for calculation of head attenuation maps in integrated PET/MRI scanners

PubMed Central

Poynton, Clare B; Chen, Kevin T; Chonde, Daniel B; Izquierdo-Garcia, David; Gollub, Randy L; Gerstner, Elizabeth R; Batchelor, Tracy T; Catana, Ciprian

2014-01-01

We present a new MRI-based attenuation correction (AC) approach for integrated PET/MRI systems that combines both segmentation- and atlas-based methods by incorporating dual-echo ultra-short echo-time (DUTE) and T1-weighted (T1w) MRI data and a probabilistic atlas. Segmented atlases were constructed from CT training data using a leave-one-out framework and combined with T1w, DUTE, and CT data to train a classifier that computes the probability of air/soft tissue/bone at each voxel. This classifier was applied to segment the MRI of the subject of interest and attenuation maps (μ-maps) were generated by assigning specific linear attenuation coefficients (LACs) to each tissue class. The μ-maps generated with this “Atlas-T1w-DUTE” approach were compared to those obtained from DUTE data using a previously proposed method. For validation of the segmentation results, segmented CT μ-maps were considered to the “silver standard”; the segmentation accuracy was assessed qualitatively and quantitatively through calculation of the Dice similarity coefficient (DSC). Relative change (RC) maps between the CT and MRI-based attenuation corrected PET volumes were also calculated for a global voxel-wise assessment of the reconstruction results. The μ-maps obtained using the Atlas-T1w-DUTE classifier agreed well with those derived from CT; the mean DSCs for the Atlas-T1w-DUTE-based μ-maps across all subjects were higher than those for DUTE-based μ-maps; the atlas-based μ-maps also showed a lower percentage of misclassified voxels across all subjects. RC maps from the atlas-based technique also demonstrated improvement in the PET data compared to the DUTE method, both globally as well as regionally. PMID:24753982

Classification of neocortical interneurons using affinity propagation.

PubMed

Santana, Roberto; McGarry, Laura M; Bielza, Concha; Larrañaga, Pedro; Yuste, Rafael

2013-01-01

In spite of over a century of research on cortical circuits, it is still unknown how many classes of cortical neurons exist. In fact, neuronal classification is a difficult problem because it is unclear how to designate a neuronal cell class and what are the best characteristics to define them. Recently, unsupervised classifications using cluster analysis based on morphological, physiological, or molecular characteristics, have provided quantitative and unbiased identification of distinct neuronal subtypes, when applied to selected datasets. However, better and more robust classification methods are needed for increasingly complex and larger datasets. Here, we explored the use of affinity propagation, a recently developed unsupervised classification algorithm imported from machine learning, which gives a representative example or exemplar for each cluster. As a case study, we applied affinity propagation to a test dataset of 337 interneurons belonging to four subtypes, previously identified based on morphological and physiological characteristics. We found that affinity propagation correctly classified most of the neurons in a blind, non-supervised manner. Affinity propagation outperformed Ward's method, a current standard clustering approach, in classifying the neurons into 4 subtypes. Affinity propagation could therefore be used in future studies to validly classify neurons, as a first step to help reverse engineer neural circuits.

A comparison of three clustering methods for finding subgroups in MRI, SMS or clinical data: SPSS TwoStep Cluster analysis, Latent Gold and SNOB.

PubMed

Kent, Peter; Jensen, Rikke K; Kongsted, Alice

2014-10-02

There are various methodological approaches to identifying clinically important subgroups and one method is to identify clusters of characteristics that differentiate people in cross-sectional and/or longitudinal data using Cluster Analysis (CA) or Latent Class Analysis (LCA). There is a scarcity of head-to-head comparisons that can inform the choice of which clustering method might be suitable for particular clinical datasets and research questions. Therefore, the aim of this study was to perform a head-to-head comparison of three commonly available methods (SPSS TwoStep CA, Latent Gold LCA and SNOB LCA). The performance of these three methods was compared: (i) quantitatively using the number of subgroups detected, the classification probability of individuals into subgroups, the reproducibility of results, and (ii) qualitatively using subjective judgments about each program's ease of use and interpretability of the presentation of results.We analysed five real datasets of varying complexity in a secondary analysis of data from other research projects. Three datasets contained only MRI findings (n = 2,060 to 20,810 vertebral disc levels), one dataset contained only pain intensity data collected for 52 weeks by text (SMS) messaging (n = 1,121 people), and the last dataset contained a range of clinical variables measured in low back pain patients (n = 543 people). Four artificial datasets (n = 1,000 each) containing subgroups of varying complexity were also analysed testing the ability of these clustering methods to detect subgroups and correctly classify individuals when subgroup membership was known. The results from the real clinical datasets indicated that the number of subgroups detected varied, the certainty of classifying individuals into those subgroups varied, the findings had perfect reproducibility, some programs were easier to use and the interpretability of the presentation of their findings also varied. The results from the artificial datasets indicated that all three clustering methods showed a near-perfect ability to detect known subgroups and correctly classify individuals into those subgroups. Our subjective judgement was that Latent Gold offered the best balance of sensitivity to subgroups, ease of use and presentation of results with these datasets but we recognise that different clustering methods may suit other types of data and clinical research questions.

Triaging Patient Complaints: Monte Carlo Cross-Validation of Six Machine Learning Classifiers

PubMed Central

Cooper, William O; Catron, Thomas F; Karrass, Jan; Zhang, Zhe; Singh, Munindar P

2017-01-01

Background Unsolicited patient complaints can be a useful service recovery tool for health care organizations. Some patient complaints contain information that may necessitate further action on the part of the health care organization and/or the health care professional. Current approaches depend on the manual processing of patient complaints, which can be costly, slow, and challenging in terms of scalability. Objective The aim of this study was to evaluate automatic patient triage, which can potentially improve response time and provide much-needed scale, thereby enhancing opportunities to encourage physicians to self-regulate. Methods We implemented a comparison of several well-known machine learning classifiers to detect whether a complaint was associated with a physician or his/her medical practice. We compared these classifiers using a real-life dataset containing 14,335 patient complaints associated with 768 physicians that was extracted from patient complaints collected by the Patient Advocacy Reporting System developed at Vanderbilt University and associated institutions. We conducted a 10-splits Monte Carlo cross-validation to validate our results. Results We achieved an accuracy of 82% and F-score of 81% in correctly classifying patient complaints with sensitivity and specificity of 0.76 and 0.87, respectively. Conclusions We demonstrate that natural language processing methods based on modeling patient complaint text can be effective in identifying those patient complaints requiring physician action. PMID:28760726

Determination of the Characteristics and Classification of Near-Infrared Spectra of Patchouli Oil (Pogostemon Cablin Benth.) from Different Origin

NASA Astrophysics Data System (ADS)

Diego, M. C. R.; Purwanto, Y. A.; Sutrisno; Budiastra, I. W.

2018-05-01

Research related to the non-destructive method of near-infrared (NIR) spectroscopy in aromatic oil is still in development in Indonesia. The objectives of the study were to determine the characteristics of the near-infrared spectra of patchouli oil and classify it based on its origin. The samples were selected from seven different places in Indonesia (Bogor and Garut from West Java, Aceh, and Jambi from Sumatra and Konawe, Masamba and Kolaka from Sulawesi Island). The spectral data of patchouli oil was obtained by FT-NIR spectrometer at the wavelength of 1000-2500 nm, and after that, the samples were subjected to composition analysis using Gas Chromatography-Mass Spectrometry. The transmittance and absorbance spectra were analyzed and then principal component analysis (PCA) was carried out. Discriminant analysis (DA) of the principal component was developed to classify patchouli oil based on its origin. The result shows that the data of both spectra (transmittance and absorbance spectra) by the PC analysis give a similar result for discriminating the seven types of patchouli oil due to their distribution and behavior. The DA of the three principal component in both data processed spectra could classify patchouli oil accurately. This result exposed that NIR spectroscopy can be successfully used as a correct method to classify patchouli oil based on its origin.

Evaluation of Machine Learning Algorithms for Classification of Primary Biological Aerosol using a new UV-LIF spectrometer

NASA Astrophysics Data System (ADS)

Ruske, S. T.; Topping, D. O.; Foot, V. E.; Kaye, P. H.; Stanley, W. R.; Morse, A. P.; Crawford, I.; Gallagher, M. W.

2016-12-01

Characterisation of bio-aerosols has important implications within Environment and Public Health sectors. Recent developments in Ultra-Violet Light Induced Fluorescence (UV-LIF) detectors such as the Wideband Integrated bio-aerosol Spectrometer (WIBS) and the newly introduced Multiparameter bio-aerosol Spectrometer (MBS) has allowed for the real time collection of fluorescence, size and morphology measurements for the purpose of discriminating between bacteria, fungal Spores and pollen. This new generation of instruments has enabled ever-larger data sets to be compiled with the aim of studying more complex environments, yet the algorithms used for specie classification remain largely invalidated. It is therefore imperative that we validate the performance of different algorithms that can be used for the task of classification, which is the focus of this study. For unsupervised learning we test Hierarchical Agglomerative Clustering with various different linkages. For supervised learning, ten methods were tested; including decision trees, ensemble methods: Random Forests, Gradient Boosting and AdaBoost; two implementations for support vector machines: libsvm and liblinear; Gaussian methods: Gaussian naïve Bayesian, quadratic and linear discriminant analysis and finally the k-nearest neighbours algorithm. The methods were applied to two different data sets measured using a new Multiparameter bio-aerosol Spectrometer. We find that clustering, in general, performs slightly worse than the supervised learning methods correctly classifying, at best, only 72.7 and 91.1 percent for the two data sets. For supervised learning the gradient boosting algorithm was found to be the most effective, on average correctly classifying 88.1 and 97.8 percent of the testing data respectively across the two data sets. We discuss the wider relevance of these results with regards to challenging existing classification in real-world environments.

Ventricular Fibrillation and Tachycardia detection from surface ECG using time-frequency representation images as input dataset for machine learning.

PubMed

Mjahad, A; Rosado-Muñoz, A; Bataller-Mompeán, M; Francés-Víllora, J V; Guerrero-Martínez, J F

2017-04-01

To safely select the proper therapy for Ventricullar Fibrillation (VF) is essential to distinct it correctly from Ventricular Tachycardia (VT) and other rhythms. Provided that the required therapy would not be the same, an erroneous detection might lead to serious injuries to the patient or even cause Ventricular Fibrillation (VF). The main novelty of this paper is the use of time-frequency (t-f) representation images as the direct input to the classifier. We hypothesize that this method allow to improve classification results as it allows to eliminate the typical feature selection and extraction stage, and its corresponding loss of information. The standard AHA and MIT-BIH databases were used for evaluation and comparison with other authors. Previous to t-f Pseudo Wigner-Ville (PWV) calculation, only a basic preprocessing for denoising and signal alignment is necessary. In order to check the validity of the method independently of the classifier, four different classifiers are used: Logistic Regression with L2 Regularization (L2 RLR), Adaptive Neural Network Classifier (ANNC), Support Vector Machine (SSVM), and Bagging classifier (BAGG). The main classification results for VF detection (including flutter episodes) are 95.56% sensitivity and 98.8% specificity, 88.80% sensitivity and 99.5% specificity for ventricular tachycardia (VT), 98.98% sensitivity and 97.7% specificity for normal sinus, and 96.87% sensitivity and 99.55% specificity for other rhythms. Results shows that using t-f data representations to feed classifiers provide superior performance values than the feature selection strategies used in previous works. It opens the door to be used in any other detection applications. Copyright © 2017 Elsevier B.V. All rights reserved.

A tool for classifying individuals with chronic back pain: using multivariate pattern analysis with functional magnetic resonance imaging data.

PubMed

Callan, Daniel; Mills, Lloyd; Nott, Connie; England, Robert; England, Shaun

2014-01-01

Chronic pain is one of the most prevalent health problems in the world today, yet neurological markers, critical to diagnosis of chronic pain, are still largely unknown. The ability to objectively identify individuals with chronic pain using functional magnetic resonance imaging (fMRI) data is important for the advancement of diagnosis, treatment, and theoretical knowledge of brain processes associated with chronic pain. The purpose of our research is to investigate specific neurological markers that could be used to diagnose individuals experiencing chronic pain by using multivariate pattern analysis with fMRI data. We hypothesize that individuals with chronic pain have different patterns of brain activity in response to induced pain. This pattern can be used to classify the presence or absence of chronic pain. The fMRI experiment consisted of alternating 14 seconds of painful electric stimulation (applied to the lower back) with 14 seconds of rest. We analyzed contrast fMRI images in stimulation versus rest in pain-related brain regions to distinguish between the groups of participants: 1) chronic pain and 2) normal controls. We employed supervised machine learning techniques, specifically sparse logistic regression, to train a classifier based on these contrast images using a leave-one-out cross-validation procedure. We correctly classified 92.3% of the chronic pain group (N = 13) and 92.3% of the normal control group (N = 13) by recognizing multivariate patterns of activity in the somatosensory and inferior parietal cortex. This technique demonstrates that differences in the pattern of brain activity to induced pain can be used as a neurological marker to distinguish between individuals with and without chronic pain. Medical, legal and business professionals have recognized the importance of this research topic and of developing objective measures of chronic pain. This method of data analysis was very successful in correctly classifying each of the two groups.

A Tool for Classifying Individuals with Chronic Back Pain: Using Multivariate Pattern Analysis with Functional Magnetic Resonance Imaging Data

PubMed Central

Callan, Daniel; Mills, Lloyd; Nott, Connie; England, Robert; England, Shaun

2014-01-01

Chronic pain is one of the most prevalent health problems in the world today, yet neurological markers, critical to diagnosis of chronic pain, are still largely unknown. The ability to objectively identify individuals with chronic pain using functional magnetic resonance imaging (fMRI) data is important for the advancement of diagnosis, treatment, and theoretical knowledge of brain processes associated with chronic pain. The purpose of our research is to investigate specific neurological markers that could be used to diagnose individuals experiencing chronic pain by using multivariate pattern analysis with fMRI data. We hypothesize that individuals with chronic pain have different patterns of brain activity in response to induced pain. This pattern can be used to classify the presence or absence of chronic pain. The fMRI experiment consisted of alternating 14 seconds of painful electric stimulation (applied to the lower back) with 14 seconds of rest. We analyzed contrast fMRI images in stimulation versus rest in pain-related brain regions to distinguish between the groups of participants: 1) chronic pain and 2) normal controls. We employed supervised machine learning techniques, specifically sparse logistic regression, to train a classifier based on these contrast images using a leave-one-out cross-validation procedure. We correctly classified 92.3% of the chronic pain group (N = 13) and 92.3% of the normal control group (N = 13) by recognizing multivariate patterns of activity in the somatosensory and inferior parietal cortex. This technique demonstrates that differences in the pattern of brain activity to induced pain can be used as a neurological marker to distinguish between individuals with and without chronic pain. Medical, legal and business professionals have recognized the importance of this research topic and of developing objective measures of chronic pain. This method of data analysis was very successful in correctly classifying each of the two groups. PMID:24905072

Novel high/low solubility classification methods for new molecular entities.

PubMed

Dave, Rutwij A; Morris, Marilyn E

2016-09-10

This research describes a rapid solubility classification approach that could be used in the discovery and development of new molecular entities. Compounds (N=635) were divided into two groups based on information available in the literature: high solubility (BDDCS/BCS 1/3) and low solubility (BDDCS/BCS 2/4). We established decision rules for determining solubility classes using measured log solubility in molar units (MLogSM) or measured solubility (MSol) in mg/ml units. ROC curve analysis was applied to determine statistically significant threshold values of MSol and MLogSM. Results indicated that NMEs with MLogSM>-3.05 or MSol>0.30mg/mL will have ≥85% probability of being highly soluble and new molecular entities with MLogSM≤-3.05 or MSol≤0.30mg/mL will have ≥85% probability of being poorly soluble. When comparing solubility classification using the threshold values of MLogSM or MSol with BDDCS, we were able to correctly classify 85% of compounds. We also evaluated solubility classification of an independent set of 108 orally administered drugs using MSol (0.3mg/mL) and our method correctly classified 81% and 95% of compounds into high and low solubility classes, respectively. The high/low solubility classification using MLogSM or MSol is novel and independent of traditionally used dose number criteria. Copyright © 2016 Elsevier B.V. All rights reserved.

Power System Transient Stability Based on Data Mining Theory

NASA Astrophysics Data System (ADS)

Cui, Zhen; Shi, Jia; Wu, Runsheng; Lu, Dan; Cui, Mingde

2018-01-01

In order to study the stability of power system, a power system transient stability based on data mining theory is designed. By introducing association rules analysis in data mining theory, an association classification method for transient stability assessment is presented. A mathematical model of transient stability assessment based on data mining technology is established. Meanwhile, combining rule reasoning with classification prediction, the method of association classification is proposed to perform transient stability assessment. The transient stability index is used to identify the samples that cannot be correctly classified in association classification. Then, according to the critical stability of each sample, the time domain simulation method is used to determine the state, so as to ensure the accuracy of the final results. The results show that this stability assessment system can improve the speed of operation under the premise that the analysis result is completely correct, and the improved algorithm can find out the inherent relation between the change of power system operation mode and the change of transient stability degree.

Credit scoring analysis using weighted k nearest neighbor

NASA Astrophysics Data System (ADS)

Mukid, M. A.; Widiharih, T.; Rusgiyono, A.; Prahutama, A.

2018-05-01

Credit scoring is a quatitative method to evaluate the credit risk of loan applications. Both statistical methods and artificial intelligence are often used by credit analysts to help them decide whether the applicants are worthy of credit. These methods aim to predict future behavior in terms of credit risk based on past experience of customers with similar characteristics. This paper reviews the weighted k nearest neighbor (WKNN) method for credit assessment by considering the use of some kernels. We use credit data from a private bank in Indonesia. The result shows that the Gaussian kernel and rectangular kernel have a better performance based on the value of percentage corrected classified whose value is 82.4% respectively.

Three-phase general border detection method for dermoscopy images using non-uniform illumination correction.

PubMed

Norton, Kerri-Ann; Iyatomi, Hitoshi; Celebi, M Emre; Ishizaki, Sumiko; Sawada, Mizuki; Suzaki, Reiko; Kobayashi, Ken; Tanaka, Masaru; Ogawa, Koichi

2012-08-01

Computer-aided diagnosis of dermoscopy images has shown great promise in developing a quantitative, objective way of classifying skin lesions. An important step in the classification process is lesion segmentation. Many studies have been successful in segmenting melanocytic skin lesions (MSLs), but few have focused on non-melanocytic skin lesions (NoMSLs), as the wide variety of lesions makes accurate segmentation difficult. We developed an automatic segmentation program for detecting borders of skin lesions in dermoscopy images. The method consists of a pre-processing phase, general lesion segmentation phase, including illumination correction, and bright region segmentation phase. We tested our method on a set of 107 NoMSLs and a set of 319 MSLs. Our method achieved precision/recall scores of 84.5% and 88.5% for NoMSLs, and 93.9% and 93.8% for MSLs, in comparison with manual extractions from four or five dermatologists. The accuracy of our method was competitive or better than five recently published methods. Our new method is the first method for detecting borders of both non-melanocytic and melanocytic skin lesions. © 2011 John Wiley & Sons A/S.

A generalized approach for producing, quantifying, and validating citizen science data from wildlife images.

PubMed

Swanson, Alexandra; Kosmala, Margaret; Lintott, Chris; Packer, Craig

2016-06-01

Citizen science has the potential to expand the scope and scale of research in ecology and conservation, but many professional researchers remain skeptical of data produced by nonexperts. We devised an approach for producing accurate, reliable data from untrained, nonexpert volunteers. On the citizen science website www.snapshotserengeti.org, more than 28,000 volunteers classified 1.51 million images taken in a large-scale camera-trap survey in Serengeti National Park, Tanzania. Each image was circulated to, on average, 27 volunteers, and their classifications were aggregated using a simple plurality algorithm. We validated the aggregated answers against a data set of 3829 images verified by experts and calculated 3 certainty metrics-level of agreement among classifications (evenness), fraction of classifications supporting the aggregated answer (fraction support), and fraction of classifiers who reported "nothing here" for an image that was ultimately classified as containing an animal (fraction blank)-to measure confidence that an aggregated answer was correct. Overall, aggregated volunteer answers agreed with the expert-verified data on 98% of images, but accuracy differed by species commonness such that rare species had higher rates of false positives and false negatives. Easily calculated analysis of variance and post-hoc Tukey tests indicated that the certainty metrics were significant indicators of whether each image was correctly classified or classifiable. Thus, the certainty metrics can be used to identify images for expert review. Bootstrapping analyses further indicated that 90% of images were correctly classified with just 5 volunteers per image. Species classifications based on the plurality vote of multiple citizen scientists can provide a reliable foundation for large-scale monitoring of African wildlife. © 2016 The Authors. Conservation Biology published by Wiley Periodicals, Inc. on behalf of Society for Conservation Biology.

A generalized approach for producing, quantifying, and validating citizen science data from wildlife images

PubMed Central

Kosmala, Margaret; Lintott, Chris; Packer, Craig

2016-01-01

Abstract Citizen science has the potential to expand the scope and scale of research in ecology and conservation, but many professional researchers remain skeptical of data produced by nonexperts. We devised an approach for producing accurate, reliable data from untrained, nonexpert volunteers. On the citizen science website www.snapshotserengeti.org, more than 28,000 volunteers classified 1.51 million images taken in a large‐scale camera‐trap survey in Serengeti National Park, Tanzania. Each image was circulated to, on average, 27 volunteers, and their classifications were aggregated using a simple plurality algorithm. We validated the aggregated answers against a data set of 3829 images verified by experts and calculated 3 certainty metrics—level of agreement among classifications (evenness), fraction of classifications supporting the aggregated answer (fraction support), and fraction of classifiers who reported “nothing here” for an image that was ultimately classified as containing an animal (fraction blank)—to measure confidence that an aggregated answer was correct. Overall, aggregated volunteer answers agreed with the expert‐verified data on 98% of images, but accuracy differed by species commonness such that rare species had higher rates of false positives and false negatives. Easily calculated analysis of variance and post‐hoc Tukey tests indicated that the certainty metrics were significant indicators of whether each image was correctly classified or classifiable. Thus, the certainty metrics can be used to identify images for expert review. Bootstrapping analyses further indicated that 90% of images were correctly classified with just 5 volunteers per image. Species classifications based on the plurality vote of multiple citizen scientists can provide a reliable foundation for large‐scale monitoring of African wildlife. PMID:27111678

Empirical evaluation of data normalization methods for molecular classification.

PubMed

Huang, Huei-Chung; Qin, Li-Xuan

2018-01-01

Data artifacts due to variations in experimental handling are ubiquitous in microarray studies, and they can lead to biased and irreproducible findings. A popular approach to correct for such artifacts is through post hoc data adjustment such as data normalization. Statistical methods for data normalization have been developed and evaluated primarily for the discovery of individual molecular biomarkers. Their performance has rarely been studied for the development of multi-marker molecular classifiers-an increasingly important application of microarrays in the era of personalized medicine. In this study, we set out to evaluate the performance of three commonly used methods for data normalization in the context of molecular classification, using extensive simulations based on re-sampling from a unique pair of microRNA microarray datasets for the same set of samples. The data and code for our simulations are freely available as R packages at GitHub. In the presence of confounding handling effects, all three normalization methods tended to improve the accuracy of the classifier when evaluated in an independent test data. The level of improvement and the relative performance among the normalization methods depended on the relative level of molecular signal, the distributional pattern of handling effects (e.g., location shift vs scale change), and the statistical method used for building the classifier. In addition, cross-validation was associated with biased estimation of classification accuracy in the over-optimistic direction for all three normalization methods. Normalization may improve the accuracy of molecular classification for data with confounding handling effects; however, it cannot circumvent the over-optimistic findings associated with cross-validation for assessing classification accuracy.

Classification and correction of the radar bright band with polarimetric radar

NASA Astrophysics Data System (ADS)

Hall, Will; Rico-Ramirez, Miguel; Kramer, Stefan

2015-04-01

The annular region of enhanced radar reflectivity, known as the Bright Band (BB), occurs when the radar beam intersects a layer of melting hydrometeors. Radar reflectivity is related to rainfall through a power law equation and so this enhanced region can lead to overestimations of rainfall by a factor of up to 5, so it is important to correct for this. The BB region can be identified by using several techniques including hydrometeor classification and freezing level forecasts from mesoscale meteorological models. Advances in dual-polarisation radar measurements and continued research in the field has led to increased accuracy in the ability to identify the melting snow region. A method proposed by Kitchen et al (1994), a form of which is currently used operationally in the UK, utilises idealised Vertical Profiles of Reflectivity (VPR) to correct for the BB enhancement. A simpler and more computationally efficient method involves the formation of an average VPR from multiple elevations for correction that can still cause a significant decrease in error (Vignal 2000). The purpose of this research is to evaluate a method that relies only on analysis of measurements from an operational C-band polarimetric radar without the need for computationally expensive models. Initial results show that LDR is a strong classifier of melting snow with a high Critical Success Index of 97% when compared to the other variables. An algorithm based on idealised VPRs resulted in the largest decrease in error when BB corrected scans are compared to rain gauges and to lower level scans with a reduction in RMSE of 61% for rain-rate measurements. References Kitchen, M., R. Brown, and A. G. Davies, 1994: Real-time correction of weather radar data for the effects of bright band, range and orographic growth in widespread precipitation. Q.J.R. Meteorol. Soc., 120, 1231-1254. Vignal, B. et al, 2000: Three methods to determine profiles of reflectivity from volumetric radar data to correct precipitation estimates. J. Appl. Meteor., 39(10), 1715-1726.

Assessment of forward head posture in females: observational and photogrammetry methods.

PubMed

Salahzadeh, Zahra; Maroufi, Nader; Ahmadi, Amir; Behtash, Hamid; Razmjoo, Arash; Gohari, Mahmoud; Parnianpour, Mohamad

2014-01-01

There are different methods to assess forward head posture (FHP) but the accuracy and discrimination ability of these methods are not clear. Here, we want to compare three postural angles for FHP assessment and also study the discrimination accuracy of three photogrammetric methods to differentiate groups categorized based on observational method. All Seventy-eight healthy female participants (23 ± 2.63 years), were classified into three groups: moderate-severe FHP, slight FHP and non FHP based on observational postural assessment rules. Applying three photogrammetric methods - craniovertebral angle, head title angle and head position angle - to measure FHP objectively. One - way ANOVA test showed a significant difference in three categorized group's craniovertebral angle (P< 0.05, F=83.07). There was no dramatic difference in head tilt angle and head position angle methods in three groups. According to Linear Discriminate Analysis (LDA) results, the canonical discriminant function (Wilks'Lambda) was 0.311 for craniovertebral angle with 79.5% of cross-validated grouped cases correctly classified. Our results showed that, craniovertebral angle method may discriminate the females with moderate-severe and non FHP more accurate than head position angle and head tilt angle. The photogrammetric method had excellent inter and intra rater reliability to assess the head and cervical posture.

ETHNOPRED: a novel machine learning method for accurate continental and sub-continental ancestry identification and population stratification correction

PubMed Central

2013-01-01

Background Population stratification is a systematic difference in allele frequencies between subpopulations. This can lead to spurious association findings in the case–control genome wide association studies (GWASs) used to identify single nucleotide polymorphisms (SNPs) associated with disease-linked phenotypes. Methods such as self-declared ancestry, ancestry informative markers, genomic control, structured association, and principal component analysis are used to assess and correct population stratification but each has limitations. We provide an alternative technique to address population stratification. Results We propose a novel machine learning method, ETHNOPRED, which uses the genotype and ethnicity data from the HapMap project to learn ensembles of disjoint decision trees, capable of accurately predicting an individual’s continental and sub-continental ancestry. To predict an individual’s continental ancestry, ETHNOPRED produced an ensemble of 3 decision trees involving a total of 10 SNPs, with 10-fold cross validation accuracy of 100% using HapMap II dataset. We extended this model to involve 29 disjoint decision trees over 149 SNPs, and showed that this ensemble has an accuracy of ≥ 99.9%, even if some of those 149 SNP values were missing. On an independent dataset, predominantly of Caucasian origin, our continental classifier showed 96.8% accuracy and improved genomic control’s λ from 1.22 to 1.11. We next used the HapMap III dataset to learn classifiers to distinguish European subpopulations (North-Western vs. Southern), East Asian subpopulations (Chinese vs. Japanese), African subpopulations (Eastern vs. Western), North American subpopulations (European vs. Chinese vs. African vs. Mexican vs. Indian), and Kenyan subpopulations (Luhya vs. Maasai). In these cases, ETHNOPRED produced ensembles of 3, 39, 21, 11, and 25 disjoint decision trees, respectively involving 31, 502, 526, 242 and 271 SNPs, with 10-fold cross validation accuracy of 86.5% ± 2.4%, 95.6% ± 3.9%, 95.6% ± 2.1%, 98.3% ± 2.0%, and 95.9% ± 1.5%. However, ETHNOPRED was unable to produce a classifier that can accurately distinguish Chinese in Beijing vs. Chinese in Denver. Conclusions ETHNOPRED is a novel technique for producing classifiers that can identify an individual’s continental and sub-continental heritage, based on a small number of SNPs. We show that its learned classifiers are simple, cost-efficient, accurate, transparent, flexible, fast, applicable to large scale GWASs, and robust to missing values. PMID:23432980

A sampling bias in identifying children in foster care using Medicaid data.

PubMed

Rubin, David M; Pati, Susmita; Luan, Xianqun; Alessandrini, Evaline A

2005-01-01

Prior research identified foster care children using Medicaid eligibility codes specific to foster care, but it is unknown whether these codes capture all foster care children. To describe the sampling bias in relying on Medicaid eligibility codes to identify foster care children. Using foster care administrative files linked to Medicaid data, we describe the proportion of children whose Medicaid eligibility was correctly encoded as foster child during a 1-year follow-up period following a new episode of foster care. Sampling bias is described by comparing claims in mental health, emergency department (ED), and other ambulatory settings among correctly and incorrectly classified foster care children. Twenty-eight percent of the 5683 sampled children were incorrectly classified in Medicaid eligibility files. In a multivariate logistic regression model, correct classification was associated with duration of foster care (>9 vs <2 months, odds ratio [OR] 7.67, 95% confidence interval [CI] 7.17-7.97), number of placements (>3 vs 1 placement, OR 4.20, 95% CI 3.14-5.64), and placement in a group home among adjudicated dependent children (OR 1.87, 95% CI 1.33-2.63). Compared with incorrectly classified children, correctly classified foster care children were 3 times more likely to use any services, 2 times more likely to visit the ED, 3 times more likely to make ambulatory visits, and 4 times more likely to use mental health care services (P < .001 for all comparisons). Identifying children in foster care using Medicaid eligibility files is prone to sampling bias that over-represents children in foster care who use more services.

Using Statistical Techniques and Web Search to Correct ESL Errors

ERIC Educational Resources Information Center

Gamon, Michael; Leacock, Claudia; Brockett, Chris; Dolan, William B.; Gao, Jianfeng; Belenko, Dmitriy; Klementiev, Alexandre

2009-01-01

In this paper we present a system for automatic correction of errors made by learners of English. The system has two novel aspects. First, machine-learned classifiers trained on large amounts of native data and a very large language model are combined to optimize the precision of suggested corrections. Second, the user can access real-life web…

CASAnova: a multiclass support vector machine model for the classification of human sperm motility patterns.

PubMed

Goodson, Summer G; White, Sarah; Stevans, Alicia M; Bhat, Sanjana; Kao, Chia-Yu; Jaworski, Scott; Marlowe, Tamara R; Kohlmeier, Martin; McMillan, Leonard; Zeisel, Steven H; O'Brien, Deborah A

2017-11-01

The ability to accurately monitor alterations in sperm motility is paramount to understanding multiple genetic and biochemical perturbations impacting normal fertilization. Computer-aided sperm analysis (CASA) of human sperm typically reports motile percentage and kinematic parameters at the population level, and uses kinematic gating methods to identify subpopulations such as progressive or hyperactivated sperm. The goal of this study was to develop an automated method that classifies all patterns of human sperm motility during in vitro capacitation following the removal of seminal plasma. We visually classified CASA tracks of 2817 sperm from 18 individuals and used a support vector machine-based decision tree to compute four hyperplanes that separate five classes based on their kinematic parameters. We then developed a web-based program, CASAnova, which applies these equations sequentially to assign a single classification to each motile sperm. Vigorous sperm are classified as progressive, intermediate, or hyperactivated, and nonvigorous sperm as slow or weakly motile. This program correctly classifies sperm motility into one of five classes with an overall accuracy of 89.9%. Application of CASAnova to capacitating sperm populations showed a shift from predominantly linear patterns of motility at initial time points to more vigorous patterns, including hyperactivated motility, as capacitation proceeds. Both intermediate and hyperactivated motility patterns were largely eliminated when sperm were incubated in noncapacitating medium, demonstrating the sensitivity of this method. The five CASAnova classifications are distinctive and reflect kinetic parameters of washed human sperm, providing an accurate, quantitative, and high-throughput method for monitoring alterations in motility. © The Authors 2017. Published by Oxford University Press on behalf of Society for the Study of Reproduction. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.

Depression assessment after traumatic brain injury: an empirically based classification method.

PubMed

Seel, Ronald T; Kreutzer, Jeffrey S

2003-11-01

To describe the patterns of depression in patients with traumatic brain injury (TBI), to evaluate the psychometric properties of the Neurobehavioral Functioning Inventory (NFI) Depression Scale, and to classify empirically NFI Depression Scale scores. Depressive symptoms were characterized by using the NFI Depression Scale, the Beck Depression Inventory (BDI), and the Minnesota Multiphasic Personality Inventory-2 (MMPI-2) Depression Scale. An outpatient clinic within a Traumatic Brain Injury Model Systems center. A demographically diverse sample of 172 outpatients with TBI, evaluated between 1996 and 2000. Not applicable. The NFI, BDI, and MMPI-2 Depression Scale. The Cronbach alpha, analysis of variance, Pearson correlations, and canonical discriminant function analysis were used to examine the psychometric properties of the NFI Depression Scale. Patients with TBI most frequently reported problems with frustration (81%), restlessness (73%), rumination (69%), boredom (66%), and sadness (66%) with the NFI Depression Scale. The percentages of patients classified as depressed with the BDI and the NFI Depression Scale were 37% and 30%, respectively. The Cronbach alpha for the NFI Depression Scale was.93, indicating a high degree of internal consistency. As hypothesized, NFI Depression Scale scores correlated highly with BDI (r=.765) and MMPI-2 Depression Scale T scores (r=.752). The NFI Depression Scale did not correlate significantly with the MMPI-2 Hypomania Scale, thus showing discriminant validity. Normal and clinically depressed BDI scores were most likely to be accurately predicted by the NFI Depression Scale, with 81% and 87% of grouped cases, respectively, correctly classified. Normal and depressed MMPI-2 Depression Scale scores were accurately predicted by the NFI Depression Scale, with 75% and 83% of grouped cases correctly classified, respectively. Patients' NFI Depression Scale scores were mapped to the corresponding BDI categories, and 3 NFI score classifications emerged: minimally depressed (13-28), borderline depressed (29-42), and clinically depressed (43-65). Our study provided further evidence that screening for depression should be a standard component of TBI assessment protocols. Between 30% and 38% of patients with TBI were classified as depressed with the NFI Depression Scale and the BDI, respectively. Our findings also provided empirical evidence that the NFI Depression Scale is a useful tool for classifying postinjury depression.

Automatic identification of inertial sensor placement on human body segments during walking.

PubMed

Weenk, Dirk; van Beijnum, Bert-Jan F; Baten, Chris T M; Hermens, Hermie J; Veltink, Peter H

2013-03-21

Current inertial motion capture systems are rarely used in biomedical applications. The attachment and connection of the sensors with cables is often a complex and time consuming task. Moreover, it is prone to errors, because each sensor has to be attached to a predefined body segment. By using wireless inertial sensors and automatic identification of their positions on the human body, the complexity of the set-up can be reduced and incorrect attachments are avoided.We present a novel method for the automatic identification of inertial sensors on human body segments during walking. This method allows the user to place (wireless) inertial sensors on arbitrary body segments. Next, the user walks for just a few seconds and the segment to which each sensor is attached is identified automatically. Walking data was recorded from ten healthy subjects using an Xsens MVN Biomech system with full-body configuration (17 inertial sensors). Subjects were asked to walk for about 6 seconds at normal walking speed (about 5 km/h). After rotating the sensor data to a global coordinate frame with x-axis in walking direction, y-axis pointing left and z-axis vertical, RMS, mean, and correlation coefficient features were extracted from x-, y- and z-components and magnitudes of the accelerations, angular velocities and angular accelerations. As a classifier, a decision tree based on the C4.5 algorithm was developed using Weka (Waikato Environment for Knowledge Analysis). After testing the algorithm with 10-fold cross-validation using 31 walking trials (involving 527 sensors), 514 sensors were correctly classified (97.5%). When a decision tree for a lower body plus trunk configuration (8 inertial sensors) was trained and tested using 10-fold cross-validation, 100% of the sensors were correctly identified. This decision tree was also tested on walking trials of 7 patients (17 walking trials) after anterior cruciate ligament reconstruction, which also resulted in 100% correct identification, thus illustrating the robustness of the method.

Are differences in leg length predictive of lateral patello-femoral pain?

PubMed

Carlson, Mary; Wilkerson, Jerry

2007-03-01

Lateral patello-femoral pain can shorten an athletic career and generally decrease an individual's physical activity and functional level, such as preventing stair climbing and reducing the ability to rise from a chair. Leg length inequality is associated with patello-femoral pain. A leg length test that best distinguishes the difference between people who have lateral patello-femoral pain and those who do not would have clinical utility. The purpose of the present study was, first, to determine if unilateral, lateral patello-femoral pain was associated with the longer leg when inequality of leg lengths existed and, second, to determine if leg length direct measurement, indirect measurement or quadriceps angle (Q angle) could correctly classify participants according to the presence or absence of patello-femoral pain. The study used an ex post facto, two-group quasi-experimental design. A volunteer sample of 52 participants (14 males, 38 females), ranged in age from 18 to 52 years. Three methods were used to measure leg lengths: palpation meter (PALM) on anterior superior iliac spines (ASIS) while participants maintained centred weight-bearing position on a high resolution pressure mat; tape measurement from ASIS to medial malleolus (supine); tape measurement from ASIS to lateral malleolus (supine). Additionally, Q angle was measured in supine position. Patellar grind test, medial retinacular and lateral patellar palpation screened for patello-femoral pain. Logistic regression analysis determined correctness of membership in painful and non-painful patello-femoral groups. The PALM method of indirect measurement of leg length differences overall correctly classified approximately 83 % of the participants. Tape measure to medial and lateral malleoli as well as Q angle did not yield significant results. The results suggested that the PALM method of measuring leg length differences may have clinical utility in differentiating between patients who are likely to sustain patello-femoral pain syndrome and those who will not.

Segmentation schema for enhancing land cover identification: A case study using Sentinel 2 data

NASA Astrophysics Data System (ADS)

Mongus, Domen; Žalik, Borut

2018-04-01

Land monitoring is performed increasingly using high and medium resolution optical satellites, such as the Sentinel-2. However, optical data is inevitably subjected to the variable operational conditions under which it was acquired. Overlapping of features caused by shadows, soft transitions between shadowed and non-shadowed regions, and temporal variability of the observed land-cover types require radiometric corrections. This study examines a new approach to enhancing the accuracy of land cover identification that resolves this problem. The proposed method constructs an ensemble-type classification model with weak classifiers tuned to the particular operational conditions under which the data was acquired. Iterative segmentation over the learning set is applied for this purpose, where feature space is partitioned according to the likelihood of misclassifications introduced by the classification model. As these are a consequence of overlapping features, such partitioning avoids the need for radiometric corrections of the data, and divides land cover types implicitly into subclasses. As a result, improved performance of all tested classification approaches were measured during the validation that was conducted on Sentinel-2 data. The highest accuracies in terms of F1-scores were achieved using the Naive Bayes Classifier as the weak classifier, while supplementing original spectral signatures with normalised difference vegetation index and texture analysis features, namely, average intensity, contrast, homogeneity, and dissimilarity. In total, an F1-score of nearly 95% was achieved in this way, with F1-scores of each particular land cover type reaching above 90%.

Classification of collected trot, passage and piaffe based on temporal variables.

PubMed

Clayton, H M

1997-05-01

The objective was to determine whether collected trot, passage and piaffe could be distinguished as separate gaits on the basis of temporal variables. Sagittal plane, 60 Hz videotapes of 10 finalists in the dressage competitions at the 1992 Olympic Games were analysed to measure the temporal variables in absolute terms and as percentages of stride duration. Classification was based on analysis of variance, a graphical method and discriminant analysis. Stride duration was sufficient to distinguish collected trot from passage and piaffe in all horses. The analysis of variance showed that the mean values of most variables differed significantly between passage and piaffe. When hindlimb stance percentage was plotted against diagonal advanced placement percentage, some overlap was found between all 3 movements indicating that individual horses could not be classified reliably in this manner. Using hindlimb stance percentage and diagonal advanced placement percentage as input in a discriminant analysis, 80% of the cases were classified correctly, but at least one horse was misclassified in each movement. When the absolute, rather than percentage, values of the 2 variables were used as input in the discriminant analysis, 90% of the cases were correctly classified and the only misclassifications were between passage and piaffe. However, the 2 horses in which piaffe was misclassified as passage were the gold and silver medallists. In general, higher placed horses tended toward longer diagonal advanced placements, especially in collected trot and passage, and shorter hindlimb stance percentages in passage and piaffe.

Construction of a multiple myeloma diagnostic model by magnetic bead-based MALDI-TOF mass spectrometry of serum and pattern recognition software.

PubMed

Wang, Qing-Tao; Li, Yong-Zhe; Liang, Yu-Fang; Hu, Chao-Jun; Zhai, Yu-Hua; Zhao, Guan-Fei; Zhang, Jian; Li, Ning; Ni, An-Ping; Chen, Wen-Ming; Xu, Yang

2009-04-01

A diagnosis of multiple myeloma (MM) is difficult to make on the basis of any single laboratory test result. Accurate diagnosis of MM generally results from a number of costly and invasive laboratory tests and medical procedures. The aim of this work is to find a new, highly specific and sensitive method for MM diagnosis. Serum samples were tested in groups representing MM (n = 54) and non-MM (n = 108). These included a subgroup of 17 plasma cell dyscrasias, a subgroup of 17 reactive plasmacytosis, 5 B cell lymphomas, and 7 other tumors with osseus metastasis, as well as 62 healthy donors as controls. Bioinformatic calculations associated with MM were performed. The decision algorithm, with a panel of three biomarkers, correctly identified 24 of 24 (100%) MM samples and 46 of 49 (93.88%) non-MM samples in the training set. During the masked test for the discriminatory model, 26 of 30 MM patients (sensitivity, 86.67%) were precisely recognized, and all 34 normal donors were successfully classified; patients with reactive plasmacytosis were also correctly classified into the non-MM group, and 11 of the other patients were incorrectly classified as MM. The results suggested that proteomic fingerprint technology combining magnetic beads with MALDI-TOF-MS has the potential for identifying individuals with MM. The biomarker classification model was suitable for preliminary assessment of MM and could potentially serve as a useful tool for MM diagnosis and differentiation diagnosis.

Validation of a new classifier for the automated analysis of the human epidermal growth factor receptor 2 (HER2) gene amplification in breast cancer specimens

PubMed Central

2013-01-01

Amplification of the human epidermal growth factor receptor 2 (HER2) is a prognostic marker for poor clinical outcome and a predictive marker for therapeutic response to targeted therapies in breast cancer patients. With the introduction of anti-HER2 therapies, accurate assessment of HER2 status has become essential. Fluorescence in situ hybridization (FISH) is a widely used technique for the determination of HER2 status in breast cancer. However, the manual signal enumeration is time-consuming. Therefore, several companies like MetaSystem have developed automated image analysis software. Some of these signal enumeration software employ the so called “tile-sampling classifier”, a programming algorithm through which the software quantifies fluorescent signals in images on the basis of square tiles of fixed dimensions. Considering that the size of tile does not always correspond to the size of a single tumor cell nucleus, some users argue that this analysis method might not completely reflect the biology of cells. For that reason, MetaSystems has developed a new classifier which is able to recognize nuclei within tissue sections in order to determine the HER2 amplification status on nuclei basis. We call this new programming algorithm “nuclei-sampling classifier”. In this study, we evaluated the accuracy of the “nuclei-sampling classifier” in determining HER2 gene amplification by FISH in nuclei of breast cancer cells. To this aim, we randomly selected from our cohort 64 breast cancer specimens (32 nonamplified and 32 amplified) and we compared results obtained through manual scoring and through this new classifier. The new classifier automatically recognized individual nuclei. The automated analysis was followed by an optional human correction, during which the user interacted with the software in order to improve the selection of cell nuclei automatically selected. Overall concordance between manual scoring and automated nuclei-sampling analysis was 98.4% (100% for nonamplified cases and 96.9% for amplified cases). However, after human correction, concordance between the two methods was 100%. We conclude that the nuclei-based classifier is a new available tool for automated quantitative HER2 FISH signals analysis in nuclei in breast cancer specimen and it can be used for clinical purposes. PMID:23379971

Application of hidden Markov models to biological data mining: a case study

NASA Astrophysics Data System (ADS)

Yin, Michael M.; Wang, Jason T.

2000-04-01

In this paper we present an example of biological data mining: the detection of splicing junction acceptors in eukaryotic genes. Identification or prediction of transcribed sequences from within genomic DNA has been a major rate-limiting step in the pursuit of genes. Programs currently available are far from being powerful enough to elucidate the gene structure completely. Here we develop a hidden Markov model (HMM) to represent the degeneracy features of splicing junction acceptor sites in eukaryotic genes. The HMM system is fully trained using an expectation maximization (EM) algorithm and the system performance is evaluated using the 10-way cross- validation method. Experimental results show that our HMM system can correctly classify more than 94% of the candidate sequences (including true and false acceptor sites) into right categories. About 90% of the true acceptor sites and 96% of the false acceptor sites in the test data are classified correctly. These results are very promising considering that only the local information in DNA is used. The proposed model will be a very important component of an effective and accurate gene structure detection system currently being developed in our lab.

Support Vector Machine and Artificial Neural Network Models for the Classification of Grapevine Varieties Using a Portable NIR Spectrophotometer.

PubMed

Gutiérrez, Salvador; Tardaguila, Javier; Fernández-Novales, Juan; Diago, María P

2015-01-01

The identification of different grapevine varieties, currently attended using visual ampelometry, DNA analysis and very recently, by hyperspectral analysis under laboratory conditions, is an issue of great importance in the wine industry. This work presents support vector machine and artificial neural network's modelling for grapevine varietal classification from in-field leaf spectroscopy. Modelling was attempted at two scales: site-specific and a global scale. Spectral measurements were obtained on the near-infrared (NIR) spectral range between 1600 to 2400 nm under field conditions in a non-destructive way using a portable spectrophotometer. For the site specific approach, spectra were collected from the adaxial side of 400 individual leaves of 20 grapevine (Vitis vinifera L.) varieties one week after veraison. For the global model, two additional sets of spectra were collected one week before harvest from two different vineyards in another vintage, each one consisting on 48 measurement from individual leaves of six varieties. Several combinations of spectra scatter correction and smoothing filtering were studied. For the training of the models, support vector machines and artificial neural networks were employed using the pre-processed spectra as input and the varieties as the classes of the models. The results from the pre-processing study showed that there was no influence whether using scatter correction or not. Also, a second-degree derivative with a window size of 5 Savitzky-Golay filtering yielded the highest outcomes. For the site-specific model, with 20 classes, the best results from the classifiers thrown an overall score of 87.25% of correctly classified samples. These results were compared under the same conditions with a model trained using partial least squares discriminant analysis, which showed a worse performance in every case. For the global model, a 6-class dataset involving samples from three different vineyards, two years and leaves monitored at post-veraison and harvest was also built up, reaching a 77.08% of correctly classified samples. The outcomes obtained demonstrate the capability of using a reliable method for fast, in-field, non-destructive grapevine varietal classification that could be very useful in viticulture and wine industry, either global or site-specific.

A False Alarm Reduction Method for a Gas Sensor Based Electronic Nose

PubMed Central

Rahman, Mohammad Mizanur; Suksompong, Prapun; Toochinda, Pisanu; Taparugssanagorn, Attaphongse

2017-01-01

Electronic noses (E-Noses) are becoming popular for food and fruit quality assessment due to their robustness and repeated usability without fatigue, unlike human experts. An E-Nose equipped with classification algorithms and having open ended classification boundaries such as the k-nearest neighbor (k-NN), support vector machine (SVM), and multilayer perceptron neural network (MLPNN), are found to suffer from false classification errors of irrelevant odor data. To reduce false classification and misclassification errors, and to improve correct rejection performance; algorithms with a hyperspheric boundary, such as a radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) with a Gaussian activation function in the hidden layer should be used. The simulation results presented in this paper show that GRNN has more correct classification efficiency and false alarm reduction capability compared to RBFNN. As the design of a GRNN and RBFNN is complex and expensive due to large numbers of neuron requirements, a simple hyperspheric classification method based on minimum, maximum, and mean (MMM) values of each class of the training dataset was presented. The MMM algorithm was simple and found to be fast and efficient in correctly classifying data of training classes, and correctly rejecting data of extraneous odors, and thereby reduced false alarms. PMID:28895910

A False Alarm Reduction Method for a Gas Sensor Based Electronic Nose.

PubMed

Rahman, Mohammad Mizanur; Charoenlarpnopparut, Chalie; Suksompong, Prapun; Toochinda, Pisanu; Taparugssanagorn, Attaphongse

2017-09-12

Electronic noses (E-Noses) are becoming popular for food and fruit quality assessment due to their robustness and repeated usability without fatigue, unlike human experts. An E-Nose equipped with classification algorithms and having open ended classification boundaries such as the k -nearest neighbor ( k -NN), support vector machine (SVM), and multilayer perceptron neural network (MLPNN), are found to suffer from false classification errors of irrelevant odor data. To reduce false classification and misclassification errors, and to improve correct rejection performance; algorithms with a hyperspheric boundary, such as a radial basis function neural network (RBFNN) and generalized regression neural network (GRNN) with a Gaussian activation function in the hidden layer should be used. The simulation results presented in this paper show that GRNN has more correct classification efficiency and false alarm reduction capability compared to RBFNN. As the design of a GRNN and RBFNN is complex and expensive due to large numbers of neuron requirements, a simple hyperspheric classification method based on minimum, maximum, and mean (MMM) values of each class of the training dataset was presented. The MMM algorithm was simple and found to be fast and efficient in correctly classifying data of training classes, and correctly rejecting data of extraneous odors, and thereby reduced false alarms.

Active Learning with Irrelevant Examples

NASA Technical Reports Server (NTRS)

Wagstaff, Kiri; Mazzoni, Dominic

2009-01-01

An improved active learning method has been devised for training data classifiers. One example of a data classifier is the algorithm used by the United States Postal Service since the 1960s to recognize scans of handwritten digits for processing zip codes. Active learning algorithms enable rapid training with minimal investment of time on the part of human experts to provide training examples consisting of correctly classified (labeled) input data. They function by identifying which examples would be most profitable for a human expert to label. The goal is to maximize classifier accuracy while minimizing the number of examples the expert must label. Although there are several well-established methods for active learning, they may not operate well when irrelevant examples are present in the data set. That is, they may select an item for labeling that the expert simply cannot assign to any of the valid classes. In the context of classifying handwritten digits, the irrelevant items may include stray marks, smudges, and mis-scans. Querying the expert about these items results in wasted time or erroneous labels, if the expert is forced to assign the item to one of the valid classes. In contrast, the new algorithm provides a specific mechanism for avoiding querying the irrelevant items. This algorithm has two components: an active learner (which could be a conventional active learning algorithm) and a relevance classifier. The combination of these components yields a method, denoted Relevance Bias, that enables the active learner to avoid querying irrelevant data so as to increase its learning rate and efficiency when irrelevant items are present. The algorithm collects irrelevant data in a set of rejected examples, then trains the relevance classifier to distinguish between labeled (relevant) training examples and the rejected ones. The active learner combines its ranking of the items with the probability that they are relevant to yield a final decision about which item to present to the expert for labeling. Experiments on several data sets have demonstrated that the Relevance Bias approach significantly decreases the number of irrelevant items queried and also accelerates learning speed.

Diagnostic Accuracy and Cost-Effectiveness of Alternative Methods for Detection of Soil-Transmitted Helminths in a Post-Treatment Setting in Western Kenya

PubMed Central

Kepha, Stella; Kihara, Jimmy H.; Njenga, Sammy M.; Pullan, Rachel L.; Brooker, Simon J.

2014-01-01

Objectives This study evaluates the diagnostic accuracy and cost-effectiveness of the Kato-Katz and Mini-FLOTAC methods for detection of soil-transmitted helminths (STH) in a post-treatment setting in western Kenya. A cost analysis also explores the cost implications of collecting samples during school surveys when compared to household surveys. Methods Stool samples were collected from children (n = 652) attending 18 schools in Bungoma County and diagnosed by the Kato-Katz and Mini-FLOTAC coprological methods. Sensitivity and additional diagnostic performance measures were analyzed using Bayesian latent class modeling. Financial and economic costs were calculated for all survey and diagnostic activities, and cost per child tested, cost per case detected and cost per STH infection correctly classified were estimated. A sensitivity analysis was conducted to assess the impact of various survey parameters on cost estimates. Results Both diagnostic methods exhibited comparable sensitivity for detection of any STH species over single and consecutive day sampling: 52.0% for single day Kato-Katz; 49.1% for single-day Mini-FLOTAC; 76.9% for consecutive day Kato-Katz; and 74.1% for consecutive day Mini-FLOTAC. Diagnostic performance did not differ significantly between methods for the different STH species. Use of Kato-Katz with school-based sampling was the lowest cost scenario for cost per child tested ($10.14) and cost per case correctly classified ($12.84). Cost per case detected was lowest for Kato-Katz used in community-based sampling ($128.24). Sensitivity analysis revealed the cost of case detection for any STH decreased non-linearly as prevalence rates increased and was influenced by the number of samples collected. Conclusions The Kato-Katz method was comparable in diagnostic sensitivity to the Mini-FLOTAC method, but afforded greater cost-effectiveness. Future work is required to evaluate the cost-effectiveness of STH surveillance in different settings. PMID:24810593

Adaptive sleep-wake discrimination for wearable devices.

PubMed

Karlen, Walter; Floreano, Dario

2011-04-01

Sleep/wake classification systems that rely on physiological signals suffer from intersubject differences that make accurate classification with a single, subject-independent model difficult. To overcome the limitations of intersubject variability, we suggest a novel online adaptation technique that updates the sleep/wake classifier in real time. The objective of the present study was to evaluate the performance of a newly developed adaptive classification algorithm that was embedded on a wearable sleep/wake classification system called SleePic. The algorithm processed ECG and respiratory effort signals for the classification task and applied behavioral measurements (obtained from accelerometer and press-button data) for the automatic adaptation task. When trained as a subject-independent classifier algorithm, the SleePic device was only able to correctly classify 74.94 ± 6.76% of the human-rated sleep/wake data. By using the suggested automatic adaptation method, the mean classification accuracy could be significantly improved to 92.98 ± 3.19%. A subject-independent classifier based on activity data only showed a comparable accuracy of 90.44 ± 3.57%. We demonstrated that subject-independent models used for online sleep-wake classification can successfully be adapted to previously unseen subjects without the intervention of human experts or off-line calibration.

Automated computer-based detection of encounter behaviours in groups of honeybees.

PubMed

Blut, Christina; Crespi, Alessandro; Mersch, Danielle; Keller, Laurent; Zhao, Linlin; Kollmann, Markus; Schellscheidt, Benjamin; Fülber, Carsten; Beye, Martin

2017-12-15

Honeybees form societies in which thousands of members integrate their behaviours to act as a single functional unit. We have little knowledge on how the collaborative features are regulated by workers' activities because we lack methods that enable collection of simultaneous and continuous behavioural information for each worker bee. In this study, we introduce the Bee Behavioral Annotation System (BBAS), which enables the automated detection of bees' behaviours in small observation hives. Continuous information on position and orientation were obtained by marking worker bees with 2D barcodes in a small observation hive. We computed behavioural and social features from the tracking information to train a behaviour classifier for encounter behaviours (interaction of workers via antennation) using a machine learning-based system. The classifier correctly detected 93% of the encounter behaviours in a group of bees, whereas 13% of the falsely classified behaviours were unrelated to encounter behaviours. The possibility of building accurate classifiers for automatically annotating behaviours may allow for the examination of individual behaviours of worker bees in the social environments of small observation hives. We envisage that BBAS will be a powerful tool for detecting the effects of experimental manipulation of social attributes and sub-lethal effects of pesticides on behaviour.

A semi-automatic method for quantification and classification of erythrocytes infected with malaria parasites in microscopic images.

PubMed

Díaz, Gloria; González, Fabio A; Romero, Eduardo

2009-04-01

Visual quantification of parasitemia in thin blood films is a very tedious, subjective and time-consuming task. This study presents an original method for quantification and classification of erythrocytes in stained thin blood films infected with Plasmodium falciparum. The proposed approach is composed of three main phases: a preprocessing step, which corrects luminance differences. A segmentation step that uses the normalized RGB color space for classifying pixels either as erythrocyte or background followed by an Inclusion-Tree representation that structures the pixel information into objects, from which erythrocytes are found. Finally, a two step classification process identifies infected erythrocytes and differentiates the infection stage, using a trained bank of classifiers. Additionally, user intervention is allowed when the approach cannot make a proper decision. Four hundred fifty malaria images were used for training and evaluating the method. Automatic identification of infected erythrocytes showed a specificity of 99.7% and a sensitivity of 94%. The infection stage was determined with an average sensitivity of 78.8% and average specificity of 91.2%.

Joint Probabilistic Reasoning About Coreference and Relations of Univeral Schema

DTIC Science & Technology

2017-10-01

containing Barack and Michelle Obama state that they are married. A variety of one - shot and iterative methods have addressed the alignment problem [25...speed. Most of the computation time for these linear models is spent on the dot-product between the sparse features of an example and the weights...of the model. In some cases , it is clear that the use of all of these features is excessive and the example can be correctly classified without such

Automated spike sorting algorithm based on Laplacian eigenmaps and k-means clustering.

PubMed

Chah, E; Hok, V; Della-Chiesa, A; Miller, J J H; O'Mara, S M; Reilly, R B

2011-02-01

This study presents a new automatic spike sorting method based on feature extraction by Laplacian eigenmaps combined with k-means clustering. The performance of the proposed method was compared against previously reported algorithms such as principal component analysis (PCA) and amplitude-based feature extraction. Two types of classifier (namely k-means and classification expectation-maximization) were incorporated within the spike sorting algorithms, in order to find a suitable classifier for the feature sets. Simulated data sets and in-vivo tetrode multichannel recordings were employed to assess the performance of the spike sorting algorithms. The results show that the proposed algorithm yields significantly improved performance with mean sorting accuracy of 73% and sorting error of 10% compared to PCA which combined with k-means had a sorting accuracy of 58% and sorting error of 10%.A correction was made to this article on 22 February 2011. The spacing of the title was amended on the abstract page. No changes were made to the article PDF and the print version was unaffected.

Using the Center for Epidemiologic Studies Depression Scale to Screen for Depression in Systemic Lupus Erythematosus

PubMed Central

Julian, Laura J.; Gregorich, Steven E.; Tonner, Chris; Yazdany, Jinoos; Trupin, Laura; Criswell, Lindsey A.; Yelin, ED; Katz, Patricia P.

2013-01-01

Objective Identifying persons with systemic lupus erythematosus (SLE) at risk for depression would facilitate the identification and treatment of an important comorbidity conferring additional risk for poor outcomes. The purpose of this study was to determine the utility of a brief screening measure, the Center for Epidemiologic Studies Depression Scale (CES-D), in detecting mood disorders in persons with SLE. Methods This cross-sectional study examined 150 persons with SLE. Screening cut points were empirically derived using threshold selection methods, and receiver operating characteristic curves were estimated. The empirically derived cut points of the CES-D were used as the screening measures and were compared to other commonly used CES-D cut points in addition to other commonly used methods to screen for depression. Diagnoses of major depressive disorder or other mood disorders were determined using a “gold standard” structured clinical interview. Results Of the 150 persons with SLE, 26% of subjects met criteria for any mood disorder and 17% met criteria for major depressive disorder. Optimal threshold estimations suggested a CES-D cut score of 24 and above, which yielded adequate sensitivity and specificity in detecting major depressive disorder (88% and 93%, respectively) and correctly classified 92% of participants. To detect the presence of any mood disorder, a cut score of 20 and above was suggested, yielding sensitivity and specificity of 87% and correctly classifying 87%. Conclusion These results suggest the CES-D may be a useful screening measure to identify patients at risk for depression. PMID:21312347

A theory of fine structure image models with an application to detection and classification of dementia

PubMed Central

Penn, Richard; Werner, Michael; Thomas, Justin

2015-01-01

Background Estimation of stochastic process models from data is a common application of time series analysis methods. Such system identification processes are often cast as hypothesis testing exercises whose intent is to estimate model parameters and test them for statistical significance. Ordinary least squares (OLS) regression and the Levenberg-Marquardt algorithm (LMA) have proven invaluable computational tools for models being described by non-homogeneous, linear, stationary, ordinary differential equations. Methods In this paper we extend stochastic model identification to linear, stationary, partial differential equations in two independent variables (2D) and show that OLS and LMA apply equally well to these systems. The method employs an original nonparametric statistic as a test for the significance of estimated parameters. Results We show gray scale and color images are special cases of 2D systems satisfying a particular autoregressive partial difference equation which estimates an analogous partial differential equation. Several applications to medical image modeling and classification illustrate the method by correctly classifying demented and normal OLS models of axial magnetic resonance brain scans according to subject Mini Mental State Exam (MMSE) scores. Comparison with 13 image classifiers from the literature indicates our classifier is at least 14 times faster than any of them and has a classification accuracy better than all but one. Conclusions Our modeling method applies to any linear, stationary, partial differential equation and the method is readily extended to 3D whole-organ systems. Further, in addition to being a robust image classifier, estimated image models offer insights into which parameters carry the most diagnostic image information and thereby suggest finer divisions could be made within a class. Image models can be estimated in milliseconds which translate to whole-organ models in seconds; such runtimes could make real-time medicine and surgery modeling possible. PMID:26029638

A new integrated dual time-point amyloid PET/MRI data analysis method.

PubMed

Cecchin, Diego; Barthel, Henryk; Poggiali, Davide; Cagnin, Annachiara; Tiepolt, Solveig; Zucchetta, Pietro; Turco, Paolo; Gallo, Paolo; Frigo, Anna Chiara; Sabri, Osama; Bui, Franco

2017-11-01

In the initial evaluation of patients with suspected dementia and Alzheimer's disease, there is no consensus on how to perform semiquantification of amyloid in such a way that it: (1) facilitates visual qualitative interpretation, (2) takes the kinetic behaviour of the tracer into consideration particularly with regard to at least partially correcting for blood flow dependence, (3) analyses the amyloid load based on accurate parcellation of cortical and subcortical areas, (4) includes partial volume effect correction (PVEC), (5) includes MRI-derived topographical indexes, (6) enables application to PET/MRI images and PET/CT images with separately acquired MR images, and (7) allows automation. A method with all of these characteristics was retrospectively tested in 86 subjects who underwent amyloid ( 18 F-florbetaben) PET/MRI in a clinical setting (using images acquired 90-110 min after injection, 53 were classified visually as amyloid-negative and 33 as amyloid-positive). Early images after tracer administration were acquired between 0 and 10 min after injection, and later images were acquired between 90 and 110 min after injection. PVEC of the PET data was carried out using the geometric transfer matrix method. Parametric images and some regional output parameters, including two innovative "dual time-point" indexes, were obtained. Subjects classified visually as amyloid-positive showed a sparse tracer uptake in the primary sensory, motor and visual areas in accordance with the isocortical stage of the topographic distribution of the amyloid plaque (Braak stages V/VI). In patients classified visually as amyloid-negative, the method revealed detectable levels of tracer uptake in the basal portions of the frontal and temporal lobes, areas that are known to be sites of early deposition of amyloid plaques that probably represented early accumulation (Braak stage A) that is typical of normal ageing. There was a strong correlation between age and the indexes of the new dual time-point amyloid imaging method in amyloid-negative patients. The method can be considered a valuable tool in both routine clinical practice and in the research setting as it will standardize data regarding amyloid deposition. It could potentially also be used to identify early amyloid plaque deposition in younger subjects in whom treatment could theoretically be more effective.

Diagnostic accuracy and cost-effectiveness of alternative methods for detection of soil-transmitted helminths in a post-treatment setting in western Kenya.

PubMed

Assefa, Liya M; Crellen, Thomas; Kepha, Stella; Kihara, Jimmy H; Njenga, Sammy M; Pullan, Rachel L; Brooker, Simon J

2014-05-01

This study evaluates the diagnostic accuracy and cost-effectiveness of the Kato-Katz and Mini-FLOTAC methods for detection of soil-transmitted helminths (STH) in a post-treatment setting in western Kenya. A cost analysis also explores the cost implications of collecting samples during school surveys when compared to household surveys. Stool samples were collected from children (n = 652) attending 18 schools in Bungoma County and diagnosed by the Kato-Katz and Mini-FLOTAC coprological methods. Sensitivity and additional diagnostic performance measures were analyzed using Bayesian latent class modeling. Financial and economic costs were calculated for all survey and diagnostic activities, and cost per child tested, cost per case detected and cost per STH infection correctly classified were estimated. A sensitivity analysis was conducted to assess the impact of various survey parameters on cost estimates. Both diagnostic methods exhibited comparable sensitivity for detection of any STH species over single and consecutive day sampling: 52.0% for single day Kato-Katz; 49.1% for single-day Mini-FLOTAC; 76.9% for consecutive day Kato-Katz; and 74.1% for consecutive day Mini-FLOTAC. Diagnostic performance did not differ significantly between methods for the different STH species. Use of Kato-Katz with school-based sampling was the lowest cost scenario for cost per child tested ($10.14) and cost per case correctly classified ($12.84). Cost per case detected was lowest for Kato-Katz used in community-based sampling ($128.24). Sensitivity analysis revealed the cost of case detection for any STH decreased non-linearly as prevalence rates increased and was influenced by the number of samples collected. The Kato-Katz method was comparable in diagnostic sensitivity to the Mini-FLOTAC method, but afforded greater cost-effectiveness. Future work is required to evaluate the cost-effectiveness of STH surveillance in different settings.

Single Versus Multiple Events Error Potential Detection in a BCI-Controlled Car Game With Continuous and Discrete Feedback.

PubMed

Kreilinger, Alex; Hiebel, Hannah; Müller-Putz, Gernot R

2016-03-01

This work aimed to find and evaluate a new method for detecting errors in continuous brain-computer interface (BCI) applications. Instead of classifying errors on a single-trial basis, the new method was based on multiple events (MEs) analysis to increase the accuracy of error detection. In a BCI-driven car game, based on motor imagery (MI), discrete events were triggered whenever subjects collided with coins and/or barriers. Coins counted as correct events, whereas barriers were errors. This new method, termed ME method, combined and averaged the classification results of single events (SEs) and determined the correctness of MI trials, which consisted of event sequences instead of SEs. The benefit of this method was evaluated in an offline simulation. In an online experiment, the new method was used to detect erroneous MI trials. Such MI trials were discarded and could be repeated by the users. We found that, even with low SE error potential (ErrP) detection rates, feasible accuracies can be achieved when combining MEs to distinguish erroneous from correct MI trials. Online, all subjects reached higher scores with error detection than without, at the cost of longer times needed for completing the game. Findings suggest that ErrP detection may become a reliable tool for monitoring continuous states in BCI applications when combining MEs. This paper demonstrates a novel technique for detecting errors in online continuous BCI applications, which yields promising results even with low single-trial detection rates.

Diagnosis of Chronic Kidney Disease Based on Support Vector Machine by Feature Selection Methods.

PubMed

Polat, Huseyin; Danaei Mehr, Homay; Cetin, Aydin

2017-04-01

As Chronic Kidney Disease progresses slowly, early detection and effective treatment are the only cure to reduce the mortality rate. Machine learning techniques are gaining significance in medical diagnosis because of their classification ability with high accuracy rates. The accuracy of classification algorithms depend on the use of correct feature selection algorithms to reduce the dimension of datasets. In this study, Support Vector Machine classification algorithm was used to diagnose Chronic Kidney Disease. To diagnose the Chronic Kidney Disease, two essential types of feature selection methods namely, wrapper and filter approaches were chosen to reduce the dimension of Chronic Kidney Disease dataset. In wrapper approach, classifier subset evaluator with greedy stepwise search engine and wrapper subset evaluator with the Best First search engine were used. In filter approach, correlation feature selection subset evaluator with greedy stepwise search engine and filtered subset evaluator with the Best First search engine were used. The results showed that the Support Vector Machine classifier by using filtered subset evaluator with the Best First search engine feature selection method has higher accuracy rate (98.5%) in the diagnosis of Chronic Kidney Disease compared to other selected methods.

Memory Alteration Test to Detect Amnestic Mild Cognitive Impairment and Early Alzheimer’s Dementia in Population with Low Educational Level

PubMed Central

Custodio, Nilton; Lira, David; Herrera-Perez, Eder; Montesinos, Rosa; Castro-Suarez, Sheila; Cuenca-Alfaro, José; Valeriano-Lorenzo, Lucía

2017-01-01

Background/Aims: Short tests to early detection of the cognitive impairment are necessary in primary care setting, particularly in populations with low educational level. The aim of this study was to assess the performance of Memory Alteration Test (M@T) to discriminate controls, patients with amnestic Mild Cognitive Impairment (aMCI) and patients with early Alzheimer’s Dementia (AD) in a sample of individuals with low level of education. Methods: Cross-sectional study to assess the performance of the M@T (study test), compared to the neuropsychological evaluation (gold standard test) scores in 247 elderly subjects with low education level from Lima-Peru. The cognitive evaluation included three sequential stages: (1) screening (to detect cases with cognitive impairment); (2) nosological diagnosis (to determinate specific disease); and (3) classification (to differentiate disease subtypes). The subjects with negative results for all stages were considered as cognitively normal (controls). The test performance was assessed by means of area under the receiver operating characteristic (ROC) curve. We calculated validity measures (sensitivity, specificity and correctly classified percentage), the internal consistency (Cronbach’s alpha coefficient), and concurrent validity (Pearson’s ratio coefficient between the M@T and Clinical Dementia Rating (CDR) scores). Results: The Cronbach’s alpha coefficient was 0.79 and Pearson’s ratio coefficient was 0.79 (p < 0.01). The AUC of M@T to discriminate between early AD and aMCI was 99.60% (sensitivity = 100.00%, specificity = 97.53% and correctly classified = 98.41%) and to discriminate between aMCI and controls was 99.56% (sensitivity = 99.17%, specificity = 91.11%, and correctly classified = 96.99%). Conclusions: The M@T is a short test with a good performance to discriminate controls, aMCI and early AD in individuals with low level of education from urban settings. PMID:28878665

A Study on the Validity of a Computer-Based Game to Assess Cognitive Processes, Reward Mechanisms, and Time Perception in Children Aged 4-8 Years

PubMed Central

Hurks, Petra PM; Aldenkamp, Albert P; van der Spek, Erik D; Rauterberg, GWM; Vles, Johan SH; Hendriksen, Jos GM

2016-01-01

Background A computer-based game, named Timo’s Adventure, was developed to assess specific cognitive functions (eg, attention, planning, and working memory), time perception, and reward mechanisms in young school-aged children. The game consists of 6 mini-games embedded in a story line and includes fantasy elements to enhance motivation. Objective The aim of this study was to investigate the validity of Timo’s Adventure in normally developing children and in children with attention-deficit/hyperactivity disorder (ADHD). Methods A total of 96 normally developing children aged 4-8 years and 40 children with ADHD were assessed using the game. Clinical validity was investigated by examining the effects of age on performances within the normally developing children, as well as performance differences between the healthy controls and the ADHD group. Results Our analyses in the normally developing children showed developmental effects; that is, older children made fewer inhibition mistakes (r=−.33, P=.001), had faster (and therefore better) reaction times (r=−.49, P<.001), and were able to produce time intervals more accurately than younger children (ρ=.35, P<.001). Discriminant analysis showed that Timo’s Adventure was accurate in most classifications whether a child belonged to the ADHD group or the normally developing group: 78% (76/97) of the children were correctly classified as having ADHD or as being in the normally developing group. The classification results showed that 72% (41/57) children in the control group were correctly classified, and 88% (35/40) of the children in the ADHD group were correctly classified as having ADHD. Sensitivity (0.89) and specificity (0.69) of Timo’s Adventure were satisfying. Conclusions Computer-based games seem to be a valid tool to assess specific strengths and weaknesses in young children with ADHD. PMID:27658428

Proteomics-Derived Cerebrospinal Fluid Markers of Autopsy-Confirmed Alzheimer’s Disease

PubMed Central

Roher, Alex E.; Maarouf, Chera L.; Sue, Lucia I.; Hu, Yiran; Wilson, Jeffrey; Beach, Thomas G.

2010-01-01

The diagnostic performance of several candidate cerebrospinal fluid (CSF) protein biomarkers of neuropathologically-confirmed Alzheimer’s disease (AD), non-demented (ND) elderly controls and non-AD dementias (NADD) was assessed. Candidate markers were selected on the basis of initial 2-dimensional gel electrophoresis studies or by literature review. Markers selected by the former method included apolipoprotein A-1 (ApoA1), hemopexin (HPX), transthyretin (TTR) and pigment epithelium-derived factor (PEDF) while markers identified from the literature included Aβ1–40, Aβ1–42, total tau, phosphorylated tau, α-1 acid glycoprotein (A1GP), haptoglobin, zinc α-2 glycoprotein (Z2GP) and apolipoprotein E (ApoE). Ventricular CSF concentrations of the markers were measured by ELISA. The concentrations of Aβ1–42, ApoA1, A1GP, ApoE, HPX and Z2GP differed significantly among AD, ND and NADD subjects. Logistic regression analysis for the diagnostic discrimination of AD from ND found that Aβ1–42, ApoA1 and HPX each had significant and independent associations with diagnosis. The CSF concentrations of these three markers distinguished AD from ND subjects with 84% sensitivity and 72% specificity, with 78% of subjects correctly classified. By comparison, using Aβ1–42 alone gave 79% sensitivity and 61% specificity, with 68% of subjects correctly classified. For the diagnostic discrimination of AD from NADD, only the concentration of Aβ1–42 was significantly related to diagnosis, with a sensitivity of 58%, specificity of 86% and 86% correctly classified. The results indicate that for the discrimination of AD from ND control subjects, measurement of a set of markers including Aβ1–42, ApoA1 and HPX improved diagnostic performance over that obtained by measurement of Aβ1–42 alone. For the discrimination of AD from NADD subjects, measurement of Aβ1–42 alone was superior. PMID:19863188

Extending the Functionality of Behavioural Change-Point Analysis with k-Means Clustering: A Case Study with the Little Penguin (Eudyptula minor)

PubMed Central

Zhang, Jingjing; Dennis, Todd E.

2015-01-01

We present a simple framework for classifying mutually exclusive behavioural states within the geospatial lifelines of animals. This method involves use of three sequentially applied statistical procedures: (1) behavioural change point analysis to partition movement trajectories into discrete bouts of same-state behaviours, based on abrupt changes in the spatio-temporal autocorrelation structure of movement parameters; (2) hierarchical multivariate cluster analysis to determine the number of different behavioural states; and (3) k-means clustering to classify inferred bouts of same-state location observations into behavioural modes. We demonstrate application of the method by analysing synthetic trajectories of known ‘artificial behaviours’ comprised of different correlated random walks, as well as real foraging trajectories of little penguins (Eudyptula minor) obtained by global-positioning-system telemetry. Our results show that the modelling procedure correctly classified 92.5% of all individual location observations in the synthetic trajectories, demonstrating reasonable ability to successfully discriminate behavioural modes. Most individual little penguins were found to exhibit three unique behavioural states (resting, commuting/active searching, area-restricted foraging), with variation in the timing and locations of observations apparently related to ambient light, bathymetry, and proximity to coastlines and river mouths. Addition of k-means clustering extends the utility of behavioural change point analysis, by providing a simple means through which the behaviours inferred for the location observations comprising individual movement trajectories can be objectively classified. PMID:25922935

Extending the Functionality of Behavioural Change-Point Analysis with k-Means Clustering: A Case Study with the Little Penguin (Eudyptula minor).

PubMed

Zhang, Jingjing; O'Reilly, Kathleen M; Perry, George L W; Taylor, Graeme A; Dennis, Todd E

2015-01-01

We present a simple framework for classifying mutually exclusive behavioural states within the geospatial lifelines of animals. This method involves use of three sequentially applied statistical procedures: (1) behavioural change point analysis to partition movement trajectories into discrete bouts of same-state behaviours, based on abrupt changes in the spatio-temporal autocorrelation structure of movement parameters; (2) hierarchical multivariate cluster analysis to determine the number of different behavioural states; and (3) k-means clustering to classify inferred bouts of same-state location observations into behavioural modes. We demonstrate application of the method by analysing synthetic trajectories of known 'artificial behaviours' comprised of different correlated random walks, as well as real foraging trajectories of little penguins (Eudyptula minor) obtained by global-positioning-system telemetry. Our results show that the modelling procedure correctly classified 92.5% of all individual location observations in the synthetic trajectories, demonstrating reasonable ability to successfully discriminate behavioural modes. Most individual little penguins were found to exhibit three unique behavioural states (resting, commuting/active searching, area-restricted foraging), with variation in the timing and locations of observations apparently related to ambient light, bathymetry, and proximity to coastlines and river mouths. Addition of k-means clustering extends the utility of behavioural change point analysis, by providing a simple means through which the behaviours inferred for the location observations comprising individual movement trajectories can be objectively classified.

Automatic staging of bladder cancer on CT urography

NASA Astrophysics Data System (ADS)

Garapati, Sankeerth S.; Hadjiiski, Lubomir M.; Cha, Kenny H.; Chan, Heang-Ping; Caoili, Elaine M.; Cohan, Richard H.; Weizer, Alon; Alva, Ajjai; Paramagul, Chintana; Wei, Jun; Zhou, Chuan

2016-03-01

Correct staging of bladder cancer is crucial for the decision of neoadjuvant chemotherapy treatment and minimizing the risk of under- or over-treatment. Subjectivity and variability of clinicians in utilizing available diagnostic information may lead to inaccuracy in staging bladder cancer. An objective decision support system that merges the information in a predictive model based on statistical outcomes of previous cases and machine learning may assist clinicians in making more accurate and consistent staging assessments. In this study, we developed a preliminary method to stage bladder cancer. With IRB approval, 42 bladder cancer cases with CTU scans were collected from patient files. The cases were classified into two classes based on pathological stage T2, which is the decision threshold for neoadjuvant chemotherapy treatment (i.e. for stage >=T2) clinically. There were 21 cancers below stage T2 and 21 cancers at stage T2 or above. All 42 lesions were automatically segmented using our auto-initialized cascaded level sets (AI-CALS) method. Morphological features were extracted, which were selected and merged by linear discriminant analysis (LDA) classifier. A leave-one-case-out resampling scheme was used to train and test the classifier using the 42 lesions. The classification accuracy was quantified using the area under the ROC curve (Az). The average training Az was 0.97 and the test Az was 0.85. The classifier consistently selected the lesion volume, a gray level feature and a contrast feature. This predictive model shows promise for assisting in assessing the bladder cancer stage.

Validation of a short food frequency questionnaire to assess calcium intake in children aged 3 to 6 years.

PubMed

Taylor, R W; Goulding, A

1998-06-01

To assess the validity of a short calcium food frequency questionnaire (FFQ) for use in young children. Calcium intake from an estimated 4 d diet record (4DDR) was compared with the calcium intake from a 35 item FFQ specifically designed to assess habitual calcium intake and previously validated for adult women. Forty-one girls and 26 boys aged 3-6 y recruited by advertisement for studies of nutrition and bone health. Mean (s.d.) calcium intakes were 798 mg (271) and 942 mg (419) for the 4DDR and FFQ respectively, (r = 0.52). Mean difference (s.d. of difference) in calcium intake between the two methods was 144 mg (355), showing that the FFQ may estimate calcium intakes 565 mg below to 854 mg above diet record values. 84% of subjects when classified by the 4DDR fell into the same or adjacent quartiles when classified by the FFQ. Only two subjects were classified in extreme quartiles for the two methods. The FFQ correctly identified 68% of children with recorded intakes less than 800 mg. The short calcium FFQ tended to overestimate actual calcium intakes in young children, and would not be appropriate for determining calcium intake of individuals. However, the FFQ demonstrated good ability to classify subjects into extremes of calcium intake. Moreover, the predictive value of the FFQ in identifying children with intakes below the current recommended intake of 800 mg was reasonably high (79%).

Benthic Habitat Mapping by Combining Lyzenga’s Optical Model and Relative Water Depth Model in Lintea Island, Southeast Sulawesi

NASA Astrophysics Data System (ADS)

Hafizt, M.; Manessa, M. D. M.; Adi, N. S.; Prayudha, B.

2017-12-01

Benthic habitat mapping using satellite data is one challenging task for practitioners and academician as benthic objects are covered by light-attenuating water column obscuring object discrimination. One common method to reduce this water-column effect is by using depth-invariant index (DII) image. However, the application of the correction in shallow coastal areas is challenging as a dark object such as seagrass could have a very low pixel value, preventing its reliable identification and classification. This limitation can be solved by specifically applying a classification process to areas with different water depth levels. The water depth level can be extracted from satellite imagery using Relative Water Depth Index (RWDI). This study proposed a new approach to improve the mapping accuracy, particularly for benthic dark objects by combining the DII of Lyzenga’s water column correction method and the RWDI of Stumpt’s method. This research was conducted in Lintea Island which has a high variation of benthic cover using Sentinel-2A imagery. To assess the effectiveness of the proposed new approach for benthic habitat mapping two different classification procedures are implemented. The first procedure is the commonly applied method in benthic habitat mapping where DII image is used as input data to all coastal area for image classification process regardless of depth variation. The second procedure is the proposed new approach where its initial step begins with the separation of the study area into shallow and deep waters using the RWDI image. Shallow area was then classified using the sunglint-corrected image as input data and the deep area was classified using DII image as input data. The final classification maps of those two areas were merged as a single benthic habitat map. A confusion matrix was then applied to evaluate the mapping accuracy of the final map. The result shows that the new proposed mapping approach can be used to map all benthic objects in all depth ranges and shows a better accuracy compared to that of classification map produced using only with DII.

Classification of jet fuels by fuzzy rule-building expert systems applied to three-way data by fast gas chromatography--fast scanning quadrupole ion trap mass spectrometry.

PubMed

Sun, Xiaobo; Zimmermann, Carolyn M; Jackson, Glen P; Bunker, Christopher E; Harrington, Peter B

2011-01-30

A fast method that can be used to classify unknown jet fuel types or detect possible property changes in jet fuel physical properties is of paramount interest to national defense and the airline industries. While fast gas chromatography (GC) has been used with conventional mass spectrometry (MS) to study jet fuels, fast GC was combined with fast scanning MS and used to classify jet fuels into lot numbers or origin for the first time by using fuzzy rule-building expert system (FuRES) classifiers. In the process of building classifiers, the data were pretreated with and without wavelet transformation and evaluated with respect to performance. Principal component transformation was used to compress the two-way data images prior to classification. Jet fuel samples were successfully classified with 99.8 ± 0.5% accuracy for both with and without wavelet compression. Ten bootstrapped Latin partitions were used to validate the generalized prediction accuracy. Optimized partial least squares (o-PLS) regression results were used as positively biased references for comparing the FuRES prediction results. The prediction results for the jet fuel samples obtained with these two methods were compared statistically. The projected difference resolution (PDR) method was also used to evaluate the fast GC and fast MS data. Two batches of aliquots of ten new samples were prepared and run independently 4 days apart to evaluate the robustness of the method. The only change in classification parameters was the use of polynomial retention time alignment to correct for drift that occurred during the 4-day span of the two collections. FuRES achieved perfect classifications for four models of uncompressed three-way data. This fast GC/fast MS method furnishes characteristics of high speed, accuracy, and robustness. This mode of measurement may be useful as a monitoring tool to track changes in the chemical composition of fuels that may also lead to property changes. Copyright © 2010 Elsevier B.V. All rights reserved.

Application of airborne hyperspectral remote sensing for the retrieval of forest inventory parameters

NASA Astrophysics Data System (ADS)

Dmitriev, Yegor V.; Kozoderov, Vladimir V.; Sokolov, Anton A.

2016-04-01

Collecting and updating forest inventory data play an important part in the forest management. The data can be obtained directly by using exact enough but low efficient ground based methods as well as from the remote sensing measurements. We present applications of airborne hyperspectral remote sensing for the retrieval of such important inventory parameters as the forest species and age composition. The hyperspectral images of the test region were obtained from the airplane equipped by the produced in Russia light-weight airborne video-spectrometer of visible and near infrared spectral range and high resolution photo-camera on the same gyro-stabilized platform. The quality of the thematic processing depends on many factors such as the atmospheric conditions, characteristics of measuring instruments, corrections and preprocessing methods, etc. An important role plays the construction of the classifier together with methods of the reduction of the feature space. The performance of different spectral classification methods is analyzed for the problem of hyperspectral remote sensing of soil and vegetation. For the reduction of the feature space we used the earlier proposed stable feature selection method. The results of the classification of hyperspectral airborne images by using the Multiclass Support Vector Machine method with Gaussian kernel and the parametric Bayesian classifier based on the Gaussian mixture model and their comparative analysis are demonstrated.

Computer-aided diagnosis system: a Bayesian hybrid classification method.

PubMed

Calle-Alonso, F; Pérez, C J; Arias-Nicolás, J P; Martín, J

2013-10-01

A novel method to classify multi-class biomedical objects is presented. The method is based on a hybrid approach which combines pairwise comparison, Bayesian regression and the k-nearest neighbor technique. It can be applied in a fully automatic way or in a relevance feedback framework. In the latter case, the information obtained from both an expert and the automatic classification is iteratively used to improve the results until a certain accuracy level is achieved, then, the learning process is finished and new classifications can be automatically performed. The method has been applied in two biomedical contexts by following the same cross-validation schemes as in the original studies. The first one refers to cancer diagnosis, leading to an accuracy of 77.35% versus 66.37%, originally obtained. The second one considers the diagnosis of pathologies of the vertebral column. The original method achieves accuracies ranging from 76.5% to 96.7%, and from 82.3% to 97.1% in two different cross-validation schemes. Even with no supervision, the proposed method reaches 96.71% and 97.32% in these two cases. By using a supervised framework the achieved accuracy is 97.74%. Furthermore, all abnormal cases were correctly classified. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

Assessing the skeletal age from a hand radiograph: automating the Tanner-Whitehouse method

NASA Astrophysics Data System (ADS)

Niemeijer, Meindert; van Ginneken, Bram; Maas, Casper A.; Beek, Frederik J. A.; Viergever, Max A.

2003-05-01

The skeletal maturity of children is usually assessed from a standard radiograph of the left hand and wrist. An established clinical method to determine the skeletal maturity is the Tanner-Whitehouse (TW2) method. This method divides the skeletal development into several stages (labelled A, B, ...,I). We are developing an automated system based on this method. In this work we focus on assigning a stage to one region of interest (ROI), the middle phalanx of the third finger. We classify each ROI as follows. A number of ROIs which have been assigned a certain stage by a radiologist are used to construct a mean image for that stage. For a new input ROI, landmarks are detected by using an Active Shape Model. These are used to align the mean images with the input image. Subsequently the correlation between each transformed mean stage image and the input is calculated. The input ROI can be assigned to the stage with the highest correlation directly, or the values can be used as features in a classifier. The method was tested on 71 cases ranging from stage E to I. The ROI was staged correctly in 73.2% of all cases and in 97.2% of all incorrectly staged cases the error was not more than one stage.

B1- non-uniformity correction of phased-array coils without measuring coil sensitivity.

PubMed

Damen, Frederick C; Cai, Kejia

2018-04-18

Parallel imaging can be used to increase SNR and shorten acquisition times, albeit, at the cost of image non-uniformity. B 1 - non-uniformity correction techniques are confounded by signal that varies not only due to coil induced B 1 - sensitivity variation, but also the object's own intrinsic signal. Herein, we propose a method that makes minimal assumptions and uses only the coil images themselves to produce a single combined B 1 - non-uniformity-corrected complex image with the highest available SNR. A novel background noise classifier is used to select voxels of sufficient quality to avoid the need for regularization. Unique properties of the magnitude and phase were used to reduce the B 1 - sensitivity to two joint additive models for estimation of the B 1 - inhomogeneity. The complementary corruption of the imaged object across the coil images is used to abate individual coil correction imperfections. Results are presented from two anatomical cases: (a) an abdominal image that is challenging in both extreme B 1 - sensitivity and intrinsic tissue signal variation, and (b) a brain image with moderate B 1 - sensitivity and intrinsic tissue signal variation. A new relative Signal-to-Noise Ratio (rSNR) quality metric is proposed to evaluate the performance of the proposed method and the RF receiving coil array. The proposed method has been shown to be robust to imaged objects with widely inhomogeneous intrinsic signal, and resilient to poorly performing coil elements. Copyright © 2018. Published by Elsevier Inc.

Retinopathy of Prematurity-assist: Novel Software for Detecting Plus Disease

PubMed Central

Pour, Elias Khalili; Pourreza, Hamidreza; Zamani, Kambiz Ameli; Mahmoudi, Alireza; Sadeghi, Arash Mir Mohammad; Shadravan, Mahla; Karkhaneh, Reza; Pour, Ramak Rouhi

2017-01-01

Purpose To design software with a novel algorithm, which analyzes the tortuosity and vascular dilatation in fundal images of retinopathy of prematurity (ROP) patients with an acceptable accuracy for detecting plus disease. Methods Eighty-seven well-focused fundal images taken with RetCam were classified to three groups of plus, non-plus, and pre-plus by agreement between three ROP experts. Automated algorithms in this study were designed based on two methods: the curvature measure and distance transform for assessment of tortuosity and vascular dilatation, respectively as two major parameters of plus disease detection. Results Thirty-eight plus, 12 pre-plus, and 37 non-plus images, which were classified by three experts, were tested by an automated algorithm and software evaluated the correct grouping of images in comparison to expert voting with three different classifiers, k-nearest neighbor, support vector machine and multilayer perceptron network. The plus, pre-plus, and non-plus images were analyzed with 72.3%, 83.7%, and 84.4% accuracy, respectively. Conclusions The new automated algorithm used in this pilot scheme for diagnosis and screening of patients with plus ROP has acceptable accuracy. With more improvements, it may become particularly useful, especially in centers without a skilled person in the ROP field. PMID:29022295

Remembering Left–Right Orientation of Pictures

PubMed Central

Bartlett, James C.; Gernsbacher, Morton Ann; Till, Robert E.

2015-01-01

In a study of recognition memory for pictures, we observed an asymmetry in classifying test items as “same” versus “different” in left–right orientation: Identical copies of previously viewed items were classified more accurately than left–right reversals of those items. Response bias could not explain this asymmetry, and, moreover, correct “same” and “different” classifications were independently manipulable: Whereas repetition of input pictures (one vs. two presentations) affected primarily correct “same” classifications, retention interval (3 hr vs. 1 week) affected primarily correct “different” classifications. In addition, repetition but not retention interval affected judgments that previously seen pictures (both identical and reversed) were “old”. These and additional findings supported a dual-process hypothesis that links “same” classifications to high familiarity, and “different” classifications to conscious sampling of images of previously viewed pictures. PMID:2949051

A neuroimaging study of conflict during word recognition.

PubMed

Riba, Jordi; Heldmann, Marcus; Carreiras, Manuel; Münte, Thomas F

2010-08-04

Using functional magnetic resonance imaging the neural activity associated with error commission and conflict monitoring in a lexical decision task was assessed. In a cohort of 20 native speakers of Spanish conflict was introduced by presenting words with high and low lexical frequency and pseudo-words with high and low syllabic frequency for the first syllable. Erroneous versus correct responses showed activation in the frontomedial and left inferior frontal cortex. A similar pattern was found for correctly classified words of low versus high lexical frequency and for correctly classified pseudo-words of high versus low syllabic frequency. Conflict-related activations for language materials largely overlapped with error-induced activations. The effect of syllabic frequency underscores the role of sublexical processing in visual word recognition and supports the view that the initial syllable mediates between the letter and word level.

Robust parameterization of time-frequency characteristics for recognition of musical genres of Mexican culture

NASA Astrophysics Data System (ADS)

Pérez Rosas, Osvaldo G.; Rivera Martínez, José L.; Maldonado Cano, Luis A.; López Rodríguez, Mario; Amaya Reyes, Laura M.; Cano Martínez, Elizabeth; García Vázquez, Mireya S.; Ramírez Acosta, Alejandro A.

2017-09-01

The automatic identification and classification of musical genres based on the sound similarities to form musical textures, it is a very active investigation area. In this context it has been created recognition systems of musical genres, formed by time-frequency characteristics extraction methods and by classification methods. The selection of this methods are important for a good development in the recognition systems. In this article they are proposed the Mel-Frequency Cepstral Coefficients (MFCC) methods as a characteristic extractor and Support Vector Machines (SVM) as a classifier for our system. The stablished parameters of the MFCC method in the system by our time-frequency analysis, represents the gamma of Mexican culture musical genres in this article. For the precision of a classification system of musical genres it is necessary that the descriptors represent the correct spectrum of each gender; to achieve this we must realize a correct parametrization of the MFCC like the one we present in this article. With the system developed we get satisfactory detection results, where the least identification percentage of musical genres was 66.67% and the one with the most precision was 100%.

Superiority of artificial neural networks for a genetic classification procedure.

PubMed

Sant'Anna, I C; Tomaz, R S; Silva, G N; Nascimento, M; Bhering, L L; Cruz, C D

2015-08-19

The correct classification of individuals is extremely important for the preservation of genetic variability and for maximization of yield in breeding programs using phenotypic traits and genetic markers. The Fisher and Anderson discriminant functions are commonly used multivariate statistical techniques for these situations, which allow for the allocation of an initially unknown individual to predefined groups. However, for higher levels of similarity, such as those found in backcrossed populations, these methods have proven to be inefficient. Recently, much research has been devoted to developing a new paradigm of computing known as artificial neural networks (ANNs), which can be used to solve many statistical problems, including classification problems. The aim of this study was to evaluate the feasibility of ANNs as an evaluation technique of genetic diversity by comparing their performance with that of traditional methods. The discriminant functions were equally ineffective in discriminating the populations, with error rates of 23-82%, thereby preventing the correct discrimination of individuals between populations. The ANN was effective in classifying populations with low and high differentiation, such as those derived from a genetic design established from backcrosses, even in cases of low differentiation of the data sets. The ANN appears to be a promising technique to solve classification problems, since the number of individuals classified incorrectly by the ANN was always lower than that of the discriminant functions. We envisage the potential relevant application of this improved procedure in the genomic classification of markers to distinguish between breeds and accessions.

Three-dimensional geometric morphometric analysis of cranio-facial sexual dimorphism in a Central European sample of known sex.

PubMed

Bigoni, L; Velemínská, J; Brůzek, J

2010-02-01

This article presents an approach for estimating the sexual dimorphism of adult crania using three-dimensional geometric morphometric methods. The study sample consisted of 139 crania of known sex (73 males and 66 females) belonging to persons who lived during the first half of the 20th century in Bohemia. The three-dimensional co-ordinates of 82 ecto-cranial landmarks and 39 semi-landmarks covering the midsagittal curve of the cranial vault were digitised using a MicroScribe G2X contact digitiser. The purposes of the investigation were to define the regions of the cranium where sexual dimorphism is most pronounced and to investigate the effectiveness of this method for determining sex from the shape of the cranium. The results demonstrate that it is better to analyse apportionable parts of the cranium rather than the cranium as a whole. Significant sexual differences (significance was determined using multivariate analysis of variance) were noted in the shape of the midsagittal curve of the vault, upper face, the region of the nose, orbits, and palate. No differences were recorded either in the shape of the cranium as a whole or in the regions of the base and the neurocranium. The greatest accuracy in determining sex was found in the region of the upper face (100% of study subjects correctly classified) and the midsagittal curve of the vault (99% of study subjects correctly classified). Copyright (c) 2010 Elsevier GmbH. All rights reserved.

Embedded feature ranking for ensemble MLP classifiers.

PubMed

Windeatt, Terry; Duangsoithong, Rakkrit; Smith, Raymond

2011-06-01

A feature ranking scheme for multilayer perceptron (MLP) ensembles is proposed, along with a stopping criterion based upon the out-of-bootstrap estimate. To solve multi-class problems feature ranking is combined with modified error-correcting output coding. Experimental results on benchmark data demonstrate the versatility of the MLP base classifier in removing irrelevant features.

Scoring and Classifying Examinees Using Measurement Decision Theory

ERIC Educational Resources Information Center

Rudner, Lawrence M.

2009-01-01

This paper describes and evaluates the use of measurement decision theory (MDT) to classify examinees based on their item response patterns. The model has a simple framework that starts with the conditional probabilities of examinees in each category or mastery state responding correctly to each item. The presented evaluation investigates: (1) the…

The Discovery of Novel Biomarkers Improves Breast Cancer Intrinsic Subtype Prediction and Reconciles the Labels in the METABRIC Data Set

PubMed Central

Milioli, Heloisa Helena; Vimieiro, Renato; Riveros, Carlos; Tishchenko, Inna; Berretta, Regina; Moscato, Pablo

2015-01-01

Background The prediction of breast cancer intrinsic subtypes has been introduced as a valuable strategy to determine patient diagnosis and prognosis, and therapy response. The PAM50 method, based on the expression levels of 50 genes, uses a single sample predictor model to assign subtype labels to samples. Intrinsic errors reported within this assay demonstrate the challenge of identifying and understanding the breast cancer groups. In this study, we aim to: a) identify novel biomarkers for subtype individuation by exploring the competence of a newly proposed method named CM1 score, and b) apply an ensemble learning, as opposed to the use of a single classifier, for sample subtype assignment. The overarching objective is to improve class prediction. Methods and Findings The microarray transcriptome data sets used in this study are: the METABRIC breast cancer data recorded for over 2000 patients, and the public integrated source from ROCK database with 1570 samples. We first computed the CM1 score to identify the probes with highly discriminative patterns of expression across samples of each intrinsic subtype. We further assessed the ability of 42 selected probes on assigning correct subtype labels using 24 different classifiers from the Weka software suite. For comparison, the same method was applied on the list of 50 genes from the PAM50 method. Conclusions The CM1 score portrayed 30 novel biomarkers for predicting breast cancer subtypes, with the confirmation of the role of 12 well-established genes. Intrinsic subtypes assigned using the CM1 list and the ensemble of classifiers are more consistent and homogeneous than the original PAM50 labels. The new subtypes show accurate distributions of current clinical markers ER, PR and HER2, and survival curves in the METABRIC and ROCK data sets. Remarkably, the paradoxical attribution of the original labels reinforces the limitations of employing a single sample classifiers to predict breast cancer intrinsic subtypes. PMID:26132585

Automated separation of merged Langerhans islets

NASA Astrophysics Data System (ADS)

Švihlík, Jan; Kybic, Jan; Habart, David

2016-03-01

This paper deals with separation of merged Langerhans islets in segmentations in order to evaluate correct histogram of islet diameters. A distribution of islet diameters is useful for determining the feasibility of islet transplantation in diabetes. First, the merged islets at training segmentations are manually separated by medical experts. Based on the single islets, the merged islets are identified and the SVM classifier is trained on both classes (merged/single islets). The testing segmentations were over-segmented using watershed transform and the most probable back merging of islets were found using trained SVM classifier. Finally, the optimized segmentation is compared with ground truth segmentation (correctly separated islets).

A Dirichlet process model for classifying and forecasting epidemic curves

PubMed Central

2014-01-01

Background A forecast can be defined as an endeavor to quantitatively estimate a future event or probabilities assigned to a future occurrence. Forecasting stochastic processes such as epidemics is challenging since there are several biological, behavioral, and environmental factors that influence the number of cases observed at each point during an epidemic. However, accurate forecasts of epidemics would impact timely and effective implementation of public health interventions. In this study, we introduce a Dirichlet process (DP) model for classifying and forecasting influenza epidemic curves. Methods The DP model is a nonparametric Bayesian approach that enables the matching of current influenza activity to simulated and historical patterns, identifies epidemic curves different from those observed in the past and enables prediction of the expected epidemic peak time. The method was validated using simulated influenza epidemics from an individual-based model and the accuracy was compared to that of the tree-based classification technique, Random Forest (RF), which has been shown to achieve high accuracy in the early prediction of epidemic curves using a classification approach. We also applied the method to forecasting influenza outbreaks in the United States from 1997–2013 using influenza-like illness (ILI) data from the Centers for Disease Control and Prevention (CDC). Results We made the following observations. First, the DP model performed as well as RF in identifying several of the simulated epidemics. Second, the DP model correctly forecasted the peak time several days in advance for most of the simulated epidemics. Third, the accuracy of identifying epidemics different from those already observed improved with additional data, as expected. Fourth, both methods correctly classified epidemics with higher reproduction numbers (R) with a higher accuracy compared to epidemics with lower R values. Lastly, in the classification of seasonal influenza epidemics based on ILI data from the CDC, the methods’ performance was comparable. Conclusions Although RF requires less computational time compared to the DP model, the algorithm is fully supervised implying that epidemic curves different from those previously observed will always be misclassified. In contrast, the DP model can be unsupervised, semi-supervised or fully supervised. Since both methods have their relative merits, an approach that uses both RF and the DP model could be beneficial. PMID:24405642

Diagnostic Error in Correctional Mental Health: Prevalence, Causes, and Consequences.

PubMed

Martin, Michael S; Hynes, Katie; Hatcher, Simon; Colman, Ian

2016-04-01

While they have important implications for inmates and resourcing of correctional institutions, diagnostic errors are rarely discussed in correctional mental health research. This review seeks to estimate the prevalence of diagnostic errors in prisons and jails and explores potential causes and consequences. Diagnostic errors are defined as discrepancies in an inmate's diagnostic status depending on who is responsible for conducting the assessment and/or the methods used. It is estimated that at least 10% to 15% of all inmates may be incorrectly classified in terms of the presence or absence of a mental illness. Inmate characteristics, relationships with staff, and cognitive errors stemming from the use of heuristics when faced with time constraints are discussed as possible sources of error. A policy example of screening for mental illness at intake to prison is used to illustrate when the risk of diagnostic error might be increased and to explore strategies to mitigate this risk. © The Author(s) 2016.

A web-based neurological pain classifier tool utilizing Bayesian decision theory for pain classification in spinal cord injury patients

NASA Astrophysics Data System (ADS)

Verma, Sneha K.; Chun, Sophia; Liu, Brent J.

2014-03-01

Pain is a common complication after spinal cord injury with prevalence estimates ranging 77% to 81%, which highly affects a patient's lifestyle and well-being. In the current clinical setting paper-based forms are used to classify pain correctly, however, the accuracy of diagnoses and optimal management of pain largely depend on the expert reviewer, which in many cases is not possible because of very few experts in this field. The need for a clinical decision support system that can be used by expert and non-expert clinicians has been cited in literature, but such a system has not been developed. We have designed and developed a stand-alone tool for correctly classifying pain type in spinal cord injury (SCI) patients, using Bayesian decision theory. Various machine learning simulation methods are used to verify the algorithm using a pilot study data set, which consists of 48 patients data set. The data set consists of the paper-based forms, collected at Long Beach VA clinic with pain classification done by expert in the field. Using the WEKA as the machine learning tool we have tested on the 48 patient dataset that the hypothesis that attributes collected on the forms and the pain location marked by patients have very significant impact on the pain type classification. This tool will be integrated with an imaging informatics system to support a clinical study that will test the effectiveness of using Proton Beam radiotherapy for treating spinal cord injury (SCI) related neuropathic pain as an alternative to invasive surgical lesioning.

Rapid pupil-based assessment of glaucomatous damage.

PubMed

Chen, Yanjun; Wyatt, Harry J; Swanson, William H; Dul, Mitchell W

2008-06-01

To investigate the ability of a technique employing pupillometry and functionally-shaped stimuli to assess loss of visual function due to glaucomatous optic neuropathy. Pairs of large stimuli, mirror images about the horizontal meridian, were displayed alternately in the upper and lower visual field. Pupil diameter was recorded and analyzed in terms of the "contrast balance" (relative sensitivity to the upper and lower stimuli), and the pupil constriction amplitude to upper and lower stimuli separately. A group of 40 patients with glaucoma was tested twice in a first session, and twice more in a second session, 1 to 3 weeks later. A group of 40 normal subjects was tested with the same protocol. Results for the normal subjects indicated functional symmetry in upper/lower retina, on average. Contrast balance results for the patients with glaucoma differed from normal: half the normal subjects had contrast balance within 0.06 log unit of equality and 80% had contrast balance within 0.1 log unit. Half the patients had contrast balances more than 0.1 log unit from equality. Patient contrast balances were moderately correlated with predictions from perimetric data (r = 0.37, p < 0.00001). Contrast balances correctly classified visual field damage in 28 patients (70%), and response amplitudes correctly classified 24 patients (60%). When contrast balance and response amplitude were combined, receiver operating characteristic area for discriminating glaucoma from normal was 0.83. Pupillary evaluation of retinal asymmetry provides a rapid method for detecting and classifying visual field defects. In this patient population, classification agreed with perimetry in 70% of eyes.

Multicategory nets of single-layer perceptrons: complexity and sample-size issues.

PubMed

Raudys, Sarunas; Kybartas, Rimantas; Zavadskas, Edmundas Kazimieras

2010-05-01

The standard cost function of multicategory single-layer perceptrons (SLPs) does not minimize the classification error rate. In order to reduce classification error, it is necessary to: 1) refuse the traditional cost function, 2) obtain near to optimal pairwise linear classifiers by specially organized SLP training and optimal stopping, and 3) fuse their decisions properly. To obtain better classification in unbalanced training set situations, we introduce the unbalance correcting term. It was found that fusion based on the Kulback-Leibler (K-L) distance and the Wu-Lin-Weng (WLW) method result in approximately the same performance in situations where sample sizes are relatively small. The explanation for this observation is by theoretically known verity that an excessive minimization of inexact criteria becomes harmful at times. Comprehensive comparative investigations of six real-world pattern recognition (PR) problems demonstrated that employment of SLP-based pairwise classifiers is comparable and as often as not outperforming the linear support vector (SV) classifiers in moderate dimensional situations. The colored noise injection used to design pseudovalidation sets proves to be a powerful tool for facilitating finite sample problems in moderate-dimensional PR tasks.

Spectral areas and ratios classifier algorithm for pancreatic tissue classification using optical spectroscopy

NASA Astrophysics Data System (ADS)

Chandra, Malavika; Scheiman, James; Simeone, Diane; McKenna, Barbara; Purdy, Julianne; Mycek, Mary-Ann

2010-01-01

Pancreatic adenocarcinoma is one of the leading causes of cancer death, in part because of the inability of current diagnostic methods to reliably detect early-stage disease. We present the first assessment of the diagnostic accuracy of algorithms developed for pancreatic tissue classification using data from fiber optic probe-based bimodal optical spectroscopy, a real-time approach that would be compatible with minimally invasive diagnostic procedures for early cancer detection in the pancreas. A total of 96 fluorescence and 96 reflectance spectra are considered from 50 freshly excised tissue sites-including human pancreatic adenocarcinoma, chronic pancreatitis (inflammation), and normal tissues-on nine patients. Classification algorithms using linear discriminant analysis are developed to distinguish among tissues, and leave-one-out cross-validation is employed to assess the classifiers' performance. The spectral areas and ratios classifier (SpARC) algorithm employs a combination of reflectance and fluorescence data and has the best performance, with sensitivity, specificity, negative predictive value, and positive predictive value for correctly identifying adenocarcinoma being 85, 89, 92, and 80%, respectively.

Metrics and textural features of MRI diffusion to improve classification of pediatric posterior fossa tumors.

PubMed

Rodriguez Gutierrez, D; Awwad, A; Meijer, L; Manita, M; Jaspan, T; Dineen, R A; Grundy, R G; Auer, D P

2014-05-01

Qualitative radiologic MR imaging review affords limited differentiation among types of pediatric posterior fossa brain tumors and cannot detect histologic or molecular subtypes, which could help to stratify treatment. This study aimed to improve current posterior fossa discrimination of histologic tumor type by using support vector machine classifiers on quantitative MR imaging features. This retrospective study included preoperative MRI in 40 children with posterior fossa tumors (17 medulloblastomas, 16 pilocytic astrocytomas, and 7 ependymomas). Shape, histogram, and textural features were computed from contrast-enhanced T2WI and T1WI and diffusivity (ADC) maps. Combinations of features were used to train tumor-type-specific classifiers for medulloblastoma, pilocytic astrocytoma, and ependymoma types in separation and as a joint posterior fossa classifier. A tumor-subtype classifier was also produced for classic medulloblastoma. The performance of different classifiers was assessed and compared by using randomly selected subsets of training and test data. ADC histogram features (25th and 75th percentiles and skewness) yielded the best classification of tumor type (on average >95.8% of medulloblastomas, >96.9% of pilocytic astrocytomas, and >94.3% of ependymomas by using 8 training samples). The resulting joint posterior fossa classifier correctly assigned >91.4% of the posterior fossa tumors. For subtype classification, 89.4% of classic medulloblastomas were correctly classified on the basis of ADC texture features extracted from the Gray-Level Co-Occurence Matrix. Support vector machine-based classifiers using ADC histogram features yielded very good discrimination among pediatric posterior fossa tumor types, and ADC textural features show promise for further subtype discrimination. These findings suggest an added diagnostic value of quantitative feature analysis of diffusion MR imaging in pediatric neuro-oncology. © 2014 by American Journal of Neuroradiology.

Evaluation of knowledge of Health care professionals on warfarin interactions with drug and herb medicinal in Central Saudi Arabia

PubMed Central

Al-Arifi, Mohamed N.; Wajid, Syed; Al-Manie, Nawaf K.; Al-Saker, Faisal M.; Babelgaith, Salmeen D.; Asiri, Yousif A.; Sales, Ibrahim

2016-01-01

Objectives: To evaluate health care professionals’ knowledge on warfarin interactions with drugs and herbs. Methods: A self-administered questionnaire was developed to assess health care professionals’ knowledge on warfarin interactions with drug and herb. Respondents were asked to classify 15 drugs that may effect on warfarin action as “enhance”, “inhibit “, “no effect”. The study sample involved health care professionals (physicians, pharmacists and nurses) from king Salman hospital, Saudi Arabia. Results: About 92.2% of health care professionals identified warfarin interactions with aspirin, 4.4% for warfarin and fluoxetine. Warfarin and cardiac agents (atenolol) was correctly identified by 11.1% of respondents. In warfarin –herb interactions section, the majority of respondents (66.7%) identified the interaction between green tea and warfarin. Approximately one-third of respondents (n=33) correctly classified warfarin interactions with cardamom. No significant difference was found between the health care professionals (p=0.49) for warfarin-drug interactions knowledge score and p= 0.52 for warfarin- herb interactions knowledge score. Conclusion: This study suggests that health care professionals’ knowledge of warfarin- drug-herb interactions was inadequate. Therefore, health care professionals should receive more education programs about drug-drug/herb interactions to provide appropriate patient counseling and optimal therapeutic outcomes. PMID:27022381

Predicting motion sickness during parabolic flight

NASA Technical Reports Server (NTRS)

Harm, Deborah L.; Schlegel, Todd T.

2002-01-01

BACKGROUND: There are large individual differences in susceptibility to motion sickness. Attempts to predict who will become motion sick have had limited success. In the present study, we examined gender differences in resting levels of salivary amylase and total protein, cardiac interbeat intervals (R-R intervals), and a sympathovagal index and evaluated their potential to correctly classify individuals into two motion sickness severity groups. METHODS: Sixteen subjects (10 men and 6 women) flew four sets of 10 parabolas aboard NASA's KC-135 aircraft. Saliva samples for amylase and total protein were collected preflight on the day of the flight and motion sickness symptoms were recorded during each parabola. Cardiovascular parameters were collected in the supine position 1-5 days before the flight. RESULTS: There were no significant gender differences in sickness severity or any of the other variables mentioned above. Discriminant analysis using salivary amylase, R-R intervals and the sympathovagal index produced a significant Wilks' lambda coefficient of 0.36, p=0.006. The analysis correctly classified 87% of the subjects into the none-mild sickness or the moderate-severe sickness group. CONCLUSIONS: The linear combination of resting levels of salivary amylase, high-frequency R-R interval levels, and a sympathovagal index may be useful in predicting motion sickness severity.

Predicting Motion Sickness During Parabolic Flight

NASA Technical Reports Server (NTRS)

Harm, Deborah L.; Schlegel, Todd T.

2002-01-01

Background: There are large individual differences in susceptibility to motion sickness. Attempts to predict who will become motion sick have had limited success. In the present study we examined gender differences in resting levels of salivary amylase and total protein, cardiac interbeat intervals (R-R intervals), and a sympathovagal index and evaluated their potential to correctly classify individuals into two motion sickness severity groups. Methods: Sixteen subjects (10 men and 6 women) flew 4 sets of 10 parabolas aboard NASA's KC-135 aircraft. Saliva samples for amylase and total protein were collected preflight on the day of the flight and motion sickness symptoms were recorded during each parabola. Cardiovascular parameters were collected in the supine position 1-5 days prior to the flight. Results: There were no significant gender differences in sickness severity or any of the other variables mentioned above. Discriminant analysis using salivary amylase, R-R intervals and the sympathovagal index produced a significant Wilks' lambda coefficient of 0.36, p= 0.006. The analysis correctly classified 87% of the subjects into the none-mild sickness or the moderate-severe sickness group. Conclusions: The linear combination of resting levels of salivary amylase, high frequency R-R interval levels, and a sympathovagal index may be useful in predicting motion sickness severity.

33 CFR 52.43 - Requests for further information; submissions of classified, privileged, and sensitive information.

Code of Federal Regulations, 2010 CFR

2010-07-01

... 33 Navigation and Navigable Waters 1 2010-07-01 2010-07-01 false Requests for further information; submissions of classified, privileged, and sensitive information. 52.43 Section 52.43 Navigation and Navigable Waters COAST GUARD, DEPARTMENT OF HOMELAND SECURITY PERSONNEL BOARD FOR CORRECTION OF MILITARY RECORDS OF THE COAST GUARD Submissions by...

Automatic Stem Cell Detection in Microscopic Whole Mouse Cryo-imaging

PubMed Central

Wuttisarnwattana, Patiwet; Gargesha, Madhusudhana; Hof, Wouter van’t; Cooke, Kenneth R.

2016-01-01

With its single cell sensitivity over volumes as large as or larger than a mouse, cryo-imaging enables imaging of stem cell biodistribution, homing, engraftment, and molecular mechanisms. We developed and evaluated a highly automated software tool to detect fluorescently labeled stem cells within very large (~200GB) cryo-imaging datasets. Cell detection steps are: preprocess, remove immaterial regions, spatially filter to create features, identify candidate pixels, classify pixels using bagging decision trees, segment cell patches, and perform 3D labeling. There are options for analysis and visualization. To train the classifier, we created synthetic images by placing realistic digital cell models onto cryo-images of control mice devoid of cells. Very good cell detection results were (precision=98.49%, recall=99.97%) for synthetic cryo-images, (precision=97.81%, recall=97.71%) for manually evaluated, actual cryo-images, and <1% false positives in control mice. An α-multiplier applied to features allows one to correct for experimental variations in cell brightness due to labeling. On dim cells (37% of standard brightness), with correction, we improved recall (49.26%→99.36%) without a significant drop in precision (99.99%→99.75%). With tail vein injection, multipotent adult progenitor cells in a graft-versus-host-disease model in the first days post injection were predominantly found in lung, liver, spleen, and bone marrow. Distribution was not simply related to blood flow. The lung contained clusters of cells while other tissues contained single cells. Our methods provided stem cell distribution anywhere in mouse with single cell sensitivity. Methods should provide a rational means of evaluating dosing, delivery methods, cell enhancements, and mechanisms for therapeutic cells. PMID:26552080

Optical Fourier diffractometry applied to degraded bone structure recognition

NASA Astrophysics Data System (ADS)

Galas, Jacek; Godwod, Krzysztof; Szawdyn, Jacek; Sawicki, Andrzej

1993-09-01

Image processing and recognition methods are useful in many fields. This paper presents the hybrid optical and digital method applied to recognition of pathological changes in bones involved by metabolic bone diseases. The trabecular bone structure, registered by x ray on the photographic film, is analyzed in the new type of computer controlled diffractometer. The set of image parameters, extracted from diffractogram, is evaluated by statistical analysis. The synthetic image descriptors in discriminant space, constructed on the base of 3 training groups of images (control, osteoporosis, and osteomalacia groups) by discriminant analysis, allow us to recognize bone samples with degraded bone structure and to recognize the disease. About 89% of the images were classified correctly. This method after optimization process will be verified in medical investigations.

Fuel loads and fuel type mapping

USGS Publications Warehouse

Chuvieco, Emilio; Riaño, David; Van Wagtendonk, Jan W.; Morsdof, Felix; Chuvieco, Emilio

2003-01-01

Correct description of fuel properties is critical to improve fire danger assessment and fire behaviour modeling, since they guide both fire ignition and fire propagation. This chapter deals with properties of fuel that can be considered static in short periods of time: biomass loads, plant geometry, compactness, etc. Mapping these properties require a detail knowledge of vegetation vertical and horizontal structure. Several systems to classify the great diversity of vegetation characteristics in few fuel types are described, as well as methods for mapping them with special emphasis on those based on remote sensing images.

Multiple directed graph large-class multi-spectral processor

NASA Technical Reports Server (NTRS)

Casasent, David; Liu, Shiaw-Dong; Yoneyama, Hideyuki

1988-01-01

Numerical analysis techniques for the interpretation of high-resolution imaging-spectrometer data are described and demonstrated. The method proposed involves the use of (1) a hierarchical classifier with a tree structure generated automatically by a Fisher linear-discriminant-function algorithm and (2) a novel multiple-directed-graph scheme which reduces the local maxima and the number of perturbations required. Results for a 500-class test problem involving simulated imaging-spectrometer data are presented in tables and graphs; 100-percent-correct classification is achieved with an improvement factor of 5.

Applying cybernetic technology to diagnose human pulmonary sounds.

PubMed

Chen, Mei-Yung; Chou, Cheng-Han

2014-06-01

Chest auscultation is a crucial and efficient method for diagnosing lung disease; however, it is a subjective process that relies on physician experience and the ability to differentiate between various sound patterns. Because the physiological signals composed of heart sounds and pulmonary sounds (PSs) are greater than 120 Hz and the human ear is not sensitive to low frequencies, successfully making diagnostic classifications is difficult. To solve this problem, we constructed various PS recognition systems for classifying six PS classes: vesicular breath sounds, bronchial breath sounds, tracheal breath sounds, crackles, wheezes, and stridor sounds. First, we used a piezoelectric microphone and data acquisition card to acquire PS signals and perform signal preprocessing. A wavelet transform was used for feature extraction, and the PS signals were decomposed into frequency subbands. Using a statistical method, we extracted 17 features that were used as the input vectors of a neural network. We proposed a 2-stage classifier combined with a back-propagation (BP) neural network and learning vector quantization (LVQ) neural network, which improves classification accuracy by using a haploid neural network. The receiver operating characteristic (ROC) curve verifies the high performance level of the neural network. To expand traditional auscultation methods, we constructed various PS diagnostic systems that can correctly classify the six common PSs. The proposed device overcomes the lack of human sensitivity to low-frequency sounds and various PS waves, characteristic values, and a spectral analysis charts are provided to elucidate the design of the human-machine interface.

Classification methods for monitoring Arctic sea ice using OKEAN passive/active two-channel microwave data

USGS Publications Warehouse

Belchansky, Gennady I.; Douglas, David C.

2000-01-01

This paper presents methods for classifying Arctic sea ice using both passive and active (2-channel) microwave imagery acquired by the Russian OKEAN 01 polar-orbiting satellite series. Methods and results are compared to sea ice classifications derived from nearly coincident Special Sensor Microwave Imager (SSM/I) and Advanced Very High Resolution Radiometer (AVHRR) image data of the Barents, Kara, and Laptev Seas. The Russian OKEAN 01 satellite data were collected over weekly intervals during October 1995 through December 1997. Methods are presented for calibrating, georeferencing and classifying the raw active radar and passive microwave OKEAN 01 data, and for correcting the OKEAN 01 microwave radiometer calibration wedge based on concurrent 37 GHz horizontal polarization SSM/I brightness temperature data. Sea ice type and ice concentration algorithms utilized OKEAN's two-channel radar and passive microwave data in a linear mixture model based on the measured values of brightness temperature and radar backscatter, together with a priori knowledge about the scattering parameters and natural emissivities of basic sea ice types. OKEAN 01 data and algorithms tended to classify lower concentrations of young or first-year sea ice when concentrations were less than 60%, and to produce higher concentrations of multi-year sea ice when concentrations were greater than 40%, when compared to estimates produced from SSM/I data. Overall, total sea ice concentration maps derived independently from OKEAN 01, SSM/I, and AVHRR satellite imagery were all highly correlated, with uniform biases, and mean differences in total ice concentration of less than four percent (sd<15%).

Multicenter evaluation of stress-first myocardial perfusion image triage by nuclear technologists and automated quantification

PubMed Central

Chaudhry, Waseem; Hussain, Nasir; Ahlberg, Alan W.; Croft, Lori B.; Fernandez, Antonio B.; Parker, Mathew W.; Swales, Heather H.; Slomka, Piotr J.; Henzlova, Milena J.; Duvall, W. Lane

2016-01-01

Background A stress-first myocardial perfusion imaging (MPI) protocol saves time, is cost effective, and decreases radiation exposure. A limitation of this protocol is the requirement for physician review of the stress images to determine the need for rest images. This hurdle could be eliminated if an experienced technologist and/or automated computer quantification could make this determination. Methods Images from consecutive patients who were undergoing a stress-first MPI with attenuation correction at two tertiary care medical centers were prospectively reviewed independently by a technologist and cardiologist blinded to clinical and stress test data. Their decision on the need for rest imaging along with automated computer quantification of perfusion results was compared with the clinical reference standard of an assessment of perfusion images by a board-certified nuclear cardiologist that included clinical and stress test data. Results A total of 250 patients (mean age 61 years and 55% female) who underwent a stress-first MPI were studied. According to the clinical reference standard, 42 (16.8%) and 208 (83.2%) stress-first images were interpreted as “needing” and “not needing” rest images, respectively. The technologists correctly classified 229 (91.6%) stress-first images as either “needing” (n = 28) or “not needing” (n = 201) rest images. Their sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) were 66.7%, 96.6%, 80.0%, and 93.5%, respectively. An automated stress TPD score ≥1.2 was associated with optimal sensitivity and specificity and correctly classified 179 (71.6%) stress-first images as either “needing” (n = 31) or “not needing” (n = 148) rest images. Its sensitivity, specificity, PPV, and NPV were 73.8%, 71.2%, 34.1%, and 93.1%, respectively. In a model whereby the computer or technologist could correct for the other's incorrect classification, 242 (96.8%) stress-first images were correctly classified. The composite sensitivity, specificity, PPV, and NPV were 83.3%, 99.5%, 97.2%, and 96.7%, respectively. Conclusion Technologists and automated quantification software had a high degree of agreement with the clinical reference standard for determining the need for rest images in a stress-first imaging protocol. Utilizing an experienced technologist and automated systems to screen stress-first images could expand the use of stress-first MPI to sites where the cardiologist is not immediately available for interpretation. PMID:26566774

Differential diagnosis between Parkinson's disease and essential tremor using the smartphone's accelerometer.

PubMed

Barrantes, Sergi; Sánchez Egea, Antonio J; González Rojas, Hernán A; Martí, Maria J; Compta, Yaroslau; Valldeoriola, Francesc; Simo Mezquita, Ester; Tolosa, Eduard; Valls-Solè, Josep

2017-01-01

The differential diagnosis between patients with essential tremor (ET) and those with Parkinson's disease (PD) whose main manifestation is tremor may be difficult unless using complex neuroimaging techniques such as 123I-FP-CIT SPECT. We considered that using smartphone's accelerometer to stablish a diagnostic test based on time-frequency differences between PD an ET could support the clinical diagnosis. The study was carried out in 17 patients with PD, 16 patients with ET, 12 healthy volunteers and 7 patients with tremor of undecided diagnosis (TUD), who were re-evaluated one year after the first visit to reach the definite diagnosis. The smartphone was placed over the hand dorsum to record epochs of 30 s at rest and 30 s during arm stretching. We generated frequency power spectra and calculated receiver operating characteristics curves (ROC) curves of total spectral power, to establish a threshold to separate subjects with and without tremor. In patients with PD and ET, we found that the ROC curve of relative energy was the feature discriminating better between the two groups. This threshold was then used to classify the TUD patients. We could correctly classify 49 out of 52 subjects in the category with/without tremor (97.96% sensitivity and 83.3% specificity) and 27 out of 32 patients in the category PD/ET (84.38% discrimination accuracy). Among TUD patients, 2 of 2 PD and 2 of 4 ET were correctly classified, and one patient having PD plus ET was classified as PD. Based on the analysis of smartphone accelerometer recordings, we found several kinematic features in the analysis of tremor that distinguished first between healthy subjects and patients and, ultimately, between PD and ET patients. The proposed method can give immediate results for the clinician to gain valuable information for the diagnosis of tremor. This can be useful in environments where more sophisticated diagnostic techniques are unavailable.

Quantagenetics® analysis of laser-induced breakdown spectroscopic data: Rapid and accurate authentication of materials

NASA Astrophysics Data System (ADS)

McManus, Catherine E.; Dowe, James; McMillan, Nancy J.

2018-07-01

Many industrial and commercial issues involve authentication of such matters as the manufacturer or geographic source of a material, and quality control of materials, determining whether specific treatments have been properly applied, or if a material is authentic or fraudulent. Often, multiple analytical techniques and tests are used, resulting in expensive and time-consuming testing procedures. Laser-Induced Breakdown Spectroscopy (LIBS) is a rapid laser ablation spectroscopic analytical method. Each LIBS spectrum contains information about the concentration of every element, some isotopic ratios, and the molecular structure of the material, making it a unique and comprehensive signature of the material. Quantagenetics® is a multivariate statistical method based on Bayesian statistics that uses the Euclidian distance between LIBS spectra of materials to classify materials (US Patents 9,063,085 and 8,699,022). The fundamental idea behind Quantagenetics® is that LIBS spectra contain sufficient information to determine the origin and history of materials. This study presents two case studies that illustrate the method. LIBS spectra from 510 Colombian emeralds from 18 mines were classified by mine. Overall, 99.4% of the spectra were correctly classified; the success rate for individual mines ranges from 98.2% to 100%. Some of the mines are separated by distances as little as 200 m, indicating that the method uses the slight but consistent differences in composition to identify the mine of origin accurately. The second study used bars of 17-4 stainless steel from three manufacturers. Each of the three bars was cut into 90 coupons; 30 of each bar received no further treatment, another 30 from each bar received one tempering and hardening treatment, and the final 30 coupons from each bar received a different heat treatment. Using LIBS spectra taken from the coupons, the Quantagenetics® method classified the 270 coupons both by manufacturer (composition) and heat treatment (structure) with an overall success rate of 95.3%. Individual success rates range from 92.4% to 97.6%. These case studies were successful despite having no preconceived knowledge of the materials; artificial intelligence allows the materials to classify themselves without human intervention or bias. Multivariate analysis of LIBS spectra using the Quantagenetics® method has promise to improve quality control and authentication of a wide variety of materials in industrial enterprises.

Discrimination of chicken seasonings and beef seasonings using electronic nose and sensory evaluation.

PubMed

Tian, Huaixiang; Li, Fenghua; Qin, Lan; Yu, Haiyan; Ma, Xia

2014-11-01

This study examines the feasibility of electronic nose as a method to discriminate chicken and beef seasonings and to predict sensory attributes. Sensory evaluation showed that 8 chicken seasonings and 4 beef seasonings could be well discriminated and classified based on 8 sensory attributes. The sensory attributes including chicken/beef, gamey, garlic, spicy, onion, soy sauce, retention, and overall aroma intensity were generated by a trained evaluation panel. Principal component analysis (PCA), discriminant factor analysis (DFA), and cluster analysis (CA) combined with electronic nose were used to discriminate seasoning samples based on the difference of the sensor response signals of chicken and beef seasonings. The correlation between sensory attributes and electronic nose sensors signal was established using partial least squares regression (PLSR) method. The results showed that the seasoning samples were all correctly classified by the electronic nose combined with PCA, DFA, and CA. The electronic nose gave good prediction results for all the sensory attributes with correlation coefficient (r) higher than 0.8. The work indicated that electronic nose is an effective method for discriminating different seasonings and predicting sensory attributes. © 2014 Institute of Food Technologists®

Treatment outcomes of saddle nose correction.

PubMed

Hyun, Sang Min; Jang, Yong Ju

2013-01-01

Many valuable classification schemes for saddle nose have been suggested that integrate clinical deformity and treatment; however, there is no consensus regarding the most suitable classification and surgical method for saddle nose correction. To present clinical characteristics and treatment outcome of saddle nose deformity and to propose a modified classification system to better characterize the variety of different saddle nose deformities. The retrospective study included 91 patients who underwent rhinoplasty for correction of saddle nose from April 1, 2003, through December 31, 2011, with a minimum follow-up of 8 months. Saddle nose was classified into 4 types according to a modified classification. Aesthetic outcomes were classified as excellent, good, fair, or poor. Patients underwent minor cosmetic concealment by dorsal augmentation (n = 8) or major septal reconstruction combined with dorsal augmentation (n = 83). Autologous costal cartilages were used in 40 patients (44%), and homologous costal cartilages were used in 5 patients (6%). According to postoperative assessment, 29 patients had excellent, 42 patients had good, 18 patients had fair, and 2 patients had poor aesthetic outcomes. No statistical difference in surgical outcome according to saddle nose classification was observed. Eight patients underwent revision rhinoplasty, owing to recurrence of saddle, wound infection, or warping of the costal cartilage for dorsal augmentation. We introduce a modified saddle nose classification scheme that is simpler and better able to characterize different deformities. Among 91 patients with saddle nose, 20 (22%) had unsuccessful outcomes (fair or poor) and 8 (9%) underwent subsequent revision rhinoplasty. Thus, management of saddle nose deformities remains challenging. 4.

Usefulness of amino acid composition to discriminate between honeydew and floral honeys. Application to honeys from a small geographic area.

PubMed

Iglesias, María Teresa; De Lorenzo, Cristina; Del Carmen Polo, María; Martín-Alvarez, Pedro Jésus; Pueyo, Encarnacíon

2004-01-14

With the aim of finding methods that could constitute a solid alternative to melissopalynological and physicochemical analyses to determine the botanical origin (floral or honeydew) of honeys, the free amino acid content of 46 honey samples has been determined. The honeys were collected in a small geographic area of approximately 2000 km(2) in central Spain. Twenty-seven honey samples were classified as floral and 19 as honeydew according to their palynological and physicochemical analyses. The resulting data have been subjected to different multivariant analysis techniques. One hundred percent of honey samples have been correctly classified into either the floral or the honeydew groups, according to their content in glutamic acid and tryptophan. It is concluded that free amino acids are good indicators of the botanical origin of honeys, saving time compared with more tedious analyses.

Unsupervised classification of cirrhotic livers using MRI data

NASA Astrophysics Data System (ADS)

Lee, Gobert; Kanematsu, Masayuki; Kato, Hiroki; Kondo, Hiroshi; Zhou, Xiangrong; Hara, Takeshi; Fujita, Hiroshi; Hoshi, Hiroaki

2008-03-01

Cirrhosis of the liver is a chronic disease. It is characterized by the presence of widespread nodules and fibrosis in the liver which results in characteristic texture patterns. Computerized analysis of hepatic texture patterns is usually based on regions-of-interest (ROIs). However, not all ROIs are typical representatives of the disease stage of the liver from which the ROIs originated. This leads to uncertainties in the ROI labels (diseased or non-diseased). On the other hand, supervised classifiers are commonly used in determining the assignment rule. This presents a problem as the training of a supervised classifier requires the correct labels of the ROIs. The main purpose of this paper is to investigate the use of an unsupervised classifier, the k-means clustering, in classifying ROI based data. In addition, a procedure for generating a receiver operating characteristic (ROC) curve depicting the classification performance of k-means clustering is also reported. Hepatic MRI images of 44 patients (16 cirrhotic; 28 non-cirrhotic) are used in this study. The MRI data are derived from gadolinium-enhanced equilibrium phase images. For each patient, 10 ROIs selected by an experienced radiologist and 7 texture features measured on each ROI are included in the MRI data. Results of the k-means classifier are depicted using an ROC curve. The area under the curve (AUC) has a value of 0.704. This is slightly lower than but comparable to that of LDA and ANN classifiers which have values 0.781 and 0.801, respectively. Methods in constructing ROC curve in relation to k-means clustering have not been previously reported in the literature.

Adaptive Criterion Setting in Perceptual Decision Making

ERIC Educational Resources Information Center

Stuttgen, Maik C.; Yildiz, Ali; Gunturkun, Onur

2011-01-01

Pigeons responded in a perceptual categorization task with six different stimuli (shades of gray), three of which were to be classified as "light" or "dark", respectively. Reinforcement probability for correct responses was varied from 0.2 to 0.6 across blocks of sessions and was unequal for correct light and dark responses. Introduction of a new…

An intelligent classifier for prognosis of cardiac resynchronization therapy based on speckle-tracking echocardiograms.

PubMed

Chao, Pei-Kuang; Wang, Chun-Li; Chan, Hsiao-Lung

2012-03-01

Predicting response after cardiac resynchronization therapy (CRT) has been a challenge of cardiologists. About 30% of selected patients based on the standard selection criteria for CRT do not show response after receiving the treatment. This study is aimed to build an intelligent classifier to assist in identifying potential CRT responders by speckle-tracking radial strain based on echocardiograms. The echocardiograms analyzed were acquired before CRT from 26 patients who have received CRT. Sequential forward selection was performed on the parameters obtained by peak-strain timing and phase space reconstruction on speckle-tracking radial strain to find an optimal set of features for creating intelligent classifiers. Support vector machine (SVM) with a linear, quadratic, and polynominal kernel were tested to build classifiers to identify potential responders and non-responders for CRT by selected features. Based on random sub-sampling validation, the best classification performance is correct rate about 95% with 96-97% sensitivity and 93-94% specificity achieved by applying SVM with a quadratic kernel on a set of 3 parameters. The selected 3 parameters contain both indexes extracted by peak-strain timing and phase space reconstruction. An intelligent classifier with an averaged correct rate, sensitivity and specificity above 90% for assisting in identifying CRT responders is built by speckle-tracking radial strain. The classifier can be applied to provide objective suggestion for patient selection of CRT. Copyright © 2011 Elsevier B.V. All rights reserved.

Estimating local scaling properties for the classification of interstitial lung disease patterns

NASA Astrophysics Data System (ADS)

Huber, Markus B.; Nagarajan, Mahesh B.; Leinsinger, Gerda; Ray, Lawrence A.; Wismueller, Axel

2011-03-01

Local scaling properties of texture regions were compared in their ability to classify morphological patterns known as 'honeycombing' that are considered indicative for the presence of fibrotic interstitial lung diseases in high-resolution computed tomography (HRCT) images. For 14 patients with known occurrence of honeycombing, a stack of 70 axial, lung kernel reconstructed images were acquired from HRCT chest exams. 241 regions of interest of both healthy and pathological (89) lung tissue were identified by an experienced radiologist. Texture features were extracted using six properties calculated from gray-level co-occurrence matrices (GLCM), Minkowski Dimensions (MDs), and the estimation of local scaling properties with Scaling Index Method (SIM). A k-nearest-neighbor (k-NN) classifier and a Multilayer Radial Basis Functions Network (RBFN) were optimized in a 10-fold cross-validation for each texture vector, and the classification accuracy was calculated on independent test sets as a quantitative measure of automated tissue characterization. A Wilcoxon signed-rank test was used to compare two accuracy distributions including the Bonferroni correction. The best classification results were obtained by the set of SIM features, which performed significantly better than all the standard GLCM and MD features (p < 0.005) for both classifiers with the highest accuracy (94.1%, 93.7%; for the k-NN and RBFN classifier, respectively). The best standard texture features were the GLCM features 'homogeneity' (91.8%, 87.2%) and 'absolute value' (90.2%, 88.5%). The results indicate that advanced texture features using local scaling properties can provide superior classification performance in computer-assisted diagnosis of interstitial lung diseases when compared to standard texture analysis methods.

Detection of Cardiovascular Disease Risk's Level for Adults Using Naive Bayes Classifier.

PubMed

Miranda, Eka; Irwansyah, Edy; Amelga, Alowisius Y; Maribondang, Marco M; Salim, Mulyadi

2016-07-01

The number of deaths caused by cardiovascular disease and stroke is predicted to reach 23.3 million in 2030. As a contribution to support prevention of this phenomenon, this paper proposes a mining model using a naïve Bayes classifier that could detect cardiovascular disease and identify its risk level for adults. The process of designing the method began by identifying the knowledge related to the cardiovascular disease profile and the level of cardiovascular disease risk factors for adults based on the medical record, and designing a mining technique model using a naïve Bayes classifier. Evaluation of this research employed two methods: accuracy, sensitivity, and specificity calculation as well as an evaluation session with cardiologists and internists. The characteristics of cardiovascular disease are identified by its primary risk factors. Those factors are diabetes mellitus, the level of lipids in the blood, coronary artery function, and kidney function. Class labels were assigned according to the values of these factors: risk level 1, risk level 2 and risk level 3. The evaluation of the classifier performance (accuracy, sensitivity, and specificity) in this research showed that the proposed model predicted the class label of tuples correctly (above 80%). More than eighty percent of respondents (including cardiologists and internists) who participated in the evaluation session agree till strongly agreed that this research followed medical procedures and that the result can support medical analysis related to cardiovascular disease. The research showed that the proposed model achieves good performance for risk level detection of cardiovascular disease.

Restoration of Lumbar Lordosis in Flat Back Deformity: Optimal Degree of Correction

PubMed Central

Kim, Ki-Tack; Lee, Sang-Hun; Kim, Hyo-Jong; Kim, Jung-Youn; Lee, Jung-Hee

2015-01-01

Study Design A retrospective comparative study. Purpose To provide an ideal correction angle of lumbar lordosis (LL) in degenerative flat back deformity. Overview of Literature The degree of correction in degenerative flat back in relation to pelvic incidence (PI) remains controversial. Methods Forty-nine patients with flat back deformity who underwent corrective surgery were enrolled. Posterior-anterior-posterior sequential operation was performed. Mean age and mean follow-up period was 65.6 years and 24.2 months, respectively. We divided the patients into two groups based on immediate postoperative radiographs-optimal correction (OC) group (PI-9°≤LL

Anatomy-guided joint tissue segmentation and topological correction for 6-month infant brain MRI with risk of autism.

PubMed

Wang, Li; Li, Gang; Adeli, Ehsan; Liu, Mingxia; Wu, Zhengwang; Meng, Yu; Lin, Weili; Shen, Dinggang

2018-06-01

Tissue segmentation of infant brain MRIs with risk of autism is critically important for characterizing early brain development and identifying biomarkers. However, it is challenging due to low tissue contrast caused by inherent ongoing myelination and maturation. In particular, at around 6 months of age, the voxel intensities in both gray matter and white matter are within similar ranges, thus leading to the lowest image contrast in the first postnatal year. Previous studies typically employed intensity images and tentatively estimated tissue probabilities to train a sequence of classifiers for tissue segmentation. However, the important prior knowledge of brain anatomy is largely ignored during the segmentation. Consequently, the segmentation accuracy is still limited and topological errors frequently exist, which will significantly degrade the performance of subsequent analyses. Although topological errors could be partially handled by retrospective topological correction methods, their results may still be anatomically incorrect. To address these challenges, in this article, we propose an anatomy-guided joint tissue segmentation and topological correction framework for isointense infant MRI. Particularly, we adopt a signed distance map with respect to the outer cortical surface as anatomical prior knowledge, and incorporate such prior information into the proposed framework to guide segmentation in ambiguous regions. Experimental results on the subjects acquired from National Database for Autism Research demonstrate the effectiveness to topological errors and also some levels of robustness to motion. Comparisons with the state-of-the-art methods further demonstrate the advantages of the proposed method in terms of both segmentation accuracy and topological correctness. © 2018 Wiley Periodicals, Inc.

Assessing and Correcting Topographic Effects on Forest Canopy Height Retrieval Using Airborne LiDAR Data

PubMed Central

Duan, Zhugeng; Zhao, Dan; Zeng, Yuan; Zhao, Yujin; Wu, Bingfang; Zhu, Jianjun

2015-01-01

Topography affects forest canopy height retrieval based on airborne Light Detection and Ranging (LiDAR) data a lot. This paper proposes a method for correcting deviations caused by topography based on individual tree crown segmentation. The point cloud of an individual tree was extracted according to crown boundaries of isolated individual trees from digital orthophoto maps (DOMs). Normalized canopy height was calculated by subtracting the elevation of centres of gravity from the elevation of point cloud. First, individual tree crown boundaries are obtained by carrying out segmentation on the DOM. Second, point clouds of the individual trees are extracted based on the boundaries. Third, precise DEM is derived from the point cloud which is classified by a multi-scale curvature classification algorithm. Finally, a height weighted correction method is applied to correct the topological effects. The method is applied to LiDAR data acquired in South China, and its effectiveness is tested using 41 field survey plots. The results show that the terrain impacts the canopy height of individual trees in that the downslope side of the tree trunk is elevated and the upslope side is depressed. This further affects the extraction of the location and crown of individual trees. A strong correlation was detected between the slope gradient and the proportions of returns with height differences more than 0.3, 0.5 and 0.8 m in the total returns, with coefficient of determination R2 of 0.83, 0.76, and 0.60 (n = 41), respectively. PMID:26016907

FT-Raman and chemometric tools for rapid determination of quality parameters in milk powder: Classification of samples for the presence of lactose and fraud detection by addition of maltodextrin.

PubMed

Rodrigues Júnior, Paulo Henrique; de Sá Oliveira, Kamila; de Almeida, Carlos Eduardo Rocha; De Oliveira, Luiz Fernando Cappa; Stephani, Rodrigo; Pinto, Michele da Silva; de Carvalho, Antônio Fernandes; Perrone, Ítalo Tuler

2016-04-01

FT-Raman spectroscopy has been explored as a quick screening method to evaluate the presence of lactose and identify milk powder samples adulterated with maltodextrin (2.5-50% w/w). Raman measurements can easily differentiate samples of milk powder, without the need for sample preparation, while traditional quality control methods, including high performance liquid chromatography, are cumbersome and slow. FT-Raman spectra were obtained from samples of whole lactose and low-lactose milk powder, both without and with addition of maltodextrin. Differences were observed between the spectra involved in identifying samples with low lactose content, as well as adulterated samples. Exploratory data analysis using Raman spectroscopy and multivariate analysis was also developed to classify samples with PCA and PLS-DA. The PLS-DA models obtained allowed to correctly classify all samples. These results demonstrate the utility of FT-Raman spectroscopy in combination with chemometrics to infer about the quality of milk powder. Copyright © 2015 Elsevier Ltd. All rights reserved.

Point Cloud Classification of Tesserae from Terrestrial Laser Data Combined with Dense Image Matching for Archaeological Information Extraction

NASA Astrophysics Data System (ADS)

Poux, F.; Neuville, R.; Billen, R.

2017-08-01

Reasoning from information extraction given by point cloud data mining allows contextual adaptation and fast decision making. However, to achieve this perceptive level, a point cloud must be semantically rich, retaining relevant information for the end user. This paper presents an automatic knowledge-based method for pre-processing multi-sensory data and classifying a hybrid point cloud from both terrestrial laser scanning and dense image matching. Using 18 features including sensor's biased data, each tessera in the high-density point cloud from the 3D captured complex mosaics of Germigny-des-prés (France) is segmented via a colour multi-scale abstraction-based featuring extracting connectivity. A 2D surface and outline polygon of each tessera is generated by a RANSAC plane extraction and convex hull fitting. Knowledge is then used to classify every tesserae based on their size, surface, shape, material properties and their neighbour's class. The detection and semantic enrichment method shows promising results of 94% correct semantization, a first step toward the creation of an archaeological smart point cloud.

Effect of soft tissue laxity of the knee joint on limb alignment correction in open-wedge high tibial osteotomy.

PubMed

Lee, Dae-Hee; Park, Sung-Chul; Park, Hyung-Joon; Han, Seung-Beom

2016-12-01

Open-wedge high tibial osteotomy (HTO) cannot always accurately correct limb alignment, resulting in under- or over-correction. This study assessed the relationship between soft tissue laxity of the knee joint and alignment correction in open-wedge HTO. This prospective study involved 85 patients (86 knees) undergoing open-wedge HTO for primary medial osteoarthritis. The mechanical axis (MA), weight-bearing line (WBL) ratio, and joint line convergence angle (JLCA) were measured on radiographs preoperatively and after 6 months, and the differences between the pre- and post-surgery values were calculated. Post-operative WBL ratios of 57-67 % were classified as acceptable correction. WBL ratios <57 and >67 % were classified as under- and over-corrections, respectively. Preoperative JLCA correlated positively with differences in MA (r = 0.358, P = 0.001) and WBL ratio (P = 0.003). Difference in JLCA showed a stronger correlation than preoperative JLCA with differences in MA (P < 0.001) and WBL ratio (P < 0.001). Difference in JLCA was the only predictor of both difference in MA (P < 0.001) and difference in WBL ratio (P < 0.001). The difference between pre- and post-operative JLCA differed significantly between the under-correction, acceptable-correction, and over-correction groups (P = 0.033). Preoperative JLCA, however, did not differ significantly between the three groups. Neither preoperative JLCA nor difference in JLCA correlated with change in posterior slope. Preoperative degree of soft tissue laxity in the knee joint was related to the degree of alignment correction, but not to alignment correction error, in open-wedge HTO. Change in soft tissue laxity around the knee from before to after open-wedge HTO correlated with both correction amount and correction error. Therefore, a too large change in JLCA from before to after open-wedge osteotomy may be due to an overly large reduction in JLCA following osteotomy, suggesting alignment over-correction during surgery. II.

A new method of hybrid frequency hopping signals selection and blind parameter estimation

NASA Astrophysics Data System (ADS)

Zeng, Xiaoyu; Jiao, Wencheng; Sun, Huixian

2018-04-01

Frequency hopping communication is widely used in military communications at home and abroad. In the case of single-channel reception, it is scarce to process multiple frequency hopping signals both effectively and simultaneously. A method of hybrid FH signals selection and blind parameter estimation is proposed. The method makes use of spectral transformation, spectral entropy calculation and PRI transformation basic theory to realize the sorting and parameter estimation of the components in the hybrid frequency hopping signal. The simulation results show that this method can correctly classify the frequency hopping component signal, and the estimated error of the frequency hopping period is about 5% and the estimated error of the frequency hopping frequency is less than 1% when the SNR is 10dB. However, the performance of this method deteriorates seriously at low SNR.

[Rapid Identification of Epicarpium Citri Grandis via Infrared Spectroscopy and Fluorescence Spectrum Imaging Technology Combined with Neural Network].

PubMed

Pan, Sha-sha; Huang, Fu-rong; Xiao, Chi; Xian, Rui-yi; Ma, Zhi-guo

2015-10-01

To explore rapid reliable methods for detection of Epicarpium citri grandis (ECG), the experiment using Fourier Transform Attenuated Total Reflection Infrared Spectroscopy (FTIR/ATR) and Fluorescence Spectrum Imaging Technology combined with Multilayer Perceptron (MLP) Neural Network pattern recognition, for the identification of ECG, and the two methods are compared. Infrared spectra and fluorescence spectral images of 118 samples, 81 ECG and 37 other kinds of ECG, are collected. According to the differences in tspectrum, the spectra data in the 550-1 800 cm(-1) wavenumber range and 400-720 nm wavelength are regarded as the study objects of discriminant analysis. Then principal component analysis (PCA) is applied to reduce the dimension of spectroscopic data of ECG and MLP Neural Network is used in combination to classify them. During the experiment were compared the effects of different methods of data preprocessing on the model: multiplicative scatter correction (MSC), standard normal variable correction (SNV), first-order derivative(FD), second-order derivative(SD) and Savitzky-Golay (SG). The results showed that: after the infrared spectra data via the Savitzky-Golay (SG) pretreatment through the MLP Neural Network with the hidden layer function as sigmoid, we can get the best discrimination of ECG, the correct percent of training set and testing set are both 100%. Using fluorescence spectral imaging technology, corrected by the multiple scattering (MSC) results in the pretreatment is the most ideal. After data preprocessing, the three layers of the MLP Neural Network of the hidden layer function as sigmoid function can get 100% correct percent of training set and 96.7% correct percent of testing set. It was shown that the FTIR/ATR and fluorescent spectral imaging technology combined with MLP Neural Network can be used for the identification study of ECG and has the advantages of rapid, reliable effect.

Assessment of four calculation methods proposed by the EC for waste hazardous property HP 14 'Ecotoxic'.

PubMed

Hennebert, Pierre; Humez, Nicolas; Conche, Isabelle; Bishop, Ian; Rebischung, Flore

2016-02-01

Legislation published in December 2014 revised both the List of Waste (LoW) and amended Appendix III of the revised Waste Framework Directive 2008/98/EC; the latter redefined hazardous properties HP 1 to HP 13 and HP 15 but left the assessment of HP 14 unchanged to allow time for the Directorate General of the Environment of the European Commission to complete a study that is examining the impacts of four different calculation methods for the assessment of HP 14. This paper is a contribution to the assessment of the four calculation methods. It also includes the results of a fifth calculation method; referred to as "Method 2 with extended M-factors". Two sets of data were utilised in the assessment; the first (Data Set #1) comprised analytical data for 32 different waste streams (16 hazardous (H), 9 non-hazardous (NH) and 7 mirror entries, as classified by the LoW) while the second data set (Data Set #2), supplied by the eco industries, comprised analytical data for 88 waste streams, all classified as hazardous (H) by the LoW. Two approaches were used to assess the five calculation methods. The first approach assessed the relative ranking of the five calculation methods by the frequency of their classification of waste streams as H. The relative ranking of the five methods (from most severe to less severe) is: Method 3>Method 1>Method 2 with extended M-factors>Method 2>Method 4. This reflects the arithmetic ranking of the concentration limits of each method when assuming M=10, and is independent of the waste streams, or the H/NH/Mirror status of the waste streams. A second approach is the absolute matching or concordance with the LoW. The LoW is taken as a reference method and the H wastes are all supposed to be HP 14. This point is discussed in the paper. The concordance for one calculation method is established by the number of wastes with identical classification by the considered calculation method and the LoW (i.e. H to H, NH to NH). The discordance is established as well, that is when the waste is classified "H" in the LoW and "NH" by calculation (i.e. an under-estimation of the hazard). For Data Set #1, Method 2 with extended M-factors matches best with the LoW (80% concordant H and non-H by LoW, and 13% discordant for H waste by LoW). This method more correctly classifies wastes containing substances with high ecotoxicity. Methods 1 and 3 have nearly as good matches (76% and 72% concordant H and non-H by LoW, and 13% and 6% respectively discordant for H waste by LoW). Method 2 with extended M-factors, but limited to the M-factors published in the CLP has insufficient concordance (64% concordant H and non-H by LoW, and 50% discordant for H waste by LoW). As the same method with extended M-factors gives the best performance, the lower performance is due to the limited set of M-factors in the CLP. Method 4 is divergent (60% concordant H and non-H by LoW, and 56% discordant for H waste by LoW). For Data Set #2, Methods 2 and 4 do not correctly classify 24 air pollution control residues from incineration 19 01 07(∗) (3/24 and 2/24 respectively), and should not be used, while Methods 3, 1 and 2 with extended M-factors successfully classify 100% of them as hazardous. From the two sets of data, Method 2 with extended M-factors (corresponding more closely to the CLP methods used for products) matches best with the LoW when the LoW code is safely known, and Method 3 and 1 will deviate from the LoW if the samples contain substances with high ecotoxicity (in particular PAHs). Methods 2 and 4 are not recommended. Formally, this conclusion depends on the waste streams that are used for the comparison of methods and the relevancy of the classification as hazardous for ecotoxicity in the LoW. Since the set is large (120 waste streams) and no selection has been made here in the available data, the conclusion should be robust. Copyright © 2015 Elsevier Ltd. All rights reserved.

Discriminant Analysis of Defective and Non-Defective Field Pea (Pisum sativum L.) into Broad Market Grades Based on Digital Image Features.

PubMed

McDonald, Linda S; Panozzo, Joseph F; Salisbury, Phillip A; Ford, Rebecca

2016-01-01

Field peas (Pisum sativum L.) are generally traded based on seed appearance, which subjectively defines broad market-grades. In this study, we developed an objective Linear Discriminant Analysis (LDA) model to classify market grades of field peas based on seed colour, shape and size traits extracted from digital images. Seeds were imaged in a high-throughput system consisting of a camera and laser positioned over a conveyor belt. Six colour intensity digital images were captured (under 405, 470, 530, 590, 660 and 850nm light) for each seed, and surface height was measured at each pixel by laser. Colour, shape and size traits were compiled across all seed in each sample to determine the median trait values. Defective and non-defective seed samples were used to calibrate and validate the model. Colour components were sufficient to correctly classify all non-defective seed samples into correct market grades. Defective samples required a combination of colour, shape and size traits to achieve 87% and 77% accuracy in market grade classification of calibration and validation sample-sets respectively. Following these results, we used the same colour, shape and size traits to develop an LDA model which correctly classified over 97% of all validation samples as defective or non-defective.

Higher sensitivity and lower specificity in post-fire mortality model validation of 11 western US tree species

USGS Publications Warehouse

Kane, Jeffrey M.; van Mantgem, Phillip J.; Lalemand, Laura; Keifer, MaryBeth

2017-01-01

Managers require accurate models to predict post-fire tree mortality to plan prescribed fire treatments and examine their effectiveness. Here we assess the performance of a common post-fire tree mortality model with an independent dataset of 11 tree species from 13 National Park Service units in the western USA. Overall model discrimination was generally strong, but performance varied considerably among species and sites. The model tended to have higher sensitivity (proportion of correctly classified dead trees) and lower specificity (proportion of correctly classified live trees) for many species, indicating an overestimation of mortality. Variation in model accuracy (percentage of live and dead trees correctly classified) among species was not related to sample size or percentage observed mortality. However, we observed a positive relationship between specificity and a species-specific bark thickness multiplier, indicating that overestimation was more common in thin-barked species. Accuracy was also quite low for thinner bark classes (<1 cm) for many species, leading to poorer model performance. Our results indicate that a common post-fire mortality model generally performs well across a range of species and sites; however, some thin-barked species and size classes would benefit from further refinement to improve model specificity.

The fusion of large scale classified side-scan sonar image mosaics.

PubMed

Reed, Scott; Tena, Ruiz Ioseba; Capus, Chris; Petillot, Yvan

2006-07-01

This paper presents a unified framework for the creation of classified maps of the seafloor from sonar imagery. Significant challenges in photometric correction, classification, navigation and registration, and image fusion are addressed. The techniques described are directly applicable to a range of remote sensing problems. Recent advances in side-scan data correction are incorporated to compensate for the sonar beam pattern and motion of the acquisition platform. The corrected images are segmented using pixel-based textural features and standard classifiers. In parallel, the navigation of the sonar device is processed using Kalman filtering techniques. A simultaneous localization and mapping framework is adopted to improve the navigation accuracy and produce georeferenced mosaics of the segmented side-scan data. These are fused within a Markovian framework and two fusion models are presented. The first uses a voting scheme regularized by an isotropic Markov random field and is applicable when the reliability of each information source is unknown. The Markov model is also used to inpaint regions where no final classification decision can be reached using pixel level fusion. The second model formally introduces the reliability of each information source into a probabilistic model. Evaluation of the two models using both synthetic images and real data from a large scale survey shows significant quantitative and qualitative improvement using the fusion approach.

Discriminant Analysis of Defective and Non-Defective Field Pea (Pisum sativum L.) into Broad Market Grades Based on Digital Image Features

PubMed Central

McDonald, Linda S.; Panozzo, Joseph F.; Salisbury, Phillip A.; Ford, Rebecca

2016-01-01

Field peas (Pisum sativum L.) are generally traded based on seed appearance, which subjectively defines broad market-grades. In this study, we developed an objective Linear Discriminant Analysis (LDA) model to classify market grades of field peas based on seed colour, shape and size traits extracted from digital images. Seeds were imaged in a high-throughput system consisting of a camera and laser positioned over a conveyor belt. Six colour intensity digital images were captured (under 405, 470, 530, 590, 660 and 850nm light) for each seed, and surface height was measured at each pixel by laser. Colour, shape and size traits were compiled across all seed in each sample to determine the median trait values. Defective and non-defective seed samples were used to calibrate and validate the model. Colour components were sufficient to correctly classify all non-defective seed samples into correct market grades. Defective samples required a combination of colour, shape and size traits to achieve 87% and 77% accuracy in market grade classification of calibration and validation sample-sets respectively. Following these results, we used the same colour, shape and size traits to develop an LDA model which correctly classified over 97% of all validation samples as defective or non-defective. PMID:27176469

Discriminant analysis of cardiovascular and respiratory variables for classification of road cyclists by specialty.

PubMed

Nikolić, Biljana; Martinović, Jelena; Matić, Milan; Stefanović, Đorđe

2018-05-29

Different variables determine the performance of cyclists, which brings up the question how these parameters may help in their classification by specialty. The aim of the study was to determine differences in cardiorespiratory parameters of male cyclists according to their specialty, flat rider (N=21), hill rider (N=35) and sprinter (N=20) and obtain the multivariate model for further cyclists classification by specialties, based on selected variables. Seventeen variables were measured at submaximal and maximum load on the cycle ergometer Cosmed E 400HK (Cosmed, Rome, Italy) (initial 100W with 25W increase, 90-100 rpm). Multivariate discriminant analysis was used to determine which variables group cyclists within their specialty, and to predict which variables can direct cyclists to a particular specialty. Among nine variables that statistically contribute to the discriminant power of the model, achieved power on the anaerobic threshold and the produced CO2 had the biggest impact. The obtained discriminatory model correctly classified 91.43% of flat riders, 85.71% of hill riders, while sprinters were classified completely correct (100%), i.e. 92.10% of examinees were correctly classified, which point out the strength of the discriminatory model. Respiratory indicators mostly contribute to the discriminant power of the model, which may significantly contribute to training practice and laboratory tests in future.

Evaluation and automatic correction of metal-implant-induced artifacts in MR-based attenuation correction in whole-body PET/MR imaging

NASA Astrophysics Data System (ADS)

Schramm, G.; Maus, J.; Hofheinz, F.; Petr, J.; Lougovski, A.; Beuthien-Baumann, B.; Platzek, I.; van den Hoff, J.

2014-06-01

The aim of this paper is to describe a new automatic method for compensation of metal-implant-induced segmentation errors in MR-based attenuation maps (MRMaps) and to evaluate the quantitative influence of those artifacts on the reconstructed PET activity concentration. The developed method uses a PET-based delineation of the patient contour to compensate metal-implant-caused signal voids in the MR scan that is segmented for PET attenuation correction. PET emission data of 13 patients with metal implants examined in a Philips Ingenuity PET/MR were reconstructed with the vendor-provided method for attenuation correction (MRMaporig, PETorig) and additionally with a method for attenuation correction (MRMapcor, PETcor) developed by our group. MRMaps produced by both methods were visually inspected for segmentation errors. The segmentation errors in MRMaporig were classified into four classes (L1 and L2 artifacts inside the lung and B1 and B2 artifacts inside the remaining body depending on the assigned attenuation coefficients). The average relative SUV differences (\\varepsilon _{rel}^{av}) between PETorig and PETcor of all regions showing wrong attenuation coefficients in MRMaporig were calculated. Additionally, relative SUVmean differences (ɛrel) of tracer accumulations in hot focal structures inside or in the vicinity of these regions were evaluated. MRMaporig showed erroneous attenuation coefficients inside the regions affected by metal artifacts and inside the patients' lung in all 13 cases. In MRMapcor, all regions with metal artifacts, except for the sternum, were filled with the soft-tissue attenuation coefficient and the lung was correctly segmented in all patients. MRMapcor only showed small residual segmentation errors in eight patients. \\varepsilon _{rel}^{av} (mean ± standard deviation) were: ( - 56 ± 3)% for B1, ( - 43 ± 4)% for B2, (21 ± 18)% for L1, (120 ± 47)% for L2 regions. ɛrel (mean ± standard deviation) of hot focal structures were: ( - 52 ± 12)% in B1, ( - 45 ± 13)% in B2, (19 ± 19)% in L1, (51 ± 31)% in L2 regions. Consequently, metal-implant-induced artifacts severely disturb MR-based attenuation correction and SUV quantification in PET/MR. The developed algorithm is able to compensate for these artifacts and improves SUV quantification accuracy distinctly.

Correction of oral contrast artifacts in CT-based attenuation correction of PET images using an automated segmentation algorithm.

PubMed

Ahmadian, Alireza; Ay, Mohammad R; Bidgoli, Javad H; Sarkar, Saeed; Zaidi, Habib

2008-10-01

Oral contrast is usually administered in most X-ray computed tomography (CT) examinations of the abdomen and the pelvis as it allows more accurate identification of the bowel and facilitates the interpretation of abdominal and pelvic CT studies. However, the misclassification of contrast medium with high-density bone in CT-based attenuation correction (CTAC) is known to generate artifacts in the attenuation map (mumap), thus resulting in overcorrection for attenuation of positron emission tomography (PET) images. In this study, we developed an automated algorithm for segmentation and classification of regions containing oral contrast medium to correct for artifacts in CT-attenuation-corrected PET images using the segmented contrast correction (SCC) algorithm. The proposed algorithm consists of two steps: first, high CT number object segmentation using combined region- and boundary-based segmentation and second, object classification to bone and contrast agent using a knowledge-based nonlinear fuzzy classifier. Thereafter, the CT numbers of pixels belonging to the region classified as contrast medium are substituted with their equivalent effective bone CT numbers using the SCC algorithm. The generated CT images are then down-sampled followed by Gaussian smoothing to match the resolution of PET images. A piecewise calibration curve was then used to convert CT pixel values to linear attenuation coefficients at 511 keV. The visual assessment of segmented regions performed by an experienced radiologist confirmed the accuracy of the segmentation and classification algorithms for delineation of contrast-enhanced regions in clinical CT images. The quantitative analysis of generated mumaps of 21 clinical CT colonoscopy datasets showed an overestimation ranging between 24.4% and 37.3% in the 3D-classified regions depending on their volume and the concentration of contrast medium. Two PET/CT studies known to be problematic demonstrated the applicability of the technique in clinical setting. More importantly, correction of oral contrast artifacts improved the readability and interpretation of the PET scan and showed substantial decrease of the SUV (104.3%) after correction. An automated segmentation algorithm for classification of irregular shapes of regions containing contrast medium was developed for wider applicability of the SCC algorithm for correction of oral contrast artifacts during the CTAC procedure. The algorithm is being refined and further validated in clinical setting.

A deep learning approach for the analysis of masses in mammograms with minimal user intervention.

PubMed

Dhungel, Neeraj; Carneiro, Gustavo; Bradley, Andrew P

2017-04-01

We present an integrated methodology for detecting, segmenting and classifying breast masses from mammograms with minimal user intervention. This is a long standing problem due to low signal-to-noise ratio in the visualisation of breast masses, combined with their large variability in terms of shape, size, appearance and location. We break the problem down into three stages: mass detection, mass segmentation, and mass classification. For the detection, we propose a cascade of deep learning methods to select hypotheses that are refined based on Bayesian optimisation. For the segmentation, we propose the use of deep structured output learning that is subsequently refined by a level set method. Finally, for the classification, we propose the use of a deep learning classifier, which is pre-trained with a regression to hand-crafted feature values and fine-tuned based on the annotations of the breast mass classification dataset. We test our proposed system on the publicly available INbreast dataset and compare the results with the current state-of-the-art methodologies. This evaluation shows that our system detects 90% of masses at 1 false positive per image, has a segmentation accuracy of around 0.85 (Dice index) on the correctly detected masses, and overall classifies masses as malignant or benign with sensitivity (Se) of 0.98 and specificity (Sp) of 0.7. Copyright © 2017 Elsevier B.V. All rights reserved.

CANDELS Visual Classifications: Scheme, Data Release, and First Results

NASA Technical Reports Server (NTRS)

Kartaltepe, Jeyhan S.; Mozena, Mark; Kocevski, Dale; McIntosh, Daniel H.; Lotz, Jennifer; Bell, Eric F.; Faber, Sandy; Ferguson, Henry; Koo, David; Bassett, Robert;

Comparison of two training strategies for essential newborn care in Brazil.

PubMed Central

Vidal, S. A.; Ronfani, L.; da Mota Silveira, S.; Mello, M. J.; dos Santos, E. R.; Buzzetti, R.; Cattaneo, A.

2001-01-01

OBJECTIVE: To compare the effectiveness of two training strategies for improving essential newborn care in the state of Pernambuco, Brazil. METHODS: Eight hospitals were selected, divided into two groups of four, and paired by geographical, structural, and functional characteristics. Doctors and nurses working at hospitals in Group 1 were given a conventional 5-day training course. Those in Group 2 were given the same manual used by Group 1 but the training course was organized as self-directed learning, with the participants having 5 weeks to complete the course. Participants' knowledge was tested at baseline, immediately after the course, and 3-6 months later. Participants' practices were observed before training and 3-6 months after training during 20 births and by interviewing 20 mothers before discharge at each hospital. FINDINGS: Not all participants completed all of the tests. The scores on the tests of knowledge improved more among those in Group 2 than those in Group 1 when the answers were classified as right or wrong, but there was no difference between groups when a scoring method was used that classified answers as correct, partially correct, incorrect, or missing. Practices related to thermal control after birth improved among those in Group 2 after training but practices related to thermal control on the ward worsened. The promotion of breastfeeding improved in both groups. CONCLUSION: There was no difference between the two training strategies, although self-directed learning was cheaper than conventional training. Neither strategy brought about the expected improvements in the quality of care. Other interventions in addition to training may be needed to improve care. PMID:11731809

The Nature and Extent of Flavored Alcoholic Beverage Consumption among Underage Youth: Results of a National Brand-specific Survey

PubMed Central

Giga, Noreen M.; Binakonsky, Jane; Ross, Craig; Siegel, Michael

2011-01-01

Background Flavored alcoholic beverages are popular among underage drinkers. Existing studies that assessed flavored alcoholic beverage use among youth relied upon respondents to correctly classify the beverages they consume, without defining what alcohol brands belong to this category. Objectives To demonstrate a new method for analyzing the consumption of flavored alcoholic beverages among youth on a brand-specific basis, without relying upon youth to correctly classify brands they consume. Methods Using a pre-recruited internet panel developed by Knowledge Networks, we measured the brands of alcohol consumed by a national sample of youth drinkers, ages 16-20 years, in the United States. The sample consisted of 108 youths who had consumed at least one drink of an alcoholic beverage in the past 30 days. We measured the brand-specific consumption of alcoholic beverages within the past 30 days, ascertaining the consumption of 380 alcohol brands, including 14 brands of flavored alcoholic beverages. Results Measuring the brand-specific consumption of flavored alcoholic beverages was feasible. Based on a brand-specific identification of flavored alcoholic beverages, nearly half of youth drinkers in the sample reported having consumed such beverages in the past 30 days. Flavored alcoholic beverage preference was concentrated among the top four brands, which accounted for nearly all of the consumption volume reported in our study. Conclusions and Scientific Significance These findings underscore the need to assess youth alcohol consumption at the brand level and the potential value of such data in better understanding underage youth drinking behavior and the factors that influence it. PMID:21517708

Deriving pathway maps from automated text analysis using a grammar-based approach.

PubMed

Olsson, Björn; Gawronska, Barbara; Erlendsson, Björn

2006-04-01

We demonstrate how automated text analysis can be used to support the large-scale analysis of metabolic and regulatory pathways by deriving pathway maps from textual descriptions found in the scientific literature. The main assumption is that correct syntactic analysis combined with domain-specific heuristics provides a good basis for relation extraction. Our method uses an algorithm that searches through the syntactic trees produced by a parser based on a Referent Grammar formalism, identifies relations mentioned in the sentence, and classifies them with respect to their semantic class and epistemic status (facts, counterfactuals, hypotheses). The semantic categories used in the classification are based on the relation set used in KEGG (Kyoto Encyclopedia of Genes and Genomes), so that pathway maps using KEGG notation can be automatically generated. We present the current version of the relation extraction algorithm and an evaluation based on a corpus of abstracts obtained from PubMed. The results indicate that the method is able to combine a reasonable coverage with high accuracy. We found that 61% of all sentences were parsed, and 97% of the parse trees were judged to be correct. The extraction algorithm was tested on a sample of 300 parse trees and was found to produce correct extractions in 90.5% of the cases.

Microarray-based gene expression profiling in patients with cryopyrin-associated periodic syndromes defines a disease-related signature and IL-1-responsive transcripts

PubMed Central

Balow, James E; Ryan, John G; Chae, Jae Jin; Booty, Matthew G; Bulua, Ariel; Stone, Deborah; Sun, Hong-Wei; Greene, James; Barham, Beverly; Goldbach-Mansky, Raphaela; Kastner, Daniel L; Aksentijevich, Ivona

2014-01-01

Objective To analyse gene expression patterns and to define a specific gene expression signature in patients with the severe end of the spectrum of cryopyrin-associated periodic syndromes (CAPS). The molecular consequences of interleukin 1 inhibition were examined by comparing gene expression patterns in 16 CAPS patients before and after treatment with anakinra. Methods We collected peripheral blood mononuclear cells from 22 CAPS patients with active disease and from 14 healthy children. Transcripts that passed stringent filtering criteria (p values ≤ false discovery rate 1%) were considered as differentially expressed genes (DEG). A set of DEG was validated by quantitative reverse transcription PCR and functional studies with primary cells from CAPS patients and healthy controls. We used 17 CAPS and 66 non-CAPS patient samples to create a set of gene expression models that differentiates CAPS patients from controls and from patients with other autoinflammatory conditions. Results Many DEG include transcripts related to the regulation of innate and adaptive immune responses, oxidative stress, cell death, cell adhesion and motility. A set of gene expression-based models comprising the CAPS-specific gene expression signature correctly classified all 17 samples from an independent dataset. This classifier also correctly identified 15 of 16 postanakinra CAPS samples despite the fact that these CAPS patients were in clinical remission. Conclusions We identified a gene expression signature that clearly distinguished CAPS patients from controls. A number of DEG were in common with other systemic inflammatory diseases such as systemic onset juvenile idiopathic arthritis. The CAPS-specific gene expression classifiers also suggest incomplete suppression of inflammation at low doses of anakinra. PMID:23223423

Development of a metabolic biosignature for detection of early Lyme disease.

PubMed

Molins, Claudia R; Ashton, Laura V; Wormser, Gary P; Hess, Ann M; Delorey, Mark J; Mahapatra, Sebabrata; Schriefer, Martin E; Belisle, John T

2015-06-15

Early Lyme disease patients often present to the clinic prior to developing a detectable antibody response to Borrelia burgdorferi, the etiologic agent. Thus, existing 2-tier serology-based assays yield low sensitivities (29%-40%) for early infection. The lack of an accurate laboratory test for early Lyme disease contributes to misconceptions about diagnosis and treatment, and underscores the need for new diagnostic approaches. Retrospective serum samples from patients with early Lyme disease, other diseases, and healthy controls were analyzed for small molecule metabolites by liquid chromatography-mass spectrometry (LC-MS). A metabolomics data workflow was applied to select a biosignature for classifying early Lyme disease and non-Lyme disease patients. A statistical model of the biosignature was trained using the patients' LC-MS data, and subsequently applied as an experimental diagnostic tool with LC-MS data from additional patient sera. The accuracy of this method was compared with standard 2-tier serology. Metabolic biosignature development selected 95 molecular features that distinguished early Lyme disease patients from healthy controls. Statistical modeling reduced the biosignature to 44 molecular features, and correctly classified early Lyme disease patients and healthy controls with a sensitivity of 88% (84%-95%), and a specificity of 95% (90%-100%). Importantly, the metabolic biosignature correctly classified 77%-95% of the of serology negative Lyme disease patients. The data provide proof-of-concept that metabolic profiling for early Lyme disease can achieve significantly greater (P < .0001) diagnostic sensitivity than current 2-tier serology, while retaining high specificity. © The Author 2015. Published by Oxford University Press on behalf of the Infectious Diseases Society of America. All rights reserved. For Permissions, please e-mail: journals.permissions@oup.com.

Multi-institutional validation of a novel textural analysis tool for preoperative stratification of suspected thyroid tumors on diffusion-weighted MRI.

PubMed

Brown, Anna M; Nagala, Sidhartha; McLean, Mary A; Lu, Yonggang; Scoffings, Daniel; Apte, Aditya; Gonen, Mithat; Stambuk, Hilda E; Shaha, Ashok R; Tuttle, R Michael; Deasy, Joseph O; Priest, Andrew N; Jani, Piyush; Shukla-Dave, Amita; Griffiths, John

2016-04-01

Ultrasound-guided fine needle aspirate cytology fails to diagnose many malignant thyroid nodules; consequently, patients may undergo diagnostic lobectomy. This study assessed whether textural analysis (TA) could noninvasively stratify thyroid nodules accurately using diffusion-weighted MRI (DW-MRI). This multi-institutional study examined 3T DW-MRI images obtained with spin echo echo planar imaging sequences. The training data set included 26 patients from Cambridge, United Kingdom, and the test data set included 18 thyroid cancer patients from Memorial Sloan Kettering Cancer Center (New York, New York, USA). Apparent diffusion coefficients (ADCs) were compared over regions of interest (ROIs) defined on thyroid nodules. TA, linear discriminant analysis (LDA), and feature reduction were performed using the 21 MaZda-generated texture parameters that best distinguished benign and malignant ROIs. Training data set mean ADC values were significantly different for benign and malignant nodules (P = 0.02) with a sensitivity and specificity of 70% and 63%, respectively, and a receiver operator characteristic (ROC) area under the curve (AUC) of 0.73. The LDA model of the top 21 textural features correctly classified 89/94 DW-MRI ROIs with 92% sensitivity, 96% specificity, and an AUC of 0.97. This algorithm correctly classified 16/18 (89%) patients in the independently obtained test set of thyroid DW-MRI scans. TA classifies thyroid nodules with high sensitivity and specificity on multi-institutional DW-MRI data sets. This method requires further validation in a larger prospective study. Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance. © 2015 The Authors. Magnetic Resonance in Medicine published by Wiley Periodicals, Inc. on behalf of International Society for Magnetic Resonance in Medicine.

Enhancement of force patterns classification based on Gaussian distributions.

PubMed

Ertelt, Thomas; Solomonovs, Ilja; Gronwald, Thomas

2018-01-23

Description of the patterns of ground reaction force is a standard method in areas such as medicine, biomechanics and robotics. The fundamental parameter is the time course of the force, which is classified visually in particular in the field of clinical diagnostics. Here, the knowledge and experience of the diagnostician is relevant for its assessment. For an objective and valid discrimination of the ground reaction force pattern, a generic method, especially in the medical field, is absolutely necessary to describe the qualities of the time-course. The aim of the presented method was to combine the approaches of two existing procedures from the fields of machine learning and the Gauss approximation in order to take advantages of both methods for the classification of ground reaction force patterns. The current limitations of both methods could be eliminated by an overarching method. Twenty-nine male athletes from different sports were examined. Each participant was given the task of performing a one-legged stopping maneuver on a force plate from the maximum possible starting speed. The individual time course of the ground reaction force of each subject was registered and approximated on the basis of eight Gaussian distributions. The descriptive coefficients were then classified using Bayesian regulated neural networks. The different sports served as the distinguishing feature. Although the athletes were all given the same task, all sports referred to a different quality in the time course of ground reaction force. Meanwhile within each sport, the athletes were homogeneous. With an overall prediction (R = 0.938) all subjects/sports were classified correctly with 94.29% accuracy. The combination of the two methods: the mathematical description of the time course of ground reaction forces on the basis of Gaussian distributions and their classification by means of Bayesian regulated neural networks, seems an adequate and promising method to discriminate the ground reaction forces without any loss of information. Copyright © 2017 Elsevier Ltd. All rights reserved.

Automatic Detection of Preposition Errors in Learner Writing

ERIC Educational Resources Information Center

De Felice, Rachele; Pulman, Stephen

2009-01-01

In this article, we present an approach to the automatic correction of preposition errors in L2 English. Our system, based on a maximum entropy classifier, achieves average precision of 42% and recall of 35% on this task. The discussion of results obtained on correct and incorrect data aims to establish what characteristics of L2 writing prove…

Weighted Feature Gaussian Kernel SVM for Emotion Recognition

PubMed Central

Jia, Qingxuan

2016-01-01

Emotion recognition with weighted feature based on facial expression is a challenging research topic and has attracted great attention in the past few years. This paper presents a novel method, utilizing subregion recognition rate to weight kernel function. First, we divide the facial expression image into some uniform subregions and calculate corresponding recognition rate and weight. Then, we get a weighted feature Gaussian kernel function and construct a classifier based on Support Vector Machine (SVM). At last, the experimental results suggest that the approach based on weighted feature Gaussian kernel function has good performance on the correct rate in emotion recognition. The experiments on the extended Cohn-Kanade (CK+) dataset show that our method has achieved encouraging recognition results compared to the state-of-the-art methods. PMID:27807443

The Application of Censored Regression Models in Low Streamflow Analyses

NASA Astrophysics Data System (ADS)

Kroll, C.; Luz, J.

2003-12-01

Estimation of low streamflow statistics at gauged and ungauged river sites is often a daunting task. This process is further confounded by the presence of intermittent streamflows, where streamflow is sometimes reported as zero, within a region. Streamflows recorded as zero may be zero, or may be less than the measurement detection limit. Such data is often referred to as censored data. Numerous methods have been developed to characterize intermittent streamflow series. Logit regression has been proposed to develop regional models of the probability annual lowflows series (such as 7-day lowflows) are zero. In addition, Tobit regression, a method of regression that allows for censored dependent variables, has been proposed for lowflow regional regression models in regions where the lowflow statistic of interest estimated as zero at some sites in the region. While these methods have been proposed, their use in practice has been limited. Here a delete-one jackknife simulation is presented to examine the performance of Logit and Tobit models of 7-day annual minimum flows in 6 USGS water resource regions in the United States. For the Logit model, an assessment is made of whether sites are correctly classified as having at least 10% of 7-day annual lowflows equal to zero. In such a situation, the 7-day, 10-year lowflow (Q710), a commonly employed low streamflow statistic, would be reported as zero. For the Tobit model, a comparison is made between results from the Tobit model, and from performing either ordinary least squares (OLS) or principal component regression (PCR) after the zero sites are dropped from the analysis. Initial results for the Logit model indicate this method to have a high probability of correctly classifying sites into groups with Q710s as zero and non-zero. Initial results also indicate the Tobit model produces better results than PCR and OLS when more than 5% of the sites in the region have Q710 values calculated as zero.

Mathematical foundations of hybrid data assimilation from a synchronization perspective

NASA Astrophysics Data System (ADS)

Penny, Stephen G.

2017-12-01

The state-of-the-art data assimilation methods used today in operational weather prediction centers around the world can be classified as generalized one-way coupled impulsive synchronization. This classification permits the investigation of hybrid data assimilation methods, which combine dynamic error estimates of the system state with long time-averaged (climatological) error estimates, from a synchronization perspective. Illustrative results show how dynamically informed formulations of the coupling matrix (via an Ensemble Kalman Filter, EnKF) can lead to synchronization when observing networks are sparse and how hybrid methods can lead to synchronization when those dynamic formulations are inadequate (due to small ensemble sizes). A large-scale application with a global ocean general circulation model is also presented. Results indicate that the hybrid methods also have useful applications in generalized synchronization, in particular, for correcting systematic model errors.

Mathematical foundations of hybrid data assimilation from a synchronization perspective.

PubMed

Penny, Stephen G

2017-12-01

The state-of-the-art data assimilation methods used today in operational weather prediction centers around the world can be classified as generalized one-way coupled impulsive synchronization. This classification permits the investigation of hybrid data assimilation methods, which combine dynamic error estimates of the system state with long time-averaged (climatological) error estimates, from a synchronization perspective. Illustrative results show how dynamically informed formulations of the coupling matrix (via an Ensemble Kalman Filter, EnKF) can lead to synchronization when observing networks are sparse and how hybrid methods can lead to synchronization when those dynamic formulations are inadequate (due to small ensemble sizes). A large-scale application with a global ocean general circulation model is also presented. Results indicate that the hybrid methods also have useful applications in generalized synchronization, in particular, for correcting systematic model errors.

A comparison of acoustic and observed sediment classifications as predictor variables for modelling biotope distributions in Galway Bay, Ireland

NASA Astrophysics Data System (ADS)

O'Carroll, Jack P. J.; Kennedy, Robert; Ren, Lei; Nash, Stephen; Hartnett, Michael; Brown, Colin

2017-10-01

The INFOMAR (Integrated Mapping For the Sustainable Development of Ireland's Marine Resource) initiative has acoustically mapped and classified a significant proportion of Ireland's Exclusive Economic Zone (EEZ), and is likely to be an important tool in Ireland's efforts to meet the criteria of the MSFD. In this study, open source and relic data were used in combination with new grab survey data to model EUNIS level 4 biotope distributions in Galway Bay, Ireland. The correct prediction rates of two artificial neural networks (ANNs) were compared to assess the effectiveness of acoustic sediment classifications versus sediments that were visually classified by an expert in the field as predictor variables. To test for autocorrelation between predictor variables the RELATE routine with Spearman rank correlation method was used. Optimal models were derived by iteratively removing predictor variables and comparing the correct prediction rates of each model. The models with the highest correct prediction rates were chosen as optimal. The optimal models each used a combination of salinity (binary; 0 = polyhaline and 1 = euhaline), proximity to reef (binary; 0 = within 50 m and 1 = outside 50 m), depth (continuous; metres) and a sediment descriptor (acoustic or observed) as predictor variables. As the status of benthic habitats is required to be assessed under the MSFD the Ecological Status (ES) of the subtidal sediments of Galway Bay was also assessed using the Infaunal Quality Index. The ANN that used observed sediment classes as predictor variables could correctly predict the distribution of biotopes 67% of the time, compared to 63% for the ANN using acoustic sediment classes. Acoustic sediment ANN predictions were affected by local sediment heterogeneity, and the lack of a mixed sediment class. The all-round poor performance of ANNs is likely to be a result of the temporally variable and sparsely distributed data within the study area.

Learning for VMM + WTA Embedded Classifiers

DTIC Science & Technology

2016-03-31

enabling correct classification of each novel acoustic signal (generator, idle car , and idle truck). The classification structure requires, after...measured on our SoC FPAA IC. The test input is composed of signals from urban environment for 3 objects (generator, idle car , and idle truck...classifier results from a rural truck data set, an urban generator set, and urban idle car dataset. Solid lines represent our extracted background

Similarities among receptor pockets and among compounds: analysis and application to in silico ligand screening.

PubMed

Fukunishi, Yoshifumi; Mikami, Yoshiaki; Nakamura, Haruki

2005-09-01

We developed a new method to evaluate the distances and similarities between receptor pockets or chemical compounds based on a multi-receptor versus multi-ligand docking affinity matrix. The receptors were classified by a cluster analysis based on calculations of the distance between receptor pockets. A set of low homologous receptors that bind a similar compound could be classified into one cluster. Based on this line of reasoning, we proposed a new in silico screening method. According to this method, compounds in a database were docked to multiple targets. The new docking score was a slightly modified version of the multiple active site correction (MASC) score. Receptors that were at a set distance from the target receptor were not included in the analysis, and the modified MASC scores were calculated for the selected receptors. The choice of the receptors is important to achieve a good screening result, and our clustering of receptors is useful to this purpose. This method was applied to the analysis of a set of 132 receptors and 132 compounds, and the results demonstrated that this method achieves a high hit ratio, as compared to that of a uniform sampling, using a receptor-ligand docking program, Sievgene, which was newly developed with a good docking performance yielding 50.8% of the reconstructed complexes at a distance of less than 2 A RMSD.

The contribution of cluster and discriminant analysis to the classification of complex aquifer systems.

PubMed

Panagopoulos, G P; Angelopoulou, D; Tzirtzilakis, E E; Giannoulopoulos, P

2016-10-01

This paper presents an innovated method for the discrimination of groundwater samples in common groups representing the hydrogeological units from where they have been pumped. This method proved very efficient even in areas with complex hydrogeological regimes. The proposed method requires chemical analyses of water samples only for major ions, meaning that it is applicable to most of cases worldwide. Another benefit of the method is that it gives a further insight of the aquifer hydrogeochemistry as it provides the ions that are responsible for the discrimination of the group. The procedure begins with cluster analysis of the dataset in order to classify the samples in the corresponding hydrogeological unit. The feasibility of the method is proven from the fact that the samples of volcanic origin were separated into two different clusters, namely the lava units and the pyroclastic-ignimbritic aquifer. The second step is the discriminant analysis of the data which provides the functions that distinguish the groups from each other and the most significant variables that define the hydrochemical composition of the aquifer. The whole procedure was highly successful as the 94.7 % of the samples were classified to the correct aquifer system. Finally, the resulted functions can be safely used to categorize samples of either unknown or doubtful origin improving thus the quality and the size of existing hydrochemical databases.

[Research on spectra recognition method for cabbages and weeds based on PCA and SIMCA].

PubMed

Zu, Qin; Deng, Wei; Wang, Xiu; Zhao, Chun-Jiang

2013-10-01

In order to improve the accuracy and efficiency of weed identification, the difference of spectral reflectance was employed to distinguish between crops and weeds. Firstly, the different combinations of Savitzky-Golay (SG) convolutional derivation and multiplicative scattering correction (MSC) method were applied to preprocess the raw spectral data. Then the clustering analysis of various types of plants was completed by using principal component analysis (PCA) method, and the feature wavelengths which were sensitive for classifying various types of plants were extracted according to the corresponding loading plots of the optimal principal components in PCA results. Finally, setting the feature wavelengths as the input variables, the soft independent modeling of class analogy (SIMCA) classification method was used to identify the various types of plants. The experimental results of classifying cabbages and weeds showed that on the basis of the optimal pretreatment by a synthetic application of MSC and SG convolutional derivation with SG's parameters set as 1rd order derivation, 3th degree polynomial and 51 smoothing points, 23 feature wavelengths were extracted in accordance with the top three principal components in PCA results. When SIMCA method was used for classification while the previously selected 23 feature wavelengths were set as the input variables, the classification rates of the modeling set and the prediction set were respectively up to 98.6% and 100%.

Does the Spine Surgeon’s Experience Affect Fracture Classification, Assessment of Stability, and Treatment Plan in Thoracolumbar Injuries?

PubMed Central

Kanna, Rishi Mugesh; Schroeder, Gregory D.; Oner, Frank Cumhur; Vialle, Luiz; Chapman, Jens; Dvorak, Marcel; Fehlings, Michael; Shetty, Ajoy Prasad; Schnake, Klaus; Kandziora, Frank; Vaccaro, Alexander R.

2017-01-01

Study Design: Prospective survey-based study. Objectives: The AO Spine thoracolumbar injury classification has been shown to have good reproducibility among clinicians. However, the influence of spine surgeons’ clinical experience on fracture classification, stability assessment, and decision on management based on this classification has not been studied. Furthermore, the usefulness of varying imaging modalities including radiographs, computed tomography (CT) and magnetic resonance imaging (MRI) in the decision process was also studied. Methods: Forty-one spine surgeons from different regions, acquainted with the AOSpine classification system, were provided with 30 thoracolumbar fractures in a 3-step assessment: first radiographs, followed by CT and MRI. Surgeons classified the fracture, evaluated stability, chose management, and identified reasons for any changes. The surgeons were divided into 2 groups based on years of clinical experience as <10 years (n = 12) and >10 years (n = 29). Results: There were no significant differences between the 2 groups in correctly classifying A1, B2, and C type fractures. Surgeons with less experience had more correct diagnosis in classifying A3 (47.2% vs 38.5% in step 1, 73.6% vs 60.3% in step 2 and 77.8% vs 65.5% in step 3), A4 (16.7% vs 24.1% in step 1, 72.9% vs 57.8% in step 2 and 70.8% vs 56.0% in step3) and B1 injuries (31.9% vs 20.7% in step 1, 41.7% vs 36.8% in step 2 and 38.9% vs 33.9% in step 3). In the assessment of fracture stability and decision on treatment, the less and more experienced surgeons performed equally. The selection of a particular treatment plan varied in all subtypes except in A1 and C type injuries. Conclusion: Surgeons’ experience did not significantly affect overall fracture classification, evaluating stability and planning the treatment. Surgeons with less experience had a higher percentage of correct classification in A3 and A4 injuries. Despite variations between them in classification, the assessment of overall stability and management decisions were similar between the 2 groups. PMID:28815158

Prediction of treatment outcome in soft tissue sarcoma based on radiologically defined habitats

NASA Astrophysics Data System (ADS)

Farhidzadeh, Hamidreza; Chaudhury, Baishali; Zhou, Mu; Goldgof, Dmitry B.; Hall, Lawrence O.; Gatenby, Robert A.; Gillies, Robert J.; Raghavan, Meera

2015-03-01

Soft tissue sarcomas are malignant tumors which develop from tissues like fat, muscle, nerves, fibrous tissue or blood vessels. They are challenging to physicians because of their relative infrequency and diverse outcomes, which have hindered development of new therapeutic agents. Additionally, assessing imaging response of these tumors to therapy is also difficult because of their heterogeneous appearance on magnetic resonance imaging (MRI). In this paper, we assessed standard of care MRI sequences performed before and after treatment using 36 patients with soft tissue sarcoma. Tumor tissue was identified by manually drawing a mask on contrast enhanced images. The Otsu segmentation method was applied to segment tumor tissue into low and high signal intensity regions on both T1 post-contrast and T2 without contrast images. This resulted in four distinctive subregions or "habitats." The features used to predict metastatic tumors and necrosis included the ratio of habitat size to whole tumor size and components of 2D intensity histograms. Individual cases were correctly classified as metastatic or non-metastatic disease with 80.55% accuracy and for necrosis ≥ 90 or necrosis <90 with 75.75% accuracy by using meta-classifiers which contained feature selectors and classifiers.

Regulatory element-based prediction identifies new susceptibility regulatory variants for osteoporosis.

PubMed

Yao, Shi; Guo, Yan; Dong, Shan-Shan; Hao, Ruo-Han; Chen, Xiao-Feng; Chen, Yi-Xiao; Chen, Jia-Bin; Tian, Qing; Deng, Hong-Wen; Yang, Tie-Lin

2017-08-01

Despite genome-wide association studies (GWASs) have identified many susceptibility genes for osteoporosis, it still leaves a large part of missing heritability to be discovered. Integrating regulatory information and GWASs could offer new insights into the biological link between the susceptibility SNPs and osteoporosis. We generated five machine learning classifiers with osteoporosis-associated variants and regulatory features data. We gained the optimal classifier and predicted genome-wide SNPs to discover susceptibility regulatory variants. We further utilized Genetic Factors for Osteoporosis Consortium (GEFOS) and three in-house GWASs samples to validate the associations for predicted positive SNPs. The random forest classifier performed best among all machine learning methods with the F1 score of 0.8871. Using the optimized model, we predicted 37,584 candidate SNPs for osteoporosis. According to the meta-analysis results, a list of regulatory variants was significantly associated with osteoporosis after multiple testing corrections and contributed to the expression of known osteoporosis-associated protein-coding genes. In summary, combining GWASs and regulatory elements through machine learning could provide additional information for understanding the mechanism of osteoporosis. The regulatory variants we predicted will provide novel targets for etiology research and treatment of osteoporosis.

Five-way smoking status classification using text hot-spot identification and error-correcting output codes.

PubMed

Cohen, Aaron M

2008-01-01

We participated in the i2b2 smoking status classification challenge task. The purpose of this task was to evaluate the ability of systems to automatically identify patient smoking status from discharge summaries. Our submission included several techniques that we compared and studied, including hot-spot identification, zero-vector filtering, inverse class frequency weighting, error-correcting output codes, and post-processing rules. We evaluated our approaches using the same methods as the i2b2 task organizers, using micro- and macro-averaged F1 as the primary performance metric. Our best performing system achieved a micro-F1 of 0.9000 on the test collection, equivalent to the best performing system submitted to the i2b2 challenge. Hot-spot identification, zero-vector filtering, classifier weighting, and error correcting output coding contributed additively to increased performance, with hot-spot identification having by far the largest positive effect. High performance on automatic identification of patient smoking status from discharge summaries is achievable with the efficient and straightforward machine learning techniques studied here.

Automated Error Detection in Physiotherapy Training.

PubMed

Jovanović, Marko; Seiffarth, Johannes; Kutafina, Ekaterina; Jonas, Stephan M

2018-01-01

Manual skills teaching, such as physiotherapy education, requires immediate teacher feedback for the students during the learning process, which to date can only be performed by expert trainers. A machine-learning system trained only on correct performances to classify and score performed movements, to identify sources of errors in the movement and give feedback to the learner. We acquire IMU and sEMG sensor data from a commercial-grade wearable device and construct an HMM-based model for gesture classification, scoring and feedback giving. We evaluate the model on publicly available and self-generated data of an exemplary movement pattern executions. The model achieves an overall accuracy of 90.71% on the public dataset and 98.9% on our dataset. An AUC of 0.99 for the ROC of the scoring method could be achieved to discriminate between correct and untrained incorrect executions. The proposed system demonstrated its suitability for scoring and feedback in manual skills training.

Prediction and Identification of Krüppel-Like Transcription Factors by Machine Learning Method.

PubMed

Liao, Zhijun; Wang, Xinrui; Chen, Xingyong; Zou, Quan

2017-01-01

The Krüppel-like factors (KLFs) are a family of containing Zn finger(ZF) motif transcription factors with 18 members in human genome, among them, KLF18 is predicted by bioinformatics. KLFs possess various physiological function involving in a number of cancers and other diseases. Here we perform a binary-class classification of KLFs and non-KLFs by machine learning methods. The protein sequences of KLFs and non-KLFs were searched from UniProt and randomly separate them into training dataset(containing positive and negative sequences) and test dataset(containing only negative sequences), after extracting the 188-dimensional(188D) feature vectors we carry out category with four classifiers(GBDT, libSVM, RF, and k-NN). On the human KLFs, we further dig into the evolutionary relationship and motif distribution, and finally we analyze the conserved amino acid residue of three zinc fingers. The classifier model from training dataset were well constructed, and the highest specificity(Sp) was 99.83% from a library for support vector machine(libSVM) and all the correctly classified rates were over 70% for 10-fold cross-validation on test dataset. The 18 human KLFs can be further divided into 7 groups and the zinc finger domains were located at the carboxyl terminus, and many conserved amino acid residues including Cysteine and Histidine, and the span and interval between them were consistent in the three ZF domains. Two classification models for KLFs prediction have been built by novel machine learning methods. Copyright© Bentham Science Publishers; For any queries, please email at epub@benthamscience.org.

Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography.

PubMed

Siu, Ho Chit; Shah, Julie A; Stirling, Leia A

2016-10-25

Surface electromyography (sEMG) is a technique for recording natural muscle activation signals, which can serve as control inputs for exoskeletons and prosthetic devices. Previous experiments have incorporated these signals using both classical and pattern-recognition control methods in order to actuate such devices. We used the results of an experiment incorporating grasp and release actions with object contact to develop an intent-recognition system based on Gaussian mixture models (GMM) and continuous-emission hidden Markov models (HMM) of sEMG data. We tested this system with data collected from 16 individuals using a forearm band with distributed sEMG sensors. The data contain trials with shifted band alignments to assess robustness to sensor placement. This study evaluated and found that pattern-recognition-based methods could classify transient anticipatory sEMG signals in the presence of shifted sensor placement and object contact. With the best-performing classifier, the effect of label lengths in the training data was also examined. A mean classification accuracy of 75.96% was achieved through a unigram HMM method with five mixture components. Classification accuracy on different sub-movements was found to be limited by the length of the shortest sub-movement, which means that shorter sub-movements within dynamic sequences require larger training sets to be classified correctly. This classification of user intent is a potential control mechanism for a dynamic grasping task involving user contact with external objects and noise. Further work is required to test its performance as part of an exoskeleton controller, which involves contact with actuated external surfaces.

Classification of Anticipatory Signals for Grasp and Release from Surface Electromyography

PubMed Central

Siu, Ho Chit; Shah, Julie A.; Stirling, Leia A.

2016-01-01

Surface electromyography (sEMG) is a technique for recording natural muscle activation signals, which can serve as control inputs for exoskeletons and prosthetic devices. Previous experiments have incorporated these signals using both classical and pattern-recognition control methods in order to actuate such devices. We used the results of an experiment incorporating grasp and release actions with object contact to develop an intent-recognition system based on Gaussian mixture models (GMM) and continuous-emission hidden Markov models (HMM) of sEMG data. We tested this system with data collected from 16 individuals using a forearm band with distributed sEMG sensors. The data contain trials with shifted band alignments to assess robustness to sensor placement. This study evaluated and found that pattern-recognition-based methods could classify transient anticipatory sEMG signals in the presence of shifted sensor placement and object contact. With the best-performing classifier, the effect of label lengths in the training data was also examined. A mean classification accuracy of 75.96% was achieved through a unigram HMM method with five mixture components. Classification accuracy on different sub-movements was found to be limited by the length of the shortest sub-movement, which means that shorter sub-movements within dynamic sequences require larger training sets to be classified correctly. This classification of user intent is a potential control mechanism for a dynamic grasping task involving user contact with external objects and noise. Further work is required to test its performance as part of an exoskeleton controller, which involves contact with actuated external surfaces. PMID:27792155

Optimizing pattern recognition-based control for partial-hand prosthesis application.

PubMed

Earley, Eric J; Adewuyi, Adenike A; Hargrove, Levi J

2014-01-01

Partial-hand amputees often retain good residual wrist motion, which is essential for functional activities involving use of the hand. Thus, a crucial design criterion for a myoelectric, partial-hand prosthesis control scheme is that it allows the user to retain residual wrist motion. Pattern recognition (PR) of electromyographic (EMG) signals is a well-studied method of controlling myoelectric prostheses. However, wrist motion degrades a PR system's ability to correctly predict hand-grasp patterns. We studied the effects of (1) window length and number of hand-grasps, (2) static and dynamic wrist motion, and (3) EMG muscle source on the ability of a PR-based control scheme to classify functional hand-grasp patterns. Our results show that training PR classifiers with both extrinsic and intrinsic muscle EMG yields a lower error rate than training with either group by itself (p<0.001); and that training in only variable wrist positions, with only dynamic wrist movements, or with both variable wrist positions and movements results in lower error rates than training in only the neutral wrist position (p<0.001). Finally, our results show that both an increase in window length and a decrease in the number of grasps available to the classifier significantly decrease classification error (p<0.001). These results remained consistent whether the classifier selected or maintained a hand-grasp.

Predict or classify: The deceptive role of time-locking in brain signal classification

NASA Astrophysics Data System (ADS)

Rusconi, Marco; Valleriani, Angelo

2016-06-01

Several experimental studies claim to be able to predict the outcome of simple decisions from brain signals measured before subjects are aware of their decision. Often, these studies use multivariate pattern recognition methods with the underlying assumption that the ability to classify the brain signal is equivalent to predict the decision itself. Here we show instead that it is possible to correctly classify a signal even if it does not contain any predictive information about the decision. We first define a simple stochastic model that mimics the random decision process between two equivalent alternatives, and generate a large number of independent trials that contain no choice-predictive information. The trials are first time-locked to the time point of the final event and then classified using standard machine-learning techniques. The resulting classification accuracy is above chance level long before the time point of time-locking. We then analyze the same trials using information theory. We demonstrate that the high classification accuracy is a consequence of time-locking and that its time behavior is simply related to the large relaxation time of the process. We conclude that when time-locking is a crucial step in the analysis of neural activity patterns, both the emergence and the timing of the classification accuracy are affected by structural properties of the network that generates the signal.

Boosted classification trees result in minor to modest improvement in the accuracy in classifying cardiovascular outcomes compared to conventional classification trees

PubMed Central

Austin, Peter C; Lee, Douglas S

2011-01-01

Purpose: Classification trees are increasingly being used to classifying patients according to the presence or absence of a disease or health outcome. A limitation of classification trees is their limited predictive accuracy. In the data-mining and machine learning literature, boosting has been developed to improve classification. Boosting with classification trees iteratively grows classification trees in a sequence of reweighted datasets. In a given iteration, subjects that were misclassified in the previous iteration are weighted more highly than subjects that were correctly classified. Classifications from each of the classification trees in the sequence are combined through a weighted majority vote to produce a final classification. The authors' objective was to examine whether boosting improved the accuracy of classification trees for predicting outcomes in cardiovascular patients. Methods: We examined the utility of boosting classification trees for classifying 30-day mortality outcomes in patients hospitalized with either acute myocardial infarction or congestive heart failure. Results: Improvements in the misclassification rate using boosted classification trees were at best minor compared to when conventional classification trees were used. Minor to modest improvements to sensitivity were observed, with only a negligible reduction in specificity. For predicting cardiovascular mortality, boosted classification trees had high specificity, but low sensitivity. Conclusions: Gains in predictive accuracy for predicting cardiovascular outcomes were less impressive than gains in performance observed in the data mining literature. PMID:22254181

A novel multiple marker bioassay utilizing HE4 and CA125 for the prediction of ovarian cancer in patients with a pelvic mass

PubMed Central

Moore, Richard G.; McMeekin, D. Scott; Brown, Amy K.; DiSilvestro, Paul; Miller, M. Craig; Allard, W. Jeffrey; Gajewski, Walter; Kurman, Robert; Bast, Robert C.; Skates, Steven J.

2012-01-01

Introduction Patients diagnosed with epithelial ovarian cancer (EOC) have improved outcomes when cared for at centers experienced in the management of EOC. The objective of this trial was to validate a predictive model to assess the risk for EOC in women with a pelvic mass. Methods Women diagnosed with a pelvic mass and scheduled to have surgery were enrolled on a multicenter prospective study. Preoperative serum levels of HE4 and CA125 were measured. Separate logistic regression algorithms for premenopausal and postmenopausal women were utilized to categorize patients into low and high risk groups for EOC. Results Twelve sites enrolled 531 evaluable patients with 352 benign tumors, 129 EOC, 22 LMP tumors, 6 non EOC and 22 non ovarian cancers. The postmenopausal group contained 150 benign cases of which 112 were classified as low risk giving a specificity of 75.0% (95% CI 66.9-81.4), and 111 EOC and 6 LMP tumors of which 108 were classified as high risk giving a sensitivity of 92.3% (95% CI=85.9-96.4). The premenopausal group had 202 benign cases of which 151 were classified as low risk providing a specificity of 74.8% (95% CI=68.2--80.6), and 18 EOC and 16 LMP tumors of which 26 were classified as high risk, providing a sensitivity of 76.5% (95% CI=58.8--89.3). Conclusion An algorithm utilizing HE4 and CA125 successfully classified patients into high and low risk groups with 93.8% of EOC correctly classified as high risk. This model can be used to effectively triage patients to centers of excellence. PMID:18851871

DOE Office of Scientific and Technical Information (OSTI.GOV)

Islam, Md. Shafiqul, E-mail: shafique@eng.ukm.my; Hannan, M.A., E-mail: hannan@eng.ukm.my; Basri, Hassan

Highlights: • Solid waste bin level detection using Dynamic Time Warping (DTW). • Gabor wavelet filter is used to extract the solid waste image features. • Multi-Layer Perceptron classifier network is used for bin image classification. • The classification performance evaluated by ROC curve analysis. - Abstract: The increasing requirement for Solid Waste Management (SWM) has become a significant challenge for municipal authorities. A number of integrated systems and methods have introduced to overcome this challenge. Many researchers have aimed to develop an ideal SWM system, including approaches involving software-based routing, Geographic Information Systems (GIS), Radio-frequency Identification (RFID), or sensormore » intelligent bins. Image processing solutions for the Solid Waste (SW) collection have also been developed; however, during capturing the bin image, it is challenging to position the camera for getting a bin area centralized image. As yet, there is no ideal system which can correctly estimate the amount of SW. This paper briefly discusses an efficient image processing solution to overcome these problems. Dynamic Time Warping (DTW) was used for detecting and cropping the bin area and Gabor wavelet (GW) was introduced for feature extraction of the waste bin image. Image features were used to train the classifier. A Multi-Layer Perceptron (MLP) classifier was used to classify the waste bin level and estimate the amount of waste inside the bin. The area under the Receiver Operating Characteristic (ROC) curves was used to statistically evaluate classifier performance. The results of this developed system are comparable to previous image processing based system. The system demonstration using DTW with GW for feature extraction and an MLP classifier led to promising results with respect to the accuracy of waste level estimation (98.50%). The application can be used to optimize the routing of waste collection based on the estimated bin level.« less

CANDELS Visual Classifications: Scheme, Data Release, and First Results

NASA Astrophysics Data System (ADS)

Kartaltepe, Jeyhan S.; Mozena, Mark; Kocevski, Dale; McIntosh, Daniel H.; Lotz, Jennifer; Bell, Eric F.; Faber, Sandy; Ferguson, Harry; Koo, David; Bassett, Robert; Bernyk, Maksym; Blancato, Kirsten; Bournaud, Frederic; Cassata, Paolo; Castellano, Marco; Cheung, Edmond; Conselice, Christopher J.; Croton, Darren; Dahlen, Tomas; de Mello, Duilia F.; DeGroot, Laura; Donley, Jennifer; Guedes, Javiera; Grogin, Norman; Hathi, Nimish; Hilton, Matt; Hollon, Brett; Koekemoer, Anton; Liu, Nick; Lucas, Ray A.; Martig, Marie; McGrath, Elizabeth; McPartland, Conor; Mobasher, Bahram; Morlock, Alice; O'Leary, Erin; Peth, Mike; Pforr, Janine; Pillepich, Annalisa; Rosario, David; Soto, Emmaris; Straughn, Amber; Telford, Olivia; Sunnquist, Ben; Trump, Jonathan; Weiner, Benjamin; Wuyts, Stijn; Inami, Hanae; Kassin, Susan; Lani, Caterina; Poole, Gregory B.; Rizer, Zachary

2015-11-01

We have undertaken an ambitious program to visually classify all galaxies in the five CANDELS fields down to H < 24.5 involving the dedicated efforts of over 65 individual classifiers. Once completed, we expect to have detailed morphological classifications for over 50,000 galaxies spanning 0 < z < 4 over all the fields, with classifications from 3 to 5 independent classifiers for each galaxy. Here, we present our detailed visual classification scheme, which was designed to cover a wide range of CANDELS science goals. This scheme includes the basic Hubble sequence types, but also includes a detailed look at mergers and interactions, the clumpiness of galaxies, k-corrections, and a variety of other structural properties. In this paper, we focus on the first field to be completed—GOODS-S, which has been classified at various depths. The wide area coverage spanning the full field (wide+deep+ERS) includes 7634 galaxies that have been classified by at least three different people. In the deep area of the field, 2534 galaxies have been classified by at least five different people at three different depths. With this paper, we release to the public all of the visual classifications in GOODS-S along with the Perl/Tk GUI that we developed to classify galaxies. We present our initial results here, including an analysis of our internal consistency and comparisons among multiple classifiers as well as a comparison to the Sérsic index. We find that the level of agreement among classifiers is quite good (>70% across the full magnitude range) and depends on both the galaxy magnitude and the galaxy type, with disks showing the highest level of agreement (>50%) and irregulars the lowest (<10%). A comparison of our classifications with the Sérsic index and rest-frame colors shows a clear separation between disk and spheroid populations. Finally, we explore morphological k-corrections between the V-band and H-band observations and find that a small fraction (84 galaxies in total) are classified as being very different between these two bands. These galaxies typically have very clumpy and extended morphology or are very faint in the V-band.

Moving towards the goals of FP2020 - classifying contraceptives.

PubMed

Festin, Mario Philip R; Kiarie, James; Solo, Julie; Spieler, Jeffrey; Malarcher, Shawn; Van Look, Paul F A; Temmerman, Marleen

2016-10-01

With the renewed focus on family planning, a clear and transparent understanding is needed for the consistent classification of contraceptives, especially in the commonly used modern/traditional system. The World Health Organization Department of Reproductive Health and Research and the United States Agency for International Development (USAID) therefore convened a technical consultation in January 2015 to address issues related to classifying contraceptives. The consultation defined modern contraceptive methods as having a sound basis in reproductive biology, a precise protocol for correct use and evidence of efficacy under various conditions based on appropriately designed studies. Methods in country programs like Fertility Awareness Based Methods [such as Standard Days Method (SDM) and TwoDay Method], Lactational Amenorrhea Method (LAM) and emergency contraception should be reported as modern. Herbs, charms and vaginal douching are not counted as contraceptive methods as they have no scientific basis in preventing pregnancy nor are in country programs. More research is needed on defining and measuring use of emergency contraceptive methods, to reflect their contribution to reducing unmet need. The ideal contraceptive classification system should be simple, easy to use, clear and consistent, with greater parsimony. Measurement challenges remain but should not be the driving force to determine what methods are counted or reported as modern or not. Family planning programs should consider multiple attributes of contraceptive methods (e.g., level of effectiveness, need for program support, duration of labeled use, hormonal or nonhormonal) to ensure they provide a variety of methods to meet the needs of women and men. Copyright © 2016 The Authors. Published by Elsevier Inc. All rights reserved.

Classification bias in commercial business lists for retail food stores in the U.S.

PubMed Central

2012-01-01

Background Aspects of the food environment such as the availability of different types of food stores have recently emerged as key modifiable factors that may contribute to the increased prevalence of obesity. Given that many of these studies have derived their results based on secondary datasets and the relationship of food stores with individual weight outcomes has been reported to vary by store type, it is important to understand the extent to which often-used secondary data correctly classify food stores. We evaluated the classification bias of food stores in Dun & Bradstreet (D&B) and InfoUSA commercial business lists. Methods We performed a full census in 274 randomly selected census tracts in the Chicago metropolitan area and collected detailed store attributes inside stores for classification. Store attributes were compared by classification match status and store type. Systematic classification bias by census tract characteristics was assessed in multivariate regression. Results D&B had a higher classification match rate than InfoUSA for supermarkets and grocery stores, while InfoUSA was higher for convenience stores. Both lists were more likely to correctly classify large supermarkets, grocery stores, and convenience stores with more cash registers and different types of service counters (supermarkets and grocery stores only). The likelihood of a correct classification match for supermarkets and grocery stores did not vary systemically by tract characteristics whereas convenience stores were more likely to be misclassified in predominately Black tracts. Conclusion Researches can rely on classification of food stores in commercial datasets for supermarkets and grocery stores whereas classifications for convenience and specialty food stores are subject to some systematic bias by neighborhood racial/ethnic composition. PMID:22512874

Who's your momma? Recognizing maternal origin of juvenile steelhead using injections of strontium chloride to create transgenerational marks

USGS Publications Warehouse

Shippentower, Gene E.; Schreck, Carl B.; Heppell, Scott A.

2011-01-01

We sought to determine whether a strontium chloride injection could be used to create a transgenerational otolith mark in steelhead Oncorhynchus mykiss. Two strontium injection trials and a survey of strontium: calcium (Sr:Ca) ratios in juvenile steelhead from various steelhead hatcheries were conducted to test the feasibility of the technique. In both trials, progeny of fish injected with strontium had significantly higher Sr:Ca ratios in the primordial region of their otoliths, as measured by an electron wavelength dispersive microprobe. In trial 1, the 5,000-mg/L treatment level showed that 56.8% of the otoliths were correctly classified, 12.2% being misclassified as belonging to the 0-mg/L treatment. In trial 2, the 20,000-mg/L treatment level showed that 30.8% of the otoliths were correctly classified, 13.5% being misclassified as belonging to the 0-mg/L treatment. There were no differences in the fertilization rates of eggs or survival rates of fry between the treatment and control groups. The Sr:Ca ratios in otoliths collected from various hatchery populations of steelhead varied and were greater than those found in otoliths from control fish in both of our injection trials. This study suggests that the marking technique led to recognizable increases in Sr:Ca ratios in some otoliths collected from fry produced by injected females. Not all progeny showed such increases, however, suggesting that the method holds promise but requires further refinement to reduce variation. Overall, there was a correct classification of about 40% across all treatments and trials; the variation in Sr:Ca ratios found among experimental trials and hatcheries indicates that care must be taken if the technique is employed where fish from more than one hatchery could be involved.

Latency correction of event-related potentials between different experimental protocols

NASA Astrophysics Data System (ADS)

Iturrate, I.; Chavarriaga, R.; Montesano, L.; Minguez, J.; Millán, JdR

2014-06-01

Objective. A fundamental issue in EEG event-related potentials (ERPs) studies is the amount of data required to have an accurate ERP model. This also impacts the time required to train a classifier for a brain-computer interface (BCI). This issue is mainly due to the poor signal-to-noise ratio and the large fluctuations of the EEG caused by several sources of variability. One of these sources is directly related to the experimental protocol or application designed, and may affect the amplitude or latency of ERPs. This usually prevents BCI classifiers from generalizing among different experimental protocols. In this paper, we analyze the effect of the amplitude and the latency variations among different experimental protocols based on the same type of ERP. Approach. We present a method to analyze and compensate for the latency variations in BCI applications. The algorithm has been tested on two widely used ERPs (P300 and observation error potentials), in three experimental protocols in each case. We report the ERP analysis and single-trial classification. Main results. The results obtained show that the designed experimental protocols significantly affect the latency of the recorded potentials but not the amplitudes. Significance. These results show how the use of latency-corrected data can be used to generalize the BCIs, reducing the calibration time when facing a new experimental protocol.

Expanding the Space of Plausible Solutions in a Medical Tutoring System for Problem-Based Learning

ERIC Educational Resources Information Center

Kazi, Hameedullah; Haddawy, Peter; Suebnukarn, Siriwan

2009-01-01

In well-defined domains such as Physics, Mathematics, and Chemistry, solutions to a posed problem can objectively be classified as correct or incorrect. In ill-defined domains such as medicine, the classification of solutions to a patient problem as correct or incorrect is much more complex. Typical tutoring systems accept only a small set of…

Predictive models reduce talent development costs in female gymnastics.

PubMed

Pion, Johan; Hohmann, Andreas; Liu, Tianbiao; Lenoir, Matthieu; Segers, Veerle

2017-04-01

This retrospective study focuses on the comparison of different predictive models based on the results of a talent identification test battery for female gymnasts. We studied to what extent these models have the potential to optimise selection procedures, and at the same time reduce talent development costs in female artistic gymnastics. The dropout rate of 243 female elite gymnasts was investigated, 5 years past talent selection, using linear (discriminant analysis) and non-linear predictive models (Kohonen feature maps and multilayer perceptron). The coaches classified 51.9% of the participants correct. Discriminant analysis improved the correct classification to 71.6% while the non-linear technique of Kohonen feature maps reached 73.7% correctness. Application of the multilayer perceptron even classified 79.8% of the gymnasts correctly. The combination of different predictive models for talent selection can avoid deselection of high-potential female gymnasts. The selection procedure based upon the different statistical analyses results in decrease of 33.3% of cost because the pool of selected athletes can be reduced to 92 instead of 138 gymnasts (as selected by the coaches). Reduction of the costs allows the limited resources to be fully invested in the high-potential athletes.

An efficient approach for surveillance of childhood diabetes by type derived from electronic health record data: the SEARCH for Diabetes in Youth Study

PubMed Central

Zhong, Victor W; Obeid, Jihad S; Craig, Jean B; Pfaff, Emily R; Thomas, Joan; Jaacks, Lindsay M; Beavers, Daniel P; Carey, Timothy S; Lawrence, Jean M; Dabelea, Dana; Hamman, Richard F; Bowlby, Deborah A; Pihoker, Catherine; Saydah, Sharon H

2016-01-01

Objective To develop an efficient surveillance approach for childhood diabetes by type across 2 large US health care systems, using phenotyping algorithms derived from electronic health record (EHR) data. Materials and Methods Presumptive diabetes cases <20 years of age from 2 large independent health care systems were identified as those having ≥1 of the 5 indicators in the past 3.5 years, including elevated HbA1c, elevated blood glucose, diabetes-related billing codes, patient problem list, and outpatient anti-diabetic medications. EHRs of all the presumptive cases were manually reviewed, and true diabetes status and diabetes type were determined. Algorithms for identifying diabetes cases overall and classifying diabetes type were either prespecified or derived from classification and regression tree analysis. Surveillance approach was developed based on the best algorithms identified. Results We developed a stepwise surveillance approach using billing code–based prespecified algorithms and targeted manual EHR review, which efficiently and accurately ascertained and classified diabetes cases by type, in both health care systems. The sensitivity and positive predictive values in both systems were approximately ≥90% for ascertaining diabetes cases overall and classifying cases with type 1 or type 2 diabetes. About 80% of the cases with “other” type were also correctly classified. This stepwise surveillance approach resulted in a >70% reduction in the number of cases requiring manual validation compared to traditional surveillance methods. Conclusion EHR data may be used to establish an efficient approach for large-scale surveillance for childhood diabetes by type, although some manual effort is still needed. PMID:27107449

[Classification of Children with Attention-Deficit/Hyperactivity Disorder and Typically Developing Children Based on Electroencephalogram Principal Component Analysis and k-Nearest Neighbor].

PubMed

Yang, Jiaojiao; Guo, Qian; Li, Wenjie; Wang, Suhong; Zou, Ling

2016-04-01

This paper aims to assist the individual clinical diagnosis of children with attention-deficit/hyperactivity disorder using electroencephalogram signal detection method.Firstly,in our experiments,we obtained and studied the electroencephalogram signals from fourteen attention-deficit/hyperactivity disorder children and sixteen typically developing children during the classic interference control task of Simon-spatial Stroop,and we completed electroencephalogram data preprocessing including filtering,segmentation,removal of artifacts and so on.Secondly,we selected the subset electroencephalogram electrodes using principal component analysis(PCA)method,and we collected the common channels of the optimal electrodes which occurrence rates were more than 90%in each kind of stimulation.We then extracted the latency(200~450ms)mean amplitude features of the common electrodes.Finally,we used the k-nearest neighbor(KNN)classifier based on Euclidean distance and the support vector machine(SVM)classifier based on radial basis kernel function to classify.From the experiment,at the same kind of interference control task,the attention-deficit/hyperactivity disorder children showed lower correct response rates and longer reaction time.The N2 emerged in prefrontal cortex while P2 presented in the inferior parietal area when all kinds of stimuli demonstrated.Meanwhile,the children with attention-deficit/hyperactivity disorder exhibited markedly reduced N2 and P2amplitude compared to typically developing children.KNN resulted in better classification accuracy than SVM classifier,and the best classification rate was 89.29%in StI task.The results showed that the electroencephalogram signals were different in the brain regions of prefrontal cortex and inferior parietal cortex between attention-deficit/hyperactivity disorder and typically developing children during the interference control task,which provided a scientific basis for the clinical diagnosis of attention-deficit/hyperactivity disorder individuals.

Deep Learning at Chest Radiography: Automated Classification of Pulmonary Tuberculosis by Using Convolutional Neural Networks.

PubMed

Lakhani, Paras; Sundaram, Baskaran

2017-08-01

Purpose To evaluate the efficacy of deep convolutional neural networks (DCNNs) for detecting tuberculosis (TB) on chest radiographs. Materials and Methods Four deidentified HIPAA-compliant datasets were used in this study that were exempted from review by the institutional review board, which consisted of 1007 posteroanterior chest radiographs. The datasets were split into training (68.0%), validation (17.1%), and test (14.9%). Two different DCNNs, AlexNet and GoogLeNet, were used to classify the images as having manifestations of pulmonary TB or as healthy. Both untrained and pretrained networks on ImageNet were used, and augmentation with multiple preprocessing techniques. Ensembles were performed on the best-performing algorithms. For cases where the classifiers were in disagreement, an independent board-certified cardiothoracic radiologist blindly interpreted the images to evaluate a potential radiologist-augmented workflow. Receiver operating characteristic curves and areas under the curve (AUCs) were used to assess model performance by using the DeLong method for statistical comparison of receiver operating characteristic curves. Results The best-performing classifier had an AUC of 0.99, which was an ensemble of the AlexNet and GoogLeNet DCNNs. The AUCs of the pretrained models were greater than that of the untrained models (P < .001). Augmenting the dataset further increased accuracy (P values for AlexNet and GoogLeNet were .03 and .02, respectively). The DCNNs had disagreement in 13 of the 150 test cases, which were blindly reviewed by a cardiothoracic radiologist, who correctly interpreted all 13 cases (100%). This radiologist-augmented approach resulted in a sensitivity of 97.3% and specificity 100%. Conclusion Deep learning with DCNNs can accurately classify TB at chest radiography with an AUC of 0.99. A radiologist-augmented approach for cases where there was disagreement among the classifiers further improved accuracy. © RSNA, 2017.

Rapid Grading of Fundus Photographs for Diabetic Retinopathy Using Crowdsourcing

PubMed Central

Villanti, Andrea C; Pearson, Jennifer L; Kirchner, Thomas R; Gupta, Omesh P; Shah, Chirag P

2014-01-01

Background Screening for diabetic retinopathy is both effective and cost-effective, but rates of screening compliance remain suboptimal. As screening improves, new methods to deal with screening data may help reduce the human resource needs. Crowdsourcing has been used in many contexts to harness distributed human intelligence for the completion of small tasks including image categorization. Objective Our goal was to develop and validate a novel method for fundus photograph grading. Methods An interface for fundus photo classification was developed for the Amazon Mechanical Turk crowdsourcing platform. We posted 19 expert-graded images for grading by Turkers, with 10 repetitions per photo for an initial proof-of-concept (Phase I). Turkers were paid US $0.10 per image. In Phase II, one prototypical image from each of the four grading categories received 500 unique Turker interpretations. Fifty draws of 1-50 Turkers were then used to estimate the variance in accuracy derived from randomly drawn samples of increasing crowd size to determine the minimum number of Turkers needed to produce valid results. In Phase III, the interface was modified to attempt to improve Turker grading. Results Across 230 grading instances in the normal versus abnormal arm of Phase I, 187 images (81.3%) were correctly classified by Turkers. Average time to grade each image was 25 seconds, including time to review training images. With the addition of grading categories, time to grade each image increased and percentage of images graded correctly decreased. In Phase II, area under the curve (AUC) of the receiver-operator characteristic (ROC) indicated that sensitivity and specificity were maximized after 7 graders for ratings of normal versus abnormal (AUC=0.98) but was significantly reduced (AUC=0.63) when Turkers were asked to specify the level of severity. With improvements to the interface in Phase III, correctly classified images by the mean Turker grade in four-category grading increased to a maximum of 52.6% (10/19 images) from 26.3% (5/19 images). Throughout all trials, 100% sensitivity for normal versus abnormal was maintained. Conclusions With minimal training, the Amazon Mechanical Turk workforce can rapidly and correctly categorize fundus photos of diabetic patients as normal or abnormal, though further refinement of the methodology is needed to improve Turker ratings of the degree of retinopathy. Images were interpreted for a total cost of US $1.10 per eye. Crowdsourcing may offer a novel and inexpensive means to reduce the skilled grader burden and increase screening for diabetic retinopathy. PMID:25356929

Error compensation of single-antenna attitude determination using GNSS for Low-dynamic applications

NASA Astrophysics Data System (ADS)

Chen, Wen; Yu, Chao; Cai, Miaomiao

2017-04-01

GNSS-based single-antenna pseudo-attitude determination method has attracted more and more attention from the field of high-dynamic navigation due to its low cost, low system complexity, and no temporal accumulated errors. Related researches indicate that this method can be an important complement or even an alternative to the traditional sensors for general accuracy requirement (such as small UAV navigation). The application of single-antenna attitude determining method to low-dynamic carrier has just started. Different from the traditional multi-antenna attitude measurement technique, the pseudo-attitude attitude determination method calculates the rotation angle of the carrier trajectory relative to the earth. Thus it inevitably contains some deviations comparing with the real attitude angle. In low-dynamic application, these deviations are particularly noticeable, which may not be ignored. The causes of the deviations can be roughly classified into three categories, including the measurement error, the offset error, and the lateral error. Empirical correction strategies for the formal two errors have been promoted in previous study, but lack of theoretical support. In this paper, we will provide quantitative description of the three type of errors and discuss the related error compensation methods. Vehicle and shipborne experiments were carried out to verify the feasibility of the proposed correction methods. Keywords: Error compensation; Single-antenna; GNSS; Attitude determination; Low-dynamic

[Research on discrimination of cabbage and weeds based on visible and near-infrared spectrum analysis].

PubMed

Zu, Qin; Zhao, Chun-Jiang; Deng, Wei; Wang, Xiu

2013-05-01

The automatic identification of weeds forms the basis for precision spraying of crops infest. The canopy spectral reflectance within the 350-2 500 nm band of two strains of cabbages and five kinds of weeds such as barnyard grass, setaria, crabgrass, goosegrass and pigweed was acquired by ASD spectrometer. According to the spectral curve characteristics, the data in different bands were compressed with different levels to improve the operation efficiency. Firstly, the spectrum was denoised in accordance with the different order of multiple scattering correction (MSC) method and Savitzky-Golay (SG) convolution smoothing method set by different parameters, then the model was built by combining the principal component analysis (PCA) method to extract principal components, finally all kinds of plants were classified by using the soft independent modeling of class analogy (SIMCA) taxonomy and the classification results were compared. The tests results indicate that after the pretreatment of the spectral data with the method of the combination of MSC and SG set with 3rd order, 5th degree polynomial, 21 smoothing points, and the top 10 principal components extraction using PCA as a classification model input variable, 100% correct classification rate was achieved, and it is able to identify cabbage and several kinds of common weeds quickly and nondestructively.

The potential of pigeons as surrogate observers in medical image perception studies

NASA Astrophysics Data System (ADS)

Krupinski, Elizabeth A.; Levenson, Richard M.; Navarro, Victor; Wasserman, Edward A.

2016-03-01

Assessment of medical image quality and how changes in image appearance impact performance are critical but assessment can be expensive and time-consuming. Could an animal (pigeon) observer with well-known visual skills and documented ability to distinguish complex visual stimuli serve as a surrogate for the human observer? Using sets of whole slide pathology (WSI) and mammographic images we trained pigeons (cohorts of 4) to detect and/or classify lesions in medical images. Standard training methods were used. A chamber equipped with a 15' display with a resistive touchscreen was used to display the images and record responses (pecks). Pigeon pellets were dispensed for correct responses. The pigeons readily learned to distinguish benign from malignant breast cancer histopathology in WSI (mean % correct responses rose 50% to 85% over 15 days) and generalized readily from 4X to 10X and 20X magnifications; to detect microcalcifications (mean % correct responses rose 50% to over 85% over 25 days); to distinguish benign from malignant breast masses (3 of 4 birds learned this task to around 80% and 60% over 10 days); and ignore compression artifacts in WSI (performance with uncompressed slides averaged 95% correct; 15:1 and 27:1 compression slides averaged 92% and 90% correct). Pigeons models may help us better understand medical image perception and may be useful in quality assessment by serving as surrogate observers for certain types of studies.

Fully convolutional network with cluster for semantic segmentation

NASA Astrophysics Data System (ADS)

Ma, Xiao; Chen, Zhongbi; Zhang, Jianlin

2018-04-01

At present, image semantic segmentation technology has been an active research topic for scientists in the field of computer vision and artificial intelligence. Especially, the extensive research of deep neural network in image recognition greatly promotes the development of semantic segmentation. This paper puts forward a method based on fully convolutional network, by cluster algorithm k-means. The cluster algorithm using the image's low-level features and initializing the cluster centers by the super-pixel segmentation is proposed to correct the set of points with low reliability, which are mistakenly classified in great probability, by the set of points with high reliability in each clustering regions. This method refines the segmentation of the target contour and improves the accuracy of the image segmentation.

Threshold Assessment of Gear Diagnostic Tools on Flight and Test Rig Data

NASA Technical Reports Server (NTRS)

Dempsey, Paula J.; Mosher, Marianne; Huff, Edward M.

2003-01-01

A method for defining thresholds for vibration-based algorithms that provides the minimum number of false alarms while maintaining sensitivity to gear damage was developed. This analysis focused on two vibration based gear damage detection algorithms, FM4 and MSA. This method was developed using vibration data collected during surface fatigue tests performed in a spur gearbox rig. The thresholds were defined based on damage progression during tests with damage. The thresholds false alarm rates were then evaluated on spur gear tests without damage. Next, the same thresholds were applied to flight data from an OH-58 helicopter transmission. Results showed that thresholds defined in test rigs can be used to define thresholds in flight to correctly classify the transmission operation as normal.

The Utility of the SASSI-3 in Early Detection of Substance Use Disorders in Not Guilty by Reason of Insanity Acquittees: An Exploratory Study

ERIC Educational Resources Information Center

Wright, Ervin E., II; Piazza, Nick J.; Laux, John M.

2008-01-01

Previous studies have shown the Substance Abuse Subtle Screening Inventory-3 (G. Miller, 1999) to be valid in classifying substance use disorders in forensic and mentally ill populations. The authors found that it also correctly classified substance use disorders in the understudied not guilty by reason of insanity population. (Contains 3 tables.)

Development of a method for the determination of Fusarium fungi on corn using mid-infrared spectroscopy with attenuated total reflection and chemometrics.

PubMed

Kos, Gregor; Lohninger, Hans; Krska, Rudolf

2003-03-01

A novel method, which enables the determination of fungal infection with Fusarium graminearum on corn within minutes, is presented. The ground sample was sieved and the particle size fraction between >250 and 100 microm was used for mid-infrared/attenuated total reflection (ATR) measurements. The sample was pressed onto the ATR crystal, and reproducible pressure was applied. After the spectra were recorded, they were subjected to principle component analysis (PCA) and classified using cluster analysis. Observed changes in the spectra reflected changes in protein, carbohydrate, and lipid contents. Ergosterol (for the total fungal biomass) and the toxin deoxynivalenol (DON; a secondary metabolite) of Fusarium fungi served as reference parameters, because of their relevance for the examination of corn based food and feed. The repeatability was highly improved by sieving prior to recording the spectra, resulting in a better clustering in PCA score/score plots. The developed method enabled the separation of samples with a toxin content of as low as 310 microg/kg from noncontaminated (blank) samples. Investigated concentration ranges were 880-3600 microg/kg for ergosterol and 310-2596 microg/kg for DON. The percentage of correctly classified samples was up to 100% for individual samples compared with a number of blank samples.

Rapid classification of heavy metal-exposed freshwater bacteria by infrared spectroscopy coupled with chemometrics using supervised method

NASA Astrophysics Data System (ADS)

Gurbanov, Rafig; Gozen, Ayse Gul; Severcan, Feride

2018-01-01

Rapid, cost-effective, sensitive and accurate methodologies to classify bacteria are still in the process of development. The major drawbacks of standard microbiological, molecular and immunological techniques call for the possible usage of infrared (IR) spectroscopy based supervised chemometric techniques. Previous applications of IR based chemometric methods have demonstrated outstanding findings in the classification of bacteria. Therefore, we have exploited an IR spectroscopy based chemometrics using supervised method namely Soft Independent Modeling of Class Analogy (SIMCA) technique for the first time to classify heavy metal-exposed bacteria to be used in the selection of suitable bacteria to evaluate their potential for environmental cleanup applications. Herein, we present the powerful differentiation and classification of laboratory strains (Escherichia coli and Staphylococcus aureus) and environmental isolates (Gordonia sp. and Microbacterium oxydans) of bacteria exposed to growth inhibitory concentrations of silver (Ag), cadmium (Cd) and lead (Pb). Our results demonstrated that SIMCA was able to differentiate all heavy metal-exposed and control groups from each other with 95% confidence level. Correct identification of randomly chosen test samples in their corresponding groups and high model distances between the classes were also achieved. We report, for the first time, the success of IR spectroscopy coupled with supervised chemometric technique SIMCA in classification of different bacteria under a given treatment.

Evolution of the anti-truncated stellar profiles of S0 galaxies since z = 0.6 in the SHARDS survey. I. Sample and methods

NASA Astrophysics Data System (ADS)

Borlaff, Alejandro; Eliche-Moral, M. Carmen; Beckman, John E.; Ciambur, Bogdan C.; Pérez-González, Pablo G.; Barro, Guillermo; Cava, Antonio; Cardiel, Nicolas

2017-08-01

Context. The controversy about the origin of the structure of early-type S0-E/S0 galaxies may be due to the difficulty of comparing surface brightness profiles with different depths, photometric corrections and point spread function (PSF) effects (which are almost always ignored). Aims: We aim to quantify the properties of Type-III (anti-truncated) discs in a sample of S0 galaxies at 0.2

Predictive models of alcohol use based on attitudes and individual values.

PubMed

García del Castillo Rodríguez, José A; López-Sánchez, Carmen; Quiles Soler, M Carmen; García del Castillo-López, Alvaro; Gázquez Pertusa, Mónica; Marzo Campos, Juan Carlos; Inglés, Candido J

2013-01-01

Two predictive models are developed in this article: the first is designed to predict people's attitudes to alcoholic drinks, while the second sets out to predict the use of alcohol in relation to selected individual values. University students (N = 1,500) were recruited through stratified sampling based on sex and academic discipline. The questionnaire used obtained information on participants' alcohol use, attitudes and personal values. The results show that the attitudes model correctly classifies 76.3% of cases. Likewise, the model for level of alcohol use correctly classifies 82% of cases. According to our results, we can conclude that there are a series of individual values that influence drinking and attitudes to alcohol use, which therefore provides us with a potentially powerful instrument for developing preventive intervention programs.

Discriminative Ocular Artifact Correction for Feature Learning in EEG Analysis.

PubMed

Xinyang Li; Cuntai Guan; Haihong Zhang; Kai Keng Ang

2017-08-01

Electrooculogram (EOG) artifact contamination is a common critical issue in general electroencephalogram (EEG) studies as well as in brain-computer interface (BCI) research. It is especially challenging when dedicated EOG channels are unavailable or when there are very few EEG channels available for independent component analysis based ocular artifact removal. It is even more challenging to avoid loss of the signal of interest during the artifact correction process, where the signal of interest can be multiple magnitudes weaker than the artifact. To address these issues, we propose a novel discriminative ocular artifact correction approach for feature learning in EEG analysis. Without extra ocular movement measurements, the artifact is extracted from raw EEG data, which is totally automatic and requires no visual inspection of artifacts. Then, artifact correction is optimized jointly with feature extraction by maximizing oscillatory correlations between trials from the same class and minimizing them between trials from different classes. We evaluate this approach on a real-world EEG dataset comprising 68 subjects performing cognitive tasks. The results showed that the approach is capable of not only suppressing the artifact components but also improving the discriminative power of a classifier with statistical significance. We also demonstrate that the proposed method addresses the confounding issues induced by ocular movements in cognitive EEG study.

Classifying social anxiety disorder using multivoxel pattern analyses of brain function and structure☆

PubMed Central

Frick, Andreas; Gingnell, Malin; Marquand, Andre F.; Howner, Katarina; Fischer, Håkan; Kristiansson, Marianne; Williams, Steven C.R.; Fredrikson, Mats; Furmark, Tomas

2014-01-01

Functional neuroimaging of social anxiety disorder (SAD) support altered neural activation to threat-provoking stimuli focally in the fear network, while structural differences are distributed over the temporal and frontal cortices as well as limbic structures. Previous neuroimaging studies have investigated the brain at the voxel level using mass-univariate methods which do not enable detection of more complex patterns of activity and structural alterations that may separate SAD from healthy individuals. Support vector machine (SVM) is a supervised machine learning method that capitalizes on brain activation and structural patterns to classify individuals. The aim of this study was to investigate if it is possible to discriminate SAD patients (n = 14) from healthy controls (n = 12) using SVM based on (1) functional magnetic resonance imaging during fearful face processing and (2) regional gray matter volume. Whole brain and region of interest (fear network) SVM analyses were performed for both modalities. For functional scans, significant classifications were obtained both at whole brain level and when restricting the analysis to the fear network while gray matter SVM analyses correctly classified participants only when using the whole brain search volume. These results support that SAD is characterized by aberrant neural activation to affective stimuli in the fear network, while disorder-related alterations in regional gray matter volume are more diffusely distributed over the whole brain. SVM may thus be useful for identifying imaging biomarkers of SAD. PMID:24239689

Galaxy Zoo: quantitative visual morphological classifications for 48 000 galaxies from CANDELS

NASA Astrophysics Data System (ADS)

Simmons, B. D.; Lintott, Chris; Willett, Kyle W.; Masters, Karen L.; Kartaltepe, Jeyhan S.; Häußler, Boris; Kaviraj, Sugata; Krawczyk, Coleman; Kruk, S. J.; McIntosh, Daniel H.; Smethurst, R. J.; Nichol, Robert C.; Scarlata, Claudia; Schawinski, Kevin; Conselice, Christopher J.; Almaini, Omar; Ferguson, Henry C.; Fortson, Lucy; Hartley, William; Kocevski, Dale; Koekemoer, Anton M.; Mortlock, Alice; Newman, Jeffrey A.; Bamford, Steven P.; Grogin, N. A.; Lucas, Ray A.; Hathi, Nimish P.; McGrath, Elizabeth; Peth, Michael; Pforr, Janine; Rizer, Zachary; Wuyts, Stijn; Barro, Guillermo; Bell, Eric F.; Castellano, Marco; Dahlen, Tomas; Dekel, Avishai; Ownsworth, Jamie; Faber, Sandra M.; Finkelstein, Steven L.; Fontana, Adriano; Galametz, Audrey; Grützbauch, Ruth; Koo, David; Lotz, Jennifer; Mobasher, Bahram; Mozena, Mark; Salvato, Mara; Wiklind, Tommy

2017-02-01

We present quantified visual morphologies of approximately 48 000 galaxies observed in three Hubble Space Telescope legacy fields by the Cosmic Assembly Near-infrared Deep Extragalactic Legacy Survey (CANDELS) and classified by participants in the Galaxy Zoo project. 90 per cent of galaxies have z ≤ 3 and are observed in rest-frame optical wavelengths by CANDELS. Each galaxy received an average of 40 independent classifications, which we combine into detailed morphological information on galaxy features such as clumpiness, bar instabilities, spiral structure, and merger and tidal signatures. We apply a consensus-based classifier weighting method that preserves classifier independence while effectively down-weighting significantly outlying classifications. After analysing the effect of varying image depth on reported classifications, we also provide depth-corrected classifications which both preserve the information in the deepest observations and also enable the use of classifications at comparable depths across the full survey. Comparing the Galaxy Zoo classifications to previous classifications of the same galaxies shows very good agreement; for some applications, the high number of independent classifications provided by Galaxy Zoo provides an advantage in selecting galaxies with a particular morphological profile, while in others the combination of Galaxy Zoo with other classifications is a more promising approach than using any one method alone. We combine the Galaxy Zoo classifications of `smooth' galaxies with parametric morphologies to select a sample of featureless discs at 1 ≤ z ≤ 3, which may represent a dynamically warmer progenitor population to the settled disc galaxies seen at later epochs.

Validation of VITEK 2 Version 4.01 Software for Detection, Identification, and Classification of Glycopeptide-Resistant Enterococci

PubMed Central

Abele-Horn, Marianne; Hommers, Leif; Trabold, René; Frosch, Matthias

2006-01-01

We evaluated the ability of the new VITEK 2 version 4.01 software to identify and detect glycopeptide-resistant enterococci compared to that of the reference broth microdilution method and to classify them into the vanA, vanB, vanC1, and vanC2 genotypes. Moreover, the accuracy of antimicrobial susceptibility testing with agents with improved potencies against glycopeptide-resistant enterococci was determined. A total of 121 enterococci were investigated. The new VITEK 2 software was able to identify 114 (94.2%) enterococcal strains correctly to the species level and to classify 119 (98.3%) enterococci correctly to the glycopeptide resistance genotype level. One Enterococcus casseliflavus strain and six Enterococcus faecium vanA strains with low-level resistance to vancomycin were identified with low discrimination, requiring additional tests. One of the vanA strains was misclassified as the vanB type, and one glycopeptide-susceptible E. facium wild type was misclassified as the vanA type. The overall essential agreements for antimicrobial susceptibility testing results were 94.2% for vancomycin, 95.9% for teicoplanin, 100% for quinupristin-dalfopristin and moxifloxacin, and 97.5% for linezolid. The rates of minor errors were 9% for teicoplanin and 5% for the other antibiotic agents. The identification and susceptibility data were produced within 4 h to 6 h 30 min and 8 h 15 min to 12 h 15 min. In conclusion, use of VITEK 2 version 4.01 software appears to be a reliable method for the identification and detection of glycopeptide-resistant enterococci as well as an improvement over the use of the former VITEK 2 database. However, a significant reduction in the detection time would be desirable. PMID:16390951

Rapid detection, classification and accurate alignment of up to a million or more related protein sequences.

PubMed

Neuwald, Andrew F

2009-08-01

The patterns of sequence similarity and divergence present within functionally diverse, evolutionarily related proteins contain implicit information about corresponding biochemical similarities and differences. A first step toward accessing such information is to statistically analyze these patterns, which, in turn, requires that one first identify and accurately align a very large set of protein sequences. Ideally, the set should include many distantly related, functionally divergent subgroups. Because it is extremely difficult, if not impossible for fully automated methods to align such sequences correctly, researchers often resort to manual curation based on detailed structural and biochemical information. However, multiply-aligning vast numbers of sequences in this way is clearly impractical. This problem is addressed using Multiply-Aligned Profiles for Global Alignment of Protein Sequences (MAPGAPS). The MAPGAPS program uses a set of multiply-aligned profiles both as a query to detect and classify related sequences and as a template to multiply-align the sequences. It relies on Karlin-Altschul statistics for sensitivity and on PSI-BLAST (and other) heuristics for speed. Using as input a carefully curated multiple-profile alignment for P-loop GTPases, MAPGAPS correctly aligned weakly conserved sequence motifs within 33 distantly related GTPases of known structure. By comparison, the sequence- and structurally based alignment methods hmmalign and PROMALS3D misaligned at least 11 and 23 of these regions, respectively. When applied to a dataset of 65 million protein sequences, MAPGAPS identified, classified and aligned (with comparable accuracy) nearly half a million putative P-loop GTPase sequences. A C++ implementation of MAPGAPS is available at http://mapgaps.igs.umaryland.edu. Supplementary data are available at Bioinformatics online.

A comparison of hair colour measurement by digital image analysis with reflective spectrophotometry.

PubMed

Vaughn, Michelle R; van Oorschot, Roland A H; Baindur-Hudson, Swati

2009-01-10

While reflective spectrophotometry is an established method for measuring macroscopic hair colour, it can be cumbersome to use on a large number of individuals and not all reflective spectrophotometry instruments are easily portable. This study investigates the use of digital photographs to measure hair colour and compares its use to reflective spectrophotometry. An understanding of the accuracy of colour determination by these methods is of relevance when undertaking specific investigations, such as those on the genetics of hair colour. Measurements of hair colour may also be of assistance in cases where a photograph is the only evidence of hair colour available (e.g. surveillance). Using the CIE L(*)a(*)b(*) colour space, the hair colour of 134 individuals of European ancestry was measured by both reflective spectrophotometry and by digital image analysis (in V++). A moderate correlation was found along all three colour axes, with Pearson correlation coefficients of 0.625, 0.593 and 0.513 for L(*), a(*) and b(*) respectively (p-values=0.000), with means being significantly overestimated by digital image analysis for all three colour components (by an average of 33.42, 3.38 and 8.00 for L(*), a(*) and b(*) respectively). When using digital image data to group individuals into clusters previously determined by reflective spectrophotometric analysis using a discriminant analysis, individuals were classified into the correct clusters 85.8% of the time when there were two clusters. The percentage of cases correctly classified decreases as the number of clusters increases. It is concluded that, although more convenient, hair colour measurement from digital images has limited use in situations requiring accurate and consistent measurements.

The Immune System as a Model for Pattern Recognition and Classification

PubMed Central

Carter, Jerome H.

2000-01-01

Objective: To design a pattern recognition engine based on concepts derived from mammalian immune systems. Design: A supervised learning system (Immunos-81) was created using software abstractions of T cells, B cells, antibodies, and their interactions. Artificial T cells control the creation of B-cell populations (clones), which compete for recognition of “unknowns.” The B-cell clone with the “simple highest avidity” (SHA) or “relative highest avidity” (RHA) is considered to have successfully classified the unknown. Measurement: Two standard machine learning data sets, consisting of eight nominal and six continuous variables, were used to test the recognition capabilities of Immunos-81. The first set (Cleveland), consisting of 303 cases of patients with suspected coronary artery disease, was used to perform a ten-way cross-validation. After completing the validation runs, the Cleveland data set was used as a training set prior to presentation of the second data set, consisting of 200 unknown cases. Results: For cross-validation runs, correct recognition using SHA ranged from a high of 96 percent to a low of 63.2 percent. The average correct classification for all runs was 83.2 percent. Using the RHA metric, 11.2 percent were labeled “too close to determine” and no further attempt was made to classify them. Of the remaining cases, 85.5 percent were correctly classified. When the second data set was presented, correct classification occurred in 73.5 percent of cases when SHA was used and in 80.3 percent of cases when RHA was used. Conclusions: The immune system offers a viable paradigm for the design of pattern recognition systems. Additional research is required to fully exploit the nuances of immune computation. PMID:10641961

Single classifier, OvO, OvA and RCC multiclass classification method in handheld based smartphone gait identification

NASA Astrophysics Data System (ADS)

Raziff, Abdul Rafiez Abdul; Sulaiman, Md Nasir; Mustapha, Norwati; Perumal, Thinagaran

2017-10-01

Gait recognition is widely used in many applications. In the application of the gait identification especially in people, the number of classes (people) is many which may comprise to more than 20. Due to the large amount of classes, the usage of single classification mapping (direct classification) may not be suitable as most of the existing algorithms are mostly designed for the binary classification. Furthermore, having many classes in a dataset may result in the possibility of having a high degree of overlapped class boundary. This paper discusses the application of multiclass classifier mappings such as one-vs-all (OvA), one-vs-one (OvO) and random correction code (RCC) on handheld based smartphone gait signal for person identification. The results is then compared with a single J48 decision tree for benchmark. From the result, it can be said that using multiclass classification mapping method thus partially improved the overall accuracy especially on OvO and RCC with width factor more than 4. For OvA, the accuracy result is worse than a single J48 due to a high number of classes.

Classification Preictal and Interictal Stages via Integrating Interchannel and Time-Domain Analysis of EEG Features.

PubMed

Lin, Lung-Chang; Chen, Sharon Chia-Ju; Chiang, Ching-Tai; Wu, Hui-Chuan; Yang, Rei-Cheng; Ouyang, Chen-Sen

2017-03-01

The life quality of patients with refractory epilepsy is extremely affected by abrupt and unpredictable seizures. A reliable method for predicting seizures is important in the management of refractory epilepsy. A critical factor in seizure prediction involves the classification of the preictal and interictal stages. This study aimed to develop an efficient, automatic, quantitative, and individualized approach for preictal/interictal stage identification. Five epileptic children, who had experienced at least 2 episodes of seizures during a 24-hour video EEG recording, were included. Artifact-free preictal and interictal EEG epochs were acquired, respectively, and characterized with 216 global feature descriptors. The best subset of 5 discriminative descriptors was identified. The best subsets showed differences among the patients. Statistical analysis revealed most of the 5 descriptors in each subset were significantly different between the preictal and interictal stages for each patient. The proposed approach yielded weighted averages of 97.50% correctness, 96.92% sensitivity, 97.78% specificity, and 95.45% precision on classifying test epochs. Although the case number was limited, this study successfully integrated a new EEG analytical method to classify preictal and interictal EEG segments and might be used further in predicting the occurrence of seizures.

Weak scratch detection and defect classification methods for a large-aperture optical element

NASA Astrophysics Data System (ADS)

Tao, Xian; Xu, De; Zhang, Zheng-Tao; Zhang, Feng; Liu, Xi-Long; Zhang, Da-Peng

2017-03-01

Surface defects on optics cause optic failure and heavy loss to the optical system. Therefore, surface defects on optics must be carefully inspected. This paper proposes a coarse-to-fine detection strategy of weak scratches in complicated dark-field images. First, all possible scratches are detected based on bionic vision. Then, each possible scratch is precisely positioned and connected to a complete scratch by the LSD and a priori knowledge. Finally, multiple scratches with various types can be detected in dark-field images. To classify defects and pollutants, a classification method based on GIST features is proposed. This paper uses many real dark-field images as experimental images. The results show that this method can detect multiple types of weak scratches in complex images and that the defects can be correctly distinguished with interference. This method satisfies the real-time and accurate detection requirements of surface defects.

Problems With Risk Reclassification Methods for Evaluating Prediction Models

PubMed Central

Pepe, Margaret S.

2011-01-01

For comparing the performance of a baseline risk prediction model with one that includes an additional predictor, a risk reclassification analysis strategy has been proposed. The first step is to cross-classify risks calculated according to the 2 models for all study subjects. Summary measures including the percentage of reclassification and the percentage of correct reclassification are calculated, along with 2 reclassification calibration statistics. The author shows that interpretations of the proposed summary measures and P values are problematic. The author's recommendation is to display the reclassification table, because it shows interesting information, but to use alternative methods for summarizing and comparing model performance. The Net Reclassification Index has been suggested as one alternative method. The author argues for reporting components of the Net Reclassification Index because they are more clinically relevant than is the single numerical summary measure. PMID:21555714

Semantic information extracting system for classification of radiological reports in radiology information system (RIS)

NASA Astrophysics Data System (ADS)

Shi, Liehang; Ling, Tonghui; Zhang, Jianguo

2016-03-01

Radiologists currently use a variety of terminologies and standards in most hospitals in China, and even there are multiple terminologies being used for different sections in one department. In this presentation, we introduce a medical semantic comprehension system (MedSCS) to extract semantic information about clinical findings and conclusion from free text radiology reports so that the reports can be classified correctly based on medical terms indexing standards such as Radlex or SONMED-CT. Our system (MedSCS) is based on both rule-based methods and statistics-based methods which improve the performance and the scalability of MedSCS. In order to evaluate the over all of the system and measure the accuracy of the outcomes, we developed computation methods to calculate the parameters of precision rate, recall rate, F-score and exact confidence interval.

Gulls identified as major source of fecal pollution in coastal waters: a microbial source tracking study.

PubMed

Araújo, Susana; Henriques, Isabel S; Leandro, Sérgio Miguel; Alves, Artur; Pereira, Anabela; Correia, António

2014-02-01

Gulls were reported as sources of fecal pollution in coastal environments and potential vectors of human infections. Microbial source tracking (MST) methods were rarely tested to identify this pollution origin. This study was conducted to ascertain the source of water fecal contamination in the Berlenga Island, Portugal. A total of 169 Escherichia coli isolates from human sewage, 423 isolates from gull feces and 334 water isolates were analyzed by BOX-PCR. An average correct classification of 79.3% was achieved. When an 85% similarity cutoff was applied 24% of water isolates were present in gull feces against 2.7% detected in sewage. Jackknifing resulted in 29.3% of water isolates classified as gull, and 10.8% classified as human. Results indicate that gulls constitute a major source of water contamination in the Berlenga Island. This study validated a methodology to differentiate human and gull fecal pollution sources in a real case of a contaminated beach. © 2013.

Chemical data as markers of the geographical origins of sugarcane spirits.

PubMed

Serafim, F A T; Pereira-Filho, Edenir R; Franco, D W

2016-04-01

In an attempt to classify sugarcane spirits according to their geographic region of origin, chemical data for 24 analytes were evaluated in 50 cachaças produced using a similar procedure in selected regions of Brazil: São Paulo - SP (15), Minas Gerais - MG (11), Rio de Janeiro - RJ (11), Paraiba -PB (9), and Ceará - CE (4). Multivariate analysis was applied to the analytical results, and the predictive abilities of different classification methods were evaluated. Principal component analysis identified five groups, and chemical similarities were observed between MG and SP samples and between RJ and PB samples. CE samples presented a distinct chemical profile. Among the samples, partial linear square discriminant analysis (PLS-DA) classified 50.2% of the samples correctly, K-nearest neighbor (KNN) 86%, and soft independent modeling of class analogy (SIMCA) 56.2%. Therefore, in this proof of concept demonstration, the proposed approach based on chemical data satisfactorily predicted the cachaças' geographic origins. Copyright © 2015 Elsevier Ltd. All rights reserved.

Clinical assessment of a radioimmunoassay for free thyroxine using a modified tracer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Chan, D.W.; Waud, J.M.; Hsu, T.H.

1983-06-01

A radioimmunoassay for measuring free thyroxine in plasma was introduced by Amersham using a I-125-labeled T/sub 4/ derivative that does not bind significantly to the thyroxine-binding proteins. This RIA was evaluated for its clinical utility in assessing 278 patients with thyroid and nonthyroidal diseases. The precision of the Amerlex free T/sub 4/ assay was expressed as coefficient of variation. The correlation coefficients (r) of a dialysis method and a free thyroxine index were 0.871 and 0.911, respectively. Free T/sub 4/ correctly classified 98% euthyroid, 92% hypothyroid, 100% hyperthyroid, 100% euthyroid with elevated TBG, and 87% of phenytoin patients. In addition,more » 80 patients with acute nonthyroidal illness were studied. Most of these patients have normal to low free T/sub 4/, very low T/sub 3/, and elevated rT/sub 3/. We found this free T/sub 4/ assay to be precise, easy to perform, and reliable in classifying thyroid status in most patients.« less

Robust stereo matching with trinary cross color census and triple image-based refinements

NASA Astrophysics Data System (ADS)

Chang, Ting-An; Lu, Xiao; Yang, Jar-Ferr

2017-12-01

For future 3D TV broadcasting systems and navigation applications, it is necessary to have accurate stereo matching which could precisely estimate depth map from two distanced cameras. In this paper, we first suggest a trinary cross color (TCC) census transform, which can help to achieve accurate disparity raw matching cost with low computational cost. The two-pass cost aggregation (TPCA) is formed to compute the aggregation cost, then the disparity map can be obtained by a range winner-take-all (RWTA) process and a white hole filling procedure. To further enhance the accuracy performance, a range left-right checking (RLRC) method is proposed to classify the results as correct, mismatched, or occluded pixels. Then, the image-based refinements for the mismatched and occluded pixels are proposed to refine the classified errors. Finally, the image-based cross voting and a median filter are employed to complete the fine depth estimation. Experimental results show that the proposed semi-global stereo matching system achieves considerably accurate disparity maps with reasonable computation cost.

Learn ++.NC: combining ensemble of classifiers with dynamically weighted consult-and-vote for efficient incremental learning of new classes.

PubMed

Muhlbaier, Michael D; Topalis, Apostolos; Polikar, Robi

2009-01-01

We have previously introduced an incremental learning algorithm Learn(++), which learns novel information from consecutive data sets by generating an ensemble of classifiers with each data set, and combining them by weighted majority voting. However, Learn(++) suffers from an inherent "outvoting" problem when asked to learn a new class omega(new) introduced by a subsequent data set, as earlier classifiers not trained on this class are guaranteed to misclassify omega(new) instances. The collective votes of earlier classifiers, for an inevitably incorrect decision, then outweigh the votes of the new classifiers' correct decision on omega(new) instances--until there are enough new classifiers to counteract the unfair outvoting. This forces Learn(++) to generate an unnecessarily large number of classifiers. This paper describes Learn(++).NC, specifically designed for efficient incremental learning of multiple new classes using significantly fewer classifiers. To do so, Learn (++).NC introduces dynamically weighted consult and vote (DW-CAV), a novel voting mechanism for combining classifiers: individual classifiers consult with each other to determine which ones are most qualified to classify a given instance, and decide how much weight, if any, each classifier's decision should carry. Experiments on real-world problems indicate that the new algorithm performs remarkably well with substantially fewer classifiers, not only as compared to its predecessor Learn(++), but also as compared to several other algorithms recently proposed for similar problems.

SU-F-J-224: Impact of 4D PET/CT On PERCIST Classification of Lung and Liver Metastases in NSLC and Colorectal Cancer

DOE Office of Scientific and Technical Information (OSTI.GOV)

Meier, J; Lopez, B; Mawlawi, O

2016-06-15

Purpose: To quantify the impact of 4D PET/CT on PERCIST metrics in lung and liver tumors in NSCLC and colorectal cancer patients. Methods: 32 patients presenting lung or liver tumors of 1–3 cm size affected by respiratory motion were scanned on a GE Discovery 690 PET/CT. The bed position with lesion(s) affected by motion was acquired in a 12 minute PET LIST mode and unlisted into 8 bins with respiratory gating. Three different CT maps were used for attenuation correction: a clinical helical CT (CT-clin), an average CT (CT-ave), and an 8-phase 4D CINE CT (CT-cine). All reconstructions were 3Dmore » OSEM, 2 iterations, 24 subsets, 6.4 Gaussian filtration, 192×192 matrix, non-TOF, and non-PSF. Reconstructions using CT-clin and CT-ave used only 3 out of the 12 minutes of the data (clinical protocol); all 12 minutes were used for the CT-cine reconstruction. The percent change of SUVbw-peak and SUVbw-max was calculated between PET-CTclin and PET-CTave. The same percent change was also calculated between PET-CTclin and PET-CTcine in each of the 8 bins and in the average of all bins. A 30% difference from PET-CTclin classified lesions as progressive metabolic disease (PMD) using maximum bin value and the average of eight bin values. Results: 30 lesions in 25 patients were evaluated. Using the bin with maximum SUVbw-peak and SUVbw-max difference, 4 and 13 lesions were classified as PMD, respectively. Using the average bin values for SUVbw-peak and SUVbw-max, 3 and 6 lesions were classified as PMD, respectively. Using PET-CTave values for SUVbw-peak and SUVbw-max, 4 and 3 lesions were classified as PMD, respectively. Conclusion: These results suggest that response evaluation in 4D PET/CT is dependent on SUV measurement (SUVpeak vs. SUVmax), number of bins (single or average), and the CT map used for attenuation correction.« less

Automated 3D Ultrasound Image Segmentation to Aid Breast Cancer Image Interpretation

PubMed Central

Gu, Peng; Lee, Won-Mean; Roubidoux, Marilyn A.; Yuan, Jie; Wang, Xueding; Carson, Paul L.

2015-01-01

Segmentation of an ultrasound image into functional tissues is of great importance to clinical diagnosis of breast cancer. However, many studies are found to segment only the mass of interest and not all major tissues. Differences and inconsistencies in ultrasound interpretation call for an automated segmentation method to make results operator-independent. Furthermore, manual segmentation of entire three-dimensional (3D) ultrasound volumes is time-consuming, resource-intensive, and clinically impractical. Here, we propose an automated algorithm to segment 3D ultrasound volumes into three major tissue types: cyst/mass, fatty tissue, and fibro-glandular tissue. To test its efficacy and consistency, the proposed automated method was employed on a database of 21 cases of whole breast ultrasound. Experimental results show that our proposed method not only distinguishes fat and non-fat tissues correctly, but performs well in classifying cyst/mass. Comparison of density assessment between the automated method and manual segmentation demonstrates good consistency with an accuracy of 85.7%. Quantitative comparison of corresponding tissue volumes, which uses overlap ratio, gives an average similarity of 74.54%, consistent with values seen in MRI brain segmentations. Thus, our proposed method exhibits great potential as an automated approach to segment 3D whole breast ultrasound volumes into functionally distinct tissues that may help to correct ultrasound speed of sound aberrations and assist in density based prognosis of breast cancer. PMID:26547117

Automated 3D ultrasound image segmentation for assistant diagnosis of breast cancer

NASA Astrophysics Data System (ADS)

Wang, Yuxin; Gu, Peng; Lee, Won-Mean; Roubidoux, Marilyn A.; Du, Sidan; Yuan, Jie; Wang, Xueding; Carson, Paul L.

2016-04-01

Segmentation of an ultrasound image into functional tissues is of great importance to clinical diagnosis of breast cancer. However, many studies are found to segment only the mass of interest and not all major tissues. Differences and inconsistencies in ultrasound interpretation call for an automated segmentation method to make results operator-independent. Furthermore, manual segmentation of entire three-dimensional (3D) ultrasound volumes is time-consuming, resource-intensive, and clinically impractical. Here, we propose an automated algorithm to segment 3D ultrasound volumes into three major tissue types: cyst/mass, fatty tissue, and fibro-glandular tissue. To test its efficacy and consistency, the proposed automated method was employed on a database of 21 cases of whole breast ultrasound. Experimental results show that our proposed method not only distinguishes fat and non-fat tissues correctly, but performs well in classifying cyst/mass. Comparison of density assessment between the automated method and manual segmentation demonstrates good consistency with an accuracy of 85.7%. Quantitative comparison of corresponding tissue volumes, which uses overlap ratio, gives an average similarity of 74.54%, consistent with values seen in MRI brain segmentations. Thus, our proposed method exhibits great potential as an automated approach to segment 3D whole breast ultrasound volumes into functionally distinct tissues that may help to correct ultrasound speed of sound aberrations and assist in density based prognosis of breast cancer.

Gait Phase Recognition for Lower-Limb Exoskeleton with Only Joint Angular Sensors

PubMed Central

Liu, Du-Xin; Wu, Xinyu; Du, Wenbin; Wang, Can; Xu, Tiantian

2016-01-01

Gait phase is widely used for gait trajectory generation, gait control and gait evaluation on lower-limb exoskeletons. So far, a variety of methods have been developed to identify the gait phase for lower-limb exoskeletons. Angular sensors on lower-limb exoskeletons are essential for joint closed-loop controlling; however, other types of sensors, such as plantar pressure, attitude or inertial measurement unit, are not indispensable.Therefore, to make full use of existing sensors, we propose a novel gait phase recognition method for lower-limb exoskeletons using only joint angular sensors. The method consists of two procedures. Firstly, the gait deviation distances during walking are calculated and classified by Fisher’s linear discriminant method, and one gait cycle is divided into eight gait phases. The validity of the classification results is also verified based on large gait samples. Secondly, we build a gait phase recognition model based on multilayer perceptron and train it with the phase-labeled gait data. The experimental result of cross-validation shows that the model has a 94.45% average correct rate of set (CRS) and an 87.22% average correct rate of phase (CRP) on the testing set, and it can predict the gait phase accurately. The novel method avoids installing additional sensors on the exoskeleton or human body and simplifies the sensory system of the lower-limb exoskeleton. PMID:27690023

[Differentiation by geometric morphometrics among 11 Anopheles (Nyssorhynchus) in Colombia].

PubMed

Calle, David Alonso; Quiñones, Martha Lucía; Erazo, Holmes Francisco; Jaramillo, Nicolás

2008-09-01

The correct identification of the Anopheles species of the subgenus Nyssorhynchus is important because this subgenus includes the main malaria vectors in Colombia. This information is necessary for focusing a malaria control program. Geometric morphometrics were used to evaluate morphometric variation of 11 species of subgenus Nyssorhynchus present in Colombia and to distinguish females of each species. Materials and methods. The specimens were obtained from series and family broods from females collected with protected human hosts as attractants. The field collected specimens and their progeny were identified at each of the associated stages by conventional keys. For some species, wild females were used. Landmarks were selected on wings from digital pictures from 336 individuals, and digitized with coordinates. The coordinate matrix was processed by generalized Procrustes analysis which generated size and shape variables, free of non-biological variation. Size and shape variables were analyzed by univariate and multivariate statistics. The subdivision of subgenus Nyssorhynchus in sections is not correlated with wing shape. Discriminant analyses correctly classified 97% of females in the section Albimanus and 86% in the section Argyritarsis. In addition, these methodologies allowed the correct identification of 3 sympatric species from Putumayo which have been difficult to identify in the adult female stage. The geometric morphometrics were demonstrated to be a very useful tool as an adjunct to taxonomy of females the use of this method is recommended in studies of the subgenus Nyssorhynchus in Colombia.

Altered enzyme-linked immunosorbent assay immunoglobulin M (IgM)/IgG optical density ratios can correctly classify all primary or secondary dengue virus infections 1 day after the onset of symptoms, when all of the viruses can be isolated.

PubMed

Falconar, Andrew K I; de Plata, Elsa; Romero-Vivas, Claudia M E

2006-09-01

We compared dengue virus (DV) isolation rates and tested whether acute primary (P) and acute/probable acute secondary (S/PS) DV infections could be correctly classified serologically when the patients' first serum (S1) samples were obtained 1 to 3 days after the onset of symptoms (AOS). DV envelope/membrane protein-specific immunoglobulin M (IgM) capture and IgG capture enzyme-linked immunosorbent assay (ELISA) titrations (1/log(10) 1.7 to 1 log(10) 6.6 dilutions) were performed on 100 paired S1 and S2 samples from suspected DV infections. The serologically confirmed S/PS infections were divided into six subgroups based on their different IgM and IgG responses. Because of their much greater dynamic ranges, IgG/IgM ELISA titer ratios were more accurate and reliable than IgM/IgG optical density (OD) ratios recorded at a single cutoff dilution for discriminating between P and S/PS infections. However, 62% of these patients' S1 samples were DV IgM and IgG titer negative (or=2.60 and <2.60) discriminatory IgM/IgG OD (DOD) ratios on these S1 samples than those published previously to correctly classify the highest percentage of these P and S/PS infections. The DV isolation rate was highest (12/12; 100%) using IgG and IgM titer-negative S1 samples collected 1 day AOS, when 100% of them were correctly classified as P or S/PS infections using these higher DOD ratios.

Evaluation of Kojima-Matsubara color vision test plates: validity in young children.

PubMed

Lee, D Y; Cotter, S A; French, A L

1997-09-01

We examined a pseudoisochromatic color plate test by Kojima and Matsubara for young children which uses drawings of familiar objects rather than letters or numbers. First, we evaluated the test's efficacy as a color deficiency screener and its validity in classifying the types of color deficiencies by comparing its results with those from the Moreland anomaloscope. Second, we eliminated the chromatic factor and evaluated the functional ability of young children to perform the task by determining how many correct responses were obtained using modified black/white replicas of the test plates. Part 1: Twenty color-normal and 13 color-deficient adults were diagnosed and classified with the Ishihara test, Panel D-15 test, and anomaloscope. Subjects were then tested with the Kojima-Matsubara test and result were compared with those from the anomaloscope. Part 2: Fifty children aged 3 to 7 years were tested with modified black/white test plate replicas. The number of correct responses for each plate was determined for five different age groups. Part 1: Among the 20 color-normal subjects, 18 read all 10 plates correctly and 2 subjects missed 1 of the 10. Only 1 of the 13 color-deficient subjects exhibited the expected responses for plates 2 to 6 (used for color deficiency screening). The color-deficient subjects' responses for plates 7 to 10, which are used to classify red-green defects, were varied and only the protanomalous subjects (n = 2) followed the expected response pattern. Part 2: Of the 10 black/white modified plates, only 2 were correctly identified by all 50 children. The other plates had a recognition rate that ranged from 32 to 98%. Because the response patterns given by most of the color-deficient adult subjects were different from those in the test manual, ambiguous results would occur if the Kojima-Matsubara test were used for color vision screening or the diagnosis of color deficiency. In addition, the difficulty that many of the young children exhibited in identifying the objects in the black/white replica plates suggests that there would be a large number of false positive errors (classifying a color normal as color deficient) when using this test in young children.

Comparative evaluation of the identification of rapidly growing non-tuberculous mycobacteria by mass spectrometry (MALDI-TOF MS), GenoType Mycobacterium CM/AS assay and partial sequencing of the rpoβ gene with phylogenetic analysis as a reference method.

PubMed

Costa-Alcalde, José Javier; Barbeito-Castiñeiras, Gema; González-Alba, José María; Aguilera, Antonio; Galán, Juan Carlos; Pérez-Del-Molino, María Luisa

2018-06-02

The American Thoracic Society and the Infectious Diseases Society of America recommend that clinically significant non-tuberculous mycobacteria (NTM) should be identified to the species level in order to determine their clinical significance. The aim of this study was to evaluate identification of rapidly growing NTM (RGM) isolated from clinical samples by using MALDI-TOF MS and a commercial molecular system. The results were compared with identification using a reference method. We included 46 clinical isolates of RGM and identified them using the commercial molecular system GenoType ® CM/AS (Hain, Lifescience, Germany), MALDI-TOF MS (Bruker) and, as reference method, partial rpoβ gene sequencing followed by BLAST and phylogenetic analysis with the 1093 sequences available in the GeneBank. The degree of agreement between GenoType ® and MALDI-TOF MS and the reference method, partial rpoβ sequencing, was 27/43 (62.8%) and 38/43 cases (88.3%) respectively. For all the samples correctly classified by GenoType ® , we obtained the same result with MALDI-TOF MS (27/27). However, MALDI-TOF MS also correctly identified 68.75% (11/16) of the samples that GenoType ® had misclassified (p=0.005). MALDI-TOF MS classified significantly better than GenoType ® . When a MALDI-TOF MS score >1.85 was achieved, MALDI-TOF MS and partial rpoβ gene sequencing were equivalent. GenoType ® was not able to distinguish between species belonging to the M. fortuitum complex. MALDI-TOF MS methodology is simple, rapid and associated with lower consumable costs than GenoType ® . The partial rpoβ sequencing methods with BLAST and phylogenetic analysis were not able to identify some RGM unequivocally. Therefore, sequencing of additional regions would be indicated in these cases. Copyright © 2018 Elsevier España, S.L.U. and Sociedad Española de Enfermedades Infecciosas y Microbiología Clínica. All rights reserved.

Ensemble of classifiers for confidence-rated classification of NDE signal

NASA Astrophysics Data System (ADS)

Banerjee, Portia; Safdarnejad, Seyed; Udpa, Lalita; Udpa, Satish

2016-02-01

Ensemble of classifiers in general, aims to improve classification accuracy by combining results from multiple weak hypotheses into a single strong classifier through weighted majority voting. Improved versions of ensemble of classifiers generate self-rated confidence scores which estimate the reliability of each of its prediction and boost the classifier using these confidence-rated predictions. However, such a confidence metric is based only on the rate of correct classification. In existing works, although ensemble of classifiers has been widely used in computational intelligence, the effect of all factors of unreliability on the confidence of classification is highly overlooked. With relevance to NDE, classification results are affected by inherent ambiguity of classifica-tion, non-discriminative features, inadequate training samples and noise due to measurement. In this paper, we extend the existing ensemble classification by maximizing confidence of every classification decision in addition to minimizing the classification error. Initial results of the approach on data from eddy current inspection show improvement in classification performance of defect and non-defect indications.

Thin-layer chromatographic identification of Chinese propolis using chemometric fingerprinting.

PubMed

Tang, Tie-xin; Guo, Wei-yan; Xu, Ye; Zhang, Si-ming; Xu, Xin-jun; Wang, Dong-mei; Zhao, Zhi-min; Zhu, Long-ping; Yang, De-po

2014-01-01

Poplar tree gum has a similar chemical composition and appearance to Chinese propolis (bee glue) and has been widely used as a counterfeit propolis because Chinese propolis is typically the poplar-type propolis, the chemical composition of which is determined mainly by the resin of poplar trees. The discrimination of Chinese propolis from poplar tree gum is a challenging task. To develop a rapid thin-layer chromatographic (TLC) identification method using chemometric fingerprinting to discriminate Chinese propolis from poplar tree gum. A new TLC method using a combination of ammonia and hydrogen peroxide vapours as the visualisation reagent was developed to characterise the chemical profile of Chinese propolis. Three separate people performed TLC on eight Chinese propolis samples and three poplar tree gum samples of varying origins. Five chemometric methods, including similarity analysis, hierarchical clustering, k-means clustering, neural network and support vector machine, were compared for use in classifying the samples based on their densitograms obtained from the TLC chromatograms via image analysis. Hierarchical clustering, neural network and support vector machine analyses achieved a correct classification rate of 100% in classifying the samples. A strategy for TLC identification of Chinese propolis using chemometric fingerprinting was proposed and it provided accurate sample classification. The study has shown that the TLC identification method using chemometric fingerprinting is a rapid, low-cost method for the discrimination of Chinese propolis from poplar tree gum and may be used for the quality control of Chinese propolis. Copyright © 2014 John Wiley & Sons, Ltd.

Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees

PubMed Central

Verhoeven, Thibault; Schmid, Konstantin; Müller, Klaus-Robert; Tangermann, Michael; Kindermans, Pieter-Jan

2017-01-01

Objective Using traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g., by subject-to-subject transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch and adapt over time. While such heuristics work well in practice, none of them can provide theoretical guarantees. Our objective is to modify an event-related potential (ERP) paradigm to work in unison with the machine learning decoder, and thus to achieve a reliable unsupervised calibrationless decoding with a guarantee to recover the true class means. Method We introduce learning from label proportions (LLP) to the BCI community as a new unsupervised, and easy-to-implement classification approach for ERP-based BCIs. The LLP estimates the mean target and non-target responses based on known proportions of these two classes in different groups of the data. We present a visual ERP speller to meet the requirements of LLP. For evaluation, we ran simulations on artificially created data sets and conducted an online BCI study with 13 subjects performing a copy-spelling task. Results Theoretical considerations show that LLP is guaranteed to minimize the loss function similar to a corresponding supervised classifier. LLP performed well in simulations and in the online application, where 84.5% of characters were spelled correctly on average without prior calibration. Significance The continuously adapting LLP classifier is the first unsupervised decoder for ERP BCIs guaranteed to find the optimal decoder. This makes it an ideal solution to avoid tedious calibration sessions. Additionally, LLP works on complementary principles compared to existing unsupervised methods, opening the door for their further enhancement when combined with LLP. PMID:28407016

Computing group cardinality constraint solutions for logistic regression problems.

PubMed

Zhang, Yong; Kwon, Dongjin; Pohl, Kilian M

2017-01-01

We derive an algorithm to directly solve logistic regression based on cardinality constraint, group sparsity and use it to classify intra-subject MRI sequences (e.g. cine MRIs) of healthy from diseased subjects. Group cardinality constraint models are often applied to medical images in order to avoid overfitting of the classifier to the training data. Solutions within these models are generally determined by relaxing the cardinality constraint to a weighted feature selection scheme. However, these solutions relate to the original sparse problem only under specific assumptions, which generally do not hold for medical image applications. In addition, inferring clinical meaning from features weighted by a classifier is an ongoing topic of discussion. Avoiding weighing features, we propose to directly solve the group cardinality constraint logistic regression problem by generalizing the Penalty Decomposition method. To do so, we assume that an intra-subject series of images represents repeated samples of the same disease patterns. We model this assumption by combining series of measurements created by a feature across time into a single group. Our algorithm then derives a solution within that model by decoupling the minimization of the logistic regression function from enforcing the group sparsity constraint. The minimum to the smooth and convex logistic regression problem is determined via gradient descent while we derive a closed form solution for finding a sparse approximation of that minimum. We apply our method to cine MRI of 38 healthy controls and 44 adult patients that received reconstructive surgery of Tetralogy of Fallot (TOF) during infancy. Our method correctly identifies regions impacted by TOF and generally obtains statistically significant higher classification accuracy than alternative solutions to this model, i.e., ones relaxing group cardinality constraints. Copyright © 2016 Elsevier B.V. All rights reserved.

An automated approach to the design of decision tree classifiers

NASA Technical Reports Server (NTRS)

Argentiero, P.; Chin, P.; Beaudet, P.

1980-01-01

The classification of large dimensional data sets arising from the merging of remote sensing data with more traditional forms of ancillary data is considered. Decision tree classification, a popular approach to the problem, is characterized by the property that samples are subjected to a sequence of decision rules before they are assigned to a unique class. An automated technique for effective decision tree design which relies only on apriori statistics is presented. This procedure utilizes a set of two dimensional canonical transforms and Bayes table look-up decision rules. An optimal design at each node is derived based on the associated decision table. A procedure for computing the global probability of correct classfication is also provided. An example is given in which class statistics obtained from an actual LANDSAT scene are used as input to the program. The resulting decision tree design has an associated probability of correct classification of .76 compared to the theoretically optimum .79 probability of correct classification associated with a full dimensional Bayes classifier. Recommendations for future research are included.

Automatic classification of hyperactive children: comparing multiple artificial intelligence approaches.

PubMed

Delavarian, Mona; Towhidkhah, Farzad; Gharibzadeh, Shahriar; Dibajnia, Parvin

2011-07-12

Automatic classification of different behavioral disorders with many similarities (e.g. in symptoms) by using an automated approach will help psychiatrists to concentrate on correct disorder and its treatment as soon as possible, to avoid wasting time on diagnosis, and to increase the accuracy of diagnosis. In this study, we tried to differentiate and classify (diagnose) 306 children with many similar symptoms and different behavioral disorders such as ADHD, depression, anxiety, comorbid depression and anxiety and conduct disorder with high accuracy. Classification was based on the symptoms and their severity. With examining 16 different available classifiers, by using "Prtools", we have proposed nearest mean classifier as the most accurate classifier with 96.92% accuracy in this research. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

GENIE: a hybrid genetic algorithm for feature classification in multispectral images

NASA Astrophysics Data System (ADS)

Perkins, Simon J.; Theiler, James P.; Brumby, Steven P.; Harvey, Neal R.; Porter, Reid B.; Szymanski, John J.; Bloch, Jeffrey J.

2000-10-01

We consider the problem of pixel-by-pixel classification of a multi- spectral image using supervised learning. Conventional spuervised classification techniques such as maximum likelihood classification and less conventional ones s uch as neural networks, typically base such classifications solely on the spectral components of each pixel. It is easy to see why: the color of a pixel provides a nice, bounded, fixed dimensional space in which these classifiers work well. It is often the case however, that spectral information alone is not sufficient to correctly classify a pixel. Maybe spatial neighborhood information is required as well. Or maybe the raw spectral components do not themselves make for easy classification, but some arithmetic combination of them would. In either of these cases we have the problem of selecting suitable spatial, spectral or spatio-spectral features that allow the classifier to do its job well. The number of all possible such features is extremely large. How can we select a suitable subset? We have developed GENIE, a hybrid learning system that combines a genetic algorithm that searches a space of image processing operations for a set that can produce suitable feature planes, and a more conventional classifier which uses those feature planes to output a final classification. In this paper we show that the use of a hybrid GA provides significant advantages over using either a GA alone or more conventional classification methods alone. We present results using high-resolution IKONOS data, looking for regions of burned forest and for roads.

Association algorithm to mine the rules that govern enzyme definition and to classify protein sequences.

PubMed

Chiu, Shih-Hau; Chen, Chien-Chi; Yuan, Gwo-Fang; Lin, Thy-Hou

2006-06-15

The number of sequences compiled in many genome projects is growing exponentially, but most of them have not been characterized experimentally. An automatic annotation scheme must be in an urgent need to reduce the gap between the amount of new sequences produced and reliable functional annotation. This work proposes rules for automatically classifying the fungus genes. The approach involves elucidating the enzyme classifying rule that is hidden in UniProt protein knowledgebase and then applying it for classification. The association algorithm, Apriori, is utilized to mine the relationship between the enzyme class and significant InterPro entries. The candidate rules are evaluated for their classificatory capacity. There were five datasets collected from the Swiss-Prot for establishing the annotation rules. These were treated as the training sets. The TrEMBL entries were treated as the testing set. A correct enzyme classification rate of 70% was obtained for the prokaryote datasets and a similar rate of about 80% was obtained for the eukaryote datasets. The fungus training dataset which lacks an enzyme class description was also used to evaluate the fungus candidate rules. A total of 88 out of 5085 test entries were matched with the fungus rule set. These were otherwise poorly annotated using their functional descriptions. The feasibility of using the method presented here to classify enzyme classes based on the enzyme domain rules is evident. The rules may be also employed by the protein annotators in manual annotation or implemented in an automatic annotation flowchart.

Neural network classification of sweet potato embryos

NASA Astrophysics Data System (ADS)

Molto, Enrique; Harrell, Roy C.

1993-05-01

Somatic embryogenesis is a process that allows for the in vitro propagation of thousands of plants in sub-liter size vessels and has been successfully applied to many significant species. The heterogeneity of maturity and quality of embryos produced with this technique requires sorting to obtain a uniform product. An automated harvester is being developed at the University of Florida to sort embryos in vitro at different stages of maturation in a suspension culture. The system utilizes machine vision to characterize embryo morphology and a fluidic based separation device to isolate embryos associated with a pre-defined, targeted morphology. Two different backpropagation neural networks (BNN) were used to classify embryos based on information extracted from the vision system. One network utilized geometric features such as embryo area, length, and symmetry as inputs. The alternative network utilized polar coordinates of an embryo's perimeter with respect to its centroid as inputs. The performances of both techniques were compared with each other and with an embryo classification method based on linear discriminant analysis (LDA). Similar results were obtained with all three techniques. Classification efficiency was improved by reducing the dimension of the feature vector trough a forward stepwise analysis by LDA. In order to enhance the purity of the sample selected as harvestable, a reject to classify option was introduced in the model and analyzed. The best classifier performances (76% overall correct classifications, 75% harvestable objects properly classified, homogeneity improvement ratio 1.5) were obtained using 8 features in a BNN.

X-ray agricultural product inspection: segmentation and classification

NASA Astrophysics Data System (ADS)

Casasent, David P.; Talukder, Ashit; Lee, Ha-Woon

1997-09-01

Processing of real-time x-ray images of randomly oriented and touching pistachio nuts for product inspection is considered. We describe the image processing used to isolate individual nuts (segmentation). This involves a new watershed transform algorithm. Segmentation results on approximately 3000 x-ray (film) and real time x-ray (linescan) nut images were excellent (greater than 99.9% correct). Initial classification results on film images are presented that indicate that the percentage of infested nuts can be reduced to 1.6% of the crop with only 2% of the good nuts rejected; this performance is much better than present manual methods and other automated classifiers have achieved.

Using the regulation of accuracy to study performance when the correct answer is not known.

PubMed

Luna, Karlos; Martín-Luengo, Beatriz

2017-08-01

We examined memory performance in multiple-choice questions when correct answers were not always present. How do participants answer when they are aware that the correct alternative may not be present? To answer this question we allowed participants to decide on the number of alternatives in their final answer (the plurality option), and whether they wanted to report or withhold their answer (report option). We also studied the memory benefits when both the plurality and the report options were available. In two experiments participants watched a crime and then answered questions with five alternatives. Half of the questions were presented with the correct alternative and half were not. Participants selected one alternative and rated confidence, then selected three alternatives and again rated confidence, and finally indicated whether they preferred the answer with one or with three alternatives (plurality option). Lastly, they decided whether to report or withhold the answer (report option). Results showed that participants' confidence in their selections was higher, that they chose more single answers, and that they preferred to report more often when the correct alternative was presented. We also attempted to classify a posteriori questions as either presented with or without the correct alternative from participants' selection. Classification was better than chance, and encouraging, but the forensic application of the classification technique is still limited since there was a large percentage of responses that were incorrectly classified. Our results also showed that the memory benefits of both plurality and report options overlap. © 2017 Scandinavian Psychological Associations and John Wiley & Sons Ltd.

Parenting style in relation to pathogenic and protective factors of Type A behaviour pattern.

PubMed

Castro, J; de Pablo, J; Toro, J; Valdés, M

1999-07-01

Studies of type A behaviour pattern suggest that it can be promoted as a whole by certain parental rearing styles. However, the association of the different components of the type A behaviour with specific rearing practices has not been clarified. The relationship between parents' rearing style and the different type A behaviour components of their children was analysed in a sample of 312 university students. Parental rearing style was assessed with the EMBU, a Swedish measure originally designed to assess one's recollections concerning one's parents rearing behaviour. Type A pattern was measured by the JAS, a self-administered questionnaire that gives the global type A score and three of its components. Hard Driving was related to Rejection and Favouring Subject in males. Speed-Impatience was related to Rejection and Control in both sexes, and Job Involvement was related to Control and Favouring Subject in females. In a discriminant factor analysis in males, Rejection, Control and Favouring Subject on the part of fathers classified correctly 80% of the subjects identified as having high or low Speed-Impatience and the variables of Rejection and Favouring Subject (also by fathers) classified correctly 69.23% of the subjects identified as high or low Hard Driving. In females, Control and Favouring Subject on the part of mothers and low Rejection by fathers classified correctly 70.37% of the subjects with high or low Job Involvement. These results suggest that different rearing characteristics are related to the various components of the type A behaviour pattern.

Prediction of protein long-range contacts using an ensemble of genetic algorithm classifiers with sequence profile centers.

PubMed

Chen, Peng; Li, Jinyan

2010-05-17

Prediction of long-range inter-residue contacts is an important topic in bioinformatics research. It is helpful for determining protein structures, understanding protein foldings, and therefore advancing the annotation of protein functions. In this paper, we propose a novel ensemble of genetic algorithm classifiers (GaCs) to address the long-range contact prediction problem. Our method is based on the key idea called sequence profile centers (SPCs). Each SPC is the average sequence profiles of residue pairs belonging to the same contact class or non-contact class. GaCs train on multiple but different pairs of long-range contact data (positive data) and long-range non-contact data (negative data). The negative data sets, having roughly the same sizes as the positive ones, are constructed by random sampling over the original imbalanced negative data. As a result, about 21.5% long-range contacts are correctly predicted. We also found that the ensemble of GaCs indeed makes an accuracy improvement by around 5.6% over the single GaC. Classifiers with the use of sequence profile centers may advance the long-range contact prediction. In line with this approach, key structural features in proteins would be determined with high efficiency and accuracy.

Robust online tracking via adaptive samples selection with saliency detection

NASA Astrophysics Data System (ADS)

Yan, Jia; Chen, Xi; Zhu, QiuPing

2013-12-01

Online tracking has shown to be successful in tracking of previously unknown objects. However, there are two important factors which lead to drift problem of online tracking, the one is how to select the exact labeled samples even when the target locations are inaccurate, and the other is how to handle the confusors which have similar features with the target. In this article, we propose a robust online tracking algorithm with adaptive samples selection based on saliency detection to overcome the drift problem. To deal with the problem of degrading the classifiers using mis-aligned samples, we introduce the saliency detection method to our tracking problem. Saliency maps and the strong classifiers are combined to extract the most correct positive samples. Our approach employs a simple yet saliency detection algorithm based on image spectral residual analysis. Furthermore, instead of using the random patches as the negative samples, we propose a reasonable selection criterion, in which both the saliency confidence and similarity are considered with the benefits that confusors in the surrounding background are incorporated into the classifiers update process before the drift occurs. The tracking task is formulated as a binary classification via online boosting framework. Experiment results in several challenging video sequences demonstrate the accuracy and stability of our tracker.

Selection of the best features for leukocytes classification in blood smear microscopic images

NASA Astrophysics Data System (ADS)

Sarrafzadeh, Omid; Rabbani, Hossein; Talebi, Ardeshir; Banaem, Hossein Usefi

2014-03-01

Automatic differential counting of leukocytes provides invaluable information to pathologist for diagnosis and treatment of many diseases. The main objective of this paper is to detect leukocytes from a blood smear microscopic image and classify them into their types: Neutrophil, Eosinophil, Basophil, Lymphocyte and Monocyte using features that pathologists consider to differentiate leukocytes. Features contain color, geometric and texture features. Colors of nucleus and cytoplasm vary among the leukocytes. Lymphocytes have single, large, round or oval and Monocytes have singular convoluted shape nucleus. Nucleus of Eosinophils is divided into 2 segments and nucleus of Neutrophils into 2 to 5 segments. Lymphocytes often have no granules, Monocytes have tiny granules, Neutrophils have fine granules and Eosinophils have large granules in cytoplasm. Six color features is extracted from both nucleus and cytoplasm, 6 geometric features only from nucleus and 6 statistical features and 7 moment invariants features only from cytoplasm of leukocytes. These features are fed to support vector machine (SVM) classifiers with one to one architecture. The results obtained by applying the proposed method on blood smear microscopic image of 10 patients including 149 white blood cells (WBCs) indicate that correct rate for all classifiers are above 93% which is in a higher level in comparison with previous literatures.

Semantic segmentation of mFISH images using convolutional networks.

PubMed

Pardo, Esteban; Morgado, José Mário T; Malpica, Norberto

2018-04-30

Multicolor in situ hybridization (mFISH) is a karyotyping technique used to detect major chromosomal alterations using fluorescent probes and imaging techniques. Manual interpretation of mFISH images is a time consuming step that can be automated using machine learning; in previous works, pixel or patch wise classification was employed, overlooking spatial information which can help identify chromosomes. In this work, we propose a fully convolutional semantic segmentation network for the interpretation of mFISH images, which uses both spatial and spectral information to classify each pixel in an end-to-end fashion. The semantic segmentation network developed was tested on samples extracted from a public dataset using cross validation. Despite having no labeling information of the image it was tested on, our algorithm yielded an average correct classification ratio (CCR) of 87.41%. Previously, this level of accuracy was only achieved with state of the art algorithms when classifying pixels from the same image in which the classifier has been trained. These results provide evidence that fully convolutional semantic segmentation networks may be employed in the computer aided diagnosis of genetic diseases with improved performance over the current image analysis methods. © 2018 International Society for Advancement of Cytometry. © 2018 International Society for Advancement of Cytometry.

Evaluation of Food Freshness and Locality by Odor Sensor

NASA Astrophysics Data System (ADS)

Koike, Takayuki; Shimada, Koji; Kamimura, Hironobu; Kaneki, Noriaki

The aim of this study was to investigate whether food freshness and locality can be classified using a food evaluation system consisting four SnO2-semiconductor gas sensors and a solid phase column, into which collecting aroma materials. The temperature of sensors was periodically changed to be in unsteady state and thus, the sensor information was increased. The parameters (in quefrency band) were extracted from sensor information using cepstrum analysis that enable to separate superimposed information on sinusoidal wave. The quefrency was used as parameters for principal component and discriminant analyses (PCA and DCA) to detect food freshness and food localities. We used three kinds of strawberries, people can perceive its odors, passed from one to three days after harvest, and kelps and Ceylon tea, people are hardly to perceive its odor, corrected from five areas as sample. Then, the deterioration of strawberries and localities of kelps and Ceylon teas were visually evaluated using the numerical analyses. While the deteriorations were classified using PCA or DCA, the localities were classified only by DCA. The findings indicate that, although odorant intensity influenced the method detecting food quality, the quefrency obtained from odorant information using cepstrum analysis were available to detect the difference in the freshness and the localities of foods.

Classifying magnetic resonance image modalities with convolutional neural networks

NASA Astrophysics Data System (ADS)

Remedios, Samuel; Pham, Dzung L.; Butman, John A.; Roy, Snehashis

2018-02-01

Magnetic Resonance (MR) imaging allows the acquisition of images with different contrast properties depending on the acquisition protocol and the magnetic properties of tissues. Many MR brain image processing techniques, such as tissue segmentation, require multiple MR contrasts as inputs, and each contrast is treated differently. Thus it is advantageous to automate the identification of image contrasts for various purposes, such as facilitating image processing pipelines, and managing and maintaining large databases via content-based image retrieval (CBIR). Most automated CBIR techniques focus on a two-step process: extracting features from data and classifying the image based on these features. We present a novel 3D deep convolutional neural network (CNN)- based method for MR image contrast classification. The proposed CNN automatically identifies the MR contrast of an input brain image volume. Specifically, we explored three classification problems: (1) identify T1-weighted (T1-w), T2-weighted (T2-w), and fluid-attenuated inversion recovery (FLAIR) contrasts, (2) identify pre vs postcontrast T1, (3) identify pre vs post-contrast FLAIR. A total of 3418 image volumes acquired from multiple sites and multiple scanners were used. To evaluate each task, the proposed model was trained on 2137 images and tested on the remaining 1281 images. Results showed that image volumes were correctly classified with 97.57% accuracy.

Correction of differential renal function for asymmetric renal area ratio in unilateral hydronephrosis.

PubMed

Aktaş, Gul Ege; Sarıkaya, Ali

2015-11-01

Children with unilateral hydronephrosis are followed up with anteroposterior pelvic diameter (APD), hydronephrosis grade, mercaptoacetyltriglycine (MAG-3) drainage pattern and differential renal function (DRF). Indeterminate drainage preserved DRF in higher grades of hydronephrosis, in some situations, complicating the decision-making process. Due to an asymmetric renal area ratio, falsely negative DRF estimations can result in missed optimal surgery times. This study was designed to assess whether correcting the DRF estimation according to kidney area could reflect the clinical situation of a hydronephrotic kidney better than a classical DRF calculation, concurrently with the hydronephrosis grade, APD and MAG-3 drainage pattern. We reviewed the MAG-3, dimercaptosuccinic acid (DMSA) scans and ultrasonography (US) of 23 children (6 girls, 17 boys, mean age: 29 ± 50 months) with unilateral hydronephrosis. MAG-3 and DMSA scans were performed within 3 months (mean 25.4 ± 30.7 days). The closest US findings (mean 41.5 ± 28.2 days) were used. DMSA DRF estimations were obtained using the geometric mean method. Secondary calculations were performed to correct the counts (the total counts divided by the number of pixels in ROI) according to kidney area. The renogram patterns of patients were evaluated and separated into subgroups. The visual assessment of DMSA scans was noted and the hydronephrotic kidney was classified in comparison to the normal contralateral kidney's uptake. The correlations of the DRF values of classical and area-corrected methods with MAG-3 renogram patterns, the visual classification of DMSA scan, the hydronephrosis grade and the APD were assessed. DRF estimations of two methods were statistically different (p: 0.001). The categories of 12 hydronephrotic kidneys were changed. There were no correlations between classical DRF estimations and the hydronephrosis grade, APD, visual classification of the DMSA scan and uptake evaluation. The DRF distributions according to MAG-3 drainage patterns were not different. Area-corrected DRF estimations correlated with all: with an increasing hydronephrosis grade and APD, DRF estimations decreased and MAG-3 drainage patterns worsened. A decrease in DRF (< 45 %) was determined when APD was ≥ 10 mm. When APD was ≥ 26 mm, a reduction of DRF below 40 % was determined. Our results suggest that correcting DRF estimation for asymmetric renal area ratio in unilateral hydronephrosis can be more robust than the classical method, especially for higher grades of hydronephrotic kidneys, under equivocal circumstances.

Purely in silico BCS classification: science based quality standards for the world's drugs.

PubMed

Dahan, Arik; Wolk, Omri; Kim, Young Hoon; Ramachandran, Chandrasekharan; Crippen, Gordon M; Takagi, Toshihide; Bermejo, Marival; Amidon, Gordon L

2013-11-04

BCS classification is a vital tool in the development of both generic and innovative drug products. The purpose of this work was to provisionally classify the world's top selling oral drugs according to the BCS, using in silico methods. Three different in silico methods were examined: the well-established group contribution (CLogP) and atom contribution (ALogP) methods, and a new method based solely on the molecular formula and element contribution (KLogP). Metoprolol was used as the benchmark for the low/high permeability class boundary. Solubility was estimated in silico using a thermodynamic equation that relies on the partition coefficient and melting point. The validity of each method was affirmed by comparison to reference data and literature. We then used each method to provisionally classify the orally administered, IR drug products found in the WHO Model list of Essential Medicines, and the top-selling oral drug products in the United States (US), Great Britain (GB), Spain (ES), Israel (IL), Japan (JP), and South Korea (KR). A combined list of 363 drugs was compiled from the various lists, and 257 drugs were classified using the different in silico permeability methods and literature solubility data, as well as BDDCS classification. Lastly, we calculated the solubility values for 185 drugs from the combined set using in silico approach. Permeability classification with the different in silico methods was correct for 69-72.4% of the 29 reference drugs with known human jejunal permeability, and for 84.6-92.9% of the 14 FDA reference drugs in the set. The correlations (r(2)) between experimental log P values of 154 drugs and their CLogP, ALogP and KLogP were 0.97, 0.82 and 0.71, respectively. The different in silico permeability methods produced comparable results: 30-34% of the US, GB, ES and IL top selling drugs were class 1, 27-36.4% were class 2, 22-25.5% were class 3, and 5.46-14% were class 4 drugs, while ∼8% could not be classified. The WHO list included significantly less class 1 and more class 3 drugs in comparison to the countries' lists, probably due to differences in commonly used drugs in developing vs industrial countries. BDDCS classified more drugs as class 1 compared to in silico BCS, likely due to the more lax benchmark for metabolism (70%), in comparison to the strict permeability benchmark (metoprolol). For 185 out of the 363 drugs, in silico solubility values were calculated, and successfully matched the literature solubility data. In conclusion, relatively simple in silico methods can be used to estimate both permeability and solubility. While CLogP produced the best correlation to experimental values, even KLogP, the most simplified in silico method that is based on molecular formula with no knowledge of molecular structure, produced comparable BCS classification to the sophisticated methods. This KLogP, when combined with a mean melting point and estimated dose, can be used to provisionally classify potential drugs from just molecular formula, even before synthesis. 49-59% of the world's top-selling drugs are highly soluble (class 1 and class 3), and are therefore candidates for waivers of in vivo bioequivalence studies. For these drugs, the replacement of expensive human studies with affordable in vitro dissolution tests would ensure their bioequivalence, and encourage the development and availability of generic drug products in both industrial and developing countries.

In/Out Status Monitoring in Mobile Asset Tracking with Wireless Sensor Networks

PubMed Central

Kim, Kwangsoo; Chung, Chin-Wan

2010-01-01

A mobile asset with a sensor node in a mobile asset tracking system moves around a monitoring area, leaves it, and then returns to the region repeatedly. The system monitors the in/out status of the mobile asset. Due to the continuous movement of the mobile asset, the system may generate an error for the in/out status of the mobile asset. When the mobile asset is inside the region, the system might determine that it is outside, or vice versa. In this paper, we propose a method to detect and correct the incorrect in/out status of the mobile asset. To solve this problem, our approach uses data about the connection state transition and the battery lifetime of the mobile node attached to the mobile asset. The connection state transition is used to classify the mobile node as normal or abnormal. The battery lifetime is used to predict a valid working period for the mobile node. We evaluate our method using real data generated by a medical asset tracking system. The experimental results show that our method, by using the estimated battery life time or by using the invalid connection state, can detect and correct most cases of incorrect in/out statuses generated by the conventional approach. PMID:22319268

Accurate method for luminous transmittance and signal detection quotients measurements in sunglasses lenses

NASA Astrophysics Data System (ADS)

Loureiro, A. D.; Gomes, L. M.; Ventura, L.

2018-02-01

The international standard ISO 12312-1 proposes transmittance tests that quantify how dark sunglasses lenses are and whether or not they are suitable for driving. To perform these tests a spectrometer is required. In this study, we present and analyze theoretically an accurate alternative method for performing these measurements using simple components. Using three LEDs and a four-channel sensor we generated weighting functions similar to the standard ones for luminous and traffic lights transmittances. From 89 sunglasses lens spectroscopy data, we calculated luminous transmittance and signal detection quotients using our obtained weighting functions and the standard ones. Mean-difference Tukey plots were used to compare the results. All tested sunglasses lenses were classified in the right category and correctly as suitable or not for driving. The greatest absolute errors for luminous transmittance and red, yellow, green and blue signal detection quotients were 0.15%, 0.17, 0.06, 0.04 and 0.18, respectively. This method will be used in a device capable to perform transmittance tests (visible, traffic lights and ultraviolet (UV)) according to the standard. It is important to measure rightly luminous transmittance and relative visual attenuation quotients to report correctly whether or not sunglasses are suitable for driving. Moreover, standard UV requirements depend on luminous transmittance.

[Prediction of histological liver damage in asymptomatic alcoholic patients by means of clinical and laboratory data].

PubMed

Iturriaga, H; Hirsch, S; Bunout, D; Díaz, M; Kelly, M; Silva, G; de la Maza, M P; Petermann, M; Ugarte, G

1993-04-01

Looking for a noninvasive method to predict liver histologic alterations in alcoholic patients without clinical signs of liver failure, we studied 187 chronic alcoholics recently abstinent, divided in 2 series. In the model series (n = 94) several clinical variables and results of common laboratory tests were confronted to the findings of liver biopsies. These were classified in 3 groups: 1. Normal liver; 2. Moderate alterations; 3. Marked alterations, including alcoholic hepatitis and cirrhosis. Multivariate methods used were logistic regression analysis and a classification and regression tree (CART). Both methods entered gamma-glutamyltransferase (GGT), aspartate-aminotransferase (AST), weight and age as significant and independent variables. Univariate analysis with GGT and AST at different cutoffs were also performed. To predict the presence of any kind of damage (Groups 2 and 3), CART and AST > 30 IU showed the higher sensitivity, specificity and correct prediction, both in the model and validation series. For prediction of marked liver damage, a score based on logistic regression and GGT > 110 IU had the higher efficiencies. It is concluded that GGT and AST are good markers of alcoholic liver damage and that, using sample cutoffs, histologic diagnosis can be correctly predicted in 80% of recently abstinent asymptomatic alcoholics.

In/out status monitoring in mobile asset tracking with wireless sensor networks.

PubMed

Kim, Kwangsoo; Chung, Chin-Wan

2010-01-01

A mobile asset with a sensor node in a mobile asset tracking system moves around a monitoring area, leaves it, and then returns to the region repeatedly. The system monitors the in/out status of the mobile asset. Due to the continuous movement of the mobile asset, the system may generate an error for the in/out status of the mobile asset. When the mobile asset is inside the region, the system might determine that it is outside, or vice versa. In this paper, we propose a method to detect and correct the incorrect in/out status of the mobile asset. To solve this problem, our approach uses data about the connection state transition and the battery lifetime of the mobile node attached to the mobile asset. The connection state transition is used to classify the mobile node as normal or abnormal. The battery lifetime is used to predict a valid working period for the mobile node. We evaluate our method using real data generated by a medical asset tracking system. The experimental results show that our method, by using the estimated battery life time or by using the invalid connection state, can detect and correct most cases of incorrect in/out statuses generated by the conventional approach.

Treatment in Borderline Class III Malocclusion: Orthodontic Camouflage (Extraction) Versus Orthognathic Surgery

PubMed Central

Rabie, A-Bakr M.; Wong, Ricky W.K.; Min, G.U.

2008-01-01

Aims: To investigate the differences in morphological characteristics of borderline class III patients who had undergone camouflage orthodontic treatment or orthognathic surgery, and to compare the treatment effects between these two modalities. Materials and Methods: Cephalograms of 25 patients (13 orthodontic, 12 surgical) with class III malocclusion were analyzed. All had a pretreatment ANB angle greater than -5º. Results: Using discriminant analysis, only Holdaway angle was selected to differentiate patients in the pretreatment stage. Seventy-two per cent patients were correctly classified. In the orthodontic group, reverse overjet was corrected by retraction of the lower incisors and downward and backward rotation of the mandible. The surgical group was corrected by setback of the lower anterior dentoalveolus and uprighting of the lower incisors. No difference was found in posttreatment soft tissue measurements between the two groups. Conclusions: Twelve degree for the Holdaway angle can be a guideline in determining the treatment modalities for borderline class III patients, but the preferences of operators and patients are also important. (2) Both therapeutic options should highlight changes in the lower dentoalveolus and lower incisors. (3) Both treatment modalities can achieve satisfactory improvements to the people. PMID:19088881

A classification on human factor accident/incident of China civil aviation in recent twelve years.

PubMed

Luo, Xiao-li

2004-10-01

To study human factor accident/incident occurred during 1990-2001 using new classification standard. The human factor accident/incident classification standard is developed on the basis of Reason's Model, combining with CAAC's traditional classifying method, and applied to the classified statistical analysis for 361 flying incidents and 35 flight accidents of China civil aviation, which is induced by human factors and occurred from 1990 to 2001. 1) the incident percentage of taxi and cruise is higher than that of takeoff, climb and descent. 2) The dominating type of flight incidents is diverging of runway, overrunning, near-miss, tail/wingtip/engine strike and ground obstacle impacting. 3) The top three accidents are out of control caused by crew, mountain collision and over runway. 4) Crew's basic operating skill is lower than what we imagined, the mostly representation is poor correcting ability when flight error happened. 5) Crew errors can be represented by incorrect control, regulation and procedure violation, disorientation and diverging percentage of correct flight level. The poor CRM skill is the dominant factor impacting China civil aviation safety, this result has a coincidence with previous study, but there is much difference and distinct characteristic in top incident phase, the type of crew error and behavior performance compared with that of advanced countries. We should strengthen CRM training for all of pilots aiming at the Chinese pilot behavior characteristic in order to improve the safety level of China civil aviation.

A Comparison of the Diagnostic Accuracy of Common Office Blood Pressure Monitoring Protocols.

PubMed

Kronish, I M; Edmondson, D; Shimbo, D; Shaffer, J A; Krakoff, L R; Schwartz, J E

2018-04-20

The optimal approach to measuring office blood pressure (BP) is uncertain. We aimed to compare BP measurement protocols that differed based on numbers of readings within and between visits and by assessment method. We enrolled a sample of 707 employees without known hypertension or cardiovascular disease, and obtained 6 standardized BP readings during each of 3 office visits at least 1 week apart, using mercury sphygmomanometer and BpTRU oscillometric devices (18 readings per participant) for a total of 12,645 readings. We used confirmatory factor analysis to develop a model estimating "true" office BP that could be used to compare the probability of correctly classifying participants' office BP status using differing numbers and types of office BP readings. Averaging two systolic BP readings across two visits correctly classified participants as having BP below or above the 140 mmHg threshold at least 95% of the time if the averaged reading was <134 mmHg or >149 mmHg, respectively. Our model demonstrated that more confidence was gained by increasing the number of visits with readings than by increasing the number of readings within a visit. No clinically significant confidence was gained by dropping the first reading versus averaging all readings, nor by measuring with a manual mercury device versus with an automated oscillometric device. Averaging two BP readings across two office visits appeared to best balance increased confidence in office BP status with efficiency of BP measurement, though the preferred measurement strategy may vary with the clinical context.

Characterization of edible seaweed harvested on the Galician coast (northwestern Spain) using pattern recognition techniques and major and trace element data.

PubMed

Romarís-Hortas, Vanessa; García-Sartal, Cristina; Barciela-Alonso, María Carmen; Moreda-Piñeiro, Antonio; Bermejo-Barrera, Pilar

2010-02-10

Major and trace elements in North Atlantic seaweed originating from Galicia (northwestern Spain) were determined by using inductively coupled plasma-optical emission spectrometry (ICP-OES) (Ba, Ca, Cu, K, Mg, Mn, Na, Sr, and Zn), inductively coupled plasma-mass spectrometry (ICP-MS) (Br and I) and hydride generation-atomic fluorescence spectrometry (HG-AFS) (As). Pattern recognition techniques were then used to classify the edible seaweed according to their type (red, brown, and green seaweed) and also their variety (Wakame, Fucus, Sea Spaghetti, Kombu, Dulse, Nori, and Sea Lettuce). Principal component analysis (PCA) and cluster analysis (CA) were used as exploratory techniques, and linear discriminant analysis (LDA) and soft independent modeling of class analogy (SIMCA) were used as classification procedures. In total, t12 elements were determined in a range of 35 edible seaweed samples (20 brown seaweed, 10 red seaweed, 4 green seaweed, and 1 canned seaweed). Natural groupings of the samples (brown, red, and green types) were observed using PCA and CA (squared Euclidean distance between objects and Ward method as clustering procedure). The application of LDA gave correct assignation percentages of 100% for brown, red, and green types at a significance level of 5%. However, a satisfactory classification (recognition and prediction) using SIMCA was obtained only for red seaweed (100% of cases correctly classified), whereas percentages of 89 and 80% were obtained for brown seaweed for recognition (training set) and prediction (testing set), respectively.

Vision 20/20: Magnetic resonance imaging-guided attenuation correction in PET/MRI: Challenges, solutions, and opportunities

DOE Office of Scientific and Technical Information (OSTI.GOV)

Mehranian, Abolfazl; Arabi, Hossein; Zaidi, Habib, E-mail: habib.zaidi@hcuge.ch

Attenuation correction is an essential component of the long chain of data correction techniques required to achieve the full potential of quantitative positron emission tomography (PET) imaging. The development of combined PET/magnetic resonance imaging (MRI) systems mandated the widespread interest in developing novel strategies for deriving accurate attenuation maps with the aim to improve the quantitative accuracy of these emerging hybrid imaging systems. The attenuation map in PET/MRI should ideally be derived from anatomical MR images; however, MRI intensities reflect proton density and relaxation time properties of biological tissues rather than their electron density and photon attenuation properties. Therefore, inmore » contrast to PET/computed tomography, there is a lack of standardized global mapping between the intensities of MRI signal and linear attenuation coefficients at 511 keV. Moreover, in standard MRI sequences, bones and lung tissues do not produce measurable signals owing to their low proton density and short transverse relaxation times. MR images are also inevitably subject to artifacts that degrade their quality, thus compromising their applicability for the task of attenuation correction in PET/MRI. MRI-guided attenuation correction strategies can be classified in three broad categories: (i) segmentation-based approaches, (ii) atlas-registration and machine learning methods, and (iii) emission/transmission-based approaches. This paper summarizes past and current state-of-the-art developments and latest advances in PET/MRI attenuation correction. The advantages and drawbacks of each approach for addressing the challenges of MR-based attenuation correction are comprehensively described. The opportunities brought by both MRI and PET imaging modalities for deriving accurate attenuation maps and improving PET quantification will be elaborated. Future prospects and potential clinical applications of these techniques and their integration in commercial systems will also be discussed.« less

Vision 20/20: Magnetic resonance imaging-guided attenuation correction in PET/MRI: Challenges, solutions, and opportunities.

PubMed

Mehranian, Abolfazl; Arabi, Hossein; Zaidi, Habib

2016-03-01

Attenuation correction is an essential component of the long chain of data correction techniques required to achieve the full potential of quantitative positron emission tomography (PET) imaging. The development of combined PET/magnetic resonance imaging (MRI) systems mandated the widespread interest in developing novel strategies for deriving accurate attenuation maps with the aim to improve the quantitative accuracy of these emerging hybrid imaging systems. The attenuation map in PET/MRI should ideally be derived from anatomical MR images; however, MRI intensities reflect proton density and relaxation time properties of biological tissues rather than their electron density and photon attenuation properties. Therefore, in contrast to PET/computed tomography, there is a lack of standardized global mapping between the intensities of MRI signal and linear attenuation coefficients at 511 keV. Moreover, in standard MRI sequences, bones and lung tissues do not produce measurable signals owing to their low proton density and short transverse relaxation times. MR images are also inevitably subject to artifacts that degrade their quality, thus compromising their applicability for the task of attenuation correction in PET/MRI. MRI-guided attenuation correction strategies can be classified in three broad categories: (i) segmentation-based approaches, (ii) atlas-registration and machine learning methods, and (iii) emission/transmission-based approaches. This paper summarizes past and current state-of-the-art developments and latest advances in PET/MRI attenuation correction. The advantages and drawbacks of each approach for addressing the challenges of MR-based attenuation correction are comprehensively described. The opportunities brought by both MRI and PET imaging modalities for deriving accurate attenuation maps and improving PET quantification will be elaborated. Future prospects and potential clinical applications of these techniques and their integration in commercial systems will also be discussed.

Using Different Standardized Methods for Species Identification: A Case Study Using Beaks from Three Ommastrephid Species

NASA Astrophysics Data System (ADS)

Hu, Guanyu; Fang, Zhou; Liu, Bilin; Chen, Xinjun; Staples, Kevin; Chen, Yong

2018-04-01

The cephalopod beak is a vital hard structure with a stable configuration and has been widely used for the identification of cephalopod species. This study was conducted to determine the best standardization method for identifying different species by measuring 12 morphological variables of the beaks of Illex argentinus, Ommastrephes bartramii, and Dosidicus gigas that were collected by Chinese jigging vessels. To remove the effects of size, these morphometric variables were standardized using three methods. The average ratios of the upper beak morphological variables and upper crest length of O. bartramii and D. gigas were found to be greater than those of I. argentinus. However, for lower beaks, only the average of LRL (lower rostrum length)/ LCL (lower crest length), LRW (lower rostrum width)/ LCL, and LLWL (lower lateral wall length)/ LCL of O. bartramii and D. gigas were greater than those of I. argentinus. The ratios of beak morphological variables and crest length were found to be all significantly different among the three species ( P < 0.001). Among the three standardization methods, the correct classification rate of stepwise discriminant analysis (SDA) was the highest using the ratios of beak morphological variables and crest length. Compared with hood length, the correct classification rate was slightly higher when using beak variables standardized by crest length using an allometric model. The correct classification rate of the lower beak was also found to be greater than that of the upper beak. This study indicates that the ratios of beak morphological variables to crest length could be used for interspecies and intraspecies identification. Meanwhile, the lower beak variables were found to be more effective than upper beak variables in classifying beaks found in the stomachs of predators.

Critical analysis of dual-chamber implantable cardioverter-defibrillator arrhythmia detection : results and technical considerations.

PubMed

Wilkoff, B L; Kühlkamp, V; Volosin, K; Ellenbogen, K; Waldecker, B; Kacet, S; Gillberg, J M; DeSouza, C M

2001-01-23

One of the perceived benefits of dual-chamber implantable cardioverter-defibrillators (ICDs) is the reduction in inappropriate therapy due to new detection algorithms. It was the purpose of the present investigation to propose methods to minimize bias during such comparisons and to report the arrhythmia detection clinical results of the PR Logic dual-chamber detection algorithm in the GEM DR ICD in the context of these methods. Between November 1997 and October 1998, 933 patients received the GEM DR ICD in this prospective multicenter study. A total of 4856 sustained arrhythmia episodes (n=311) with stored electrogram and marker channel were classified by the investigators; 3488 episodes (n=232) were ventricular tachycardia (VT)/ventricular fibrillation (VF), and 1368 episodes (n=149) were supraventricular tachycardia (SVT). The overall detection results were corrected for multiple episodes within a patient with the generalized estimating equations (GEE) method with an exchangeable correlation structure between episodes. The relative sensitivity for detection of sustained VT and/or VF was 100.0% (3488 of 3488, n=232; 95% CI 98.3% to 100%), the VT/VF positive predictivity was 88.4% uncorrected (3488 of 3945, n=278) and 78.1% corrected (95% CI 73.3% to 82.3%) with the GEE method, and the SVT positive predictivity was 100.0% (911 of 911, n=101; 95% CI 96% to 100%). A structured approach to analysis limits the bias inherent in the evaluation of tachycardia discrimination algorithms through the use of relative VT/VF sensitivity, VT/VF positive predictivity, and SVT positive predictivity along with corrections for multiple tachycardia episodes in a single patient.

Dynamic analysis environment for nuclear forensic analyses

NASA Astrophysics Data System (ADS)

Stork, C. L.; Ummel, C. C.; Stuart, D. S.; Bodily, S.; Goldblum, B. L.

2017-01-01

A Dynamic Analysis Environment (DAE) software package is introduced to facilitate group inclusion/exclusion method testing, evaluation and comparison for pre-detonation nuclear forensics applications. Employing DAE, the multivariate signatures of a questioned material can be compared to the signatures for different, known groups, enabling the linking of the questioned material to its potential process, location, or fabrication facility. Advantages of using DAE for group inclusion/exclusion include built-in query tools for retrieving data of interest from a database, the recording and documentation of all analysis steps, a clear visualization of the analysis steps intelligible to a non-expert, and the ability to integrate analysis tools developed in different programming languages. Two group inclusion/exclusion methods are implemented in DAE: principal component analysis, a parametric feature extraction method, and k nearest neighbors, a nonparametric pattern recognition method. Spent Fuel Isotopic Composition (SFCOMPO), an open source international database of isotopic compositions for spent nuclear fuels (SNF) from 14 reactors, is used to construct PCA and KNN models for known reactor groups, and 20 simulated SNF samples are utilized in evaluating the performance of these group inclusion/exclusion models. For all 20 simulated samples, PCA in conjunction with the Q statistic correctly excludes a large percentage of reactor groups and correctly includes the true reactor of origination. Employing KNN, 14 of the 20 simulated samples are classified to their true reactor of origination.

Validation of a side-scan sonar method for quantifying walleye spawning habitat availability in the littoral zone of northern Wisconsin Lakes

USGS Publications Warehouse

Richter, Jacob T.; Sloss, Brian L.; Isermann, Daniel A.

2016-01-01

Previous research has generally ignored the potential effects of spawning habitat availability and quality on recruitment of Walleye Sander vitreus, largely because information on spawning habitat is lacking for many lakes. Furthermore, traditional transect-based methods used to describe habitat are time and labor intensive. Our objectives were to determine if side-scan sonar could be used to accurately classify Walleye spawning habitat in the nearshore littoral zone and provide lakewide estimates of spawning habitat availability similar to estimates obtained from a transect–quadrat-based method. Based on assessments completed on 16 northern Wisconsin lakes, interpretation of side-scan sonar images resulted in correct identification of substrate size-class for 93% (177 of 191) of selected locations and all incorrect classifications were within ± 1 class of the correct substrate size-class. Gravel, cobble, and rubble substrates were incorrectly identified from side-scan images in only two instances (1% misclassification), suggesting that side-scan sonar can be used to accurately identify preferred Walleye spawning substrates. Additionally, we detected no significant differences in estimates of lakewide littoral zone substrate compositions estimated using side-scan sonar and a traditional transect–quadrat-based method. Our results indicate that side-scan sonar offers a practical, accurate, and efficient technique for assessing substrate composition and quantifying potential Walleye spawning habitat in the nearshore littoral zone of north temperate lakes.

Retinal biometrics based on Iterative Closest Point algorithm.

PubMed

Hatanaka, Yuji; Tajima, Mikiya; Kawasaki, Ryo; Saito, Koko; Ogohara, Kazunori; Muramatsu, Chisako; Sunayama, Wataru; Fujita, Hiroshi

2017-07-01

The pattern of blood vessels in the eye is unique to each person because it rarely changes over time. Therefore, it is well known that retinal blood vessels are useful for biometrics. This paper describes a biometrics method using the Jaccard similarity coefficient (JSC) based on blood vessel regions in retinal image pairs. The retinal image pairs were rough matched by the center of their optic discs. Moreover, the image pairs were aligned using the Iterative Closest Point algorithm based on detailed blood vessel skeletons. For registration, perspective transform was applied to the retinal images. Finally, the pairs were classified as either correct or incorrect using the JSC of the blood vessel region in the image pairs. The proposed method was applied to temporal retinal images, which were obtained in 2009 (695 images) and 2013 (87 images). The 87 images acquired in 2013 were all from persons already examined in 2009. The accuracy of the proposed method reached 100%.

Comparison of Various Equations for Estimating GFR in Malawi: How to Determine Renal Function in Resource Limited Settings?

PubMed Central

Phiri, Sam; Rothenbacher, Dietrich; Neuhann, Florian

2015-01-01

Background Chronic kidney disease (CKD) is a probably underrated public health problem in Sub-Saharan-Africa, in particular in combination with HIV-infection. Knowledge about the CKD prevalence is scarce and in the available literature different methods to classify CKD are used impeding comparison and general prevalence estimates. Methods This study assessed different serum-creatinine based equations for glomerular filtration rates (eGFR) and compared them to a cystatin C based equation. The study was conducted in Lilongwe, Malawi enrolling a population of 363 adults of which 32% were HIV-positive. Results Comparison of formulae based on Bland-Altman-plots and accuracy revealed best performance for the CKD-EPI equation without the correction factor for black Americans. Analyzing the differences between HIV-positive and –negative individuals CKD-EPI systematically overestimated eGFR in comparison to cystatin C and therefore lead to underestimation of CKD in HIV-positives. Conclusions Our findings underline the importance for standardization of eGFR calculation in a Sub-Saharan African setting, to further investigate the differences with regard to HIV status and to develop potential correction factors as established for age and sex. PMID:26083345

Detection and classification of human body odor using an electronic nose.

PubMed

Wongchoosuk, Chatchawal; Lutz, Mario; Kerdcharoen, Teerakiat

2009-01-01

An electronic nose (E-nose) has been designed and equipped with software that can detect and classify human armpit body odor. An array of metal oxide sensors was used for detecting volatile organic compounds. The measurement circuit employs a voltage divider resistor to measure the sensitivity of each sensor. This E-nose was controlled by in-house developed software through a portable USB data acquisition card with a principle component analysis (PCA) algorithm implemented for pattern recognition and classification. Because gas sensor sensitivity in the detection of armpit odor samples is affected by humidity, we propose a new method and algorithms combining hardware/software for the correction of the humidity noise. After the humidity correction, the E-nose showed the capability of detecting human body odor and distinguishing the body odors from two persons in a relative manner. The E-nose is still able to recognize people, even after application of deodorant. In conclusion, this is the first report of the application of an E-nose for armpit odor recognition.

Detection and Classification of Human Body Odor Using an Electronic Nose

PubMed Central

Wongchoosuk, Chatchawal; Lutz, Mario; Kerdcharoen, Teerakiat

2009-01-01

An electronic nose (E-nose) has been designed and equipped with software that can detect and classify human armpit body odor. An array of metal oxide sensors was used for detecting volatile organic compounds. The measurement circuit employs a voltage divider resistor to measure the sensitivity of each sensor. This E-nose was controlled by in-house developed software through a portable USB data acquisition card with a principle component analysis (PCA) algorithm implemented for pattern recognition and classification. Because gas sensor sensitivity in the detection of armpit odor samples is affected by humidity, we propose a new method and algorithms combining hardware/software for the correction of the humidity noise. After the humidity correction, the E-nose showed the capability of detecting human body odor and distinguishing the body odors from two persons in a relative manner. The E-nose is still able to recognize people, even after application of deodorant. In conclusion, this is the first report of the application of an E-nose for armpit odor recognition. PMID:22399995

SU-D-BRB-01: A Predictive Planning Tool for Stereotactic Radiosurgery

DOE Office of Scientific and Technical Information (OSTI.GOV)

Palefsky, S; Roper, J; Elder, E

Purpose: To demonstrate the feasibility of a predictive planning tool which provides SRS planning guidance based on simple patient anatomical properties: PTV size, PTV shape and distance from critical structures. Methods: Ten framed SRS cases treated at Winship Cancer Institute of Emory University were analyzed to extract data on PTV size, sphericity (shape), and distance from critical structures such as the brainstem and optic chiasm. The cases consisted of five pairs. Each pair consisted of two cases with a similar diagnosis (such as pituitary adenoma or arteriovenous malformation) that were treated with different techniques: DCA, or IMRS. A Naive Bayesmore » Classifier was trained on this data to establish the conditions under which each treatment modality was used. This model was validated by classifying ten other randomly-selected cases into DCA or IMRS classes, calculating the probability of each technique, and comparing results to the treated technique. Results: Of the ten cases used to validate the model, nine had their technique predicted correctly. The three cases treated with IMRS were all identified as such. Their probabilities of being treated with IMRS ranged between 59% and 100%. Six of the seven cases treated with DCA were correctly classified. These probabilities ranged between 51% and 95%. One case treated with DCA was incorrectly predicted to be an IMRS plan. The model’s confidence in this case was 91%. Conclusion: These findings indicate that a predictive planning tool based on simple patient anatomical properties can predict the SRS technique used for treatment. The algorithm operated with 90% accuracy. With further validation on larger patient populations, this tool may be used clinically to guide planners in choosing an appropriate treatment technique. The prediction algorithm could also be adapted to guide selection of treatment parameters such as treatment modality and number of fields for radiotherapy across anatomical sites.« less

Toward the characterization of biological toxins using field-based FT-IR spectroscopic instrumentation

NASA Astrophysics Data System (ADS)

Schiering, David W.; Walton, Robert B.; Brown, Christopher W.; Norman, Mark L.; Brewer, Joseph; Scott, James

2004-12-01

IR spectroscopy is a broadly applicable technique for the identification of covalent materials. Recent advances in instrumentation have made Fourier Transform infrared (FT-IR) spectroscopy available for field characterization of suspect materials. Presently, this instrumentation is broadly deployed and used for the identification of potential chemical hazards. This discussion concerns work towards expanding the analytical utility of field-based FT-IR spectrometry in the characterization of biological threats. Two classes of materials were studied: biologically produced chemical toxins which were non-peptide in nature and peptide toxin. The IR spectroscopic identification of aflatoxin-B1, trichothecene T2 mycotoxin, and strychnine was evaluated using the approach of spectral searching against large libraries of materials. For pure components, the IR method discriminated the above toxins at better than the 99% confidence level. The ability to identify non-peptide toxins in mixtures was also evaluated using a "spectral stripping" search approach. For the mixtures evaluated, this method was able to identify the mixture components from ca. 32K spectral library entries. Castor bean extract containing ricin was used as a representative peptide toxin. Due to similarity in protein spectra, a SIMCA pattern recognition methodology was evaluated for classifying peptide toxins. In addition to castor bean extract the method was validated using bovine serum albumin and myoglobin as simulants. The SIMCA approach was successful in correctly classifying these samples at the 95% confidence level.

Region grouping in natural foliage scenes: image statistics and human performance.

PubMed

Ing, Almon D; Wilson, J Anthony; Geisler, Wilson S

2010-04-27

This study investigated the mechanisms of grouping and segregation in natural scenes of close-up foliage, an important class of scenes for human and non-human primates. Close-up foliage images were collected with a digital camera calibrated to match the responses of human L, M, and S cones at each pixel. The images were used to construct a database of hand-segmented leaves and branches that correctly localizes the image region subtended by each object. We considered a task where a visual system is presented with two image patches and is asked to assign a category label (either same or different) depending on whether the patches appear to lie on the same surface or different surfaces. We estimated several approximately ideal classifiers for the task, each of which used a unique set of image properties. Of the image properties considered, we found that ideal classifiers rely primarily on the difference in average intensity and color between patches, and secondarily on the differences in the contrasts between patches. In psychophysical experiments, human performance mirrored the trends predicted by the ideal classifiers. In an initial phase without corrective feedback, human accuracy was slightly below ideal. After practice with feedback, human accuracy was approximately ideal.

Using CRANID to test the population affinity of known crania.

PubMed

Kallenberger, Lauren; Pilbrow, Varsha

2012-11-01

CRANID is a statistical program used to infer the source population of a cranium of unknown origin by comparing its cranial dimensions with a worldwide craniometric database. It has great potential for estimating ancestry in archaeological, forensic and repatriation cases. In this paper we test the validity of CRANID in classifying crania of known geographic origin. Twenty-three crania of known geographic origin but unknown sex were selected from the osteological collections of the University of Melbourne. Only 18 crania showed good statistical match with the CRANID database. Without considering accuracy of sex allocation, 11 crania were accurately classified into major geographic regions and nine were correctly classified to geographically closest available reference populations. Four of the five crania with poor statistical match were nonetheless correctly allocated to major geographical regions, although none was accurately assigned to geographically closest reference samples. We conclude that if sex allocations are overlooked, CRANID can accurately assign 39% of specimens to geographically closest matching reference samples and 48% to major geographic regions. Better source population representation may improve goodness of fit, but known sex-differentiated samples are needed to further test the utility of CRANID. © 2012 The Authors Journal of Anatomy © 2012 Anatomical Society.

NCLEX-RN performance: predicting success on the computerized examination.

PubMed

Beeman, P B; Waterhouse, J K

2001-01-01

Since the adoption of the Computerized Adaptive Testing (CAT) format of the National Certification Licensure Examination for Registered Nurses (NCLEX-RN), no studies have been reported in the literature on predictors of successful performance by baccalaureate nursing graduates on the licensure examination. In this study, a discriminant analysis was used to identify which of 21 variables can be significant predictors of success on the CAT NCLEX-RN. The convenience sample consisted of 289 individuals who graduated from a baccalaureate nursing program between 1995 and 1998. Seven significant predictor variables were identified. The total number of C+ or lower grades earned in nursing theory courses was the best predictor, followed by grades in several individual nursing courses. More than 93 per cent of graduates were correctly classified. Ninety-four per cent of NCLEX "passes" were correctly classified, as were 92 per cent of NCLEX failures. This degree of accuracy in classifying CAT NCLEX-RN failures represents a marked improvement over results reported in previous studies of licensure examinations, and suggests the discriminant function will be helpful in identifying future students in danger of failure. J Prof Nurs 17:158-165, 2001. Copyright 2001 by W.B. Saunders Company

Chess Revision: Acquiring the Rules of Chess Variants through FOL Theory Revision from Examples

NASA Astrophysics Data System (ADS)

Muggleton, Stephen; Paes, Aline; Santos Costa, Vítor; Zaverucha, Gerson

The game of chess has been a major testbed for research in artificial intelligence, since it requires focus on intelligent reasoning. Particularly, several challenges arise to machine learning systems when inducing a model describing legal moves of the chess, including the collection of the examples, the learning of a model correctly representing the official rules of the game, covering all the branches and restrictions of the correct moves, and the comprehensibility of such a model. Besides, the game of chess has inspired the creation of numerous variants, ranging from faster to more challenging or to regional versions of the game. The question arises if it is possible to take advantage of an initial classifier of chess as a starting point to obtain classifiers for the different variants. We approach this problem as an instance of theory revision from examples. The initial classifier of chess is inspired by a FOL theory approved by a chess expert and the examples are defined as sequences of moves within a game. Starting from a standard revision system, we argue that abduction and negation are also required to best address this problem. Experimental results show the effectiveness of our approach.

Sex estimation in a modern American osteological sample using a discriminant function analysis from the calcaneus.

PubMed

DiMichele, Daniel L; Spradley, M Katherine

2012-09-10

Reliable methods for sex estimation during the development of a biological profile are important to the forensic community in instances when the common skeletal elements used to assess sex are absent or damaged. Sex estimation from the calcaneus has potentially significant importance for the forensic community. Specifically, measurements of the calcaneus provide an additional reliable method for sex estimation via discriminant function analysis based on a North American forensic population. Research on a modern American sample was chosen in order to develop up-to-date population specific discriminant functions for sex estimation. The current study addresses this matter, building upon previous research and introduces a new measurement, posterior circumference that promises to advance the accuracy of use of this single, highly resistant bone in future instances of sex determination from partial skeletal remains. Data were collected from The William Bass Skeletal Collection, housed at The University of Tennessee. Sample size includes 320 adult individuals born between the years 1900 and 1985. The sample was comprised of 136 females and 184 males. Skeletons used for measurements were confined to those with fused diaphyses showing no signs of pathology or damage that may have altered measurements, and that also had accompanying records that included information on ancestry, age, and sex. Measurements collected and analyzed include maximum length, load-arm length, load-arm width, and posterior circumference. The sample was used to compute a discriminant function, based on all four variables, and was performed in SAS 9.1.3. The discriminant function obtained an overall cross-validated classification rate of 86.69%. Females were classified correctly in 88.64% of the cases and males were correctly classified in 84.75% of the cases. Due to the increasing heterogeneity of current populations further discussion on this topic will include the importance that the re-evaluation of past studies has on modern forensic populations. Due to secular and micro evolutionary changes among populations, the near future must include additional methods being updated, and new methods being examined, both which should cover a wide population spectrum. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

Persistence of the Intuitive Conception of Living Things in Adolescence

NASA Astrophysics Data System (ADS)

Babai, Reuven; Sekal, Rachel; Stavy, Ruth

2010-02-01

This study investigated whether intuitive, naive conceptions of "living things" based on objects' mobility (movement = alive) persist into adolescence and affect 10th graders' accuracy of responses and reaction times during object classification. Most of the 58 students classified the test objects correctly as living/nonliving, yet they demonstrated significantly longer reaction times for classifying plants compared to animals and for classifying dynamic objects compared to static inanimate objects. Findings indicated that, despite prior learning in biology, the intuitive conception of living things persists up to age 15-16 years, affecting related reasoning processes. Consideration of these findings may help educators in their decisions about the nature of examples they use in their classrooms.

Zero velocity interval detection based on a continuous hidden Markov model in micro inertial pedestrian navigation

NASA Astrophysics Data System (ADS)

Sun, Wei; Ding, Wei; Yan, Huifang; Duan, Shunli

2018-06-01

Shoe-mounted pedestrian navigation systems based on micro inertial sensors rely on zero velocity updates to correct their positioning errors in time, which effectively makes determining the zero velocity interval play a key role during normal walking. However, as walking gaits are complicated, and vary from person to person, it is difficult to detect walking gaits with a fixed threshold method. This paper proposes a pedestrian gait classification method based on a hidden Markov model. Pedestrian gait data are collected with a micro inertial measurement unit installed at the instep. On the basis of analyzing the characteristics of the pedestrian walk, a single direction angular rate gyro output is used to classify gait features. The angular rate data are modeled into a univariate Gaussian mixture model with three components, and a four-state left–right continuous hidden Markov model (CHMM) is designed to classify the normal walking gait. The model parameters are trained and optimized using the Baum–Welch algorithm and then the sliding window Viterbi algorithm is used to decode the gait. Walking data are collected through eight subjects walking along the same route at three different speeds; the leave-one-subject-out cross validation method is conducted to test the model. Experimental results show that the proposed algorithm can accurately detect different walking gaits of zero velocity interval. The location experiment shows that the precision of CHMM-based pedestrian navigation improved by 40% when compared to the angular rate threshold method.

Comparing ensemble learning methods based on decision tree classifiers for protein fold recognition.

PubMed

Bardsiri, Mahshid Khatibi; Eftekhari, Mahdi

2014-01-01

In this paper, some methods for ensemble learning of protein fold recognition based on a decision tree (DT) are compared and contrasted against each other over three datasets taken from the literature. According to previously reported studies, the features of the datasets are divided into some groups. Then, for each of these groups, three ensemble classifiers, namely, random forest, rotation forest and AdaBoost.M1 are employed. Also, some fusion methods are introduced for combining the ensemble classifiers obtained in the previous step. After this step, three classifiers are produced based on the combination of classifiers of types random forest, rotation forest and AdaBoost.M1. Finally, the three different classifiers achieved are combined to make an overall classifier. Experimental results show that the overall classifier obtained by the genetic algorithm (GA) weighting fusion method, is the best one in comparison to previously applied methods in terms of classification accuracy.

A new strategy for snow-cover mapping using remote sensing data and ensemble based systems techniques

NASA Astrophysics Data System (ADS)

Roberge, S.; Chokmani, K.; De Sève, D.

2012-04-01

The snow cover plays an important role in the hydrological cycle of Quebec (Eastern Canada). Consequently, evaluating its spatial extent interests the authorities responsible for the management of water resources, especially hydropower companies. The main objective of this study is the development of a snow-cover mapping strategy using remote sensing data and ensemble based systems techniques. Planned to be tested in a near real-time operational mode, this snow-cover mapping strategy has the advantage to provide the probability of a pixel to be snow covered and its uncertainty. Ensemble systems are made of two key components. First, a method is needed to build an ensemble of classifiers that is diverse as much as possible. Second, an approach is required to combine the outputs of individual classifiers that make up the ensemble in such a way that correct decisions are amplified, and incorrect ones are cancelled out. In this study, we demonstrate the potential of ensemble systems to snow-cover mapping using remote sensing data. The chosen classifier is a sequential thresholds algorithm using NOAA-AVHRR data adapted to conditions over Eastern Canada. Its special feature is the use of a combination of six sequential thresholds varying according to the day in the winter season. Two versions of the snow-cover mapping algorithm have been developed: one is specific for autumn (from October 1st to December 31st) and the other for spring (from March 16th to May 31st). In order to build the ensemble based system, different versions of the algorithm are created by varying randomly its parameters. One hundred of the versions are included in the ensemble. The probability of a pixel to be snow, no-snow or cloud covered corresponds to the amount of votes the pixel has been classified as such by all classifiers. The overall performance of ensemble based mapping is compared to the overall performance of the chosen classifier, and also with ground observations at meteorological stations.

Empirical evaluation of data normalization methods for molecular classification

PubMed Central

Huang, Huei-Chung

2018-01-01

Background Data artifacts due to variations in experimental handling are ubiquitous in microarray studies, and they can lead to biased and irreproducible findings. A popular approach to correct for such artifacts is through post hoc data adjustment such as data normalization. Statistical methods for data normalization have been developed and evaluated primarily for the discovery of individual molecular biomarkers. Their performance has rarely been studied for the development of multi-marker molecular classifiers—an increasingly important application of microarrays in the era of personalized medicine. Methods In this study, we set out to evaluate the performance of three commonly used methods for data normalization in the context of molecular classification, using extensive simulations based on re-sampling from a unique pair of microRNA microarray datasets for the same set of samples. The data and code for our simulations are freely available as R packages at GitHub. Results In the presence of confounding handling effects, all three normalization methods tended to improve the accuracy of the classifier when evaluated in an independent test data. The level of improvement and the relative performance among the normalization methods depended on the relative level of molecular signal, the distributional pattern of handling effects (e.g., location shift vs scale change), and the statistical method used for building the classifier. In addition, cross-validation was associated with biased estimation of classification accuracy in the over-optimistic direction for all three normalization methods. Conclusion Normalization may improve the accuracy of molecular classification for data with confounding handling effects; however, it cannot circumvent the over-optimistic findings associated with cross-validation for assessing classification accuracy. PMID:29666754

77 FR 39899 - Technical Corrections

Federal Register 2010, 2011, 2012, 2013, 2014

2012-07-06

..., Nuclear material, Oil and gas exploration--well logging, Reporting and recordkeeping requirements... recordkeeping requirements, Source material, Uranium. 10 CFR Part 50 Antitrust, Classified information, Criminal... measures, Special nuclear material, Uranium enrichment by gaseous diffusion. 10 CFR Part 81 Administrative...

MOLECULAR MODELING FOR PRIORITIZATION OF TOXICITY BIOASSAYS

EPA Science Inventory

The results of this study demonstrate the importance of receptor flexibility. However, when different receptors in the endocrine system are considered simultaneously most molecules, even weak environmental agents, are classified correctly. The ultimate goal of this research is ...

Resistance of Loblolly Pine Sources to Fusiform Rust in Field Progeny Tests

Treesearch

H.R. Powers; E.G. Kuhlman

1987-01-01

Results of concentrated basidiospore spray (CBS) inoculations correlated well with field infection. Generally, the CBS system correctly classified resistant and susceptible sources, but it classed seven sources with field resistance as susceptible.

Utilizing LANDSAT imagery to monitor land-use change - A case study in Ohio

NASA Technical Reports Server (NTRS)

Gordon, S. I.

1980-01-01

A study, performed in Ohio, of the nature and extent of interpretation errors in the application of Landsat imagery to land-use planning and modeling is reported. Potential errors associated with the misalignment of pixels after geometric correction and with misclassification of land cover or land use due to spectral similarities were identified on interpreted computer-compatible tapes of a portion of Franklin County for two adjacent days of 1975 and one day of 1973, and the extents of these errors were quantified by comparison with a ground-checked set of aerial-photograph interpretations. The open-space and agricultural categories are found to be the most consistently classified, while the more urban areas were classified correctly only from about 43 to 8% of the time. It is thus recommended that the direct application of Landsat data to land-use planning must await improvements in classification techniques and accuracy.

Thermal imaging as a lie detection tool at airports.

PubMed

Warmelink, Lara; Vrij, Aldert; Mann, Samantha; Leal, Sharon; Forrester, Dave; Fisher, Ronald P

2011-02-01

We tested the accuracy of thermal imaging as a lie detection tool in airport screening. Fifty-one passengers in an international airport departure hall told the truth or lied about their forthcoming trip in an interview. Their skin temperature was recorded via a thermal imaging camera. Liars' skin temperature rose significantly during the interview, whereas truth tellers' skin temperature remained constant. On the basis of these different patterns, 64% of truth tellers and 69% of liars were classified correctly. The interviewers made veracity judgements independently from the thermal recordings. The interviewers outperformed the thermal recordings and classified 72% of truth tellers and 77% of liars correctly. Accuracy rates based on the combination of thermal imaging scores and interviewers' judgements were the same as accuracy rates based on interviewers' judgements alone. Implications of the findings for the suitability of thermal imaging as a lie detection tool in airports are discussed.

Evaluation of normalized metal artifact reduction (NMAR) in kVCT using MVCT prior images for radiotherapy treatment planning

DOE Office of Scientific and Technical Information (OSTI.GOV)

Paudel, M. R.; Mackenzie, M.; Rathee, S.

2013-08-15

Purpose: To evaluate the metal artifacts in kilovoltage computed tomography (kVCT) images that are corrected using a normalized metal artifact reduction (NMAR) method with megavoltage CT (MVCT) prior images.Methods: Tissue characterization phantoms containing bilateral steel inserts are used in all experiments. Two MVCT images, one without any metal artifact corrections and the other corrected using a modified iterative maximum likelihood polychromatic algorithm for CT (IMPACT) are translated to pseudo-kVCT images. These are then used as prior images without tissue classification in an NMAR technique for correcting the experimental kVCT image. The IMPACT method in MVCT included an additional model formore » the pair/triplet production process and the energy dependent response of the MVCT detectors. An experimental kVCT image, without the metal inserts and reconstructed using the filtered back projection (FBP) method, is artificially patched with the known steel inserts to get a reference image. The regular NMAR image containing the steel inserts that uses tissue classified kVCT prior and the NMAR images reconstructed using MVCT priors are compared with the reference image for metal artifact reduction. The Eclipse treatment planning system is used to calculate radiotherapy dose distributions on the corrected images and on the reference image using the Anisotropic Analytical Algorithm with 6 MV parallel opposed 5 × 10 cm{sup 2} fields passing through the bilateral steel inserts, and the results are compared. Gafchromic film is used to measure the actual dose delivered in a plane perpendicular to the beams at the isocenter.Results: The streaking and shading in the NMAR image using tissue classifications are significantly reduced. However, the structures, including metal, are deformed. Some uniform regions appear to have eroded from one side. There is a large variation of attenuation values inside the metal inserts. Similar results are seen in commercially corrected image. Use of MVCT prior images without tissue classification in NMAR significantly reduces these problems. The radiation dose calculated on the reference image is close to the dose measured using the film. Compared to the reference image, the calculated dose difference in the conventional NMAR image, the corrected images using uncorrected MVCT image, and IMPACT corrected MVCT image as priors is ∼15.5%, ∼5%, and ∼2.7%, respectively, at the isocenter.Conclusions: The deformation and erosion of the structures present in regular NMAR corrected images can be largely reduced by using MVCT priors without tissue segmentation. The attenuation value of metal being incorrect, large dose differences relative to the true value can result when using the conventional NMAR image. This difference can be significantly reduced if MVCT images are used as priors. Reduced tissue deformation, better tissue visualization, and correct information about the electron density of the tissues and metals in the artifact corrected images could help delineate the structures better, as well as calculate radiation dose more correctly, thus enhancing the quality of the radiotherapy treatment planning.« less

Combination of laser-induced breakdown spectroscopy and Raman spectroscopy for multivariate classification of bacteria

NASA Astrophysics Data System (ADS)

Prochazka, D.; Mazura, M.; Samek, O.; Rebrošová, K.; Pořízka, P.; Klus, J.; Prochazková, P.; Novotný, J.; Novotný, K.; Kaiser, J.

2018-01-01

In this work, we investigate the impact of data provided by complementary laser-based spectroscopic methods on multivariate classification accuracy. Discrimination and classification of five Staphylococcus bacterial strains and one strain of Escherichia coli is presented. The technique that we used for measurements is a combination of Raman spectroscopy and Laser-Induced Breakdown Spectroscopy (LIBS). Obtained spectroscopic data were then processed using Multivariate Data Analysis algorithms. Principal Components Analysis (PCA) was selected as the most suitable technique for visualization of bacterial strains data. To classify the bacterial strains, we used Neural Networks, namely a supervised version of Kohonen's self-organizing maps (SOM). We were processing results in three different ways - separately from LIBS measurements, from Raman measurements, and we also merged data from both mentioned methods. The three types of results were then compared. By applying the PCA to Raman spectroscopy data, we observed that two bacterial strains were fully distinguished from the rest of the data set. In the case of LIBS data, three bacterial strains were fully discriminated. Using a combination of data from both methods, we achieved the complete discrimination of all bacterial strains. All the data were classified with a high success rate using SOM algorithm. The most accurate classification was obtained using a combination of data from both techniques. The classification accuracy varied, depending on specific samples and techniques. As for LIBS, the classification accuracy ranged from 45% to 100%, as for Raman Spectroscopy from 50% to 100% and in case of merged data, all samples were classified correctly. Based on the results of the experiments presented in this work, we can assume that the combination of Raman spectroscopy and LIBS significantly enhances discrimination and classification accuracy of bacterial species and strains. The reason is the complementarity in obtained chemical information while using these two methods.

Artificial Neural Networks as a powerful numerical tool to classify specific features of a tooth based on 3D scan data.

PubMed

Raith, Stefan; Vogel, Eric Per; Anees, Naeema; Keul, Christine; Güth, Jan-Frederik; Edelhoff, Daniel; Fischer, Horst

2017-01-01

Chairside manufacturing based on digital image acquisition is gainingincreasing importance in dentistry. For the standardized application of these methods, it is paramount to have highly automated digital workflows that can process acquired 3D image data of dental surfaces. Artificial Neural Networks (ANNs) arenumerical methods primarily used to mimic the complex networks of neural connections in the natural brain. Our hypothesis is that an ANNcan be developed that is capable of classifying dental cusps with sufficient accuracy. This bears enormous potential for an application in chairside manufacturing workflows in the dental field, as it closes the gap between digital acquisition of dental geometries and modern computer-aided manufacturing techniques.Three-dimensional surface scans of dental casts representing natural full dental arches were transformed to range image data. These data were processed using an automated algorithm to detect candidates for tooth cusps according to salient geometrical features. These candidates were classified following common dental terminology and used as training data for a tailored ANN.For the actual cusp feature description, two different approaches were developed and applied to the available data: The first uses the relative location of the detected cusps as input data and the second method directly takes the image information given in the range images. In addition, a combination of both was implemented and investigated.Both approaches showed high performance with correct classifications of 93.3% and 93.5%, respectively, with improvements by the combination shown to be minor.This article presents for the first time a fully automated method for the classification of teeththat could be confirmed to work with sufficient precision to exhibit the potential for its use in clinical practice,which is a prerequisite for automated computer-aided planning of prosthetic treatments with subsequent automated chairside manufacturing. Copyright © 2016 Elsevier Ltd. All rights reserved.

Landslide Susceptibility Evaluation on agricultural terraces of DOURO VALLEY (PORTUGAL), using physically based mathematical models.

NASA Astrophysics Data System (ADS)

Faria, Ana; Bateira, Carlos; Laura, Soares; Fernandes, Joana; Gonçalves, José; Marques, Fernando

2016-04-01

The work focuses the evaluation of landslide susceptibility in Douro Region agricultural terraces, supported by dry stone walls and earth embankments, using two physically based models. The applied models, SHALSTAB (Montgomery et al.,1994; Dietrich et al., 1995) and SINMAP (PACK et al., 2005), combine an infinite slope stability model with a steady state hydrological model, and both use the following geophysical parameters: cohesion, friction angle, specific weight and soil thickness. The definition of the contributing areas is different in both models. The D∞ methodology used by SINMAP model suggests a great influence of the terraces morphology, providing a much more diffuse flow on the internal flow modelling. The MD8 used in SHALSTAB promotes an important degree of flow concentration, representing an internal flow based on preferential paths of the runoff as the areas more susceptible to saturation processes. The model validation is made through the contingency matrix method (Fawcett, 2006; Raia et al., 2014) and implies the confrontation with the inventory of past landslides. The True Positive Rate shows that SHALSTAB classifies 77% of the landslides on the high susceptibility areas, while SINMAP reaches 90%. The SINMAP has a False Positive Rate (represents the percentage of the slipped area that is classified as unstable but without landslides) of 83% and the SHALSTAB has 67%. The reliability (analyzes the areas that were correctly classified on the total area) of SHALSTAB is better (33% against 18% of SINMAP). Relative to Precision (refers to the ratio of the slipped area correctly classified over the whole area classified as unstable) SHALSTAB has better results (0.00298 against 0.00283 of SINMAP). It was elaborate the index TPR/FPR and better results obtained by SHALSTAB (1.14 against 1.09 of SINMAP). SHALSTAB shows a better performance in the definition of susceptibility most prone areas to instability processes. One of the reasons for the difference of predictive capacity of the models is related with the construction methods of contributory areas. The SHALSTAB susceptibility map shows better discrimination of the unstable areas, which is important to the estates decision makers in order to organize the priority of the hazard mitigation process. References Dietrich, W. E.; Reiss, R.; Hsu, M-L.; Montgomery, D.(1995) - A process-based model for colluvial soil depth and shallow landsliding using digital elevation data. Hydrological Processes. ISSN 1099-1085. Vol. 9, n.° 3-4, pp.383-400. Fawcett, T.(2006) - An introduction to ROC analysis. Pattern Recognition Letters. ISSN 0167-8655. Vol. 27, n.° 8, pp.861-874. Montgomery, David R.; Dietrich, William E.- A physically based model for the topographic control on shallow landsliding. Water Resources Research. ISSN 1944-7973. Vol. 30, n.° 4 (1994), p.1153-1171. Raia, S., [et al.]- Improving predictive power of physically based rainfall-induced shallow landslide models: a probabilistic approach. Geoscientific Model Development. ISSN 1991-959X. Vol. 7, n.° 2 (2014), p.495-514.

Convolutional neural networks for vibrational spectroscopic data analysis.

PubMed

Acquarelli, Jacopo; van Laarhoven, Twan; Gerretzen, Jan; Tran, Thanh N; Buydens, Lutgarde M C; Marchiori, Elena

2017-02-15

In this work we show that convolutional neural networks (CNNs) can be efficiently used to classify vibrational spectroscopic data and identify important spectral regions. CNNs are the current state-of-the-art in image classification and speech recognition and can learn interpretable representations of the data. These characteristics make CNNs a good candidate for reducing the need for preprocessing and for highlighting important spectral regions, both of which are crucial steps in the analysis of vibrational spectroscopic data. Chemometric analysis of vibrational spectroscopic data often relies on preprocessing methods involving baseline correction, scatter correction and noise removal, which are applied to the spectra prior to model building. Preprocessing is a critical step because even in simple problems using 'reasonable' preprocessing methods may decrease the performance of the final model. We develop a new CNN based method and provide an accompanying publicly available software. It is based on a simple CNN architecture with a single convolutional layer (a so-called shallow CNN). Our method outperforms standard classification algorithms used in chemometrics (e.g. PLS) in terms of accuracy when applied to non-preprocessed test data (86% average accuracy compared to the 62% achieved by PLS), and it achieves better performance even on preprocessed test data (96% average accuracy compared to the 89% achieved by PLS). For interpretability purposes, our method includes a procedure for finding important spectral regions, thereby facilitating qualitative interpretation of results. Copyright © 2016 Elsevier B.V. All rights reserved.

Robust through-the-wall radar image classification using a target-model alignment procedure.

PubMed

Smith, Graeme E; Mobasseri, Bijan G

2012-02-01

A through-the-wall radar image (TWRI) bears little resemblance to the equivalent optical image, making it difficult to interpret. To maximize the intelligence that may be obtained, it is desirable to automate the classification of targets in the image to support human operators. This paper presents a technique for classifying stationary targets based on the high-range resolution profile (HRRP) extracted from 3-D TWRIs. The dependence of the image on the target location is discussed using a system point spread function (PSF) approach. It is shown that the position dependence will cause a classifier to fail, unless the image to be classified is aligned to a classifier-training location. A target image alignment technique based on deconvolution of the image with the system PSF is proposed. Comparison of the aligned target images with measured images shows the alignment process introducing normalized mean squared error (NMSE) ≤ 9%. The HRRP extracted from aligned target images are classified using a naive Bayesian classifier supported by principal component analysis. The classifier is tested using a real TWRI of canonical targets behind a concrete wall and shown to obtain correct classification rates ≥ 97%. © 2011 IEEE

Toward Automated Cochlear Implant Fitting Procedures Based on Event-Related Potentials.

PubMed

Finke, Mareike; Billinger, Martin; Büchner, Andreas

Cochlear implants (CIs) restore hearing to the profoundly deaf by direct electrical stimulation of the auditory nerve. To provide an optimal electrical stimulation pattern the CI must be individually fitted to each CI user. To date, CI fitting is primarily based on subjective feedback from the user. However, not all CI users are able to provide such feedback, for example, small children. This study explores the possibility of using the electroencephalogram (EEG) to objectively determine if CI users are able to hear differences in tones presented to them, which has potential applications in CI fitting or closed loop systems. Deviant and standard stimuli were presented to 12 CI users in an active auditory oddball paradigm. The EEG was recorded in two sessions and classification of the EEG data was performed with shrinkage linear discriminant analysis. Also, the impact of CI artifact removal on classification performance and the possibility to reuse a trained classifier in future sessions were evaluated. Overall, classification performance was above chance level for all participants although performance varied considerably between participants. Also, artifacts were successfully removed from the EEG without impairing classification performance. Finally, reuse of the classifier causes only a small loss in classification performance. Our data provide first evidence that EEG can be automatically classified on single-trial basis in CI users. Despite the slightly poorer classification performance over sessions, classifier and CI artifact correction appear stable over successive sessions. Thus, classifier and artifact correction weights can be reused without repeating the set-up procedure in every session, which makes the technique easier applicable. With our present data, we can show successful classification of event-related cortical potential patterns in CI users. In the future, this has the potential to objectify and automate parts of CI fitting procedures.

A qualitative signature for early diagnosis of hepatocellular carcinoma based on relative expression orderings.

PubMed

Ao, Lu; Zhang, Zimei; Guan, Qingzhou; Guo, Yating; Guo, You; Zhang, Jiahui; Lv, Xingwei; Huang, Haiyan; Zhang, Huarong; Wang, Xianlong; Guo, Zheng

2018-04-23

Currently, using biopsy specimens to confirm suspicious liver lesions of early hepatocellular carcinoma are not entirely reliable because of insufficient sampling amount and inaccurate sampling location. It is necessary to develop a signature to aid early hepatocellular carcinoma diagnosis using biopsy specimens even when the sampling location is inaccurate. Based on the within-sample relative expression orderings of gene pairs, we identified a simple qualitative signature to distinguish both hepatocellular carcinoma and adjacent non-tumour tissues from cirrhosis tissues of non-hepatocellular carcinoma patients. A signature consisting of 19 gene pairs was identified in the training data sets and validated in 2 large collections of samples from biopsy and surgical resection specimens. For biopsy specimens, 95.7% of 141 hepatocellular carcinoma tissues and all (100%) of 108 cirrhosis tissues of non-hepatocellular carcinoma patients were correctly classified. Especially, all (100%) of 60 hepatocellular carcinoma adjacent normal tissues and 77.5% of 80 hepatocellular carcinoma adjacent cirrhosis tissues were classified to hepatocellular carcinoma. For surgical resection specimens, 99.7% of 733 hepatocellular carcinoma specimens were correctly classified to hepatocellular carcinoma, while 96.1% of 254 hepatocellular carcinoma adjacent cirrhosis tissues and 95.9% of 538 hepatocellular carcinoma adjacent normal tissues were classified to hepatocellular carcinoma. In contrast, 17.0% of 47 cirrhosis from non-hepatocellular carcinoma patients waiting for liver transplantation were classified to hepatocellular carcinoma, indicating that some patients with long-lasting cirrhosis could have already gained hepatocellular carcinoma characteristics. The signature can distinguish both hepatocellular carcinoma tissues and tumour-adjacent tissues from cirrhosis tissues of non-hepatocellular carcinoma patients even using inaccurately sampled biopsy specimens, which can aid early diagnosis of hepatocellular carcinoma. © 2018 The Authors. Liver International Published by John Wiley & Sons Ltd.

The discrimination between star-forming and AGN galaxies in the absence of Hαand [NII]: A machine learning approach

NASA Astrophysics Data System (ADS)

Teimoorinia, H.; Keown, J.

2018-05-01

In the absence of the two emission lines Hαand [NII] (6584Å) in a BPT diagram, we show that other spectral information is sufficiently informative to distinguish AGN galaxies from star-forming galaxies. We use pattern recognition methods and a sample of galaxy spectra from the Sloan Digital Sky Survey (SDSS) to show that, in this survey, the flux and equivalent width of [OIII] (5007Å) and Hβ, along with the 4000Å break, can be used to classify galaxies in a BPT diagram. This method provides a higher accuracy of predictions than those which use stellar mass and [OIII]/Hβ. First, we use BPT diagrams and various physical parameters to re-classify the galaxies. Next, using confusion matrices, we determine the `correctly' predicted classes as well as confused cases. In this way, we investigate the effect of each parameter in the confusion matrices and rank the physical parameters used in the discrimination of the different classes. We show that in this survey, for example, {g - r} colour can provide the same accuracy as galaxy stellar mass to predict whether or not a galaxy hosts an AGN. Finally, with the same information, we also rank the parameters involved in the discrimination of Seyfert and LINER galaxies.

Semantic Shot Classification in Sports Video

NASA Astrophysics Data System (ADS)

Duan, Ling-Yu; Xu, Min; Tian, Qi

2003-01-01

In this paper, we present a unified framework for semantic shot classification in sports videos. Unlike previous approaches, which focus on clustering by aggregating shots with similar low-level features, the proposed scheme makes use of domain knowledge of a specific sport to perform a top-down video shot classification, including identification of video shot classes for each sport, and supervised learning and classification of the given sports video with low-level and middle-level features extracted from the sports video. It is observed that for each sport we can predefine a small number of semantic shot classes, about 5~10, which covers 90~95% of sports broadcasting video. With the supervised learning method, we can map the low-level features to middle-level semantic video shot attributes such as dominant object motion (a player), camera motion patterns, and court shape, etc. On the basis of the appropriate fusion of those middle-level shot classes, we classify video shots into the predefined video shot classes, each of which has a clear semantic meaning. The proposed method has been tested over 4 types of sports videos: tennis, basketball, volleyball and soccer. Good classification accuracy of 85~95% has been achieved. With correctly classified sports video shots, further structural and temporal analysis, such as event detection, video skimming, table of content, etc, will be greatly facilitated.

Probing many-body localization with neural networks

NASA Astrophysics Data System (ADS)

Schindler, Frank; Regnault, Nicolas; Neupert, Titus

2017-06-01

We show that a simple artificial neural network trained on entanglement spectra of individual states of a many-body quantum system can be used to determine the transition between a many-body localized and a thermalizing regime. Specifically, we study the Heisenberg spin-1/2 chain in a random external field. We employ a multilayer perceptron with a single hidden layer, which is trained on labeled entanglement spectra pertaining to the fully localized and fully thermal regimes. We then apply this network to classify spectra belonging to states in the transition region. For training, we use a cost function that contains, in addition to the usual error and regularization parts, a term that favors a confident classification of the transition region states. The resulting phase diagram is in good agreement with the one obtained by more conventional methods and can be computed for small systems. In particular, the neural network outperforms conventional methods in classifying individual eigenstates pertaining to a single disorder realization. It allows us to map out the structure of these eigenstates across the transition with spatial resolution. Furthermore, we analyze the network operation using the dreaming technique to show that the neural network correctly learns by itself the power-law structure of the entanglement spectra in the many-body localized regime.

Algorithms and Results of Eye Tissues Differentiation Based on RF Ultrasound

PubMed Central

Jurkonis, R.; Janušauskas, A.; Marozas, V.; Jegelevičius, D.; Daukantas, S.; Patašius, M.; Paunksnis, A.; Lukoševičius, A.

2012-01-01

Algorithms and software were developed for analysis of B-scan ultrasonic signals acquired from commercial diagnostic ultrasound system. The algorithms process raw ultrasonic signals in backscattered spectrum domain, which is obtained using two time-frequency methods: short-time Fourier and Hilbert-Huang transformations. The signals from selected regions of eye tissues are characterized by parameters: B-scan envelope amplitude, approximated spectral slope, approximated spectral intercept, mean instantaneous frequency, mean instantaneous bandwidth, and parameters of Nakagami distribution characterizing Hilbert-Huang transformation output. The backscattered ultrasound signal parameters characterizing intraocular and orbit tissues were processed by decision tree data mining algorithm. The pilot trial proved that applied methods are able to correctly classify signals from corpus vitreum blood, extraocular muscle, and orbit tissues. In 26 cases of ocular tissues classification, one error occurred, when tissues were classified into classes of corpus vitreum blood, extraocular muscle, and orbit tissue. In this pilot classification parameters of spectral intercept and Nakagami parameter for instantaneous frequencies distribution of the 1st intrinsic mode function were found specific for corpus vitreum blood, orbit and extraocular muscle tissues. We conclude that ultrasound data should be further collected in clinical database to establish background for decision support system for ocular tissue noninvasive differentiation. PMID:22654643

A path towards uncertainty assignment in an operational cloud-phase algorithm from ARM vertically pointing active sensors

DOE PAGES

Riihimaki, Laura D.; Comstock, Jennifer M.; Anderson, Kevin K.; ...

2016-06-10

Knowledge of cloud phase (liquid, ice, mixed, etc.) is necessary to describe the radiative impact of clouds and their lifetimes, but is a property that is difficult to simulate correctly in climate models. One step towards improving those simulations is to make observations of cloud phase with sufficient accuracy to help constrain model representations of cloud processes. In this study, we outline a methodology using a basic Bayesian classifier to estimate the probabilities of cloud-phase class from Atmospheric Radiation Measurement (ARM) vertically pointing active remote sensors. The advantage of this method over previous ones is that it provides uncertainty informationmore » on the phase classification. We also test the value of including higher moments of the cloud radar Doppler spectrum than are traditionally used operationally. Using training data of known phase from the Mixed-Phase Arctic Cloud Experiment (M-PACE) field campaign, we demonstrate a proof of concept for how the method can be used to train an algorithm that identifies ice, liquid, mixed phase, and snow. Over 95 % of data are identified correctly for pure ice and liquid cases used in this study. Mixed-phase and snow cases are more problematic to identify correctly. When lidar data are not available, including additional information from the Doppler spectrum provides substantial improvement to the algorithm. As a result, this is a first step towards an operational algorithm and can be expanded to include additional categories such as drizzle with additional training data.« less

A path towards uncertainty assignment in an operational cloud-phase algorithm from ARM vertically pointing active sensors

NASA Astrophysics Data System (ADS)

Riihimaki, Laura D.; Comstock, Jennifer M.; Anderson, Kevin K.; Holmes, Aimee; Luke, Edward

2016-06-01

Knowledge of cloud phase (liquid, ice, mixed, etc.) is necessary to describe the radiative impact of clouds and their lifetimes, but is a property that is difficult to simulate correctly in climate models. One step towards improving those simulations is to make observations of cloud phase with sufficient accuracy to help constrain model representations of cloud processes. In this study, we outline a methodology using a basic Bayesian classifier to estimate the probabilities of cloud-phase class from Atmospheric Radiation Measurement (ARM) vertically pointing active remote sensors. The advantage of this method over previous ones is that it provides uncertainty information on the phase classification. We also test the value of including higher moments of the cloud radar Doppler spectrum than are traditionally used operationally. Using training data of known phase from the Mixed-Phase Arctic Cloud Experiment (M-PACE) field campaign, we demonstrate a proof of concept for how the method can be used to train an algorithm that identifies ice, liquid, mixed phase, and snow. Over 95 % of data are identified correctly for pure ice and liquid cases used in this study. Mixed-phase and snow cases are more problematic to identify correctly. When lidar data are not available, including additional information from the Doppler spectrum provides substantial improvement to the algorithm. This is a first step towards an operational algorithm and can be expanded to include additional categories such as drizzle with additional training data.

Evaluation of machine learning algorithms for classification of primary biological aerosol using a new UV-LIF spectrometer

NASA Astrophysics Data System (ADS)

Ruske, Simon; Topping, David O.; Foot, Virginia E.; Kaye, Paul H.; Stanley, Warren R.; Crawford, Ian; Morse, Andrew P.; Gallagher, Martin W.

2017-03-01

Characterisation of bioaerosols has important implications within environment and public health sectors. Recent developments in ultraviolet light-induced fluorescence (UV-LIF) detectors such as the Wideband Integrated Bioaerosol Spectrometer (WIBS) and the newly introduced Multiparameter Bioaerosol Spectrometer (MBS) have allowed for the real-time collection of fluorescence, size and morphology measurements for the purpose of discriminating between bacteria, fungal spores and pollen.This new generation of instruments has enabled ever larger data sets to be compiled with the aim of studying more complex environments. In real world data sets, particularly those from an urban environment, the population may be dominated by non-biological fluorescent interferents, bringing into question the accuracy of measurements of quantities such as concentrations. It is therefore imperative that we validate the performance of different algorithms which can be used for the task of classification.For unsupervised learning we tested hierarchical agglomerative clustering with various different linkages. For supervised learning, 11 methods were tested, including decision trees, ensemble methods (random forests, gradient boosting and AdaBoost), two implementations for support vector machines (libsvm and liblinear) and Gaussian methods (Gaussian naïve Bayesian, quadratic and linear discriminant analysis, the k-nearest neighbours algorithm and artificial neural networks).The methods were applied to two different data sets produced using the new MBS, which provides multichannel UV-LIF fluorescence signatures for single airborne biological particles. The first data set contained mixed PSLs and the second contained a variety of laboratory-generated aerosol.Clustering in general performs slightly worse than the supervised learning methods, correctly classifying, at best, only 67. 6 and 91. 1 % for the two data sets respectively. For supervised learning the gradient boosting algorithm was found to be the most effective, on average correctly classifying 82. 8 and 98. 27 % of the testing data, respectively, across the two data sets.A possible alternative to gradient boosting is neural networks. We do however note that this method requires much more user input than the other methods, and we suggest that further research should be conducted using this method, especially using parallelised hardware such as the GPU, which would allow for larger networks to be trained, which could possibly yield better results.We also saw that some methods, such as clustering, failed to utilise the additional shape information provided by the instrument, whilst for others, such as the decision trees, ensemble methods and neural networks, improved performance could be attained with the inclusion of such information.

Evaluation of normalized metal artifact reduction (NMAR) in kVCT using MVCT prior images for radiotherapy treatment planning.

PubMed

Paudel, M R; Mackenzie, M; Fallone, B G; Rathee, S

2013-08-01

To evaluate the metal artifacts in kilovoltage computed tomography (kVCT) images that are corrected using a normalized metal artifact reduction (NMAR) method with megavoltage CT (MVCT) prior images. Tissue characterization phantoms containing bilateral steel inserts are used in all experiments. Two MVCT images, one without any metal artifact corrections and the other corrected using a modified iterative maximum likelihood polychromatic algorithm for CT (IMPACT) are translated to pseudo-kVCT images. These are then used as prior images without tissue classification in an NMAR technique for correcting the experimental kVCT image. The IMPACT method in MVCT included an additional model for the pair∕triplet production process and the energy dependent response of the MVCT detectors. An experimental kVCT image, without the metal inserts and reconstructed using the filtered back projection (FBP) method, is artificially patched with the known steel inserts to get a reference image. The regular NMAR image containing the steel inserts that uses tissue classified kVCT prior and the NMAR images reconstructed using MVCT priors are compared with the reference image for metal artifact reduction. The Eclipse treatment planning system is used to calculate radiotherapy dose distributions on the corrected images and on the reference image using the Anisotropic Analytical Algorithm with 6 MV parallel opposed 5×10 cm2 fields passing through the bilateral steel inserts, and the results are compared. Gafchromic film is used to measure the actual dose delivered in a plane perpendicular to the beams at the isocenter. The streaking and shading in the NMAR image using tissue classifications are significantly reduced. However, the structures, including metal, are deformed. Some uniform regions appear to have eroded from one side. There is a large variation of attenuation values inside the metal inserts. Similar results are seen in commercially corrected image. Use of MVCT prior images without tissue classification in NMAR significantly reduces these problems. The radiation dose calculated on the reference image is close to the dose measured using the film. Compared to the reference image, the calculated dose difference in the conventional NMAR image, the corrected images using uncorrected MVCT image, and IMPACT corrected MVCT image as priors is ∼15.5%, ∼5%, and ∼2.7%, respectively, at the isocenter. The deformation and erosion of the structures present in regular NMAR corrected images can be largely reduced by using MVCT priors without tissue segmentation. The attenuation value of metal being incorrect, large dose differences relative to the true value can result when using the conventional NMAR image. This difference can be significantly reduced if MVCT images are used as priors. Reduced tissue deformation, better tissue visualization, and correct information about the electron density of the tissues and metals in the artifact corrected images could help delineate the structures better, as well as calculate radiation dose more correctly, thus enhancing the quality of the radiotherapy treatment planning.

Neurofilament light chain in cerebrospinal fluid and prediction of disease activity in clinically isolated syndrome and relapsing-remitting multiple sclerosis.

PubMed

Håkansson, I; Tisell, A; Cassel, P; Blennow, K; Zetterberg, H; Lundberg, P; Dahle, C; Vrethem, M; Ernerudh, J

2017-05-01

Improved biomarkers are needed to facilitate clinical decision-making and as surrogate endpoints in clinical trials in multiple sclerosis (MS). We assessed whether neurodegenerative and neuroinflammatory markers in cerebrospinal fluid (CSF) at initial sampling could predict disease activity during 2 years of follow-up in patients with clinically isolated syndrome (CIS) and relapsing-remitting MS. Using multiplex bead array and enzyme-linked immunosorbent assay, CXCL1, CXCL8, CXCL10, CXCL13, CCL20, CCL22, neurofilament light chain (NFL), neurofilament heavy chain, glial fibrillary acidic protein, chitinase-3-like-1, matrix metalloproteinase-9 and osteopontin were analysed in CSF from 41 patients with CIS or relapsing-remitting MS and 22 healthy controls. Disease activity (relapses, magnetic resonance imaging activity or disability worsening) in patients was recorded during 2 years of follow-up in this prospective longitudinal cohort study. In a logistic regression analysis model, NFL in CSF at baseline emerged as the best predictive marker, correctly classifying 93% of patients who showed evidence of disease activity during 2 years of follow-up and 67% of patients who did not, with an overall proportion of 85% (33 of 39 patients) correctly classified. Combining NFL with either neurofilament heavy chain or osteopontin resulted in 87% overall correctly classified patients, whereas combining NFL with a chemokine did not improve results. This study demonstrates the potential prognostic value of NFL in baseline CSF in CIS and relapsing-remitting MS and supports its use as a predictive biomarker of disease activity. © 2017 EAN.

Chinese mothers' perceptions of their child's weight and obesity status.

PubMed

Chen, Shu; Binns, Colin W; Maycock, Bruce; Zhao, Yun; Liu, Yi

2014-01-01

This study recorded maternal perceptions of preschool children's weight in Chinese mothers living in Australia and China. A survey was undertaken of 1951 mothers living in Chengdu and Wuhan, China and 89 Chinese mothers living in Perth, Australia. All participants were mothers with children aged 2-4 years. The children's weight and height were measured and their weight status were classified using the International Obesity Task Force 2012 revised international child body mass index cut-offs. The prevalence of overweight or obese in children was 16.7% in China and 8% in Australia. The overall percentages of correct maternal perception of the child's weight were 35% in underweight children, 69.2% in normal weight children but only 10.8% in overweight/ obese children. Among the overweight/obese children, only 14% in Australia and 10.8% in China were classified as overweight/obese by their mothers. Within the group of underweight children, normal weight mothers (p=0.004) and mothers with older age children (p=0.015) were more likely to correctly classify children's weight status. A higher percentage of overweight/obese mothers (p=0.002) and mothers who over-estimated her own weight status (p<0.001) have correct perception of the weight status of their overweight/obese children, compared to their counterparts. There was a high prevalence of incorrect maternal perception of preschool children's weight status in Chinese mothers, especially those with overweight/obese children. To address the obesity epidemic in children, future health promotion programs should put improved efforts to educate parents about obesity and its health consequences in order to reduce misperceptions.

Classification of brain tumours using short echo time 1H MR spectra

NASA Astrophysics Data System (ADS)

Devos, A.; Lukas, L.; Suykens, J. A. K.; Vanhamme, L.; Tate, A. R.; Howe, F. A.; Majós, C.; Moreno-Torres, A.; van der Graaf, M.; Arús, C.; Van Huffel, S.

2004-09-01

The purpose was to objectively compare the application of several techniques and the use of several input features for brain tumour classification using Magnetic Resonance Spectroscopy (MRS). Short echo time 1H MRS signals from patients with glioblastomas ( n = 87), meningiomas ( n = 57), metastases ( n = 39), and astrocytomas grade II ( n = 22) were provided by six centres in the European Union funded INTERPRET project. Linear discriminant analysis, least squares support vector machines (LS-SVM) with a linear kernel and LS-SVM with radial basis function kernel were applied and evaluated over 100 stratified random splittings of the dataset into training and test sets. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of binary classifiers, while the percentage of correct classifications was used to evaluate the multiclass classifiers. The influence of several factors on the classification performance has been tested: L2- vs. water normalization, magnitude vs. real spectra and baseline correction. The effect of input feature reduction was also investigated by using only the selected frequency regions containing the most discriminatory information, and peak integrated values. Using L2-normalized complete spectra the automated binary classifiers reached a mean test AUC of more than 0.95, except for glioblastomas vs. metastases. Similar results were obtained for all classification techniques and input features except for water normalized spectra, where classification performance was lower. This indicates that data acquisition and processing can be simplified for classification purposes, excluding the need for separate water signal acquisition, baseline correction or phasing.

Automated detection of focal cortical dysplasia type II with surface-based magnetic resonance imaging postprocessing and machine learning.

PubMed

Jin, Bo; Krishnan, Balu; Adler, Sophie; Wagstyl, Konrad; Hu, Wenhan; Jones, Stephen; Najm, Imad; Alexopoulos, Andreas; Zhang, Kai; Zhang, Jianguo; Ding, Meiping; Wang, Shuang; Wang, Zhong Irene

2018-05-01

Focal cortical dysplasia (FCD) is a major pathology in patients undergoing surgical resection to treat pharmacoresistant epilepsy. Magnetic resonance imaging (MRI) postprocessing methods may provide essential help for detection of FCD. In this study, we utilized surface-based MRI morphometry and machine learning for automated lesion detection in a mixed cohort of patients with FCD type II from 3 different epilepsy centers. Sixty-one patients with pharmacoresistant epilepsy and histologically proven FCD type II were included in the study. The patients had been evaluated at 3 different epilepsy centers using 3 different MRI scanners. T1-volumetric sequence was used for postprocessing. A normal database was constructed with 120 healthy controls. We also included 35 healthy test controls and 15 disease test controls with histologically confirmed hippocampal sclerosis to assess specificity. Features were calculated and incorporated into a nonlinear neural network classifier, which was trained to identify lesional cluster. We optimized the threshold of the output probability map from the classifier by performing receiver operating characteristic (ROC) analyses. Success of detection was defined by overlap between the final cluster and the manual labeling. Performance was evaluated using k-fold cross-validation. The threshold of 0.9 showed optimal sensitivity of 73.7% and specificity of 90.0%. The area under the curve for the ROC analysis was 0.75, which suggests a discriminative classifier. Sensitivity and specificity were not significantly different for patients from different centers, suggesting robustness of performance. Correct detection rate was significantly lower in patients with initially normal MRI than patients with unequivocally positive MRI. Subgroup analysis showed the size of the training group and normal control database impacted classifier performance. Automated surface-based MRI morphometry equipped with machine learning showed robust performance across cohorts from different centers and scanners. The proposed method may be a valuable tool to improve FCD detection in presurgical evaluation for patients with pharmacoresistant epilepsy. Wiley Periodicals, Inc. © 2018 International League Against Epilepsy.

Correcting the influence of vegetation on surface soil moisture indices by using hyperspectral artificial 3D-canopy models

NASA Astrophysics Data System (ADS)

Spengler, D.; Kuester, T.; Frick, A.; Scheffler, D.; Kaufmann, H.

2013-10-01

Surface soil moisture content is one of the key variables used for many applications especially in hydrology, meteorology and agriculture. Hyperspectral remote sensing provides effective methodologies for mapping soil moisture content over a broad area by different indices such as NSMI [1,2] and SMGM [3]. Both indices can achieve a high accuracy for non-vegetation influenced soil samples, but their accuracy is limited in case of the presence of vegetation. Since, the increase of the vegetation cover leads to non-linear variations of the indices. In this study a new methodology for moisture indices correcting the influence of vegetation is presented consisting of several processing steps. First, hyperspectral reflectance data are classified in terms of crop type and growth stage. Second, based on these parameters 3D plant models from a database used to simulate typical canopy reflectance considering variations in the canopy structure (e.g. plant density and distribution) and the soil moisture content for actual solar illumination and sensor viewing angles. Third, a vegetation correction function is developed, based on the calculated soil moisture indices and vegetation indices of the simulated canopy reflectance data. Finally this function is applied on hyperspectral image data. The method is tested on two hyperspectral image data sets of the AISA DUAL at the test site Fichtwald in Germany. The results show a significant improvements compared to solely use of NSMI index. Up to a vegetation cover of 75 % the correction function minimise the influences of vegetation cover significantly. If the vegetation is denser the method leads to inadequate quality to predict the soil moisture content. In summary it can be said that applying the method on weakly to moderately overgrown with vegetation locations enables a significant improvement in the quantification of soil moisture and thus greatly expands the scope of NSMI.

Features analysis for identification of date and party hubs in protein interaction network of Saccharomyces Cerevisiae.

PubMed

Mirzarezaee, Mitra; Araabi, Babak N; Sadeghi, Mehdi

2010-12-19

It has been understood that biological networks have modular organizations which are the sources of their observed complexity. Analysis of networks and motifs has shown that two types of hubs, party hubs and date hubs, are responsible for this complexity. Party hubs are local coordinators because of their high co-expressions with their partners, whereas date hubs display low co-expressions and are assumed as global connectors. However there is no mutual agreement on these concepts in related literature with different studies reporting their results on different data sets. We investigated whether there is a relation between the biological features of Saccharomyces Cerevisiae's proteins and their roles as non-hubs, intermediately connected, party hubs, and date hubs. We propose a classifier that separates these four classes. We extracted different biological characteristics including amino acid sequences, domain contents, repeated domains, functional categories, biological processes, cellular compartments, disordered regions, and position specific scoring matrix from various sources. Several classifiers are examined and the best feature-sets based on average correct classification rate and correlation coefficients of the results are selected. We show that fusion of five feature-sets including domains, Position Specific Scoring Matrix-400, cellular compartments level one, and composition pairs with two and one gaps provide the best discrimination with an average correct classification rate of 77%. We study a variety of known biological feature-sets of the proteins and show that there is a relation between domains, Position Specific Scoring Matrix-400, cellular compartments level one, composition pairs with two and one gaps of Saccharomyces Cerevisiae's proteins, and their roles in the protein interaction network as non-hubs, intermediately connected, party hubs and date hubs. This study also confirms the possibility of predicting non-hubs, party hubs and date hubs based on their biological features with acceptable accuracy. If such a hypothesis is correct for other species as well, similar methods can be applied to predict the roles of proteins in those species.

PCA method for automated detection of mispronounced words

NASA Astrophysics Data System (ADS)

Ge, Zhenhao; Sharma, Sudhendu R.; Smith, Mark J. T.

2011-06-01

This paper presents a method for detecting mispronunciations with the aim of improving Computer Assisted Language Learning (CALL) tools used by foreign language learners. The algorithm is based on Principle Component Analysis (PCA). It is hierarchical with each successive step refining the estimate to classify the test word as being either mispronounced or correct. Preprocessing before detection, like normalization and time-scale modification, is implemented to guarantee uniformity of the feature vectors input to the detection system. The performance using various features including spectrograms and Mel-Frequency Cepstral Coefficients (MFCCs) are compared and evaluated. Best results were obtained using MFCCs, achieving up to 99% accuracy in word verification and 93% in native/non-native classification. Compared with Hidden Markov Models (HMMs) which are used pervasively in recognition application, this particular approach is computational efficient and effective when training data is limited.

Classification of plum spirit drinks by synchronous fluorescence spectroscopy.

PubMed

Sádecká, J; Jakubíková, M; Májek, P; Kleinová, A

2016-04-01

Synchronous fluorescence spectroscopy was used in combination with principal component analysis (PCA) and linear discriminant analysis (LDA) for the differentiation of plum spirits according to their geographical origin. A total of 14 Czech, 12 Hungarian and 18 Slovak plum spirit samples were used. The samples were divided in two categories: colorless (22 samples) and colored (22 samples). Synchronous fluorescence spectra (SFS) obtained at a wavelength difference of 60 nm provided the best results. Considering the PCA-LDA applied to the SFS of all samples, Czech, Hungarian and Slovak colorless samples were properly classified in both the calibration and prediction sets. 100% of correct classification was also obtained for Czech and Hungarian colored samples. However, one group of Slovak colored samples was classified as belonging to the Hungarian group in the calibration set. Thus, the total correct classifications obtained were 94% and 100% for the calibration and prediction steps, respectively. The results were compared with those obtained using near-infrared (NIR) spectroscopy. Applying PCA-LDA to NIR spectra (5500-6000 cm(-1)), the total correct classifications were 91% and 92% for the calibration and prediction steps, respectively, which were slightly lower than those obtained using SFS. Copyright © 2015 Elsevier Ltd. All rights reserved.

Paroxysmal atrial fibrillation prediction method with shorter HRV sequences.

PubMed

Boon, K H; Khalil-Hani, M; Malarvili, M B; Sia, C W

2016-10-01

This paper proposes a method that predicts the onset of paroxysmal atrial fibrillation (PAF), using heart rate variability (HRV) segments that are shorter than those applied in existing methods, while maintaining good prediction accuracy. PAF is a common cardiac arrhythmia that increases the health risk of a patient, and the development of an accurate predictor of the onset of PAF is clinical important because it increases the possibility to stabilize (electrically) and prevent the onset of atrial arrhythmias with different pacing techniques. We investigate the effect of HRV features extracted from different lengths of HRV segments prior to PAF onset with the proposed PAF prediction method. The pre-processing stage of the predictor includes QRS detection, HRV quantification and ectopic beat correction. Time-domain, frequency-domain, non-linear and bispectrum features are then extracted from the quantified HRV. In the feature selection, the HRV feature set and classifier parameters are optimized simultaneously using an optimization procedure based on genetic algorithm (GA). Both full feature set and statistically significant feature subset are optimized by GA respectively. For the statistically significant feature subset, Mann-Whitney U test is used to filter non-statistical significance features that cannot pass the statistical test at 20% significant level. The final stage of our predictor is the classifier that is based on support vector machine (SVM). A 10-fold cross-validation is applied in performance evaluation, and the proposed method achieves 79.3% prediction accuracy using 15-minutes HRV segment. This accuracy is comparable to that achieved by existing methods that use 30-minutes HRV segments, most of which achieves accuracy of around 80%. More importantly, our method significantly outperforms those that applied segments shorter than 30 minutes. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Association algorithm to mine the rules that govern enzyme definition and to classify protein sequences

PubMed Central

Chiu, Shih-Hau; Chen, Chien-Chi; Yuan, Gwo-Fang; Lin, Thy-Hou

2006-01-01

Background The number of sequences compiled in many genome projects is growing exponentially, but most of them have not been characterized experimentally. An automatic annotation scheme must be in an urgent need to reduce the gap between the amount of new sequences produced and reliable functional annotation. This work proposes rules for automatically classifying the fungus genes. The approach involves elucidating the enzyme classifying rule that is hidden in UniProt protein knowledgebase and then applying it for classification. The association algorithm, Apriori, is utilized to mine the relationship between the enzyme class and significant InterPro entries. The candidate rules are evaluated for their classificatory capacity. Results There were five datasets collected from the Swiss-Prot for establishing the annotation rules. These were treated as the training sets. The TrEMBL entries were treated as the testing set. A correct enzyme classification rate of 70% was obtained for the prokaryote datasets and a similar rate of about 80% was obtained for the eukaryote datasets. The fungus training dataset which lacks an enzyme class description was also used to evaluate the fungus candidate rules. A total of 88 out of 5085 test entries were matched with the fungus rule set. These were otherwise poorly annotated using their functional descriptions. Conclusion The feasibility of using the method presented here to classify enzyme classes based on the enzyme domain rules is evident. The rules may be also employed by the protein annotators in manual annotation or implemented in an automatic annotation flowchart. PMID:16776838

Corrective Techniques and Future Directions for Treatment of Residual Refractive Error Following Cataract Surgery

PubMed Central

Moshirfar, Majid; McCaughey, Michael V; Santiago-Caban, Luis

2015-01-01

Postoperative residual refractive error following cataract surgery is not an uncommon occurrence for a large proportion of modern-day patients. Residual refractive errors can be broadly classified into 3 main categories: myopic, hyperopic, and astigmatic. The degree to which a residual refractive error adversely affects a patient is dependent on the magnitude of the error, as well as the specific type of intraocular lens the patient possesses. There are a variety of strategies for resolving residual refractive errors that must be individualized for each specific patient scenario. In this review, the authors discuss contemporary methods for rectification of residual refractive error, along with their respective indications/contraindications, and efficacies. PMID:25663845

Corrective Techniques and Future Directions for Treatment of Residual Refractive Error Following Cataract Surgery.

PubMed

Moshirfar, Majid; McCaughey, Michael V; Santiago-Caban, Luis

2014-12-01

Postoperative residual refractive error following cataract surgery is not an uncommon occurrence for a large proportion of modern-day patients. Residual refractive errors can be broadly classified into 3 main categories: myopic, hyperopic, and astigmatic. The degree to which a residual refractive error adversely affects a patient is dependent on the magnitude of the error, as well as the specific type of intraocular lens the patient possesses. There are a variety of strategies for resolving residual refractive errors that must be individualized for each specific patient scenario. In this review, the authors discuss contemporary methods for rectification of residual refractive error, along with their respective indications/contraindications, and efficacies.

Metal surface corrosion grade estimation from single image

NASA Astrophysics Data System (ADS)

Chen, Yijun; Qi, Lin; Sun, Huyuan; Fan, Hao; Dong, Junyu

2018-04-01

Metal corrosion can cause many problems, how to quickly and effectively assess the grade of metal corrosion and timely remediation is a very important issue. Typically, this is done by trained surveyors at great cost. Assisting them in the inspection process by computer vision and artificial intelligence would decrease the inspection cost. In this paper, we propose a dataset of metal surface correction used for computer vision detection and present a comparison between standard computer vision techniques by using OpenCV and deep learning method for automatic metal surface corrosion grade estimation from single image on this dataset. The test has been performed by classifying images and calculating the accuracy for the two different approaches.

Intelligent Color Vision System for Ripeness Classification of Oil Palm Fresh Fruit Bunch

PubMed Central

Fadilah, Norasyikin; Mohamad-Saleh, Junita; Halim, Zaini Abdul; Ibrahim, Haidi; Ali, Syed Salim Syed

2012-01-01

Ripeness classification of oil palm fresh fruit bunches (FFBs) during harvesting is important to ensure that they are harvested during optimum stage for maximum oil production. This paper presents the application of color vision for automated ripeness classification of oil palm FFB. Images of oil palm FFBs of type DxP Yangambi were collected and analyzed using digital image processing techniques. Then the color features were extracted from those images and used as the inputs for Artificial Neural Network (ANN) learning. The performance of the ANN for ripeness classification of oil palm FFB was investigated using two methods: training ANN with full features and training ANN with reduced features based on the Principal Component Analysis (PCA) data reduction technique. Results showed that compared with using full features in ANN, using the ANN trained with reduced features can improve the classification accuracy by 1.66% and is more effective in developing an automated ripeness classifier for oil palm FFB. The developed ripeness classifier can act as a sensor in determining the correct oil palm FFB ripeness category. PMID:23202043

Automatic classification of ovarian cancer types from cytological images using deep convolutional neural networks.

PubMed

Wu, Miao; Yan, Chuanbo; Liu, Huiqiang; Liu, Qian

2018-06-29

Ovarian cancer is one of the most common gynecologic malignancies. Accurate classification of ovarian cancer types (serous carcinoma, mucous carcinoma, endometrioid carcinoma, transparent cell carcinoma) is an essential part in the different diagnosis. Computer-aided diagnosis (CADx) can provide useful advice for pathologists to determine the diagnosis correctly. In our study, we employed a Deep Convolutional Neural Networks (DCNN) based on AlexNet to automatically classify the different types of ovarian cancers from cytological images. The DCNN consists of five convolutional layers, three max pooling layers, and two full reconnect layers. Then we trained the model by two group input data separately, one was original image data and the other one was augmented image data including image enhancement and image rotation. The testing results are obtained by the method of 10-fold cross-validation, showing that the accuracy of classification models has been improved from 72.76 to 78.20% by using augmented images as training data. The developed scheme was useful for classifying ovarian cancers from cytological images. © 2018 The Author(s).

Shift-, rotation-, and scale-invariant shape recognition system using an optical Hough transform

NASA Astrophysics Data System (ADS)

Schmid, Volker R.; Bader, Gerhard; Lueder, Ernst H.

1998-02-01

We present a hybrid shape recognition system with an optical Hough transform processor. The features of the Hough space offer a separate cancellation of distortions caused by translations and rotations. Scale invariance is also provided by suitable normalization. The proposed system extends the capabilities of Hough transform based detection from only straight lines to areas bounded by edges. A very compact optical design is achieved by a microlens array processor accepting incoherent light as direct optical input and realizing the computationally expensive connections massively parallel. Our newly developed algorithm extracts rotation and translation invariant normalized patterns of bright spots on a 2D grid. A neural network classifier maps the 2D features via a nonlinear hidden layer onto the classification output vector. We propose initialization of the connection weights according to regions of activity specifically assigned to each neuron in the hidden layer using a competitive network. The presented system is designed for industry inspection applications. Presently we have demonstrated detection of six different machined parts in real-time. Our method yields very promising detection results of more than 96% correctly classified parts.

Intelligent color vision system for ripeness classification of oil palm fresh fruit bunch.

PubMed

Fadilah, Norasyikin; Mohamad-Saleh, Junita; Abdul Halim, Zaini; Ibrahim, Haidi; Syed Ali, Syed Salim

2012-10-22

Ripeness classification of oil palm fresh fruit bunches (FFBs) during harvesting is important to ensure that they are harvested during optimum stage for maximum oil production. This paper presents the application of color vision for automated ripeness classification of oil palm FFB. Images of oil palm FFBs of type DxP Yangambi were collected and analyzed using digital image processing techniques. Then the color features were extracted from those images and used as the inputs for Artificial Neural Network (ANN) learning. The performance of the ANN for ripeness classification of oil palm FFB was investigated using two methods: training ANN with full features and training ANN with reduced features based on the Principal Component Analysis (PCA) data reduction technique. Results showed that compared with using full features in ANN, using the ANN trained with reduced features can improve the classification accuracy by 1.66% and is more effective in developing an automated ripeness classifier for oil palm FFB. The developed ripeness classifier can act as a sensor in determining the correct oil palm FFB ripeness category.

[Identification of special quality eggs with NIR spectroscopy technology based on symbol entropy feature extraction method].

PubMed

Zhao, Yong; Hong, Wen-Xue

2011-11-01

Fast, nondestructive and accurate identification of special quality eggs is an urgent problem. The present paper proposed a new feature extraction method based on symbol entropy to identify near infrared spectroscopy of special quality eggs. The authors selected normal eggs, free range eggs, selenium-enriched eggs and zinc-enriched eggs as research objects and measured the near-infrared diffuse reflectance spectra in the range of 12 000-4 000 cm(-1). Raw spectra were symbolically represented with aggregation approximation algorithm and symbolic entropy was extracted as feature vector. An error-correcting output codes multiclass support vector machine classifier was designed to identify the spectrum. Symbolic entropy feature is robust when parameter changed and the highest recognition rate reaches up to 100%. The results show that the identification method of special quality eggs using near-infrared is feasible and the symbol entropy can be used as a new feature extraction method of near-infrared spectra.

Application of the Optimized Summed Scored Attributes Method to Sex Estimation in Asian Crania.

PubMed

Tallman, Sean D; Go, Matthew C

2018-05-01

The optimized summed scored attributes (OSSA) method was recently introduced and validated for nonmetric ancestry estimation between American Black and White individuals. The method proceeds by scoring, dichotomizing, and subsequently summing ordinal morphoscopic trait scores to maximize between-group differences. This study tests the applicability of the OSSA method for sex estimation using five cranial traits given the methodological similarities between classifying sex and ancestry. A large sample of documented crania from Japan and Thailand (n = 744 males, 320 females) are used to develop a heuristically selected OSSA sectioning point of ≤1 separating males and females. This sectioning point is validated using a holdout sample of Japanese, Thai, and Filipino (n = 178 males, 82 females) individuals. The results indicate a general correct classification rate of 82% using all five traits, and 81% when excluding the mental eminence. Designating an OSSA score of 2 as indeterminate is recommended. © 2017 American Academy of Forensic Sciences.

Validation of the ICU-DaMa tool for automatically extracting variables for minimum dataset and quality indicators: The importance of data quality assessment.

PubMed

Sirgo, Gonzalo; Esteban, Federico; Gómez, Josep; Moreno, Gerard; Rodríguez, Alejandro; Blanch, Lluis; Guardiola, Juan José; Gracia, Rafael; De Haro, Lluis; Bodí, María

2018-04-01

Big data analytics promise insights into healthcare processes and management, improving outcomes while reducing costs. However, data quality is a major challenge for reliable results. Business process discovery techniques and an associated data model were used to develop data management tool, ICU-DaMa, for extracting variables essential for overseeing the quality of care in the intensive care unit (ICU). To determine the feasibility of using ICU-DaMa to automatically extract variables for the minimum dataset and ICU quality indicators from the clinical information system (CIS). The Wilcoxon signed-rank test and Fisher's exact test were used to compare the values extracted from the CIS with ICU-DaMa for 25 variables from all patients attended in a polyvalent ICU during a two-month period against the gold standard of values manually extracted by two trained physicians. Discrepancies with the gold standard were classified into plausibility, conformance, and completeness errors. Data from 149 patients were included. Although there were no significant differences between the automatic method and the manual method, we detected differences in values for five variables, including one plausibility error and two conformance and completeness errors. Plausibility: 1) Sex, ICU-DaMa incorrectly classified one male patient as female (error generated by the Hospital's Admissions Department). Conformance: 2) Reason for isolation, ICU-DaMa failed to detect a human error in which a professional misclassified a patient's isolation. 3) Brain death, ICU-DaMa failed to detect another human error in which a professional likely entered two mutually exclusive values related to the death of the patient (brain death and controlled donation after circulatory death). Completeness: 4) Destination at ICU discharge, ICU-DaMa incorrectly classified two patients due to a professional failing to fill out the patient discharge form when thepatients died. 5) Length of continuous renal replacement therapy, data were missing for one patient because the CRRT device was not connected to the CIS. Automatic generation of minimum dataset and ICU quality indicators using ICU-DaMa is feasible. The discrepancies were identified and can be corrected by improving CIS ergonomics, training healthcare professionals in the culture of the quality of information, and using tools for detecting and correcting data errors. Copyright © 2018 Elsevier B.V. All rights reserved.

Progressive Classification Using Support Vector Machines

NASA Technical Reports Server (NTRS)

Wagstaff, Kiri; Kocurek, Michael

2009-01-01

An algorithm for progressive classification of data, analogous to progressive rendering of images, makes it possible to compromise between speed and accuracy. This algorithm uses support vector machines (SVMs) to classify data. An SVM is a machine learning algorithm that builds a mathematical model of the desired classification concept by identifying the critical data points, called support vectors. Coarse approximations to the concept require only a few support vectors, while precise, highly accurate models require far more support vectors. Once the model has been constructed, the SVM can be applied to new observations. The cost of classifying a new observation is proportional to the number of support vectors in the model. When computational resources are limited, an SVM of the appropriate complexity can be produced. However, if the constraints are not known when the model is constructed, or if they can change over time, a method for adaptively responding to the current resource constraints is required. This capability is particularly relevant for spacecraft (or any other real-time systems) that perform onboard data analysis. The new algorithm enables the fast, interactive application of an SVM classifier to a new set of data. The classification process achieved by this algorithm is characterized as progressive because a coarse approximation to the true classification is generated rapidly and thereafter iteratively refined. The algorithm uses two SVMs: (1) a fast, approximate one and (2) slow, highly accurate one. New data are initially classified by the fast SVM, producing a baseline approximate classification. For each classified data point, the algorithm calculates a confidence index that indicates the likelihood that it was classified correctly in the first pass. Next, the data points are sorted by their confidence indices and progressively reclassified by the slower, more accurate SVM, starting with the items most likely to be incorrectly classified. The user can halt this reclassification process at any point, thereby obtaining the best possible result for a given amount of computation time. Alternatively, the results can be displayed as they are generated, providing the user with real-time feedback about the current accuracy of classification.

Image processing for x-ray inspection of pistachio nuts

NASA Astrophysics Data System (ADS)

Casasent, David P.

2001-03-01

A review is provided of image processing techniques that have been applied to the inspection of pistachio nuts using X-ray images. X-ray sensors provide non-destructive internal product detail not available from other sensors. The primary concern in this data is detecting the presence of worm infestations in nuts, since they have been linked to the presence of aflatoxin. We describe new techniques for segmentation, feature selection, selection of product categories (clusters), classifier design, etc. Specific novel results include: a new segmentation algorithm to produce images of isolated product items; preferable classifier operation (the classifier with the best probability of correct recognition Pc is not best); higher-order discrimination information is present in standard features (thus, high-order features appear useful); classifiers that use new cluster categories of samples achieve improved performance. Results are presented for X-ray images of pistachio nuts; however, all techniques have use in other product inspection applications.

Optimal threshold estimation for binary classifiers using game theory.

PubMed

Sanchez, Ignacio Enrique

2016-01-01

Many bioinformatics algorithms can be understood as binary classifiers. They are usually compared using the area under the receiver operating characteristic ( ROC ) curve. On the other hand, choosing the best threshold for practical use is a complex task, due to uncertain and context-dependent skews in the abundance of positives in nature and in the yields/costs for correct/incorrect classification. We argue that considering a classifier as a player in a zero-sum game allows us to use the minimax principle from game theory to determine the optimal operating point. The proposed classifier threshold corresponds to the intersection between the ROC curve and the descending diagonal in ROC space and yields a minimax accuracy of 1-FPR. Our proposal can be readily implemented in practice, and reveals that the empirical condition for threshold estimation of "specificity equals sensitivity" maximizes robustness against uncertainties in the abundance of positives in nature and classification costs.

Bladder cancer staging in CT urography: effect of stage labels on statistical modeling of a decision support system

NASA Astrophysics Data System (ADS)

Gandikota, Dhanuj; Hadjiiski, Lubomir; Cha, Kenny H.; Chan, Heang-Ping; Caoili, Elaine M.; Cohan, Richard H.; Weizer, Alon; Alva, Ajjai; Paramagul, Chintana; Wei, Jun; Zhou, Chuan

2018-02-01

In bladder cancer, stage T2 is an important threshold in the decision of administering neoadjuvant chemotherapy. Our long-term goal is to develop a quantitative computerized decision support system (CDSS-S) to aid clinicians in accurate staging. In this study, we examined the effect of stage labels of the training samples on modeling such a system. We used a data set of 84 bladder cancers imaged with CT Urography (CTU). At clinical staging prior to treatment, 43 lesions were staged as below stage T2 and 41 were stage T2 or above. After cystectomy and pathological staging that is considered the gold standard, 10 of the lesions were upstaged to stage T2 or above. After correcting the stage labels, 33 lesions were below stage T2, and 51 were stage T2 or above. For the CDSS-S, the lesions were segmented using our AI-CALS method and radiomic features were extracted. We trained a linear discriminant analysis (LDA) classifier with leave-one-case-out cross validation to distinguish between bladder lesions of stage T2 or above and those below stage T2. The CDSS-S was trained and tested with the corrected post-cystectomy labels, and as a comparison, CDSS-S was also trained with understaged pre-treatment labels and tested on lesions with corrected labels. The test AUC for the CDSS-S trained with corrected labels was 0.89 +/- 0.04. For the CDSS-S trained with understaged pre-treatment labels and tested on the lesions with corrected labels, the test AUC was 0.86 +/- 0.04. The likelihood of stage T2 or above for 9 out of the 10 understaged lesions was correctly increased for the CDSS-S trained with corrected labels. The CDSS-S is sensitive to the accuracy of stage labeling. The CDSS-S trained with correct labels shows promise in prediction of the bladder cancer stage.

Pairwise Classifier Ensemble with Adaptive Sub-Classifiers for fMRI Pattern Analysis.

PubMed

Kim, Eunwoo; Park, HyunWook

2017-02-01

The multi-voxel pattern analysis technique is applied to fMRI data for classification of high-level brain functions using pattern information distributed over multiple voxels. In this paper, we propose a classifier ensemble for multiclass classification in fMRI analysis, exploiting the fact that specific neighboring voxels can contain spatial pattern information. The proposed method converts the multiclass classification to a pairwise classifier ensemble, and each pairwise classifier consists of multiple sub-classifiers using an adaptive feature set for each class-pair. Simulated and real fMRI data were used to verify the proposed method. Intra- and inter-subject analyses were performed to compare the proposed method with several well-known classifiers, including single and ensemble classifiers. The comparison results showed that the proposed method can be generally applied to multiclass classification in both simulations and real fMRI analyses.

Novel grid combined with peripheral distortion correction for ultra-widefield image grading of age-related macular degeneration

PubMed Central

Mach, Steven; Garas, Shady; Kim, Ivana K; Vavvas, Demetrios G; Miller, Joan W; Husain, Deeba; Miller, John B

2017-01-01

Purpose Eyes with age-related macular degeneration (AMD) often harbor pathological changes in the retinal periphery and perimacular region. These extramacular changes have not been well classified, but may be phenotypically and functionally relevant. The purpose of this study was to demonstrate a novel grid to systematically study peripheral retinal abnormalities in AMD using geometric distortion-corrected ultra-widefield (UWF) imaging. Methods This is a cross-sectional observational case series. Consecutive patients with AMD without any other coexisting vitreoretinal disease and control patients over age 50 without AMD or any other vitreoretinal disease were imaged using Optos 200 Tx. Captured 200° UWF images were corrected for peripheral geometric distortion using Optos transformation software. A newly developed grid to study perimacular and peripheral abnormalities in AMD was then projected onto the images. Results Peripheral and perimacular changes such as drusen, retinal pigment epithelium changes and atrophy were found in patients with AMD. The presented grid in conjunction with geometric distortion-corrected UWF images allowed for systematic study of these peripheral changes in AMD. Conclusion We present a novel grid to study peripheral and posterior pole changes in AMD. The grid is unique in that it adds a perimacular zone, which may be important in characterizing certain phenotypes in AMD. Our UWF images were corrected for geometric peripheral distortion to accurately reflect the anatomical dimensions of the retina. This grid offers a reliable and reproducible foundation for the exploration of peripheral retinal pathology associated with AMD. PMID:29184386

Automatic analysis and classification of surface electromyography.

PubMed

Abou-Chadi, F E; Nashar, A; Saad, M

2001-01-01

In this paper, parametric modeling of surface electromyography (EMG) algorithms that facilitates automatic SEMG feature extraction and artificial neural networks (ANN) are combined for providing an integrated system for the automatic analysis and diagnosis of myopathic disorders. Three paradigms of ANN were investigated: the multilayer backpropagation algorithm, the self-organizing feature map algorithm and a probabilistic neural network model. The performance of the three classifiers was compared with that of the old Fisher linear discriminant (FLD) classifiers. The results have shown that the three ANN models give higher performance. The percentage of correct classification reaches 90%. Poorer diagnostic performance was obtained from the FLD classifier. The system presented here indicates that surface EMG, when properly processed, can be used to provide the physician with a diagnostic assist device.

An investigation of the use of discriminant analysis for the classification of blade edge type from cut marks made by metal and bamboo blades.

PubMed

Bonney, Heather

2014-08-01

Analysis of cut marks in bone is largely limited to two dimensional qualitative description. Development of morphological classification methods using measurements from cut mark cross sections could have multiple uses across palaeoanthropological and archaeological disciplines, where cutting edge types are used to investigate and reconstruct behavioral patterns. An experimental study was undertaken, using porcine bone, to determine the usefulness of discriminant function analysis in classifying cut marks by blade edge type, from a number of measurements taken from their cross-sectional profile. The discriminant analysis correctly classified 86.7% of the experimental cut marks into serrated, non-serrated and bamboo blade types. The technique was then used to investigate a series of cut marks of unknown origin from a collection of trophy skulls from the Torres Strait Islands, to investigate whether they were made by bamboo or metal blades. Nineteen out of twenty of the cut marks investigated were classified as bamboo which supports the non-contemporaneous ethnographic accounts of the knives used for trophy taking and defleshing remains. With further investigation across a variety of blade types, this technique could prove a valuable tool in the interpretation of cut mark evidence from a wide variety of contexts, particularly in forensic anthropology where the requirement for presentation of evidence in a statistical format is becoming increasingly important. © 2014 Wiley Periodicals, Inc.

The classification of secondary colorectal liver cancer in human biopsy samples using angular dispersive x-ray diffraction and multivariate analysis

NASA Astrophysics Data System (ADS)

Theodorakou, Chrysoula; Farquharson, Michael J.

2009-08-01

The motivation behind this study is to assess whether angular dispersive x-ray diffraction (ADXRD) data, processed using multivariate analysis techniques, can be used for classifying secondary colorectal liver cancer tissue and normal surrounding liver tissue in human liver biopsy samples. The ADXRD profiles from a total of 60 samples of normal liver tissue and colorectal liver metastases were measured using a synchrotron radiation source. The data were analysed for 56 samples using nonlinear peak-fitting software. Four peaks were fitted to all of the ADXRD profiles, and the amplitude, area, amplitude and area ratios for three of the four peaks were calculated and used for the statistical and multivariate analysis. The statistical analysis showed that there are significant differences between all the peak-fitting parameters and ratios between the normal and the diseased tissue groups. The technique of soft independent modelling of class analogy (SIMCA) was used to classify normal liver tissue and colorectal liver metastases resulting in 67% of the normal tissue samples and 60% of the secondary colorectal liver tissue samples being classified correctly. This study has shown that the ADXRD data of normal and secondary colorectal liver cancer are statistically different and x-ray diffraction data analysed using multivariate analysis have the potential to be used as a method of tissue classification.

Effective user guidance in online interactive semantic segmentation

NASA Astrophysics Data System (ADS)

Petersen, Jens; Bendszus, Martin; Debus, Jürgen; Heiland, Sabine; Maier-Hein, Klaus H.

2017-03-01

With the recent success of machine learning based solutions for automatic image parsing, the availability of reference image annotations for algorithm training is one of the major bottlenecks in medical image segmentation. We are interested in interactive semantic segmentation methods that can be used in an online fashion to generate expert segmentations. These can be used to train automated segmentation techniques or, from an application perspective, for quick and accurate tumor progression monitoring. Using simulated user interactions in a MRI glioblastoma segmentation task, we show that if the user possesses knowledge of the correct segmentation it is significantly (p <= 0.009) better to present data and current segmentation to the user in such a manner that they can easily identify falsely classified regions compared to guiding the user to regions where the classifier exhibits high uncertainty, resulting in differences of mean Dice scores between +0.070 (Whole tumor) and +0.136 (Tumor Core) after 20 iterations. The annotation process should cover all classes equally, which results in a significant (p <= 0.002) improvement compared to completely random annotations anywhere in falsely classified regions for small tumor regions such as the necrotic tumor core (mean Dice +0.151 after 20 it.) and non-enhancing abnormalities (mean Dice +0.069 after 20 it.). These findings provide important insights for the development of efficient interactive segmentation systems and user interfaces.

A Robust Step Detection Algorithm and Walking Distance Estimation Based on Daily Wrist Activity Recognition Using a Smart Band.

PubMed

Trong Bui, Duong; Nguyen, Nhan Duc; Jeong, Gu-Min

2018-06-25

Human activity recognition and pedestrian dead reckoning are an interesting field because of their importance utilities in daily life healthcare. Currently, these fields are facing many challenges, one of which is the lack of a robust algorithm with high performance. This paper proposes a new method to implement a robust step detection and adaptive distance estimation algorithm based on the classification of five daily wrist activities during walking at various speeds using a smart band. The key idea is that the non-parametric adaptive distance estimator is performed after two activity classifiers and a robust step detector. In this study, two classifiers perform two phases of recognizing five wrist activities during walking. Then, a robust step detection algorithm, which is integrated with an adaptive threshold, peak and valley correction algorithm, is applied to the classified activities to detect the walking steps. In addition, the misclassification activities are fed back to the previous layer. Finally, three adaptive distance estimators, which are based on a non-parametric model of the average walking speed, calculate the length of each strike. The experimental results show that the average classification accuracy is about 99%, and the accuracy of the step detection is 98.7%. The error of the estimated distance is 2.2⁻4.2% depending on the type of wrist activities.

Sleep versus wake classification from heart rate variability using computational intelligence: consideration of rejection in classification models.

PubMed

Lewicke, Aaron; Sazonov, Edward; Corwin, Michael J; Neuman, Michael; Schuckers, Stephanie

2008-01-01

Reliability of classification performance is important for many biomedical applications. A classification model which considers reliability in the development of the model such that unreliable segments are rejected would be useful, particularly, in large biomedical data sets. This approach is demonstrated in the development of a technique to reliably determine sleep and wake using only the electrocardiogram (ECG) of infants. Typically, sleep state scoring is a time consuming task in which sleep states are manually derived from many physiological signals. The method was tested with simultaneous 8-h ECG and polysomnogram (PSG) determined sleep scores from 190 infants enrolled in the collaborative home infant monitoring evaluation (CHIME) study. Learning vector quantization (LVQ) neural network, multilayer perceptron (MLP) neural network, and support vector machines (SVMs) are tested as the classifiers. After systematic rejection of difficult to classify segments, the models can achieve 85%-87% correct classification while rejecting only 30% of the data. This corresponds to a Kappa statistic of 0.65-0.68. With rejection, accuracy improves by about 8% over a model without rejection. Additionally, the impact of the PSG scored indeterminate state epochs is analyzed. The advantages of a reliable sleep/wake classifier based only on ECG include high accuracy, simplicity of use, and low intrusiveness. Reliability of the classification can be built directly in the model, such that unreliable segments are rejected.

Comparative evaluation of support vector machine classification for computer aided detection of breast masses in mammography

NASA Astrophysics Data System (ADS)

Lesniak, J. M.; Hupse, R.; Blanc, R.; Karssemeijer, N.; Székely, G.

2012-08-01

False positive (FP) marks represent an obstacle for effective use of computer-aided detection (CADe) of breast masses in mammography. Typically, the problem can be approached either by developing more discriminative features or by employing different classifier designs. In this paper, the usage of support vector machine (SVM) classification for FP reduction in CADe is investigated, presenting a systematic quantitative evaluation against neural networks, k-nearest neighbor classification, linear discriminant analysis and random forests. A large database of 2516 film mammography examinations and 73 input features was used to train the classifiers and evaluate for their performance on correctly diagnosed exams as well as false negatives. Further, classifier robustness was investigated using varying training data and feature sets as input. The evaluation was based on the mean exam sensitivity in 0.05-1 FPs on normals on the free-response receiver operating characteristic curve (FROC), incorporated into a tenfold cross validation framework. It was found that SVM classification using a Gaussian kernel offered significantly increased detection performance (P = 0.0002) compared to the reference methods. Varying training data and input features, SVMs showed improved exploitation of large feature sets. It is concluded that with the SVM-based CADe a significant reduction of FPs is possible outperforming other state-of-the-art approaches for breast mass CADe.

Indicators of Ecological Change

DTIC Science & Technology

2005-03-01

Vine 0.07 0.26 Yellow Jasmine LM Gymnopogon ambiguus Graminae Cryptophyte Geophyte Grass 0.17 0.45 Beard grass RLD Haplopappus divaricatus Asteraceae...cross-validation procedure. The cross-validation analysis 7 determines the percentage of observations correctly classified. In essence , a cross-8

Shallow water bathymetry correction using sea bottom classification with multispectral satellite imagery

NASA Astrophysics Data System (ADS)

Kazama, Yoriko; Yamamoto, Tomonori

2017-10-01

Bathymetry at shallow water especially shallower than 15m is an important area for environmental monitoring and national defense. Because the depth of shallow water is changeable by the sediment deposition and the ocean waves, the periodic monitoring at shoe area is needed. Utilization of satellite images are well matched for widely and repeatedly monitoring at sea area. Sea bottom terrain model using by remote sensing data have been developed and these methods based on the radiative transfer model of the sun irradiance which is affected by the atmosphere, water, and sea bottom. We adopted that general method of the sea depth extraction to the satellite imagery, WorldView-2; which has very fine spatial resolution (50cm/pix) and eight bands at visible to near-infrared wavelengths. From high-spatial resolution satellite images, there is possibility to know the coral reefs and the rock area's detail terrain model which offers important information for the amphibious landing. In addition, the WorldView-2 satellite sensor has the band at near the ultraviolet wavelength that is transmitted through the water. On the other hand, the previous study showed that the estimation error by the satellite imagery was related to the sea bottom materials such as sand, coral reef, sea alga, and rocks. Therefore, in this study, we focused on sea bottom materials, and tried to improve the depth estimation accuracy. First, we classified the sea bottom materials by the SVM method, which used the depth data acquired by multi-beam sonar as supervised data. Then correction values in the depth estimation equation were calculated applying the classification results. As a result, the classification accuracy of sea bottom materials was 93%, and the depth estimation error using the correction by the classification result was within 1.2m.

Speech Recognition: Proceedings of a Workshop Held in Palo Alto, California on 19-20 February 1986

DTIC Science & Technology

1986-02-01

always make the system fail - sometimes even when not trying to do so. Finally, Dr. Jelinek of IBM warned that the not-invented-here syndrome is hard to...Evaluation of its performance on 365 sentences indicates that 70% of the nasals are correctly located, with one impostor accepted for ev- ery nasal. Most...for each feature. Evaluation of the classifier performance on the same database indicates that 80% of the nasals and impostors are correctly id

matK-QR classifier: a patterns based approach for plant species identification.

PubMed

More, Ravi Prabhakar; Mane, Rupali Chandrashekhar; Purohit, Hemant J

2016-01-01

DNA barcoding is widely used and most efficient approach that facilitates rapid and accurate identification of plant species based on the short standardized segment of the genome. The nucleotide sequences of maturaseK ( matK ) and ribulose-1, 5-bisphosphate carboxylase ( rbcL ) marker loci are commonly used in plant species identification. Here, we present a new and highly efficient approach for identifying a unique set of discriminating nucleotide patterns to generate a signature (i.e. regular expression) for plant species identification. In order to generate molecular signatures, we used matK and rbcL loci datasets, which encompass 125 plant species in 52 genera reported by the CBOL plant working group. Initially, we performed Multiple Sequence Alignment (MSA) of all species followed by Position Specific Scoring Matrix (PSSM) for both loci to achieve a percentage of discrimination among species. Further, we detected Discriminating Patterns (DP) at genus and species level using PSSM for the matK dataset. Combining DP and consecutive pattern distances, we generated molecular signatures for each species. Finally, we performed a comparative assessment of these signatures with the existing methods including BLASTn, Support Vector Machines (SVM), Jrip-RIPPER, J48 (C4.5 algorithm), and the Naïve Bayes (NB) methods against NCBI-GenBank matK dataset. Due to the higher discrimination success obtained with the matK as compared to the rbcL , we selected matK gene for signature generation. We generated signatures for 60 species based on identified discriminating patterns at genus and species level. Our comparative assessment results suggest that a total of 46 out of 60 species could be correctly identified using generated signatures, followed by BLASTn (34 species), SVM (18 species), C4.5 (7 species), NB (4 species) and RIPPER (3 species) methods As a final outcome of this study, we converted signatures into QR codes and developed a software matK -QR Classifier (http://www.neeri.res.in/matk_classifier/index.htm), which search signatures in the query matK gene sequences and predict corresponding plant species. This novel approach of employing pattern-based signatures opens new avenues for the classification of species. In addition to existing methods, we believe that matK -QR Classifier would be a valuable tool for molecular taxonomists enabling precise identification of plant species.

Retinal phenotypic characterization of patients with ABCA4 retinopathydue to the homozygous p.Ala1773Val mutation

PubMed Central

López-Rubio, Salvador; Chacon-Camacho, Oscar F.; Matsui, Rodrigo; Guadarrama-Vallejo, Dalia; Astiazarán, Mirena C.

2018-01-01

Purpose To describe the retinal clinical features of a group of Mexican patients with Stargardt disease carrying the uncommon p.Ala1773Val founder mutation in ABCA4. Methods Ten patients carrying the p.Ala1773Val mutation, nine of them homozygously, were included. Visual function studies included best-corrected visual acuity, electroretinography, Goldmann kinetic visual fields, and full-field electroretinography (ERG). In addition, imaging studies, such as optical coherence tomography (OCT), short-wave autofluorescence imaging, and quantitative analyses of hypofluorescence, were performed in each patient. Results Best-corrected visual acuities ranged from 20/200 to 4/200. The median age of the patients at diagnosis was 23.3 years. The majority of the patients had photophobia and nyctalopia, and were classified as Fishman stage 4 (widespread choriocapillaris atrophy, resorption of flecks, and greatly reduced ERG amplitudes). An atypical retinal pigmentation pattern was observed in the patients, and the majority showed cone-rod dystrophy on full-field ERG. In vivo retinal microstructure assessment with OCT demonstrated central retinal thinning, variable loss of photoreceptors, and three different patterns of structural retinal degeneration. Two dissimilar patterns of abnormal autofluorescence were observed. No apparent age-related differences in the pattern of retinal degeneration were observed. Conclusions The results indicate that this particular mutation in ABCA4 is associated with a severe retinal phenotype and thus, could be classified as null. Careful phenotyping of patients carrying specific mutations in ABCA4 is essential to enhance our understanding of disease expression linked to particular mutations and the resulting genotype–phenotype correlations. PMID:29422768

The nature and extent of flavored alcoholic beverage consumption among underage youth: results of a national brand-specific survey.

PubMed

Giga, Noreen M; Binakonsky, Jane; Ross, Craig; Siegel, Michael

2011-07-01

Flavored alcoholic beverages are popular among underage drinkers. Existing studies that assessed flavored alcoholic beverage use among youth relied upon respondents to correctly classify the beverages they consume, without defining what alcohol brands belong to this category. The aim is to demonstrate a new method for analyzing the consumption of flavored alcoholic beverages among youth on a brand-specific basis, without relying upon youth to correctly classify brands they consume. Using a prerecruited Internet panel developed by Knowledge Networks, we measured the brands of alcohol consumed by a national sample of youth drinkers, aged 16?20 years, in the United States. The sample consisted of 108 youths who had consumed at least one drink of an alcoholic beverage in the past 30 days. We measured the brand-specific consumption of alcoholic beverages within the past 30 days, ascertaining the consumption of 380 alcohol brands, including 14 brands of flavored alcoholic beverages. Measuring the brand-specific consumption of flavored alcoholic beverages was feasible. Based on a brand-specific identification of flavored alcoholic beverages, nearly half of the youth drinkers in the sample reported having consumed such beverages in the past 30 days. Flavored alcoholic beverage preference was concentrated among the top four brands, which accounted for almost all of the consumption volume reported in our study. These findings underscore the need to assess youth alcohol consumption at the brand level and the potential value of such data in better understanding underage youth drinking behavior and the factors that influence it.

IATA for skin sensitization potential – 1 out of 2 or 2 out of 3? ...

EPA Pesticide Factsheets

To meet EU regulatory requirements and to avoid or minimize animal testing, there is a need for non-animal methods to assess skin sensitization potential. Given the complexity of the skin sensitization endpoint, there is an expectation that integrated testing and assessment approaches (IATA) will need to be developed which rely on assays representing key events in the pathway. Three non-animal assays have been formally validated: the direct peptide reactivity assay (DPRA), the KeratinoSensTM assay and the h-CLAT assay. At the same time, there have been many efforts to develop IATA with the “2 out of 3” approach attracting much attention whereby a chemical is classified on the basis of the majority outcome. A set of 271 chemicals with mouse, human and non-animal sensitization test data was evaluated to compare the predictive performances of the 3 individual non-animal assays, their binary combinations and the ‘2 out of 3’ approach. The analysis revealed that the most predictive approach was to use both the DPRA and h-CLAT: 1. Perform DPRA – if positive, classify as a sensitizer; 2. If negative, perform h-CLAT – a positive outcome denotes a sensitizer, a negative, a non-sensitizer. With this approach, 83% (LLNA) and 93% (human) of the non-sensitizer predictions were correct, in contrast to the ‘2 out of 3’ approach which had 69% (LLNA) and 79% (human) of non-sensitizer predictions correct. The views expressed are those of the authors and do not ne

Wave function continuity and the diagonal Born-Oppenheimer correction at conical intersections

DOE Office of Scientific and Technical Information (OSTI.GOV)

Meek, Garrett A.; Levine, Benjamin G., E-mail: levine@chemistry.msu.edu

2016-05-14

We demonstrate that though exact in principle, the expansion of the total molecular wave function as a sum over adiabatic Born-Oppenheimer (BO) vibronic states makes inclusion of the second-derivative nonadiabatic energy term near conical intersections practically problematic. In order to construct a well-behaved molecular wave function that has density at a conical intersection, the individual BO vibronic states in the summation must be discontinuous. When the second-derivative nonadiabatic terms are added to the Hamiltonian, singularities in the diagonal BO corrections (DBOCs) of the individual BO states arise from these discontinuities. In contrast to the well-known singularities in the first-derivative couplingsmore » at conical intersections, these singularities are non-integrable, resulting in undefined DBOC matrix elements. Though these singularities suggest that the exact molecular wave function may not have density at the conical intersection point, there is no physical basis for this constraint. Instead, the singularities are artifacts of the chosen basis of discontinuous functions. We also demonstrate that continuity of the total molecular wave function does not require continuity of the individual adiabatic nuclear wave functions. We classify nonadiabatic molecular dynamics methods according to the constraints placed on wave function continuity and analyze their formal properties. Based on our analysis, it is recommended that the DBOC be neglected when employing mixed quantum-classical methods and certain approximate quantum dynamical methods in the adiabatic representation.« less

Wave function continuity and the diagonal Born-Oppenheimer correction at conical intersections

NASA Astrophysics Data System (ADS)

Meek, Garrett A.; Levine, Benjamin G.

2016-05-01

We demonstrate that though exact in principle, the expansion of the total molecular wave function as a sum over adiabatic Born-Oppenheimer (BO) vibronic states makes inclusion of the second-derivative nonadiabatic energy term near conical intersections practically problematic. In order to construct a well-behaved molecular wave function that has density at a conical intersection, the individual BO vibronic states in the summation must be discontinuous. When the second-derivative nonadiabatic terms are added to the Hamiltonian, singularities in the diagonal BO corrections (DBOCs) of the individual BO states arise from these discontinuities. In contrast to the well-known singularities in the first-derivative couplings at conical intersections, these singularities are non-integrable, resulting in undefined DBOC matrix elements. Though these singularities suggest that the exact molecular wave function may not have density at the conical intersection point, there is no physical basis for this constraint. Instead, the singularities are artifacts of the chosen basis of discontinuous functions. We also demonstrate that continuity of the total molecular wave function does not require continuity of the individual adiabatic nuclear wave functions. We classify nonadiabatic molecular dynamics methods according to the constraints placed on wave function continuity and analyze their formal properties. Based on our analysis, it is recommended that the DBOC be neglected when employing mixed quantum-classical methods and certain approximate quantum dynamical methods in the adiabatic representation.

Novel methods for parameter-based analysis of myocardial tissue in MR images

NASA Astrophysics Data System (ADS)

Hennemuth, A.; Behrens, S.; Kuehnel, C.; Oeltze, S.; Konrad, O.; Peitgen, H.-O.

2007-03-01

The analysis of myocardial tissue with contrast-enhanced MR yields multiple parameters, which can be used to classify the examined tissue. Perfusion images are often distorted by motion, while late enhancement images are acquired with a different size and resolution. Therefore, it is common to reduce the analysis to a visual inspection, or to the examination of parameters related to the 17-segment-model proposed by the American Heart Association (AHA). As this simplification comes along with a considerable loss of information, our purpose is to provide methods for a more accurate analysis regarding topological and functional tissue features. In order to achieve this, we implemented registration methods for the motion correction of the perfusion sequence and the matching of the late enhancement information onto the perfusion image and vice versa. For the motion corrected perfusion sequence, vector images containing the voxel enhancement curves' semi-quantitative parameters are derived. The resulting vector images are combined with the late enhancement information and form the basis for the tissue examination. For the exploration of data we propose different modes: the inspection of the enhancement curves and parameter distribution in areas automatically segmented using the late enhancement information, the inspection of regions segmented in parameter space by user defined threshold intervals and the topological comparison of regions segmented with different settings. Results showed a more accurate detection of distorted regions in comparison to the AHA-model-based evaluation.

Wave function continuity and the diagonal Born-Oppenheimer correction at conical intersections.

PubMed

Meek, Garrett A; Levine, Benjamin G

2016-05-14

We demonstrate that though exact in principle, the expansion of the total molecular wave function as a sum over adiabatic Born-Oppenheimer (BO) vibronic states makes inclusion of the second-derivative nonadiabatic energy term near conical intersections practically problematic. In order to construct a well-behaved molecular wave function that has density at a conical intersection, the individual BO vibronic states in the summation must be discontinuous. When the second-derivative nonadiabatic terms are added to the Hamiltonian, singularities in the diagonal BO corrections (DBOCs) of the individual BO states arise from these discontinuities. In contrast to the well-known singularities in the first-derivative couplings at conical intersections, these singularities are non-integrable, resulting in undefined DBOC matrix elements. Though these singularities suggest that the exact molecular wave function may not have density at the conical intersection point, there is no physical basis for this constraint. Instead, the singularities are artifacts of the chosen basis of discontinuous functions. We also demonstrate that continuity of the total molecular wave function does not require continuity of the individual adiabatic nuclear wave functions. We classify nonadiabatic molecular dynamics methods according to the constraints placed on wave function continuity and analyze their formal properties. Based on our analysis, it is recommended that the DBOC be neglected when employing mixed quantum-classical methods and certain approximate quantum dynamical methods in the adiabatic representation.

Data preprocessing methods of FT-NIR spectral data for the classification cooking oil

NASA Astrophysics Data System (ADS)

Ruah, Mas Ezatul Nadia Mohd; Rasaruddin, Nor Fazila; Fong, Sim Siong; Jaafar, Mohd Zuli

2014-12-01

This recent work describes the data pre-processing method of FT-NIR spectroscopy datasets of cooking oil and its quality parameters with chemometrics method. Pre-processing of near-infrared (NIR) spectral data has become an integral part of chemometrics modelling. Hence, this work is dedicated to investigate the utility and effectiveness of pre-processing algorithms namely row scaling, column scaling and single scaling process with Standard Normal Variate (SNV). The combinations of these scaling methods have impact on exploratory analysis and classification via Principle Component Analysis plot (PCA). The samples were divided into palm oil and non-palm cooking oil. The classification model was build using FT-NIR cooking oil spectra datasets in absorbance mode at the range of 4000cm-1-14000cm-1. Savitzky Golay derivative was applied before developing the classification model. Then, the data was separated into two sets which were training set and test set by using Duplex method. The number of each class was kept equal to 2/3 of the class that has the minimum number of sample. Then, the sample was employed t-statistic as variable selection method in order to select which variable is significant towards the classification models. The evaluation of data pre-processing were looking at value of modified silhouette width (mSW), PCA and also Percentage Correctly Classified (%CC). The results show that different data processing strategies resulting to substantial amount of model performances quality. The effects of several data pre-processing i.e. row scaling, column standardisation and single scaling process with Standard Normal Variate indicated by mSW and %CC. At two PCs model, all five classifier gave high %CC except Quadratic Distance Analysis.

Field trial of applicability of lot quality assurance sampling survey method for rapid assessment of prevalence of active trachoma.

PubMed Central

Myatt, Mark; Limburg, Hans; Minassian, Darwin; Katyola, Damson

2003-01-01

OBJECTIVE: To test the applicability of lot quality assurance sampling (LQAS) for the rapid assessment of the prevalence of active trachoma. METHODS: Prevalence of active trachoma in six communities was found by examining all children aged 2-5 years. Trial surveys were conducted in these communities. A sampling plan appropriate for classifying communities with prevalences < or =20% and > or =40% was applied to the survey data. Operating characteristic and average sample number curves were plotted, and screening test indices were calculated. The ability of LQAS to provide a three-class classification system was investigated. FINDINGS: Ninety-six trial surveys were conducted. All communities with prevalences < or =20% and > or =40% were identified correctly. The method discriminated between communities with prevalences < or =30% and >30%, with sensitivity of 98% (95% confidence interval (CI)=88.2-99.9%), specificity of 84.4% (CI=69.9-93.0%), positive predictive value of 87.7% (CI=75.7-94.5%), negative predictive value of 97.4% (CI=84.9-99.9%), and accuracy of 91.7% (CI=83.8-96.1%). Agreement between the three prevalence classes and survey classifications was 84.4% (CI=75.2-90.7%). The time needed to complete the surveys was consistent with the need to complete a survey in one day. CONCLUSION: Lot quality assurance sampling provides a method of classifying communities according to the prevalence of active trachoma. It merits serious consideration as a replacement for the assessment of the prevalence of active trachoma with the currently used trachoma rapid assessment method. It may be extended to provide a multi-class classification method. PMID:14997240

Influence of handling-relevant factors on the behaviour of a novel calculus-detection device.

PubMed

Meissner, Grit; Oehme, Bernd; Strackeljan, Jens; Kocher, Thomas

2005-03-01

The aim of periodontal therapy is always the complete debridement of root surfaces with the removal of calculus and without damaging cementum. We have recently demonstrated the feasibility of a surface recognition device that discriminates dental surfaces by mathematical analysis of reflected ultrasound waves. This principle should enable the construction of calculus detecting ultrasonic device. Pre-clinical test results are presented here. An impulse generator, coupled to a conventional piezo-driven ultrasonic scaler, sends signals to the cementum via the tip of an ultrasound device. The oscillation signal reflected from the surface contains the information necessary to analyse its characteristics. In order to discriminate different surfaces, learning sets were generated from 70 extracted teeth using standardized tip angle/lateral force combinations. The complete device was then used to classify root surfaces unknown to the system. About 80% of enamel and cementum was correctly identified in vivo (sensitivity: 75%, specificity: 82%). The surface discrimination method was not influenced by the application conditions examined. A new set of 200 tests on 10 teeth was correctly recognized in 82% of the cases (sensitivity: 87%, specificity: 76%). It was shown in vitro that the tooth surface recognition system is able to function correctly, independent of the lateral forces and the tip angle of the instrument. Copyright 2005 Blackwell Munksgaard.

Classification of time-of-flight secondary ion mass spectrometry spectra from complex Cu-Fe sulphides by principal component analysis and artificial neural networks.

PubMed

Kalegowda, Yogesh; Harmer, Sarah L

2013-01-08

Artificial neural network (ANN) and a hybrid principal component analysis-artificial neural network (PCA-ANN) classifiers have been successfully implemented for classification of static time-of-flight secondary ion mass spectrometry (ToF-SIMS) mass spectra collected from complex Cu-Fe sulphides (chalcopyrite, bornite, chalcocite and pyrite) at different flotation conditions. ANNs are very good pattern classifiers because of: their ability to learn and generalise patterns that are not linearly separable; their fault and noise tolerance capability; and high parallelism. In the first approach, fragments from the whole ToF-SIMS spectrum were used as input to the ANN, the model yielded high overall correct classification rates of 100% for feed samples, 88% for conditioned feed samples and 91% for Eh modified samples. In the second approach, the hybrid pattern classifier PCA-ANN was integrated. PCA is a very effective multivariate data analysis tool applied to enhance species features and reduce data dimensionality. Principal component (PC) scores which accounted for 95% of the raw spectral data variance, were used as input to the ANN, the model yielded high overall correct classification rates of 88% for conditioned feed samples and 95% for Eh modified samples. Copyright © 2012 Elsevier B.V. All rights reserved.

Authenticity assessment of banknotes using portable near infrared spectrometer and chemometrics.

PubMed

da Silva Oliveira, Vanessa; Honorato, Ricardo Saldanha; Honorato, Fernanda Araújo; Pereira, Claudete Fernandes

2018-05-01

Spectra recorded using a portable near infrared (NIR) spectrometer, Soft Independent Modeling of Class Analogy (SIMCA) and Linear Discriminant Analysis (LDA) associated to Successive Projections Algorithm (SPA) models were applied to identify counterfeit and authentic Brazilian Real (R$20, R$50 and R$100) banknotes, enabling a simple field analysis. NIR spectra (950-1650nm) were recorded from seven different areas of the banknotes (two with fluorescent ink, one over watermark, three with intaglio printing process and one over the serial numbers with typography printing). SIMCA and SPA-LDA models were built using 1st derivative preprocessed spectral data from one of the intaglio areas. For the SIMCA models, all authentic (300) banknotes were correctly classified and the counterfeits (227) were not classified. For the two classes SPA-LDA models (authentic and counterfeit currencies), all the test samples were correctly classified into their respective class. The number of selected variables by SPA varied from two to nineteen for R$20, R$50 and R$100 currencies. These results show that the use of the portable near-infrared with SIMCA or SPA-LDA models can be a completely effective, fast, and non-destructive way to identify authenticity of banknotes as well as permitting field analysis. Copyright © 2018 Elsevier B.V. All rights reserved.

Chemometric Analysis of Gas Chromatography – Mass Spectrometry Data using Fast Retention Time Alignment via a Total Ion Current Shift Function

DOE Office of Scientific and Technical Information (OSTI.GOV)

Nadeau, Jeremy S.; Wright, Bob W.; Synovec, Robert E.

2010-04-15

A critical comparison of methods for correcting severely retention time shifted gas chromatography-mass spectrometry (GC-MS) data is presented. The method reported herein is an adaptation to the Piecewise Alignment Algorithm to quickly align severely shifted one-dimensional (1D) total ion current (TIC) data, then applying these shifts to broadly align all mass channels throughout the separation, referred to as a TIC shift function (SF). The maximum shift varied from (-) 5 s in the beginning of the chromatographic separation to (+) 20 s toward the end of the separation, equivalent to a maximum shift of over 5 peak widths. Implementing themore » TIC shift function (TIC SF) prior to Fisher Ratio (F-Ratio) feature selection and then principal component analysis (PCA) was found to be a viable approach to classify complex chromatograms, that in this study were obtained from GC-MS separations of three gasoline samples serving as complex test mixtures, referred to as types C, M and S. The reported alignment algorithm via the TIC SF approach corrects for large dynamic shifting in the data as well as subtle peak-to-peak shifts. The benefits of the overall TIC SF alignment and feature selection approach were quantified using the degree-of-class separation (DCS) metric of the PCA scores plots using the type C and M samples, since they were the most similar, and thus the most challenging samples to properly classify. The DCS values showed an increase from an initial value of essentially zero for the unaligned GC-TIC data to a value of 7.9 following alignment; however, the DCS was unchanged by feature selection using F-Ratios for the GC-TIC data. The full mass spectral data provided an increase to a final DCS of 13.7 after alignment and two-dimensional (2D) F-Ratio feature selection.« less

Modelling the Impact and Cost-Effectiveness of Biomarker Tests as Compared with Pathogen-Specific Diagnostics in the Management of Undifferentiated Fever in Remote Tropical Settings

PubMed Central

Lubell, Yoel; Althaus, Thomas; Blacksell, Stuart D.; Paris, Daniel H.; Mayxay, Mayfong; Pan-Ngum, Wirichada; White, Lisa J.; Day, Nicholas P. J.; Newton, Paul N.

2016-01-01

Background Malaria accounts for a small fraction of febrile cases in increasingly large areas of the malaria endemic world. Point-of-care tests to improve the management of non-malarial fevers appropriate for primary care are few, consisting of either diagnostic tests for specific pathogens or testing for biomarkers of host response that indicate whether antibiotics might be required. The impact and cost-effectiveness of these approaches are relatively unexplored and methods to do so are not well-developed. Methods We model the ability of dengue and scrub typhus rapid tests to inform antibiotic treatment, as compared with testing for elevated C-Reactive Protein (CRP), a biomarker of host-inflammation. Using data on causes of fever in rural Laos, we estimate the proportion of outpatients that would be correctly classified as requiring an antibiotic and the likely cost-effectiveness of the approaches. Results Use of either pathogen-specific test slightly increased the proportion of patients correctly classified as requiring antibiotics. CRP testing was consistently superior to the pathogen-specific tests, despite heterogeneity in causes of fever. All testing strategies are likely to result in higher average costs, but only the scrub typhus and CRP tests are likely to be cost-effective when considering direct health benefits, with median cost per disability adjusted life year averted of approximately $48 USD and $94 USD, respectively. Conclusions Testing for viral infections is unlikely to be cost-effective when considering only direct health benefits to patients. Testing for prevalent bacterial pathogens can be cost-effective, having the benefit of informing not only whether treatment is required, but also as to the most appropriate antibiotic; this advantage, however, varies widely in response to heterogeneity in causes of fever. Testing for biomarkers of host inflammation is likely to be consistently cost-effective despite high heterogeneity, and can also offer substantial reductions in over-use of antimicrobials in viral infections. PMID:27027303

Purposeful Variable Selection and Stratification to Impute Missing FAST Data in Trauma Research

PubMed Central

Fuchs, Paul A.; del Junco, Deborah J.; Fox, Erin E.; Holcomb, John B.; Rahbar, Mohammad H.; Wade, Charles A.; Alarcon, Louis H.; Brasel, Karen J.; Bulger, Eileen M.; Cohen, Mitchell J.; Myers, John G.; Muskat, Peter; Phelan, Herb A.; Schreiber, Martin A.; Cotton, Bryan A.

2013-01-01

Background The Focused Assessment with Sonography for Trauma (FAST) exam is an important variable in many retrospective trauma studies. The purpose of this study was to devise an imputation method to overcome missing data for the FAST exam. Due to variability in patients’ injuries and trauma care, these data are unlikely to be missing completely at random (MCAR), raising concern for validity when analyses exclude patients with missing values. Methods Imputation was conducted under a less restrictive, more plausible missing at random (MAR) assumption. Patients with missing FAST exams had available data on alternate, clinically relevant elements that were strongly associated with FAST results in complete cases, especially when considered jointly. Subjects with missing data (32.7%) were divided into eight mutually exclusive groups based on selected variables that both described the injury and were associated with missing FAST values. Additional variables were selected within each group to classify missing FAST values as positive or negative, and correct FAST exam classification based on these variables was determined for patients with non-missing FAST values. Results Severe head/neck injury (odds ratio, OR=2.04), severe extremity injury (OR=4.03), severe abdominal injury (OR=1.94), no injury (OR=1.94), other abdominal injury (OR=0.47), other head/neck injury (OR=0.57) and other extremity injury (OR=0.45) groups had significant ORs for missing data; the other group odds ratio was not significant (OR=0.84). All 407 missing FAST values were imputed, with 109 classified as positive. Correct classification of non-missing FAST results using the alternate variables was 87.2%. Conclusions Purposeful imputation for missing FAST exams based on interactions among selected variables assessed by simple stratification may be a useful adjunct to sensitivity analysis in the evaluation of imputation strategies under different missing data mechanisms. This approach has the potential for widespread application in clinical and translational research and validation is warranted. Level of Evidence Level II Prognostic or Epidemiological PMID:23778515

Learning from label proportions in brain-computer interfaces: Online unsupervised learning with guarantees.

PubMed

Hübner, David; Verhoeven, Thibault; Schmid, Konstantin; Müller, Klaus-Robert; Tangermann, Michael; Kindermans, Pieter-Jan

2017-01-01

Using traditional approaches, a brain-computer interface (BCI) requires the collection of calibration data for new subjects prior to online use. Calibration time can be reduced or eliminated e.g., by subject-to-subject transfer of a pre-trained classifier or unsupervised adaptive classification methods which learn from scratch and adapt over time. While such heuristics work well in practice, none of them can provide theoretical guarantees. Our objective is to modify an event-related potential (ERP) paradigm to work in unison with the machine learning decoder, and thus to achieve a reliable unsupervised calibrationless decoding with a guarantee to recover the true class means. We introduce learning from label proportions (LLP) to the BCI community as a new unsupervised, and easy-to-implement classification approach for ERP-based BCIs. The LLP estimates the mean target and non-target responses based on known proportions of these two classes in different groups of the data. We present a visual ERP speller to meet the requirements of LLP. For evaluation, we ran simulations on artificially created data sets and conducted an online BCI study with 13 subjects performing a copy-spelling task. Theoretical considerations show that LLP is guaranteed to minimize the loss function similar to a corresponding supervised classifier. LLP performed well in simulations and in the online application, where 84.5% of characters were spelled correctly on average without prior calibration. The continuously adapting LLP classifier is the first unsupervised decoder for ERP BCIs guaranteed to find the optimal decoder. This makes it an ideal solution to avoid tedious calibration sessions. Additionally, LLP works on complementary principles compared to existing unsupervised methods, opening the door for their further enhancement when combined with LLP.

Prediction of skin sensitization potency using machine learning approaches.

PubMed

Zang, Qingda; Paris, Michael; Lehmann, David M; Bell, Shannon; Kleinstreuer, Nicole; Allen, David; Matheson, Joanna; Jacobs, Abigail; Casey, Warren; Strickland, Judy

2017-07-01

The replacement of animal use in testing for regulatory classification of skin sensitizers is a priority for US federal agencies that use data from such testing. Machine learning models that classify substances as sensitizers or non-sensitizers without using animal data have been developed and evaluated. Because some regulatory agencies require that sensitizers be further classified into potency categories, we developed statistical models to predict skin sensitization potency for murine local lymph node assay (LLNA) and human outcomes. Input variables for our models included six physicochemical properties and data from three non-animal test methods: direct peptide reactivity assay; human cell line activation test; and KeratinoSens™ assay. Models were built to predict three potency categories using four machine learning approaches and were validated using external test sets and leave-one-out cross-validation. A one-tiered strategy modeled all three categories of response together while a two-tiered strategy modeled sensitizer/non-sensitizer responses and then classified the sensitizers as strong or weak sensitizers. The two-tiered model using the support vector machine with all assay and physicochemical data inputs provided the best performance, yielding accuracy of 88% for prediction of LLNA outcomes (120 substances) and 81% for prediction of human test outcomes (87 substances). The best one-tiered model predicted LLNA outcomes with 78% accuracy and human outcomes with 75% accuracy. By comparison, the LLNA predicts human potency categories with 69% accuracy (60 of 87 substances correctly categorized). These results suggest that computational models using non-animal methods may provide valuable information for assessing skin sensitization potency. Copyright © 2017 John Wiley & Sons, Ltd. Copyright © 2017 John Wiley & Sons, Ltd.

Decision Making Configurations: An Alternative to the Centralization/Decentralization Conceptualization.

ERIC Educational Resources Information Center

Cullen, John B.; Perrewe, Pamela L.

1981-01-01

Used factors identified in the literature as predictors of centralization/decentralization as potential discriminating variables among several decision making configurations in university affiliated professional schools. The model developed from multiple discriminant analysis had reasonable success in classifying correctly only the decentralized…

77 FR 25732 - Tuna-Tariff-Rate Quota; the Tariff-Rate Quota for Calendar Year 2012 Tuna Classifiable Under...

Federal Register 2010, 2011, 2012, 2013, 2014

2012-05-01

... containers for Calendar Year 2012; correction. SUMMARY: U.S. Customs and Border Protection (CBP) published in... containers for Calendar Year 2012. Inadvertently, no CBP Decision Number was listed in the heading of that...

Aggression against Women by Men: Sexual and Spousal Assault.

ERIC Educational Resources Information Center

Dewhurst, Ann Marie; And Others

1992-01-01

Compared 19 sexual offenders, 22 batterers, 10 violent community comparison subjects, and 21 community comparison subjects on demographic, personality, and attitudinal variables. Discriminating variables correctly classified 75 percent of participants. Hostility toward women and depression were two best discriminating variables, suggesting that…

Classification of ipsilateral breast tumor recurrences after breast conservation therapy can predict patient prognosis and facilitate treatment planning

PubMed Central

Yi, Min; Buchholz, Thomas A.; Meric-Bernstam, Funda; Bedrosian, Isabelle; Hwang, Rosa F.; Ross, Merrick I.; Kuerer, Henry M.; Luo, Sheng; Gonzalez-Angulo, Ana M.; Buzdar, Aman U.; Symmans, W. Fraser; Feig, Barry W.; Lucci, Anthony; Huang, Eugene H.; Hunt, Kelly K.

2015-01-01

Objective To classify ipsilateral breast tumor recurrences (IBTR) as either new primary tumors (NP) or true local recurrence (TR). We utilized two different methods and compared sensitivities and specificities between them. Our goal was to determine whether distinguishing NP from TR had prognostic value. Summary Background Data After breast-conservation therapy (BCT), IBTR may be classified into two distinct types (NP and TR). Studies have attempted to classify IBTR by using tumor location, histologic subtype, DNA flow cytometry data, or gene-expression profiling data. Methods 447 (7.9%) of 5660 patients undergoing BCT from 1970 to 2005 experienced IBTR. Clinical data from 397 patients were available for review. We classified IBTRs as NP or TR on the basis of either tumor location and histologic subtype (method 1) or tumor location, histologic subtype, estrogen receptor (ER) status and human epidermal growth factor receptor 2 (HER-2) status (method 2). Kaplan-Meier curves and log-rank tests were used to evaluate overall and disease-specific survival (DSS) differences between the two groups. Classification methods were validated by calculating sensitivity and specificity values using a Bayesian method. Results Of 397 patients, 196 (49.4%) were classified as NP by method 1 and 212 (53.4%) were classified as NP by method 2. The sensitivity and specificity values were 0.812 and 0.867 for method 1 and 0.870 and 0.800 for method 2, respectively. Regardless of method used, patients classified as NP developed contralateral breast carcinoma more often but had better 10-year overall and DSS rates than those classified as TR. Patients with TR were more likely to develop metastatic disease after IBTR. Conclusion IBTR classified as TR and NP had clinically different features, suggesting that classifying IBTR may provide clinically significant data for the management of IBTR. PMID:21209588

Ifcwall Reconstruction from Unstructured Point Clouds

NASA Astrophysics Data System (ADS)

Bassier, M.; Klein, R.; Van Genechten, B.; Vergauwen, M.

2018-05-01

The automated reconstruction of Building Information Modeling (BIM) objects from point cloud data is still ongoing research. A key aspect is the creation of accurate wall geometry as it forms the basis for further reconstruction of objects in a BIM. After segmenting and classifying the initial point cloud, the labelled segments are processed and the wall topology is reconstructed. However, the preocedure is challenging due to noise, occlusions and the complexity of the input data.In this work, a method is presented to automatically reconstruct consistent wall geometry from point clouds. More specifically, the use of room information is proposed to aid the wall topology creation. First, a set of partial walls is constructed based on classified planar primitives. Next, the rooms are identified using the retrieved wall information along with the floors and ceilings. The wall topology is computed by the intersection of the partial walls conditioned on the room information. The final wall geometry is defined by creating IfcWallStandardCase objects conform the IFC4 standard. The result is a set of walls according to the as-built conditions of a building. The experiments prove that the used method is a reliable framework for wall reconstruction from unstructured point cloud data. Also, the implementation of room information reduces the rate of false positives for the wall topology. Given the walls, ceilings and floors, 94% of the rooms is correctly identified. A key advantage of the proposed method is that it deals with complex rooms and is not bound to single storeys.

Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus Mykiss) Classification Using Image-Based Features

PubMed Central

Císař, Petr; Labbé, Laurent; Souček, Pavel; Pelissier, Pablo; Kerneis, Thierry

2018-01-01

The main aim of this study was to develop a new objective method for evaluating the impacts of different diets on the live fish skin using image-based features. In total, one-hundred and sixty rainbow trout (Oncorhynchus mykiss) were fed either a fish-meal based diet (80 fish) or a 100% plant-based diet (80 fish) and photographed using consumer-grade digital camera. Twenty-three colour features and four texture features were extracted. Four different classification methods were used to evaluate fish diets including Random forest (RF), Support vector machine (SVM), Logistic regression (LR) and k-Nearest neighbours (k-NN). The SVM with radial based kernel provided the best classifier with correct classification rate (CCR) of 82% and Kappa coefficient of 0.65. Although the both LR and RF methods were less accurate than SVM, they achieved good classification with CCR 75% and 70% respectively. The k-NN was the least accurate (40%) classification model. Overall, it can be concluded that consumer-grade digital cameras could be employed as the fast, accurate and non-invasive sensor for classifying rainbow trout based on their diets. Furthermore, these was a close association between image-based features and fish diet received during cultivation. These procedures can be used as non-invasive, accurate and precise approaches for monitoring fish status during the cultivation by evaluating diet’s effects on fish skin. PMID:29596375

Comparative Performance Analysis of Support Vector Machine, Random Forest, Logistic Regression and k-Nearest Neighbours in Rainbow Trout (Oncorhynchus Mykiss) Classification Using Image-Based Features.

PubMed

Saberioon, Mohammadmehdi; Císař, Petr; Labbé, Laurent; Souček, Pavel; Pelissier, Pablo; Kerneis, Thierry

2018-03-29

The main aim of this study was to develop a new objective method for evaluating the impacts of different diets on the live fish skin using image-based features. In total, one-hundred and sixty rainbow trout ( Oncorhynchus mykiss ) were fed either a fish-meal based diet (80 fish) or a 100% plant-based diet (80 fish) and photographed using consumer-grade digital camera. Twenty-three colour features and four texture features were extracted. Four different classification methods were used to evaluate fish diets including Random forest (RF), Support vector machine (SVM), Logistic regression (LR) and k -Nearest neighbours ( k -NN). The SVM with radial based kernel provided the best classifier with correct classification rate (CCR) of 82% and Kappa coefficient of 0.65. Although the both LR and RF methods were less accurate than SVM, they achieved good classification with CCR 75% and 70% respectively. The k -NN was the least accurate (40%) classification model. Overall, it can be concluded that consumer-grade digital cameras could be employed as the fast, accurate and non-invasive sensor for classifying rainbow trout based on their diets. Furthermore, these was a close association between image-based features and fish diet received during cultivation. These procedures can be used as non-invasive, accurate and precise approaches for monitoring fish status during the cultivation by evaluating diet's effects on fish skin.

Integration of RNA-Seq and RPPA data for survival time prediction in cancer patients.

PubMed

Isik, Zerrin; Ercan, Muserref Ece

2017-10-01

Integration of several types of patient data in a computational framework can accelerate the identification of more reliable biomarkers, especially for prognostic purposes. This study aims to identify biomarkers that can successfully predict the potential survival time of a cancer patient by integrating the transcriptomic (RNA-Seq), proteomic (RPPA), and protein-protein interaction (PPI) data. The proposed method -RPBioNet- employs a random walk-based algorithm that works on a PPI network to identify a limited number of protein biomarkers. Later, the method uses gene expression measurements of the selected biomarkers to train a classifier for the survival time prediction of patients. RPBioNet was applied to classify kidney renal clear cell carcinoma (KIRC), glioblastoma multiforme (GBM), and lung squamous cell carcinoma (LUSC) patients based on their survival time classes (long- or short-term). The RPBioNet method correctly identified the survival time classes of patients with between 66% and 78% average accuracy for three data sets. RPBioNet operates with only 20 to 50 biomarkers and can achieve on average 6% higher accuracy compared to the closest alternative method, which uses only RNA-Seq data in the biomarker selection. Further analysis of the most predictive biomarkers highlighted genes that are common for both cancer types, as they may be driver proteins responsible for cancer progression. The novelty of this study is the integration of a PPI network with mRNA and protein expression data to identify more accurate prognostic biomarkers that can be used for clinical purposes in the future. Copyright © 2017 Elsevier Ltd. All rights reserved.

Quantifying human disturbance in watersheds: Variable selection and performance of a GIS-based disturbance index for predicting the biological condition of perennial streams

USGS Publications Warehouse

Falcone, James A.; Carlisle, Daren M.; Weber, Lisa C.

2010-01-01

Characterizing the relative severity of human disturbance in watersheds is often part of stream assessments and is frequently done with the aid of Geographic Information System (GIS)-derived data. However, the choice of variables and how they are used to quantify disturbance are often subjective. In this study, we developed a number of disturbance indices by testing sets of variables, scoring methods, and weightings of 33 potential disturbance factors derived from readily available GIS data. The indices were calibrated using 770 watersheds located in the western United States for which the severity of disturbance had previously been classified from detailed local data by the United States Environmental Protection Agency (USEPA) Environmental Monitoring and Assessment Program (EMAP). The indices were calibrated by determining which variable or variable combinations and aggregation method best differentiated between least- and most-disturbed sites. Indices composed of several variables performed better than any individual variable, and best results came from a threshold method of scoring using six uncorrelated variables: housing unit density, road density, pesticide application, dam storage, land cover along a mainstem buffer, and distance to nearest canal/pipeline. The final index was validated with 192 withheld watersheds and correctly classified about two-thirds (68%) of least- and most-disturbed sites. These results provide information about the potential for using a disturbance index as a screening tool for a priori ranking of watersheds at a regional/national scale, and which landscape variables and methods of combination may be most helpful in doing so.

Evaluation of artificial neural network algorithms for predicting METs and activity type from accelerometer data: validation on an independent sample.

PubMed

Freedson, Patty S; Lyden, Kate; Kozey-Keadle, Sarah; Staudenmayer, John

2011-12-01

Previous work from our laboratory provided a "proof of concept" for use of artificial neural networks (nnets) to estimate metabolic equivalents (METs) and identify activity type from accelerometer data (Staudenmayer J, Pober D, Crouter S, Bassett D, Freedson P, J Appl Physiol 107: 1330-1307, 2009). The purpose of this study was to develop new nnets based on a larger, more diverse, training data set and apply these nnet prediction models to an independent sample to evaluate the robustness and flexibility of this machine-learning modeling technique. The nnet training data set (University of Massachusetts) included 277 participants who each completed 11 activities. The independent validation sample (n = 65) (University of Tennessee) completed one of three activity routines. Criterion measures were 1) measured METs assessed using open-circuit indirect calorimetry; and 2) observed activity to identify activity type. The nnet input variables included five accelerometer count distribution features and the lag-1 autocorrelation. The bias and root mean square errors for the nnet MET trained on University of Massachusetts and applied to University of Tennessee were +0.32 and 1.90 METs, respectively. Seventy-seven percent of the activities were correctly classified as sedentary/light, moderate, or vigorous intensity. For activity type, household and locomotion activities were correctly classified by the nnet activity type 98.1 and 89.5% of the time, respectively, and sport was correctly classified 23.7% of the time. Use of this machine-learning technique operates reasonably well when applied to an independent sample. We propose the creation of an open-access activity dictionary, including accelerometer data from a broad array of activities, leading to further improvements in prediction accuracy for METs, activity intensity, and activity type.

Optical differentiation between malignant and benign lymphadenopathy by grey scale texture analysis of endobronchial ultrasound convex probe images.

PubMed

Nguyen, Phan; Bashirzadeh, Farzad; Hundloe, Justin; Salvado, Olivier; Dowson, Nicholas; Ware, Robert; Masters, Ian Brent; Bhatt, Manoj; Kumar, Aravind Ravi; Fielding, David

2012-03-01

Morphologic and sonographic features of endobronchial ultrasound (EBUS) convex probe images are helpful in predicting metastatic lymph nodes. Grey scale texture analysis is a well-established methodology that has been applied to ultrasound images in other fields of medicine. The aim of this study was to determine if this methodology could differentiate between benign and malignant lymphadenopathy of EBUS images. Lymph nodes from digital images of EBUS procedures were manually mapped to obtain a region of interest and were analyzed in a prediction set. The regions of interest were analyzed for the following grey scale texture features in MATLAB (version 7.8.0.347 [R2009a]): mean pixel value, difference between maximal and minimal pixel value, SEM pixel value, entropy, correlation, energy, and homogeneity. Significant grey scale texture features were used to assess a validation set compared with fluoro-D-glucose (FDG)-PET-CT scan findings where available. Fifty-two malignant nodes and 48 benign nodes were in the prediction set. Malignant nodes had a greater difference in the maximal and minimal pixel values, SEM pixel value, entropy, and correlation, and a lower energy (P < .0001 for all values). Fifty-one lymph nodes were in the validation set; 44 of 51 (86.3%) were classified correctly. Eighteen of these lymph nodes also had FDG-PET-CT scan assessment, which correctly classified 14 of 18 nodes (77.8%), compared with grey scale texture analysis, which correctly classified 16 of 18 nodes (88.9%). Grey scale texture analysis of EBUS convex probe images can be used to differentiate malignant and benign lymphadenopathy. Preliminary results are comparable to FDG-PET-CT scan.

Dexamethasone Stimulated Gene Expression in Peripheral Blood is a Sensitive Marker for Glucocorticoid Receptor Resistance in Depressed Patients

PubMed Central

Menke, Andreas; Arloth, Janine; Pütz, Benno; Weber, Peter; Klengel, Torsten; Mehta, Divya; Gonik, Mariya; Rex-Haffner, Monika; Rubel, Jennifer; Uhr, Manfred; Lucae, Susanne; Deussing, Jan M; Müller-Myhsok, Bertram; Holsboer, Florian; Binder, Elisabeth B

2012-01-01

Although gene expression profiles in peripheral blood in major depression are not likely to identify genes directly involved in the pathomechanism of affective disorders, they may serve as biomarkers for this disorder. As previous studies using baseline gene expression profiles have provided mixed results, our approach was to use an in vivo dexamethasone challenge test and to compare glucocorticoid receptor (GR)-mediated changes in gene expression between depressed patients and healthy controls. Whole genome gene expression data (baseline and following GR-stimulation with 1.5 mg dexamethasone p.o.) from two independent cohorts were analyzed to identify gene expression pattern that would predict case and control status using a training (N=18 cases/18 controls) and a test cohort (N=11/13). Dexamethasone led to reproducible regulation of 2670 genes in controls and 1151 transcripts in cases. Several genes, including FKBP5 and DUSP1, previously associated with the pathophysiology of major depression, were found to be reliable markers of GR-activation. Using random forest analyses for classification, GR-stimulated gene expression outperformed baseline gene expression as a classifier for case and control status with a correct classification of 79.1 vs 41.6% in the test cohort. GR-stimulated gene expression performed best in dexamethasone non-suppressor patients (88.7% correctly classified with 100% sensitivity), but also correctly classified 77.3% of the suppressor patients (76.7% sensitivity), when using a refined set of 19 genes. Our study suggests that in vivo stimulated gene expression in peripheral blood cells could be a promising molecular marker of altered GR-functioning, an important component of the underlying pathology, in patients suffering from depressive episodes. PMID:22237309

Classification of Error Related Brain Activity in an Auditory Identification Task with Conditions of Varying Complexity

NASA Astrophysics Data System (ADS)

Kakkos, I.; Gkiatis, K.; Bromis, K.; Asvestas, P. A.; Karanasiou, I. S.; Ventouras, E. M.; Matsopoulos, G. K.

2017-11-01

The detection of an error is the cognitive evaluation of an action outcome that is considered undesired or mismatches an expected response. Brain activity during monitoring of correct and incorrect responses elicits Event Related Potentials (ERPs) revealing complex cerebral responses to deviant sensory stimuli. Development of accurate error detection systems is of great importance both concerning practical applications and in investigating the complex neural mechanisms of decision making. In this study, data are used from an audio identification experiment that was implemented with two levels of complexity in order to investigate neurophysiological error processing mechanisms in actors and observers. To examine and analyse the variations of the processing of erroneous sensory information for each level of complexity we employ Support Vector Machines (SVM) classifiers with various learning methods and kernels using characteristic ERP time-windowed features. For dimensionality reduction and to remove redundant features we implement a feature selection framework based on Sequential Forward Selection (SFS). The proposed method provided high accuracy in identifying correct and incorrect responses both for actors and for observers with mean accuracy of 93% and 91% respectively. Additionally, computational time was reduced and the effects of the nesting problem usually occurring in SFS of large feature sets were alleviated.

Inferring Temperature Inversions in Hot Jupiters Via Spitzer Emission Spectroscopy

NASA Astrophysics Data System (ADS)

Garhart, Emily; Deming, Drake; Mandell, Avi

2016-10-01

We present a systematic study of 35 hot Jupiter secondary eclipses, including 16 hot Jupiters never before characterized via emission, observed at the 3.6 μm and 4.5 μm bandpasses of Warm Spitzer in order to classify their atmospheric structure, namely, the existence of temperature inversions. This is a robust study in that these planets orbit stars with a wide range of compositions, temperatures, and activity levels. This diverse sample allows us to investigate the source of planetary temperature inversions, specifically, its correlation with stellar irradiance and magnetic activity. We correct for systematic and intra-pixel sensitivity effects with a pixel level decorrelation (PLD) method described in Deming et al. (2015). The relationship between eclipse depths and a best-fit blackbody function versus stellar activity, a method described in Knutson et al. (2010), will ultimately enable us to appraise the current hypotheses of temperature inversions.

Detection of text strings from mixed text/graphics images

NASA Astrophysics Data System (ADS)

Tsai, Chien-Hua; Papachristou, Christos A.

2000-12-01

A robust system for text strings separation from mixed text/graphics images is presented. Based on a union-find (region growing) strategy the algorithm is thus able to classify the text from graphics and adapts to changes in document type, language category (e.g., English, Chinese and Japanese), text font style and size, and text string orientation within digital images. In addition, it allows for a document skew that usually occurs in documents, without skew correction prior to discrimination while these proposed methods such a projection profile or run length coding are not always suitable for the condition. The method has been tested with a variety of printed documents from different origins with one common set of parameters, and the experimental results of the performance of the algorithm in terms of computational efficiency are demonstrated by using several tested images from the evaluation.

Applying a statistical PTB detection procedure to complement the gold standard.

PubMed

Noor, Norliza Mohd; Yunus, Ashari; Bakar, S A R Abu; Hussin, Amran; Rijal, Omar Mohd

2011-04-01

This paper investigates a novel statistical discrimination procedure to detect PTB when the gold standard requirement is taken into consideration. Archived data were used to establish two groups of patients which are the control and test group. The control group was used to develop the statistical discrimination procedure using four vectors of wavelet coefficients as feature vectors for the detection of pulmonary tuberculosis (PTB), lung cancer (LC), and normal lung (NL). This discrimination procedure was investigated using the test group where the number of sputum positive and sputum negative cases that were correctly classified as PTB cases were noted. The proposed statistical discrimination method is able to detect PTB patients and LC with high true positive fraction. The method is also able to detect PTB patients that are sputum negative and therefore may be used as a complement to the gold standard. Copyright © 2010 Elsevier Ltd. All rights reserved.

A general system for automatic biomedical image segmentation using intensity neighborhoods.

PubMed

Chen, Cheng; Ozolek, John A; Wang, Wei; Rohde, Gustavo K

2011-01-01

Image segmentation is important with applications to several problems in biology and medicine. While extensively researched, generally, current segmentation methods perform adequately in the applications for which they were designed, but often require extensive modifications or calibrations before being used in a different application. We describe an approach that, with few modifications, can be used in a variety of image segmentation problems. The approach is based on a supervised learning strategy that utilizes intensity neighborhoods to assign each pixel in a test image its correct class based on training data. We describe methods for modeling rotations and variations in scales as well as a subset selection for training the classifiers. We show that the performance of our approach in tissue segmentation tasks in magnetic resonance and histopathology microscopy images, as well as nuclei segmentation from fluorescence microscopy images, is similar to or better than several algorithms specifically designed for each of these applications.

Infrared thermography based on artificial intelligence as a screening method for carpal tunnel syndrome diagnosis.

PubMed

Jesensek Papez, B; Palfy, M; Mertik, M; Turk, Z

2009-01-01

This study further evaluated a computer-based infrared thermography (IRT) system, which employs artificial neural networks for the diagnosis of carpal tunnel syndrome (CTS) using a large database of 502 thermal images of the dorsal and palmar side of 132 healthy and 119 pathological hands. It confirmed the hypothesis that the dorsal side of the hand is of greater importance than the palmar side when diagnosing CTS thermographically. Using this method it was possible correctly to classify 72.2% of all hands (healthy and pathological) based on dorsal images and > 80% of hands when only severely affected and healthy hands were considered. Compared with the gold standard electromyographic diagnosis of CTS, IRT cannot be recommended as an adequate diagnostic tool when exact severity level diagnosis is required, however we conclude that IRT could be used as a screening tool for severe cases in populations with high ergonomic risk factors of CTS.

Comparison of projection skills of deterministic ensemble methods using pseudo-simulation data generated from multivariate Gaussian distribution

NASA Astrophysics Data System (ADS)

Oh, Seok-Geun; Suh, Myoung-Seok

2017-07-01

The projection skills of five ensemble methods were analyzed according to simulation skills, training period, and ensemble members, using 198 sets of pseudo-simulation data (PSD) produced by random number generation assuming the simulated temperature of regional climate models. The PSD sets were classified into 18 categories according to the relative magnitude of bias, variance ratio, and correlation coefficient, where each category had 11 sets (including 1 truth set) with 50 samples. The ensemble methods used were as follows: equal weighted averaging without bias correction (EWA_NBC), EWA with bias correction (EWA_WBC), weighted ensemble averaging based on root mean square errors and correlation (WEA_RAC), WEA based on the Taylor score (WEA_Tay), and multivariate linear regression (Mul_Reg). The projection skills of the ensemble methods improved generally as compared with the best member for each category. However, their projection skills are significantly affected by the simulation skills of the ensemble member. The weighted ensemble methods showed better projection skills than non-weighted methods, in particular, for the PSD categories having systematic biases and various correlation coefficients. The EWA_NBC showed considerably lower projection skills than the other methods, in particular, for the PSD categories with systematic biases. Although Mul_Reg showed relatively good skills, it showed strong sensitivity to the PSD categories, training periods, and number of members. On the other hand, the WEA_Tay and WEA_RAC showed relatively superior skills in both the accuracy and reliability for all the sensitivity experiments. This indicates that WEA_Tay and WEA_RAC are applicable even for simulation data with systematic biases, a short training period, and a small number of ensemble members.

Name that tune: decoding music from the listening brain.

PubMed

Schaefer, Rebecca S; Farquhar, Jason; Blokland, Yvonne; Sadakata, Makiko; Desain, Peter

2011-05-15

In the current study we use electroencephalography (EEG) to detect heard music from the brain signal, hypothesizing that the time structure in music makes it especially suitable for decoding perception from EEG signals. While excluding music with vocals, we classified the perception of seven different musical fragments of about three seconds, both individually and cross-participants, using only time domain information (the event-related potential, ERP). The best individual results are 70% correct in a seven-class problem while using single trials, and when using multiple trials we achieve 100% correct after six presentations of the stimulus. When classifying across participants, a maximum rate of 53% was reached, supporting a general representation of each musical fragment over participants. While for some music stimuli the amplitude envelope correlated well with the ERP, this was not true for all stimuli. Aspects of the stimulus that may contribute to the differences between the EEG responses to the pieces of music are discussed. Copyright © 2010 Elsevier Inc. All rights reserved.

Indonesian palm civet coffee discrimination using UV-visible spectroscopy and several chemometrics methods

NASA Astrophysics Data System (ADS)

Yulia, M.; Suhandy, D.

2017-05-01

Indonesian palm civet coffee or kopi luwak (Indonesian words for coffee and palm civet) is well known as the world’s priciest and rarest coffee. To protect the authenticity of luwak coffee and protect consumer from luwak coffee adulteration, it is very important to develop a simple and inexpensive method to discriminate between civet and non-civet coffee. The discrimination between civet and non-civet coffee in ground roasted (powder) samples is very challenging since it is very difficult to distinguish between the two by using conventional method. In this research, the use of UV-Visible spectra combined with two chemometric methods, SIMCA and PLS-DA, was evaluated to discriminate civet and non-civet ground coffee samples. The spectral data of civet and non-civet coffee were acquired using UV-Vis spectrometer (Genesys™ 10S UV-Vis, Thermo Scientific, USA). The result shows that using both supervised discrimination methods: SIMCA and PLS-DA, all samples were correctly classified into their corresponding classes with 100% rate for accuracy, sensitivity and specificity, respectively.

Development of Matched (migratory Analytical Time Change Easy Detection) Method for Satellite-Tracked Migratory Birds

NASA Astrophysics Data System (ADS)

Doko, Tomoko; Chen, Wenbo; Higuchi, Hiroyoshi

2016-06-01

Satellite tracking technology has been used to reveal the migration patterns and flyways of migratory birds. In general, bird migration can be classified according to migration status. These statuses include the wintering period, spring migration, breeding period, and autumn migration. To determine the migration status, periods of these statuses should be individually determined, but there is no objective method to define 'a threshold date' for when an individual bird changes its status. The research objective is to develop an effective and objective method to determine threshold dates of migration status based on satellite-tracked data. The developed method was named the "MATCHED (Migratory Analytical Time Change Easy Detection) method". In order to demonstrate the method, data acquired from satellite-tracked Tundra Swans were used. MATCHED method is composed by six steps: 1) dataset preparation, 2) time frame creation, 3) automatic identification, 4) visualization of change points, 5) interpretation, and 6) manual correction. Accuracy was tested. In general, MATCHED method was proved powerful to identify the change points between migration status as well as stopovers. Nevertheless, identifying "exact" threshold dates is still challenging. Limitation and application of this method was discussed.

On the design of classifiers for crop inventories

NASA Technical Reports Server (NTRS)

Heydorn, R. P.; Takacs, H. C.

1986-01-01

Crop proportion estimators that use classifications of satellite data to correct, in an additive way, a given estimate acquired from ground observations are discussed. A linear version of these estimators is optimal, in terms of minimum variance, when the regression of the ground observations onto the satellite observations in linear. When this regression is not linear, but the reverse regression (satellite observations onto ground observations) is linear, the estimator is suboptimal but still has certain appealing variance properties. In this paper expressions are derived for those regressions which relate the intercepts and slopes to conditional classification probabilities. These expressions are then used to discuss the question of classifier designs that can lead to low-variance crop proportion estimates. Variance expressions for these estimates in terms of classifier omission and commission errors are also derived.

Ultrasonic Signal Processing for Structural Health Monitoring

NASA Astrophysics Data System (ADS)

Michaels, Jennifer E.; Michaels, Thomas E.

2004-02-01

Permanently mounted ultrasonic sensors are a key component of systems under development for structural health monitoring. Signal processing plays a critical role in the viability of such systems due to the difficulty in interpreting signals received from structures of complex geometry. This paper describes a differential feature-based approach to classifying signal changes as either "environmental" or "structural". Data are presented from piezoelectric discs bonded to an aluminum specimen subjected to both environmental changes and introduction of artificial defects. The classifier developed as part of this study was able to correctly identify artificial defects that were not part of the initial training and evaluation data sets. Central to the success of the classifier was the use of the Short Time Cross Correlation to measure coherency between the signal and reference as a function of time.

Detection and diagnosis of colitis on computed tomography using deep convolutional neural networks.

PubMed

Liu, Jiamin; Wang, David; Lu, Le; Wei, Zhuoshi; Kim, Lauren; Turkbey, Evrim B; Sahiner, Berkman; Petrick, Nicholas A; Summers, Ronald M

2017-09-01

Colitis refers to inflammation of the inner lining of the colon that is frequently associated with infection and allergic reactions. In this paper, we propose deep convolutional neural networks methods for lesion-level colitis detection and a support vector machine (SVM) classifier for patient-level colitis diagnosis on routine abdominal CT scans. The recently developed Faster Region-based Convolutional Neural Network (Faster RCNN) is utilized for lesion-level colitis detection. For each 2D slice, rectangular region proposals are generated by region proposal networks (RPN). Then, each region proposal is jointly classified and refined by a softmax classifier and bounding-box regressor. Two convolutional neural networks, eight layers of ZF net and 16 layers of VGG net are compared for colitis detection. Finally, for each patient, the detections on all 2D slices are collected and a SVM classifier is applied to develop a patient-level diagnosis. We trained and evaluated our method with 80 colitis patients and 80 normal cases using 4 × 4-fold cross validation. For lesion-level colitis detection, with ZF net, the mean of average precisions (mAP) were 48.7% and 50.9% for RCNN and Faster RCNN, respectively. The detection system achieved sensitivities of 51.4% and 54.0% at two false positives per patient for RCNN and Faster RCNN, respectively. With VGG net, Faster RCNN increased the mAP to 56.9% and increased the sensitivity to 58.4% at two false positive per patient. For patient-level colitis diagnosis, with ZF net, the average areas under the ROC curve (AUC) were 0.978 ± 0.009 and 0.984 ± 0.008 for RCNN and Faster RCNN method, respectively. The difference was not statistically significant with P = 0.18. At the optimal operating point, the RCNN method correctly identified 90.4% (72.3/80) of the colitis patients and 94.0% (75.2/80) of normal cases. The sensitivity improved to 91.6% (73.3/80) and the specificity improved to 95.0% (76.0/80) for the Faster RCNN method. With VGG net, Faster RCNN increased the AUC to 0.986 ± 0.007 and increased the diagnosis sensitivity to 93.7% (75.0/80) and specificity was unchanged at 95.0% (76.0/80). Colitis detection and diagnosis by deep convolutional neural networks is accurate and promising for future clinical application. Published 2017. This article is a U.S. Government work and is in the public domain in the USA.

Automatic image hanging protocol for chest radiographs in PACS.

PubMed

Luo, Hui; Hao, Wei; Foos, David H; Cornelius, Craig W

2006-04-01

Chest radiography is one of the most widely used techniques in diagnostic imaging. It comprises at least one-third of all diagnostic radiographic procedures in hospitals. However, in the picture archive and communication system, images are often stored with the projection and orientation unknown or mislabeled, which causes inefficiency for radiologists' interpretation. To address this problem, an automatic hanging protocol for chest radiographs is presented. The method targets the most effective region in a chest radiograph, and extracts a set of size-, rotation-, and translation-invariant features from it. Then, a well-trained classifier is used to recognize the projection. The orientation of the radiograph is later identified by locating the neck, heart, and abdomen positions in the radiographs. Initial experiments are performed on the radiographs collected from daily routine chest exams in hospitals and show promising results. Using the presented protocol, 98.2% of all cases could be hung correctly on projection view (without protocol, 62%), and 96.1% had correct orientation (without protocol, 75%). A workflow study on the protocol also demonstrates a significant improvement in efficiency for image display.

Exploring "psychic transparency" during pregnancy: a mixed-methods approach.

PubMed

Oriol, Cécile; Tordjman, Sylvie; Dayan, Jacques; Poulain, Patrice; Rosenblum, Ouriel; Falissard, Bruno; Dindoyal, Asha; Naudet, Florian

2016-08-12

Psychic transparency is described as a psychic crisis occurring during pregnancy. The objective was to test if it was clinically detectable. Seven primiparous and seven nulliparous subjects were recorded during 5 min of spontaneous speech about their dreams. 25 raters from five groups (psychoanalysts, psychiatrists, general practitioners, pregnant women and medical students) listened to the audiotapes. They were asked to rate the probability of the women being pregnant or not. Their ability to discriminate the primiparous women was tested. The probability of being identified correctly or not was calculated for each woman. A qualitative analysis of the speech samples was performed. No group of rater was able to correctly classify pregnant and non-pregnant women. However, the raters' choices were not completely random. The wish to be pregnant or to have a baby could be linked to a primiparous classification whereas job priorities could be linked to a nulliparous classification. It was not possible to detect Psychic transparency in this study. The wish for a child might be easier to identify. In addition, the raters' choices seemed to be connected to social representations of motherhood.

Discrimination thresholds of normal and anomalous trichromats: Model of senescent changes in ocular media density on the Cambridge Colour Test

PubMed Central

Shinomori, Keizo; Panorgias, Athanasios; Werner, John S.

2017-01-01

Age-related changes in chromatic discrimination along dichromatic confusion lines were measured with the Cambridge Colour Test (CCT). One hundred and sixty-two individuals (16 to 88 years old) with normal Rayleigh matches were the major focus of this paper. An additional 32 anomalous trichromats classified by their Rayleigh matches were also tested. All subjects were screened to rule out abnormalities of the anterior and posterior segments. Thresholds on all three chromatic vectors measured with the CCT showed age-related increases. Protan and deutan vector thresholds increased linearly with age while the tritan vector threshold was described with a bilinear model. Analysis and modeling demonstrated that the nominal vectors of the CCT are shifted by senescent changes in ocular media density, and a method for correcting the CCT vectors is demonstrated. A correction for these shifts indicates that classification among individuals of different ages is unaffected. New vector thresholds for elderly observers and for all age groups are suggested based on calculated tolerance limits. PMID:26974943

Discriminative Learning of Receptive Fields from Responses to Non-Gaussian Stimulus Ensembles

PubMed Central

Meyer, Arne F.; Diepenbrock, Jan-Philipp; Happel, Max F. K.; Ohl, Frank W.; Anemüller, Jörn

2014-01-01

Analysis of sensory neurons' processing characteristics requires simultaneous measurement of presented stimuli and concurrent spike responses. The functional transformation from high-dimensional stimulus space to the binary space of spike and non-spike responses is commonly described with linear-nonlinear models, whose linear filter component describes the neuron's receptive field. From a machine learning perspective, this corresponds to the binary classification problem of discriminating spike-eliciting from non-spike-eliciting stimulus examples. The classification-based receptive field (CbRF) estimation method proposed here adapts a linear large-margin classifier to optimally predict experimental stimulus-response data and subsequently interprets learned classifier weights as the neuron's receptive field filter. Computational learning theory provides a theoretical framework for learning from data and guarantees optimality in the sense that the risk of erroneously assigning a spike-eliciting stimulus example to the non-spike class (and vice versa) is minimized. Efficacy of the CbRF method is validated with simulations and for auditory spectro-temporal receptive field (STRF) estimation from experimental recordings in the auditory midbrain of Mongolian gerbils. Acoustic stimulation is performed with frequency-modulated tone complexes that mimic properties of natural stimuli, specifically non-Gaussian amplitude distribution and higher-order correlations. Results demonstrate that the proposed approach successfully identifies correct underlying STRFs, even in cases where second-order methods based on the spike-triggered average (STA) do not. Applied to small data samples, the method is shown to converge on smaller amounts of experimental recordings and with lower estimation variance than the generalized linear model and recent information theoretic methods. Thus, CbRF estimation may prove useful for investigation of neuronal processes in response to natural stimuli and in settings where rapid adaptation is induced by experimental design. PMID:24699631

Discriminative learning of receptive fields from responses to non-Gaussian stimulus ensembles.

PubMed

Meyer, Arne F; Diepenbrock, Jan-Philipp; Happel, Max F K; Ohl, Frank W; Anemüller, Jörn

2014-01-01

Analysis of sensory neurons' processing characteristics requires simultaneous measurement of presented stimuli and concurrent spike responses. The functional transformation from high-dimensional stimulus space to the binary space of spike and non-spike responses is commonly described with linear-nonlinear models, whose linear filter component describes the neuron's receptive field. From a machine learning perspective, this corresponds to the binary classification problem of discriminating spike-eliciting from non-spike-eliciting stimulus examples. The classification-based receptive field (CbRF) estimation method proposed here adapts a linear large-margin classifier to optimally predict experimental stimulus-response data and subsequently interprets learned classifier weights as the neuron's receptive field filter. Computational learning theory provides a theoretical framework for learning from data and guarantees optimality in the sense that the risk of erroneously assigning a spike-eliciting stimulus example to the non-spike class (and vice versa) is minimized. Efficacy of the CbRF method is validated with simulations and for auditory spectro-temporal receptive field (STRF) estimation from experimental recordings in the auditory midbrain of Mongolian gerbils. Acoustic stimulation is performed with frequency-modulated tone complexes that mimic properties of natural stimuli, specifically non-Gaussian amplitude distribution and higher-order correlations. Results demonstrate that the proposed approach successfully identifies correct underlying STRFs, even in cases where second-order methods based on the spike-triggered average (STA) do not. Applied to small data samples, the method is shown to converge on smaller amounts of experimental recordings and with lower estimation variance than the generalized linear model and recent information theoretic methods. Thus, CbRF estimation may prove useful for investigation of neuronal processes in response to natural stimuli and in settings where rapid adaptation is induced by experimental design.

Development of a method to assess compliance with ergonomic posture in dental students

PubMed Central

Garcia, Patrícia Petromilli Nordi Sasso; Wajngarten, Danielle; Campos, Juliana Alvares Duarte Bonini

2018-01-01

CONTEXT: The ergonomic posture protocol is extremely important for the maintenance of occupational health in dentistry. The lack of compliance with this protocol results in a high risk of developing musculoskeletal disorders. AIMS: This study developed a direct observation method for the evaluation of dental student compliance with ergonomic posture protocol. SUBJECTS AND METHODS: The method is named compliance assessment of dental ergonomic posture requirements (CADEP). During the development of the method, 14 items were elaborated considering the theory of dental ergonomics. Each item should be classified as appropriate, partially appropriate, or inappropriate. After evaluation, all item values should be added, and the final score expressed as the percent of compliance with correct postures, with a score range of 0%–100%. STATISTICAL ANALYSIS USED: The reliability of CADEP was assessed through intra- and interobserver reproducibility. For the CADEP application, 73 senior year students from the undergraduate course in dentistry were evaluated. The intra- and interexaminer concordance was estimated using the intraclass correlation coefficient (ρ). A descriptive statistical analysis was performed. RESULTS: The reproducibility of evaluator 1 (ρ =0.90; confidence interval [CI] 95%: 0.83–0.94), evaluator 2 (ρ = 0.83; CI 95%: 0.70–0.90), the interexaminer in the first evaluation (ρ = 0.81; CI 95%:0.67–0.89), and in the second one (ρ = 0.76; CI 95%: 0.59–0.87) was classified as good. In the analysis of the compliance, it was verified that moderate compliance was the most prevalent among the evaluated students (65.6%, CI 95%: 60.3%–70.7%). CONCLUSIONS: CADEP was valid and reliable for the assessment of dentistry students’ compliance regarding ergonomic posture requirements. PMID:29693025

Ion mobility spectrometry fingerprints: A rapid detection technology for adulteration of sesame oil.

PubMed

Zhang, Liangxiao; Shuai, Qian; Li, Peiwu; Zhang, Qi; Ma, Fei; Zhang, Wen; Ding, Xiaoxia

2016-02-01

A simple and rapid detection technology was proposed based on ion mobility spectrometry (IMS) fingerprints to determine potential adulteration of sesame oil. Oil samples were diluted by n-hexane and analyzed by IMS for 20s. Then, chemometric methods were employed to establish discriminant models for sesame oils and four other edible oils, pure and adulterated sesame oils, and pure and counterfeit sesame oils, respectively. Finally, Random Forests (RF) classification model could correctly classify all five types of edible oils. The detection results indicated that the discriminant models built by recursive support vector machine (R-SVM) method could identify adulterated sesame oil samples (⩾ 10%) with an accuracy value of 94.2%. Therefore, IMS was shown to be an effective method to detect the adulterated sesame oils. Meanwhile, IMS fingerprints work well to detect the counterfeit sesame oils produced by adding sesame oil essence into cheaper edible oils. Copyright © 2015 Elsevier Ltd. All rights reserved.

Benchmark studies on the building blocks of DNA. 3. Watson-Crick and stacked base pairs.

PubMed

Szalay, Péter G; Watson, Thomas; Perera, Ajith; Lotrich, Victor; Bartlett, Rodney J

2013-04-18

Excited states of stacked adenine-thymine and guanine-cytosine pairs as well as the Watson-Crick pair of guanine-thymine have been investigated using the equation of motion coupled-cluster (EOM-CC) method with single and double as well as approximate triple excitations. Transitions have been assigned, and the form of the excitations has been analyzed. The majority of the excitations could be classified as localized on the nucleobases, but for all three studied systems, charge-transfer (CT) transitions could also be identified. The main aim of this study was to compare the performance of lower-level methods (ADC(2) and TDDFT) to the high-level EOM-CC ones. It was shown that both ADC(2) and TDDFT with long-range correction have nonsystematic error in excitation energies, causing alternation of the energetic ordering of the excitations. Considering the high costs of the EOM-CC calculations, there is a need for reliable new approximate methods.

How automated image analysis techniques help scientists in species identification and classification?

PubMed

Yousef Kalafi, Elham; Town, Christopher; Kaur Dhillon, Sarinder

2017-09-04

Identification of taxonomy at a specific level is time consuming and reliant upon expert ecologists. Hence the demand for automated species identification increased over the last two decades. Automation of data classification is primarily focussed on images, incorporating and analysing image data has recently become easier due to developments in computational technology. Research efforts in identification of species include specimens' image processing, extraction of identical features, followed by classifying them into correct categories. In this paper, we discuss recent automated species identification systems, categorizing and evaluating their methods. We reviewed and compared different methods in step by step scheme of automated identification and classification systems of species images. The selection of methods is influenced by many variables such as level of classification, number of training data and complexity of images. The aim of writing this paper is to provide researchers and scientists an extensive background study on work related to automated species identification, focusing on pattern recognition techniques in building such systems for biodiversity studies.

Computer-assisted bladder cancer grading: α-shapes for color space decomposition

NASA Astrophysics Data System (ADS)

Niazi, M. K. K.; Parwani, Anil V.; Gurcan, Metin N.

2016-03-01

According to American Cancer Society, around 74,000 new cases of bladder cancer are expected during 2015 in the US. To facilitate the bladder cancer diagnosis, we present an automatic method to differentiate carcinoma in situ (CIS) from normal/reactive cases that will work on hematoxylin and eosin (H and E) stained images of bladder. The method automatically determines the color deconvolution matrix by utilizing the α-shapes of the color distribution in the RGB color space. Then, variations in the boundary of transitional epithelium are quantified, and sizes of nuclei in the transitional epithelium are measured. We also approximate the "nuclear to cytoplasmic ratio" by computing the ratio of the average shortest distance between transitional epithelium and nuclei to average nuclei size. Nuclei homogeneity is measured by computing the kurtosis of the nuclei size histogram. The results show that 30 out of 34 (88.2%) images were correctly classified by the proposed method, indicating that these novel features are viable markers to differentiate CIS from normal/reactive bladder.

Can we recognize horses by their ocular biometric traits using deep convolutional neural networks?

NASA Astrophysics Data System (ADS)

Trokielewicz, Mateusz; Szadkowski, Mateusz

2017-08-01

This paper aims at determining the viability of horse recognition by the means of ocular biometrics and deep convolutional neural networks (deep CNNs). Fast and accurate identification of race horses before racing is crucial for ensuring that exactly the horses that were declared are participating, using methods that are non-invasive and friendly to these delicate animals. As typical iris recognition methods require lot of fine-tuning of the method parameters and high-quality data, CNNs seem like a natural candidate to be applied for recognition thanks to their potentially excellent abilities in describing texture, combined with ease of implementation in an end-to-end manner. Also, with such approach we can easily utilize both iris and periocular features without constructing complicated algorithms for each. We thus present a simple CNN classifier, able to correctly identify almost 80% of the samples in an identification scenario, and give equal error rate (EER) of less than 10% in a verification scenario.