Detection of eardrum abnormalities using ensemble deep learning approaches

NASA Astrophysics Data System (ADS)

Senaras, Caglar; Moberly, Aaron C.; Teknos, Theodoros; Essig, Garth; Elmaraghy, Charles; Taj-Schaal, Nazhat; Yua, Lianbo; Gurcan, Metin N.

2018-02-01

In this study, we proposed an approach to report the condition of the eardrum as "normal" or "abnormal" by ensembling two different deep learning architectures. In the first network (Network 1), we applied transfer learning to the Inception V3 network by using 409 labeled samples. As a second network (Network 2), we designed a convolutional neural network to take advantage of auto-encoders by using additional 673 unlabeled eardrum samples. The individual classification accuracies of the Network 1 and Network 2 were calculated as 84.4%(+/- 12.1%) and 82.6% (+/- 11.3%), respectively. Only 32% of the errors of the two networks were the same, making it possible to combine two approaches to achieve better classification accuracy. The proposed ensemble method allows us to achieve robust classification because it has high accuracy (84.4%) with the lowest standard deviation (+/- 10.3%).

Modified Bat Algorithm for Feature Selection with the Wisconsin Diagnosis Breast Cancer (WDBC) Dataset

PubMed

Jeyasingh, Suganthi; Veluchamy, Malathi

2017-05-01

Early diagnosis of breast cancer is essential to save lives of patients. Usually, medical datasets include a large variety of data that can lead to confusion during diagnosis. The Knowledge Discovery on Database (KDD) process helps to improve efficiency. It requires elimination of inappropriate and repeated data from the dataset before final diagnosis. This can be done using any of the feature selection algorithms available in data mining. Feature selection is considered as a vital step to increase the classification accuracy. This paper proposes a Modified Bat Algorithm (MBA) for feature selection to eliminate irrelevant features from an original dataset. The Bat algorithm was modified using simple random sampling to select the random instances from the dataset. Ranking was with the global best features to recognize the predominant features available in the dataset. The selected features are used to train a Random Forest (RF) classification algorithm. The MBA feature selection algorithm enhanced the classification accuracy of RF in identifying the occurrence of breast cancer. The Wisconsin Diagnosis Breast Cancer Dataset (WDBC) was used for estimating the performance analysis of the proposed MBA feature selection algorithm. The proposed algorithm achieved better performance in terms of Kappa statistic, Mathew’s Correlation Coefficient, Precision, F-measure, Recall, Mean Absolute Error (MAE), Root Mean Square Error (RMSE), Relative Absolute Error (RAE) and Root Relative Squared Error (RRSE). Creative Commons Attribution License

Fast, Simple and Accurate Handwritten Digit Classification by Training Shallow Neural Network Classifiers with the ‘Extreme Learning Machine’ Algorithm

PubMed Central

McDonnell, Mark D.; Tissera, Migel D.; Vladusich, Tony; van Schaik, André; Tapson, Jonathan

2015-01-01

Recent advances in training deep (multi-layer) architectures have inspired a renaissance in neural network use. For example, deep convolutional networks are becoming the default option for difficult tasks on large datasets, such as image and speech recognition. However, here we show that error rates below 1% on the MNIST handwritten digit benchmark can be replicated with shallow non-convolutional neural networks. This is achieved by training such networks using the ‘Extreme Learning Machine’ (ELM) approach, which also enables a very rapid training time (∼ 10 minutes). Adding distortions, as is common practise for MNIST, reduces error rates even further. Our methods are also shown to be capable of achieving less than 5.5% error rates on the NORB image database. To achieve these results, we introduce several enhancements to the standard ELM algorithm, which individually and in combination can significantly improve performance. The main innovation is to ensure each hidden-unit operates only on a randomly sized and positioned patch of each image. This form of random ‘receptive field’ sampling of the input ensures the input weight matrix is sparse, with about 90% of weights equal to zero. Furthermore, combining our methods with a small number of iterations of a single-batch backpropagation method can significantly reduce the number of hidden-units required to achieve a particular performance. Our close to state-of-the-art results for MNIST and NORB suggest that the ease of use and accuracy of the ELM algorithm for designing a single-hidden-layer neural network classifier should cause it to be given greater consideration either as a standalone method for simpler problems, or as the final classification stage in deep neural networks applied to more difficult problems. PMID:26262687

Value Driven Information Processing and Fusion

DTIC Science & Technology

2016-03-01

consensus approach allows a decentralized approach to achieve the optimal error exponent of the centralized counterpart, a conclusion that is signifi...SECURITY CLASSIFICATION OF: The objective of the project is to develop a general framework for value driven decentralized information processing...including: optimal data reduction in a network setting for decentralized inference with quantization constraint; interactive fusion that allows queries and

Optimal number of features as a function of sample size for various classification rules.

PubMed

Hua, Jianping; Xiong, Zixiang; Lowey, James; Suh, Edward; Dougherty, Edward R

2005-04-15

Given the joint feature-label distribution, increasing the number of features always results in decreased classification error; however, this is not the case when a classifier is designed via a classification rule from sample data. Typically (but not always), for fixed sample size, the error of a designed classifier decreases and then increases as the number of features grows. The potential downside of using too many features is most critical for small samples, which are commonplace for gene-expression-based classifiers for phenotype discrimination. For fixed sample size and feature-label distribution, the issue is to find an optimal number of features. Since only in rare cases is there a known distribution of the error as a function of the number of features and sample size, this study employs simulation for various feature-label distributions and classification rules, and across a wide range of sample and feature-set sizes. To achieve the desired end, finding the optimal number of features as a function of sample size, it employs massively parallel computation. Seven classifiers are treated: 3-nearest-neighbor, Gaussian kernel, linear support vector machine, polynomial support vector machine, perceptron, regular histogram and linear discriminant analysis. Three Gaussian-based models are considered: linear, nonlinear and bimodal. In addition, real patient data from a large breast-cancer study is considered. To mitigate the combinatorial search for finding optimal feature sets, and to model the situation in which subsets of genes are co-regulated and correlation is internal to these subsets, we assume that the covariance matrix of the features is blocked, with each block corresponding to a group of correlated features. Altogether there are a large number of error surfaces for the many cases. These are provided in full on a companion website, which is meant to serve as resource for those working with small-sample classification. For the companion website, please visit http://public.tgen.org/tamu/ofs/ e-dougherty@ee.tamu.edu.

Satellite inventory of Minnesota forest resources

NASA Technical Reports Server (NTRS)

Bauer, Marvin E.; Burk, Thomas E.; Ek, Alan R.; Coppin, Pol R.; Lime, Stephen D.; Walsh, Terese A.; Walters, David K.; Befort, William; Heinzen, David F.

1993-01-01

The methods and results of using Landsat Thematic Mapper (TM) data to classify and estimate the acreage of forest covertypes in northeastern Minnesota are described. Portions of six TM scenes covering five counties with a total area of 14,679 square miles were classified into six forest and five nonforest classes. The approach involved the integration of cluster sampling, image processing, and estimation. Using cluster sampling, 343 plots, each 88 acres in size, were photo interpreted and field mapped as a source of reference data for classifier training and calibration of the TM data classifications. Classification accuracies of up to 75 percent were achieved; most misclassification was between similar or related classes. An inverse method of calibration, based on the error rates obtained from the classifications of the cluster plots, was used to adjust the classification class proportions for classification errors. The resulting area estimates for total forest land in the five-county area were within 3 percent of the estimate made independently by the USDA Forest Service. Area estimates for conifer and hardwood forest types were within 0.8 and 6.0 percent respectively, of the Forest Service estimates. A trial of a second method of estimating the same classes as the Forest Service resulted in standard errors of 0.002 to 0.015. A study of the use of multidate TM data for change detection showed that forest canopy depletion, canopy increment, and no change could be identified with greater than 90 percent accuracy. The project results have been the basis for the Minnesota Department of Natural Resources and the Forest Service to define and begin to implement an annual system of forest inventory which utilizes Landsat TM data to detect changes in forest cover.

Choosing the Most Effective Pattern Classification Model under Learning-Time Constraint.

PubMed

Saito, Priscila T M; Nakamura, Rodrigo Y M; Amorim, Willian P; Papa, João P; de Rezende, Pedro J; Falcão, Alexandre X

2015-01-01

Nowadays, large datasets are common and demand faster and more effective pattern analysis techniques. However, methodologies to compare classifiers usually do not take into account the learning-time constraints required by applications. This work presents a methodology to compare classifiers with respect to their ability to learn from classification errors on a large learning set, within a given time limit. Faster techniques may acquire more training samples, but only when they are more effective will they achieve higher performance on unseen testing sets. We demonstrate this result using several techniques, multiple datasets, and typical learning-time limits required by applications.

Acquiring Research-grade ALSM Data in the Commercial Marketplace

NASA Astrophysics Data System (ADS)

Haugerud, R. A.; Harding, D. J.; Latypov, D.; Martinez, D.; Routh, S.; Ziegler, J.

2003-12-01

The Puget Sound Lidar Consortium, working with TerraPoint, LLC, has procured a large volume of ALSM (topographic lidar) data for scientific research. Research-grade ALSM data can be characterized by their completeness, density, and accuracy. Complete data include-at a minimum-X, Y, Z, time, and classification (ground, vegetation, structure, blunder) for each laser reflection. Off-nadir angle and return number for multiple returns are also useful. We began with a pulse density of 1/sq m, and after limited experiments still find this density satisfactory in the dense second-growth forests of western Washington. Lower pulse densities would have produced unacceptably limited sampling in forested areas and aliased some topographic features. Higher pulse densities do not produce markedly better topographic models, in part because of limitations of reproducibility between the overlapping survey swaths used to achieve higher density. Our experience in a variety of forest types demonstrates that the fraction of pulses that produce ground returns varies with vegetation cover, laser beam divergence, laser power, and detector sensitivity, but have not quantified this relationship. The most significant operational limits on vertical accuracy of ALSM appear to be instrument calibration and the accuracy with which returns are classified as ground or vegetation. TerraPoint has recently implemented in-situ calibration using overlapping swaths (Latypov and Zosse, 2002, see http://www.terrapoint.com/News_damirACSM_ASPRS2002.html). On the consumer side, we routinely perform a similar overlap analysis to produce maps of relative Z error between swaths; we find that in bare, low-slope regions the in-situ calibration has reduced this internal Z error to 6-10 cm RMSE. Comparison with independent ground control points commonly illuminates inconsistencies in how GPS heights have been reduced to orthometric heights. Once these inconsistencies are resolved, it appears that the internal errors are the bulk of the error of the survey. The error maps suggest that with in-situ calibration, minor time-varying errors with a period of circa 1 sec are the largest remaining source of survey error. For forested terrain, limited ground penetration and errors in return classification can severely limit the accuracy of resulting topographic models. Initial work by Haugerud and Harding demonstrated the feasibility of fully-automatic return classification; however, TerraPoint has found that better results can be obtained more effectively with 3rd-party classification software that allows a mix of automated routines and human intervention. Our relationship has been evolving since early 2000. Important aspects of this relationship include close communication between data producer and consumer, a willingness to learn from each other, significant technical expertise and resources on the consumer side, and continued refinement of achievable, quantitative performance and accuracy specifications. Most recently we have instituted a slope-dependent Z accuracy specification that TerraPoint first developed as a heuristic for surveying mountainous terrain in Switzerland. We are now working on quantifying the internal consistency of topographic models in forested areas, using a variant of overlap analysis, and standards for the spatial distribution of internal errors.

A data-driven modeling approach to stochastic computation for low-energy biomedical devices.

PubMed

Lee, Kyong Ho; Jang, Kuk Jin; Shoeb, Ali; Verma, Naveen

2011-01-01

Low-power devices that can detect clinically relevant correlations in physiologically-complex patient signals can enable systems capable of closed-loop response (e.g., controlled actuation of therapeutic stimulators, continuous recording of disease states, etc.). In ultra-low-power platforms, however, hardware error sources are becoming increasingly limiting. In this paper, we present how data-driven methods, which allow us to accurately model physiological signals, also allow us to effectively model and overcome prominent hardware error sources with nearly no additional overhead. Two applications, EEG-based seizure detection and ECG-based arrhythmia-beat classification, are synthesized to a logic-gate implementation, and two prominent error sources are introduced: (1) SRAM bit-cell errors and (2) logic-gate switching errors ('stuck-at' faults). Using patient data from the CHB-MIT and MIT-BIH databases, performance similar to error-free hardware is achieved even for very high fault rates (up to 0.5 for SRAMs and 7 × 10(-2) for logic) that cause computational bit error rates as high as 50%.

Optimized Time-Gated Fluorescence Spectroscopy for the Classification and Recycling of Fluorescently Labeled Plastics.

PubMed

Fomin, Petr; Zhelondz, Dmitry; Kargel, Christian

2017-05-01

For the production of high-quality parts from recycled plastics, a very high purity of the plastic waste to be recycled is mandatory. The incorporation of fluorescent tracers ("markers") into plastics during the manufacturing process helps overcome typical problems of non-tracer based optical classification methods. Despite the unique emission spectra of fluorescent markers, the classification becomes difficult when the host plastics exhibit (strong) autofluorescence that spectrally overlaps the marker fluorescence. Increasing the marker concentration is not an option from an economic perspective and might also adversely affect the properties of the plastics. A measurement approach that suppresses the autofluorescence in the acquired signal is time-gated fluorescence spectroscopy (TGFS). Unfortunately, TGFS is associated with a lower signal-to-noise (S/N) ratio, which results in larger classification errors. In order to optimize the S/N ratio we investigate and validate the best TGFS parameters-derived from a model for the fluorescence signal-for plastics labeled with four specifically designed fluorescent markers. In this study we also demonstrate the implementation of TGFS on a measurement and classification prototype system and determine its performance. Mean values for a sensitivity of [Formula: see text] = 99.93% and precision [Formula: see text] = 99.80% were achieved, proving that a highly reliable classification of plastics can be achieved in practice.

Normalization of relative and incomplete temporal expressions in clinical narratives.

PubMed

Sun, Weiyi; Rumshisky, Anna; Uzuner, Ozlem

2015-09-01

To improve the normalization of relative and incomplete temporal expressions (RI-TIMEXes) in clinical narratives. We analyzed the RI-TIMEXes in temporally annotated corpora and propose two hypotheses regarding the normalization of RI-TIMEXes in the clinical narrative domain: the anchor point hypothesis and the anchor relation hypothesis. We annotated the RI-TIMEXes in three corpora to study the characteristics of RI-TMEXes in different domains. This informed the design of our RI-TIMEX normalization system for the clinical domain, which consists of an anchor point classifier, an anchor relation classifier, and a rule-based RI-TIMEX text span parser. We experimented with different feature sets and performed an error analysis for each system component. The annotation confirmed the hypotheses that we can simplify the RI-TIMEXes normalization task using two multi-label classifiers. Our system achieves anchor point classification, anchor relation classification, and rule-based parsing accuracy of 74.68%, 87.71%, and 57.2% (82.09% under relaxed matching criteria), respectively, on the held-out test set of the 2012 i2b2 temporal relation challenge. Experiments with feature sets reveal some interesting findings, such as: the verbal tense feature does not inform the anchor relation classification in clinical narratives as much as the tokens near the RI-TIMEX. Error analysis showed that underrepresented anchor point and anchor relation classes are difficult to detect. We formulate the RI-TIMEX normalization problem as a pair of multi-label classification problems. Considering only RI-TIMEX extraction and normalization, the system achieves statistically significant improvement over the RI-TIMEX results of the best systems in the 2012 i2b2 challenge. © The Author 2015. Published by Oxford University Press on behalf of the American Medical Informatics Association. All rights reserved. For Permissions, please email: journals.permissions@oup.com.

Classification-Based Spatial Error Concealment for Visual Communications

NASA Astrophysics Data System (ADS)

Chen, Meng; Zheng, Yefeng; Wu, Min

2006-12-01

In an error-prone transmission environment, error concealment is an effective technique to reconstruct the damaged visual content. Due to large variations of image characteristics, different concealment approaches are necessary to accommodate the different nature of the lost image content. In this paper, we address this issue and propose using classification to integrate the state-of-the-art error concealment techniques. The proposed approach takes advantage of multiple concealment algorithms and adaptively selects the suitable algorithm for each damaged image area. With growing awareness that the design of sender and receiver systems should be jointly considered for efficient and reliable multimedia communications, we proposed a set of classification-based block concealment schemes, including receiver-side classification, sender-side attachment, and sender-side embedding. Our experimental results provide extensive performance comparisons and demonstrate that the proposed classification-based error concealment approaches outperform the conventional approaches.

A Locality-Constrained and Label Embedding Dictionary Learning Algorithm for Image Classification.

PubMed

Zhengming Li; Zhihui Lai; Yong Xu; Jian Yang; Zhang, David

2017-02-01

Locality and label information of training samples play an important role in image classification. However, previous dictionary learning algorithms do not take the locality and label information of atoms into account together in the learning process, and thus their performance is limited. In this paper, a discriminative dictionary learning algorithm, called the locality-constrained and label embedding dictionary learning (LCLE-DL) algorithm, was proposed for image classification. First, the locality information was preserved using the graph Laplacian matrix of the learned dictionary instead of the conventional one derived from the training samples. Then, the label embedding term was constructed using the label information of atoms instead of the classification error term, which contained discriminating information of the learned dictionary. The optimal coding coefficients derived by the locality-based and label-based reconstruction were effective for image classification. Experimental results demonstrated that the LCLE-DL algorithm can achieve better performance than some state-of-the-art algorithms.

Convolutional neural network with transfer learning for rice type classification

NASA Astrophysics Data System (ADS)

Patel, Vaibhav Amit; Joshi, Manjunath V.

2018-04-01

Presently, rice type is identified manually by humans, which is time consuming and error prone. Therefore, there is a need to do this by machine which makes it faster with greater accuracy. This paper proposes a deep learning based method for classification of rice types. We propose two methods to classify the rice types. In the first method, we train a deep convolutional neural network (CNN) using the given segmented rice images. In the second method, we train a combination of a pretrained VGG16 network and the proposed method, while using transfer learning in which the weights of a pretrained network are used to achieve better accuracy. Our approach can also be used for classification of rice grain as broken or fine. We train a 5-class model for classifying rice types using 4000 training images and another 2- class model for the classification of broken and normal rice using 1600 training images. We observe that despite having distinct rice images, our architecture, pretrained on ImageNet data boosts classification accuracy significantly.

Application of partial least squares near-infrared spectral classification in diabetic identification

NASA Astrophysics Data System (ADS)

Yan, Wen-juan; Yang, Ming; He, Guo-quan; Qin, Lin; Li, Gang

2014-11-01

In order to identify the diabetic patients by using tongue near-infrared (NIR) spectrum - a spectral classification model of the NIR reflectivity of the tongue tip is proposed, based on the partial least square (PLS) method. 39sample data of tongue tip's NIR spectra are harvested from healthy people and diabetic patients , respectively. After pretreatment of the reflectivity, the spectral data are set as the independent variable matrix, and information of classification as the dependent variables matrix, Samples were divided into two groups - i.e. 53 samples as calibration set and 25 as prediction set - then the PLS is used to build the classification model The constructed modelfrom the 53 samples has the correlation of 0.9614 and the root mean square error of cross-validation (RMSECV) of 0.1387.The predictions for the 25 samples have the correlation of 0.9146 and the RMSECV of 0.2122.The experimental result shows that the PLS method can achieve good classification on features of healthy people and diabetic patients.

Expected energy-based restricted Boltzmann machine for classification.

PubMed

Elfwing, S; Uchibe, E; Doya, K

2015-04-01

In classification tasks, restricted Boltzmann machines (RBMs) have predominantly been used in the first stage, either as feature extractors or to provide initialization of neural networks. In this study, we propose a discriminative learning approach to provide a self-contained RBM method for classification, inspired by free-energy based function approximation (FE-RBM), originally proposed for reinforcement learning. For classification, the FE-RBM method computes the output for an input vector and a class vector by the negative free energy of an RBM. Learning is achieved by stochastic gradient-descent using a mean-squared error training objective. In an earlier study, we demonstrated that the performance and the robustness of FE-RBM function approximation can be improved by scaling the free energy by a constant that is related to the size of network. In this study, we propose that the learning performance of RBM function approximation can be further improved by computing the output by the negative expected energy (EE-RBM), instead of the negative free energy. To create a deep learning architecture, we stack several RBMs on top of each other. We also connect the class nodes to all hidden layers to try to improve the performance even further. We validate the classification performance of EE-RBM using the MNIST data set and the NORB data set, achieving competitive performance compared with other classifiers such as standard neural networks, deep belief networks, classification RBMs, and support vector machines. The purpose of using the NORB data set is to demonstrate that EE-RBM with binary input nodes can achieve high performance in the continuous input domain. Copyright © 2014 The Authors. Published by Elsevier Ltd.. All rights reserved.

C-fuzzy variable-branch decision tree with storage and classification error rate constraints

NASA Astrophysics Data System (ADS)

Yang, Shiueng-Bien

2009-10-01

The C-fuzzy decision tree (CFDT), which is based on the fuzzy C-means algorithm, has recently been proposed. The CFDT is grown by selecting the nodes to be split according to its classification error rate. However, the CFDT design does not consider the classification time taken to classify the input vector. Thus, the CFDT can be improved. We propose a new C-fuzzy variable-branch decision tree (CFVBDT) with storage and classification error rate constraints. The design of the CFVBDT consists of two phases-growing and pruning. The CFVBDT is grown by selecting the nodes to be split according to the classification error rate and the classification time in the decision tree. Additionally, the pruning method selects the nodes to prune based on the storage requirement and the classification time of the CFVBDT. Furthermore, the number of branches of each internal node is variable in the CFVBDT. Experimental results indicate that the proposed CFVBDT outperforms the CFDT and other methods.

Multiple-rule bias in the comparison of classification rules

PubMed Central

Yousefi, Mohammadmahdi R.; Hua, Jianping; Dougherty, Edward R.

2011-01-01

Motivation: There is growing discussion in the bioinformatics community concerning overoptimism of reported results. Two approaches contributing to overoptimism in classification are (i) the reporting of results on datasets for which a proposed classification rule performs well and (ii) the comparison of multiple classification rules on a single dataset that purports to show the advantage of a certain rule. Results: This article provides a careful probabilistic analysis of the second issue and the ‘multiple-rule bias’, resulting from choosing a classification rule having minimum estimated error on the dataset. It quantifies this bias corresponding to estimating the expected true error of the classification rule possessing minimum estimated error and it characterizes the bias from estimating the true comparative advantage of the chosen classification rule relative to the others by the estimated comparative advantage on the dataset. The analysis is applied to both synthetic and real data using a number of classification rules and error estimators. Availability: We have implemented in C code the synthetic data distribution model, classification rules, feature selection routines and error estimation methods. The code for multiple-rule analysis is implemented in MATLAB. The source code is available at http://gsp.tamu.edu/Publications/supplementary/yousefi11a/. Supplementary simulation results are also included. Contact: edward@ece.tamu.edu Supplementary Information: Supplementary data are available at Bioinformatics online. PMID:21546390

Exploring diversity in ensemble classification: Applications in large area land cover mapping

NASA Astrophysics Data System (ADS)

Mellor, Andrew; Boukir, Samia

2017-07-01

Ensemble classifiers, such as random forests, are now commonly applied in the field of remote sensing, and have been shown to perform better than single classifier systems, resulting in reduced generalisation error. Diversity across the members of ensemble classifiers is known to have a strong influence on classification performance - whereby classifier errors are uncorrelated and more uniformly distributed across ensemble members. The relationship between ensemble diversity and classification performance has not yet been fully explored in the fields of information science and machine learning and has never been examined in the field of remote sensing. This study is a novel exploration of ensemble diversity and its link to classification performance, applied to a multi-class canopy cover classification problem using random forests and multisource remote sensing and ancillary GIS data, across seven million hectares of diverse dry-sclerophyll dominated public forests in Victoria Australia. A particular emphasis is placed on analysing the relationship between ensemble diversity and ensemble margin - two key concepts in ensemble learning. The main novelty of our work is on boosting diversity by emphasizing the contribution of lower margin instances used in the learning process. Exploring the influence of tree pruning on diversity is also a new empirical analysis that contributes to a better understanding of ensemble performance. Results reveal insights into the trade-off between ensemble classification accuracy and diversity, and through the ensemble margin, demonstrate how inducing diversity by targeting lower margin training samples is a means of achieving better classifier performance for more difficult or rarer classes and reducing information redundancy in classification problems. Our findings inform strategies for collecting training data and designing and parameterising ensemble classifiers, such as random forests. This is particularly important in large area remote sensing applications, for which training data is costly and resource intensive to collect.

Study on Classification Accuracy Inspection of Land Cover Data Aided by Automatic Image Change Detection Technology

NASA Astrophysics Data System (ADS)

Xie, W.-J.; Zhang, L.; Chen, H.-P.; Zhou, J.; Mao, W.-J.

2018-04-01

The purpose of carrying out national geographic conditions monitoring is to obtain information of surface changes caused by human social and economic activities, so that the geographic information can be used to offer better services for the government, enterprise and public. Land cover data contains detailed geographic conditions information, thus has been listed as one of the important achievements in the national geographic conditions monitoring project. At present, the main issue of the production of the land cover data is about how to improve the classification accuracy. For the land cover data quality inspection and acceptance, classification accuracy is also an important check point. So far, the classification accuracy inspection is mainly based on human-computer interaction or manual inspection in the project, which are time consuming and laborious. By harnessing the automatic high-resolution remote sensing image change detection technology based on the ERDAS IMAGINE platform, this paper carried out the classification accuracy inspection test of land cover data in the project, and presented a corresponding technical route, which includes data pre-processing, change detection, result output and information extraction. The result of the quality inspection test shows the effectiveness of the technical route, which can meet the inspection needs for the two typical errors, that is, missing and incorrect update error, and effectively reduces the work intensity of human-computer interaction inspection for quality inspectors, and also provides a technical reference for the data production and quality control of the land cover data.

Automated Identification of Abnormal Adult EEGs

PubMed Central

López, S.; Suarez, G.; Jungreis, D.; Obeid, I.; Picone, J.

2016-01-01

The interpretation of electroencephalograms (EEGs) is a process that is still dependent on the subjective analysis of the examiners. Though interrater agreement on critical events such as seizures is high, it is much lower on subtler events (e.g., when there are benign variants). The process used by an expert to interpret an EEG is quite subjective and hard to replicate by machine. The performance of machine learning technology is far from human performance. We have been developing an interpretation system, AutoEEG, with a goal of exceeding human performance on this task. In this work, we are focusing on one of the early decisions made in this process – whether an EEG is normal or abnormal. We explore two baseline classification algorithms: k-Nearest Neighbor (kNN) and Random Forest Ensemble Learning (RF). A subset of the TUH EEG Corpus was used to evaluate performance. Principal Components Analysis (PCA) was used to reduce the dimensionality of the data. kNN achieved a 41.8% detection error rate while RF achieved an error rate of 31.7%. These error rates are significantly lower than those obtained by random guessing based on priors (49.5%). The majority of the errors were related to misclassification of normal EEGs. PMID:27195311

Clarification of terminology in medication errors: definitions and classification.

PubMed

Ferner, Robin E; Aronson, Jeffrey K

2006-01-01

We have previously described and analysed some terms that are used in drug safety and have proposed definitions. Here we discuss and define terms that are used in the field of medication errors, particularly terms that are sometimes misunderstood or misused. We also discuss the classification of medication errors. A medication error is a failure in the treatment process that leads to, or has the potential to lead to, harm to the patient. Errors can be classified according to whether they are mistakes, slips, or lapses. Mistakes are errors in the planning of an action. They can be knowledge based or rule based. Slips and lapses are errors in carrying out an action - a slip through an erroneous performance and a lapse through an erroneous memory. Classification of medication errors is important because the probabilities of errors of different classes are different, as are the potential remedies.

Quantitative CT based radiomics as predictor of resectability of pancreatic adenocarcinoma

NASA Astrophysics Data System (ADS)

van der Putten, Joost; Zinger, Svitlana; van der Sommen, Fons; de With, Peter H. N.; Prokop, Mathias; Hermans, John

2018-02-01

In current clinical practice, the resectability of pancreatic ductal adenocarcinoma (PDA) is determined subjec- tively by a physician, which is an error-prone procedure. In this paper, we present a method for automated determination of resectability of PDA from a routine abdominal CT, to reduce such decision errors. The tumor features are extracted from a group of patients with both hypo- and iso-attenuating tumors, of which 29 were resectable and 21 were not. The tumor contours are supplied by a medical expert. We present an approach that uses intensity, shape, and texture features to determine tumor resectability. The best classification results are obtained with fine Gaussian SVM and the L0 Feature Selection algorithms. Compared to expert predictions made on the same dataset, our method achieves better classification results. We obtain significantly better results on correctly predicting non-resectability (+17%) compared to a expert, which is essential for patient treatment (negative prediction value). Moreover, our predictions of resectability exceed expert predictions by approximately 3% (positive prediction value).

A non-contact method based on multiple signal classification algorithm to reduce the measurement time for accurately heart rate detection

NASA Astrophysics Data System (ADS)

Bechet, P.; Mitran, R.; Munteanu, M.

2013-08-01

Non-contact methods for the assessment of vital signs are of great interest for specialists due to the benefits obtained in both medical and special applications, such as those for surveillance, monitoring, and search and rescue. This paper investigates the possibility of implementing a digital processing algorithm based on the MUSIC (Multiple Signal Classification) parametric spectral estimation in order to reduce the observation time needed to accurately measure the heart rate. It demonstrates that, by proper dimensioning the signal subspace, the MUSIC algorithm can be optimized in order to accurately assess the heart rate during an 8-28 s time interval. The validation of the processing algorithm performance was achieved by minimizing the mean error of the heart rate after performing simultaneous comparative measurements on several subjects. In order to calculate the error the reference value of heart rate was measured using a classic measurement system through direct contact.

Error studies of Halbach Magnets

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

Brooks, S.

2017-03-02

These error studies were done on the Halbach magnets for the CBETA “First Girder” as described in note [CBETA001]. The CBETA magnets have since changed slightly to the lattice in [CBETA009]. However, this is not a large enough change to significantly affect the results here. The QF and BD arc FFAG magnets are considered. For each assumed set of error distributions and each ideal magnet, 100 random magnets with errors are generated. These are then run through an automated version of the iron wire multipole cancellation algorithm. The maximum wire diameter allowed is 0.063” as in the proof-of-principle magnets. Initially,more » 32 wires (2 per Halbach wedge) are tried, then if this does not achieve 1e-­4 level accuracy in the simulation, 48 and then 64 wires. By “1e-4 accuracy”, it is meant the FOM defined by √(Σ n≥sextupole a n 2+b n 2) is less than 1 unit, where the multipoles are taken at the maximum nominal beam radius, R=23mm for these magnets. The algorithm initially uses 20 convergence interations. If 64 wires does not achieve 1e-­4 accuracy, this is increased to 50 iterations to check for slow converging cases. There are also classifications for magnets that do not achieve 1e-4 but do achieve 1e-3 (FOM ≤ 10 units). This is technically within the spec discussed in the Jan 30, 2017 review; however, there will be errors in practical shimming not dealt with in the simulation, so it is preferable to do much better than the spec in the simulation.« less

Improved Classification of Lung Cancer Using Radial Basis Function Neural Network with Affine Transforms of Voss Representation.

PubMed

Adetiba, Emmanuel; Olugbara, Oludayo O

2015-01-01

Lung cancer is one of the diseases responsible for a large number of cancer related death cases worldwide. The recommended standard for screening and early detection of lung cancer is the low dose computed tomography. However, many patients diagnosed die within one year, which makes it essential to find alternative approaches for screening and early detection of lung cancer. We present computational methods that can be implemented in a functional multi-genomic system for classification, screening and early detection of lung cancer victims. Samples of top ten biomarker genes previously reported to have the highest frequency of lung cancer mutations and sequences of normal biomarker genes were respectively collected from the COSMIC and NCBI databases to validate the computational methods. Experiments were performed based on the combinations of Z-curve and tetrahedron affine transforms, Histogram of Oriented Gradient (HOG), Multilayer perceptron and Gaussian Radial Basis Function (RBF) neural networks to obtain an appropriate combination of computational methods to achieve improved classification of lung cancer biomarker genes. Results show that a combination of affine transforms of Voss representation, HOG genomic features and Gaussian RBF neural network perceptibly improves classification accuracy, specificity and sensitivity of lung cancer biomarker genes as well as achieving low mean square error.

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.

Automatic Identification of Critical Follow-Up Recommendation Sentences in Radiology Reports

PubMed Central

Yetisgen-Yildiz, Meliha; Gunn, Martin L.; Xia, Fei; Payne, Thomas H.

2011-01-01

Communication of follow-up recommendations when abnormalities are identified on imaging studies is prone to error. When recommendations are not systematically identified and promptly communicated to referrers, poor patient outcomes can result. Using information technology can improve communication and improve patient safety. In this paper, we describe a text processing approach that uses natural language processing (NLP) and supervised text classification methods to automatically identify critical recommendation sentences in radiology reports. To increase the classification performance we enhanced the simple unigram token representation approach with lexical, semantic, knowledge-base, and structural features. We tested different combinations of those features with the Maximum Entropy (MaxEnt) classification algorithm. Classifiers were trained and tested with a gold standard corpus annotated by a domain expert. We applied 5-fold cross validation and our best performing classifier achieved 95.60% precision, 79.82% recall, 87.0% F-score, and 99.59% classification accuracy in identifying the critical recommendation sentences in radiology reports. PMID:22195225

Automatic identification of critical follow-up recommendation sentences in radiology reports.

PubMed

Yetisgen-Yildiz, Meliha; Gunn, Martin L; Xia, Fei; Payne, Thomas H

2011-01-01

Communication of follow-up recommendations when abnormalities are identified on imaging studies is prone to error. When recommendations are not systematically identified and promptly communicated to referrers, poor patient outcomes can result. Using information technology can improve communication and improve patient safety. In this paper, we describe a text processing approach that uses natural language processing (NLP) and supervised text classification methods to automatically identify critical recommendation sentences in radiology reports. To increase the classification performance we enhanced the simple unigram token representation approach with lexical, semantic, knowledge-base, and structural features. We tested different combinations of those features with the Maximum Entropy (MaxEnt) classification algorithm. Classifiers were trained and tested with a gold standard corpus annotated by a domain expert. We applied 5-fold cross validation and our best performing classifier achieved 95.60% precision, 79.82% recall, 87.0% F-score, and 99.59% classification accuracy in identifying the critical recommendation sentences in radiology reports.

The use of a contextual, modal and psychological classification of medication errors in the emergency department: a retrospective descriptive study.

PubMed

Cabilan, C J; Hughes, James A; Shannon, Carl

2017-12-01

To describe the contextual, modal and psychological classification of medication errors in the emergency department to know the factors associated with the reported medication errors. The causes of medication errors are unique in every clinical setting; hence, error minimisation strategies are not always effective. For this reason, it is fundamental to understand the causes specific to the emergency department so that targeted strategies can be implemented. Retrospective analysis of reported medication errors in the emergency department. All voluntarily staff-reported medication-related incidents from 2010-2015 from the hospital's electronic incident management system were retrieved for analysis. Contextual classification involved the time, place and the type of medications involved. Modal classification pertained to the stage and issue (e.g. wrong medication, wrong patient). Psychological classification categorised the errors in planning (knowledge-based and rule-based errors) and skill (slips and lapses). There were 405 errors reported. Most errors occurred in the acute care area, short-stay unit and resuscitation area, during the busiest shifts (0800-1559, 1600-2259). Half of the errors involved high-alert medications. Many of the errors occurred during administration (62·7%), prescribing (28·6%) and commonly during both stages (18·5%). Wrong dose, wrong medication and omission were the issues that dominated. Knowledge-based errors characterised the errors that occurred in prescribing and administration. The highest proportion of slips (79·5%) and lapses (76·1%) occurred during medication administration. It is likely that some of the errors occurred due to the lack of adherence to safety protocols. Technology such as computerised prescribing, barcode medication administration and reminder systems could potentially decrease the medication errors in the emergency department. There was a possibility that some of the errors could be prevented if safety protocols were adhered to, which highlights the need to also address clinicians' attitudes towards safety. Technology can be implemented to help minimise errors in the ED, but this must be coupled with efforts to enhance the culture of safety. © 2017 John Wiley & Sons Ltd.

Computationally efficient target classification in multispectral image data with Deep Neural Networks

NASA Astrophysics Data System (ADS)

Cavigelli, Lukas; Bernath, Dominic; Magno, Michele; Benini, Luca

2016-10-01

Detecting and classifying targets in video streams from surveillance cameras is a cumbersome, error-prone and expensive task. Often, the incurred costs are prohibitive for real-time monitoring. This leads to data being stored locally or transmitted to a central storage site for post-incident examination. The required communication links and archiving of the video data are still expensive and this setup excludes preemptive actions to respond to imminent threats. An effective way to overcome these limitations is to build a smart camera that analyzes the data on-site, close to the sensor, and transmits alerts when relevant video sequences are detected. Deep neural networks (DNNs) have come to outperform humans in visual classifications tasks and are also performing exceptionally well on other computer vision tasks. The concept of DNNs and Convolutional Networks (ConvNets) can easily be extended to make use of higher-dimensional input data such as multispectral data. We explore this opportunity in terms of achievable accuracy and required computational effort. To analyze the precision of DNNs for scene labeling in an urban surveillance scenario we have created a dataset with 8 classes obtained in a field experiment. We combine an RGB camera with a 25-channel VIS-NIR snapshot sensor to assess the potential of multispectral image data for target classification. We evaluate several new DNNs, showing that the spectral information fused together with the RGB frames can be used to improve the accuracy of the system or to achieve similar accuracy with a 3x smaller computation effort. We achieve a very high per-pixel accuracy of 99.1%. Even for scarcely occurring, but particularly interesting classes, such as cars, 75% of the pixels are labeled correctly with errors occurring only around the border of the objects. This high accuracy was obtained with a training set of only 30 labeled images, paving the way for fast adaptation to various application scenarios.

Effects of uncertainty and variability on population declines and IUCN Red List classifications.

PubMed

Rueda-Cediel, Pamela; Anderson, Kurt E; Regan, Tracey J; Regan, Helen M

2018-01-22

The International Union for Conservation of Nature (IUCN) Red List Categories and Criteria is a quantitative framework for classifying species according to extinction risk. Population models may be used to estimate extinction risk or population declines. Uncertainty and variability arise in threat classifications through measurement and process error in empirical data and uncertainty in the models used to estimate extinction risk and population declines. Furthermore, species traits are known to affect extinction risk. We investigated the effects of measurement and process error, model type, population growth rate, and age at first reproduction on the reliability of risk classifications based on projected population declines on IUCN Red List classifications. We used an age-structured population model to simulate true population trajectories with different growth rates, reproductive ages and levels of variation, and subjected them to measurement error. We evaluated the ability of scalar and matrix models parameterized with these simulated time series to accurately capture the IUCN Red List classification generated with true population declines. Under all levels of measurement error tested and low process error, classifications were reasonably accurate; scalar and matrix models yielded roughly the same rate of misclassifications, but the distribution of errors differed; matrix models led to greater overestimation of extinction risk than underestimations; process error tended to contribute to misclassifications to a greater extent than measurement error; and more misclassifications occurred for fast, rather than slow, life histories. These results indicate that classifications of highly threatened taxa (i.e., taxa with low growth rates) under criterion A are more likely to be reliable than for less threatened taxa when assessed with population models. Greater scrutiny needs to be placed on data used to parameterize population models for species with high growth rates, particularly when available evidence indicates a potential transition to higher risk categories. © 2018 Society for Conservation Biology.

Human Error Assessment and Reduction Technique (HEART) and Human Factor Analysis and Classification System (HFACS)

NASA Technical Reports Server (NTRS)

Alexander, Tiffaney Miller

2017-01-01

Research results have shown that more than half of aviation, aerospace and aeronautics mishaps incidents are attributed to human error. As a part of Safety within space exploration ground processing operations, the identification and/or classification of underlying contributors and causes of human error must be identified, in order to manage human error. This research provides a framework and methodology using the Human Error Assessment and Reduction Technique (HEART) and Human Factor Analysis and Classification System (HFACS), as an analysis tool to identify contributing factors, their impact on human error events, and predict the Human Error probabilities (HEPs) of future occurrences. This research methodology was applied (retrospectively) to six (6) NASA ground processing operations scenarios and thirty (30) years of Launch Vehicle related mishap data. This modifiable framework can be used and followed by other space and similar complex operations.

Human Error Assessment and Reduction Technique (HEART) and Human Factor Analysis and Classification System (HFACS)

NASA Technical Reports Server (NTRS)

Alexander, Tiffaney Miller

2017-01-01

Research results have shown that more than half of aviation, aerospace and aeronautics mishaps/incidents are attributed to human error. As a part of Safety within space exploration ground processing operations, the identification and/or classification of underlying contributors and causes of human error must be identified, in order to manage human error. This research provides a framework and methodology using the Human Error Assessment and Reduction Technique (HEART) and Human Factor Analysis and Classification System (HFACS), as an analysis tool to identify contributing factors, their impact on human error events, and predict the Human Error probabilities (HEPs) of future occurrences. This research methodology was applied (retrospectively) to six (6) NASA ground processing operations scenarios and thirty (30) years of Launch Vehicle related mishap data. This modifiable framework can be used and followed by other space and similar complex operations.

Human Error Assessment and Reduction Technique (HEART) and Human Factor Analysis and Classification System (HFACS)

NASA Technical Reports Server (NTRS)

Alexander, Tiffaney Miller

2017-01-01

Research results have shown that more than half of aviation, aerospace and aeronautics mishaps incidents are attributed to human error. As a part of Quality within space exploration ground processing operations, the identification and or classification of underlying contributors and causes of human error must be identified, in order to manage human error.This presentation will provide a framework and methodology using the Human Error Assessment and Reduction Technique (HEART) and Human Factor Analysis and Classification System (HFACS), as an analysis tool to identify contributing factors, their impact on human error events, and predict the Human Error probabilities (HEPs) of future occurrences. This research methodology was applied (retrospectively) to six (6) NASA ground processing operations scenarios and thirty (30) years of Launch Vehicle related mishap data. This modifiable framework can be used and followed by other space and similar complex operations.

Factors That Affect Large Subunit Ribosomal DNA Amplicon Sequencing Studies of Fungal Communities: Classification Method, Primer Choice, and Error

PubMed Central

Porter, Teresita M.; Golding, G. Brian

2012-01-01

Nuclear large subunit ribosomal DNA is widely used in fungal phylogenetics and to an increasing extent also amplicon-based environmental sequencing. The relatively short reads produced by next-generation sequencing, however, makes primer choice and sequence error important variables for obtaining accurate taxonomic classifications. In this simulation study we tested the performance of three classification methods: 1) a similarity-based method (BLAST + Metagenomic Analyzer, MEGAN); 2) a composition-based method (Ribosomal Database Project naïve Bayesian classifier, NBC); and, 3) a phylogeny-based method (Statistical Assignment Package, SAP). We also tested the effects of sequence length, primer choice, and sequence error on classification accuracy and perceived community composition. Using a leave-one-out cross validation approach, results for classifications to the genus rank were as follows: BLAST + MEGAN had the lowest error rate and was particularly robust to sequence error; SAP accuracy was highest when long LSU query sequences were classified; and, NBC runs significantly faster than the other tested methods. All methods performed poorly with the shortest 50–100 bp sequences. Increasing simulated sequence error reduced classification accuracy. Community shifts were detected due to sequence error and primer selection even though there was no change in the underlying community composition. Short read datasets from individual primers, as well as pooled datasets, appear to only approximate the true community composition. We hope this work informs investigators of some of the factors that affect the quality and interpretation of their environmental gene surveys. PMID:22558215

Masked and unmasked error-related potentials during continuous control and feedback

NASA Astrophysics Data System (ADS)

Lopes Dias, Catarina; Sburlea, Andreea I.; Müller-Putz, Gernot R.

2018-06-01

The detection of error-related potentials (ErrPs) in tasks with discrete feedback is well established in the brain–computer interface (BCI) field. However, the decoding of ErrPs in tasks with continuous feedback is still in its early stages. Objective. We developed a task in which subjects have continuous control of a cursor’s position by means of a joystick. The cursor’s position was shown to the participants in two different modalities of continuous feedback: normal and jittered. The jittered feedback was created to mimic the instability that could exist if participants controlled the trajectory directly with brain signals. Approach. This paper studies the electroencephalographic (EEG)—measurable signatures caused by a loss of control over the cursor’s trajectory, causing a target miss. Main results. In both feedback modalities, time-locked potentials revealed the typical frontal-central components of error-related potentials. Errors occurring during the jittered feedback (masked errors) were delayed in comparison to errors occurring during normal feedback (unmasked errors). Masked errors displayed lower peak amplitudes than unmasked errors. Time-locked classification analysis allowed a good distinction between correct and error classes (average Cohen-, average TPR  =  81.8% and average TNR  =  96.4%). Time-locked classification analysis between masked error and unmasked error classes revealed results at chance level (average Cohen-, average TPR  =  60.9% and average TNR  =  58.3%). Afterwards, we performed asynchronous detection of ErrPs, combining both masked and unmasked trials. The asynchronous detection of ErrPs in a simulated online scenario resulted in an average TNR of 84.0% and in an average TPR of 64.9%. Significance. The time-locked classification results suggest that the masked and unmasked errors were indistinguishable in terms of classification. The asynchronous classification results suggest that the feedback modality did not hinder the asynchronous detection of ErrPs.

Improvement in defect classification efficiency by grouping disposition for reticle inspection

NASA Astrophysics Data System (ADS)

Lai, Rick; Hsu, Luke T. H.; Chang, Peter; Ho, C. H.; Tsai, Frankie; Long, Garrett; Yu, Paul; Miller, John; Hsu, Vincent; Chen, Ellison

2005-11-01

As the lithography design rule of IC manufacturing continues to migrate toward more advanced technology nodes, the mask error enhancement factor (MEEF) increases and necessitates the use of aggressive OPC features. These aggressive OPC features pose challenges to reticle inspection due to high false detection, which is time-consuming for defect classification and impacts the throughput of mask manufacturing. Moreover, higher MEEF leads to stricter mask defect capture criteria so that new generation reticle inspection tool is equipped with better detection capability. Hence, mask process induced defects, which were once undetectable, are now detected and results in the increase of total defect count. Therefore, how to review and characterize reticle defects efficiently is becoming more significant. A new defect review system called ReviewSmart has been developed based on the concept of defect grouping disposition. The review system intelligently bins repeating or similar defects into defect groups and thus allows operators to review massive defects more efficiently. Compared to the conventional defect review method, ReviewSmart not only reduces defect classification time and human judgment error, but also eliminates desensitization that is formerly inevitable. In this study, we attempt to explore the most efficient use of ReviewSmart by evaluating various defect binning conditions. The optimal binning conditions are obtained and have been verified for fidelity qualification through inspection reports (IRs) of production masks. The experiment results help to achieve the best defect classification efficiency when using ReviewSmart in the mask manufacturing and development.

Her2Net: A Deep Framework for Semantic Segmentation and Classification of Cell Membranes and Nuclei in Breast Cancer Evaluation.

PubMed

Saha, Monjoy; Chakraborty, Chandan

2018-05-01

We present an efficient deep learning framework for identifying, segmenting, and classifying cell membranes and nuclei from human epidermal growth factor receptor-2 (HER2)-stained breast cancer images with minimal user intervention. This is a long-standing issue for pathologists because the manual quantification of HER2 is error-prone, costly, and time-consuming. Hence, we propose a deep learning-based HER2 deep neural network (Her2Net) to solve this issue. The convolutional and deconvolutional parts of the proposed Her2Net framework consisted mainly of multiple convolution layers, max-pooling layers, spatial pyramid pooling layers, deconvolution layers, up-sampling layers, and trapezoidal long short-term memory (TLSTM). A fully connected layer and a softmax layer were also used for classification and error estimation. Finally, HER2 scores were calculated based on the classification results. The main contribution of our proposed Her2Net framework includes the implementation of TLSTM and a deep learning framework for cell membrane and nucleus detection, segmentation, and classification and HER2 scoring. Our proposed Her2Net achieved 96.64% precision, 96.79% recall, 96.71% F-score, 93.08% negative predictive value, 98.33% accuracy, and a 6.84% false-positive rate. Our results demonstrate the high accuracy and wide applicability of the proposed Her2Net in the context of HER2 scoring for breast cancer evaluation.

Pattern recognition invariant under changes of scale and orientation

NASA Astrophysics Data System (ADS)

Arsenault, Henri H.; Parent, Sebastien; Moisan, Sylvain

1997-08-01

We have used a modified method proposed by neiberg and Casasent to successfully classify five kinds of military vehicles. The method uses a wedge filter to achieve scale invariance, and lines in a multi-dimensional feature space correspond to each target with out-of-plane orientations over 360 degrees around a vertical axis. The images were not binarized, but were filtered in a preprocessing step to reduce aliasing. The feature vectors were normalized and orthogonalized by means of a neural network. Out-of-plane rotations of 360 degrees and scale changes of a factor of four were considered. Error-free classification was achieved.

Automatic EEG artifact removal: a weighted support vector machine approach with error correction.

PubMed

Shao, Shi-Yun; Shen, Kai-Quan; Ong, Chong Jin; Wilder-Smith, Einar P V; Li, Xiao-Ping

2009-02-01

An automatic electroencephalogram (EEG) artifact removal method is presented in this paper. Compared to past methods, it has two unique features: 1) a weighted version of support vector machine formulation that handles the inherent unbalanced nature of component classification and 2) the ability to accommodate structural information typically found in component classification. The advantages of the proposed method are demonstrated on real-life EEG recordings with comparisons made to several benchmark methods. Results show that the proposed method is preferable to the other methods in the context of artifact removal by achieving a better tradeoff between removing artifacts and preserving inherent brain activities. Qualitative evaluation of the reconstructed EEG epochs also demonstrates that after artifact removal inherent brain activities are largely preserved.

On the use of interaction error potentials for adaptive brain computer interfaces.

PubMed

Llera, A; van Gerven, M A J; Gómez, V; Jensen, O; Kappen, H J

2011-12-01

We propose an adaptive classification method for the Brain Computer Interfaces (BCI) which uses Interaction Error Potentials (IErrPs) as a reinforcement signal and adapts the classifier parameters when an error is detected. We analyze the quality of the proposed approach in relation to the misclassification of the IErrPs. In addition we compare static versus adaptive classification performance using artificial and MEG data. We show that the proposed adaptive framework significantly improves the static classification methods. Copyright © 2011 Elsevier Ltd. All rights reserved.

A Generic Deep-Learning-Based Approach for Automated Surface Inspection.

PubMed

Ren, Ruoxu; Hung, Terence; Tan, Kay Chen

2018-03-01

Automated surface inspection (ASI) is a challenging task in industry, as collecting training dataset is usually costly and related methods are highly dataset-dependent. In this paper, a generic approach that requires small training data for ASI is proposed. First, this approach builds classifier on the features of image patches, where the features are transferred from a pretrained deep learning network. Next, pixel-wise prediction is obtained by convolving the trained classifier over input image. An experiment on three public and one industrial data set is carried out. The experiment involves two tasks: 1) image classification and 2) defect segmentation. The results of proposed algorithm are compared against several best benchmarks in literature. In the classification tasks, the proposed method improves accuracy by 0.66%-25.50%. In the segmentation tasks, the proposed method reduces error escape rates by 6.00%-19.00% in three defect types and improves accuracies by 2.29%-9.86% in all seven defect types. In addition, the proposed method achieves 0.0% error escape rate in the segmentation task of industrial data.

Analyzing thematic maps and mapping for accuracy

USGS Publications Warehouse

Rosenfield, G.H.

1982-01-01

Two problems which exist while attempting to test the accuracy of thematic maps and mapping are: (1) evaluating the accuracy of thematic content, and (2) evaluating the effects of the variables on thematic mapping. Statistical analysis techniques are applicable to both these problems and include techniques for sampling the data and determining their accuracy. In addition, techniques for hypothesis testing, or inferential statistics, are used when comparing the effects of variables. A comprehensive and valid accuracy test of a classification project, such as thematic mapping from remotely sensed data, includes the following components of statistical analysis: (1) sample design, including the sample distribution, sample size, size of the sample unit, and sampling procedure; and (2) accuracy estimation, including estimation of the variance and confidence limits. Careful consideration must be given to the minimum sample size necessary to validate the accuracy of a given. classification category. The results of an accuracy test are presented in a contingency table sometimes called a classification error matrix. Usually the rows represent the interpretation, and the columns represent the verification. The diagonal elements represent the correct classifications. The remaining elements of the rows represent errors by commission, and the remaining elements of the columns represent the errors of omission. For tests of hypothesis that compare variables, the general practice has been to use only the diagonal elements from several related classification error matrices. These data are arranged in the form of another contingency table. The columns of the table represent the different variables being compared, such as different scales of mapping. The rows represent the blocking characteristics, such as the various categories of classification. The values in the cells of the tables might be the counts of correct classification or the binomial proportions of these counts divided by either the row totals or the column totals from the original classification error matrices. In hypothesis testing, when the results of tests of multiple sample cases prove to be significant, some form of statistical test must be used to separate any results that differ significantly from the others. In the past, many analyses of the data in this error matrix were made by comparing the relative magnitudes of the percentage of correct classifications, for either individual categories, the entire map or both. More rigorous analyses have used data transformations and (or) two-way classification analysis of variance. A more sophisticated step of data analysis techniques would be to use the entire classification error matrices using the methods of discrete multivariate analysis or of multiviariate analysis of variance.

Analysis of DSN software anomalies

NASA Technical Reports Server (NTRS)

Galorath, D. D.; Hecht, H.; Hecht, M.; Reifer, D. J.

1981-01-01

A categorized data base of software errors which were discovered during the various stages of development and operational use of the Deep Space Network DSN/Mark 3 System was developed. A study team identified several existing error classification schemes (taxonomies), prepared a detailed annotated bibliography of the error taxonomy literature, and produced a new classification scheme which was tuned to the DSN anomaly reporting system and encapsulated the work of others. Based upon the DSN/RCI error taxonomy, error data on approximately 1000 reported DSN/Mark 3 anomalies were analyzed, interpreted and classified. Next, error data are summarized and histograms were produced highlighting key tendencies.

Sub-pixel image classification for forest types in East Texas

NASA Astrophysics Data System (ADS)

Westbrook, Joey

Sub-pixel classification is the extraction of information about the proportion of individual materials of interest within a pixel. Landcover classification at the sub-pixel scale provides more discrimination than traditional per-pixel multispectral classifiers for pixels where the material of interest is mixed with other materials. It allows for the un-mixing of pixels to show the proportion of each material of interest. The materials of interest for this study are pine, hardwood, mixed forest and non-forest. The goal of this project was to perform a sub-pixel classification, which allows a pixel to have multiple labels, and compare the result to a traditional supervised classification, which allows a pixel to have only one label. The satellite image used was a Landsat 5 Thematic Mapper (TM) scene of the Stephen F. Austin Experimental Forest in Nacogdoches County, Texas and the four cover type classes are pine, hardwood, mixed forest and non-forest. Once classified, a multi-layer raster datasets was created that comprised four raster layers where each layer showed the percentage of that cover type within the pixel area. Percentage cover type maps were then produced and the accuracy of each was assessed using a fuzzy error matrix for the sub-pixel classifications, and the results were compared to the supervised classification in which a traditional error matrix was used. The overall accuracy of the sub-pixel classification using the aerial photo for both training and reference data had the highest (65% overall) out of the three sub-pixel classifications. This was understandable because the analyst can visually observe the cover types actually on the ground for training data and reference data, whereas using the FIA (Forest Inventory and Analysis) plot data, the analyst must assume that an entire pixel contains the exact percentage of a cover type found in a plot. An increase in accuracy was found after reclassifying each sub-pixel classification from nine classes with 10 percent interval each to five classes with 20 percent interval each. When compared to the supervised classification which has a satisfactory overall accuracy of 90%, none of the sub-pixel classification achieved the same level. However, since traditional per-pixel classifiers assign only one label to pixels throughout the landscape while sub-pixel classifications assign multiple labels to each pixel, the traditional 85% accuracy of acceptance for pixel-based classifications should not apply to sub-pixel classifications. More research is needed in order to define the level of accuracy that is deemed acceptable for sub-pixel classifications.

Neyman-Pearson classification algorithms and NP receiver operating characteristics

PubMed Central

Tong, Xin; Feng, Yang; Li, Jingyi Jessica

2018-01-01

In many binary classification applications, such as disease diagnosis and spam detection, practitioners commonly face the need to limit type I error (that is, the conditional probability of misclassifying a class 0 observation as class 1) so that it remains below a desired threshold. To address this need, the Neyman-Pearson (NP) classification paradigm is a natural choice; it minimizes type II error (that is, the conditional probability of misclassifying a class 1 observation as class 0) while enforcing an upper bound, α, on the type I error. Despite its century-long history in hypothesis testing, the NP paradigm has not been well recognized and implemented in classification schemes. Common practices that directly limit the empirical type I error to no more than α do not satisfy the type I error control objective because the resulting classifiers are likely to have type I errors much larger than α, and the NP paradigm has not been properly implemented in practice. We develop the first umbrella algorithm that implements the NP paradigm for all scoring-type classification methods, such as logistic regression, support vector machines, and random forests. Powered by this algorithm, we propose a novel graphical tool for NP classification methods: NP receiver operating characteristic (NP-ROC) bands motivated by the popular ROC curves. NP-ROC bands will help choose α in a data-adaptive way and compare different NP classifiers. We demonstrate the use and properties of the NP umbrella algorithm and NP-ROC bands, available in the R package nproc, through simulation and real data studies. PMID:29423442

Neyman-Pearson classification algorithms and NP receiver operating characteristics.

PubMed

Tong, Xin; Feng, Yang; Li, Jingyi Jessica

2018-02-01

In many binary classification applications, such as disease diagnosis and spam detection, practitioners commonly face the need to limit type I error (that is, the conditional probability of misclassifying a class 0 observation as class 1) so that it remains below a desired threshold. To address this need, the Neyman-Pearson (NP) classification paradigm is a natural choice; it minimizes type II error (that is, the conditional probability of misclassifying a class 1 observation as class 0) while enforcing an upper bound, α, on the type I error. Despite its century-long history in hypothesis testing, the NP paradigm has not been well recognized and implemented in classification schemes. Common practices that directly limit the empirical type I error to no more than α do not satisfy the type I error control objective because the resulting classifiers are likely to have type I errors much larger than α, and the NP paradigm has not been properly implemented in practice. We develop the first umbrella algorithm that implements the NP paradigm for all scoring-type classification methods, such as logistic regression, support vector machines, and random forests. Powered by this algorithm, we propose a novel graphical tool for NP classification methods: NP receiver operating characteristic (NP-ROC) bands motivated by the popular ROC curves. NP-ROC bands will help choose α in a data-adaptive way and compare different NP classifiers. We demonstrate the use and properties of the NP umbrella algorithm and NP-ROC bands, available in the R package nproc, through simulation and real data studies.

A Bio-Inspired Herbal Tea Flavour Assessment Technique

PubMed Central

Zakaria, Nur Zawatil Isqi; Masnan, Maz Jamilah; Zakaria, Ammar; Shakaff, Ali Yeon Md

2014-01-01

Herbal-based products are becoming a widespread production trend among manufacturers for the domestic and international markets. As the production increases to meet the market demand, it is very crucial for the manufacturer to ensure that their products have met specific criteria and fulfil the intended quality determined by the quality controller. One famous herbal-based product is herbal tea. This paper investigates bio-inspired flavour assessments in a data fusion framework involving an e-nose and e-tongue. The objectives are to attain good classification of different types and brands of herbal tea, classification of different flavour masking effects and finally classification of different concentrations of herbal tea. Two data fusion levels were employed in this research, low level data fusion and intermediate level data fusion. Four classification approaches; LDA, SVM, KNN and PNN were examined in search of the best classifier to achieve the research objectives. In order to evaluate the classifiers' performance, an error estimator based on k-fold cross validation and leave-one-out were applied. Classification based on GC-MS TIC data was also included as a comparison to the classification performance using fusion approaches. Generally, KNN outperformed the other classification techniques for the three flavour assessments in the low level data fusion and intermediate level data fusion. However, the classification results based on GC-MS TIC data are varied. PMID:25010697

Evaluation of normalization methods for cDNA microarray data by k-NN classification

PubMed Central

Wu, Wei; Xing, Eric P; Myers, Connie; Mian, I Saira; Bissell, Mina J

2005-01-01

Background Non-biological factors give rise to unwanted variations in cDNA microarray data. There are many normalization methods designed to remove such variations. However, to date there have been few published systematic evaluations of these techniques for removing variations arising from dye biases in the context of downstream, higher-order analytical tasks such as classification. Results Ten location normalization methods that adjust spatial- and/or intensity-dependent dye biases, and three scale methods that adjust scale differences were applied, individually and in combination, to five distinct, published, cancer biology-related cDNA microarray data sets. Leave-one-out cross-validation (LOOCV) classification error was employed as the quantitative end-point for assessing the effectiveness of a normalization method. In particular, a known classifier, k-nearest neighbor (k-NN), was estimated from data normalized using a given technique, and the LOOCV error rate of the ensuing model was computed. We found that k-NN classifiers are sensitive to dye biases in the data. Using NONRM and GMEDIAN as baseline methods, our results show that single-bias-removal techniques which remove either spatial-dependent dye bias (referred later as spatial effect) or intensity-dependent dye bias (referred later as intensity effect) moderately reduce LOOCV classification errors; whereas double-bias-removal techniques which remove both spatial- and intensity effect reduce LOOCV classification errors even further. Of the 41 different strategies examined, three two-step processes, IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS and IGLOESS-SLLOESS, all of which removed intensity effect globally and spatial effect locally, appear to reduce LOOCV classification errors most consistently and effectively across all data sets. We also found that the investigated scale normalization methods do not reduce LOOCV classification error. Conclusion Using LOOCV error of k-NNs as the evaluation criterion, three double-bias-removal normalization strategies, IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS and IGLOESS-SLLOESS, outperform other strategies for removing spatial effect, intensity effect and scale differences from cDNA microarray data. The apparent sensitivity of k-NN LOOCV classification error to dye biases suggests that this criterion provides an informative measure for evaluating normalization methods. All the computational tools used in this study were implemented using the R language for statistical computing and graphics. PMID:16045803

Evaluation of normalization methods for cDNA microarray data by k-NN classification.

PubMed

Wu, Wei; Xing, Eric P; Myers, Connie; Mian, I Saira; Bissell, Mina J

2005-07-26

Non-biological factors give rise to unwanted variations in cDNA microarray data. There are many normalization methods designed to remove such variations. However, to date there have been few published systematic evaluations of these techniques for removing variations arising from dye biases in the context of downstream, higher-order analytical tasks such as classification. Ten location normalization methods that adjust spatial- and/or intensity-dependent dye biases, and three scale methods that adjust scale differences were applied, individually and in combination, to five distinct, published, cancer biology-related cDNA microarray data sets. Leave-one-out cross-validation (LOOCV) classification error was employed as the quantitative end-point for assessing the effectiveness of a normalization method. In particular, a known classifier, k-nearest neighbor (k-NN), was estimated from data normalized using a given technique, and the LOOCV error rate of the ensuing model was computed. We found that k-NN classifiers are sensitive to dye biases in the data. Using NONRM and GMEDIAN as baseline methods, our results show that single-bias-removal techniques which remove either spatial-dependent dye bias (referred later as spatial effect) or intensity-dependent dye bias (referred later as intensity effect) moderately reduce LOOCV classification errors; whereas double-bias-removal techniques which remove both spatial- and intensity effect reduce LOOCV classification errors even further. Of the 41 different strategies examined, three two-step processes, IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS and IGLOESS-SLLOESS, all of which removed intensity effect globally and spatial effect locally, appear to reduce LOOCV classification errors most consistently and effectively across all data sets. We also found that the investigated scale normalization methods do not reduce LOOCV classification error. Using LOOCV error of k-NNs as the evaluation criterion, three double-bias-removal normalization strategies, IGLOESS-SLFILTERW7, ISTSPLINE-SLLOESS and IGLOESS-SLLOESS, outperform other strategies for removing spatial effect, intensity effect and scale differences from cDNA microarray data. The apparent sensitivity of k-NN LOOCV classification error to dye biases suggests that this criterion provides an informative measure for evaluating normalization methods. All the computational tools used in this study were implemented using the R language for statistical computing and graphics.

Correlation-based pattern recognition for implantable defibrillators.

PubMed Central

Wilkins, J.

1996-01-01

An estimated 300,000 Americans die each year from cardiac arrhythmias. Historically, drug therapy or surgery were the only treatment options available for patients suffering from arrhythmias. Recently, implantable arrhythmia management devices have been developed. These devices allow abnormal cardiac rhythms to be sensed and corrected in vivo. Proper arrhythmia classification is critical to selecting the appropriate therapeutic intervention. The classification problem is made more challenging by the power/computation constraints imposed by the short battery life of implantable devices. Current devices utilize heart rate-based classification algorithms. Although easy to implement, rate-based approaches have unacceptably high error rates in distinguishing supraventricular tachycardia (SVT) from ventricular tachycardia (VT). Conventional morphology assessment techniques used in ECG analysis often require too much computation to be practical for implantable devices. In this paper, a computationally-efficient, arrhythmia classification architecture using correlation-based morphology assessment is presented. The architecture classifies individuals heart beats by assessing similarity between an incoming cardiac signal vector and a series of prestored class templates. A series of these beat classifications are used to make an overall rhythm assessment. The system makes use of several new results in the field of pattern recognition. The resulting system achieved excellent accuracy in discriminating SVT and VT. PMID:8947674

Bayesian learning for spatial filtering in an EEG-based brain-computer interface.

PubMed

Zhang, Haihong; Yang, Huijuan; Guan, Cuntai

2013-07-01

Spatial filtering for EEG feature extraction and classification is an important tool in brain-computer interface. However, there is generally no established theory that links spatial filtering directly to Bayes classification error. To address this issue, this paper proposes and studies a Bayesian analysis theory for spatial filtering in relation to Bayes error. Following the maximum entropy principle, we introduce a gamma probability model for describing single-trial EEG power features. We then formulate and analyze the theoretical relationship between Bayes classification error and the so-called Rayleigh quotient, which is a function of spatial filters and basically measures the ratio in power features between two classes. This paper also reports our extensive study that examines the theory and its use in classification, using three publicly available EEG data sets and state-of-the-art spatial filtering techniques and various classifiers. Specifically, we validate the positive relationship between Bayes error and Rayleigh quotient in real EEG power features. Finally, we demonstrate that the Bayes error can be practically reduced by applying a new spatial filter with lower Rayleigh quotient.

Sources of error in estimating truck traffic from automatic vehicle classification data

DOT National Transportation Integrated Search

1998-10-01

Truck annual average daily traffic estimation errors resulting from sample classification counts are computed in this paper under two scenarios. One scenario investigates an improper factoring procedure that may be used by highway agencies. The study...

Using reconstructed IVUS images for coronary plaque classification.

PubMed

Caballero, Karla L; Barajas, Joel; Pujol, Oriol; Rodriguez, Oriol; Radeva, Petia

2007-01-01

Coronary plaque rupture is one of the principal causes of sudden death in western societies. Reliable diagnostic of the different plaque types are of great interest for the medical community the predicting their evolution and applying an effective treatment. To achieve this, a tissue classification must be performed. Intravascular Ultrasound (IVUS) represents a technique to explore the vessel walls and to observe its histological properties. In this paper, a method to reconstruct IVUS images from the raw Radio Frequency (RF) data coming from ultrasound catheter is proposed. This framework offers a normalization scheme to compare accurately different patient studies. The automatic tissue classification is based on texture analysis and Adapting Boosting (Adaboost) learning technique combined with Error Correcting Output Codes (ECOC). In this study, 9 in-vivo cases are reconstructed with 7 different parameter set. This method improves the classification rate based on images, yielding a 91% of well-detected tissue using the best parameter set. It also reduces the inter-patient variability compared with the analysis of DICOM images, which are obtained from the commercial equipment.

Style consistent classification of isogenous patterns.

PubMed

Sarkar, Prateek; Nagy, George

2005-01-01

In many applications of pattern recognition, patterns appear together in groups (fields) that have a common origin. For example, a printed word is usually a field of character patterns printed in the same font. A common origin induces consistency of style in features measured on patterns. The features of patterns co-occurring in a field are statistically dependent because they share the same, albeit unknown, style. Style constrained classifiers achieve higher classification accuracy by modeling such dependence among patterns in a field. Effects of style consistency on the distributions of field-features (concatenation of pattern features) can be modeled by hierarchical mixtures. Each field derives from a mixture of styles, while, within a field, a pattern derives from a class-style conditional mixture of Gaussians. Based on this model, an optimal style constrained classifier processes entire fields of patterns rendered in a consistent but unknown style. In a laboratory experiment, style constrained classification reduced errors on fields of printed digits by nearly 25 percent over singlet classifiers. Longer fields favor our classification method because they furnish more information about the underlying style.

Automated Classification of Phonological Errors in Aphasic Language

PubMed Central

Ahuja, Sanjeev B.; Reggia, James A.; Berndt, Rita S.

1984-01-01

Using heuristically-guided state space search, a prototype program has been developed to simulate and classify phonemic errors occurring in the speech of neurologically-impaired patients. Simulations are based on an interchangeable rule/operator set of elementary errors which represent a theory of phonemic processing faults. This work introduces and evaluates a novel approach to error simulation and classification, it provides a prototype simulation tool for neurolinguistic research, and it forms the initial phase of a larger research effort involving computer modelling of neurolinguistic processes.

ANALYSIS OF A CLASSIFICATION ERROR MATRIX USING CATEGORICAL DATA TECHNIQUES.

USGS Publications Warehouse

Rosenfield, George H.; Fitzpatrick-Lins, Katherine

1984-01-01

Summary form only given. A classification error matrix typically contains tabulation results of an accuracy evaluation of a thematic classification, such as that of a land use and land cover map. The diagonal elements of the matrix represent the counts corrected, and the usual designation of classification accuracy has been the total percent correct. The nondiagonal elements of the matrix have usually been neglected. The classification error matrix is known in statistical terms as a contingency table of categorical data. As an example, an application of these methodologies to a problem of remotely sensed data concerning two photointerpreters and four categories of classification indicated that there is no significant difference in the interpretation between the two photointerpreters, and that there are significant differences among the interpreted category classifications. However, two categories, oak and cottonwood, are not separable in classification in this experiment at the 0. 51 percent probability. A coefficient of agreement is determined for the interpreted map as a whole, and individually for each of the interpreted categories. A conditional coefficient of agreement for the individual categories is compared to other methods for expressing category accuracy which have already been presented in the remote sensing literature.

New wideband radar target classification method based on neural learning and modified Euclidean metric

NASA Astrophysics Data System (ADS)

Jiang, Yicheng; Cheng, Ping; Ou, Yangkui

2001-09-01

A new method for target classification of high-range resolution radar is proposed. It tries to use neural learning to obtain invariant subclass features of training range profiles. A modified Euclidean metric based on the Box-Cox transformation technique is investigated for Nearest Neighbor target classification improvement. The classification experiments using real radar data of three different aircraft have demonstrated that classification error can reduce 8% if this method proposed in this paper is chosen instead of the conventional method. The results of this paper have shown that by choosing an optimized metric, it is indeed possible to reduce the classification error without increasing the number of samples.

What Do Spelling Errors Tell Us? Classification and Analysis of Errors Made by Greek Schoolchildren with and without Dyslexia

ERIC Educational Resources Information Center

Protopapas, Athanassios; Fakou, Aikaterini; Drakopoulou, Styliani; Skaloumbakas, Christos; Mouzaki, Angeliki

2013-01-01

In this study we propose a classification system for spelling errors and determine the most common spelling difficulties of Greek children with and without dyslexia. Spelling skills of 542 children from the general population and 44 children with dyslexia, Grades 3-4 and 7, were assessed with a dictated common word list and age-appropriate…

Effectiveness of Global Features for Automatic Medical Image Classification and Retrieval – the experiences of OHSU at ImageCLEFmed

PubMed Central

Kalpathy-Cramer, Jayashree; Hersh, William

2008-01-01

In 2006 and 2007, Oregon Health & Science University (OHSU) participated in the automatic image annotation task for medical images at ImageCLEF, an annual international benchmarking event that is part of the Cross Language Evaluation Forum (CLEF). The goal of the automatic annotation task was to classify 1000 test images based on the Image Retrieval in Medical Applications (IRMA) code, given a set of 10,000 training images. There were 116 distinct classes in 2006 and 2007. We evaluated the efficacy of a variety of primarily global features for this classification task. These included features based on histograms, gray level correlation matrices and the gist technique. A multitude of classifiers including k-nearest neighbors, two-level neural networks, support vector machines, and maximum likelihood classifiers were evaluated. Our official error rates for the 1000 test images were 26% in 2006 using the flat classification structure. The error count in 2007 was 67.8 using the hierarchical classification error computation based on the IRMA code in 2007. Confusion matrices as well as clustering experiments were used to identify visually similar classes. The use of the IRMA code did not help us in the classification task as the semantic hierarchy of the IRMA classes did not correspond well with the hierarchy based on clustering of image features that we used. Our most frequent misclassification errors were along the view axis. Subsequent experiments based on a two-stage classification system decreased our error rate to 19.8% for the 2006 dataset and our error count to 55.4 for the 2007 data. PMID:19884953

Moments and Root-Mean-Square Error of the Bayesian MMSE Estimator of Classification Error in the Gaussian Model.

PubMed

Zollanvari, Amin; Dougherty, Edward R

2014-06-01

The most important aspect of any classifier is its error rate, because this quantifies its predictive capacity. Thus, the accuracy of error estimation is critical. Error estimation is problematic in small-sample classifier design because the error must be estimated using the same data from which the classifier has been designed. Use of prior knowledge, in the form of a prior distribution on an uncertainty class of feature-label distributions to which the true, but unknown, feature-distribution belongs, can facilitate accurate error estimation (in the mean-square sense) in circumstances where accurate completely model-free error estimation is impossible. This paper provides analytic asymptotically exact finite-sample approximations for various performance metrics of the resulting Bayesian Minimum Mean-Square-Error (MMSE) error estimator in the case of linear discriminant analysis (LDA) in the multivariate Gaussian model. These performance metrics include the first, second, and cross moments of the Bayesian MMSE error estimator with the true error of LDA, and therefore, the Root-Mean-Square (RMS) error of the estimator. We lay down the theoretical groundwork for Kolmogorov double-asymptotics in a Bayesian setting, which enables us to derive asymptotic expressions of the desired performance metrics. From these we produce analytic finite-sample approximations and demonstrate their accuracy via numerical examples. Various examples illustrate the behavior of these approximations and their use in determining the necessary sample size to achieve a desired RMS. The Supplementary Material contains derivations for some equations and added figures.

Error-related brain activity and error awareness in an error classification paradigm.

PubMed

Di Gregorio, Francesco; Steinhauser, Marco; Maier, Martin E

2016-10-01

Error-related brain activity has been linked to error detection enabling adaptive behavioral adjustments. However, it is still unclear which role error awareness plays in this process. Here, we show that the error-related negativity (Ne/ERN), an event-related potential reflecting early error monitoring, is dissociable from the degree of error awareness. Participants responded to a target while ignoring two different incongruent distractors. After responding, they indicated whether they had committed an error, and if so, whether they had responded to one or to the other distractor. This error classification paradigm allowed distinguishing partially aware errors, (i.e., errors that were noticed but misclassified) and fully aware errors (i.e., errors that were correctly classified). The Ne/ERN was larger for partially aware errors than for fully aware errors. Whereas this speaks against the idea that the Ne/ERN foreshadows the degree of error awareness, it confirms the prediction of a computational model, which relates the Ne/ERN to post-response conflict. This model predicts that stronger distractor processing - a prerequisite of error classification in our paradigm - leads to lower post-response conflict and thus a smaller Ne/ERN. This implies that the relationship between Ne/ERN and error awareness depends on how error awareness is related to response conflict in a specific task. Our results further indicate that the Ne/ERN but not the degree of error awareness determines adaptive performance adjustments. Taken together, we conclude that the Ne/ERN is dissociable from error awareness and foreshadows adaptive performance adjustments. Our results suggest that the relationship between the Ne/ERN and error awareness is correlative and mediated by response conflict. Copyright © 2016 Elsevier Inc. All rights reserved.

A Framework of Temporal-Spatial Descriptors-Based Feature Extraction for Improved Myoelectric Pattern Recognition.

PubMed

Khushaba, Rami N; Al-Timemy, Ali H; Al-Ani, Ahmed; Al-Jumaily, Adel

2017-10-01

The extraction of the accurate and efficient descriptors of muscular activity plays an important role in tackling the challenging problem of myoelectric control of powered prostheses. In this paper, we present a new feature extraction framework that aims to give an enhanced representation of muscular activities through increasing the amount of information that can be extracted from individual and combined electromyogram (EMG) channels. We propose to use time-domain descriptors (TDDs) in estimating the EMG signal power spectrum characteristics; a step that preserves the computational power required for the construction of spectral features. Subsequently, TDD is used in a process that involves: 1) representing the temporal evolution of the EMG signals by progressively tracking the correlation between the TDD extracted from each analysis time window and a nonlinearly mapped version of it across the same EMG channel and 2) representing the spatial coherence between the different EMG channels, which is achieved by calculating the correlation between the TDD extracted from the differences of all possible combinations of pairs of channels and their nonlinearly mapped versions. The proposed temporal-spatial descriptors (TSDs) are validated on multiple sparse and high-density (HD) EMG data sets collected from a number of intact-limbed and amputees performing a large number of hand and finger movements. Classification results showed significant reductions in the achieved error rates in comparison to other methods, with the improvement of at least 8% on average across all subjects. Additionally, the proposed TSDs achieved significantly well in problems with HD-EMG with average classification errors of <5% across all subjects using windows lengths of 50 ms only.

Toward attenuating the impact of arm positions on electromyography pattern-recognition based motion classification in transradial amputees

PubMed Central

2012-01-01

Background Electromyography (EMG) pattern-recognition based control strategies for multifunctional myoelectric prosthesis systems have been studied commonly in a controlled laboratory setting. Before these myoelectric prosthesis systems are clinically viable, it will be necessary to assess the effect of some disparities between the ideal laboratory setting and practical use on the control performance. One important obstacle is the impact of arm position variation that causes the changes of EMG pattern when performing identical motions in different arm positions. This study aimed to investigate the impacts of arm position variation on EMG pattern-recognition based motion classification in upper-limb amputees and the solutions for reducing these impacts. Methods With five unilateral transradial (TR) amputees, the EMG signals and tri-axial accelerometer mechanomyography (ACC-MMG) signals were simultaneously collected from both amputated and intact arms when performing six classes of arm and hand movements in each of five arm positions that were considered in the study. The effect of the arm position changes was estimated in terms of motion classification error and compared between amputated and intact arms. Then the performance of three proposed methods in attenuating the impact of arm positions was evaluated. Results With EMG signals, the average intra-position and inter-position classification errors across all five arm positions and five subjects were around 7.3% and 29.9% from amputated arms, respectively, about 1.0% and 10% low in comparison with those from intact arms. While ACC-MMG signals could yield a similar intra-position classification error (9.9%) as EMG, they had much higher inter-position classification error with an average value of 81.1% over the arm positions and the subjects. When the EMG data from all five arm positions were involved in the training set, the average classification error reached a value of around 10.8% for amputated arms. Using a two-stage cascade classifier, the average classification error was around 9.0% over all five arm positions. Reducing ACC-MMG channels from 8 to 2 only increased the average position classification error across all five arm positions from 0.7% to 1.0% in amputated arms. Conclusions The performance of EMG pattern-recognition based method in classifying movements strongly depends on arm positions. This dependency is a little stronger in intact arm than in amputated arm, which suggests that the investigations associated with practical use of a myoelectric prosthesis should use the limb amputees as subjects instead of using able-body subjects. The two-stage cascade classifier mode with ACC-MMG for limb position identification and EMG for limb motion classification may be a promising way to reduce the effect of limb position variation on classification performance. PMID:23036049

Long-term surface EMG monitoring using K-means clustering and compressive sensing

NASA Astrophysics Data System (ADS)

Balouchestani, Mohammadreza; Krishnan, Sridhar

2015-05-01

In this work, we present an advanced K-means clustering algorithm based on Compressed Sensing theory (CS) in combination with the K-Singular Value Decomposition (K-SVD) method for Clustering of long-term recording of surface Electromyography (sEMG) signals. The long-term monitoring of sEMG signals aims at recording of the electrical activity produced by muscles which are very useful procedure for treatment and diagnostic purposes as well as for detection of various pathologies. The proposed algorithm is examined for three scenarios of sEMG signals including healthy person (sEMG-Healthy), a patient with myopathy (sEMG-Myopathy), and a patient with neuropathy (sEMG-Neuropathr), respectively. The proposed algorithm can easily scan large sEMG datasets of long-term sEMG recording. We test the proposed algorithm with Principal Component Analysis (PCA) and Linear Correlation Coefficient (LCC) dimensionality reduction methods. Then, the output of the proposed algorithm is fed to K-Nearest Neighbours (K-NN) and Probabilistic Neural Network (PNN) classifiers in order to calclute the clustering performance. The proposed algorithm achieves a classification accuracy of 99.22%. This ability allows reducing 17% of Average Classification Error (ACE), 9% of Training Error (TE), and 18% of Root Mean Square Error (RMSE). The proposed algorithm also reduces 14% clustering energy consumption compared to the existing K-Means clustering algorithm.

On the identification of sleep stages in mouse electroencephalography time-series.

PubMed

Lampert, Thomas; Plano, Andrea; Austin, Jim; Platt, Bettina

2015-05-15

The automatic identification of sleep stages in electroencephalography (EEG) time-series is a long desired goal for researchers concerned with the study of sleep disorders. This paper presents advances towards achieving this goal, with particular application to EEG time-series recorded from mice. Approaches in the literature apply supervised learning classifiers, however, these do not reach the performance levels required for use within a laboratory. In this paper, detection reliability is increased, most notably in the case of REM stage identification, by naturally decomposing the problem and applying a support vector machine (SVM) based classifier to each of the EEG channels. Their outputs are integrated within a multiple classifier system. Furthermore, there exists no general consensus on the ideal choice of parameter values in such systems. Therefore, an investigation into the effects upon the classification performance is presented by varying parameters such as the epoch length; features size; number of training samples; and the method for calculating the power spectral density estimate. Finally, the results of these investigations are brought together to demonstrate the performance of the proposed classification algorithm in two cases: intra-animal classification and inter-animal classification. It is shown that, within a dataset of 10 EEG recordings, and using less than 1% of an EEG as training data, a mean classification errors of Awake 6.45%, NREM 5.82%, and REM 6.65% (with standard deviations less than 0.6%) are achieved in intra-animal analysis and, when using the equivalent of 7% of one EEG as training data, Awake 10.19%, NREM 7.75%, and REM 17.43% are achieved in inter-animal analysis (with mean standard deviations of 6.42%, 2.89%, and 9.69% respectively). A software package implementing the proposed approach will be made available through Cybula Ltd. Copyright © 2015 Elsevier B.V. All rights reserved.

Integrated Low-Rank-Based Discriminative Feature Learning for Recognition.

PubMed

Zhou, Pan; Lin, Zhouchen; Zhang, Chao

2016-05-01

Feature learning plays a central role in pattern recognition. In recent years, many representation-based feature learning methods have been proposed and have achieved great success in many applications. However, these methods perform feature learning and subsequent classification in two separate steps, which may not be optimal for recognition tasks. In this paper, we present a supervised low-rank-based approach for learning discriminative features. By integrating latent low-rank representation (LatLRR) with a ridge regression-based classifier, our approach combines feature learning with classification, so that the regulated classification error is minimized. In this way, the extracted features are more discriminative for the recognition tasks. Our approach benefits from a recent discovery on the closed-form solutions to noiseless LatLRR. When there is noise, a robust Principal Component Analysis (PCA)-based denoising step can be added as preprocessing. When the scale of a problem is large, we utilize a fast randomized algorithm to speed up the computation of robust PCA. Extensive experimental results demonstrate the effectiveness and robustness of our method.

Algorithmic Classification of Five Characteristic Types of Paraphasias.

PubMed

Fergadiotis, Gerasimos; Gorman, Kyle; Bedrick, Steven

2016-12-01

This study was intended to evaluate a series of algorithms developed to perform automatic classification of paraphasic errors (formal, semantic, mixed, neologistic, and unrelated errors). We analyzed 7,111 paraphasias from the Moss Aphasia Psycholinguistics Project Database (Mirman et al., 2010) and evaluated the classification accuracy of 3 automated tools. First, we used frequency norms from the SUBTLEXus database (Brysbaert & New, 2009) to differentiate nonword errors and real-word productions. Then we implemented a phonological-similarity algorithm to identify phonologically related real-word errors. Last, we assessed the performance of a semantic-similarity criterion that was based on word2vec (Mikolov, Yih, & Zweig, 2013). Overall, the algorithmic classification replicated human scoring for the major categories of paraphasias studied with high accuracy. The tool that was based on the SUBTLEXus frequency norms was more than 97% accurate in making lexicality judgments. The phonological-similarity criterion was approximately 91% accurate, and the overall classification accuracy of the semantic classifier ranged from 86% to 90%. Overall, the results highlight the potential of tools from the field of natural language processing for the development of highly reliable, cost-effective diagnostic tools suitable for collecting high-quality measurement data for research and clinical purposes.

Human error analysis of commercial aviation accidents using the human factors analysis and classification system (HFACS)

DOT National Transportation Integrated Search

2001-02-01

The Human Factors Analysis and Classification System (HFACS) is a general human error framework : originally developed and tested within the U.S. military as a tool for investigating and analyzing the human : causes of aviation accidents. Based upon ...

Current Assessment and Classification of Suicidal Phenomena using the FDA 2012 Draft Guidance Document on Suicide Assessment: A Critical Review.

PubMed

Sheehan, David V; Giddens, Jennifer M; Sheehan, Kathy Harnett

2014-09-01

Standard international classification criteria require that classification categories be comprehensive to avoid type II error. Categories should be mutually exclusive and definitions should be clear and unambiguous (to avoid type I and type II errors). In addition, the classification system should be robust enough to last over time and provide comparability between data collections. This article was designed to evaluate the extent to which the classification system contained in the United States Food and Drug Administration 2012 Draft Guidance for the prospective assessment and classification of suicidal ideation and behavior in clinical trials meets these criteria. A critical review is used to assess the extent to which the proposed categories contained in the Food and Drug Administration 2012 Draft Guidance are comprehensive, unambiguous, and robust. Assumptions that underlie the classification system are also explored. The Food and Drug Administration classification system contained in the 2012 Draft Guidance does not capture the full range of suicidal ideation and behavior (type II error). Definitions, moreover, are frequently ambiguous (susceptible to multiple interpretations), and the potential for misclassification (type I and type II errors) is compounded by frequent mismatches in category titles and definitions. These issues have the potential to compromise data comparability within clinical trial sites, across sites, and over time. These problems need to be remedied because of the potential for flawed data output and consequent threats to public health, to research on the safety of medications, and to the search for effective medication treatments for suicidality.

An experimental study of interstitial lung tissue classification in HRCT images using ANN and role of cost functions

NASA Astrophysics Data System (ADS)

Dash, Jatindra K.; Kale, Mandar; Mukhopadhyay, Sudipta; Khandelwal, Niranjan; Prabhakar, Nidhi; Garg, Mandeep; Kalra, Naveen

2017-03-01

In this paper, we investigate the effect of the error criteria used during a training phase of the artificial neural network (ANN) on the accuracy of the classifier for classification of lung tissues affected with Interstitial Lung Diseases (ILD). Mean square error (MSE) and the cross-entropy (CE) criteria are chosen being most popular choice in state-of-the-art implementations. The classification experiment performed on the six interstitial lung disease (ILD) patterns viz. Consolidation, Emphysema, Ground Glass Opacity, Micronodules, Fibrosis and Healthy from MedGIFT database. The texture features from an arbitrary region of interest (AROI) are extracted using Gabor filter. Two different neural networks are trained with the scaled conjugate gradient back propagation algorithm with MSE and CE error criteria function respectively for weight updation. Performance is evaluated in terms of average accuracy of these classifiers using 4 fold cross-validation. Each network is trained for five times for each fold with randomly initialized weight vectors and accuracies are computed. Significant improvement in classification accuracy is observed when ANN is trained by using CE (67.27%) as error function compared to MSE (63.60%). Moreover, standard deviation of the classification accuracy for the network trained with CE (6.69) error criteria is found less as compared to network trained with MSE (10.32) criteria.

Construction of a Calibrated Probabilistic Classification Catalog: Application to 50k Variable Sources in the All-Sky Automated Survey

NASA Astrophysics Data System (ADS)

Richards, Joseph W.; Starr, Dan L.; Miller, Adam A.; Bloom, Joshua S.; Butler, Nathaniel R.; Brink, Henrik; Crellin-Quick, Arien

2012-12-01

With growing data volumes from synoptic surveys, astronomers necessarily must become more abstracted from the discovery and introspection processes. Given the scarcity of follow-up resources, there is a particularly sharp onus on the frameworks that replace these human roles to provide accurate and well-calibrated probabilistic classification catalogs. Such catalogs inform the subsequent follow-up, allowing consumers to optimize the selection of specific sources for further study and permitting rigorous treatment of classification purities and efficiencies for population studies. Here, we describe a process to produce a probabilistic classification catalog of variability with machine learning from a multi-epoch photometric survey. In addition to producing accurate classifications, we show how to estimate calibrated class probabilities and motivate the importance of probability calibration. We also introduce a methodology for feature-based anomaly detection, which allows discovery of objects in the survey that do not fit within the predefined class taxonomy. Finally, we apply these methods to sources observed by the All-Sky Automated Survey (ASAS), and release the Machine-learned ASAS Classification Catalog (MACC), a 28 class probabilistic classification catalog of 50,124 ASAS sources in the ASAS Catalog of Variable Stars. We estimate that MACC achieves a sub-20% classification error rate and demonstrate that the class posterior probabilities are reasonably calibrated. MACC classifications compare favorably to the classifications of several previous domain-specific ASAS papers and to the ASAS Catalog of Variable Stars, which had classified only 24% of those sources into one of 12 science classes.

CONSTRUCTION OF A CALIBRATED PROBABILISTIC CLASSIFICATION CATALOG: APPLICATION TO 50k VARIABLE SOURCES IN THE ALL-SKY AUTOMATED SURVEY

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

Richards, Joseph W.; Starr, Dan L.; Miller, Adam A.

2012-12-15

With growing data volumes from synoptic surveys, astronomers necessarily must become more abstracted from the discovery and introspection processes. Given the scarcity of follow-up resources, there is a particularly sharp onus on the frameworks that replace these human roles to provide accurate and well-calibrated probabilistic classification catalogs. Such catalogs inform the subsequent follow-up, allowing consumers to optimize the selection of specific sources for further study and permitting rigorous treatment of classification purities and efficiencies for population studies. Here, we describe a process to produce a probabilistic classification catalog of variability with machine learning from a multi-epoch photometric survey. In additionmore » to producing accurate classifications, we show how to estimate calibrated class probabilities and motivate the importance of probability calibration. We also introduce a methodology for feature-based anomaly detection, which allows discovery of objects in the survey that do not fit within the predefined class taxonomy. Finally, we apply these methods to sources observed by the All-Sky Automated Survey (ASAS), and release the Machine-learned ASAS Classification Catalog (MACC), a 28 class probabilistic classification catalog of 50,124 ASAS sources in the ASAS Catalog of Variable Stars. We estimate that MACC achieves a sub-20% classification error rate and demonstrate that the class posterior probabilities are reasonably calibrated. MACC classifications compare favorably to the classifications of several previous domain-specific ASAS papers and to the ASAS Catalog of Variable Stars, which had classified only 24% of those sources into one of 12 science classes.« less

Particle Swarm Optimization approach to defect detection in armour ceramics.

PubMed

Kesharaju, Manasa; Nagarajah, Romesh

2017-03-01

In this research, various extracted features were used in the development of an automated ultrasonic sensor based inspection system that enables defect classification in each ceramic component prior to despatch to the field. Classification is an important task and large number of irrelevant, redundant features commonly introduced to a dataset reduces the classifiers performance. Feature selection aims to reduce the dimensionality of the dataset while improving the performance of a classification system. In the context of a multi-criteria optimization problem (i.e. to minimize classification error rate and reduce number of features) such as one discussed in this research, the literature suggests that evolutionary algorithms offer good results. Besides, it is noted that Particle Swarm Optimization (PSO) has not been explored especially in the field of classification of high frequency ultrasonic signals. Hence, a binary coded Particle Swarm Optimization (BPSO) technique is investigated in the implementation of feature subset selection and to optimize the classification error rate. In the proposed method, the population data is used as input to an Artificial Neural Network (ANN) based classification system to obtain the error rate, as ANN serves as an evaluator of PSO fitness function. Copyright © 2016. Published by Elsevier B.V.

The impact of OCR accuracy on automated cancer classification of pathology reports.

PubMed

Zuccon, Guido; Nguyen, Anthony N; Bergheim, Anton; Wickman, Sandra; Grayson, Narelle

2012-01-01

To evaluate the effects of Optical Character Recognition (OCR) on the automatic cancer classification of pathology reports. Scanned images of pathology reports were converted to electronic free-text using a commercial OCR system. A state-of-the-art cancer classification system, the Medical Text Extraction (MEDTEX) system, was used to automatically classify the OCR reports. Classifications produced by MEDTEX on the OCR versions of the reports were compared with the classification from a human amended version of the OCR reports. The employed OCR system was found to recognise scanned pathology reports with up to 99.12% character accuracy and up to 98.95% word accuracy. Errors in the OCR processing were found to minimally impact on the automatic classification of scanned pathology reports into notifiable groups. However, the impact of OCR errors is not negligible when considering the extraction of cancer notification items, such as primary site, histological type, etc. The automatic cancer classification system used in this work, MEDTEX, has proven to be robust to errors produced by the acquisition of freetext pathology reports from scanned images through OCR software. However, issues emerge when considering the extraction of cancer notification items.

Human Vision-Motivated Algorithm Allows Consistent Retinal Vessel Classification Based on Local Color Contrast for Advancing General Diagnostic Exams.

PubMed

Ivanov, Iliya V; Leitritz, Martin A; Norrenberg, Lars A; Völker, Michael; Dynowski, Marek; Ueffing, Marius; Dietter, Johannes

2016-02-01

Abnormalities of blood vessel anatomy, morphology, and ratio can serve as important diagnostic markers for retinal diseases such as AMD or diabetic retinopathy. Large cohort studies demand automated and quantitative image analysis of vascular abnormalities. Therefore, we developed an analytical software tool to enable automated standardized classification of blood vessels supporting clinical reading. A dataset of 61 images was collected from a total of 33 women and 8 men with a median age of 38 years. The pupils were not dilated, and images were taken after dark adaption. In contrast to current methods in which classification is based on vessel profile intensity averages, and similar to human vision, local color contrast was chosen as a discriminator to allow artery vein discrimination and arterial-venous ratio (AVR) calculation without vessel tracking. With 83% ± 1 standard error of the mean for our dataset, we achieved best classification for weighted lightness information from a combination of the red, green, and blue channels. Tested on an independent dataset, our method reached 89% correct classification, which, when benchmarked against conventional ophthalmologic classification, shows significantly improved classification scores. Our study demonstrates that vessel classification based on local color contrast can cope with inter- or intraimage lightness variability and allows consistent AVR calculation. We offer an open-source implementation of this method upon request, which can be integrated into existing tool sets and applied to general diagnostic exams.

Error Detection in Mechanized Classification Systems

ERIC Educational Resources Information Center

Hoyle, W. G.

1976-01-01

When documentary material is indexed by a mechanized classification system, and the results judged by trained professionals, the number of documents in disagreement, after suitable adjustment, defines the error rate of the system. In a test case disagreement was 22 percent and, of this 22 percent, the computer correctly identified two-thirds of…

Information analysis of a spatial database for ecological land classification

NASA Technical Reports Server (NTRS)

Davis, Frank W.; Dozier, Jeff

1990-01-01

An ecological land classification was developed for a complex region in southern California using geographic information system techniques of map overlay and contingency table analysis. Land classes were identified by mutual information analysis of vegetation pattern in relation to other mapped environmental variables. The analysis was weakened by map errors, especially errors in the digital elevation data. Nevertheless, the resulting land classification was ecologically reasonable and performed well when tested with higher quality data from the region.

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.

Discrimination of corn from monocotyledonous weeds with ultraviolet (UV) induced fluorescence.

PubMed

Panneton, Bernard; Guillaume, Serge; Samson, Guy; Roger, Jean-Michel

2011-01-01

In production agriculture, savings in herbicides can be achieved if weeds can be discriminated from crop, allowing the targeting of weed control to weed-infested areas only. Previous studies demonstrated the potential of ultraviolet (UV) induced fluorescence to discriminate corn from weeds and recently, robust models have been obtained for the discrimination between monocots (including corn) and dicots. Here, we developed a new approach to achieve robust discrimination of monocot weeds from corn. To this end, four corn hybrids (Elite 60T05, Monsanto DKC 26-78, Pioneer 39Y85 (RR), and Syngenta N2555 (Bt, LL)) and four monocot weeds (Digitaria ischaemum (Schreb.) I, Echinochloa crus-galli (L.) Beauv., Panicum capillare (L.), and Setaria glauca (L.) Beauv.) were grown either in a greenhouse or in a growth cabinet and UV (327 nm) induced fluorescence spectra (400 to 755 nm) were measured under controlled or uncontrolled ambient light intensity and temperature. This resulted in three contrasting data sets suitable for testing the robustness of discrimination models. In the blue-green region (400 to 550 nm), the shape of the spectra did not contain any useful information for discrimination. Therefore, the integral of the blue-green region (415 to 455 nm) was used as a normalizing factor for the red fluorescence intensity (670 to 755 nm). The shape of the normalized red fluorescence spectra did not contribute to the discrimination and in the end, only the integral of the normalized red fluorescence intensity was left as a single discriminant variable. Applying a threshold on this variable minimizing the classification error resulted in calibration errors ranging from 14.2% to 15.8%, but this threshold varied largely between data sets. Therefore, to achieve robustness, a model calibration scheme was developed based on the collection of a calibration data set from 75 corn plants. From this set, a new threshold can be estimated as the 85% quantile on the cumulative frequency curve of the integral of the normalized red fluorescence. With this approach the classification error was nearly constant (16.0% to 18.5%), thereby indicating the potential of UV-induced fluorescence to reliably discriminate corn from monocot weeds.

Classification of echolocation clicks from odontocetes in the Southern California Bight.

PubMed

Roch, Marie A; Klinck, Holger; Baumann-Pickering, Simone; Mellinger, David K; Qui, Simon; Soldevilla, Melissa S; Hildebrand, John A

2011-01-01

This study presents a system for classifying echolocation clicks of six species of odontocetes in the Southern California Bight: Visually confirmed bottlenose dolphins, short- and long-beaked common dolphins, Pacific white-sided dolphins, Risso's dolphins, and presumed Cuvier's beaked whales. Echolocation clicks are represented by cepstral feature vectors that are classified by Gaussian mixture models. A randomized cross-validation experiment is designed to provide conditions similar to those found in a field-deployed system. To prevent matched conditions from inappropriately lowering the error rate, echolocation clicks associated with a single sighting are never split across the training and test data. Sightings are randomly permuted before assignment to folds in the experiment. This allows different combinations of the training and test data to be used while keeping data from each sighting entirely in the training or test set. The system achieves a mean error rate of 22% across 100 randomized three-fold cross-validation experiments. Four of the six species had mean error rates lower than the overall mean, with the presumed Cuvier's beaked whale clicks showing the best performance (<2% error rate). Long-beaked common and bottlenose dolphins proved the most difficult to classify, with mean error rates of 53% and 68%, respectively.

Hierarchically Structured Non-Intrusive Sign Language Recognition. Chapter 2

NASA Technical Reports Server (NTRS)

Zieren, Jorg; Zieren, Jorg; Kraiss, Karl-Friedrich

2007-01-01

This work presents a hierarchically structured approach at the nonintrusive recognition of sign language from a monocular frontal view. Robustness is achieved through sophisticated localization and tracking methods, including a combined EM/CAMSHIFT overlap resolution procedure and the parallel pursuit of multiple hypotheses about hands position and movement. This allows handling of ambiguities and automatically corrects tracking errors. A biomechanical skeleton model and dynamic motion prediction using Kalman filters represents high level knowledge. Classification is performed by Hidden Markov Models. 152 signs from German sign language were recognized with an accuracy of 97.6%.

Structural MRI-based detection of Alzheimer's disease using feature ranking and classification error.

PubMed

Beheshti, Iman; Demirel, Hasan; Farokhian, Farnaz; Yang, Chunlan; Matsuda, Hiroshi

2016-12-01

This paper presents an automatic computer-aided diagnosis (CAD) system based on feature ranking for detection of Alzheimer's disease (AD) using structural magnetic resonance imaging (sMRI) data. The proposed CAD system is composed of four systematic stages. First, global and local differences in the gray matter (GM) of AD patients compared to the GM of healthy controls (HCs) are analyzed using a voxel-based morphometry technique. The aim is to identify significant local differences in the volume of GM as volumes of interests (VOIs). Second, the voxel intensity values of the VOIs are extracted as raw features. Third, the raw features are ranked using a seven-feature ranking method, namely, statistical dependency (SD), mutual information (MI), information gain (IG), Pearson's correlation coefficient (PCC), t-test score (TS), Fisher's criterion (FC), and the Gini index (GI). The features with higher scores are more discriminative. To determine the number of top features, the estimated classification error based on training set made up of the AD and HC groups is calculated, with the vector size that minimized this error selected as the top discriminative feature. Fourth, the classification is performed using a support vector machine (SVM). In addition, a data fusion approach among feature ranking methods is introduced to improve the classification performance. The proposed method is evaluated using a data-set from ADNI (130 AD and 130 HC) with 10-fold cross-validation. The classification accuracy of the proposed automatic system for the diagnosis of AD is up to 92.48% using the sMRI data. An automatic CAD system for the classification of AD based on feature-ranking method and classification errors is proposed. In this regard, seven-feature ranking methods (i.e., SD, MI, IG, PCC, TS, FC, and GI) are evaluated. The optimal size of top discriminative features is determined by the classification error estimation in the training phase. The experimental results indicate that the performance of the proposed system is comparative to that of state-of-the-art classification models. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Combined empirical mode decomposition and texture features for skin lesion classification using quadratic support vector machine.

PubMed

Wahba, Maram A; Ashour, Amira S; Napoleon, Sameh A; Abd Elnaby, Mustafa M; Guo, Yanhui

2017-12-01

Basal cell carcinoma is one of the most common malignant skin lesions. Automated lesion identification and classification using image processing techniques is highly required to reduce the diagnosis errors. In this study, a novel technique is applied to classify skin lesion images into two classes, namely the malignant Basal cell carcinoma and the benign nevus. A hybrid combination of bi-dimensional empirical mode decomposition and gray-level difference method features is proposed after hair removal. The combined features are further classified using quadratic support vector machine (Q-SVM). The proposed system has achieved outstanding performance of 100% accuracy, sensitivity and specificity compared to other support vector machine procedures as well as with different extracted features. Basal Cell Carcinoma is effectively classified using Q-SVM with the proposed combined features.

The relationship between twelve-month home stimulation and school achievement.

PubMed

van Doorninck, W J; Caldwell, B M; Wright, C; Frankenburg, W K

1981-09-01

Home Observation for Measurement of the Environment (HOME) was designed to reflect parental support of early cognitive and socioemotional development. 12-month HOME scores were correlated with elementary school achievement, 5--9 years later. 50 low-income children were rank ordered by a weighted average of centile estimates of achievement test scores, letter grades, and curriculum levels in reading and math. 24 children were classified as having significant school achievement problems. The HOME total score correlated significantly, r = .37, with school centile scores among the low-income families. The statistically more appropriate contingency table analysis revealed a 68% correct classification rate and a significantly reduced error rate over random or blanket prediction. The results supported the predictive value of the 12-month HOME for school achievement among low-income families. In an additional sample of 21 middle-income families, there was insufficient variability among HOME scores to allow prediction. The HOME total scores were highly correlated, r = .86, among siblings tested at least 10 months apart.

Constrained binary classification using ensemble learning: an application to cost-efficient targeted PrEP strategies.

PubMed

Zheng, Wenjing; Balzer, Laura; van der Laan, Mark; Petersen, Maya

2018-01-30

Binary classification problems are ubiquitous in health and social sciences. In many cases, one wishes to balance two competing optimality considerations for a binary classifier. For instance, in resource-limited settings, an human immunodeficiency virus prevention program based on offering pre-exposure prophylaxis (PrEP) to select high-risk individuals must balance the sensitivity of the binary classifier in detecting future seroconverters (and hence offering them PrEP regimens) with the total number of PrEP regimens that is financially and logistically feasible for the program. In this article, we consider a general class of constrained binary classification problems wherein the objective function and the constraint are both monotonic with respect to a threshold. These include the minimization of the rate of positive predictions subject to a minimum sensitivity, the maximization of sensitivity subject to a maximum rate of positive predictions, and the Neyman-Pearson paradigm, which minimizes the type II error subject to an upper bound on the type I error. We propose an ensemble approach to these binary classification problems based on the Super Learner methodology. This approach linearly combines a user-supplied library of scoring algorithms, with combination weights and a discriminating threshold chosen to minimize the constrained optimality criterion. We then illustrate the application of the proposed classifier to develop an individualized PrEP targeting strategy in a resource-limited setting, with the goal of minimizing the number of PrEP offerings while achieving a minimum required sensitivity. This proof of concept data analysis uses baseline data from the ongoing Sustainable East Africa Research in Community Health study. Copyright © 2017 John Wiley & Sons, Ltd. Copyright © 2017 John Wiley & Sons, Ltd.

Documentation of procedures for textural/spatial pattern recognition techniques

NASA Technical Reports Server (NTRS)

Haralick, R. M.; Bryant, W. F.

1976-01-01

A C-130 aircraft was flown over the Sam Houston National Forest on March 21, 1973 at 10,000 feet altitude to collect multispectral scanner (MSS) data. Existing textural and spatial automatic processing techniques were used to classify the MSS imagery into specified timber categories. Several classification experiments were performed on this data using features selected from the spectral bands and a textural transform band. The results indicate that (1) spatial post-processing a classified image can cut the classification error to 1/2 or 1/3 of its initial value, (2) spatial post-processing the classified image using combined spectral and textural features produces a resulting image with less error than post-processing a classified image using only spectral features and (3) classification without spatial post processing using the combined spectral textural features tends to produce about the same error rate as a classification without spatial post processing using only spectral features.

Quantification of Coffea arabica and Coffea canephora var. robusta concentration in blends by means of synchronous fluorescence and UV-Vis spectroscopies.

PubMed

Dankowska, A; Domagała, A; Kowalewski, W

2017-09-01

The potential of fluorescence, UV-Vis spectroscopies as well as the low- and mid-level data fusion of both spectroscopies for the quantification of concentrations of roasted Coffea arabica and Coffea canephora var. robusta in coffee blends was investigated. Principal component analysis was used to reduce data multidimensionality. To calculate the level of undeclared addition, multiple linear regression (PCA-MLR) models were used with lowest root mean square error of calibration (RMSEC) of 3.6% and root mean square error of cross-validation (RMSECV) of 7.9%. LDA analysis was applied to fluorescence intensities and UV spectra of Coffea arabica, canephora samples, and their mixtures in order to examine classification ability. The best performance of PCA-LDA analysis was observed for data fusion of UV and fluorescence intensity measurements at wavelength interval of 60nm. LDA showed that data fusion can achieve over 96% of correct classifications (sensitivity) in the test set and 100% of correct classifications in the training set, with low-level data fusion. The corresponding results for individual spectroscopies ranged from 90% (UV-Vis spectroscopy) to 77% (synchronous fluorescence) in the test set, and from 93% to 97% in the training set. The results demonstrate that fluorescence, UV, and visible spectroscopies complement each other, giving a complementary effect for the quantification of roasted Coffea arabica and Coffea canephora var. robusta concentration in blends. Copyright © 2017 Elsevier B.V. All rights reserved.

Electrode channel selection based on backtracking search optimization in motor imagery brain-computer interfaces.

PubMed

Dai, Shengfa; Wei, Qingguo

2017-01-01

Common spatial pattern algorithm is widely used to estimate spatial filters in motor imagery based brain-computer interfaces. However, use of a large number of channels will make common spatial pattern tend to over-fitting and the classification of electroencephalographic signals time-consuming. To overcome these problems, it is necessary to choose an optimal subset of the whole channels to save computational time and improve the classification accuracy. In this paper, a novel method named backtracking search optimization algorithm is proposed to automatically select the optimal channel set for common spatial pattern. Each individual in the population is a N-dimensional vector, with each component representing one channel. A population of binary codes generate randomly in the beginning, and then channels are selected according to the evolution of these codes. The number and positions of 1's in the code denote the number and positions of chosen channels. The objective function of backtracking search optimization algorithm is defined as the combination of classification error rate and relative number of channels. Experimental results suggest that higher classification accuracy can be achieved with much fewer channels compared to standard common spatial pattern with whole channels.

Human error analysis of commercial aviation accidents: application of the Human Factors Analysis and Classification system (HFACS).

PubMed

Wiegmann, D A; Shappell, S A

2001-11-01

The Human Factors Analysis and Classification System (HFACS) is a general human error framework originally developed and tested within the U.S. military as a tool for investigating and analyzing the human causes of aviation accidents. Based on Reason's (1990) model of latent and active failures, HFACS addresses human error at all levels of the system, including the condition of aircrew and organizational factors. The purpose of the present study was to assess the utility of the HFACS framework as an error analysis and classification tool outside the military. The HFACS framework was used to analyze human error data associated with aircrew-related commercial aviation accidents that occurred between January 1990 and December 1996 using database records maintained by the NTSB and the FAA. Investigators were able to reliably accommodate all the human causal factors associated with the commercial aviation accidents examined in this study using the HFACS system. In addition, the classification of data using HFACS highlighted several critical safety issues in need of intervention research. These results demonstrate that the HFACS framework can be a viable tool for use within the civil aviation arena. However, additional research is needed to examine its applicability to areas outside the flight deck, such as aircraft maintenance and air traffic control domains.

Practical Procedures for Constructing Mastery Tests to Minimize Errors of Classification and to Maximize or Optimize Decision Reliability.

ERIC Educational Resources Information Center

Byars, Alvin Gregg

The objectives of this investigation are to develop, describe, assess, and demonstrate procedures for constructing mastery tests to minimize errors of classification and to maximize decision reliability. The guidelines are based on conditions where item exchangeability is a reasonable assumption and the test constructor can control the number of…

A fuzzy neural network for intelligent data processing

NASA Astrophysics Data System (ADS)

Xie, Wei; Chu, Feng; Wang, Lipo; Lim, Eng Thiam

2005-03-01

In this paper, we describe an incrementally generated fuzzy neural network (FNN) for intelligent data processing. This FNN combines the features of initial fuzzy model self-generation, fast input selection, partition validation, parameter optimization and rule-base simplification. A small FNN is created from scratch -- there is no need to specify the initial network architecture, initial membership functions, or initial weights. Fuzzy IF-THEN rules are constantly combined and pruned to minimize the size of the network while maintaining accuracy; irrelevant inputs are detected and deleted, and membership functions and network weights are trained with a gradient descent algorithm, i.e., error backpropagation. Experimental studies on synthesized data sets demonstrate that the proposed Fuzzy Neural Network is able to achieve accuracy comparable to or higher than both a feedforward crisp neural network, i.e., NeuroRule, and a decision tree, i.e., C4.5, with more compact rule bases for most of the data sets used in our experiments. The FNN has achieved outstanding results for cancer classification based on microarray data. The excellent classification result for Small Round Blue Cell Tumors (SRBCTs) data set is shown. Compared with other published methods, we have used a much fewer number of genes for perfect classification, which will help researchers directly focus their attention on some specific genes and may lead to discovery of deep reasons of the development of cancers and discovery of drugs.

Comparing K-mer based methods for improved classification of 16S sequences.

PubMed

Vinje, Hilde; Liland, Kristian Hovde; Almøy, Trygve; Snipen, Lars

2015-07-01

The need for precise and stable taxonomic classification is highly relevant in modern microbiology. Parallel to the explosion in the amount of sequence data accessible, there has also been a shift in focus for classification methods. Previously, alignment-based methods were the most applicable tools. Now, methods based on counting K-mers by sliding windows are the most interesting classification approach with respect to both speed and accuracy. Here, we present a systematic comparison on five different K-mer based classification methods for the 16S rRNA gene. The methods differ from each other both in data usage and modelling strategies. We have based our study on the commonly known and well-used naïve Bayes classifier from the RDP project, and four other methods were implemented and tested on two different data sets, on full-length sequences as well as fragments of typical read-length. The difference in classification error obtained by the methods seemed to be small, but they were stable and for both data sets tested. The Preprocessed nearest-neighbour (PLSNN) method performed best for full-length 16S rRNA sequences, significantly better than the naïve Bayes RDP method. On fragmented sequences the naïve Bayes Multinomial method performed best, significantly better than all other methods. For both data sets explored, and on both full-length and fragmented sequences, all the five methods reached an error-plateau. We conclude that no K-mer based method is universally best for classifying both full-length sequences and fragments (reads). All methods approach an error plateau indicating improved training data is needed to improve classification from here. Classification errors occur most frequent for genera with few sequences present. For improving the taxonomy and testing new classification methods, the need for a better and more universal and robust training data set is crucial.

An experimental evaluation of the incidence of fitness-function/search-algorithm combinations on the classification performance of myoelectric control systems with iPCA tuning

PubMed Central

2013-01-01

Background The information of electromyographic signals can be used by Myoelectric Control Systems (MCSs) to actuate prostheses. These devices allow the performing of movements that cannot be carried out by persons with amputated limbs. The state of the art in the development of MCSs is based on the use of individual principal component analysis (iPCA) as a stage of pre-processing of the classifiers. The iPCA pre-processing implies an optimization stage which has not yet been deeply explored. Methods The present study considers two factors in the iPCA stage: namely A (the fitness function), and B (the search algorithm). The A factor comprises two levels, namely A1 (the classification error) and A2 (the correlation factor). Otherwise, the B factor has four levels, specifically B1 (the Sequential Forward Selection, SFS), B2 (the Sequential Floating Forward Selection, SFFS), B3 (Artificial Bee Colony, ABC), and B4 (Particle Swarm Optimization, PSO). This work evaluates the incidence of each one of the eight possible combinations between A and B factors over the classification error of the MCS. Results A two factor ANOVA was performed on the computed classification errors and determined that: (1) the interactive effects over the classification error are not significative (F0.01,3,72 = 4.0659 > f AB  = 0.09), (2) the levels of factor A have significative effects on the classification error (F0.02,1,72 = 5.0162 < f A  = 6.56), and (3) the levels of factor B over the classification error are not significative (F0.01,3,72 = 4.0659 > f B  = 0.08). Conclusions Considering the classification performance we found a superiority of using the factor A2 in combination with any of the levels of factor B. With respect to the time performance the analysis suggests that the PSO algorithm is at least 14 percent better than its best competitor. The latter behavior has been observed for a particular configuration set of parameters in the search algorithms. Future works will investigate the effect of these parameters in the classification performance, such as length of the reduced size vector, number of particles and bees used during optimal search, the cognitive parameters in the PSO algorithm as well as the limit of cycles to improve a solution in the ABC algorithm. PMID:24369728

Exploring human error in military aviation flight safety events using post-incident classification systems.

PubMed

Hooper, Brionny J; O'Hare, David P A

2013-08-01

Human error classification systems theoretically allow researchers to analyze postaccident data in an objective and consistent manner. The Human Factors Analysis and Classification System (HFACS) framework is one such practical analysis tool that has been widely used to classify human error in aviation. The Cognitive Error Taxonomy (CET) is another. It has been postulated that the focus on interrelationships within HFACS can facilitate the identification of the underlying causes of pilot error. The CET provides increased granularity at the level of unsafe acts. The aim was to analyze the influence of factors at higher organizational levels on the unsafe acts of front-line operators and to compare the errors of fixed-wing and rotary-wing operations. This study analyzed 288 aircraft incidents involving human error from an Australasian military organization occurring between 2001 and 2008. Action errors accounted for almost twice (44%) the proportion of rotary wing compared to fixed wing (23%) incidents. Both classificatory systems showed significant relationships between precursor factors such as the physical environment, mental and physiological states, crew resource management, training and personal readiness, and skill-based, but not decision-based, acts. The CET analysis showed different predisposing factors for different aspects of skill-based behaviors. Skill-based errors in military operations are more prevalent in rotary wing incidents and are related to higher level supervisory processes in the organization. The Cognitive Error Taxonomy provides increased granularity to HFACS analyses of unsafe acts.

Automatic Quality Inspection of Percussion Cap Mass Production by Means of 3D Machine Vision and Machine Learning Techniques

NASA Astrophysics Data System (ADS)

Tellaeche, A.; Arana, R.; Ibarguren, A.; Martínez-Otzeta, J. M.

The exhaustive quality control is becoming very important in the world's globalized market. One of these examples where quality control becomes critical is the percussion cap mass production. These elements must achieve a minimum tolerance deviation in their fabrication. This paper outlines a machine vision development using a 3D camera for the inspection of the whole production of percussion caps. This system presents multiple problems, such as metallic reflections in the percussion caps, high speed movement of the system and mechanical errors and irregularities in percussion cap placement. Due to these problems, it is impossible to solve the problem by traditional image processing methods, and hence, machine learning algorithms have been tested to provide a feasible classification of the possible errors present in the percussion caps.

Automated classification of Acid Rock Drainage potential from Corescan drill core imagery

NASA Astrophysics Data System (ADS)

Cracknell, M. J.; Jackson, L.; Parbhakar-Fox, A.; Savinova, K.

2017-12-01

Classification of the acid forming potential of waste rock is important for managing environmental hazards associated with mining operations. Current methods for the classification of acid rock drainage (ARD) potential usually involve labour intensive and subjective assessment of drill core and/or hand specimens. Manual methods are subject to operator bias, human error and the amount of material that can be assessed within a given time frame is limited. The automated classification of ARD potential documented here is based on the ARD Index developed by Parbhakar-Fox et al. (2011). This ARD Index involves the combination of five indicators: A - sulphide content; B - sulphide alteration; C - sulphide morphology; D - primary neutraliser content; and E - sulphide mineral association. Several components of the ARD Index require accurate identification of sulphide minerals. This is achieved by classifying Corescan Red-Green-Blue true colour images into the presence or absence of sulphide minerals using supervised classification. Subsequently, sulphide classification images are processed and combined with Corescan SWIR-based mineral classifications to obtain information on sulphide content, indices representing sulphide textures (disseminated versus massive and degree of veining), and spatially associated minerals. This information is combined to calculate ARD Index indicator values that feed into the classification of ARD potential. Automated ARD potential classifications of drill core samples associated with a porphyry Cu-Au deposit are compared to manually derived classifications and those obtained by standard static geochemical testing and X-ray diffractometry analyses. Results indicate a high degree of similarity between automated and manual ARD potential classifications. Major differences between approaches are observed in sulphide and neutraliser mineral percentages, likely due to the subjective nature of manual estimates of mineral content. The automated approach presented here for the classification of ARD potential offers rapid, repeatable and accurate outcomes comparable to manually derived classifications. Methods for automated ARD classifications from digital drill core data represent a step-change for geoenvironmental management practices in the mining industry.

How should children with speech sound disorders be classified? A review and critical evaluation of current classification systems.

PubMed

Waring, R; Knight, R

2013-01-01

Children with speech sound disorders (SSD) form a heterogeneous group who differ in terms of the severity of their condition, underlying cause, speech errors, involvement of other aspects of the linguistic system and treatment response. To date there is no universal and agreed-upon classification system. Instead, a number of theoretically differing classification systems have been proposed based on either an aetiological (medical) approach, a descriptive-linguistic approach or a processing approach. To describe and review the supporting evidence, and to provide a critical evaluation of the current childhood SSD classification systems. Descriptions of the major specific approaches to classification are reviewed and research papers supporting the reliability and validity of the systems are evaluated. Three specific paediatric SSD classification systems; the aetiologic-based Speech Disorders Classification System, the descriptive-linguistic Differential Diagnosis system, and the processing-based Psycholinguistic Framework are identified as potentially useful in classifying children with SSD into homogeneous subgroups. The Differential Diagnosis system has a growing body of empirical support from clinical population studies, across language error pattern studies and treatment efficacy studies. The Speech Disorders Classification System is currently a research tool with eight proposed subgroups. The Psycholinguistic Framework is a potential bridge to linking cause and surface level speech errors. There is a need for a universally agreed-upon classification system that is useful to clinicians and researchers. The resulting classification system needs to be robust, reliable and valid. A universal classification system would allow for improved tailoring of treatments to subgroups of SSD which may, in turn, lead to improved treatment efficacy. © 2012 Royal College of Speech and Language Therapists.

The application of Aronson's taxonomy to medication errors in nursing.

PubMed

Johnson, Maree; Young, Helen

2011-01-01

Medication administration is a frequent nursing activity that is prone to error. In this study of 318 self-reported medication incidents (including near misses), very few resulted in patient harm-7% required intervention or prolonged hospitalization or caused temporary harm. Aronson's classification system provided an excellent framework for analysis of the incidents with a close connection between the type of error and the change strategy to minimize medication incidents. Taking a behavioral approach to medication error classification has provided helpful strategies for nurses such as nurse-call cards on patient lockers when patients are absent and checking of medication sign-off by outgoing and incoming staff at handover.

Estimation of sex and stature using anthropometry of the upper extremity in an Australian population.

PubMed

Howley, Donna; Howley, Peter; Oxenham, Marc F

2018-06-01

Stature and a further 8 anthropometric dimensions were recorded from the arms and hands of a sample of 96 staff and students from the Australian National University and The University of Newcastle, Australia. These dimensions were used to create simple and multiple logistic regression models for sex estimation and simple and multiple linear regression equations for stature estimation of a contemporary Australian population. Overall sex classification accuracies using the models created were comparable to similar studies. The stature estimation models achieved standard errors of estimates (SEE) which were comparable to and in many cases lower than those achieved in similar research. Generic, non sex-specific models achieved similar SEEs and R 2 values to the sex-specific models indicating stature may be accurately estimated when sex is unknown. Copyright © 2018 Elsevier B.V. All rights reserved.

Center for Seismic Studies Final Technical Report, October 1992 through October 1993

DTIC Science & Technology

1994-02-07

SECURITY CLASSIFICATION 18. SECURITY CLASSIFICATION 19. SECURITY CLASSIFICATION 20. LIMITATION OF ABSTRACT OF REPORT OF THIS PAGE OF ABSTRACT...Upper limit of depth error as a function of mb for estimates based on P and S waves for three netowrks : GSETr-2, ALPHA, and ALPHA + a 50 station...U 4A 4 U 4S as 1 I I I Figure 42: Upper limit of depth error as a function of mb for estimatesbased on P and S waves for three netowrk : GSETT-2o ALPHA

Assimilation of a knowledge base and physical models to reduce errors in passive-microwave classifications of sea ice

NASA Technical Reports Server (NTRS)

Maslanik, J. A.; Key, J.

1992-01-01

An expert system framework has been developed to classify sea ice types using satellite passive microwave data, an operational classification algorithm, spatial and temporal information, ice types estimated from a dynamic-thermodynamic model, output from a neural network that detects the onset of melt, and knowledge about season and region. The rule base imposes boundary conditions upon the ice classification, modifies parameters in the ice algorithm, determines a `confidence' measure for the classified data, and under certain conditions, replaces the algorithm output with model output. Results demonstrate the potential power of such a system for minimizing overall error in the classification and for providing non-expert data users with a means of assessing the usefulness of the classification results for their applications.

Spelling in adolescents with dyslexia: errors and modes of assessment.

PubMed

Tops, Wim; Callens, Maaike; Bijn, Evi; Brysbaert, Marc

2014-01-01

In this study we focused on the spelling of high-functioning students with dyslexia. We made a detailed classification of the errors in a word and sentence dictation task made by 100 students with dyslexia and 100 matched control students. All participants were in the first year of their bachelor's studies and had Dutch as mother tongue. Three main error categories were distinguished: phonological, orthographic, and grammatical errors (on the basis of morphology and language-specific spelling rules). The results indicated that higher-education students with dyslexia made on average twice as many spelling errors as the controls, with effect sizes of d ≥ 2. When the errors were classified as phonological, orthographic, or grammatical, we found a slight dominance of phonological errors in students with dyslexia. Sentence dictation did not provide more information than word dictation in the correct classification of students with and without dyslexia. © Hammill Institute on Disabilities 2012.

A Guide for Setting the Cut-Scores to Minimize Weighted Classification Errors in Test Batteries

ERIC Educational Resources Information Center

Grabovsky, Irina; Wainer, Howard

2017-01-01

In this article, we extend the methodology of the Cut-Score Operating Function that we introduced previously and apply it to a testing scenario with multiple independent components and different testing policies. We derive analytically the overall classification error rate for a test battery under the policy when several retakes are allowed for…

Automated Detection of Diabetic Retinopathy using Deep Learning.

PubMed

Lam, Carson; Yi, Darvin; Guo, Margaret; Lindsey, Tony

2018-01-01

Diabetic retinopathy is a leading cause of blindness among working-age adults. Early detection of this condition is critical for good prognosis. In this paper, we demonstrate the use of convolutional neural networks (CNNs) on color fundus images for the recognition task of diabetic retinopathy staging. Our network models achieved test metric performance comparable to baseline literature results, with validation sensitivity of 95%. We additionally explored multinomial classification models, and demonstrate that errors primarily occur in the misclassification of mild disease as normal due to the CNNs inability to detect subtle disease features. We discovered that preprocessing with contrast limited adaptive histogram equalization and ensuring dataset fidelity by expert verification of class labels improves recognition of subtle features. Transfer learning on pretrained GoogLeNet and AlexNet models from ImageNet improved peak test set accuracies to 74.5%, 68.8%, and 57.2% on 2-ary, 3-ary, and 4-ary classification models, respectively.

Evaluation of algorithms for estimating wheat acreage from multispectral scanner data. [Kansas and Texas

NASA Technical Reports Server (NTRS)

Nalepka, R. F. (Principal Investigator); Richardson, W.; Pentland, A. P.

1976-01-01

The author has identified the following significant results. Fourteen different classification algorithms were tested for their ability to estimate the proportion of wheat in an area. For some algorithms, accuracy of classification in field centers was observed. The data base consisted of ground truth and LANDSAT data from 55 sections (1 x 1 mile) from five LACIE intensive test sites in Kansas and Texas. Signatures obtained from training fields selected at random from the ground truth were generally representative of the data distribution patterns. LIMMIX, an algorithm that chooses a pure signature when the data point is close enough to a signature mean and otherwise chooses the best mixture of a pair of signatures, reduced the average absolute error to 6.1% and the bias to 1.0%. QRULE run with a null test achieved a similar reduction.

Spatial methods for deriving crop rotation history

NASA Astrophysics Data System (ADS)

Mueller-Warrant, George W.; Trippe, Kristin M.; Whittaker, Gerald W.; Anderson, Nicole P.; Sullivan, Clare S.

2017-08-01

Benefits of converting 11 years of remote sensing classification data into cropping history of agricultural fields included measuring lengths of rotation cycles and identifying specific sequences of intervening crops grown between final years of old grass seed stands and establishment of new ones. Spatial and non-spatial methods were complementary. Individual-year classification errors were often correctable in spreadsheet-based non-spatial analysis, whereas their presence in spatial data generally led to exclusion of fields from further analysis. Markov-model testing of non-spatial data revealed that year-to-year cropping sequences did not match average frequencies for transitions among crops grown in western Oregon, implying that rotations into new grass seed stands were influenced by growers' desires to achieve specific objectives. Moran's I spatial analysis of length of time between consecutive grass seed stands revealed that clustering of fields was relatively uncommon, with high and low value clusters only accounting for 7.1 and 6.2% of fields.

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.

[Classifications in forensic medicine and their logical basis].

PubMed

Kovalev, A V; Shmarov, L A; Ten'kov, A A

2014-01-01

The objective of the present study was to characterize the main requirements for the correct construction of classifications used in forensic medicine, with special reference to the errors that occur in the relevant text-books, guidelines, and manuals and the ways to avoid them. This publication continues the series of thematic articles of the authors devoted to the logical errors in the expert conclusions. The preparation of further publications is underway to report the results of the in-depth analysis of the logical errors encountered in expert conclusions, text-books, guidelines, and manuals.

Sensitivity analysis of the GEMS soil organic carbon model to land cover land use classification uncertainties under different climate scenarios in Senegal

USGS Publications Warehouse

Dieye, A.M.; Roy, David P.; Hanan, N.P.; Liu, S.; Hansen, M.; Toure, A.

2012-01-01

Spatially explicit land cover land use (LCLU) change information is needed to drive biogeochemical models that simulate soil organic carbon (SOC) dynamics. Such information is increasingly being mapped using remotely sensed satellite data with classification schemes and uncertainties constrained by the sensing system, classification algorithms and land cover schemes. In this study, automated LCLU classification of multi-temporal Landsat satellite data were used to assess the sensitivity of SOC modeled by the Global Ensemble Biogeochemical Modeling System (GEMS). The GEMS was run for an area of 1560 km2 in Senegal under three climate change scenarios with LCLU maps generated using different Landsat classification approaches. This research provides a method to estimate the variability of SOC, specifically the SOC uncertainty due to satellite classification errors, which we show is dependent not only on the LCLU classification errors but also on where the LCLU classes occur relative to the other GEMS model inputs.

Risk-Aware Planetary Rover Operation: Autonomous Terrain Classification and Path Planning

NASA Technical Reports Server (NTRS)

Ono, Masahiro; Fuchs, Thoams J.; Steffy, Amanda; Maimone, Mark; Yen, Jeng

2015-01-01

Identifying and avoiding terrain hazards (e.g., soft soil and pointy embedded rocks) are crucial for the safety of planetary rovers. This paper presents a newly developed groundbased Mars rover operation tool that mitigates risks from terrain by automatically identifying hazards on the terrain, evaluating their risks, and suggesting operators safe paths options that avoids potential risks while achieving specified goals. The tool will bring benefits to rover operations by reducing operation cost, by reducing cognitive load of rover operators, by preventing human errors, and most importantly, by significantly reducing the risk of the loss of rovers.

Evaluating data mining algorithms using molecular dynamics trajectories.

PubMed

Tatsis, Vasileios A; Tjortjis, Christos; Tzirakis, Panagiotis

2013-01-01

Molecular dynamics simulations provide a sample of a molecule's conformational space. Experiments on the mus time scale, resulting in large amounts of data, are nowadays routine. Data mining techniques such as classification provide a way to analyse such data. In this work, we evaluate and compare several classification algorithms using three data sets which resulted from computer simulations, of a potential enzyme mimetic biomolecule. We evaluated 65 classifiers available in the well-known data mining toolkit Weka, using 'classification' errors to assess algorithmic performance. Results suggest that: (i) 'meta' classifiers perform better than the other groups, when applied to molecular dynamics data sets; (ii) Random Forest and Rotation Forest are the best classifiers for all three data sets; and (iii) classification via clustering yields the highest classification error. Our findings are consistent with bibliographic evidence, suggesting a 'roadmap' for dealing with such data.

Noise tolerant dendritic lattice associative memories

NASA Astrophysics Data System (ADS)

Ritter, Gerhard X.; Schmalz, Mark S.; Hayden, Eric; Tucker, Marc

2011-09-01

Linear classifiers based on computation over the real numbers R (e.g., with operations of addition and multiplication) denoted by (R, +, x), have been represented extensively in the literature of pattern recognition. However, a different approach to pattern classification involves the use of addition, maximum, and minimum operations over the reals in the algebra (R, +, maximum, minimum) These pattern classifiers, based on lattice algebra, have been shown to exhibit superior information storage capacity, fast training and short convergence times, high pattern classification accuracy, and low computational cost. Such attributes are not always found, for example, in classical neural nets based on the linear inner product. In a special type of lattice associative memory (LAM), called a dendritic LAM or DLAM, it is possible to achieve noise-tolerant pattern classification by varying the design of noise or error acceptance bounds. This paper presents theory and algorithmic approaches for the computation of noise-tolerant lattice associative memories (LAMs) under a variety of input constraints. Of particular interest are the classification of nonergodic data in noise regimes with time-varying statistics. DLAMs, which are a specialization of LAMs derived from concepts of biological neural networks, have successfully been applied to pattern classification from hyperspectral remote sensing data, as well as spatial object recognition from digital imagery. The authors' recent research in the development of DLAMs is overviewed, with experimental results that show utility for a wide variety of pattern classification applications. Performance results are presented in terms of measured computational cost, noise tolerance, classification accuracy, and throughput for a variety of input data and noise levels.

Bayesian Optimization for Neuroimaging Pre-processing in Brain Age Classification and Prediction

PubMed Central

Lancaster, Jenessa; Lorenz, Romy; Leech, Rob; Cole, James H.

2018-01-01

Neuroimaging-based age prediction using machine learning is proposed as a biomarker of brain aging, relating to cognitive performance, health outcomes and progression of neurodegenerative disease. However, even leading age-prediction algorithms contain measurement error, motivating efforts to improve experimental pipelines. T1-weighted MRI is commonly used for age prediction, and the pre-processing of these scans involves normalization to a common template and resampling to a common voxel size, followed by spatial smoothing. Resampling parameters are often selected arbitrarily. Here, we sought to improve brain-age prediction accuracy by optimizing resampling parameters using Bayesian optimization. Using data on N = 2003 healthy individuals (aged 16–90 years) we trained support vector machines to (i) distinguish between young (<22 years) and old (>50 years) brains (classification) and (ii) predict chronological age (regression). We also evaluated generalisability of the age-regression model to an independent dataset (CamCAN, N = 648, aged 18–88 years). Bayesian optimization was used to identify optimal voxel size and smoothing kernel size for each task. This procedure adaptively samples the parameter space to evaluate accuracy across a range of possible parameters, using independent sub-samples to iteratively assess different parameter combinations to arrive at optimal values. When distinguishing between young and old brains a classification accuracy of 88.1% was achieved, (optimal voxel size = 11.5 mm3, smoothing kernel = 2.3 mm). For predicting chronological age, a mean absolute error (MAE) of 5.08 years was achieved, (optimal voxel size = 3.73 mm3, smoothing kernel = 3.68 mm). This was compared to performance using default values of 1.5 mm3 and 4mm respectively, resulting in MAE = 5.48 years, though this 7.3% improvement was not statistically significant. When assessing generalisability, best performance was achieved when applying the entire Bayesian optimization framework to the new dataset, out-performing the parameters optimized for the initial training dataset. Our study outlines the proof-of-principle that neuroimaging models for brain-age prediction can use Bayesian optimization to derive case-specific pre-processing parameters. Our results suggest that different pre-processing parameters are selected when optimization is conducted in specific contexts. This potentially motivates use of optimization techniques at many different points during the experimental process, which may improve statistical sensitivity and reduce opportunities for experimenter-led bias. PMID:29483870

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.

CURE-SMOTE algorithm and hybrid algorithm for feature selection and parameter optimization based on random forests.

PubMed

Ma, Li; Fan, Suohai

2017-03-14

The random forests algorithm is a type of classifier with prominent universality, a wide application range, and robustness for avoiding overfitting. But there are still some drawbacks to random forests. Therefore, to improve the performance of random forests, this paper seeks to improve imbalanced data processing, feature selection and parameter optimization. We propose the CURE-SMOTE algorithm for the imbalanced data classification problem. Experiments on imbalanced UCI data reveal that the combination of Clustering Using Representatives (CURE) enhances the original synthetic minority oversampling technique (SMOTE) algorithms effectively compared with the classification results on the original data using random sampling, Borderline-SMOTE1, safe-level SMOTE, C-SMOTE, and k-means-SMOTE. Additionally, the hybrid RF (random forests) algorithm has been proposed for feature selection and parameter optimization, which uses the minimum out of bag (OOB) data error as its objective function. Simulation results on binary and higher-dimensional data indicate that the proposed hybrid RF algorithms, hybrid genetic-random forests algorithm, hybrid particle swarm-random forests algorithm and hybrid fish swarm-random forests algorithm can achieve the minimum OOB error and show the best generalization ability. The training set produced from the proposed CURE-SMOTE algorithm is closer to the original data distribution because it contains minimal noise. Thus, better classification results are produced from this feasible and effective algorithm. Moreover, the hybrid algorithm's F-value, G-mean, AUC and OOB scores demonstrate that they surpass the performance of the original RF algorithm. Hence, this hybrid algorithm provides a new way to perform feature selection and parameter optimization.

Density-based penalty parameter optimization on C-SVM.

PubMed

Liu, Yun; Lian, Jie; Bartolacci, Michael R; Zeng, Qing-An

2014-01-01

The support vector machine (SVM) is one of the most widely used approaches for data classification and regression. SVM achieves the largest distance between the positive and negative support vectors, which neglects the remote instances away from the SVM interface. In order to avoid a position change of the SVM interface as the result of an error system outlier, C-SVM was implemented to decrease the influences of the system's outliers. Traditional C-SVM holds a uniform parameter C for both positive and negative instances; however, according to the different number proportions and the data distribution, positive and negative instances should be set with different weights for the penalty parameter of the error terms. Therefore, in this paper, we propose density-based penalty parameter optimization of C-SVM. The experiential results indicated that our proposed algorithm has outstanding performance with respect to both precision and recall.

Irrigated lands assessment for water management: Technique test. [California

NASA Technical Reports Server (NTRS)

Wall, S. L.; Brown, C. E.; Eriksson, M.; Grigg, C. A.; Thomas, R. W.; Colwell, R. N.; Estes, J. E.; Tinney, L. R.; Baggett, J. O.; Sawyer, G.

1981-01-01

A procedure for estimating irrigated land using full frame LANDSAT imagery was demonstrated. Relatively inexpensive interpretation of multidate LANDSAT photographic enlargements was used to produce a map of irrigated land in California. The LANDSAT and ground maps were then linked by regression equations to enable precise estimation of irrigated land area by county, basin, and statewide. Land irrigated at least once in California in 1979 was estimated to be 9.86 million acres, with an expected error of less than 1.75% at the 99% level of confidence. To achieve the same level of error with a ground-only sample would have required 3 to 5 times as many ground sample units statewide. A procedure for relatively inexpensive computer classification of LANDSAT digital data to irrigated land categories was also developed. This procedure is based on ratios of MSS band 7 and 5, and gave good results for several counties in the Central Valley.

Real-time recognition of feedback error-related potentials during a time-estimation task.

PubMed

Lopez-Larraz, Eduardo; Iturrate, Iñaki; Montesano, Luis; Minguez, Javier

2010-01-01

Feedback error-related potentials are a promising brain process in the field of rehabilitation since they are related to human learning. Due to the fact that many therapeutic strategies rely on the presentation of feedback stimuli, potentials generated by these stimuli could be used to ameliorate the patient's progress. In this paper we propose a method that can identify, in real-time, feedback evoked potentials in a time-estimation task. We have tested our system with five participants in two different days with a separation of three weeks between them, achieving a mean single-trial detection performance of 71.62% for real-time recognition, and 78.08% in offline classification. Additionally, an analysis of the stability of the signal between the two days is performed, suggesting that the feedback responses are stable enough to be used without the needing of training again the user.

Evaluation criteria for software classification inventories, accuracies, and maps

NASA Technical Reports Server (NTRS)

Jayroe, R. R., Jr.

1976-01-01

Statistical criteria are presented for modifying the contingency table used to evaluate tabular classification results obtained from remote sensing and ground truth maps. This classification technique contains information on the spatial complexity of the test site, on the relative location of classification errors, on agreement of the classification maps with ground truth maps, and reduces back to the original information normally found in a contingency table.

The search for structure - Object classification in large data sets. [for astronomers

NASA Technical Reports Server (NTRS)

Kurtz, Michael J.

1988-01-01

Research concerning object classifications schemes are reviewed, focusing on large data sets. Classification techniques are discussed, including syntactic, decision theoretic methods, fuzzy techniques, and stochastic and fuzzy grammars. Consideration is given to the automation of MK classification (Morgan and Keenan, 1973) and other problems associated with the classification of spectra. In addition, the classification of galaxies is examined, including the problems of systematic errors, blended objects, galaxy types, and galaxy clusters.

Accuracy of outpatient service data for activity-based funding in New South Wales, Australia.

PubMed

Munyisia, Esther N; Reid, David; Yu, Ping

2017-05-01

Despite increasing research on activity-based funding (ABF), there is no empirical evidence on the accuracy of outpatient service data for payment. This study aimed to identify data entry errors affecting ABF in two drug and alcohol outpatient clinic services in Australia. An audit was carried out on healthcare workers' (doctors, nurses, psychologists, social workers, counsellors, and aboriginal health education officers) data entry errors in an outpatient electronic documentation system. Of the 6919 data entries in the electronic documentation system, 7.5% (518) had errors, 68.7% of the errors were related to a wrong primary activity, 14.5% were due to a wrong activity category, 14.5% were as a result of a wrong combination of primary activity and modality of care, 1.9% were due to inaccurate information on a client's presence during service delivery and 0.4% were related to a wrong modality of care. Data entry errors may affect the amount of funding received by a healthcare organisation, which in turn may affect the quality of treatment provided to clients due to the possibility of underfunding the organisation. To reduce errors or achieve an error-free environment, there is a need to improve the naming convention of data elements, their descriptions and alignment with the national standard classification of outpatient services. It is also important to support healthcare workers in their data entry by embedding safeguards in the electronic documentation system such as flags for inaccurate data elements.

Undergraduate paramedic students cannot do drug calculations.

PubMed

Eastwood, Kathryn; Boyle, Malcolm J; Williams, Brett

2012-01-01

Previous investigation of drug calculation skills of qualified paramedics has highlighted poor mathematical ability with no published studies having been undertaken on undergraduate paramedics. There are three major error classifications. Conceptual errors involve an inability to formulate an equation from information given, arithmetical errors involve an inability to operate a given equation, and finally computation errors are simple errors of addition, subtraction, division and multiplication. The objective of this study was to determine if undergraduate paramedics at a large Australia university could accurately perform common drug calculations and basic mathematical equations normally required in the workplace. A cross-sectional study methodology using a paper-based questionnaire was administered to undergraduate paramedic students to collect demographical data, student attitudes regarding their drug calculation performance, and answers to a series of basic mathematical and drug calculation questions. Ethics approval was granted. The mean score of correct answers was 39.5% with one student scoring 100%, 3.3% of students (n=3) scoring greater than 90%, and 63% (n=58) scoring 50% or less, despite 62% (n=57) of the students stating they 'did not have any drug calculations issues'. On average those who completed a minimum of year 12 Specialist Maths achieved scores over 50%. Conceptual errors made up 48.5%, arithmetical 31.1% and computational 17.4%. This study suggests undergraduate paramedics have deficiencies in performing accurate calculations, with conceptual errors indicating a fundamental lack of mathematical understanding. The results suggest an unacceptable level of mathematical competence to practice safely in the unpredictable prehospital environment.

Procedural Error and Task Interruption

DTIC Science & Technology

2016-09-30

red for research on errors and individual differences . Results indicate predictive validity for fluid intelligence and specifi c forms of work...TERMS procedural error, task interruption, individual differences , fluid intelligence, sleep deprivation 16. SECURITY CLASSIFICATION OF: 17...and individual differences . It generates rich data on several kinds of errors, including procedural errors in which steps are skipped or repeated

The Sources of Error in Spanish Writing.

ERIC Educational Resources Information Center

Justicia, Fernando; Defior, Sylvia; Pelegrina, Santiago; Martos, Francisco J.

1999-01-01

Determines the pattern of errors in Spanish spelling. Analyzes and proposes a classification system for the errors made by children in the initial stages of the acquisition of spelling skills. Finds the diverse forms of only 20 Spanish words produces 36% of the spelling errors in Spanish; and substitution is the most frequent type of error. (RS)

A research of selected textural features for detection of asbestos-cement roofing sheets using orthoimages

NASA Astrophysics Data System (ADS)

Książek, Judyta

2015-10-01

At present, there has been a great interest in the development of texture based image classification methods in many different areas. This study presents the results of research carried out to assess the usefulness of selected textural features for detection of asbestos-cement roofs in orthophotomap classification. Two different orthophotomaps of southern Poland (with ground resolution: 5 cm and 25 cm) were used. On both orthoimages representative samples for two classes: asbestos-cement roofing sheets and other roofing materials were selected. Estimation of texture analysis usefulness was conducted using machine learning methods based on decision trees (C5.0 algorithm). For this purpose, various sets of texture parameters were calculated in MaZda software. During the calculation of decision trees different numbers of texture parameters groups were considered. In order to obtain the best settings for decision trees models cross-validation was performed. Decision trees models with the lowest mean classification error were selected. The accuracy of the classification was held based on validation data sets, which were not used for the classification learning. For 5 cm ground resolution samples, the lowest mean classification error was 15.6%. The lowest mean classification error in the case of 25 cm ground resolution was 20.0%. The obtained results confirm potential usefulness of the texture parameter image processing for detection of asbestos-cement roofing sheets. In order to improve the accuracy another extended study should be considered in which additional textural features as well as spectral characteristics should be analyzed.

Application of principal component analysis to distinguish patients with schizophrenia from healthy controls based on fractional anisotropy measurements.

PubMed

Caprihan, A; Pearlson, G D; Calhoun, V D

2008-08-15

Principal component analysis (PCA) is often used to reduce the dimension of data before applying more sophisticated data analysis methods such as non-linear classification algorithms or independent component analysis. This practice is based on selecting components corresponding to the largest eigenvalues. If the ultimate goal is separation of data in two groups, then these set of components need not have the most discriminatory power. We measured the distance between two such populations using Mahalanobis distance and chose the eigenvectors to maximize it, a modified PCA method, which we call the discriminant PCA (DPCA). DPCA was applied to diffusion tensor-based fractional anisotropy images to distinguish age-matched schizophrenia subjects from healthy controls. The performance of the proposed method was evaluated by the one-leave-out method. We show that for this fractional anisotropy data set, the classification error with 60 components was close to the minimum error and that the Mahalanobis distance was twice as large with DPCA, than with PCA. Finally, by masking the discriminant function with the white matter tracts of the Johns Hopkins University atlas, we identified left superior longitudinal fasciculus as the tract which gave the least classification error. In addition, with six optimally chosen tracts the classification error was zero.

Impact of Compounding Error on Strategies for Subtyping Pathogenic Bacteria

PubMed Central

Orfe, Lisa; Davis, Margaret A.; Lafrentz, Stacey; Kang, Min-Su

2008-01-01

Abstract Comparative-omics will identify a multitude of markers that can be used for intraspecific discrimination between strains of bacteria. It seems intuitive that with this plethora of markers we can construct higher resolution subtyping assays using discrete markers to define strain “barcodes.” Unfortunately, with each new marker added to an assay, overall assay robustness declines because errors are compounded exponentially. For example, the difference in accuracy of strain classification for an assay with 60 markers will change from 99.9% to 54.7% when average probe accuracy declines from 99.999% to 99.0%. To illustrate this effect empirically, we constructed a 19 probe bead-array for subtyping Listeria monocytogenes and showed that despite seemingly reliable individual probe accuracy (>97%), our best classification results at the strain level were <75%. A more robust strategy would use as few markers as possible to achieve strain discrimination. Consequently, we developed two variable number of tandem repeat (VNTR) assays (Vibrio parahaemolyticus and L. monocytogenes) and demonstrate that these assays along with a published assay (Salmonella enterica) produce robust results when products were machine scored. The discriminatory ability with four to seven VNTR loci was comparable to pulsed-field gel electrophoresis. Passage experiments showed some instability with ca. 5% of passaged lines showing evidence for new alleles within 30 days (V. parahaemolyticus and S. enterica). Changes were limited to a single locus and allele so conservative rules can be used to determine strain matching. Most importantly, VNTRs appear robust and portable and can clearly discriminate between strains with relatively few loci thereby limiting effects of compounding error. PMID:18713065

Pareto-optimal multi-objective dimensionality reduction deep auto-encoder for mammography classification.

PubMed

Taghanaki, Saeid Asgari; Kawahara, Jeremy; Miles, Brandon; Hamarneh, Ghassan

2017-07-01

Feature reduction is an essential stage in computer aided breast cancer diagnosis systems. Multilayer neural networks can be trained to extract relevant features by encoding high-dimensional data into low-dimensional codes. Optimizing traditional auto-encoders works well only if the initial weights are close to a proper solution. They are also trained to only reduce the mean squared reconstruction error (MRE) between the encoder inputs and the decoder outputs, but do not address the classification error. The goal of the current work is to test the hypothesis that extending traditional auto-encoders (which only minimize reconstruction error) to multi-objective optimization for finding Pareto-optimal solutions provides more discriminative features that will improve classification performance when compared to single-objective and other multi-objective approaches (i.e. scalarized and sequential). In this paper, we introduce a novel multi-objective optimization of deep auto-encoder networks, in which the auto-encoder optimizes two objectives: MRE and mean classification error (MCE) for Pareto-optimal solutions, rather than just MRE. These two objectives are optimized simultaneously by a non-dominated sorting genetic algorithm. We tested our method on 949 X-ray mammograms categorized into 12 classes. The results show that the features identified by the proposed algorithm allow a classification accuracy of up to 98.45%, demonstrating favourable accuracy over the results of state-of-the-art methods reported in the literature. We conclude that adding the classification objective to the traditional auto-encoder objective and optimizing for finding Pareto-optimal solutions, using evolutionary multi-objective optimization, results in producing more discriminative features. Copyright © 2017 Elsevier B.V. All rights reserved.

Wildlife management by habitat units: A preliminary plan of action

NASA Technical Reports Server (NTRS)

Frentress, C. D.; Frye, R. G.

1975-01-01

Procedures for yielding vegetation type maps were developed using LANDSAT data and a computer assisted classification analysis (LARSYS) to assist in managing populations of wildlife species by defined area units. Ground cover in Travis County, Texas was classified on two occasions using a modified version of the unsupervised approach to classification. The first classification produced a total of 17 classes. Examination revealed that further grouping was justified. A second analysis produced 10 classes which were displayed on printouts which were later color-coded. The final classification was 82 percent accurate. While the classification map appeared to satisfactorily depict the existing vegetation, two classes were determined to contain significant error. The major sources of error could have been eliminated by stratifying cluster sites more closely among previously mapped soil associations that are identified with particular plant associations and by precisely defining class nomenclature using established criteria early in the analysis.

The Relationship between Occurrence Timing of Dispensing Errors and Subsequent Danger to Patients under the Situation According to the Classification of Drugs by Efficacy.

PubMed

Tsuji, Toshikazu; Nagata, Kenichiro; Kawashiri, Takehiro; Yamada, Takaaki; Irisa, Toshihiro; Murakami, Yuko; Kanaya, Akiko; Egashira, Nobuaki; Masuda, Satohiro

2016-01-01

There are many reports regarding various medical institutions' attempts at the prevention of dispensing errors. However, the relationship between occurrence timing of dispensing errors and subsequent danger to patients has not been studied under the situation according to the classification of drugs by efficacy. Therefore, we analyzed the relationship between position and time regarding the occurrence of dispensing errors. Furthermore, we investigated the relationship between occurrence timing of them and danger to patients. In this study, dispensing errors and incidents in three categories (drug name errors, drug strength errors, drug count errors) were classified into two groups in terms of its drug efficacy (efficacy similarity (-) group, efficacy similarity (+) group), into three classes in terms of the occurrence timing of dispensing errors (initial phase errors, middle phase errors, final phase errors). Then, the rates of damage shifting from "dispensing errors" to "damage to patients" were compared as an index of danger between two groups and among three classes. Consequently, the rate of damage in "efficacy similarity (-) group" was significantly higher than that in "efficacy similarity (+) group". Furthermore, the rate of damage is the highest in "initial phase errors", the lowest in "final phase errors" among three classes. From the results of this study, it became clear that the earlier the timing of dispensing errors occurs, the more severe the damage to patients becomes.

Classification Model for Forest Fire Hotspot Occurrences Prediction Using ANFIS Algorithm

NASA Astrophysics Data System (ADS)

Wijayanto, A. K.; Sani, O.; Kartika, N. D.; Herdiyeni, Y.

2017-01-01

This study proposed the application of data mining technique namely Adaptive Neuro-Fuzzy inference system (ANFIS) on forest fires hotspot data to develop classification models for hotspots occurrence in Central Kalimantan. Hotspot is a point that is indicated as the location of fires. In this study, hotspot distribution is categorized as true alarm and false alarm. ANFIS is a soft computing method in which a given inputoutput data set is expressed in a fuzzy inference system (FIS). The FIS implements a nonlinear mapping from its input space to the output space. The method of this study classified hotspots as target objects by correlating spatial attributes data using three folds in ANFIS algorithm to obtain the best model. The best result obtained from the 3rd fold provided low error for training (error = 0.0093676) and also low error testing result (error = 0.0093676). Attribute of distance to road is the most determining factor that influences the probability of true and false alarm where the level of human activities in this attribute is higher. This classification model can be used to develop early warning system of forest fire.

Automatic Classification of Aerial Imagery for Urban Hydrological Applications

NASA Astrophysics Data System (ADS)

Paul, A.; Yang, C.; Breitkopf, U.; Liu, Y.; Wang, Z.; Rottensteiner, F.; Wallner, M.; Verworn, A.; Heipke, C.

2018-04-01

In this paper we investigate the potential of automatic supervised classification for urban hydrological applications. In particular, we contribute to runoff simulations using hydrodynamic urban drainage models. In order to assess whether the capacity of the sewers is sufficient to avoid surcharge within certain return periods, precipitation is transformed into runoff. The transformation of precipitation into runoff requires knowledge about the proportion of drainage-effective areas and their spatial distribution in the catchment area. Common simulation methods use the coefficient of imperviousness as an important parameter to estimate the overland flow, which subsequently contributes to the pipe flow. The coefficient of imperviousness is the percentage of area covered by impervious surfaces such as roofs or road surfaces. It is still common practice to assign the coefficient of imperviousness for each particular land parcel manually by visual interpretation of aerial images. Based on classification results of these imagery we contribute to an objective automatic determination of the coefficient of imperviousness. In this context we compare two classification techniques: Random Forests (RF) and Conditional Random Fields (CRF). Experimental results performed on an urban test area show good results and confirm that the automated derivation of the coefficient of imperviousness, apart from being more objective and, thus, reproducible, delivers more accurate results than the interactive estimation. We achieve an overall accuracy of about 85 % for both classifiers. The root mean square error of the differences of the coefficient of imperviousness compared to the reference is 4.4 % for the CRF-based classification, and 3.8 % for the RF-based classification.

Integration of multi-array sensors and support vector machines for the detection and classification of organophosphate nerve agents

NASA Astrophysics Data System (ADS)

Land, Walker H., Jr.; Sadik, Omowunmi A.; Embrechts, Mark J.; Leibensperger, Dale; Wong, Lut; Wanekaya, Adam; Uematsu, Michiko

2003-08-01

Due to the increased threats of chemical and biological weapons of mass destruction (WMD) by international terrorist organizations, a significant effort is underway to develop tools that can be used to detect and effectively combat biochemical warfare. Furthermore, recent events have highlighted awareness that chemical and biological agents (CBAs) may become the preferred, cheap alternative WMD, because these agents can effectively attack large populations while leaving infrastructures intact. Despite the availability of numerous sensing devices, intelligent hybrid sensors that can detect and degrade CBAs are virtually nonexistent. This paper reports the integration of multi-array sensors with Support Vector Machines (SVMs) for the detection of organophosphates nerve agents using parathion and dichlorvos as model stimulants compounds. SVMs were used for the design and evaluation of new and more accurate data extraction, preprocessing and classification. Experimental results for the paradigms developed using Structural Risk Minimization, show a significant increase in classification accuracy when compared to the existing AromaScan baseline system. Specifically, the results of this research has demonstrated that, for the Parathion versus Dichlorvos pair, when compared to the AromaScan baseline system: (1) a 23% improvement in the overall ROC Az index using the S2000 kernel, with similar improvements with the Gaussian and polynomial (of degree 2) kernels, (2) a significant 173% improvement in specificity with the S2000 kernel. This means that the number of false negative errors were reduced by 173%, while making no false positive errors, when compared to the AromaScan base line performance. (3) The Gaussian and polynomial kernels demonstrated similar specificity at 100% sensitivity. All SVM classifiers provided essentially perfect classification performance for the Dichlorvos versus Trichlorfon pair. For the most difficult classification task, the Parathion versus Paraoxon pair, the following results were achieved (using the three SVM kernels: (1) ROC Az indices from approximately 93% to greater than 99%, (2) partial Az values from ~79% to 93%, (3) specificities from 76% to ~84% at 100 and 98% sensitivity, and (4) PPVs from 73% to ~84% at 100% and 98% sensitivities. These are excellent results, considering only one atom differentiates these nerve agents.

Classification based upon gene expression data: bias and precision of error rates.

PubMed

Wood, Ian A; Visscher, Peter M; Mengersen, Kerrie L

2007-06-01

Gene expression data offer a large number of potentially useful predictors for the classification of tissue samples into classes, such as diseased and non-diseased. The predictive error rate of classifiers can be estimated using methods such as cross-validation. We have investigated issues of interpretation and potential bias in the reporting of error rate estimates. The issues considered here are optimization and selection biases, sampling effects, measures of misclassification rate, baseline error rates, two-level external cross-validation and a novel proposal for detection of bias using the permutation mean. Reporting an optimal estimated error rate incurs an optimization bias. Downward bias of 3-5% was found in an existing study of classification based on gene expression data and may be endemic in similar studies. Using a simulated non-informative dataset and two example datasets from existing studies, we show how bias can be detected through the use of label permutations and avoided using two-level external cross-validation. Some studies avoid optimization bias by using single-level cross-validation and a test set, but error rates can be more accurately estimated via two-level cross-validation. In addition to estimating the simple overall error rate, we recommend reporting class error rates plus where possible the conditional risk incorporating prior class probabilities and a misclassification cost matrix. We also describe baseline error rates derived from three trivial classifiers which ignore the predictors. R code which implements two-level external cross-validation with the PAMR package, experiment code, dataset details and additional figures are freely available for non-commercial use from http://www.maths.qut.edu.au/profiles/wood/permr.jsp

Gaussian-based filters for detecting Martian dust devils

USGS Publications Warehouse

Yang, F.; Mlsna, P.A.; Geissler, P.

2006-01-01

The ability to automatically detect dust devils in the Martian atmosphere from orbital imagery is becoming important both for scientific studies of the planet and for the planning of future robotic and manned missions. This paper describes our approach for the unsupervised detection of dust devils and the preliminary results achieved to date. The algorithm centers upon the use of a filter constructed from Gaussian profiles to match dust devil characteristics over a range of scale and orientation. The classification step is designed to reduce false positive errors caused by static surface features such as craters. A brief discussion of planned future work is included. ?? 2006 IEEE.

LACIE performance predictor FOC users manual

NASA Technical Reports Server (NTRS)

1976-01-01

The LACIE Performance Predictor (LPP) is a computer simulation of the LACIE process for predicting worldwide wheat production. The simulation provides for the introduction of various errors into the system and provides estimates based on these errors, thus allowing the user to determine the impact of selected error sources. The FOC LPP simulates the acquisition of the sample segment data by the LANDSAT Satellite (DAPTS), the classification of the agricultural area within the sample segment (CAMS), the estimation of the wheat yield (YES), and the production estimation and aggregation (CAS). These elements include data acquisition characteristics, environmental conditions, classification algorithms, the LACIE aggregation and data adjustment procedures. The operational structure for simulating these elements consists of the following key programs: (1) LACIE Utility Maintenance Process, (2) System Error Executive, (3) Ephemeris Generator, (4) Access Generator, (5) Acquisition Selector, (6) LACIE Error Model (LEM), and (7) Post Processor.

Sensitivity of geographic information system outputs to errors in remotely sensed data

NASA Technical Reports Server (NTRS)

Ramapriyan, H. K.; Boyd, R. K.; Gunther, F. J.; Lu, Y. C.

1981-01-01

The sensitivity of the outputs of a geographic information system (GIS) to errors in inputs derived from remotely sensed data (RSD) is investigated using a suitability model with per-cell decisions and a gridded geographic data base whose cells are larger than the RSD pixels. The process of preparing RSD as input to a GIS is analyzed, and the errors associated with classification and registration are examined. In the case of the model considered, it is found that the errors caused during classification and registration are partially compensated by the aggregation of pixels. The compensation is quantified by means of an analytical model, a Monte Carlo simulation, and experiments with Landsat data. The results show that error reductions of the order of 50% occur because of aggregation when 25 pixels of RSD are used per cell in the geographic data base.

Improved semi-supervised online boosting for object tracking

NASA Astrophysics Data System (ADS)

Li, Yicui; Qi, Lin; Tan, Shukun

2016-10-01

The advantage of an online semi-supervised boosting method which takes object tracking problem as a classification problem, is training a binary classifier from labeled and unlabeled examples. Appropriate object features are selected based on real time changes in the object. However, the online semi-supervised boosting method faces one key problem: The traditional self-training using the classification results to update the classifier itself, often leads to drifting or tracking failure, due to the accumulated error during each update of the tracker. To overcome the disadvantages of semi-supervised online boosting based on object tracking methods, the contribution of this paper is an improved online semi-supervised boosting method, in which the learning process is guided by positive (P) and negative (N) constraints, termed P-N constraints, which restrict the labeling of the unlabeled samples. First, we train the classification by an online semi-supervised boosting. Then, this classification is used to process the next frame. Finally, the classification is analyzed by the P-N constraints, which are used to verify if the labels of unlabeled data assigned by the classifier are in line with the assumptions made about positive and negative samples. The proposed algorithm can effectively improve the discriminative ability of the classifier and significantly alleviate the drifting problem in tracking applications. In the experiments, we demonstrate real-time tracking of our tracker on several challenging test sequences where our tracker outperforms other related on-line tracking methods and achieves promising tracking performance.

Photoacoustic discrimination of vascular and pigmented lesions using classical and Bayesian methods

NASA Astrophysics Data System (ADS)

Swearingen, Jennifer A.; Holan, Scott H.; Feldman, Mary M.; Viator, John A.

2010-01-01

Discrimination of pigmented and vascular lesions in skin can be difficult due to factors such as size, subungual location, and the nature of lesions containing both melanin and vascularity. Misdiagnosis may lead to precancerous or cancerous lesions not receiving proper medical care. To aid in the rapid and accurate diagnosis of such pathologies, we develop a photoacoustic system to determine the nature of skin lesions in vivo. By irradiating skin with two laser wavelengths, 422 and 530 nm, we induce photoacoustic responses, and the relative response at these two wavelengths indicates whether the lesion is pigmented or vascular. This response is due to the distinct absorption spectrum of melanin and hemoglobin. In particular, pigmented lesions have ratios of photoacoustic amplitudes of approximately 1.4 to 1 at the two wavelengths, while vascular lesions have ratios of about 4.0 to 1. Furthermore, we consider two statistical methods for conducting classification of lesions: standard multivariate analysis classification techniques and a Bayesian-model-based approach. We study 15 human subjects with eight vascular and seven pigmented lesions. Using the classical method, we achieve a perfect classification rate, while the Bayesian approach has an error rate of 20%.

Classification of DNA nucleotides with transverse tunneling currents

NASA Astrophysics Data System (ADS)

Nyvold Pedersen, Jonas; Boynton, Paul; Di Ventra, Massimiliano; Jauho, Antti-Pekka; Flyvbjerg, Henrik

2017-01-01

It has been theoretically suggested and experimentally demonstrated that fast and low-cost sequencing of DNA, RNA, and peptide molecules might be achieved by passing such molecules between electrodes embedded in a nanochannel. The experimental realization of this scheme faces major challenges, however. In realistic liquid environments, typical currents in tunneling devices are of the order of picoamps. This corresponds to only six electrons per microsecond, and this number affects the integration time required to do current measurements in real experiments. This limits the speed of sequencing, though current fluctuations due to Brownian motion of the molecule average out during the required integration time. Moreover, data acquisition equipment introduces noise, and electronic filters create correlations in time-series data. We discuss how these effects must be included in the analysis of, e.g., the assignment of specific nucleobases to current signals. As the signals from different molecules overlap, unambiguous classification is impossible with a single measurement. We argue that the assignment of molecules to a signal is a standard pattern classification problem and calculation of the error rates is straightforward. The ideas presented here can be extended to other sequencing approaches of current interest.

Linear Discriminant Analysis Achieves High Classification Accuracy for the BOLD fMRI Response to Naturalistic Movie Stimuli

PubMed Central

Mandelkow, Hendrik; de Zwart, Jacco A.; Duyn, Jeff H.

2016-01-01

Naturalistic stimuli like movies evoke complex perceptual processes, which are of great interest in the study of human cognition by functional MRI (fMRI). However, conventional fMRI analysis based on statistical parametric mapping (SPM) and the general linear model (GLM) is hampered by a lack of accurate parametric models of the BOLD response to complex stimuli. In this situation, statistical machine-learning methods, a.k.a. multivariate pattern analysis (MVPA), have received growing attention for their ability to generate stimulus response models in a data-driven fashion. However, machine-learning methods typically require large amounts of training data as well as computational resources. In the past, this has largely limited their application to fMRI experiments involving small sets of stimulus categories and small regions of interest in the brain. By contrast, the present study compares several classification algorithms known as Nearest Neighbor (NN), Gaussian Naïve Bayes (GNB), and (regularized) Linear Discriminant Analysis (LDA) in terms of their classification accuracy in discriminating the global fMRI response patterns evoked by a large number of naturalistic visual stimuli presented as a movie. Results show that LDA regularized by principal component analysis (PCA) achieved high classification accuracies, above 90% on average for single fMRI volumes acquired 2 s apart during a 300 s movie (chance level 0.7% = 2 s/300 s). The largest source of classification errors were autocorrelations in the BOLD signal compounded by the similarity of consecutive stimuli. All classifiers performed best when given input features from a large region of interest comprising around 25% of the voxels that responded significantly to the visual stimulus. Consistent with this, the most informative principal components represented widespread distributions of co-activated brain regions that were similar between subjects and may represent functional networks. In light of these results, the combination of naturalistic movie stimuli and classification analysis in fMRI experiments may prove to be a sensitive tool for the assessment of changes in natural cognitive processes under experimental manipulation. PMID:27065832

Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks

PubMed Central

Mostafa, Hesham; Pedroni, Bruno; Sheik, Sadique; Cauwenberghs, Gert

2017-01-01

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing custom silicon devices to accelerate inference in ANNs. Accelerating the training phase, however, has attracted relatively little attention. In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation. Learning is performed in parallel with inference in the forward pass, removing the need for an explicit backward pass and requiring no extra weight lookup. By using binary state variables in the feedforward network and ternary errors in truncated-error backpropagation, the need for any multiplications in the forward and backward passes is removed, and memory requirements for the pipelining are drastically reduced. Further reduction in addition operations owing to the sparsity in the forward neural and backpropagating error signal paths contributes to highly efficient hardware implementation. For proof-of-concept validation, we demonstrate on-line learning of MNIST handwritten digit classification on a Spartan 6 FPGA interfacing with an external 1Gb DDR2 DRAM, that shows small degradation in test error performance compared to an equivalently sized binary ANN trained off-line using standard back-propagation and exact errors. Our results highlight an attractive synergy between pipelined backpropagation and binary-state networks in substantially reducing computation and memory requirements, making pipelined on-line learning practical in deep networks. PMID:28932180

Hardware-Efficient On-line Learning through Pipelined Truncated-Error Backpropagation in Binary-State Networks.

PubMed

Mostafa, Hesham; Pedroni, Bruno; Sheik, Sadique; Cauwenberghs, Gert

2017-01-01

Artificial neural networks (ANNs) trained using backpropagation are powerful learning architectures that have achieved state-of-the-art performance in various benchmarks. Significant effort has been devoted to developing custom silicon devices to accelerate inference in ANNs. Accelerating the training phase, however, has attracted relatively little attention. In this paper, we describe a hardware-efficient on-line learning technique for feedforward multi-layer ANNs that is based on pipelined backpropagation. Learning is performed in parallel with inference in the forward pass, removing the need for an explicit backward pass and requiring no extra weight lookup. By using binary state variables in the feedforward network and ternary errors in truncated-error backpropagation, the need for any multiplications in the forward and backward passes is removed, and memory requirements for the pipelining are drastically reduced. Further reduction in addition operations owing to the sparsity in the forward neural and backpropagating error signal paths contributes to highly efficient hardware implementation. For proof-of-concept validation, we demonstrate on-line learning of MNIST handwritten digit classification on a Spartan 6 FPGA interfacing with an external 1Gb DDR2 DRAM, that shows small degradation in test error performance compared to an equivalently sized binary ANN trained off-line using standard back-propagation and exact errors. Our results highlight an attractive synergy between pipelined backpropagation and binary-state networks in substantially reducing computation and memory requirements, making pipelined on-line learning practical in deep networks.

Error Analysis in Composition of Iranian Lower Intermediate Students

ERIC Educational Resources Information Center

Taghavi, Mehdi

2012-01-01

Learners make errors during the process of learning languages. This study examines errors in writing task of twenty Iranian lower intermediate male students aged between 13 and 15. A subject was given to the participants was a composition about the seasons of a year. All of the errors were identified and classified. Corder's classification (1967)…

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.

Credit Risk Evaluation Using a C-Variable Least Squares Support Vector Classification Model

NASA Astrophysics Data System (ADS)

Yu, Lean; Wang, Shouyang; Lai, K. K.

Credit risk evaluation is one of the most important issues in financial risk management. In this paper, a C-variable least squares support vector classification (C-VLSSVC) model is proposed for credit risk analysis. The main idea of this model is based on the prior knowledge that different classes may have different importance for modeling and more weights should be given to those classes with more importance. The C-VLSSVC model can be constructed by a simple modification of the regularization parameter in LSSVC, whereby more weights are given to the lease squares classification errors with important classes than the lease squares classification errors with unimportant classes while keeping the regularized terms in its original form. For illustration purpose, a real-world credit dataset is used to test the effectiveness of the C-VLSSVC model.

Hybrid analysis of multiaxis electromagnetic data for discrimination of munitions and explosives of concern

USGS Publications Warehouse

Friedel, M.J.; Asch, T.H.; Oden, C.

2012-01-01

The remediation of land containing munitions and explosives of concern, otherwise known as unexploded ordnance, is an ongoing problem facing the U.S. Department of Defense and similar agencies worldwide that have used or are transferring training ranges or munitions disposal areas to civilian control. The expense associated with cleanup of land previously used for military training and war provides impetus for research towards enhanced discrimination of buried unexploded ordnance. Towards reducing that expense, a multiaxis electromagnetic induction data collection and software system, called ALLTEM, was designed and tested with support from the U.S. Department of Defense Environmental Security Technology Certification Program. ALLTEM is an on-time time-domain system that uses a continuous triangle-wave excitation to measure the target-step response rather than traditional impulse response. The system cycles through three orthogonal transmitting loops and records a total of 19 different transmitting and receiving loop combinations with a nominal spatial data sampling interval of 20 cm. Recorded data are pre-processed and then used in a hybrid discrimination scheme involving both data-driven and numerical classification techniques. The data-driven classification scheme is accomplished in three steps. First, field observations are used to train a type of unsupervised artificial neural network, a self-organizing map (SOM). Second, the SOM is used to simultaneously estimate target parameters (depth, azimuth, inclination, item type and weight) by iterative minimization of the topographic error vectors. Third, the target classification is accomplished by evaluating histograms of the estimated parameters. The numerical classification scheme is also accomplished in three steps. First, the Biot–Savart law is used to model the primary magnetic fields from the transmitter coils and the secondary magnetic fields generated by currents induced in the target materials in the ground. Second, the target response is modelled by three orthogonal dipoles from prolate, oblate and triaxial ellipsoids with one long axis and two shorter axes. Each target consists of all three dipoles. Third, unknown target parameters are determined by comparing modelled to measured target responses. By comparing the rms error among the self-organizing map and numerical classification results, we achieved greater than 95 per cent detection and correct classification of the munitions and explosives of concern at the direct fire and indirect fire test areas at the UXO Standardized Test Site at the Aberdeen Proving Ground, Maryland in 2010.

Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia

PubMed Central

Kim, Junghoe; Calhoun, Vince D.; Shim, Eunsoo; Lee, Jong-Hwan

2015-01-01

Functional connectivity (FC) patterns obtained from resting-state functional magnetic resonance imaging data are commonly employed to study neuropsychiatric conditions by using pattern classifiers such as the support vector machine (SVM). Meanwhile, a deep neural network (DNN) with multiple hidden layers has shown its ability to systematically extract lower-to-higher level information of image and speech data from lower-to-higher hidden layers, markedly enhancing classification accuracy. The objective of this study was to adopt the DNN for whole-brain resting-state FC pattern classification of schizophrenia (SZ) patients vs. healthy controls (HCs) and identification of aberrant FC patterns associated with SZ. We hypothesized that the lower-to-higher level features learned via the DNN would significantly enhance the classification accuracy, and proposed an adaptive learning algorithm to explicitly control the weight sparsity in each hidden layer via L1-norm regularization. Furthermore, the weights were initialized via stacked autoencoder based pre-training to further improve the classification performance. Classification accuracy was systematically evaluated as a function of (1) the number of hidden layers/nodes, (2) the use of L1-norm regularization, (3) the use of the pre-training, (4) the use of framewise displacement (FD) removal, and (5) the use of anatomical/functional parcellation. Using FC patterns from anatomically parcellated regions without FD removal, an error rate of 14.2% was achieved by employing three hidden layers and 50 hidden nodes with both L1-norm regularization and pre-training, which was substantially lower than the error rate from the SVM (22.3%). Moreover, the trained DNN weights (i.e., the learned features) were found to represent the hierarchical organization of aberrant FC patterns in SZ compared with HC. Specifically, pairs of nodes extracted from the lower hidden layer represented sparse FC patterns implicated in SZ, which was quantified by using kurtosis/modularity measures and features from the higher hidden layer showed holistic/global FC patterns differentiating SZ from HC. Our proposed schemes and reported findings attained by using the DNN classifier and whole-brain FC data suggest that such approaches show improved ability to learn hidden patterns in brain imaging data, which may be useful for developing diagnostic tools for SZ and other neuropsychiatric disorders and identifying associated aberrant FC patterns. PMID:25987366

Hybrid analysis of multiaxis electromagnetic data for discrimination of munitions and explosives of concern

NASA Astrophysics Data System (ADS)

Friedel, M. J.; Asch, T. H.; Oden, C.

2012-08-01

The remediation of land containing munitions and explosives of concern, otherwise known as unexploded ordnance, is an ongoing problem facing the U.S. Department of Defense and similar agencies worldwide that have used or are transferring training ranges or munitions disposal areas to civilian control. The expense associated with cleanup of land previously used for military training and war provides impetus for research towards enhanced discrimination of buried unexploded ordnance. Towards reducing that expense, a multiaxis electromagnetic induction data collection and software system, called ALLTEM, was designed and tested with support from the U.S. Department of Defense Environmental Security Technology Certification Program. ALLTEM is an on-time time-domain system that uses a continuous triangle-wave excitation to measure the target-step response rather than traditional impulse response. The system cycles through three orthogonal transmitting loops and records a total of 19 different transmitting and receiving loop combinations with a nominal spatial data sampling interval of 20 cm. Recorded data are pre-processed and then used in a hybrid discrimination scheme involving both data-driven and numerical classification techniques. The data-driven classification scheme is accomplished in three steps. First, field observations are used to train a type of unsupervised artificial neural network, a self-organizing map (SOM). Second, the SOM is used to simultaneously estimate target parameters (depth, azimuth, inclination, item type and weight) by iterative minimization of the topographic error vectors. Third, the target classification is accomplished by evaluating histograms of the estimated parameters. The numerical classification scheme is also accomplished in three steps. First, the Biot-Savart law is used to model the primary magnetic fields from the transmitter coils and the secondary magnetic fields generated by currents induced in the target materials in the ground. Second, the target response is modelled by three orthogonal dipoles from prolate, oblate and triaxial ellipsoids with one long axis and two shorter axes. Each target consists of all three dipoles. Third, unknown target parameters are determined by comparing modelled to measured target responses. By comparing the rms error among the self-organizing map and numerical classification results, we achieved greater than 95 per cent detection and correct classification of the munitions and explosives of concern at the direct fire and indirect fire test areas at the UXO Standardized Test Site at the Aberdeen Proving Ground, Maryland in 2010.

Exception handling for sensor fusion

NASA Astrophysics Data System (ADS)

Chavez, G. T.; Murphy, Robin R.

1993-08-01

This paper presents a control scheme for handling sensing failures (sensor malfunctions, significant degradations in performance due to changes in the environment, and errant expectations) in sensor fusion for autonomous mobile robots. The advantages of the exception handling mechanism are that it emphasizes a fast response to sensing failures, is able to use only a partial causal model of sensing failure, and leads to a graceful degradation of sensing if the sensing failure cannot be compensated for. The exception handling mechanism consists of two modules: error classification and error recovery. The error classification module in the exception handler attempts to classify the type and source(s) of the error using a modified generate-and-test procedure. If the source of the error is isolated, the error recovery module examines its cache of recovery schemes, which either repair or replace the current sensing configuration. If the failure is due to an error in expectation or cannot be identified, the planner is alerted. Experiments using actual sensor data collected by the CSM Mobile Robotics/Machine Perception Laboratory's Denning mobile robot demonstrate the operation of the exception handling mechanism.

Using beta binomials to estimate classification uncertainty for ensemble models.

PubMed

Clark, Robert D; Liang, Wenkel; Lee, Adam C; Lawless, Michael S; Fraczkiewicz, Robert; Waldman, Marvin

2014-01-01

Quantitative structure-activity (QSAR) models have enormous potential for reducing drug discovery and development costs as well as the need for animal testing. Great strides have been made in estimating their overall reliability, but to fully realize that potential, researchers and regulators need to know how confident they can be in individual predictions. Submodels in an ensemble model which have been trained on different subsets of a shared training pool represent multiple samples of the model space, and the degree of agreement among them contains information on the reliability of ensemble predictions. For artificial neural network ensembles (ANNEs) using two different methods for determining ensemble classification - one using vote tallies and the other averaging individual network outputs - we have found that the distribution of predictions across positive vote tallies can be reasonably well-modeled as a beta binomial distribution, as can the distribution of errors. Together, these two distributions can be used to estimate the probability that a given predictive classification will be in error. Large data sets comprised of logP, Ames mutagenicity, and CYP2D6 inhibition data are used to illustrate and validate the method. The distributions of predictions and errors for the training pool accurately predicted the distribution of predictions and errors for large external validation sets, even when the number of positive and negative examples in the training pool were not balanced. Moreover, the likelihood of a given compound being prospectively misclassified as a function of the degree of consensus between networks in the ensemble could in most cases be estimated accurately from the fitted beta binomial distributions for the training pool. Confidence in an individual predictive classification by an ensemble model can be accurately assessed by examining the distributions of predictions and errors as a function of the degree of agreement among the constituent submodels. Further, ensemble uncertainty estimation can often be improved by adjusting the voting or classification threshold based on the parameters of the error distribution. Finally, the profiles for models whose predictive uncertainty estimates are not reliable provide clues to that effect without the need for comparison to an external test set.

Undergraduate paramedic students cannot do drug calculations

PubMed Central

Eastwood, Kathryn; Boyle, Malcolm J; Williams, Brett

2012-01-01

BACKGROUND: Previous investigation of drug calculation skills of qualified paramedics has highlighted poor mathematical ability with no published studies having been undertaken on undergraduate paramedics. There are three major error classifications. Conceptual errors involve an inability to formulate an equation from information given, arithmetical errors involve an inability to operate a given equation, and finally computation errors are simple errors of addition, subtraction, division and multiplication. The objective of this study was to determine if undergraduate paramedics at a large Australia university could accurately perform common drug calculations and basic mathematical equations normally required in the workplace. METHODS: A cross-sectional study methodology using a paper-based questionnaire was administered to undergraduate paramedic students to collect demographical data, student attitudes regarding their drug calculation performance, and answers to a series of basic mathematical and drug calculation questions. Ethics approval was granted. RESULTS: The mean score of correct answers was 39.5% with one student scoring 100%, 3.3% of students (n=3) scoring greater than 90%, and 63% (n=58) scoring 50% or less, despite 62% (n=57) of the students stating they ‘did not have any drug calculations issues’. On average those who completed a minimum of year 12 Specialist Maths achieved scores over 50%. Conceptual errors made up 48.5%, arithmetical 31.1% and computational 17.4%. CONCLUSIONS: This study suggests undergraduate paramedics have deficiencies in performing accurate calculations, with conceptual errors indicating a fundamental lack of mathematical understanding. The results suggest an unacceptable level of mathematical competence to practice safely in the unpredictable prehospital environment. PMID:25215067

Using failure mode and effects analysis to improve the safety of neonatal parenteral nutrition.

PubMed

Arenas Villafranca, Jose Javier; Gómez Sánchez, Araceli; Nieto Guindo, Miriam; Faus Felipe, Vicente

2014-07-15

Failure mode and effects analysis (FMEA) was used to identify potential errors and to enable the implementation of measures to improve the safety of neonatal parenteral nutrition (PN). FMEA was used to analyze the preparation and dispensing of neonatal PN from the perspective of the pharmacy service in a general hospital. A process diagram was drafted, illustrating the different phases of the neonatal PN process. Next, the failures that could occur in each of these phases were compiled and cataloged, and a questionnaire was developed in which respondents were asked to rate the following aspects of each error: incidence, detectability, and severity. The highest scoring failures were considered high risk and identified as priority areas for improvements to be made. The evaluation process detected a total of 82 possible failures. Among the phases with the highest number of possible errors were transcription of the medical order, formulation of the PN, and preparation of material for the formulation. After the classification of these 82 possible failures and of their relative importance, a checklist was developed to achieve greater control in the error-detection process. FMEA demonstrated that use of the checklist reduced the level of risk and improved the detectability of errors. FMEA was useful for detecting medication errors in the PN preparation process and enabling corrective measures to be taken. A checklist was developed to reduce errors in the most critical aspects of the process. Copyright © 2014 by the American Society of Health-System Pharmacists, Inc. All rights reserved.

Original and Mirror Face Images and Minimum Squared Error Classification for Visible Light Face Recognition.

PubMed

Wang, Rong

2015-01-01

In real-world applications, the image of faces varies with illumination, facial expression, and poses. It seems that more training samples are able to reveal possible images of the faces. Though minimum squared error classification (MSEC) is a widely used method, its applications on face recognition usually suffer from the problem of a limited number of training samples. In this paper, we improve MSEC by using the mirror faces as virtual training samples. We obtained the mirror faces generated from original training samples and put these two kinds of samples into a new set. The face recognition experiments show that our method does obtain high accuracy performance in classification.

Generating highly accurate prediction hypotheses through collaborative ensemble learning

NASA Astrophysics Data System (ADS)

Arsov, Nino; Pavlovski, Martin; Basnarkov, Lasko; Kocarev, Ljupco

2017-03-01

Ensemble generation is a natural and convenient way of achieving better generalization performance of learning algorithms by gathering their predictive capabilities. Here, we nurture the idea of ensemble-based learning by combining bagging and boosting for the purpose of binary classification. Since the former improves stability through variance reduction, while the latter ameliorates overfitting, the outcome of a multi-model that combines both strives toward a comprehensive net-balancing of the bias-variance trade-off. To further improve this, we alter the bagged-boosting scheme by introducing collaboration between the multi-model’s constituent learners at various levels. This novel stability-guided classification scheme is delivered in two flavours: during or after the boosting process. Applied among a crowd of Gentle Boost ensembles, the ability of the two suggested algorithms to generalize is inspected by comparing them against Subbagging and Gentle Boost on various real-world datasets. In both cases, our models obtained a 40% generalization error decrease. But their true ability to capture details in data was revealed through their application for protein detection in texture analysis of gel electrophoresis images. They achieve improved performance of approximately 0.9773 AUROC when compared to the AUROC of 0.9574 obtained by an SVM based on recursive feature elimination.

Machine Learning Techniques for Stellar Light Curve Classification

NASA Astrophysics Data System (ADS)

Hinners, Trisha A.; Tat, Kevin; Thorp, Rachel

2018-07-01

We apply machine learning techniques in an attempt to predict and classify stellar properties from noisy and sparse time-series data. We preprocessed over 94 GB of Kepler light curves from the Mikulski Archive for Space Telescopes (MAST) to classify according to 10 distinct physical properties using both representation learning and feature engineering approaches. Studies using machine learning in the field have been primarily done on simulated data, making our study one of the first to use real light-curve data for machine learning approaches. We tuned our data using previous work with simulated data as a template and achieved mixed results between the two approaches. Representation learning using a long short-term memory recurrent neural network produced no successful predictions, but our work with feature engineering was successful for both classification and regression. In particular, we were able to achieve values for stellar density, stellar radius, and effective temperature with low error (∼2%–4%) and good accuracy (∼75%) for classifying the number of transits for a given star. The results show promise for improvement for both approaches upon using larger data sets with a larger minority class. This work has the potential to provide a foundation for future tools and techniques to aid in the analysis of astrophysical data.

Rank preserving sparse learning for Kinect based scene classification.

PubMed

Tao, Dapeng; Jin, Lianwen; Yang, Zhao; Li, Xuelong

2013-10-01

With the rapid development of the RGB-D sensors and the promptly growing population of the low-cost Microsoft Kinect sensor, scene classification, which is a hard, yet important, problem in computer vision, has gained a resurgence of interest recently. That is because the depth of information provided by the Kinect sensor opens an effective and innovative way for scene classification. In this paper, we propose a new scheme for scene classification, which applies locality-constrained linear coding (LLC) to local SIFT features for representing the RGB-D samples and classifies scenes through the cooperation between a new rank preserving sparse learning (RPSL) based dimension reduction and a simple classification method. RPSL considers four aspects: 1) it preserves the rank order information of the within-class samples in a local patch; 2) it maximizes the margin between the between-class samples on the local patch; 3) the L1-norm penalty is introduced to obtain the parsimony property; and 4) it models the classification error minimization by utilizing the least-squares error minimization. Experiments are conducted on the NYU Depth V1 dataset and demonstrate the robustness and effectiveness of RPSL for scene classification.

Comparison of two Classification methods (MLC and SVM) to extract land use and land cover in Johor Malaysia

NASA Astrophysics Data System (ADS)

Rokni Deilmai, B.; Ahmad, B. Bin; Zabihi, H.

2014-06-01

Mapping is essential for the analysis of the land use and land cover, which influence many environmental processes and properties. For the purpose of the creation of land cover maps, it is important to minimize error. These errors will propagate into later analyses based on these land cover maps. The reliability of land cover maps derived from remotely sensed data depends on an accurate classification. In this study, we have analyzed multispectral data using two different classifiers including Maximum Likelihood Classifier (MLC) and Support Vector Machine (SVM). To pursue this aim, Landsat Thematic Mapper data and identical field-based training sample datasets in Johor Malaysia used for each classification method, which results indicate in five land cover classes forest, oil palm, urban area, water, rubber. Classification results indicate that SVM was more accurate than MLC. With demonstrated capability to produce reliable cover results, the SVM methods should be especially useful for land cover classification.

Automatic white blood cell classification using pre-trained deep learning models: ResNet and Inception

NASA Astrophysics Data System (ADS)

Habibzadeh, Mehdi; Jannesari, Mahboobeh; Rezaei, Zahra; Baharvand, Hossein; Totonchi, Mehdi

2018-04-01

This works gives an account of evaluation of white blood cell differential counts via computer aided diagnosis (CAD) system and hematology rules. Leukocytes, also called white blood cells (WBCs) play main role of the immune system. Leukocyte is responsible for phagocytosis and immunity and therefore in defense against infection involving the fatal diseases incidence and mortality related issues. Admittedly, microscopic examination of blood samples is a time consuming, expensive and error-prone task. A manual diagnosis would search for specific Leukocytes and number abnormalities in the blood slides while complete blood count (CBC) examination is performed. Complications may arise from the large number of varying samples including different types of Leukocytes, related sub-types and concentration in blood, which makes the analysis prone to human error. This process can be automated by computerized techniques which are more reliable and economical. In essence, we seek to determine a fast, accurate mechanism for classification and gather information about distribution of white blood evidences which may help to diagnose the degree of any abnormalities during CBC test. In this work, we consider the problem of pre-processing and supervised classification of white blood cells into their four primary types including Neutrophils, Eosinophils, Lymphocytes, and Monocytes using a consecutive proposed deep learning framework. For first step, this research proposes three consecutive pre-processing calculations namely are color distortion; bounding box distortion (crop) and image flipping mirroring. In second phase, white blood cell recognition performed with hierarchy topological feature extraction using Inception and ResNet architectures. Finally, the results obtained from the preliminary analysis of cell classification with (11200) training samples and 1244 white blood cells evaluation data set are presented in confusion matrices and interpreted using accuracy rate, and false positive with the classification framework being validated with experiments conducted on poor quality blood images sized 320 × 240 pixels. The deferential outcomes in the challenging cell detection task, as shown in result section, indicate that there is a significant achievement in using Inception and ResNet architecture with proposed settings. Our framework detects on average 100% of the four main white blood cell types using ResNet V1 50 while also alternative promising result with 99.84% and 99.46% accuracy rate obtained with ResNet V1 152 and ResNet 101, respectively with 3000 epochs and fine-tuning all layers. Further statistical confusion matrix tests revealed that this work achieved 1, 0.9979, 0.9989 sensitivity values when area under the curve (AUC) scores above 1, 0.9992, 0.9833 on three proposed techniques. In addition, current work shows negligible and small false negative 0, 2, 1 and substantial false positive with 0, 0, 5 values in Leukocytes detection.

User intent prediction with a scaled conjugate gradient trained artificial neural network for lower limb amputees using a powered prosthesis.

PubMed

Woodward, Richard B; Spanias, John A; Hargrove, Levi J

2016-08-01

Powered lower limb prostheses have the ability to provide greater mobility for amputee patients. Such prostheses often have pre-programmed modes which can allow activities such as climbing stairs and descending ramps, something which many amputees struggle with when using non-powered limbs. Previous literature has shown how pattern classification can allow seamless transitions between modes with a high accuracy and without any user interaction. Although accurate, training and testing each subject with their own dependent data is time consuming. By using subject independent datasets, whereby a unique subject is tested against a pooled dataset of other subjects, we believe subject training time can be reduced while still achieving an accurate classification. We present here an intent recognition system using an artificial neural network (ANN) with a scaled conjugate gradient learning algorithm to classify gait intention with user-dependent and independent datasets for six unilateral lower limb amputees. We compare these results against a linear discriminant analysis (LDA) classifier. The ANN was found to have significantly lower classification error (P<;0.05) than LDA with all user-dependent step-types, as well as transitional steps for user-independent datasets. Both types of classifiers are capable of making fast decisions; 1.29 and 2.83 ms for the LDA and ANN respectively. These results suggest that ANNs can provide suitable and accurate offline classification in prosthesis gait prediction.

Three-Class Mammogram Classification Based on Descriptive CNN Features

PubMed Central

Zhang, Qianni; Jadoon, Adeel

2017-01-01

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques. PMID:28191461

Three-Class Mammogram Classification Based on Descriptive CNN Features.

PubMed

Jadoon, M Mohsin; Zhang, Qianni; Haq, Ihsan Ul; Butt, Sharjeel; Jadoon, Adeel

2017-01-01

In this paper, a novel classification technique for large data set of mammograms using a deep learning method is proposed. The proposed model targets a three-class classification study (normal, malignant, and benign cases). In our model we have presented two methods, namely, convolutional neural network-discrete wavelet (CNN-DW) and convolutional neural network-curvelet transform (CNN-CT). An augmented data set is generated by using mammogram patches. To enhance the contrast of mammogram images, the data set is filtered by contrast limited adaptive histogram equalization (CLAHE). In the CNN-DW method, enhanced mammogram images are decomposed as its four subbands by means of two-dimensional discrete wavelet transform (2D-DWT), while in the second method discrete curvelet transform (DCT) is used. In both methods, dense scale invariant feature (DSIFT) for all subbands is extracted. Input data matrix containing these subband features of all the mammogram patches is created that is processed as input to convolutional neural network (CNN). Softmax layer and support vector machine (SVM) layer are used to train CNN for classification. Proposed methods have been compared with existing methods in terms of accuracy rate, error rate, and various validation assessment measures. CNN-DW and CNN-CT have achieved accuracy rate of 81.83% and 83.74%, respectively. Simulation results clearly validate the significance and impact of our proposed model as compared to other well-known existing techniques.

Automatic classification of background EEG activity in healthy and sick neonates

NASA Astrophysics Data System (ADS)

Löfhede, Johan; Thordstein, Magnus; Löfgren, Nils; Flisberg, Anders; Rosa-Zurera, Manuel; Kjellmer, Ingemar; Lindecrantz, Kaj

2010-02-01

The overall aim of our research is to develop methods for a monitoring system to be used at neonatal intensive care units. When monitoring a baby, a range of different types of background activity needs to be considered. In this work, we have developed a scheme for automatic classification of background EEG activity in newborn babies. EEG from six full-term babies who were displaying a burst suppression pattern while suffering from the after-effects of asphyxia during birth was included along with EEG from 20 full-term healthy newborn babies. The signals from the healthy babies were divided into four behavioural states: active awake, quiet awake, active sleep and quiet sleep. By using a number of features extracted from the EEG together with Fisher's linear discriminant classifier we have managed to achieve 100% correct classification when separating burst suppression EEG from all four healthy EEG types and 93% true positive classification when separating quiet sleep from the other types. The other three sleep stages could not be classified. When the pathological burst suppression pattern was detected, the analysis was taken one step further and the signal was segmented into burst and suppression, allowing clinically relevant parameters such as suppression length and burst suppression ratio to be calculated. The segmentation of the burst suppression EEG works well, with a probability of error around 4%.

Inter-class sparsity based discriminative least square regression.

PubMed

Wen, Jie; Xu, Yong; Li, Zuoyong; Ma, Zhongli; Xu, Yuanrong

2018-06-01

Least square regression is a very popular supervised classification method. However, two main issues greatly limit its performance. The first one is that it only focuses on fitting the input features to the corresponding output labels while ignoring the correlations among samples. The second one is that the used label matrix, i.e., zero-one label matrix is inappropriate for classification. To solve these problems and improve the performance, this paper presents a novel method, i.e., inter-class sparsity based discriminative least square regression (ICS_DLSR), for multi-class classification. Different from other methods, the proposed method pursues that the transformed samples have a common sparsity structure in each class. For this goal, an inter-class sparsity constraint is introduced to the least square regression model such that the margins of samples from the same class can be greatly reduced while those of samples from different classes can be enlarged. In addition, an error term with row-sparsity constraint is introduced to relax the strict zero-one label matrix, which allows the method to be more flexible in learning the discriminative transformation matrix. These factors encourage the method to learn a more compact and discriminative transformation for regression and thus has the potential to perform better than other methods. Extensive experimental results show that the proposed method achieves the best performance in comparison with other methods for multi-class classification. Copyright © 2018 Elsevier Ltd. All rights reserved.

On the Discriminant Analysis in the 2-Populations Case

NASA Astrophysics Data System (ADS)

Rublík, František

2008-01-01

The empirical Bayes Gaussian rule, which in the normal case yields good values of the probability of total error, may yield high values of the maximum probability error. From this point of view the presented modified version of the classification rule of Broffitt, Randles and Hogg appears to be superior. The modification included in this paper is termed as a WR method, and the choice of its weights is discussed. The mentioned methods are also compared with the K nearest neighbours classification rule.

A classification of errors in lay comprehension of medical documents.

PubMed

Keselman, Alla; Smith, Catherine Arnott

2012-12-01

Emphasis on participatory medicine requires that patients and consumers participate in tasks traditionally reserved for healthcare providers. This includes reading and comprehending medical documents, often but not necessarily in the context of interacting with Personal Health Records (PHRs). Research suggests that while giving patients access to medical documents has many benefits (e.g., improved patient-provider communication), lay people often have difficulty understanding medical information. Informatics can address the problem by developing tools that support comprehension; this requires in-depth understanding of the nature and causes of errors that lay people make when comprehending clinical documents. The objective of this study was to develop a classification scheme of comprehension errors, based on lay individuals' retellings of two documents containing clinical text: a description of a clinical trial and a typical office visit note. While not comprehensive, the scheme can serve as a foundation of further development of a taxonomy of patients' comprehension errors. Eighty participants, all healthy volunteers, read and retold two medical documents. A data-driven content analysis procedure was used to extract and classify retelling errors. The resulting hierarchical classification scheme contains nine categories and 23 subcategories. The most common error made by the participants involved incorrectly recalling brand names of medications. Other common errors included misunderstanding clinical concepts, misreporting the objective of a clinical research study and physician's findings during a patient's visit, and confusing and misspelling clinical terms. A combination of informatics support and health education is likely to improve the accuracy of lay comprehension of medical documents. Published by Elsevier Inc.

An extension of the receiver operating characteristic curve and AUC-optimal classification.

PubMed

Takenouchi, Takashi; Komori, Osamu; Eguchi, Shinto

2012-10-01

While most proposed methods for solving classification problems focus on minimization of the classification error rate, we are interested in the receiver operating characteristic (ROC) curve, which provides more information about classification performance than the error rate does. The area under the ROC curve (AUC) is a natural measure for overall assessment of a classifier based on the ROC curve. We discuss a class of concave functions for AUC maximization in which a boosting-type algorithm including RankBoost is considered, and the Bayesian risk consistency and the lower bound of the optimum function are discussed. A procedure derived by maximizing a specific optimum function has high robustness, based on gross error sensitivity. Additionally, we focus on the partial AUC, which is the partial area under the ROC curve. For example, in medical screening, a high true-positive rate to the fixed lower false-positive rate is preferable and thus the partial AUC corresponding to lower false-positive rates is much more important than the remaining AUC. We extend the class of concave optimum functions for partial AUC optimality with the boosting algorithm. We investigated the validity of the proposed method through several experiments with data sets in the UCI repository.

Classification of melanoma lesions using sparse coded features and random forests

NASA Astrophysics Data System (ADS)

Rastgoo, Mojdeh; Lemaître, Guillaume; Morel, Olivier; Massich, Joan; Garcia, Rafael; Meriaudeau, Fabrice; Marzani, Franck; Sidibé, Désiré

2016-03-01

Malignant melanoma is the most dangerous type of skin cancer, yet it is the most treatable kind of cancer, conditioned by its early diagnosis which is a challenging task for clinicians and dermatologists. In this regard, CAD systems based on machine learning and image processing techniques are developed to differentiate melanoma lesions from benign and dysplastic nevi using dermoscopic images. Generally, these frameworks are composed of sequential processes: pre-processing, segmentation, and classification. This architecture faces mainly two challenges: (i) each process is complex with the need to tune a set of parameters, and is specific to a given dataset; (ii) the performance of each process depends on the previous one, and the errors are accumulated throughout the framework. In this paper, we propose a framework for melanoma classification based on sparse coding which does not rely on any pre-processing or lesion segmentation. Our framework uses Random Forests classifier and sparse representation of three features: SIFT, Hue and Opponent angle histograms, and RGB intensities. The experiments are carried out on the public PH2 dataset using a 10-fold cross-validation. The results show that SIFT sparse-coded feature achieves the highest performance with sensitivity and specificity of 100% and 90.3% respectively, with a dictionary size of 800 atoms and a sparsity level of 2. Furthermore, the descriptor based on RGB intensities achieves similar results with sensitivity and specificity of 100% and 71.3%, respectively for a smaller dictionary size of 100 atoms. In conclusion, dictionary learning techniques encode strong structures of dermoscopic images and provide discriminant descriptors.

Review of medication errors that are new or likely to occur more frequently with electronic medication management systems.

PubMed

Van de Vreede, Melita; McGrath, Anne; de Clifford, Jan

2018-05-14

Objective. The aim of the present study was to identify and quantify medication errors reportedly related to electronic medication management systems (eMMS) and those considered likely to occur more frequently with eMMS. This included developing a new classification system relevant to eMMS errors. Methods. Eight Victorian hospitals with eMMS participated in a retrospective audit of reported medication incidents from their incident reporting databases between May and July 2014. Site-appointed project officers submitted deidentified incidents they deemed new or likely to occur more frequently due to eMMS, together with the Incident Severity Rating (ISR). The authors reviewed and classified incidents. Results. There were 5826 medication-related incidents reported. In total, 93 (47 prescribing errors, 46 administration errors) were identified as new or potentially related to eMMS. Only one ISR2 (moderate) and no ISR1 (severe or death) errors were reported, so harm to patients in this 3-month period was minimal. The most commonly reported error types were 'human factors' and 'unfamiliarity or training' (70%) and 'cross-encounter or hybrid system errors' (22%). Conclusions. Although the results suggest that the errors reported were of low severity, organisations must remain vigilant to the risk of new errors and avoid the assumption that eMMS is the panacea to all medication error issues. What is known about the topic? eMMS have been shown to reduce some types of medication errors, but it has been reported that some new medication errors have been identified and some are likely to occur more frequently with eMMS. There are few published Australian studies that have reported on medication error types that are likely to occur more frequently with eMMS in more than one organisation and that include administration and prescribing errors. What does this paper add? This paper includes a new simple classification system for eMMS that is useful and outlines the most commonly reported incident types and can inform organisations and vendors on possible eMMS improvements. The paper suggests a new classification system for eMMS medication errors. What are the implications for practitioners? The results of the present study will highlight to organisations the need for ongoing review of system design, refinement of workflow issues, staff education and training and reporting and monitoring of errors.

Evaluation of spatial filtering on the accuracy of wheat area estimate

NASA Technical Reports Server (NTRS)

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

1982-01-01

A 3 x 3 pixel spatial filter for postclassification was used for wheat classification to evaluate the effects of this procedure on the accuracy of area estimation using LANDSAT digital data obtained from a single pass. Quantitative analyses were carried out in five test sites (approx 40 sq km each) and t tests showed that filtering with threshold values significantly decreased errors of commission and omission. In area estimation filtering improved the overestimate of 4.5% to 2.7% and the root-mean-square error decreased from 126.18 ha to 107.02 ha. Extrapolating the same procedure of automatic classification using spatial filtering for postclassification to the whole study area, the accuracy in area estimate was improved from the overestimate of 10.9% to 9.7%. It is concluded that when single pass LANDSAT data is used for crop identification and area estimation the postclassification procedure using a spatial filter provides a more accurate area estimate by reducing classification errors.

Maximum likelihood estimation of label imperfections and its use in the identification of mislabeled patterns

NASA Technical Reports Server (NTRS)

Chittineni, C. B.

1979-01-01

The problem of estimating label imperfections and the use of the estimation in identifying mislabeled patterns is presented. Expressions for the maximum likelihood estimates of classification errors and a priori probabilities are derived from the classification of a set of labeled patterns. Expressions also are given for the asymptotic variances of probability of correct classification and proportions. Simple models are developed for imperfections in the labels and for classification errors and are used in the formulation of a maximum likelihood estimation scheme. Schemes are presented for the identification of mislabeled patterns in terms of threshold on the discriminant functions for both two-class and multiclass cases. Expressions are derived for the probability that the imperfect label identification scheme will result in a wrong decision and are used in computing thresholds. The results of practical applications of these techniques in the processing of remotely sensed multispectral data are presented.

Semiautomated object-based classification of rain-induced landslides with VHR multispectral images on Madeira Island

NASA Astrophysics Data System (ADS)

Heleno, Sandra; Matias, Magda; Pina, Pedro; Sousa, António Jorge

2016-04-01

A method for semiautomated landslide detection and mapping, with the ability to separate source and run-out areas, is presented in this paper. It combines object-based image analysis and a support vector machine classifier and is tested using a GeoEye-1 multispectral image, sensed 3 days after a major damaging landslide event that occurred on Madeira Island (20 February 2010), and a pre-event lidar digital terrain model. The testing is developed in a 15 km2 wide study area, where 95 % of the number of landslides scars are detected by this supervised approach. The classifier presents a good performance in the delineation of the overall landslide area, with commission errors below 26 % and omission errors below 24 %. In addition, fair results are achieved in the separation of the source from the run-out landslide areas, although in less illuminated slopes this discrimination is less effective than in sunnier, east-facing slopes.

Unsupervised classification of operator workload from brain signals.

PubMed

Schultze-Kraft, Matthias; Dähne, Sven; Gugler, Manfred; Curio, Gabriel; Blankertz, Benjamin

2016-06-01

In this study we aimed for the classification of operator workload as it is expected in many real-life workplace environments. We explored brain-signal based workload predictors that differ with respect to the level of label information required for training, including entirely unsupervised approaches. Subjects executed a task on a touch screen that required continuous effort of visual and motor processing with alternating difficulty. We first employed classical approaches for workload state classification that operate on the sensor space of EEG and compared those to the performance of three state-of-the-art spatial filtering methods: common spatial patterns (CSPs) analysis, which requires binary label information; source power co-modulation (SPoC) analysis, which uses the subjects' error rate as a target function; and canonical SPoC (cSPoC) analysis, which solely makes use of cross-frequency power correlations induced by different states of workload and thus represents an unsupervised approach. Finally, we investigated the effects of fusing brain signals and peripheral physiological measures (PPMs) and examined the added value for improving classification performance. Mean classification accuracies of 94%, 92% and 82% were achieved with CSP, SPoC, cSPoC, respectively. These methods outperformed the approaches that did not use spatial filtering and they extracted physiologically plausible components. The performance of the unsupervised cSPoC is significantly increased by augmenting it with PPM features. Our analyses ensured that the signal sources used for classification were of cortical origin and not contaminated with artifacts. Our findings show that workload states can be successfully differentiated from brain signals, even when less and less information from the experimental paradigm is used, thus paving the way for real-world applications in which label information may be noisy or entirely unavailable.

Unsupervised classification of operator workload from brain signals

NASA Astrophysics Data System (ADS)

Schultze-Kraft, Matthias; Dähne, Sven; Gugler, Manfred; Curio, Gabriel; Blankertz, Benjamin

2016-06-01

Objective. In this study we aimed for the classification of operator workload as it is expected in many real-life workplace environments. We explored brain-signal based workload predictors that differ with respect to the level of label information required for training, including entirely unsupervised approaches. Approach. Subjects executed a task on a touch screen that required continuous effort of visual and motor processing with alternating difficulty. We first employed classical approaches for workload state classification that operate on the sensor space of EEG and compared those to the performance of three state-of-the-art spatial filtering methods: common spatial patterns (CSPs) analysis, which requires binary label information; source power co-modulation (SPoC) analysis, which uses the subjects’ error rate as a target function; and canonical SPoC (cSPoC) analysis, which solely makes use of cross-frequency power correlations induced by different states of workload and thus represents an unsupervised approach. Finally, we investigated the effects of fusing brain signals and peripheral physiological measures (PPMs) and examined the added value for improving classification performance. Main results. Mean classification accuracies of 94%, 92% and 82% were achieved with CSP, SPoC, cSPoC, respectively. These methods outperformed the approaches that did not use spatial filtering and they extracted physiologically plausible components. The performance of the unsupervised cSPoC is significantly increased by augmenting it with PPM features. Significance. Our analyses ensured that the signal sources used for classification were of cortical origin and not contaminated with artifacts. Our findings show that workload states can be successfully differentiated from brain signals, even when less and less information from the experimental paradigm is used, thus paving the way for real-world applications in which label information may be noisy or entirely unavailable.

Misclassification Errors in Unsupervised Classification Methods. Comparison Based on the Simulation of Targeted Proteomics Data

PubMed Central

Andreev, Victor P; Gillespie, Brenda W; Helfand, Brian T; Merion, Robert M

2016-01-01

Unsupervised classification methods are gaining acceptance in omics studies of complex common diseases, which are often vaguely defined and are likely the collections of disease subtypes. Unsupervised classification based on the molecular signatures identified in omics studies have the potential to reflect molecular mechanisms of the subtypes of the disease and to lead to more targeted and successful interventions for the identified subtypes. Multiple classification algorithms exist but none is ideal for all types of data. Importantly, there are no established methods to estimate sample size in unsupervised classification (unlike power analysis in hypothesis testing). Therefore, we developed a simulation approach allowing comparison of misclassification errors and estimating the required sample size for a given effect size, number, and correlation matrix of the differentially abundant proteins in targeted proteomics studies. All the experiments were performed in silico. The simulated data imitated the expected one from the study of the plasma of patients with lower urinary tract dysfunction with the aptamer proteomics assay Somascan (SomaLogic Inc, Boulder, CO), which targeted 1129 proteins, including 330 involved in inflammation, 180 in stress response, 80 in aging, etc. Three popular clustering methods (hierarchical, k-means, and k-medoids) were compared. K-means clustering performed much better for the simulated data than the other two methods and enabled classification with misclassification error below 5% in the simulated cohort of 100 patients based on the molecular signatures of 40 differentially abundant proteins (effect size 1.5) from among the 1129-protein panel. PMID:27524871

Computer discrimination procedures applicable to aerial and ERTS multispectral data

NASA Technical Reports Server (NTRS)

Richardson, A. J.; Torline, R. J.; Allen, W. A.

1970-01-01

Two statistical models are compared in the classification of crops recorded on color aerial photographs. A theory of error ellipses is applied to the pattern recognition problem. An elliptical boundary condition classification model (EBC), useful for recognition of candidate patterns, evolves out of error ellipse theory. The EBC model is compared with the minimum distance to the mean (MDM) classification model in terms of pattern recognition ability. The pattern recognition results of both models are interpreted graphically using scatter diagrams to represent measurement space. Measurement space, for this report, is determined by optical density measurements collected from Kodak Ektachrome Infrared Aero Film 8443 (EIR). The EBC model is shown to be a significant improvement over the MDM model.

Statistical learning from nonrecurrent experience with discrete input variables and recursive-error-minimization equations

NASA Astrophysics Data System (ADS)

Carter, Jeffrey R.; Simon, Wayne E.

1990-08-01

Neural networks are trained using Recursive Error Minimization (REM) equations to perform statistical classification. Using REM equations with continuous input variables reduces the required number of training experiences by factors of one to two orders of magnitude over standard back propagation. Replacing the continuous input variables with discrete binary representations reduces the number of connections by a factor proportional to the number of variables reducing the required number of experiences by another order of magnitude. Undesirable effects of using recurrent experience to train neural networks for statistical classification problems are demonstrated and nonrecurrent experience used to avoid these undesirable effects. 1. THE 1-41 PROBLEM The statistical classification problem which we address is is that of assigning points in ddimensional space to one of two classes. The first class has a covariance matrix of I (the identity matrix) the covariance matrix of the second class is 41. For this reason the problem is known as the 1-41 problem. Both classes have equal probability of occurrence and samples from both classes may appear anywhere throughout the ddimensional space. Most samples near the origin of the coordinate system will be from the first class while most samples away from the origin will be from the second class. Since the two classes completely overlap it is impossible to have a classifier with zero error. The minimum possible error is known as the Bayes error and

Calibration of remotely sensed proportion or area estimates for misclassification error

Treesearch

Raymond L. Czaplewski; Glenn P. Catts

1992-01-01

Classifications of remotely sensed data contain misclassification errors that bias areal estimates. Monte Carlo techniques were used to compare two statistical methods that correct or calibrate remotely sensed areal estimates for misclassification bias using reference data from an error matrix. The inverse calibration estimator was consistently superior to the...

Mapping gully-affected areas in the region of Taroudannt, Morocco based on Object-Based Image Analysis (OBIA)

NASA Astrophysics Data System (ADS)

d'Oleire-Oltmanns, Sebastian; Marzolff, Irene; Tiede, Dirk; Blaschke, Thomas

2015-04-01

The need for area-wide landform mapping approaches, especially in terms of land degradation, can be ascribed to the fact that within area-wide landform mapping approaches, the (spatial) context of erosional landforms is considered by providing additional information on the physiography neighboring the distinct landform. This study presents an approach for the detection of gully-affected areas by applying object-based image analysis in the region of Taroudannt, Morocco, which is highly affected by gully erosion while simultaneously representing a major region of agro-industry with a high demand of arable land. Various sensors provide readily available high-resolution optical satellite data with a much better temporal resolution than 3D terrain data which lead to the development of an area-wide mapping approach to extract gully-affected areas using only optical satellite imagery. The classification rule-set was developed with a clear focus on virtual spatial independence within the software environment of eCognition Developer. This allows the incorporation of knowledge about the target objects under investigation. Only optical QuickBird-2 satellite data and freely-available OpenStreetMap (OSM) vector data were used as input data. The OSM vector data were incorporated in order to mask out plantations and residential areas. Optical input data are more readily available for a broad range of users compared to terrain data, which is considered to be a major advantage. The methodology additionally incorporates expert knowledge and freely-available vector data in a cyclic object-based image analysis approach. This connects the two fields of geomorphology and remote sensing. The classification results allow conclusions on the current distribution of gullies. The results of the classification were checked against manually delineated reference data incorporating expert knowledge based on several field campaigns in the area, resulting in an overall classification accuracy of 62%. The error of omission accounts for 38% and the error of commission for 16%, respectively. Additionally, a manual assessment was carried out to assess the quality of the applied classification algorithm. The limited error of omission contributes with 23% to the overall error of omission and the limited error of commission contributes with 98% to the overall error of commission. This assessment improves the results and confirms the high quality of the developed approach for area-wide mapping of gully-affected areas in larger regions. In the field of landform mapping, the overall quality of the classification results is often assessed with more than one method to incorporate all aspects adequately.

Constructing the L2-Graph for Robust Subspace Learning and Subspace Clustering.

PubMed

Peng, Xi; Yu, Zhiding; Yi, Zhang; Tang, Huajin

2017-04-01

Under the framework of graph-based learning, the key to robust subspace clustering and subspace learning is to obtain a good similarity graph that eliminates the effects of errors and retains only connections between the data points from the same subspace (i.e., intrasubspace data points). Recent works achieve good performance by modeling errors into their objective functions to remove the errors from the inputs. However, these approaches face the limitations that the structure of errors should be known prior and a complex convex problem must be solved. In this paper, we present a novel method to eliminate the effects of the errors from the projection space (representation) rather than from the input space. We first prove that l 1 -, l 2 -, l ∞ -, and nuclear-norm-based linear projection spaces share the property of intrasubspace projection dominance, i.e., the coefficients over intrasubspace data points are larger than those over intersubspace data points. Based on this property, we introduce a method to construct a sparse similarity graph, called L2-graph. The subspace clustering and subspace learning algorithms are developed upon L2-graph. We conduct comprehensive experiment on subspace learning, image clustering, and motion segmentation and consider several quantitative benchmarks classification/clustering accuracy, normalized mutual information, and running time. Results show that L2-graph outperforms many state-of-the-art methods in our experiments, including L1-graph, low rank representation (LRR), and latent LRR, least square regression, sparse subspace clustering, and locally linear representation.

Data mining: Potential applications in research on nutrition and health.

PubMed

Batterham, Marijka; Neale, Elizabeth; Martin, Allison; Tapsell, Linda

2017-02-01

Data mining enables further insights from nutrition-related research, but caution is required. The aim of this analysis was to demonstrate and compare the utility of data mining methods in classifying a categorical outcome derived from a nutrition-related intervention. Baseline data (23 variables, 8 categorical) on participants (n = 295) in an intervention trial were used to classify participants in terms of meeting the criteria of achieving 10 000 steps per day. Results from classification and regression trees (CARTs), random forests, adaptive boosting, logistic regression, support vector machines and neural networks were compared using area under the curve (AUC) and error assessments. The CART produced the best model when considering the AUC (0.703), overall error (18%) and within class error (28%). Logistic regression also performed reasonably well compared to the other models (AUC 0.675, overall error 23%, within class error 36%). All the methods gave different rankings of variables' importance. CART found that body fat, quality of life using the SF-12 Physical Component Summary (PCS) and the cholesterol: HDL ratio were the most important predictors of meeting the 10 000 steps criteria, while logistic regression showed the SF-12PCS, glucose levels and level of education to be the most significant predictors (P ≤ 0.01). Differing outcomes suggest caution is required with a single data mining method, particularly in a dataset with nonlinear relationships and outliers and when exploring relationships that were not the primary outcomes of the research. © 2017 Dietitians Association of Australia.

Maximum-likelihood techniques for joint segmentation-classification of multispectral chromosome images.

PubMed

Schwartzkopf, Wade C; Bovik, Alan C; Evans, Brian L

2005-12-01

Traditional chromosome imaging has been limited to grayscale images, but recently a 5-fluorophore combinatorial labeling technique (M-FISH) was developed wherein each class of chromosomes binds with a different combination of fluorophores. This results in a multispectral image, where each class of chromosomes has distinct spectral components. In this paper, we develop new methods for automatic chromosome identification by exploiting the multispectral information in M-FISH chromosome images and by jointly performing chromosome segmentation and classification. We (1) develop a maximum-likelihood hypothesis test that uses multispectral information, together with conventional criteria, to select the best segmentation possibility; (2) use this likelihood function to combine chromosome segmentation and classification into a robust chromosome identification system; and (3) show that the proposed likelihood function can also be used as a reliable indicator of errors in segmentation, errors in classification, and chromosome anomalies, which can be indicators of radiation damage, cancer, and a wide variety of inherited diseases. We show that the proposed multispectral joint segmentation-classification method outperforms past grayscale segmentation methods when decomposing touching chromosomes. We also show that it outperforms past M-FISH classification techniques that do not use segmentation information.

Classification accuracy on the family planning participation status using kernel discriminant analysis

NASA Astrophysics Data System (ADS)

Kurniawan, Dian; Suparti; Sugito

2018-05-01

Population growth in Indonesia has increased every year. According to the population census conducted by the Central Bureau of Statistics (BPS) in 2010, the population of Indonesia has reached 237.6 million people. Therefore, to control the population growth rate, the government hold Family Planning or Keluarga Berencana (KB) program for couples of childbearing age. The purpose of this program is to improve the health of mothers and children in order to manifest prosperous society by controlling births while ensuring control of population growth. The data used in this study is the updated family data of Semarang city in 2016 that conducted by National Family Planning Coordinating Board (BKKBN). From these data, classifiers with kernel discriminant analysis will be obtained, and also classification accuracy will be obtained from that method. The result of the analysis showed that normal kernel discriminant analysis gives 71.05 % classification accuracy with 28.95 % classification error. Whereas triweight kernel discriminant analysis gives 73.68 % classification accuracy with 26.32 % classification error. Using triweight kernel discriminant for data preprocessing of family planning participation of childbearing age couples in Semarang City of 2016 can be stated better than with normal kernel discriminant.

A parametric multiclass Bayes error estimator for the multispectral scanner spatial model performance evaluation

NASA Technical Reports Server (NTRS)

Mobasseri, B. G.; Mcgillem, C. D.; Anuta, P. E. (Principal Investigator)

1978-01-01

The author has identified the following significant results. The probability of correct classification of various populations in data was defined as the primary performance index. The multispectral data being of multiclass nature as well, required a Bayes error estimation procedure that was dependent on a set of class statistics alone. The classification error was expressed in terms of an N dimensional integral, where N was the dimensionality of the feature space. The multispectral scanner spatial model was represented by a linear shift, invariant multiple, port system where the N spectral bands comprised the input processes. The scanner characteristic function, the relationship governing the transformation of the input spatial, and hence, spectral correlation matrices through the systems, was developed.

Iterative random vs. Kennard-Stone sampling for IR spectrum-based classification task using PLS2-DA

NASA Astrophysics Data System (ADS)

Lee, Loong Chuen; Liong, Choong-Yeun; Jemain, Abdul Aziz

2018-04-01

External testing (ET) is preferred over auto-prediction (AP) or k-fold-cross-validation in estimating more realistic predictive ability of a statistical model. With IR spectra, Kennard-stone (KS) sampling algorithm is often used to split the data into training and test sets, i.e. respectively for model construction and for model testing. On the other hand, iterative random sampling (IRS) has not been the favored choice though it is theoretically more likely to produce reliable estimation. The aim of this preliminary work is to compare performances of KS and IRS in sampling a representative training set from an attenuated total reflectance - Fourier transform infrared spectral dataset (of four varieties of blue gel pen inks) for PLS2-DA modeling. The `best' performance achievable from the dataset is estimated with AP on the full dataset (APF, error). Both IRS (n = 200) and KS were used to split the dataset in the ratio of 7:3. The classic decision rule (i.e. maximum value-based) is employed for new sample prediction via partial least squares - discriminant analysis (PLS2-DA). Error rate of each model was estimated repeatedly via: (a) AP on full data (APF, error); (b) AP on training set (APS, error); and (c) ET on the respective test set (ETS, error). A good PLS2-DA model is expected to produce APS, error and EVS, error that is similar to the APF, error. Bearing that in mind, the similarities between (a) APS, error vs. APF, error; (b) ETS, error vs. APF, error and; (c) APS, error vs. ETS, error were evaluated using correlation tests (i.e. Pearson and Spearman's rank test), using series of PLS2-DA models computed from KS-set and IRS-set, respectively. Overall, models constructed from IRS-set exhibits more similarities between the internal and external error rates than the respective KS-set, i.e. less risk of overfitting. In conclusion, IRS is more reliable than KS in sampling representative training set.

A dictionary learning approach for human sperm heads classification.

PubMed

Shaker, Fariba; Monadjemi, S Amirhassan; Alirezaie, Javad; Naghsh-Nilchi, Ahmad Reza

2017-12-01

To diagnose infertility in men, semen analysis is conducted in which sperm morphology is one of the factors that are evaluated. Since manual assessment of sperm morphology is time-consuming and subjective, automatic classification methods are being developed. Automatic classification of sperm heads is a complicated task due to the intra-class differences and inter-class similarities of class objects. In this research, a Dictionary Learning (DL) technique is utilized to construct a dictionary of sperm head shapes. This dictionary is used to classify the sperm heads into four different classes. Square patches are extracted from the sperm head images. Columnized patches from each class of sperm are used to learn class-specific dictionaries. The patches from a test image are reconstructed using each class-specific dictionary and the overall reconstruction error for each class is used to select the best matching class. Average accuracy, precision, recall, and F-score are used to evaluate the classification method. The method is evaluated using two publicly available datasets of human sperm head shapes. The proposed DL based method achieved an average accuracy of 92.2% on the HuSHeM dataset, and an average recall of 62% on the SCIAN-MorphoSpermGS dataset. The results show a significant improvement compared to a previously published shape-feature-based method. We have achieved high-performance results. In addition, our proposed approach offers a more balanced classifier in which all four classes are recognized with high precision and recall. In this paper, we use a Dictionary Learning approach in classifying human sperm heads. It is shown that the Dictionary Learning method is far more effective in classifying human sperm heads than classifiers using shape-based features. Also, a dataset of human sperm head shapes is introduced to facilitate future research. Copyright © 2017 Elsevier Ltd. All rights reserved.

Unbiased Taxonomic Annotation of Metagenomic Samples

PubMed Central

Fosso, Bruno; Pesole, Graziano; Rosselló, Francesc

2018-01-01

Abstract The classification of reads from a metagenomic sample using a reference taxonomy is usually based on first mapping the reads to the reference sequences and then classifying each read at a node under the lowest common ancestor of the candidate sequences in the reference taxonomy with the least classification error. However, this taxonomic annotation can be biased by an imbalanced taxonomy and also by the presence of multiple nodes in the taxonomy with the least classification error for a given read. In this article, we show that the Rand index is a better indicator of classification error than the often used area under the receiver operating characteristic (ROC) curve and F-measure for both balanced and imbalanced reference taxonomies, and we also address the second source of bias by reducing the taxonomic annotation problem for a whole metagenomic sample to a set cover problem, for which a logarithmic approximation can be obtained in linear time and an exact solution can be obtained by integer linear programming. Experimental results with a proof-of-concept implementation of the set cover approach to taxonomic annotation in a next release of the TANGO software show that the set cover approach further reduces ambiguity in the taxonomic annotation obtained with TANGO without distorting the relative abundance profile of the metagenomic sample. PMID:29028181

Global land cover mapping: a review and uncertainty analysis

USGS Publications Warehouse

Congalton, Russell G.; Gu, Jianyu; Yadav, Kamini; Thenkabail, Prasad S.; Ozdogan, Mutlu

2014-01-01

Given the advances in remotely sensed imagery and associated technologies, several global land cover maps have been produced in recent times including IGBP DISCover, UMD Land Cover, Global Land Cover 2000 and GlobCover 2009. However, the utility of these maps for specific applications has often been hampered due to considerable amounts of uncertainties and inconsistencies. A thorough review of these global land cover projects including evaluating the sources of error and uncertainty is prudent and enlightening. Therefore, this paper describes our work in which we compared, summarized and conducted an uncertainty analysis of the four global land cover mapping projects using an error budget approach. The results showed that the classification scheme and the validation methodology had the highest error contribution and implementation priority. A comparison of the classification schemes showed that there are many inconsistencies between the definitions of the map classes. This is especially true for the mixed type classes for which thresholds vary for the attributes/discriminators used in the classification process. Examination of these four global mapping projects provided quite a few important lessons for the future global mapping projects including the need for clear and uniform definitions of the classification scheme and an efficient, practical, and valid design of the accuracy assessment.

Defining and classifying medical error: lessons for patient safety reporting systems.

PubMed

Tamuz, M; Thomas, E J; Franchois, K E

2004-02-01

It is important for healthcare providers to report safety related events, but little attention has been paid to how the definition and classification of events affects a hospital's ability to learn from its experience. To examine how the definition and classification of safety related events influences key organizational routines for gathering information, allocating incentives, and analyzing event reporting data. In semi-structured interviews, professional staff and administrators in a tertiary care teaching hospital and its pharmacy were asked to describe the existing programs designed to monitor medication safety, including the reporting systems. With a focus primarily on the pharmacy staff, interviews were audio recorded, transcribed, and analyzed using qualitative research methods. Eighty six interviews were conducted, including 36 in the hospital pharmacy. Examples are presented which show that: (1) the definition of an event could lead to under-reporting; (2) the classification of a medication error into alternative categories can influence the perceived incentives and disincentives for incident reporting; (3) event classification can enhance or impede organizational routines for data analysis and learning; and (4) routines that promote organizational learning within the pharmacy can reduce the flow of medication error data to the hospital. These findings from one hospital raise important practical and research questions about how reporting systems are influenced by the definition and classification of safety related events. By understanding more clearly how hospitals define and classify their experience, we may improve our capacity to learn and ultimately improve patient safety.

Semi-automatic classification of glaciovolcanic landforms: An object-based mapping approach based on geomorphometry

NASA Astrophysics Data System (ADS)

Pedersen, G. B. M.

2016-02-01

A new object-oriented approach is developed to classify glaciovolcanic landforms (Procedure A) and their landform elements boundaries (Procedure B). It utilizes the principle that glaciovolcanic edifices are geomorphometrically distinct from lava shields and plains (Pedersen and Grosse, 2014), and the approach is tested on data from Reykjanes Peninsula, Iceland. The outlined procedures utilize slope and profile curvature attribute maps (20 m/pixel) and the classified results are evaluated quantitatively through error matrix maps (Procedure A) and visual inspection (Procedure B). In procedure A, the highest obtained accuracy is 94.1%, but even simple mapping procedures provide good results (> 90% accuracy). Successful classification of glaciovolcanic landform element boundaries (Procedure B) is also achieved and this technique has the potential to delineate the transition from intraglacial to subaerial volcanic activity in orthographic view. This object-oriented approach based on geomorphometry overcomes issues with vegetation cover, which has been typically problematic for classification schemes utilizing spectral data. Furthermore, it handles complex edifice outlines well and is easily incorporated into a GIS environment, where results can be edited or fused with other mapping results. The approach outlined here is designed to map glaciovolcanic edifices within the Icelandic neovolcanic zone but may also be applied to similar subaerial or submarine volcanic settings, where steep volcanic edifices are surrounded by flat plains.

Fuzziness-based active learning framework to enhance hyperspectral image classification performance for discriminative and generative classifiers

PubMed Central

2018-01-01

Hyperspectral image classification with a limited number of training samples without loss of accuracy is desirable, as collecting such data is often expensive and time-consuming. However, classifiers trained with limited samples usually end up with a large generalization error. To overcome the said problem, we propose a fuzziness-based active learning framework (FALF), in which we implement the idea of selecting optimal training samples to enhance generalization performance for two different kinds of classifiers, discriminative and generative (e.g. SVM and KNN). The optimal samples are selected by first estimating the boundary of each class and then calculating the fuzziness-based distance between each sample and the estimated class boundaries. Those samples that are at smaller distances from the boundaries and have higher fuzziness are chosen as target candidates for the training set. Through detailed experimentation on three publically available datasets, we showed that when trained with the proposed sample selection framework, both classifiers achieved higher classification accuracy and lower processing time with the small amount of training data as opposed to the case where the training samples were selected randomly. Our experiments demonstrate the effectiveness of our proposed method, which equates favorably with the state-of-the-art methods. PMID:29304512

Fisher classifier and its probability of error estimation

NASA Technical Reports Server (NTRS)

Chittineni, C. B.

1979-01-01

Computationally efficient expressions are derived for estimating the probability of error using the leave-one-out method. The optimal threshold for the classification of patterns projected onto Fisher's direction is derived. A simple generalization of the Fisher classifier to multiple classes is presented. Computational expressions are developed for estimating the probability of error of the multiclass Fisher classifier.

Human factors analysis and classification system-HFACS.

DOT National Transportation Integrated Search

2000-02-01

Human error has been implicated in 70 to 80% of all civil and military aviation accidents. Yet, most accident : reporting systems are not designed around any theoretical framework of human error. As a result, most : accident databases are not conduci...

Robust colour calibration of an imaging system using a colour space transform and advanced regression modelling.

PubMed

Jackman, Patrick; Sun, Da-Wen; Elmasry, Gamal

2012-08-01

A new algorithm for the conversion of device dependent RGB colour data into device independent L*a*b* colour data without introducing noticeable error has been developed. By combining a linear colour space transform and advanced multiple regression methodologies it was possible to predict L*a*b* colour data with less than 2.2 colour units of error (CIE 1976). By transforming the red, green and blue colour components into new variables that better reflect the structure of the L*a*b* colour space, a low colour calibration error was immediately achieved (ΔE(CAL) = 14.1). Application of a range of regression models on the data further reduced the colour calibration error substantially (multilinear regression ΔE(CAL) = 5.4; response surface ΔE(CAL) = 2.9; PLSR ΔE(CAL) = 2.6; LASSO regression ΔE(CAL) = 2.1). Only the PLSR models deteriorated substantially under cross validation. The algorithm is adaptable and can be easily recalibrated to any working computer vision system. The algorithm was tested on a typical working laboratory computer vision system and delivered only a very marginal loss of colour information ΔE(CAL) = 2.35. Colour features derived on this system were able to safely discriminate between three classes of ham with 100% correct classification whereas colour features measured on a conventional colourimeter were not. Copyright © 2012 Elsevier Ltd. All rights reserved.

IMPACTS OF PATCH SIZE AND LANDSCAPE HETEROGENEITY ON THEMATIC IMAGE CLASSIFICATION ACCURACY

EPA Science Inventory

Impacts of Patch Size and Landscape Heterogeneity on Thematic Image Classification Accuracy.
Currently, most thematic accuracy assessments of classified remotely sensed images oily account for errors between the various classes employed, at particular pixels of interest, thu...

Utilization of aerial laser scanning data in investigations of modern fortifications complexes in Poland. (Polish Title: Wykorzystanie danych lotniczego skaningu laserowego w metodyce badawczej zespołów fortyfikacji nowszej w Polsce)

NASA Astrophysics Data System (ADS)

Zawieska, D.; Ostrowski, W.; Antoszewski, M.

2013-12-01

Due to the turbulent history extremely reach and unique resources of military architectural objects (modern fortification complexes) are located in Poland. The paper presents results of analysis of utilization of aerial laser scanning data for identification and visualization of forts in Poland. A cloud of point from the ISOK Projects has been utilized for that purpose. Two types of areas are distinguished in this Project, covered by products of diversified standards: standards II - laser scanning of the increased density (12 points per sq.m.), standard I - laser scanning of the basic density (4 points per sq.m.). Investigations were carried out concerning the quality of geospatial data classification with respect to further topographic analysis of fortifications. These investigations were performed for four test sites, two test sites for each standard. Objects were selected in such a way that fortifications were characterized by the sufficient level of restoration and that at least one point located in forest and one point located in an open area could be located for each standard. The preliminary verification of the classification correctness was performed with the use of ArcGIS 10.1 software package, basing on the shaded Digital Elevation Model (DEM) and the Digital Fortification Model (DFM), an orthophotomap and the analysis of sections of the spatial cloud of points. Changes of classification of point clouds were introduced with the use of TerraSolid software package. Basing on the performed analysis two groups of errors of point cloud classification were detected. In the first group fragments of fortification facilities were classified with errors; in the case of the second group - entire elements of fortifications were classified with errors or they remained unclassified. The first type error, which occurs in the majority of cases, results in errors of 2x4 meters in object locations and variations of elevations of those fragments of DFM, which achieve up to 14 m. At present, fortifications are partially or entirely covered with forests or invasive vegetation. Therefore, the influence of the land cover and the terrain slope on the DEM quality, obtained from Lidar data, should be considered in evaluation of the ISOK data potential for topographic investigations of fortifications. Investigations performed in the world proved that if the area is covered by dense, 70 year old forests, where forest clearance is not performed, this may result in double decrease of the created DTM. (comparing to the open area). In the summary it may be stressed that performed experimental works proved the high usefulness of ISOK laser scanning data for identification of forms of fortifications and for their visualization. As opposed to conventional information acquisition methods (field inventory together with historical documents), laser scanning data is the new generation of geospatial data. They create the possibility to develop the new technology, to be utilized in protection and inventory of military architectural objects in Poland.

Sea ice classification using fast learning neural networks

NASA Technical Reports Server (NTRS)

Dawson, M. S.; Fung, A. K.; Manry, M. T.

1992-01-01

A first learning neural network approach to the classification of sea ice is presented. The fast learning (FL) neural network and a multilayer perceptron (MLP) trained with backpropagation learning (BP network) were tested on simulated data sets based on the known dominant scattering characteristics of the target class. Four classes were used in the data simulation: open water, thick lossy saline ice, thin saline ice, and multiyear ice. The BP network was unable to consistently converge to less than 25 percent error while the FL method yielded an average error of approximately 1 percent on the first iteration of training. The fast learning method presented can significantly reduce the CPU time necessary to train a neural network as well as consistently yield higher classification accuracy than BP networks.

High-density force myography: A possible alternative for upper-limb prosthetic control.

PubMed

Radmand, Ashkan; Scheme, Erik; Englehart, Kevin

2016-01-01

Several multiple degree-of-freedom upper-limb prostheses that have the promise of highly dexterous control have recently been developed. Inadequate controllability, however, has limited adoption of these devices. Introducing more robust control methods will likely result in higher acceptance rates. This work investigates the suitability of using high-density force myography (HD-FMG) for prosthetic control. HD-FMG uses a high-density array of pressure sensors to detect changes in the pressure patterns between the residual limb and socket caused by the contraction of the forearm muscles. In this work, HD-FMG outperforms the standard electromyography (EMG)-based system in detecting different wrist and hand gestures. With the arm in a fixed, static position, eight hand and wrist motions were classified with 0.33% error using the HD-FMG technique. Comparatively, classification errors in the range of 2.2%-11.3% have been reported in the literature for multichannel EMG-based approaches. As with EMG, position variation in HD-FMG can introduce classification error, but incorporating position variation into the training protocol reduces this effect. Channel reduction was also applied to the HD-FMG technique to decrease the dimensionality of the problem as well as the size of the sensorized area. We found that with informed, symmetric channel reduction, classification error could be decreased to 0.02%.

Improved wetland remote sensing in Yellowstone National Park using classification trees to combine TM imagery and ancillary environmental data

USGS Publications Warehouse

Wright, C.; Gallant, Alisa L.

2007-01-01

The U.S. Fish and Wildlife Service uses the term palustrine wetland to describe vegetated wetlands traditionally identified as marsh, bog, fen, swamp, or wet meadow. Landsat TM imagery was combined with image texture and ancillary environmental data to model probabilities of palustrine wetland occurrence in Yellowstone National Park using classification trees. Model training and test locations were identified from National Wetlands Inventory maps, and classification trees were built for seven years spanning a range of annual precipitation. At a coarse level, palustrine wetland was separated from upland. At a finer level, five palustrine wetland types were discriminated: aquatic bed (PAB), emergent (PEM), forested (PFO), scrub–shrub (PSS), and unconsolidated shore (PUS). TM-derived variables alone were relatively accurate at separating wetland from upland, but model error rates dropped incrementally as image texture, DEM-derived terrain variables, and other ancillary GIS layers were added. For classification trees making use of all available predictors, average overall test error rates were 7.8% for palustrine wetland/upland models and 17.0% for palustrine wetland type models, with consistent accuracies across years. However, models were prone to wetland over-prediction. While the predominant PEM class was classified with omission and commission error rates less than 14%, we had difficulty identifying the PAB and PSS classes. Ancillary vegetation information greatly improved PSS classification and moderately improved PFO discrimination. Association with geothermal areas distinguished PUS wetlands. Wetland over-prediction was exacerbated by class imbalance in likely combination with spatial and spectral limitations of the TM sensor. Wetland probability surfaces may be more informative than hard classification, and appear to respond to climate-driven wetland variability. The developed method is portable, relatively easy to implement, and should be applicable in other settings and over larger extents.

Common component classification: what can we learn from machine learning?

PubMed

Anderson, Ariana; Labus, Jennifer S; Vianna, Eduardo P; Mayer, Emeran A; Cohen, Mark S

2011-05-15

Machine learning methods have been applied to classifying fMRI scans by studying locations in the brain that exhibit temporal intensity variation between groups, frequently reporting classification accuracy of 90% or better. Although empirical results are quite favorable, one might doubt the ability of classification methods to withstand changes in task ordering and the reproducibility of activation patterns over runs, and question how much of the classification machines' power is due to artifactual noise versus genuine neurological signal. To examine the true strength and power of machine learning classifiers we create and then deconstruct a classifier to examine its sensitivity to physiological noise, task reordering, and across-scan classification ability. The models are trained and tested both within and across runs to assess stability and reproducibility across conditions. We demonstrate the use of independent components analysis for both feature extraction and artifact removal and show that removal of such artifacts can reduce predictive accuracy even when data has been cleaned in the preprocessing stages. We demonstrate how mistakes in the feature selection process can cause the cross-validation error seen in publication to be a biased estimate of the testing error seen in practice and measure this bias by purposefully making flawed models. We discuss other ways to introduce bias and the statistical assumptions lying behind the data and model themselves. Finally we discuss the complications in drawing inference from the smaller sample sizes typically seen in fMRI studies, the effects of small or unbalanced samples on the Type 1 and Type 2 error rates, and how publication bias can give a false confidence of the power of such methods. Collectively this work identifies challenges specific to fMRI classification and methods affecting the stability of models. Copyright © 2010 Elsevier Inc. All rights reserved.

J-Plus: Morphological Classification Of Compact And Extended Sources By Pdf Analysis

NASA Astrophysics Data System (ADS)

López-Sanjuan, C.; Vázquez-Ramió, H.; Varela, J.; Spinoso, D.; Cristóbal-Hornillos, D.; Viironen, K.; Muniesa, D.; J-PLUS Collaboration

2017-10-01

We present a morphological classification of J-PLUS EDR sources into compact (i.e. stars) and extended (i.e. galaxies). Such classification is based on the Bayesian modelling of the concentration distribution, including observational errors and magnitude + sky position priors. We provide the star / galaxy probability of each source computed from the gri images. The comparison with the SDSS number counts support our classification up to r 21. The 31.7 deg² analised comprises 150k stars and 101k galaxies.

Combined texture feature analysis of segmentation and classification of benign and malignant tumour CT slices.

PubMed

Padma, A; Sukanesh, R

2013-01-01

A computer software system is designed for the segmentation and classification of benign from malignant tumour slices in brain computed tomography (CT) images. This paper presents a method to find and select both the dominant run length and co-occurrence texture features of region of interest (ROI) of the tumour region of each slice to be segmented by Fuzzy c means clustering (FCM) and evaluate the performance of support vector machine (SVM)-based classifiers in classifying benign and malignant tumour slices. Two hundred and six tumour confirmed CT slices are considered in this study. A total of 17 texture features are extracted by a feature extraction procedure, and six features are selected using Principal Component Analysis (PCA). This study constructed the SVM-based classifier with the selected features and by comparing the segmentation results with the experienced radiologist labelled ground truth (target). Quantitative analysis between ground truth and segmented tumour is presented in terms of segmentation accuracy, segmentation error and overlap similarity measures such as the Jaccard index. The classification performance of the SVM-based classifier with the same selected features is also evaluated using a 10-fold cross-validation method. The proposed system provides some newly found texture features have an important contribution in classifying benign and malignant tumour slices efficiently and accurately with less computational time. The experimental results showed that the proposed system is able to achieve the highest segmentation and classification accuracy effectiveness as measured by jaccard index and sensitivity and specificity.

Predicting complications of percutaneous coronary intervention using a novel support vector method.

PubMed

Lee, Gyemin; Gurm, Hitinder S; Syed, Zeeshan

2013-01-01

To explore the feasibility of a novel approach using an augmented one-class learning algorithm to model in-laboratory complications of percutaneous coronary intervention (PCI). Data from the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) multicenter registry for the years 2007 and 2008 (n=41 016) were used to train models to predict 13 different in-laboratory PCI complications using a novel one-plus-class support vector machine (OP-SVM) algorithm. The performance of these models in terms of discrimination and calibration was compared to the performance of models trained using the following classification algorithms on BMC2 data from 2009 (n=20 289): logistic regression (LR), one-class support vector machine classification (OC-SVM), and two-class support vector machine classification (TC-SVM). For the OP-SVM and TC-SVM approaches, variants of the algorithms with cost-sensitive weighting were also considered. The OP-SVM algorithm and its cost-sensitive variant achieved the highest area under the receiver operating characteristic curve for the majority of the PCI complications studied (eight cases). Similar improvements were observed for the Hosmer-Lemeshow χ(2) value (seven cases) and the mean cross-entropy error (eight cases). The OP-SVM algorithm based on an augmented one-class learning problem improved discrimination and calibration across different PCI complications relative to LR and traditional support vector machine classification. Such an approach may have value in a broader range of clinical domains.

Predicting complications of percutaneous coronary intervention using a novel support vector method

PubMed Central

Lee, Gyemin; Gurm, Hitinder S; Syed, Zeeshan

2013-01-01

Objective To explore the feasibility of a novel approach using an augmented one-class learning algorithm to model in-laboratory complications of percutaneous coronary intervention (PCI). Materials and methods Data from the Blue Cross Blue Shield of Michigan Cardiovascular Consortium (BMC2) multicenter registry for the years 2007 and 2008 (n=41 016) were used to train models to predict 13 different in-laboratory PCI complications using a novel one-plus-class support vector machine (OP-SVM) algorithm. The performance of these models in terms of discrimination and calibration was compared to the performance of models trained using the following classification algorithms on BMC2 data from 2009 (n=20 289): logistic regression (LR), one-class support vector machine classification (OC-SVM), and two-class support vector machine classification (TC-SVM). For the OP-SVM and TC-SVM approaches, variants of the algorithms with cost-sensitive weighting were also considered. Results The OP-SVM algorithm and its cost-sensitive variant achieved the highest area under the receiver operating characteristic curve for the majority of the PCI complications studied (eight cases). Similar improvements were observed for the Hosmer–Lemeshow χ2 value (seven cases) and the mean cross-entropy error (eight cases). Conclusions The OP-SVM algorithm based on an augmented one-class learning problem improved discrimination and calibration across different PCI complications relative to LR and traditional support vector machine classification. Such an approach may have value in a broader range of clinical domains. PMID:23599229

Further examination of embedded performance validity indicators for the Conners' Continuous Performance Test and Brief Test of Attention in a large outpatient clinical sample.

PubMed

Sharland, Michael J; Waring, Stephen C; Johnson, Brian P; Taran, Allise M; Rusin, Travis A; Pattock, Andrew M; Palcher, Jeanette A

2018-01-01

Assessing test performance validity is a standard clinical practice and although studies have examined the utility of cognitive/memory measures, few have examined attention measures as indicators of performance validity beyond the Reliable Digit Span. The current study further investigates the classification probability of embedded Performance Validity Tests (PVTs) within the Brief Test of Attention (BTA) and the Conners' Continuous Performance Test (CPT-II), in a large clinical sample. This was a retrospective study of 615 patients consecutively referred for comprehensive outpatient neuropsychological evaluation. Non-credible performance was defined two ways: failure on one or more PVTs and failure on two or more PVTs. Classification probability of the BTA and CPT-II into non-credible groups was assessed. Sensitivity, specificity, positive predictive value, and negative predictive value were derived to identify clinically relevant cut-off scores. When using failure on two or more PVTs as the indicator for non-credible responding compared to failure on one or more PVTs, highest classification probability, or area under the curve (AUC), was achieved by the BTA (AUC = .87 vs. .79). CPT-II Omission, Commission, and Total Errors exhibited higher classification probability as well. Overall, these findings corroborate previous findings, extending them to a large clinical sample. BTA and CPT-II are useful embedded performance validity indicators within a clinical battery but should not be used in isolation without other performance validity indicators.

An embedded implementation based on adaptive filter bank for brain-computer interface systems.

PubMed

Belwafi, Kais; Romain, Olivier; Gannouni, Sofien; Ghaffari, Fakhreddine; Djemal, Ridha; Ouni, Bouraoui

2018-07-15

Brain-computer interface (BCI) is a new communication pathway for users with neurological deficiencies. The implementation of a BCI system requires complex electroencephalography (EEG) signal processing including filtering, feature extraction and classification algorithms. Most of current BCI systems are implemented on personal computers. Therefore, there is a great interest in implementing BCI on embedded platforms to meet system specifications in terms of time response, cost effectiveness, power consumption, and accuracy. This article presents an embedded-BCI (EBCI) system based on a Stratix-IV field programmable gate array. The proposed system relays on the weighted overlap-add (WOLA) algorithm to perform dynamic filtering of EEG-signals by analyzing the event-related desynchronization/synchronization (ERD/ERS). The EEG-signals are classified, using the linear discriminant analysis algorithm, based on their spatial features. The proposed system performs fast classification within a time delay of 0.430 s/trial, achieving an average accuracy of 76.80% according to an offline approach and 80.25% using our own recording. The estimated power consumption of the prototype is approximately 0.7 W. Results show that the proposed EBCI system reduces the overall classification error rate for the three datasets of the BCI-competition by 5% compared to other similar implementations. Moreover, experiment shows that the proposed system maintains a high accuracy rate with a short processing time, a low power consumption, and a low cost. Performing dynamic filtering of EEG-signals using WOLA increases the recognition rate of ERD/ERS patterns of motor imagery brain activity. This approach allows to develop a complete prototype of a EBCI system that achieves excellent accuracy rates. Copyright © 2018 Elsevier B.V. All rights reserved.

Di-codon Usage for Gene Classification

NASA Astrophysics Data System (ADS)

Nguyen, Minh N.; Ma, Jianmin; Fogel, Gary B.; Rajapakse, Jagath C.

Classification of genes into biologically related groups facilitates inference of their functions. Codon usage bias has been described previously as a potential feature for gene classification. In this paper, we demonstrate that di-codon usage can further improve classification of genes. By using both codon and di-codon features, we achieve near perfect accuracies for the classification of HLA molecules into major classes and sub-classes. The method is illustrated on 1,841 HLA sequences which are classified into two major classes, HLA-I and HLA-II. Major classes are further classified into sub-groups. A binary SVM using di-codon usage patterns achieved 99.95% accuracy in the classification of HLA genes into major HLA classes; and multi-class SVM achieved accuracy rates of 99.82% and 99.03% for sub-class classification of HLA-I and HLA-II genes, respectively. Furthermore, by combining codon and di-codon usages, the prediction accuracies reached 100%, 99.82%, and 99.84% for HLA major class classification, and for sub-class classification of HLA-I and HLA-II genes, respectively.

Cough event classification by pretrained deep neural network.

PubMed

Liu, Jia-Ming; You, Mingyu; Wang, Zheng; Li, Guo-Zheng; Xu, Xianghuai; Qiu, Zhongmin

2015-01-01

Cough is an essential symptom in respiratory diseases. In the measurement of cough severity, an accurate and objective cough monitor is expected by respiratory disease society. This paper aims to introduce a better performed algorithm, pretrained deep neural network (DNN), to the cough classification problem, which is a key step in the cough monitor. The deep neural network models are built from two steps, pretrain and fine-tuning, followed by a Hidden Markov Model (HMM) decoder to capture tamporal information of the audio signals. By unsupervised pretraining a deep belief network, a good initialization for a deep neural network is learned. Then the fine-tuning step is a back propogation tuning the neural network so that it can predict the observation probability associated with each HMM states, where the HMM states are originally achieved by force-alignment with a Gaussian Mixture Model Hidden Markov Model (GMM-HMM) on the training samples. Three cough HMMs and one noncough HMM are employed to model coughs and noncoughs respectively. The final decision is made based on viterbi decoding algorihtm that generates the most likely HMM sequence for each sample. A sample is labeled as cough if a cough HMM is found in the sequence. The experiments were conducted on a dataset that was collected from 22 patients with respiratory diseases. Patient dependent (PD) and patient independent (PI) experimental settings were used to evaluate the models. Five criteria, sensitivity, specificity, F1, macro average and micro average are shown to depict different aspects of the models. From overall evaluation criteria, the DNN based methods are superior to traditional GMM-HMM based method on F1 and micro average with maximal 14% and 11% error reduction in PD and 7% and 10% in PI, meanwhile keep similar performances on macro average. They also surpass GMM-HMM model on specificity with maximal 14% error reduction on both PD and PI. In this paper, we tried pretrained deep neural network in cough classification problem. Our results showed that comparing with the conventional GMM-HMM framework, the HMM-DNN could get better overall performance on cough classification task.

Deep neural network with weight sparsity control and pre-training extracts hierarchical features and enhances classification performance: Evidence from whole-brain resting-state functional connectivity patterns of schizophrenia.

PubMed

Kim, Junghoe; Calhoun, Vince D; Shim, Eunsoo; Lee, Jong-Hwan

2016-01-01

Functional connectivity (FC) patterns obtained from resting-state functional magnetic resonance imaging data are commonly employed to study neuropsychiatric conditions by using pattern classifiers such as the support vector machine (SVM). Meanwhile, a deep neural network (DNN) with multiple hidden layers has shown its ability to systematically extract lower-to-higher level information of image and speech data from lower-to-higher hidden layers, markedly enhancing classification accuracy. The objective of this study was to adopt the DNN for whole-brain resting-state FC pattern classification of schizophrenia (SZ) patients vs. healthy controls (HCs) and identification of aberrant FC patterns associated with SZ. We hypothesized that the lower-to-higher level features learned via the DNN would significantly enhance the classification accuracy, and proposed an adaptive learning algorithm to explicitly control the weight sparsity in each hidden layer via L1-norm regularization. Furthermore, the weights were initialized via stacked autoencoder based pre-training to further improve the classification performance. Classification accuracy was systematically evaluated as a function of (1) the number of hidden layers/nodes, (2) the use of L1-norm regularization, (3) the use of the pre-training, (4) the use of framewise displacement (FD) removal, and (5) the use of anatomical/functional parcellation. Using FC patterns from anatomically parcellated regions without FD removal, an error rate of 14.2% was achieved by employing three hidden layers and 50 hidden nodes with both L1-norm regularization and pre-training, which was substantially lower than the error rate from the SVM (22.3%). Moreover, the trained DNN weights (i.e., the learned features) were found to represent the hierarchical organization of aberrant FC patterns in SZ compared with HC. Specifically, pairs of nodes extracted from the lower hidden layer represented sparse FC patterns implicated in SZ, which was quantified by using kurtosis/modularity measures and features from the higher hidden layer showed holistic/global FC patterns differentiating SZ from HC. Our proposed schemes and reported findings attained by using the DNN classifier and whole-brain FC data suggest that such approaches show improved ability to learn hidden patterns in brain imaging data, which may be useful for developing diagnostic tools for SZ and other neuropsychiatric disorders and identifying associated aberrant FC patterns. Copyright © 2015 Elsevier Inc. All rights reserved.

Halftoning Algorithms and Systems.

DTIC Science & Technology

1996-08-01

TERMS 15. NUMBER IF PAGESi. Halftoning algorithms; error diffusions ; color printing; topographic maps 16. PRICE CODE 17. SECURITY CLASSIFICATION 18...graylevels for each screen level. In the case of error diffusion algorithms, the calibration procedure using the new centering concept manifests itself as a...Novel Centering Concept for Overlapping Correction Paper / Transparency (Patent Applied 5/94)I * Applications To Error Diffusion * To Dithering (IS&T

Simulation techniques for estimating error in the classification of normal patterns

NASA Technical Reports Server (NTRS)

Whitsitt, S. J.; Landgrebe, D. A.

1974-01-01

Methods of efficiently generating and classifying samples with specified multivariate normal distributions were discussed. Conservative confidence tables for sample sizes are given for selective sampling. Simulation results are compared with classified training data. Techniques for comparing error and separability measure for two normal patterns are investigated and used to display the relationship between the error and the Chernoff bound.

Algorithms for Hyperspectral Endmember Extraction and Signature Classification with Morphological Dendritic Networks

NASA Astrophysics Data System (ADS)

Schmalz, M.; Ritter, G.

Accurate multispectral or hyperspectral signature classification is key to the nonimaging detection and recognition of space objects. Additionally, signature classification accuracy depends on accurate spectral endmember determination [1]. Previous approaches to endmember computation and signature classification were based on linear operators or neural networks (NNs) expressed in terms of the algebra (R, +, x) [1,2]. Unfortunately, class separation in these methods tends to be suboptimal, and the number of signatures that can be accurately classified often depends linearly on the number of NN inputs. This can lead to poor endmember distinction, as well as potentially significant classification errors in the presence of noise or densely interleaved signatures. In contrast to traditional CNNs, autoassociative morphological memories (AMM) are a construct similar to Hopfield autoassociatived memories defined on the (R, +, ?,?) lattice algebra [3]. Unlimited storage and perfect recall of noiseless real valued patterns has been proven for AMMs [4]. However, AMMs suffer from sensitivity to specific noise models, that can be characterized as erosive and dilative noise. On the other hand, the prior definition of a set of endmembers corresponds to material spectra lying on vertices of the minimum convex region covering the image data. These vertices can be characterized as morphologically independent patterns. It has further been shown that AMMs can be based on dendritic computation [3,6]. These techniques yield improved accuracy and class segmentation/separation ability in the presence of highly interleaved signature data. In this paper, we present a procedure for endmember determination based on AMM noise sensitivity, which employs morphological dendritic computation. We show that detected endmembers can be exploited by AMM based classification techniques, to achieve accurate signature classification in the presence of noise, closely spaced or interleaved signatures, and simulated camera optical distortions. In particular, we examine two critical cases: (1) classification of multiple closely spaced signatures that are difficult to separate using distance measures, and (2) classification of materials in simulated hyperspectral images of spaceborne satellites. In each case, test data are derived from a NASA database of space material signatures. Additional analysis pertains to computational complexity and noise sensitivity, which are superior to classical NN based techniques.

The Human Factors Analysis and Classification System : HFACS : final report.

DOT National Transportation Integrated Search

2000-02-01

Human error has been implicated in 70 to 80% of all civil and military aviation accidents. Yet, most accident reporting systems are not designed around any theoretical framework of human error. As a result, most accident databases are not conducive t...

Statistical classification of drug incidents due to look-alike sound-alike mix-ups.

PubMed

Wong, Zoie Shui Yee

2016-06-01

It has been recognised that medication names that look or sound similar are a cause of medication errors. This study builds statistical classifiers for identifying medication incidents due to look-alike sound-alike mix-ups. A total of 227 patient safety incident advisories related to medication were obtained from the Canadian Patient Safety Institute's Global Patient Safety Alerts system. Eight feature selection strategies based on frequent terms, frequent drug terms and constituent terms were performed. Statistical text classifiers based on logistic regression, support vector machines with linear, polynomial, radial-basis and sigmoid kernels and decision tree were trained and tested. The models developed achieved an average accuracy of above 0.8 across all the model settings. The receiver operating characteristic curves indicated the classifiers performed reasonably well. The results obtained in this study suggest that statistical text classification can be a feasible method for identifying medication incidents due to look-alike sound-alike mix-ups based on a database of advisories from Global Patient Safety Alerts. © The Author(s) 2014.

Learning-based landmarks detection for osteoporosis analysis

NASA Astrophysics Data System (ADS)

Cheng, Erkang; Zhu, Ling; Yang, Jie; Azhari, Azhari; Sitam, Suhardjo; Liang, Xin; Megalooikonomou, Vasileios; Ling, Haibin

2016-03-01

Osteoporosis is the common cause for a broken bone among senior citizens. Early diagnosis of osteoporosis requires routine examination which may be costly for patients. A potential low cost diagnosis is to identify a senior citizen at high risk of osteoporosis by pre-screening during routine dental examination. Therefore, osteoporosis analysis using dental radiographs severs as a key step in routine dental examination. The aim of this study is to localize landmarks in dental radiographs which are helpful to assess the evidence of osteoporosis. We collect eight landmarks which are critical in osteoporosis analysis. Our goal is to localize these landmarks automatically for a given dental radiographic image. To address the challenges such as large variations of appearances in subjects, in this paper, we formulate the task into a multi-class classification problem. A hybrid feature pool is used to represent these landmarks. For the discriminative classification problem, we use a random forest to fuse the hybrid feature representation. In the experiments, we also evaluate the performances of individual feature component and the hybrid fused feature. Our proposed method achieves average detection error of 2:9mm.

A Confidence Paradigm for Classification Systems

DTIC Science & Technology

2008-09-01

methodology to determine how much confi- dence one should have in a classifier output. This research proposes a framework to determine the level of...theoretical framework that attempts to unite the viewpoints of the classification system developer (or engineer) and the classification system user (or...operating point. An algorithm is developed that minimizes a “confidence” measure called Binned Error in the Posterior ( BEP ). Then, we prove that training a

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.

Differences in chewing sounds of dry-crisp snacks by multivariate data analysis

NASA Astrophysics Data System (ADS)

De Belie, N.; Sivertsvik, M.; De Baerdemaeker, J.

2003-09-01

Chewing sounds of different types of dry-crisp snacks (two types of potato chips, prawn crackers, cornflakes and low calorie snacks from extruded starch) were analysed to assess differences in sound emission patterns. The emitted sounds were recorded by a microphone placed over the ear canal. The first bite and the first subsequent chew were selected from the time signal and a fast Fourier transformation provided the power spectra. Different multivariate analysis techniques were used for classification of the snack groups. This included principal component analysis (PCA) and unfold partial least-squares (PLS) algorithms, as well as multi-way techniques such as three-way PLS, three-way PCA (Tucker3), and parallel factor analysis (PARAFAC) on the first bite and subsequent chew. The models were evaluated by calculating the classification errors and the root mean square error of prediction (RMSEP) for independent validation sets. It appeared that the logarithm of the power spectra obtained from the chewing sounds could be used successfully to distinguish the different snack groups. When different chewers were used, recalibration of the models was necessary. Multi-way models distinguished better between chewing sounds of different snack groups than PCA on bite or chew separately and than unfold PLS. From all three-way models applied, N-PLS with three components showed the best classification capabilities, resulting in classification errors of 14-18%. The major amount of incorrect classifications was due to one type of potato chips that had a very irregular shape, resulting in a wide variation of the emitted sounds.

Towards the Automatic Classification of Avian Flight Calls for Bioacoustic Monitoring

PubMed Central

Bello, Juan Pablo; Farnsworth, Andrew; Robbins, Matt; Keen, Sara; Klinck, Holger; Kelling, Steve

2016-01-01

Automatic classification of animal vocalizations has great potential to enhance the monitoring of species movements and behaviors. This is particularly true for monitoring nocturnal bird migration, where automated classification of migrants’ flight calls could yield new biological insights and conservation applications for birds that vocalize during migration. In this paper we investigate the automatic classification of bird species from flight calls, and in particular the relationship between two different problem formulations commonly found in the literature: classifying a short clip containing one of a fixed set of known species (N-class problem) and the continuous monitoring problem, the latter of which is relevant to migration monitoring. We implemented a state-of-the-art audio classification model based on unsupervised feature learning and evaluated it on three novel datasets, one for studying the N-class problem including over 5000 flight calls from 43 different species, and two realistic datasets for studying the monitoring scenario comprising hundreds of thousands of audio clips that were compiled by means of remote acoustic sensors deployed in the field during two migration seasons. We show that the model achieves high accuracy when classifying a clip to one of N known species, even for a large number of species. In contrast, the model does not perform as well in the continuous monitoring case. Through a detailed error analysis (that included full expert review of false positives and negatives) we show the model is confounded by varying background noise conditions and previously unseen vocalizations. We also show that the model needs to be parameterized and benchmarked differently for the continuous monitoring scenario. Finally, we show that despite the reduced performance, given the right conditions the model can still characterize the migration pattern of a specific species. The paper concludes with directions for future research. PMID:27880836

Classification of toxicity effects of biotransformed hepatic drugs using whale optimized support vector machines.

PubMed

Tharwat, Alaa; Moemen, Yasmine S; Hassanien, Aboul Ella

2017-04-01

Measuring toxicity is an important step in drug development. Nevertheless, the current experimental methods used to estimate the drug toxicity are expensive and time-consuming, indicating that they are not suitable for large-scale evaluation of drug toxicity in the early stage of drug development. Hence, there is a high demand to develop computational models that can predict the drug toxicity risks. In this study, we used a dataset that consists of 553 drugs that biotransformed in liver. The toxic effects were calculated for the current data, namely, mutagenic, tumorigenic, irritant and reproductive effect. Each drug is represented by 31 chemical descriptors (features). The proposed model consists of three phases. In the first phase, the most discriminative subset of features is selected using rough set-based methods to reduce the classification time while improving the classification performance. In the second phase, different sampling methods such as Random Under-Sampling, Random Over-Sampling and Synthetic Minority Oversampling Technique (SMOTE), BorderLine SMOTE and Safe Level SMOTE are used to solve the problem of imbalanced dataset. In the third phase, the Support Vector Machines (SVM) classifier is used to classify an unknown drug into toxic or non-toxic. SVM parameters such as the penalty parameter and kernel parameter have a great impact on the classification accuracy of the model. In this paper, Whale Optimization Algorithm (WOA) has been proposed to optimize the parameters of SVM, so that the classification error can be reduced. The experimental results proved that the proposed model achieved high sensitivity to all toxic effects. Overall, the high sensitivity of the WOA+SVM model indicates that it could be used for the prediction of drug toxicity in the early stage of drug development. Copyright © 2017 Elsevier Inc. All rights reserved.

Kernel Wiener filter and its application to pattern recognition.

PubMed

Yoshino, Hirokazu; Dong, Chen; Washizawa, Yoshikazu; Yamashita, Yukihiko

2010-11-01

The Wiener filter (WF) is widely used for inverse problems. From an observed signal, it provides the best estimated signal with respect to the squared error averaged over the original and the observed signals among linear operators. The kernel WF (KWF), extended directly from WF, has a problem that an additive noise has to be handled by samples. Since the computational complexity of kernel methods depends on the number of samples, a huge computational cost is necessary for the case. By using the first-order approximation of kernel functions, we realize KWF that can handle such a noise not by samples but as a random variable. We also propose the error estimation method for kernel filters by using the approximations. In order to show the advantages of the proposed methods, we conducted the experiments to denoise images and estimate errors. We also apply KWF to classification since KWF can provide an approximated result of the maximum a posteriori classifier that provides the best recognition accuracy. The noise term in the criterion can be used for the classification in the presence of noise or a new regularization to suppress changes in the input space, whereas the ordinary regularization for the kernel method suppresses changes in the feature space. In order to show the advantages of the proposed methods, we conducted experiments of binary and multiclass classifications and classification in the presence of noise.

Consequences of land-cover misclassification in models of impervious surface

USGS Publications Warehouse

McMahon, G.

2007-01-01

Model estimates of impervious area as a function of landcover area may be biased and imprecise because of errors in the land-cover classification. This investigation of the effects of land-cover misclassification on impervious surface models that use National Land Cover Data (NLCD) evaluates the consequences of adjusting land-cover within a watershed to reflect uncertainty assessment information. Model validation results indicate that using error-matrix information to adjust land-cover values used in impervious surface models does not substantially improve impervious surface predictions. Validation results indicate that the resolution of the landcover data (Level I and Level II) is more important in predicting impervious surface accurately than whether the land-cover data have been adjusted using information in the error matrix. Level I NLCD, adjusted for land-cover misclassification, is preferable to the other land-cover options for use in models of impervious surface. This result is tied to the lower classification error rates for the Level I NLCD. ?? 2007 American Society for Photogrammetry and Remote Sensing.

Improved classification accuracy by feature extraction using genetic algorithms

NASA Astrophysics Data System (ADS)

Patriarche, Julia; Manduca, Armando; Erickson, Bradley J.

2003-05-01

A feature extraction algorithm has been developed for the purposes of improving classification accuracy. The algorithm uses a genetic algorithm / hill-climber hybrid to generate a set of linearly recombined features, which may be of reduced dimensionality compared with the original set. The genetic algorithm performs the global exploration, and a hill climber explores local neighborhoods. Hybridizing the genetic algorithm with a hill climber improves both the rate of convergence, and the final overall cost function value; it also reduces the sensitivity of the genetic algorithm to parameter selection. The genetic algorithm includes the operators: crossover, mutation, and deletion / reactivation - the last of these effects dimensionality reduction. The feature extractor is supervised, and is capable of deriving a separate feature space for each tissue (which are reintegrated during classification). A non-anatomical digital phantom was developed as a gold standard for testing purposes. In tests with the phantom, and with images of multiple sclerosis patients, classification with feature extractor derived features yielded lower error rates than using standard pulse sequences, and with features derived using principal components analysis. Using the multiple sclerosis patient data, the algorithm resulted in a mean 31% reduction in classification error of pure tissues.

Locally Weighted Score Estimation for Quantile Classification in Binary Regression Models

PubMed Central

Rice, John D.; Taylor, Jeremy M. G.

2016-01-01

One common use of binary response regression methods is classification based on an arbitrary probability threshold dictated by the particular application. Since this is given to us a priori, it is sensible to incorporate the threshold into our estimation procedure. Specifically, for the linear logistic model, we solve a set of locally weighted score equations, using a kernel-like weight function centered at the threshold. The bandwidth for the weight function is selected by cross validation of a novel hybrid loss function that combines classification error and a continuous measure of divergence between observed and fitted values; other possible cross-validation functions based on more common binary classification metrics are also examined. This work has much in common with robust estimation, but diers from previous approaches in this area in its focus on prediction, specifically classification into high- and low-risk groups. Simulation results are given showing the reduction in error rates that can be obtained with this method when compared with maximum likelihood estimation, especially under certain forms of model misspecification. Analysis of a melanoma data set is presented to illustrate the use of the method in practice. PMID:28018492

Error detection and reduction in blood banking.

PubMed

Motschman, T L; Moore, S B

1996-12-01

Error management plays a major role in facility process improvement efforts. By detecting and reducing errors, quality and, therefore, patient care improve. It begins with a strong organizational foundation of management attitude with clear, consistent employee direction and appropriate physical facilities. Clearly defined critical processes, critical activities, and SOPs act as the framework for operations as well as active quality monitoring. To assure that personnel can detect an report errors they must be trained in both operational duties and error management practices. Use of simulated/intentional errors and incorporation of error detection into competency assessment keeps employees practiced, confident, and diminishes fear of the unknown. Personnel can clearly see that errors are indeed used as opportunities for process improvement and not for punishment. The facility must have a clearly defined and consistently used definition for reportable errors. Reportable errors should include those errors with potentially harmful outcomes as well as those errors that are "upstream," and thus further away from the outcome. A well-written error report consists of who, what, when, where, why/how, and follow-up to the error. Before correction can occur, an investigation to determine the underlying cause of the error should be undertaken. Obviously, the best corrective action is prevention. Correction can occur at five different levels; however, only three of these levels are directed at prevention. Prevention requires a method to collect and analyze data concerning errors. In the authors' facility a functional error classification method and a quality system-based classification have been useful. An active method to search for problems uncovers them further upstream, before they can have disastrous outcomes. In the continual quest for improving processes, an error management program is itself a process that needs improvement, and we must strive to always close the circle of quality assurance. Ultimately, the goal of better patient care will be the reward.

Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition.

PubMed

Tang, Xin; Feng, Guo-Can; Li, Xiao-Xin; Cai, Jia-Xin

2015-01-01

Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC) achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC). Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis) of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our method achieves the state-of-the-art results on AR, FERET, FRGC and LFW databases.

Learning Low-Rank Class-Specific Dictionary and Sparse Intra-Class Variant Dictionary for Face Recognition

PubMed Central

Tang, Xin; Feng, Guo-can; Li, Xiao-xin; Cai, Jia-xin

2015-01-01

Face recognition is challenging especially when the images from different persons are similar to each other due to variations in illumination, expression, and occlusion. If we have sufficient training images of each person which can span the facial variations of that person under testing conditions, sparse representation based classification (SRC) achieves very promising results. However, in many applications, face recognition often encounters the small sample size problem arising from the small number of available training images for each person. In this paper, we present a novel face recognition framework by utilizing low-rank and sparse error matrix decomposition, and sparse coding techniques (LRSE+SC). Firstly, the low-rank matrix recovery technique is applied to decompose the face images per class into a low-rank matrix and a sparse error matrix. The low-rank matrix of each individual is a class-specific dictionary and it captures the discriminative feature of this individual. The sparse error matrix represents the intra-class variations, such as illumination, expression changes. Secondly, we combine the low-rank part (representative basis) of each person into a supervised dictionary and integrate all the sparse error matrix of each individual into a within-individual variant dictionary which can be applied to represent the possible variations between the testing and training images. Then these two dictionaries are used to code the query image. The within-individual variant dictionary can be shared by all the subjects and only contribute to explain the lighting conditions, expressions, and occlusions of the query image rather than discrimination. At last, a reconstruction-based scheme is adopted for face recognition. Since the within-individual dictionary is introduced, LRSE+SC can handle the problem of the corrupted training data and the situation that not all subjects have enough samples for training. Experimental results show that our method achieves the state-of-the-art results on AR, FERET, FRGC and LFW databases. PMID:26571112

Simulated rRNA/DNA Ratios Show Potential To Misclassify Active Populations as Dormant

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

Steven, Blaire; Hesse, Cedar; Soghigian, John

The use of rRNA/DNA ratios derived from surveys of rRNA sequences in RNA and DNA extracts is an appealing but poorly validated approach to infer the activity status of environmental microbes. To improve the interpretation of rRNA/DNA ratios, we performed simulations to investigate the effects of community structure, rRNA amplification, and sampling depth on the accuracy of rRNA/DNA ratios in classifying bacterial populations as “active” or “dormant.” Community structure was an insignificant factor. In contrast, the extent of rRNA amplification that occurs as cells transition from dormant to growing had a significant effect (P < 0.0001) on classification accuracy, withmore » misclassification errors ranging from 16 to 28%, depending on the rRNA amplification model. The error rate increased to 47% when communities included a mixture of rRNA amplification models, but most of the inflated error was false negatives (i.e., active populations misclassified as dormant). Sampling depth also affected error rates (P < 0.001). Inadequate sampling depth produced various artifacts that are characteristic of rRNA/DNA ratios generated from real communities. These data show important constraints on the use of rRNA/DNA ratios to infer activity status. Whereas classification of populations as active based on rRNA/DNA ratios appears generally valid, classification of populations as dormant is potentially far less accurate.« less

Simulated rRNA/DNA Ratios Show Potential To Misclassify Active Populations as Dormant

DOE PAGES

Steven, Blaire; Hesse, Cedar; Soghigian, John; ...

2017-03-31

The use of rRNA/DNA ratios derived from surveys of rRNA sequences in RNA and DNA extracts is an appealing but poorly validated approach to infer the activity status of environmental microbes. To improve the interpretation of rRNA/DNA ratios, we performed simulations to investigate the effects of community structure, rRNA amplification, and sampling depth on the accuracy of rRNA/DNA ratios in classifying bacterial populations as “active” or “dormant.” Community structure was an insignificant factor. In contrast, the extent of rRNA amplification that occurs as cells transition from dormant to growing had a significant effect (P < 0.0001) on classification accuracy, withmore » misclassification errors ranging from 16 to 28%, depending on the rRNA amplification model. The error rate increased to 47% when communities included a mixture of rRNA amplification models, but most of the inflated error was false negatives (i.e., active populations misclassified as dormant). Sampling depth also affected error rates (P < 0.001). Inadequate sampling depth produced various artifacts that are characteristic of rRNA/DNA ratios generated from real communities. These data show important constraints on the use of rRNA/DNA ratios to infer activity status. Whereas classification of populations as active based on rRNA/DNA ratios appears generally valid, classification of populations as dormant is potentially far less accurate.« less

Regulation of IAP (Inhibitor of Apoptosis) Gene Expression by the p53 Tumor Suppressor Protein

DTIC Science & Technology

2005-05-01

adenovirus, gene therapy, polymorphism, 31 16. PRICE CODE 17. SECURITY CLASSIFICATION 18. SECURITY CLASSIFICATION 19. SECURITY CLASSIFICATION 20...averaged results of three inde- pendent experiments, with standard error. Right panel: Level of p53 in infected cells using the antibody Ab-6 (Calbiochem...with highly purified mitochondria as described in (2). The arrow marks oligomerized BAK. The right _ -. panel depicts the purity of BMH CrosIinked Mito

An Analysis of U.S. Army Fratricide Incidents during the Global War on Terror (11 September 2001 to 31 March 2008)

DTIC Science & Technology

2010-03-15

Swiss cheese model of human error causation. ................................................................... 3  2. Results for the classification of...based on Reason’s “ Swiss cheese ” model of human error (1990). Figure 1 describes how an accident is likely to occur when all of the errors, or “holes...align. A detailed description of HFACS can be found in Wiegmann and Shappell (2003). Figure 1. The Swiss cheese model of human error

Object-Based Land Use Classification of Agricultural Land by Coupling Multi-Temporal Spectral Characteristics and Phenological Events in Germany

NASA Astrophysics Data System (ADS)

Knoefel, Patrick; Loew, Fabian; Conrad, Christopher

2015-04-01

Crop maps based on classification of remotely sensed data are of increased attendance in agricultural management. This induces a more detailed knowledge about the reliability of such spatial information. However, classification of agricultural land use is often limited by high spectral similarities of the studied crop types. More, spatially and temporally varying agro-ecological conditions can introduce confusion in crop mapping. Classification errors in crop maps in turn may have influence on model outputs, like agricultural production monitoring. One major goal of the PhenoS project ("Phenological structuring to determine optimal acquisition dates for Sentinel-2 data for field crop classification"), is the detection of optimal phenological time windows for land cover classification purposes. Since many crop species are spectrally highly similar, accurate classification requires the right selection of satellite images for a certain classification task. In the course of one growing season, phenological phases exist where crops are separable with higher accuracies. For this purpose, coupling of multi-temporal spectral characteristics and phenological events is promising. The focus of this study is set on the separation of spectrally similar cereal crops like winter wheat, barley, and rye of two test sites in Germany called "Harz/Central German Lowland" and "Demmin". However, this study uses object based random forest (RF) classification to investigate the impact of image acquisition frequency and timing on crop classification uncertainty by permuting all possible combinations of available RapidEye time series recorded on the test sites between 2010 and 2014. The permutations were applied to different segmentation parameters. Then, classification uncertainty was assessed and analysed, based on the probabilistic soft-output from the RF algorithm at the per-field basis. From this soft output, entropy was calculated as a spatial measure of classification uncertainty. The results indicate that uncertainty estimates provide a valuable addition to traditional accuracy assessments and helps the user to allocate error in crop maps.

A new classification of glaucomas

PubMed Central

Bordeianu, Constantin-Dan

2014-01-01

Purpose To suggest a new glaucoma classification that is pathogenic, etiologic, and clinical. Methods After discussing the logical pathway used in criteria selection, the paper presents the new classification and compares it with the classification currently in use, that is, the one issued by the European Glaucoma Society in 2008. Results The paper proves that the new classification is clear (being based on a coherent and consistently followed set of criteria), is comprehensive (framing all forms of glaucoma), and helps in understanding the sickness understanding (in that it uses a logical framing system). The great advantage is that it facilitates therapeutic decision making in that it offers direct therapeutic suggestions and avoids errors leading to disasters. Moreover, the scheme remains open to any new development. Conclusion The suggested classification is a pathogenic, etiologic, and clinical classification that fulfills the conditions of an ideal classification. The suggested classification is the first classification in which the main criterion is consistently used for the first 5 to 7 crossings until its differentiation capabilities are exhausted. Then, secondary criteria (etiologic and clinical) pick up the relay until each form finds its logical place in the scheme. In order to avoid unclear aspects, the genetic criterion is no longer used, being replaced by age, one of the clinical criteria. The suggested classification brings only benefits to all categories of ophthalmologists: the beginners will have a tool to better understand the sickness and to ease their decision making, whereas the experienced doctors will have their practice simplified. For all doctors, errors leading to therapeutic disasters will be less likely to happen. Finally, researchers will have the object of their work gathered in the group of glaucoma with unknown or uncertain pathogenesis, whereas the results of their work will easily find a logical place in the scheme, as the suggested classification remains open to any new development. PMID:25246759

Developing EHR-driven heart failure risk prediction models using CPXR(Log) with the probabilistic loss function.

PubMed

Taslimitehrani, Vahid; Dong, Guozhu; Pereira, Naveen L; Panahiazar, Maryam; Pathak, Jyotishman

2016-04-01

Computerized survival prediction in healthcare identifying the risk of disease mortality, helps healthcare providers to effectively manage their patients by providing appropriate treatment options. In this study, we propose to apply a classification algorithm, Contrast Pattern Aided Logistic Regression (CPXR(Log)) with the probabilistic loss function, to develop and validate prognostic risk models to predict 1, 2, and 5year survival in heart failure (HF) using data from electronic health records (EHRs) at Mayo Clinic. The CPXR(Log) constructs a pattern aided logistic regression model defined by several patterns and corresponding local logistic regression models. One of the models generated by CPXR(Log) achieved an AUC and accuracy of 0.94 and 0.91, respectively, and significantly outperformed prognostic models reported in prior studies. Data extracted from EHRs allowed incorporation of patient co-morbidities into our models which helped improve the performance of the CPXR(Log) models (15.9% AUC improvement), although did not improve the accuracy of the models built by other classifiers. We also propose a probabilistic loss function to determine the large error and small error instances. The new loss function used in the algorithm outperforms other functions used in the previous studies by 1% improvement in the AUC. This study revealed that using EHR data to build prediction models can be very challenging using existing classification methods due to the high dimensionality and complexity of EHR data. The risk models developed by CPXR(Log) also reveal that HF is a highly heterogeneous disease, i.e., different subgroups of HF patients require different types of considerations with their diagnosis and treatment. Our risk models provided two valuable insights for application of predictive modeling techniques in biomedicine: Logistic risk models often make systematic prediction errors, and it is prudent to use subgroup based prediction models such as those given by CPXR(Log) when investigating heterogeneous diseases. Copyright © 2016 Elsevier Inc. All rights reserved.

Landsat D Thematic Mapper image dimensionality reduction and geometric correction accuracy

NASA Technical Reports Server (NTRS)

Ford, G. E.

1986-01-01

To characterize and quantify the performance of the Landsat thematic mapper (TM), techniques for dimensionality reduction by linear transformation have been studied and evaluated and the accuracy of the correction of geometric errors in TM images analyzed. Theoretical evaluations and comparisons for existing methods for the design of linear transformation for dimensionality reduction are presented. These methods include the discrete Karhunen Loeve (KL) expansion, Multiple Discriminant Analysis (MDA), Thematic Mapper (TM)-Tasseled Cap Linear Transformation and Singular Value Decomposition (SVD). A unified approach to these design problems is presented in which each method involves optimizing an objective function with respect to the linear transformation matrix. From these studies, four modified methods are proposed. They are referred to as the Space Variant Linear Transformation, the KL Transform-MDA hybrid method, and the First and Second Version of the Weighted MDA method. The modifications involve the assignment of weights to classes to achieve improvements in the class conditional probability of error for classes with high weights. Experimental evaluations of the existing and proposed methods have been performed using the six reflective bands of the TM data. It is shown that in terms of probability of classification error and the percentage of the cumulative eigenvalues, the six reflective bands of the TM data require only a three dimensional feature space. It is shown experimentally as well that for the proposed methods, the classes with high weights have improvements in class conditional probability of error estimates as expected.

Classification of burn wounds using support vector machines

NASA Astrophysics Data System (ADS)

Acha, Begona; Serrano, Carmen; Palencia, Sergio; Murillo, Juan Jose

2004-05-01

The purpose of this work is to improve a previous method developed by the authors for the classification of burn wounds into their depths. The inputs of the system are color and texture information, as these are the characteristics observed by physicians in order to give a diagnosis. Our previous work consisted in segmenting the burn wound from the rest of the image and classifying the burn into its depth. In this paper we focus on the classification problem only. We already proposed to use a Fuzzy-ARTMAP neural network (NN). However, we may take advantage of new powerful classification tools such as Support Vector Machines (SVM). We apply the five-folded cross validation scheme to divide the database into training and validating sets. Then, we apply a feature selection method for each classifier, which will give us the set of features that yields the smallest classification error for each classifier. Features used to classify are first-order statistical parameters extracted from the L*, u* and v* color components of the image. The feature selection algorithms used are the Sequential Forward Selection (SFS) and the Sequential Backward Selection (SBS) methods. As data of the problem faced here are not linearly separable, the SVM was trained using some different kernels. The validating process shows that the SVM method, when using a Gaussian kernel of variance 1, outperforms classification results obtained with the rest of the classifiers, yielding an error classification rate of 0.7% whereas the Fuzzy-ARTMAP NN attained 1.6 %.

Comparative assessment of LANDSAT-D MSS and TM data quality for mapping applications in the Southeast

NASA Technical Reports Server (NTRS)

1984-01-01

Rectifications of multispectral scanner and thematic mapper data sets for full and subscene areas, analyses of planimetric errors, assessments of the number and distribution of ground control points required to minimize errors, and factors contributing to error residual are examined. Other investigations include the generation of three dimensional terrain models and the effects of spatial resolution on digital classification accuracies.

Cluster designs to assess the prevalence of acute malnutrition by lot quality assurance sampling: a validation study by computer simulation.

PubMed

Olives, Casey; Pagano, Marcello; Deitchler, Megan; Hedt, Bethany L; Egge, Kari; Valadez, Joseph J

2009-04-01

Traditional lot quality assurance sampling (LQAS) methods require simple random sampling to guarantee valid results. However, cluster sampling has been proposed to reduce the number of random starting points. This study uses simulations to examine the classification error of two such designs, a 67x3 (67 clusters of three observations) and a 33x6 (33 clusters of six observations) sampling scheme to assess the prevalence of global acute malnutrition (GAM). Further, we explore the use of a 67x3 sequential sampling scheme for LQAS classification of GAM prevalence. Results indicate that, for independent clusters with moderate intracluster correlation for the GAM outcome, the three sampling designs maintain approximate validity for LQAS analysis. Sequential sampling can substantially reduce the average sample size that is required for data collection. The presence of intercluster correlation can impact dramatically the classification error that is associated with LQAS analysis.

Influence of ECG measurement accuracy on ECG diagnostic statements.

PubMed

Zywietz, C; Celikag, D; Joseph, G

1996-01-01

Computer analysis of electrocardiograms (ECGs) provides a large amount of ECG measurement data, which may be used for diagnostic classification and storage in ECG databases. Until now, neither error limits for ECG measurements have been specified nor has their influence on diagnostic statements been systematically investigated. An analytical method is presented to estimate the influence of measurement errors on the accuracy of diagnostic ECG statements. Systematic (offset) errors will usually result in an increase of false positive or false negative statements since they cause a shift of the working point on the receiver operating characteristics curve. Measurement error dispersion broadens the distribution function of discriminative measurement parameters and, therefore, usually increases the overlap between discriminative parameters. This results in a flattening of the receiver operating characteristics curve and an increase of false positive and false negative classifications. The method developed has been applied to ECG conduction defect diagnoses by using the proposed International Electrotechnical Commission's interval measurement tolerance limits. These limits appear too large because more than 30% of false positive atrial conduction defect statements and 10-18% of false intraventricular conduction defect statements could be expected due to tolerated measurement errors. To assure long-term usability of ECG measurement databases, it is recommended that systems provide its error tolerance limits obtained on a defined test set.

Decision support system for determining the contact lens for refractive errors patients with classification ID3

NASA Astrophysics Data System (ADS)

Situmorang, B. H.; Setiawan, M. P.; Tosida, E. T.

2017-01-01

Refractive errors are abnormalities of the refraction of light so that the shadows do not focus precisely on the retina resulting in blurred vision [1]. Refractive errors causing the patient should wear glasses or contact lenses in order eyesight returned to normal. The use of glasses or contact lenses in a person will be different from others, it is influenced by patient age, the amount of tear production, vision prescription, and astigmatic. Because the eye is one organ of the human body is very important to see, then the accuracy in determining glasses or contact lenses which will be used is required. This research aims to develop a decision support system that can produce output on the right contact lenses for refractive errors patients with a value of 100% accuracy. Iterative Dichotomize Three (ID3) classification methods will generate gain and entropy values of attributes that include code sample data, age of the patient, astigmatic, the ratio of tear production, vision prescription, and classes that will affect the outcome of the decision tree. The eye specialist test result for the training data obtained the accuracy rate of 96.7% and an error rate of 3.3%, the result test using confusion matrix obtained the accuracy rate of 96.1% and an error rate of 3.1%; for the data testing obtained accuracy rate of 100% and an error rate of 0.

Classification, Seriation, and Counting in Grades 1, 2, and 3 as Two-Year Longitudinal Predictors for Low Achieving in Numerical Facility and Arithmetical Achievement?

ERIC Educational Resources Information Center

Desoete, Annemie; Stock, Pieter; Schepens, Annemie; Baeyens, Dieter; Roeyers, Herbert

2009-01-01

Previous research stresses the importance of seriation, classification, and counting abilities that should be assessed in kindergarten, when looking for crucial predictors of mathematical learning disabilities in Grade 1. This study examines (n = 158) two-year-long predictive relationships between children's seriation, classification, procedural…

Concussion classification via deep learning using whole-brain white matter fiber strains

PubMed Central

Cai, Yunliang; Wu, Shaoju; Zhao, Wei; Li, Zhigang; Wu, Zheyang

2018-01-01

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based machine learning classifiers including deep learning, SVM, and RF consistently outperformed all scalar injury metrics across all performance categories (e.g., leave-one-out accuracy of 0.828–0.862 vs. 0.690–0.776, and .632+ error of 0.148–0.176 vs. 0.207–0.292). Further, deep learning achieved the best cross-validation accuracy, sensitivity, AUC, and .632+ error. These findings demonstrate the superior performances of deep learning in concussion prediction and suggest its promise for future applications in biomechanical investigations of traumatic brain injury. PMID:29795640

Concussion classification via deep learning using whole-brain white matter fiber strains.

PubMed

Cai, Yunliang; Wu, Shaoju; Zhao, Wei; Li, Zhigang; Wu, Zheyang; Ji, Songbai

2018-01-01

Developing an accurate and reliable injury predictor is central to the biomechanical studies of traumatic brain injury. State-of-the-art efforts continue to rely on empirical, scalar metrics based on kinematics or model-estimated tissue responses explicitly pre-defined in a specific brain region of interest. They could suffer from loss of information. A single training dataset has also been used to evaluate performance but without cross-validation. In this study, we developed a deep learning approach for concussion classification using implicit features of the entire voxel-wise white matter fiber strains. Using reconstructed American National Football League (NFL) injury cases, leave-one-out cross-validation was employed to objectively compare injury prediction performances against two baseline machine learning classifiers (support vector machine (SVM) and random forest (RF)) and four scalar metrics via univariate logistic regression (Brain Injury Criterion (BrIC), cumulative strain damage measure of the whole brain (CSDM-WB) and the corpus callosum (CSDM-CC), and peak fiber strain in the CC). Feature-based machine learning classifiers including deep learning, SVM, and RF consistently outperformed all scalar injury metrics across all performance categories (e.g., leave-one-out accuracy of 0.828-0.862 vs. 0.690-0.776, and .632+ error of 0.148-0.176 vs. 0.207-0.292). Further, deep learning achieved the best cross-validation accuracy, sensitivity, AUC, and .632+ error. These findings demonstrate the superior performances of deep learning in concussion prediction and suggest its promise for future applications in biomechanical investigations of traumatic brain injury.

The generalization ability of online SVM classification based on Markov sampling.

PubMed

Xu, Jie; Yan Tang, Yuan; Zou, Bin; Xu, Zongben; Li, Luoqing; Lu, Yang

2015-03-01

In this paper, we consider online support vector machine (SVM) classification learning algorithms with uniformly ergodic Markov chain (u.e.M.c.) samples. We establish the bound on the misclassification error of an online SVM classification algorithm with u.e.M.c. samples based on reproducing kernel Hilbert spaces and obtain a satisfactory convergence rate. We also introduce a novel online SVM classification algorithm based on Markov sampling, and present the numerical studies on the learning ability of online SVM classification based on Markov sampling for benchmark repository. The numerical studies show that the learning performance of the online SVM classification algorithm based on Markov sampling is better than that of classical online SVM classification based on random sampling as the size of training samples is larger.

Aspen, climate, and sudden decline in western USA

Treesearch

Gerald E. Rehfeldt; Dennis E. Ferguson; Nicholas L. Crookston

2009-01-01

A bioclimate model predicting the presence or absence of aspen, Populus tremuloides, in western USA from climate variables was developed by using the Random Forests classification tree on Forest Inventory data from about 118,000 permanent sample plots. A reasonably parsimonious model used eight predictors to describe aspen's climate profile. Classification errors...

Multi-template tensor-based morphometry: Application to analysis of Alzheimer's disease

PubMed Central

Koikkalainen, Juha; Lötjönen, Jyrki; Thurfjell, Lennart; Rueckert, Daniel; Waldemar, Gunhild; Soininen, Hilkka

2012-01-01

In this paper methods for using multiple templates in tensor-based morphometry (TBM) are presented and comparedtothe conventional single-template approach. TBM analysis requires non-rigid registrations which are often subject to registration errors. When using multiple templates and, therefore, multiple registrations, it can be assumed that the registration errors are averaged and eventually compensated. Four different methods are proposed for multi-template TBM. The methods were evaluated using magnetic resonance (MR) images of healthy controls, patients with stable or progressive mild cognitive impairment (MCI), and patients with Alzheimer's disease (AD) from the ADNI database (N=772). The performance of TBM features in classifying images was evaluated both quantitatively and qualitatively. Classification results show that the multi-template methods are statistically significantly better than the single-template method. The overall classification accuracy was 86.0% for the classification of control and AD subjects, and 72.1%for the classification of stable and progressive MCI subjects. The statistical group-level difference maps produced using multi-template TBM were smoother, formed larger continuous regions, and had larger t-values than the maps obtained with single-template TBM. PMID:21419228

Predicting alpine headwater stream intermittency: a case study in the northern Rocky Mountains

USGS Publications Warehouse

Sando, Thomas R.; Blasch, Kyle W.

2015-01-01

This investigation used climatic, geological, and environmental data coupled with observational stream intermittency data to predict alpine headwater stream intermittency. Prediction was made using a random forest classification model. Results showed that the most important variables in the prediction model were snowpack persistence, represented by average snow extent from March through July, mean annual mean monthly minimum temperature, and surface geology types. For stream catchments with intermittent headwater streams, snowpack, on average, persisted until early June, whereas for stream catchments with perennial headwater streams, snowpack, on average, persisted until early July. Additionally, on average, stream catchments with intermittent headwater streams were about 0.7 °C warmer than stream catchments with perennial headwater streams. Finally, headwater stream catchments primarily underlain by coarse, permeable sediment are significantly more likely to have intermittent headwater streams than those primarily underlain by impermeable bedrock. Comparison of the predicted streamflow classification with observed stream status indicated a four percent classification error for first-order streams and a 21 percent classification error for all stream orders in the study area.

A framework for software fault tolerance in real-time systems

NASA Technical Reports Server (NTRS)

Anderson, T.; Knight, J. C.

1983-01-01

A classification scheme for errors and a technique for the provision of software fault tolerance in cyclic real-time systems is presented. The technique requires that the process structure of a system be represented by a synchronization graph which is used by an executive as a specification of the relative times at which they will communicate during execution. Communication between concurrent processes is severely limited and may only take place between processes engaged in an exchange. A history of error occurrences is maintained by an error handler. When an error is detected, the error handler classifies it using the error history information and then initiates appropriate recovery action.

JDINAC: joint density-based non-parametric differential interaction network analysis and classification using high-dimensional sparse omics data.

PubMed

Ji, Jiadong; He, Di; Feng, Yang; He, Yong; Xue, Fuzhong; Xie, Lei

2017-10-01

A complex disease is usually driven by a number of genes interwoven into networks, rather than a single gene product. Network comparison or differential network analysis has become an important means of revealing the underlying mechanism of pathogenesis and identifying clinical biomarkers for disease classification. Most studies, however, are limited to network correlations that mainly capture the linear relationship among genes, or rely on the assumption of a parametric probability distribution of gene measurements. They are restrictive in real application. We propose a new Joint density based non-parametric Differential Interaction Network Analysis and Classification (JDINAC) method to identify differential interaction patterns of network activation between two groups. At the same time, JDINAC uses the network biomarkers to build a classification model. The novelty of JDINAC lies in its potential to capture non-linear relations between molecular interactions using high-dimensional sparse data as well as to adjust confounding factors, without the need of the assumption of a parametric probability distribution of gene measurements. Simulation studies demonstrate that JDINAC provides more accurate differential network estimation and lower classification error than that achieved by other state-of-the-art methods. We apply JDINAC to a Breast Invasive Carcinoma dataset, which includes 114 patients who have both tumor and matched normal samples. The hub genes and differential interaction patterns identified were consistent with existing experimental studies. Furthermore, JDINAC discriminated the tumor and normal sample with high accuracy by virtue of the identified biomarkers. JDINAC provides a general framework for feature selection and classification using high-dimensional sparse omics data. R scripts available at https://github.com/jijiadong/JDINAC. lxie@iscb.org. Supplementary data are available at Bioinformatics online. © The Author (2017). Published by Oxford University Press. All rights reserved. For Permissions, please email: journals.permissions@oup.com

Galaxy And Mass Assembly: automatic morphological classification of galaxies using statistical learning

NASA Astrophysics Data System (ADS)

Sreejith, Sreevarsha; Pereverzyev, Sergiy, Jr.; Kelvin, Lee S.; Marleau, Francine R.; Haltmeier, Markus; Ebner, Judith; Bland-Hawthorn, Joss; Driver, Simon P.; Graham, Alister W.; Holwerda, Benne W.; Hopkins, Andrew M.; Liske, Jochen; Loveday, Jon; Moffett, Amanda J.; Pimbblet, Kevin A.; Taylor, Edward N.; Wang, Lingyu; Wright, Angus H.

2018-03-01

We apply four statistical learning methods to a sample of 7941 galaxies (z < 0.06) from the Galaxy And Mass Assembly survey to test the feasibility of using automated algorithms to classify galaxies. Using 10 features measured for each galaxy (sizes, colours, shape parameters, and stellar mass), we apply the techniques of Support Vector Machines, Classification Trees, Classification Trees with Random Forest (CTRF) and Neural Networks, and returning True Prediction Ratios (TPRs) of 75.8 per cent, 69.0 per cent, 76.2 per cent, and 76.0 per cent, respectively. Those occasions whereby all four algorithms agree with each other yet disagree with the visual classification (`unanimous disagreement') serves as a potential indicator of human error in classification, occurring in ˜ 9 per cent of ellipticals, ˜ 9 per cent of little blue spheroids, ˜ 14 per cent of early-type spirals, ˜ 21 per cent of intermediate-type spirals, and ˜ 4 per cent of late-type spirals and irregulars. We observe that the choice of parameters rather than that of algorithms is more crucial in determining classification accuracy. Due to its simplicity in formulation and implementation, we recommend the CTRF algorithm for classifying future galaxy data sets. Adopting the CTRF algorithm, the TPRs of the five galaxy types are : E, 70.1 per cent; LBS, 75.6 per cent; S0-Sa, 63.6 per cent; Sab-Scd, 56.4 per cent, and Sd-Irr, 88.9 per cent. Further, we train a binary classifier using this CTRF algorithm that divides galaxies into spheroid-dominated (E, LBS, and S0-Sa) and disc-dominated (Sab-Scd and Sd-Irr), achieving an overall accuracy of 89.8 per cent. This translates into an accuracy of 84.9 per cent for spheroid-dominated systems and 92.5 per cent for disc-dominated systems.

Epileptic seizure detection in EEG signal with GModPCA and support vector machine.

PubMed

Jaiswal, Abeg Kumar; Banka, Haider

2017-01-01

Epilepsy is one of the most common neurological disorders caused by recurrent seizures. Electroencephalograms (EEGs) record neural activity and can detect epilepsy. Visual inspection of an EEG signal for epileptic seizure detection is a time-consuming process and may lead to human error; therefore, recently, a number of automated seizure detection frameworks were proposed to replace these traditional methods. Feature extraction and classification are two important steps in these procedures. Feature extraction focuses on finding the informative features that could be used for classification and correct decision-making. Therefore, proposing effective feature extraction techniques for seizure detection is of great significance. Principal Component Analysis (PCA) is a dimensionality reduction technique used in different fields of pattern recognition including EEG signal classification. Global modular PCA (GModPCA) is a variation of PCA. In this paper, an effective framework with GModPCA and Support Vector Machine (SVM) is presented for epileptic seizure detection in EEG signals. The feature extraction is performed with GModPCA, whereas SVM trained with radial basis function kernel performed the classification between seizure and nonseizure EEG signals. Seven different experimental cases were conducted on the benchmark epilepsy EEG dataset. The system performance was evaluated using 10-fold cross-validation. In addition, we prove analytically that GModPCA has less time and space complexities as compared to PCA. The experimental results show that EEG signals have strong inter-sub-pattern correlations. GModPCA and SVM have been able to achieve 100% accuracy for the classification between normal and epileptic signals. Along with this, seven different experimental cases were tested. The classification results of the proposed approach were better than were compared the results of some of the existing methods proposed in literature. It is also found that the time and space complexities of GModPCA are less as compared to PCA. This study suggests that GModPCA and SVM could be used for automated epileptic seizure detection in EEG signal.

Software platform for managing the classification of error- related potentials of observers

NASA Astrophysics Data System (ADS)

Asvestas, P.; Ventouras, E.-C.; Kostopoulos, S.; Sidiropoulos, K.; Korfiatis, V.; Korda, A.; Uzunolglu, A.; Karanasiou, I.; Kalatzis, I.; Matsopoulos, G.

2015-09-01

Human learning is partly based on observation. Electroencephalographic recordings of subjects who perform acts (actors) or observe actors (observers), contain a negative waveform in the Evoked Potentials (EPs) of the actors that commit errors and of observers who observe the error-committing actors. This waveform is called the Error-Related Negativity (ERN). Its detection has applications in the context of Brain-Computer Interfaces. The present work describes a software system developed for managing EPs of observers, with the aim of classifying them into observations of either correct or incorrect actions. It consists of an integrated platform for the storage, management, processing and classification of EPs recorded during error-observation experiments. The system was developed using C# and the following development tools and frameworks: MySQL, .NET Framework, Entity Framework and Emgu CV, for interfacing with the machine learning library of OpenCV. Up to six features can be computed per EP recording per electrode. The user can select among various feature selection algorithms and then proceed to train one of three types of classifiers: Artificial Neural Networks, Support Vector Machines, k-nearest neighbour. Next the classifier can be used for classifying any EP curve that has been inputted to the database.

Multi-factorial analysis of class prediction error: estimating optimal number of biomarkers for various classification rules.

PubMed

Khondoker, Mizanur R; Bachmann, Till T; Mewissen, Muriel; Dickinson, Paul; Dobrzelecki, Bartosz; Campbell, Colin J; Mount, Andrew R; Walton, Anthony J; Crain, Jason; Schulze, Holger; Giraud, Gerard; Ross, Alan J; Ciani, Ilenia; Ember, Stuart W J; Tlili, Chaker; Terry, Jonathan G; Grant, Eilidh; McDonnell, Nicola; Ghazal, Peter

2010-12-01

Machine learning and statistical model based classifiers have increasingly been used with more complex and high dimensional biological data obtained from high-throughput technologies. Understanding the impact of various factors associated with large and complex microarray datasets on the predictive performance of classifiers is computationally intensive, under investigated, yet vital in determining the optimal number of biomarkers for various classification purposes aimed towards improved detection, diagnosis, and therapeutic monitoring of diseases. We investigate the impact of microarray based data characteristics on the predictive performance for various classification rules using simulation studies. Our investigation using Random Forest, Support Vector Machines, Linear Discriminant Analysis and k-Nearest Neighbour shows that the predictive performance of classifiers is strongly influenced by training set size, biological and technical variability, replication, fold change and correlation between biomarkers. Optimal number of biomarkers for a classification problem should therefore be estimated taking account of the impact of all these factors. A database of average generalization errors is built for various combinations of these factors. The database of generalization errors can be used for estimating the optimal number of biomarkers for given levels of predictive accuracy as a function of these factors. Examples show that curves from actual biological data resemble that of simulated data with corresponding levels of data characteristics. An R package optBiomarker implementing the method is freely available for academic use from the Comprehensive R Archive Network (http://www.cran.r-project.org/web/packages/optBiomarker/).

Quantitative morphometrical characterization of human pronuclear zygotes.

PubMed

Beuchat, A; Thévenaz, P; Unser, M; Ebner, T; Senn, A; Urner, F; Germond, M; Sorzano, C O S

2008-09-01

Identification of embryos with high implantation potential remains a challenge in in vitro fertilization (IVF). Subjective pronuclear (PN) zygote scoring systems have been developed for that purpose. The aim of this work was to provide a software tool that enables objective measuring of morphological characteristics of the human PN zygote. A computer program was created to analyse zygote images semi-automatically, providing precise morphological measurements. The accuracy of this approach was first validated by comparing zygotes from two different IVF centres with computer-assisted measurements or subjective scoring. Computer-assisted measurement and subjective scoring were then compared for their ability to classify zygotes with high and low implantation probability by using a linear discriminant analysis. Zygote images coming from the two IVF centres were analysed with the software, resulting in a series of precise measurements of 24 variables. Using subjective scoring, the cytoplasmic halo was the only feature which was significantly different between the two IVF centres. Computer-assisted measurements revealed significant differences between centres in PN centring, PN proximity, cytoplasmic halo and features related to nucleolar precursor bodies distribution. The zygote classification error achieved with the computer-assisted measurements (0.363) was slightly inferior to that of the subjective ones (0.393). A precise and objective characterization of the morphology of human PN zygotes can be achieved by the use of an advanced image analysis tool. This computer-assisted analysis allows for a better morphological characterization of human zygotes and can be used for classification.

Detection of Periodic Leg Movements by Machine Learning Methods Using Polysomnographic Parameters Other Than Leg Electromyography

PubMed Central

Umut, İlhan; Çentik, Güven

2016-01-01

The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, K-nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while K-nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present. PMID:27213008

Detection of Periodic Leg Movements by Machine Learning Methods Using Polysomnographic Parameters Other Than Leg Electromyography.

PubMed

Umut, İlhan; Çentik, Güven

2016-01-01

The number of channels used for polysomnographic recording frequently causes difficulties for patients because of the many cables connected. Also, it increases the risk of having troubles during recording process and increases the storage volume. In this study, it is intended to detect periodic leg movement (PLM) in sleep with the use of the channels except leg electromyography (EMG) by analysing polysomnography (PSG) data with digital signal processing (DSP) and machine learning methods. PSG records of 153 patients of different ages and genders with PLM disorder diagnosis were examined retrospectively. A novel software was developed for the analysis of PSG records. The software utilizes the machine learning algorithms, statistical methods, and DSP methods. In order to classify PLM, popular machine learning methods (multilayer perceptron, K-nearest neighbour, and random forests) and logistic regression were used. Comparison of classified results showed that while K-nearest neighbour classification algorithm had higher average classification rate (91.87%) and lower average classification error value (RMSE = 0.2850), multilayer perceptron algorithm had the lowest average classification rate (83.29%) and the highest average classification error value (RMSE = 0.3705). Results showed that PLM can be classified with high accuracy (91.87%) without leg EMG record being present.

Effects of stress typicality during speeded grammatical classification.

PubMed

Arciuli, Joanne; Cupples, Linda

2003-01-01

The experiments reported here were designed to investigate the influence of stress typicality during speeded grammatical classification of disyllabic English words by native and non-native speakers. Trochaic nouns and iambic gram verbs were considered to be typically stressed, whereas iambic nouns and trochaic verbs were considered to be atypically stressed. Experiments 1a and 2a showed that while native speakers classified typically stressed words individual more quickly and more accurately than atypically stressed words during differences reading, there were no overall effects during classification of spoken stimuli. However, a subgroup of native speakers with high error rates did show a significant effect during classification of spoken stimuli. Experiments 1b and 2b showed that non-native speakers classified typically stressed words more quickly and more accurately than atypically stressed words during reading. Typically stressed words were classified more accurately than atypically stressed words when the stimuli were spoken. Importantly, there was a significant relationship between error rates, vocabulary size and the size of the stress typicality effect in each experiment. We conclude that participants use information about lexical stress to help them distinguish between disyllabic nouns and verbs during speeded grammatical classification. This is especially so for individuals with a limited vocabulary who lack other knowledge (e.g., semantic knowledge) about the differences between these grammatical categories.

Automatic classification of diseases from free-text death certificates for real-time surveillance.

PubMed

Koopman, Bevan; Karimi, Sarvnaz; Nguyen, Anthony; McGuire, Rhydwyn; Muscatello, David; Kemp, Madonna; Truran, Donna; Zhang, Ming; Thackway, Sarah

2015-07-15

Death certificates provide an invaluable source for mortality statistics which can be used for surveillance and early warnings of increases in disease activity and to support the development and monitoring of prevention or response strategies. However, their value can be realised only if accurate, quantitative data can be extracted from death certificates, an aim hampered by both the volume and variable nature of certificates written in natural language. This study aims to develop a set of machine learning and rule-based methods to automatically classify death certificates according to four high impact diseases of interest: diabetes, influenza, pneumonia and HIV. Two classification methods are presented: i) a machine learning approach, where detailed features (terms, term n-grams and SNOMED CT concepts) are extracted from death certificates and used to train a set of supervised machine learning models (Support Vector Machines); and ii) a set of keyword-matching rules. These methods were used to identify the presence of diabetes, influenza, pneumonia and HIV in a death certificate. An empirical evaluation was conducted using 340,142 death certificates, divided between training and test sets, covering deaths from 2000-2007 in New South Wales, Australia. Precision and recall (positive predictive value and sensitivity) were used as evaluation measures, with F-measure providing a single, overall measure of effectiveness. A detailed error analysis was performed on classification errors. Classification of diabetes, influenza, pneumonia and HIV was highly accurate (F-measure 0.96). More fine-grained ICD-10 classification effectiveness was more variable but still high (F-measure 0.80). The error analysis revealed that word variations as well as certain word combinations adversely affected classification. In addition, anomalies in the ground truth likely led to an underestimation of the effectiveness. The high accuracy and low cost of the classification methods allow for an effective means for automatic and real-time surveillance of diabetes, influenza, pneumonia and HIV deaths. In addition, the methods are generally applicable to other diseases of interest and to other sources of medical free-text besides death certificates.

The Effect of Error Correction vs. Error Detection on Iranian Pre-Intermediate EFL Learners' Writing Achievement

ERIC Educational Resources Information Center

Abedi, Razie; Latifi, Mehdi; Moinzadeh, Ahmad

2010-01-01

This study tries to answer some ever-existent questions in writing fields regarding approaching the most effective ways to give feedback to students' errors in writing by comparing the effect of error correction and error detection on the improvement of students' writing ability. In order to achieve this goal, 60 pre-intermediate English learners…

Measures of Linguistic Accuracy in Second Language Writing Research.

ERIC Educational Resources Information Center

Polio, Charlene G.

1997-01-01

Investigates the reliability of measures of linguistic accuracy in second language writing. The study uses a holistic scale, error-free T-units, and an error classification system on the essays of English-as-a-Second-Language students and discusses why disagreements arise within a rater and between raters. (24 references) (Author/CK)

[Study of inversion and classification of particle size distribution under dependent model algorithm].

PubMed

Sun, Xiao-Gang; Tang, Hong; Yuan, Gui-Bin

2008-05-01

For the total light scattering particle sizing technique, an inversion and classification method was proposed with the dependent model algorithm. The measured particle system was inversed simultaneously by different particle distribution functions whose mathematic model was known in advance, and then classified according to the inversion errors. The simulation experiments illustrated that it is feasible to use the inversion errors to determine the particle size distribution. The particle size distribution function was obtained accurately at only three wavelengths in the visible light range with the genetic algorithm, and the inversion results were steady and reliable, which decreased the number of multi wavelengths to the greatest extent and increased the selectivity of light source. The single peak distribution inversion error was less than 5% and the bimodal distribution inversion error was less than 10% when 5% stochastic noise was put in the transmission extinction measurement values at two wavelengths. The running time of this method was less than 2 s. The method has advantages of simplicity, rapidity, and suitability for on-line particle size measurement.

Classification accuracy for stratification with remotely sensed data

Treesearch

Raymond L. Czaplewski; Paul L. Patterson

2003-01-01

Tools are developed that help specify the classification accuracy required from remotely sensed data. These tools are applied during the planning stage of a sample survey that will use poststratification, prestratification with proportional allocation, or double sampling for stratification. Accuracy standards are developed in terms of an “error matrix,” which is...

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.

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.

On the statistical assessment of classifiers using DNA microarray data

PubMed Central

Ancona, N; Maglietta, R; Piepoli, A; D'Addabbo, A; Cotugno, R; Savino, M; Liuni, S; Carella, M; Pesole, G; Perri, F

2006-01-01

Background In this paper we present a method for the statistical assessment of cancer predictors which make use of gene expression profiles. The methodology is applied to a new data set of microarray gene expression data collected in Casa Sollievo della Sofferenza Hospital, Foggia – Italy. The data set is made up of normal (22) and tumor (25) specimens extracted from 25 patients affected by colon cancer. We propose to give answers to some questions which are relevant for the automatic diagnosis of cancer such as: Is the size of the available data set sufficient to build accurate classifiers? What is the statistical significance of the associated error rates? In what ways can accuracy be considered dependant on the adopted classification scheme? How many genes are correlated with the pathology and how many are sufficient for an accurate colon cancer classification? The method we propose answers these questions whilst avoiding the potential pitfalls hidden in the analysis and interpretation of microarray data. Results We estimate the generalization error, evaluated through the Leave-K-Out Cross Validation error, for three different classification schemes by varying the number of training examples and the number of the genes used. The statistical significance of the error rate is measured by using a permutation test. We provide a statistical analysis in terms of the frequencies of the genes involved in the classification. Using the whole set of genes, we found that the Weighted Voting Algorithm (WVA) classifier learns the distinction between normal and tumor specimens with 25 training examples, providing e = 21% (p = 0.045) as an error rate. This remains constant even when the number of examples increases. Moreover, Regularized Least Squares (RLS) and Support Vector Machines (SVM) classifiers can learn with only 15 training examples, with an error rate of e = 19% (p = 0.035) and e = 18% (p = 0.037) respectively. Moreover, the error rate decreases as the training set size increases, reaching its best performances with 35 training examples. In this case, RLS and SVM have error rates of e = 14% (p = 0.027) and e = 11% (p = 0.019). Concerning the number of genes, we found about 6000 genes (p < 0.05) correlated with the pathology, resulting from the signal-to-noise statistic. Moreover the performances of RLS and SVM classifiers do not change when 74% of genes is used. They progressively reduce up to e = 16% (p < 0.05) when only 2 genes are employed. The biological relevance of a set of genes determined by our statistical analysis and the major roles they play in colorectal tumorigenesis is discussed. Conclusions The method proposed provides statistically significant answers to precise questions relevant for the diagnosis and prognosis of cancer. We found that, with as few as 15 examples, it is possible to train statistically significant classifiers for colon cancer diagnosis. As for the definition of the number of genes sufficient for a reliable classification of colon cancer, our results suggest that it depends on the accuracy required. PMID:16919171

Error Patterns with Fraction Calculations at Fourth Grade as a Function of Students' Mathematics Achievement Status

ERIC Educational Resources Information Center

Schumacher, Robin F.; Malone, Amelia S.

2017-01-01

The goal of this study was to describe fraction-calculation errors among fourth-grade students and to determine whether error patterns differed as a function of problem type (addition vs. subtraction; like vs. unlike denominators), orientation (horizontal vs. vertical), or mathematics-achievement status (low-, average-, or high-achieving). We…

Speech variability effects on recognition accuracy associated with concurrent task performance by pilots

NASA Technical Reports Server (NTRS)

Simpson, C. A.

1985-01-01

In the present study of the responses of pairs of pilots to aircraft warning classification tasks using an isolated word, speaker-dependent speech recognition system, the induced stress was manipulated by means of different scoring procedures for the classification task and by the inclusion of a competitive manual control task. Both speech patterns and recognition accuracy were analyzed, and recognition errors were recorded by type for an isolated word speaker-dependent system and by an offline technique for a connected word speaker-dependent system. While errors increased with task loading for the isolated word system, there was no such effect for task loading in the case of the connected word system.

The pot calling the kettle black: the extent and type of errors in a computerized immunization registry and by parent report.

PubMed

MacDonald, Shannon E; Schopflocher, Donald P; Golonka, Richard P

2014-01-04

Accurate classification of children's immunization status is essential for clinical care, administration and evaluation of immunization programs, and vaccine program research. Computerized immunization registries have been proposed as a valuable alternative to provider paper records or parent report, but there is a need to better understand the challenges associated with their use. This study assessed the accuracy of immunization status classification in an immunization registry as compared to parent report and determined the number and type of errors occurring in both sources. This study was a sub-analysis of a larger study which compared the characteristics of children whose immunizations were up to date (UTD) at two years as compared to those not UTD. Children's immunization status was initially determined from a population-based immunization registry, and then compared to parent report of immunization status, as reported in a postal survey. Discrepancies between the two sources were adjudicated by review of immunization providers' hard-copy clinic records. Descriptive analyses included calculating proportions and confidence intervals for errors in classification and reporting of the type and frequency of errors. Among the 461 survey respondents, there were 60 discrepancies in immunization status. The majority of errors were due to parent report (n = 44), but the registry was not without fault (n = 16). Parents tended to erroneously report their child as UTD, whereas the registry was more likely to wrongly classify children as not UTD. Reasons for registry errors included failure to account for varicella disease history, variable number of doses required due to age at series initiation, and doses administered out of the region. These results confirm that parent report is often flawed, but also identify that registries are prone to misclassification of immunization status. Immunization program administrators and researchers need to institute measures to identify and reduce misclassification, in order for registries to play an effective role in the control of vaccine-preventable disease.

The pot calling the kettle black: the extent and type of errors in a computerized immunization registry and by parent report

PubMed Central

2014-01-01

Background Accurate classification of children’s immunization status is essential for clinical care, administration and evaluation of immunization programs, and vaccine program research. Computerized immunization registries have been proposed as a valuable alternative to provider paper records or parent report, but there is a need to better understand the challenges associated with their use. This study assessed the accuracy of immunization status classification in an immunization registry as compared to parent report and determined the number and type of errors occurring in both sources. Methods This study was a sub-analysis of a larger study which compared the characteristics of children whose immunizations were up to date (UTD) at two years as compared to those not UTD. Children’s immunization status was initially determined from a population-based immunization registry, and then compared to parent report of immunization status, as reported in a postal survey. Discrepancies between the two sources were adjudicated by review of immunization providers’ hard-copy clinic records. Descriptive analyses included calculating proportions and confidence intervals for errors in classification and reporting of the type and frequency of errors. Results Among the 461 survey respondents, there were 60 discrepancies in immunization status. The majority of errors were due to parent report (n = 44), but the registry was not without fault (n = 16). Parents tended to erroneously report their child as UTD, whereas the registry was more likely to wrongly classify children as not UTD. Reasons for registry errors included failure to account for varicella disease history, variable number of doses required due to age at series initiation, and doses administered out of the region. Conclusions These results confirm that parent report is often flawed, but also identify that registries are prone to misclassification of immunization status. Immunization program administrators and researchers need to institute measures to identify and reduce misclassification, in order for registries to play an effective role in the control of vaccine-preventable disease. PMID:24387002

Bayesian Network Structure Learning for Urban Land Use Classification from Landsat ETM+ and Ancillary Data

NASA Astrophysics Data System (ADS)

Park, M.; Stenstrom, M. K.

2004-12-01

Recognizing urban information from the satellite imagery is problematic due to the diverse features and dynamic changes of urban landuse. The use of Landsat imagery for urban land use classification involves inherent uncertainty due to its spatial resolution and the low separability among land uses. To resolve the uncertainty problem, we investigated the performance of Bayesian networks to classify urban land use since Bayesian networks provide a quantitative way of handling uncertainty and have been successfully used in many areas. In this study, we developed the optimized networks for urban land use classification from Landsat ETM+ images of Marina del Rey area based on USGS land cover/use classification level III. The networks started from a tree structure based on mutual information between variables and added the links to improve accuracy. This methodology offers several advantages: (1) The network structure shows the dependency relationships between variables. The class node value can be predicted even with particular band information missing due to sensor system error. The missing information can be inferred from other dependent bands. (2) The network structure provides information of variables that are important for the classification, which is not available from conventional classification methods such as neural networks and maximum likelihood classification. In our case, for example, bands 1, 5 and 6 are the most important inputs in determining the land use of each pixel. (3) The networks can be reduced with those input variables important for classification. This minimizes the problem without considering all possible variables. We also examined the effect of incorporating ancillary data: geospatial information such as X and Y coordinate values of each pixel and DEM data, and vegetation indices such as NDVI and Tasseled Cap transformation. The results showed that the locational information improved overall accuracy (81%) and kappa coefficient (76%), and lowered the omission and commission errors compared with using only spectral data (accuracy 71%, kappa coefficient 62%). Incorporating DEM data did not significantly improve overall accuracy (74%) and kappa coefficient (66%) but lowered the omission and commission errors. Incorporating NDVI did not much improve the overall accuracy (72%) and k coefficient (65%). Including Tasseled Cap transformation reduced the accuracy (accuracy 70%, kappa 61%). Therefore, additional information from the DEM and vegetation indices was not useful as locational ancillary data.

Vector quantizer designs for joint compression and terrain categorization of multispectral imagery

NASA Technical Reports Server (NTRS)

Gorman, John D.; Lyons, Daniel F.

1994-01-01

Two vector quantizer designs for compression of multispectral imagery and their impact on terrain categorization performance are evaluated. The mean-squared error (MSE) and classification performance of the two quantizers are compared, and it is shown that a simple two-stage design minimizing MSE subject to a constraint on classification performance has a significantly better classification performance than a standard MSE-based tree-structured vector quantizer followed by maximum likelihood classification. This improvement in classification performance is obtained with minimal loss in MSE performance. The results show that it is advantageous to tailor compression algorithm designs to the required data exploitation tasks. Applications of joint compression/classification include compression for the archival or transmission of Landsat imagery that is later used for land utility surveys and/or radiometric analysis.

Training sample selection based on self-training for liver cirrhosis classification using ultrasound images

NASA Astrophysics Data System (ADS)

Fujita, Yusuke; Mitani, Yoshihiro; Hamamoto, Yoshihiko; Segawa, Makoto; Terai, Shuji; Sakaida, Isao

2017-03-01

Ultrasound imaging is a popular and non-invasive tool used in the diagnoses of liver disease. Cirrhosis is a chronic liver disease and it can advance to liver cancer. Early detection and appropriate treatment are crucial to prevent liver cancer. However, ultrasound image analysis is very challenging, because of the low signal-to-noise ratio of ultrasound images. To achieve the higher classification performance, selection of training regions of interest (ROIs) is very important that effect to classification accuracy. The purpose of our study is cirrhosis detection with high accuracy using liver ultrasound images. In our previous works, training ROI selection by MILBoost and multiple-ROI classification based on the product rule had been proposed, to achieve high classification performance. In this article, we propose self-training method to select training ROIs effectively. Evaluation experiments were performed to evaluate effect of self-training, using manually selected ROIs and also automatically selected ROIs. Experimental results show that self-training for manually selected ROIs achieved higher classification performance than other approaches, including our conventional methods. The manually ROI definition and sample selection are important to improve classification accuracy in cirrhosis detection using ultrasound images.

Autonomous target recognition using remotely sensed surface vibration measurements

NASA Astrophysics Data System (ADS)

Geurts, James; Ruck, Dennis W.; Rogers, Steven K.; Oxley, Mark E.; Barr, Dallas N.

1993-09-01

The remotely measured surface vibration signatures of tactical military ground vehicles are investigated for use in target classification and identification friend or foe (IFF) systems. The use of remote surface vibration sensing by a laser radar reduces the effects of partial occlusion, concealment, and camouflage experienced by automatic target recognition systems using traditional imagery in a tactical battlefield environment. Linear Predictive Coding (LPC) efficiently represents the vibration signatures and nearest neighbor classifiers exploit the LPC feature set using a variety of distortion metrics. Nearest neighbor classifiers achieve an 88 percent classification rate in an eight class problem, representing a classification performance increase of thirty percent from previous efforts. A novel confidence figure of merit is implemented to attain a 100 percent classification rate with less than 60 percent rejection. The high classification rates are achieved on a target set which would pose significant problems to traditional image-based recognition systems. The targets are presented to the sensor in a variety of aspects and engine speeds at a range of 1 kilometer. The classification rates achieved demonstrate the benefits of using remote vibration measurement in a ground IFF system. The signature modeling and classification system can also be used to identify rotary and fixed-wing targets.

Automated compound classification using a chemical ontology.

PubMed

Bobach, Claudia; Böhme, Timo; Laube, Ulf; Püschel, Anett; Weber, Lutz

2012-12-29

Classification of chemical compounds into compound classes by using structure derived descriptors is a well-established method to aid the evaluation and abstraction of compound properties in chemical compound databases. MeSH and recently ChEBI are examples of chemical ontologies that provide a hierarchical classification of compounds into general compound classes of biological interest based on their structural as well as property or use features. In these ontologies, compounds have been assigned manually to their respective classes. However, with the ever increasing possibilities to extract new compounds from text documents using name-to-structure tools and considering the large number of compounds deposited in databases, automated and comprehensive chemical classification methods are needed to avoid the error prone and time consuming manual classification of compounds. In the present work we implement principles and methods to construct a chemical ontology of classes that shall support the automated, high-quality compound classification in chemical databases or text documents. While SMARTS expressions have already been used to define chemical structure class concepts, in the present work we have extended the expressive power of such class definitions by expanding their structure-based reasoning logic. Thus, to achieve the required precision and granularity of chemical class definitions, sets of SMARTS class definitions are connected by OR and NOT logical operators. In addition, AND logic has been implemented to allow the concomitant use of flexible atom lists and stereochemistry definitions. The resulting chemical ontology is a multi-hierarchical taxonomy of concept nodes connected by directed, transitive relationships. A proposal for a rule based definition of chemical classes has been made that allows to define chemical compound classes more precisely than before. The proposed structure-based reasoning logic allows to translate chemistry expert knowledge into a computer interpretable form, preventing erroneous compound assignments and allowing automatic compound classification. The automated assignment of compounds in databases, compound structure files or text documents to their related ontology classes is possible through the integration with a chemical structure search engine. As an application example, the annotation of chemical structure files with a prototypic ontology is demonstrated.

Automated compound classification using a chemical ontology

PubMed Central

2012-01-01

Background Classification of chemical compounds into compound classes by using structure derived descriptors is a well-established method to aid the evaluation and abstraction of compound properties in chemical compound databases. MeSH and recently ChEBI are examples of chemical ontologies that provide a hierarchical classification of compounds into general compound classes of biological interest based on their structural as well as property or use features. In these ontologies, compounds have been assigned manually to their respective classes. However, with the ever increasing possibilities to extract new compounds from text documents using name-to-structure tools and considering the large number of compounds deposited in databases, automated and comprehensive chemical classification methods are needed to avoid the error prone and time consuming manual classification of compounds. Results In the present work we implement principles and methods to construct a chemical ontology of classes that shall support the automated, high-quality compound classification in chemical databases or text documents. While SMARTS expressions have already been used to define chemical structure class concepts, in the present work we have extended the expressive power of such class definitions by expanding their structure-based reasoning logic. Thus, to achieve the required precision and granularity of chemical class definitions, sets of SMARTS class definitions are connected by OR and NOT logical operators. In addition, AND logic has been implemented to allow the concomitant use of flexible atom lists and stereochemistry definitions. The resulting chemical ontology is a multi-hierarchical taxonomy of concept nodes connected by directed, transitive relationships. Conclusions A proposal for a rule based definition of chemical classes has been made that allows to define chemical compound classes more precisely than before. The proposed structure-based reasoning logic allows to translate chemistry expert knowledge into a computer interpretable form, preventing erroneous compound assignments and allowing automatic compound classification. The automated assignment of compounds in databases, compound structure files or text documents to their related ontology classes is possible through the integration with a chemical structure search engine. As an application example, the annotation of chemical structure files with a prototypic ontology is demonstrated. PMID:23273256

Medication errors: definitions and classification

PubMed Central

Aronson, Jeffrey K

2009-01-01

To understand medication errors and to identify preventive strategies, we need to classify them and define the terms that describe them. The four main approaches to defining technical terms consider etymology, usage, previous definitions, and the Ramsey–Lewis method (based on an understanding of theory and practice). A medication error is ‘a failure in the treatment process that leads to, or has the potential to lead to, harm to the patient’. Prescribing faults, a subset of medication errors, should be distinguished from prescription errors. A prescribing fault is ‘a failure in the prescribing [decision-making] process that leads to, or has the potential to lead to, harm to the patient’. The converse of this, ‘balanced prescribing’ is ‘the use of a medicine that is appropriate to the patient's condition and, within the limits created by the uncertainty that attends therapeutic decisions, in a dosage regimen that optimizes the balance of benefit to harm’. This excludes all forms of prescribing faults, such as irrational, inappropriate, and ineffective prescribing, underprescribing and overprescribing. A prescription error is ‘a failure in the prescription writing process that results in a wrong instruction about one or more of the normal features of a prescription’. The ‘normal features’ include the identity of the recipient, the identity of the drug, the formulation, dose, route, timing, frequency, and duration of administration. Medication errors can be classified, invoking psychological theory, as knowledge-based mistakes, rule-based mistakes, action-based slips, and memory-based lapses. This classification informs preventive strategies. PMID:19594526

Classification of edible oils and modeling of their physico-chemical properties by chemometric methods using mid-IR spectroscopy

NASA Astrophysics Data System (ADS)

Luna, Aderval S.; da Silva, Arnaldo P.; Ferré, Joan; Boqué, Ricard

This research work describes two studies for the classification and characterization of edible oils and its quality parameters through Fourier transform mid infrared spectroscopy (FT-mid-IR) together with chemometric methods. The discrimination of canola, sunflower, corn and soybean oils was investigated using SVM-DA, SIMCA and PLS-DA. Using FT-mid-IR, DPLS was able to classify 100% of the samples from the validation set, but SIMCA and SVM-DA were not. The quality parameters: refraction index and relative density of edible oils were obtained from reference methods. Prediction models for FT-mid-IR spectra were calculated for these quality parameters using partial least squares (PLS) and support vector machines (SVM). Several preprocessing alternatives (first derivative, multiplicative scatter correction, mean centering, and standard normal variate) were investigated. The best result for the refraction index was achieved with SVM as well as for the relative density except when the preprocessing combination of mean centering and first derivative was used. For both of quality parameters, the best results obtained for the figures of merit expressed by the root mean square error of cross validation (RMSECV) and prediction (RMSEP) were equal to 0.0001.

Feature extraction using extrema sampling of discrete derivatives for spike sorting in implantable upper-limb neural prostheses.

PubMed

Zamani, Majid; Demosthenous, Andreas

2014-07-01

Next generation neural interfaces for upper-limb (and other) prostheses aim to develop implantable interfaces for one or more nerves, each interface having many neural signal channels that work reliably in the stump without harming the nerves. To achieve real-time multi-channel processing it is important to integrate spike sorting on-chip to overcome limitations in transmission bandwidth. This requires computationally efficient algorithms for feature extraction and clustering suitable for low-power hardware implementation. This paper describes a new feature extraction method for real-time spike sorting based on extrema analysis (namely positive peaks and negative peaks) of spike shapes and their discrete derivatives at different frequency bands. Employing simulation across different datasets, the accuracy and computational complexity of the proposed method are assessed and compared with other methods. The average classification accuracy of the proposed method in conjunction with online sorting (O-Sort) is 91.6%, outperforming all the other methods tested with the O-Sort clustering algorithm. The proposed method offers a better tradeoff between classification error and computational complexity, making it a particularly strong choice for on-chip spike sorting.

Artificial neuron-glia networks learning approach based on cooperative coevolution.

PubMed

Mesejo, Pablo; Ibáñez, Oscar; Fernández-Blanco, Enrique; Cedrón, Francisco; Pazos, Alejandro; Porto-Pazos, Ana B

2015-06-01

Artificial Neuron-Glia Networks (ANGNs) are a novel bio-inspired machine learning approach. They extend classical Artificial Neural Networks (ANNs) by incorporating recent findings and suppositions about the way information is processed by neural and astrocytic networks in the most evolved living organisms. Although ANGNs are not a consolidated method, their performance against the traditional approach, i.e. without artificial astrocytes, was already demonstrated on classification problems. However, the corresponding learning algorithms developed so far strongly depends on a set of glial parameters which are manually tuned for each specific problem. As a consequence, previous experimental tests have to be done in order to determine an adequate set of values, making such manual parameter configuration time-consuming, error-prone, biased and problem dependent. Thus, in this paper, we propose a novel learning approach for ANGNs that fully automates the learning process, and gives the possibility of testing any kind of reasonable parameter configuration for each specific problem. This new learning algorithm, based on coevolutionary genetic algorithms, is able to properly learn all the ANGNs parameters. Its performance is tested on five classification problems achieving significantly better results than ANGN and competitive results with ANN approaches.

Intermittent Demand Forecasting in a Tertiary Pediatric Intensive Care Unit.

PubMed

Cheng, Chen-Yang; Chiang, Kuo-Liang; Chen, Meng-Yin

2016-10-01

Forecasts of the demand for medical supplies both directly and indirectly affect the operating costs and the quality of the care provided by health care institutions. Specifically, overestimating demand induces an inventory surplus, whereas underestimating demand possibly compromises patient safety. Uncertainty in forecasting the consumption of medical supplies generates intermittent demand events. The intermittent demand patterns for medical supplies are generally classified as lumpy, erratic, smooth, and slow-moving demand. This study was conducted with the purpose of advancing a tertiary pediatric intensive care unit's efforts to achieve a high level of accuracy in its forecasting of the demand for medical supplies. On this point, several demand forecasting methods were compared in terms of the forecast accuracy of each. The results confirm that applying Croston's method combined with a single exponential smoothing method yields the most accurate results for forecasting lumpy, erratic, and slow-moving demand, whereas the Simple Moving Average (SMA) method is the most suitable for forecasting smooth demand. In addition, when the classification of demand consumption patterns were combined with the demand forecasting models, the forecasting errors were minimized, indicating that this classification framework can play a role in improving patient safety and reducing inventory management costs in health care institutions.

Linear and Order Statistics Combiners for Pattern Classification

NASA Technical Reports Server (NTRS)

Tumer, Kagan; Ghosh, Joydeep; Lau, Sonie (Technical Monitor)

2001-01-01

Several researchers have experimentally shown that substantial improvements can be obtained in difficult pattern recognition problems by combining or integrating the outputs of multiple classifiers. This chapter provides an analytical framework to quantify the improvements in classification results due to combining. The results apply to both linear combiners and order statistics combiners. We first show that to a first order approximation, the error rate obtained over and above the Bayes error rate, is directly proportional to the variance of the actual decision boundaries around the Bayes optimum boundary. Combining classifiers in output space reduces this variance, and hence reduces the 'added' error. If N unbiased classifiers are combined by simple averaging. the added error rate can be reduced by a factor of N if the individual errors in approximating the decision boundaries are uncorrelated. Expressions are then derived for linear combiners which are biased or correlated, and the effect of output correlations on ensemble performance is quantified. For order statistics based non-linear combiners, we derive expressions that indicate how much the median, the maximum and in general the i-th order statistic can improve classifier performance. The analysis presented here facilitates the understanding of the relationships among error rates, classifier boundary distributions, and combining in output space. Experimental results on several public domain data sets are provided to illustrate the benefits of combining and to support the analytical results.

Precise-spike-driven synaptic plasticity: learning hetero-association of spatiotemporal spike patterns.

PubMed

Yu, Qiang; Tang, Huajin; Tan, Kay Chen; Li, Haizhou

2013-01-01

A new learning rule (Precise-Spike-Driven (PSD) Synaptic Plasticity) is proposed for processing and memorizing spatiotemporal patterns. PSD is a supervised learning rule that is analytically derived from the traditional Widrow-Hoff rule and can be used to train neurons to associate an input spatiotemporal spike pattern with a desired spike train. Synaptic adaptation is driven by the error between the desired and the actual output spikes, with positive errors causing long-term potentiation and negative errors causing long-term depression. The amount of modification is proportional to an eligibility trace that is triggered by afferent spikes. The PSD rule is both computationally efficient and biologically plausible. The properties of this learning rule are investigated extensively through experimental simulations, including its learning performance, its generality to different neuron models, its robustness against noisy conditions, its memory capacity, and the effects of its learning parameters. Experimental results show that the PSD rule is capable of spatiotemporal pattern classification, and can even outperform a well studied benchmark algorithm with the proposed relative confidence criterion. The PSD rule is further validated on a practical example of an optical character recognition problem. The results again show that it can achieve a good recognition performance with a proper encoding. Finally, a detailed discussion is provided about the PSD rule and several related algorithms including tempotron, SPAN, Chronotron and ReSuMe.

Precise-Spike-Driven Synaptic Plasticity: Learning Hetero-Association of Spatiotemporal Spike Patterns

PubMed Central

Yu, Qiang; Tang, Huajin; Tan, Kay Chen; Li, Haizhou

2013-01-01

A new learning rule (Precise-Spike-Driven (PSD) Synaptic Plasticity) is proposed for processing and memorizing spatiotemporal patterns. PSD is a supervised learning rule that is analytically derived from the traditional Widrow-Hoff rule and can be used to train neurons to associate an input spatiotemporal spike pattern with a desired spike train. Synaptic adaptation is driven by the error between the desired and the actual output spikes, with positive errors causing long-term potentiation and negative errors causing long-term depression. The amount of modification is proportional to an eligibility trace that is triggered by afferent spikes. The PSD rule is both computationally efficient and biologically plausible. The properties of this learning rule are investigated extensively through experimental simulations, including its learning performance, its generality to different neuron models, its robustness against noisy conditions, its memory capacity, and the effects of its learning parameters. Experimental results show that the PSD rule is capable of spatiotemporal pattern classification, and can even outperform a well studied benchmark algorithm with the proposed relative confidence criterion. The PSD rule is further validated on a practical example of an optical character recognition problem. The results again show that it can achieve a good recognition performance with a proper encoding. Finally, a detailed discussion is provided about the PSD rule and several related algorithms including tempotron, SPAN, Chronotron and ReSuMe. PMID:24223789

Spinal intra-operative three-dimensional navigation with infra-red tool tracking: correlation between clinical and absolute engineering accuracy

NASA Astrophysics Data System (ADS)

Guha, Daipayan; Jakubovic, Raphael; Gupta, Shaurya; Yang, Victor X. D.

2017-02-01

Computer-assisted navigation (CAN) may guide spinal surgeries, reliably reducing screw breach rates. Definitions of screw breach, if reported, vary widely across studies. Absolute quantitative error is theoretically a more precise and generalizable metric of navigation accuracy, but has been computed variably and reported in fewer than 25% of clinical studies of CAN-guided pedicle screw accuracy. We reviewed a prospectively-collected series of 209 pedicle screws placed with CAN guidance to characterize the correlation between clinical pedicle screw accuracy, based on postoperative imaging, and absolute quantitative navigation accuracy. We found that acceptable screw accuracy was achieved for significantly fewer screws based on 2mm grade vs. Heary grade, particularly in the lumbar spine. Inter-rater agreement was good for the Heary classification and moderate for the 2mm grade, significantly greater among radiologists than surgeon raters. Mean absolute translational/angular accuracies were 1.75mm/3.13° and 1.20mm/3.64° in the axial and sagittal planes, respectively. There was no correlation between clinical and absolute navigation accuracy, in part because surgeons appear to compensate for perceived translational navigation error by adjusting screw medialization angle. Future studies of navigation accuracy should therefore report absolute translational and angular errors. Clinical screw grades based on post-operative imaging, if reported, may be more reliable if performed in multiple by radiologist raters.

Wetland Assessment Using Unmanned Aerial Vehicle (uav) Photogrammetry

NASA Astrophysics Data System (ADS)

Boon, M. A.; Greenfield, R.; Tesfamichael, S.

2016-06-01

The use of Unmanned Arial Vehicle (UAV) photogrammetry is a valuable tool to enhance our understanding of wetlands. Accurate planning derived from this technological advancement allows for more effective management and conservation of wetland areas. This paper presents results of a study that aimed at investigating the use of UAV photogrammetry as a tool to enhance the assessment of wetland ecosystems. The UAV images were collected during a single flight within 2½ hours over a 100 ha area at the Kameelzynkraal farm, Gauteng Province, South Africa. An AKS Y-6 MKII multi-rotor UAV and a digital camera on a motion compensated gimbal mount were utilised for the survey. Twenty ground control points (GCPs) were surveyed using a Trimble GPS to achieve geometrical precision and georeferencing accuracy. Structure-from-Motion (SfM) computer vision techniques were used to derive ultra-high resolution point clouds, orthophotos and 3D models from the multi-view photos. The geometric accuracy of the data based on the 20 GCP's were 0.018 m for the overall, 0.0025 m for the vertical root mean squared error (RMSE) and an over all root mean square reprojection error of 0.18 pixel. The UAV products were then edited and subsequently analysed, interpreted and key attributes extracted using a selection of tools/ software applications to enhance the wetland assessment. The results exceeded our expectations and provided a valuable and accurate enhancement to the wetland delineation, classification and health assessment which even with detailed field studies would have been difficult to achieve.

A semi-Markov model for mitosis segmentation in time-lapse phase contrast microscopy image sequences of stem cell populations.

PubMed

Liu, An-An; Li, Kang; Kanade, Takeo

2012-02-01

We propose a semi-Markov model trained in a max-margin learning framework for mitosis event segmentation in large-scale time-lapse phase contrast microscopy image sequences of stem cell populations. Our method consists of three steps. First, we apply a constrained optimization based microscopy image segmentation method that exploits phase contrast optics to extract candidate subsequences in the input image sequence that contains mitosis events. Then, we apply a max-margin hidden conditional random field (MM-HCRF) classifier learned from human-annotated mitotic and nonmitotic sequences to classify each candidate subsequence as a mitosis or not. Finally, a max-margin semi-Markov model (MM-SMM) trained on manually-segmented mitotic sequences is utilized to reinforce the mitosis classification results, and to further segment each mitosis into four predefined temporal stages. The proposed method outperforms the event-detection CRF model recently reported by Huh as well as several other competing methods in very challenging image sequences of multipolar-shaped C3H10T1/2 mesenchymal stem cells. For mitosis detection, an overall precision of 95.8% and a recall of 88.1% were achieved. For mitosis segmentation, the mean and standard deviation for the localization errors of the start and end points of all mitosis stages were well below 1 and 2 frames, respectively. In particular, an overall temporal location error of 0.73 ± 1.29 frames was achieved for locating daughter cell birth events.

Automatic classification for mammogram backgrounds based on bi-rads complexity definition and on a multi content analysis framework

NASA Astrophysics Data System (ADS)

Wu, Jie; Besnehard, Quentin; Marchessoux, Cédric

2011-03-01

Clinical studies for the validation of new medical imaging devices require hundreds of images. An important step in creating and tuning the study protocol is the classification of images into "difficult" and "easy" cases. This consists of classifying the image based on features like the complexity of the background, the visibility of the disease (lesions). Therefore, an automatic medical background classification tool for mammograms would help for such clinical studies. This classification tool is based on a multi-content analysis framework (MCA) which was firstly developed to recognize image content of computer screen shots. With the implementation of new texture features and a defined breast density scale, the MCA framework is able to automatically classify digital mammograms with a satisfying accuracy. BI-RADS (Breast Imaging Reporting Data System) density scale is used for grouping the mammograms, which standardizes the mammography reporting terminology and assessment and recommendation categories. Selected features are input into a decision tree classification scheme in MCA framework, which is the so called "weak classifier" (any classifier with a global error rate below 50%). With the AdaBoost iteration algorithm, these "weak classifiers" are combined into a "strong classifier" (a classifier with a low global error rate) for classifying one category. The results of classification for one "strong classifier" show the good accuracy with the high true positive rates. For the four categories the results are: TP=90.38%, TN=67.88%, FP=32.12% and FN =9.62%.

Error Patterns with Fraction Calculations at Fourth Grade as a Function of Students' Mathematics Achievement Status

ERIC Educational Resources Information Center

Schumacher, Robin F.; Malone, Amelia S.

2017-01-01

The goal of the present study was to describe fraction-calculation errors among 4th-grade students and determine whether error patterns differed as a function of problem type (addition vs. subtraction; like vs. unlike denominators), orientation (horizontal vs. vertical), or mathematics-achievement status (low- vs. average- vs. high-achieving). We…

Medication administration errors from a nursing viewpoint: a formal consensus of definition and scenarios using a Delphi technique.

PubMed

Shawahna, Ramzi; Masri, Dina; Al-Gharabeh, Rawan; Deek, Rawan; Al-Thayba, Lama; Halaweh, Masa

2016-02-01

To develop and achieve formal consensus on a definition of medication administration errors and scenarios that should or should not be considered as medication administration errors in hospitalised patient settings. Medication administration errors occur frequently in hospitalised patient settings. Currently, there is no formal consensus on a definition of medication administration errors or scenarios that should or should not be considered as medication administration errors. This was a descriptive study using Delphi technique. A panel of experts (n = 50) recruited from major hospitals, nursing schools and universities in Palestine took part in the study. Three Delphi rounds were followed to achieve consensus on a proposed definition of medication administration errors and a series of 61 scenarios representing potential medication administration error situations formulated into a questionnaire. In the first Delphi round, key contact nurses' views on medication administration errors were explored. In the second Delphi round, consensus was achieved to accept the proposed definition of medication administration errors and to include 36 (59%) scenarios and exclude 1 (1·6%) as medication administration errors. In the third Delphi round, consensus was achieved to consider further 14 (23%) and exclude 2 (3·3%) as medication administration errors while the remaining eight (13·1%) were considered equivocal. Of the 61 scenarios included in the Delphi process, experts decided to include 50 scenarios as medication administration errors, exclude three scenarios and include or exclude eight scenarios depending on the individual clinical situation. Consensus on a definition and scenarios representing medication administration errors can be achieved using formal consensus techniques. Researchers should be aware that using different definitions of medication administration errors, inclusion or exclusion of medication administration error situations could significantly affect the rate of medication administration errors reported in their studies. Consensual definitions and medication administration error situations can be used in future epidemiology studies investigating medication administration errors in hospitalised patient settings which may permit and promote direct comparisons of different studies. © 2015 John Wiley & Sons Ltd.

Classification of electroencephalograph signals using time-frequency decomposition and linear discriminant analysis

NASA Astrophysics Data System (ADS)

Szuflitowska, B.; Orlowski, P.

2017-08-01

Automated detection system consists of two key steps: extraction of features from EEG signals and classification for detection of pathology activity. The EEG sequences were analyzed using Short-Time Fourier Transform and the classification was performed using Linear Discriminant Analysis. The accuracy of the technique was tested on three sets of EEG signals: epilepsy, healthy and Alzheimer's Disease. The classification error below 10% has been considered a success. The higher accuracy are obtained for new data of unknown classes than testing data. The methodology can be helpful in differentiation epilepsy seizure and disturbances in the EEG signal in Alzheimer's Disease.

Lexical Errors in Second Language Scientific Writing: Some Conceptual Implications

ERIC Educational Resources Information Center

Carrió Pastor, María Luisa; Mestre-Mestre, Eva María

2014-01-01

Nowadays, scientific writers are required not only a thorough knowledge of their subject field, but also a sound command of English as a lingua franca. In this paper, the lexical errors produced in scientific texts written in English by non-native researchers are identified to propose a classification of the categories they contain. This study…

Land use surveys by means of automatic interpretation of LANDSAT system data

NASA Technical Reports Server (NTRS)

Dejesusparada, N. (Principal Investigator); Lombardo, M. A.; Novo, E. M. L. D.; Niero, M.; Foresti, C.

1981-01-01

Analyses for seven land-use classes are presented. The classes are: urban area, industrial area, bare soil, cultivated area, pastureland, reforestation, and natural vegetation. The automatic classification of LANDSAT MSS data using a maximum likelihood algorithm shows a 39% average error of emission and a 3.45 error of commission for the seven classes.

Anatomical and/or pathological predictors for the “incorrect” classification of red dot markers on wrist radiographs taken following trauma

PubMed Central

Kranz, R

2015-01-01

Objective: To establish the prevalence of red dot markers in a sample of wrist radiographs and to identify any anatomical and/or pathological characteristics that predict “incorrect” red dot classification. Methods: Accident and emergency (A&E) wrist cases from a digital imaging and communications in medicine/digital teaching library were examined for red dot prevalence and for the presence of several anatomical and pathological features. Binary logistic regression analyses were run to establish if any of these features were predictors of incorrect red dot classification. Results: 398 cases were analysed. Red dot was “incorrectly” classified in 8.5% of cases; 6.3% were “false negatives” (“FNs”)and 2.3% false positives (FPs) (one decimal place). Old fractures [odds ratio (OR), 5.070 (1.256–20.471)] and reported degenerative change [OR, 9.870 (2.300–42.359)] were found to predict FPs. Frykman V [OR, 9.500 (1.954–46.179)], Frykman VI [OR, 6.333 (1.205–33.283)] and non-Frykman positive abnormalities [OR, 4.597 (1.264–16.711)] predict “FNs”. Old fractures and Frykman VI were predictive of error at 90% confidence interval (CI); the rest at 95% CI. Conclusion: The five predictors of incorrect red dot classification may inform the image interpretation training of radiographers and other professionals to reduce diagnostic error. Verification with larger samples would reinforce these findings. Advances in knowledge: All healthcare providers strive to eradicate diagnostic error. By examining specific anatomical and pathological predictors on radiographs for such error, as well as extrinsic factors that may affect reporting accuracy, image interpretation training can focus on these “problem” areas and influence which radiographic abnormality detection schemes are appropriate to implement in A&E departments. PMID:25496373

How Should Children with Speech Sound Disorders be Classified? A Review and Critical Evaluation of Current Classification Systems

ERIC Educational Resources Information Center

Waring, R.; Knight, R.

2013-01-01

Background: Children with speech sound disorders (SSD) form a heterogeneous group who differ in terms of the severity of their condition, underlying cause, speech errors, involvement of other aspects of the linguistic system and treatment response. To date there is no universal and agreed-upon classification system. Instead, a number of…

Evaluation of the confusion matrix method in the validation of an automated system for measuring feeding behaviour of cattle.

PubMed

Ruuska, Salla; Hämäläinen, Wilhelmiina; Kajava, Sari; Mughal, Mikaela; Matilainen, Pekka; Mononen, Jaakko

2018-03-01

The aim of the present study was to evaluate empirically confusion matrices in device validation. We compared the confusion matrix method to linear regression and error indices in the validation of a device measuring feeding behaviour of dairy cattle. In addition, we studied how to extract additional information on classification errors with confusion probabilities. The data consisted of 12 h behaviour measurements from five dairy cows; feeding and other behaviour were detected simultaneously with a device and from video recordings. The resulting 216 000 pairs of classifications were used to construct confusion matrices and calculate performance measures. In addition, hourly durations of each behaviour were calculated and the accuracy of measurements was evaluated with linear regression and error indices. All three validation methods agreed when the behaviour was detected very accurately or inaccurately. Otherwise, in the intermediate cases, the confusion matrix method and error indices produced relatively concordant results, but the linear regression method often disagreed with them. Our study supports the use of confusion matrix analysis in validation since it is robust to any data distribution and type of relationship, it makes a stringent evaluation of validity, and it offers extra information on the type and sources of errors. Copyright © 2018 Elsevier B.V. All rights reserved.

Bayes-LQAS: classifying the prevalence of global acute malnutrition

PubMed Central

2010-01-01

Lot Quality Assurance Sampling (LQAS) applications in health have generally relied on frequentist interpretations for statistical validity. Yet health professionals often seek statements about the probability distribution of unknown parameters to answer questions of interest. The frequentist paradigm does not pretend to yield such information, although a Bayesian formulation might. This is the source of an error made in a recent paper published in this journal. Many applications lend themselves to a Bayesian treatment, and would benefit from such considerations in their design. We discuss Bayes-LQAS (B-LQAS), which allows for incorporation of prior information into the LQAS classification procedure, and thus shows how to correct the aforementioned error. Further, we pay special attention to the formulation of Bayes Operating Characteristic Curves and the use of prior information to improve survey designs. As a motivating example, we discuss the classification of Global Acute Malnutrition prevalence and draw parallels between the Bayes and classical classifications schemes. We also illustrate the impact of informative and non-informative priors on the survey design. Results indicate that using a Bayesian approach allows the incorporation of expert information and/or historical data and is thus potentially a valuable tool for making accurate and precise classifications. PMID:20534159

Bayes-LQAS: classifying the prevalence of global acute malnutrition.

PubMed

Olives, Casey; Pagano, Marcello

2010-06-09

Lot Quality Assurance Sampling (LQAS) applications in health have generally relied on frequentist interpretations for statistical validity. Yet health professionals often seek statements about the probability distribution of unknown parameters to answer questions of interest. The frequentist paradigm does not pretend to yield such information, although a Bayesian formulation might. This is the source of an error made in a recent paper published in this journal. Many applications lend themselves to a Bayesian treatment, and would benefit from such considerations in their design. We discuss Bayes-LQAS (B-LQAS), which allows for incorporation of prior information into the LQAS classification procedure, and thus shows how to correct the aforementioned error. Further, we pay special attention to the formulation of Bayes Operating Characteristic Curves and the use of prior information to improve survey designs. As a motivating example, we discuss the classification of Global Acute Malnutrition prevalence and draw parallels between the Bayes and classical classifications schemes. We also illustrate the impact of informative and non-informative priors on the survey design. Results indicate that using a Bayesian approach allows the incorporation of expert information and/or historical data and is thus potentially a valuable tool for making accurate and precise classifications.

Optimization of the ANFIS using a genetic algorithm for physical work rate classification.

PubMed

Habibi, Ehsanollah; Salehi, Mina; Yadegarfar, Ghasem; Taheri, Ali

2018-03-13

Recently, a new method was proposed for physical work rate classification based on an adaptive neuro-fuzzy inference system (ANFIS). This study aims to present a genetic algorithm (GA)-optimized ANFIS model for a highly accurate classification of physical work rate. Thirty healthy men participated in this study. Directly measured heart rate and oxygen consumption of the participants in the laboratory were used for training the ANFIS classifier model in MATLAB version 8.0.0 using a hybrid algorithm. A similar process was done using the GA as an optimization technique. The accuracy, sensitivity and specificity of the ANFIS classifier model were increased successfully. The mean accuracy of the model was increased from 92.95 to 97.92%. Also, the calculated root mean square error of the model was reduced from 5.4186 to 3.1882. The maximum estimation error of the optimized ANFIS during the network testing process was ± 5%. The GA can be effectively used for ANFIS optimization and leads to an accurate classification of physical work rate. In addition to high accuracy, simple implementation and inter-individual variability consideration are two other advantages of the presented model.

Galaxy Zoo 1: data release of morphological classifications for nearly 900 000 galaxies

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

Linott, C.; Slosar, A.; Lintott, C.

Morphology is a powerful indicator of a galaxy's dynamical and merger history. It is strongly correlated with many physical parameters, including mass, star formation history and the distribution of mass. The Galaxy Zoo project collected simple morphological classifications of nearly 900,000 galaxies drawn from the Sloan Digital Sky Survey, contributed by hundreds of thousands of volunteers. This large number of classifications allows us to exclude classifier error, and measure the influence of subtle biases inherent in morphological classification. This paper presents the data collected by the project, alongside measures of classification accuracy and bias. The data are now publicly availablemore » and full catalogues can be downloaded in electronic format from http://data.galaxyzoo.org.« less

Spotting East African mammals in open savannah from space.

PubMed

Yang, Zheng; Wang, Tiejun; Skidmore, Andrew K; de Leeuw, Jan; Said, Mohammed Y; Freer, Jim

2014-01-01

Knowledge of population dynamics is essential for managing and conserving wildlife. Traditional methods of counting wild animals such as aerial survey or ground counts not only disturb animals, but also can be labour intensive and costly. New, commercially available very high-resolution satellite images offer great potential for accurate estimates of animal abundance over large open areas. However, little research has been conducted in the area of satellite-aided wildlife census, although computer processing speeds and image analysis algorithms have vastly improved. This paper explores the possibility of detecting large animals in the open savannah of Maasai Mara National Reserve, Kenya from very high-resolution GeoEye-1 satellite images. A hybrid image classification method was employed for this specific purpose by incorporating the advantages of both pixel-based and object-based image classification approaches. This was performed in two steps: firstly, a pixel-based image classification method, i.e., artificial neural network was applied to classify potential targets with similar spectral reflectance at pixel level; and then an object-based image classification method was used to further differentiate animal targets from the surrounding landscapes through the applications of expert knowledge. As a result, the large animals in two pilot study areas were successfully detected with an average count error of 8.2%, omission error of 6.6% and commission error of 13.7%. The results of the study show for the first time that it is feasible to perform automated detection and counting of large wild animals in open savannahs from space, and therefore provide a complementary and alternative approach to the conventional wildlife survey techniques.

Comparison of three methods for long-term monitoring of boreal lake area using Landsat TM and ETM+ imagery

USGS Publications Warehouse

Roach, Jennifer K.; Griffith, Brad; Verbyla, David

2012-01-01

Programs to monitor lake area change are becoming increasingly important in high latitude regions, and their development often requires evaluating tradeoffs among different approaches in terms of accuracy of measurement, consistency across multiple users over long time periods, and efficiency. We compared three supervised methods for lake classification from Landsat imagery (density slicing, classification trees, and feature extraction). The accuracy of lake area and number estimates was evaluated relative to high-resolution aerial photography acquired within two days of satellite overpasses. The shortwave infrared band 5 was better at separating surface water from nonwater when used alone than when combined with other spectral bands. The simplest of the three methods, density slicing, performed best overall. The classification tree method resulted in the most omission errors (approx. 2x), feature extraction resulted in the most commission errors (approx. 4x), and density slicing had the least directional bias (approx. half of the lakes with overestimated area and half of the lakes with underestimated area). Feature extraction was the least consistent across training sets (i.e., large standard error among different training sets). Density slicing was the best of the three at classifying small lakes as evidenced by its lower optimal minimum lake size criterion of 5850 m2 compared with the other methods (8550 m2). Contrary to conventional wisdom, the use of additional spectral bands and a more sophisticated method not only required additional processing effort but also had a cost in terms of the accuracy and consistency of lake classifications.

Cluster designs to assess the prevalence of acute malnutrition by lot quality assurance sampling: a validation study by computer simulation

PubMed Central

Olives, Casey; Pagano, Marcello; Deitchler, Megan; Hedt, Bethany L; Egge, Kari; Valadez, Joseph J

2009-01-01

Traditional lot quality assurance sampling (LQAS) methods require simple random sampling to guarantee valid results. However, cluster sampling has been proposed to reduce the number of random starting points. This study uses simulations to examine the classification error of two such designs, a 67×3 (67 clusters of three observations) and a 33×6 (33 clusters of six observations) sampling scheme to assess the prevalence of global acute malnutrition (GAM). Further, we explore the use of a 67×3 sequential sampling scheme for LQAS classification of GAM prevalence. Results indicate that, for independent clusters with moderate intracluster correlation for the GAM outcome, the three sampling designs maintain approximate validity for LQAS analysis. Sequential sampling can substantially reduce the average sample size that is required for data collection. The presence of intercluster correlation can impact dramatically the classification error that is associated with LQAS analysis. PMID:20011037

Electroencephalography epilepsy classifications using hybrid cuckoo search and neural network

NASA Astrophysics Data System (ADS)

Pratiwi, A. B.; Damayanti, A.; Miswanto

2017-07-01

Epilepsy is a condition that affects the brain and causes repeated seizures. This seizure is episodes that can vary and nearly undetectable to long periods of vigorous shaking or brain contractions. Epilepsy often can be confirmed with an electrocephalography (EEG). Neural Networks has been used in biomedic signal analysis, it has successfully classified the biomedic signal, such as EEG signal. In this paper, a hybrid cuckoo search and neural network are used to recognize EEG signal for epilepsy classifications. The weight of the multilayer perceptron is optimized by the cuckoo search algorithm based on its error. The aim of this methods is making the network faster to obtained the local or global optimal then the process of classification become more accurate. Based on the comparison results with the traditional multilayer perceptron, the hybrid cuckoo search and multilayer perceptron provides better performance in term of error convergence and accuracy. The purpose methods give MSE 0.001 and accuracy 90.0 %.

iACP-GAEnsC: Evolutionary genetic algorithm based ensemble classification of anticancer peptides by utilizing hybrid feature space.

PubMed

Akbar, Shahid; Hayat, Maqsood; Iqbal, Muhammad; Jan, Mian Ahmad

2017-06-01

Cancer is a fatal disease, responsible for one-quarter of all deaths in developed countries. Traditional anticancer therapies such as, chemotherapy and radiation, are highly expensive, susceptible to errors and ineffective techniques. These conventional techniques induce severe side-effects on human cells. Due to perilous impact of cancer, the development of an accurate and highly efficient intelligent computational model is desirable for identification of anticancer peptides. In this paper, evolutionary intelligent genetic algorithm-based ensemble model, 'iACP-GAEnsC', is proposed for the identification of anticancer peptides. In this model, the protein sequences are formulated, using three different discrete feature representation methods, i.e., amphiphilic Pseudo amino acid composition, g-Gap dipeptide composition, and Reduce amino acid alphabet composition. The performance of the extracted feature spaces are investigated separately and then merged to exhibit the significance of hybridization. In addition, the predicted results of individual classifiers are combined together, using optimized genetic algorithm and simple majority technique in order to enhance the true classification rate. It is observed that genetic algorithm-based ensemble classification outperforms than individual classifiers as well as simple majority voting base ensemble. The performance of genetic algorithm-based ensemble classification is highly reported on hybrid feature space, with an accuracy of 96.45%. In comparison to the existing techniques, 'iACP-GAEnsC' model has achieved remarkable improvement in terms of various performance metrics. Based on the simulation results, it is observed that 'iACP-GAEnsC' model might be a leading tool in the field of drug design and proteomics for researchers. Copyright © 2017 Elsevier B.V. All rights reserved.

Enhancing spatial resolution of (18)F positron imaging with the Timepix detector by classification of primary fired pixels using support vector machine.

PubMed

Wang, Qian; Liu, Zhen; Ziegler, Sibylle I; Shi, Kuangyu

2015-07-07

Position-sensitive positron cameras using silicon pixel detectors have been applied for some preclinical and intraoperative clinical applications. However, the spatial resolution of a positron camera is limited by positron multiple scattering in the detector. An incident positron may fire a number of successive pixels on the imaging plane. It is still impossible to capture the primary fired pixel along a particle trajectory by hardware or to perceive the pixel firing sequence by direct observation. Here, we propose a novel data-driven method to improve the spatial resolution by classifying the primary pixels within the detector using support vector machine. A classification model is constructed by learning the features of positron trajectories based on Monte-Carlo simulations using Geant4. Topological and energy features of pixels fired by (18)F positrons were considered for the training and classification. After applying the classification model on measurements, the primary fired pixels of the positron tracks in the silicon detector were estimated. The method was tested and assessed for [(18)F]FDG imaging of an absorbing edge protocol and a leaf sample. The proposed method improved the spatial resolution from 154.6   ±   4.2 µm (energy weighted centroid approximation) to 132.3   ±   3.5 µm in the absorbing edge measurements. For the positron imaging of a leaf sample, the proposed method achieved lower root mean square error relative to phosphor plate imaging, and higher similarity with the reference optical image. The improvements of the preliminary results support further investigation of the proposed algorithm for the enhancement of positron imaging in clinical and preclinical applications.

Enhancing spatial resolution of 18F positron imaging with the Timepix detector by classification of primary fired pixels using support vector machine

NASA Astrophysics Data System (ADS)

Wang, Qian; Liu, Zhen; Ziegler, Sibylle I.; Shi, Kuangyu

2015-07-01

Position-sensitive positron cameras using silicon pixel detectors have been applied for some preclinical and intraoperative clinical applications. However, the spatial resolution of a positron camera is limited by positron multiple scattering in the detector. An incident positron may fire a number of successive pixels on the imaging plane. It is still impossible to capture the primary fired pixel along a particle trajectory by hardware or to perceive the pixel firing sequence by direct observation. Here, we propose a novel data-driven method to improve the spatial resolution by classifying the primary pixels within the detector using support vector machine. A classification model is constructed by learning the features of positron trajectories based on Monte-Carlo simulations using Geant4. Topological and energy features of pixels fired by 18F positrons were considered for the training and classification. After applying the classification model on measurements, the primary fired pixels of the positron tracks in the silicon detector were estimated. The method was tested and assessed for [18F]FDG imaging of an absorbing edge protocol and a leaf sample. The proposed method improved the spatial resolution from 154.6   ±   4.2 µm (energy weighted centroid approximation) to 132.3   ±   3.5 µm in the absorbing edge measurements. For the positron imaging of a leaf sample, the proposed method achieved lower root mean square error relative to phosphor plate imaging, and higher similarity with the reference optical image. The improvements of the preliminary results support further investigation of the proposed algorithm for the enhancement of positron imaging in clinical and preclinical applications.

Superordinate Shape Classification Using Natural Shape Statistics

ERIC Educational Resources Information Center

Wilder, John; Feldman, Jacob; Singh, Manish

2011-01-01

This paper investigates the classification of shapes into broad natural categories such as "animal" or "leaf". We asked whether such coarse classifications can be achieved by a simple statistical classification of the shape skeleton. We surveyed databases of natural shapes, extracting shape skeletons and tabulating their…

Automated segmentation of thyroid gland on CT images with multi-atlas label fusion and random classification forest

NASA Astrophysics Data System (ADS)

Liu, Jiamin; Chang, Kevin; Kim, Lauren; Turkbey, Evrim; Lu, Le; Yao, Jianhua; Summers, Ronald

2015-03-01

The thyroid gland plays an important role in clinical practice, especially for radiation therapy treatment planning. For patients with head and neck cancer, radiation therapy requires a precise delineation of the thyroid gland to be spared on the pre-treatment planning CT images to avoid thyroid dysfunction. In the current clinical workflow, the thyroid gland is normally manually delineated by radiologists or radiation oncologists, which is time consuming and error prone. Therefore, a system for automated segmentation of the thyroid is desirable. However, automated segmentation of the thyroid is challenging because the thyroid is inhomogeneous and surrounded by structures that have similar intensities. In this work, the thyroid gland segmentation is initially estimated by multi-atlas label fusion algorithm. The segmentation is refined by supervised statistical learning based voxel labeling with a random forest algorithm. Multiatlas label fusion (MALF) transfers expert-labeled thyroids from atlases to a target image using deformable registration. Errors produced by label transfer are reduced by label fusion that combines the results produced by all atlases into a consensus solution. Then, random forest (RF) employs an ensemble of decision trees that are trained on labeled thyroids to recognize features. The trained forest classifier is then applied to the thyroid estimated from the MALF by voxel scanning to assign the class-conditional probability. Voxels from the expert-labeled thyroids in CT volumes are treated as positive classes; background non-thyroid voxels as negatives. We applied this automated thyroid segmentation system to CT scans of 20 patients. The results showed that the MALF achieved an overall 0.75 Dice Similarity Coefficient (DSC) and the RF classification further improved the DSC to 0.81.

Methodology for cork plank characterization (Quercus suber L.) by near-infrared spectroscopy and image analysis

NASA Astrophysics Data System (ADS)

Prades, Cristina; García-Olmo, Juan; Romero-Prieto, Tomás; García de Ceca, José L.; López-Luque, Rafael

2010-06-01

The procedures used today to characterize cork plank for the manufacture of cork bottle stoppers continue to be based on a traditional, manual method that is highly subjective. Furthermore, there is no specific legislation regarding cork classification. The objective of this viability study is to assess the potential of near-infrared spectroscopy (NIRS) technology for characterizing cork plank according to the following variables: aspect or visual quality, porosity, moisture and geographical origin. In order to calculate the porosity coefficient, an image analysis program was specifically developed in Visual Basic language for a desktop scanner. A set comprising 170 samples from two geographical areas of Andalusia (Spain) was classified into eight quality classes by visual inspection. Spectra were obtained in the transverse and tangential sections of the cork planks using an NIRSystems 6500 SY II reflectance spectrophotometer. The quantitative calibrations showed cross-validation coefficients of determination of 0.47 for visual quality, 0.69 for porosity and 0.66 for moisture. The results obtained using NIRS technology are promising considering the heterogeneity and variability of a natural product such as cork in spite of the fact that the standard error of cross validation (SECV) in the quantitative analysis is greater than the standard error of laboratory (SEL) for the three variables. The qualitative analysis regarding geographical origin achieved very satisfactory results. Applying these methods in industry will permit quality control procedures to be automated, as well as establishing correlations between the different classification systems currently used in the sector. These methods can be implemented in the cork chain of custody certification and will also provide a certainly more objective tool for assessing the economic value of the product.

Object-Based Random Forest Classification of Land Cover from Remotely Sensed Imagery for Industrial and Mining Reclamation

NASA Astrophysics Data System (ADS)

Chen, Y.; Luo, M.; Xu, L.; Zhou, X.; Ren, J.; Zhou, J.

2018-04-01

The RF method based on grid-search parameter optimization could achieve a classification accuracy of 88.16 % in the classification of images with multiple feature variables. This classification accuracy was higher than that of SVM and ANN under the same feature variables. In terms of efficiency, the RF classification method performs better than SVM and ANN, it is more capable of handling multidimensional feature variables. The RF method combined with object-based analysis approach could highlight the classification accuracy further. The multiresolution segmentation approach on the basis of ESP scale parameter optimization was used for obtaining six scales to execute image segmentation, when the segmentation scale was 49, the classification accuracy reached the highest value of 89.58 %. The classification accuracy of object-based RF classification was 1.42 % higher than that of pixel-based classification (88.16 %), and the classification accuracy was further improved. Therefore, the RF classification method combined with object-based analysis approach could achieve relatively high accuracy in the classification and extraction of land use information for industrial and mining reclamation areas. Moreover, the interpretation of remotely sensed imagery using the proposed method could provide technical support and theoretical reference for remotely sensed monitoring land reclamation.

Local receptive field constrained stacked sparse autoencoder for classification of hyperspectral images.

PubMed

Wan, Xiaoqing; Zhao, Chunhui

2017-06-01

As a competitive machine learning algorithm, the stacked sparse autoencoder (SSA) has achieved outstanding popularity in exploiting high-level features for classification of hyperspectral images (HSIs). In general, in the SSA architecture, the nodes between adjacent layers are fully connected and need to be iteratively fine-tuned during the pretraining stage; however, the nodes of previous layers further away may be less likely to have a dense correlation to the given node of subsequent layers. Therefore, to reduce the classification error and increase the learning rate, this paper proposes the general framework of locally connected SSA; that is, the biologically inspired local receptive field (LRF) constrained SSA architecture is employed to simultaneously characterize the local correlations of spectral features and extract high-level feature representations of hyperspectral data. In addition, the appropriate receptive field constraint is concurrently updated by measuring the spatial distances from the neighbor nodes to the corresponding node. Finally, the efficient random forest classifier is cascaded to the last hidden layer of the SSA architecture as a benchmark classifier. Experimental results on two real HSI datasets demonstrate that the proposed hierarchical LRF constrained stacked sparse autoencoder and random forest (SSARF) provides encouraging results with respect to other contrastive methods, for instance, the improvements of overall accuracy in a range of 0.72%-10.87% for the Indian Pines dataset and 0.74%-7.90% for the Kennedy Space Center dataset; moreover, it generates lower running time compared with the result provided by similar SSARF based methodology.

VO2 estimation using 6-axis motion sensor with sports activity classification.

PubMed

Nagata, Takashi; Nakamura, Naoteru; Miyatake, Masato; Yuuki, Akira; Yomo, Hiroyuki; Kawabata, Takashi; Hara, Shinsuke

2016-08-01

In this paper, we focus on oxygen consumption (VO2) estimation using 6-axis motion sensor (3-axis accelerometer and 3-axis gyroscope) for people playing sports with diverse intensities. The VO2 estimated with a small motion sensor can be used to calculate the energy expenditure, however, its accuracy depends on the intensities of various types of activities. In order to achieve high accuracy over a wide range of intensities, we employ an estimation framework that first classifies activities with a simple machine-learning based classification algorithm. We prepare different coefficients of linear regression model for different types of activities, which are determined with training data obtained by experiments. The best-suited model is used for each type of activity when VO2 is estimated. The accuracy of the employed framework depends on the trade-off between the degradation due to classification errors and improvement brought by applying separate, optimum model to VO2 estimation. Taking this trade-off into account, we evaluate the accuracy of the employed estimation framework by using a set of experimental data consisting of VO2 and motion data of people with a wide range of intensities of exercises, which were measured by a VO2 meter and motion sensor, respectively. Our numerical results show that the employed framework can improve the estimation accuracy in comparison to a reference method that uses a common regression model for all types of activities.

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.

Error, Power, and Blind Sentinels: The Statistics of Seagrass Monitoring

PubMed Central

Schultz, Stewart T.; Kruschel, Claudia; Bakran-Petricioli, Tatjana; Petricioli, Donat

2015-01-01

We derive statistical properties of standard methods for monitoring of habitat cover worldwide, and criticize them in the context of mandated seagrass monitoring programs, as exemplified by Posidonia oceanica in the Mediterranean Sea. We report the novel result that cartographic methods with non-trivial classification errors are generally incapable of reliably detecting habitat cover losses less than about 30 to 50%, and the field labor required to increase their precision can be orders of magnitude higher than that required to estimate habitat loss directly in a field campaign. We derive a universal utility threshold of classification error in habitat maps that represents the minimum habitat map accuracy above which direct methods are superior. Widespread government reliance on blind-sentinel methods for monitoring seafloor can obscure the gradual and currently ongoing losses of benthic resources until the time has long passed for meaningful management intervention. We find two classes of methods with very high statistical power for detecting small habitat cover losses: 1) fixed-plot direct methods, which are over 100 times as efficient as direct random-plot methods in a variable habitat mosaic; and 2) remote methods with very low classification error such as geospatial underwater videography, which is an emerging, low-cost, non-destructive method for documenting small changes at millimeter visual resolution. General adoption of these methods and their further development will require a fundamental cultural change in conservation and management bodies towards the recognition and promotion of requirements of minimal statistical power and precision in the development of international goals for monitoring these valuable resources and the ecological services they provide. PMID:26367863

Land use in the Paraiba Valley through remotely sensed data. [Brazil

NASA Technical Reports Server (NTRS)

Dejesusparada, N. (Principal Investigator); Lombardo, M. A.; Novo, E. M. L. D.; Niero, M.; Foresti, C.

1980-01-01

A methodology for land use survey was developed and land use modification rates were determined using LANDSAT imagery of the Paraiba Valley (state of Sao Paulo). Both visual and automatic interpretation methods were employed to analyze seven land use classes: urban area, industrial area, bare soil, cultivated area, pastureland, reforestation and natural vegetation. By means of visual interpretation, little spectral differences are observed among those classes. The automatic classification of LANDSAT MSS data using maximum likelihood algorithm shows a 39% average error of omission and a 3.4% error of inclusion for the seven classes. The complexity of land uses in the study area, the large spectral variations of analyzed classes, and the low resolution of LANDSAT data influenced the classification results.

Multilayer perceptron, fuzzy sets, and classification

NASA Technical Reports Server (NTRS)

Pal, Sankar K.; Mitra, Sushmita

1992-01-01

A fuzzy neural network model based on the multilayer perceptron, using the back-propagation algorithm, and capable of fuzzy classification of patterns is described. The input vector consists of membership values to linguistic properties while the output vector is defined in terms of fuzzy class membership values. This allows efficient modeling of fuzzy or uncertain patterns with appropriate weights being assigned to the backpropagated errors depending upon the membership values at the corresponding outputs. During training, the learning rate is gradually decreased in discrete steps until the network converges to a minimum error solution. The effectiveness of the algorithm is demonstrated on a speech recognition problem. The results are compared with those of the conventional MLP, the Bayes classifier, and the other related models.

Bilevel Model-Based Discriminative Dictionary Learning for Recognition.

PubMed

Zhou, Pan; Zhang, Chao; Lin, Zhouchen

2017-03-01

Most supervised dictionary learning methods optimize the combinations of reconstruction error, sparsity prior, and discriminative terms. Thus, the learnt dictionaries may not be optimal for recognition tasks. Also, the sparse codes learning models in the training and the testing phases are inconsistent. Besides, without utilizing the intrinsic data structure, many dictionary learning methods only employ the l 0 or l 1 norm to encode each datum independently, limiting the performance of the learnt dictionaries. We present a novel bilevel model-based discriminative dictionary learning method for recognition tasks. The upper level directly minimizes the classification error, while the lower level uses the sparsity term and the Laplacian term to characterize the intrinsic data structure. The lower level is subordinate to the upper level. Therefore, our model achieves an overall optimality for recognition in that the learnt dictionary is directly tailored for recognition. Moreover, the sparse codes learning models in the training and the testing phases can be the same. We further propose a novel method to solve our bilevel optimization problem. It first replaces the lower level with its Karush-Kuhn-Tucker conditions and then applies the alternating direction method of multipliers to solve the equivalent problem. Extensive experiments demonstrate the effectiveness and robustness of our method.

One-Class Classification-Based Real-Time Activity Error Detection in Smart Homes.

PubMed

Das, Barnan; Cook, Diane J; Krishnan, Narayanan C; Schmitter-Edgecombe, Maureen

2016-08-01

Caring for individuals with dementia is frequently associated with extreme physical and emotional stress, which often leads to depression. Smart home technology and advances in machine learning techniques can provide innovative solutions to reduce caregiver burden. One key service that caregivers provide is prompting individuals with memory limitations to initiate and complete daily activities. We hypothesize that sensor technologies combined with machine learning techniques can automate the process of providing reminder-based interventions. The first step towards automated interventions is to detect when an individual faces difficulty with activities. We propose machine learning approaches based on one-class classification that learn normal activity patterns. When we apply these classifiers to activity patterns that were not seen before, the classifiers are able to detect activity errors, which represent potential prompt situations. We validate our approaches on smart home sensor data obtained from older adult participants, some of whom faced difficulties performing routine activities and thus committed errors.

Improving the mapping of crop types in the Midwestern U.S. by fusing Landsat and MODIS satellite data

NASA Astrophysics Data System (ADS)

Zhu, Likai; Radeloff, Volker C.; Ives, Anthony R.

2017-06-01

Mapping crop types is of great importance for assessing agricultural production, land-use patterns, and the environmental effects of agriculture. Indeed, both radiometric and spatial resolution of Landsat's sensors images are optimized for cropland monitoring. However, accurate mapping of crop types requires frequent cloud-free images during the growing season, which are often not available, and this raises the question of whether Landsat data can be combined with data from other satellites. Here, our goal is to evaluate to what degree fusing Landsat with MODIS Nadir Bidirectional Reflectance Distribution Function (BRDF)-Adjusted Reflectance (NBAR) data can improve crop-type classification. Choosing either one or two images from all cloud-free Landsat observations available for the Arlington Agricultural Research Station area in Wisconsin from 2010 to 2014, we generated 87 combinations of images, and used each combination as input into the Spatial and Temporal Adaptive Reflectance Fusion Model (STARFM) algorithm to predict Landsat-like images at the nominal dates of each 8-day MODIS NBAR product. Both the original Landsat and STARFM-predicted images were then classified with a support vector machine (SVM), and we compared the classification errors of three scenarios: 1) classifying the one or two original Landsat images of each combination only, 2) classifying the one or two original Landsat images plus all STARFM-predicted images, and 3) classifying the one or two original Landsat images together with STARFM-predicted images for key dates. Our results indicated that using two Landsat images as the input of STARFM did not significantly improve the STARFM predictions compared to using only one, and predictions using Landsat images between July and August as input were most accurate. Including all STARFM-predicted images together with the Landsat images significantly increased average classification error by 4% points (from 21% to 25%) compared to using only Landsat images. However, incorporating only STARFM-predicted images for key dates decreased average classification error by 2% points (from 21% to 19%) compared to using only Landsat images. In particular, if only a single Landsat image was available, adding STARFM predictions for key dates significantly decreased the average classification error by 4 percentage points from 30% to 26% (p < 0.05). We conclude that adding STARFM-predicted images can be effective for improving crop-type classification when only limited Landsat observations are available, but carefully selecting images from a full set of STARFM predictions is crucial. We developed an approach to identify the optimal subsets of all STARFM predictions, which gives an alternative method of feature selection for future research.

An Automated and Intelligent Medical Decision Support System for Brain MRI Scans Classification.

PubMed

Siddiqui, Muhammad Faisal; Reza, Ahmed Wasif; Kanesan, Jeevan

2015-01-01

A wide interest has been observed in the medical health care applications that interpret neuroimaging scans by machine learning systems. This research proposes an intelligent, automatic, accurate, and robust classification technique to classify the human brain magnetic resonance image (MRI) as normal or abnormal, to cater down the human error during identifying the diseases in brain MRIs. In this study, fast discrete wavelet transform (DWT), principal component analysis (PCA), and least squares support vector machine (LS-SVM) are used as basic components. Firstly, fast DWT is employed to extract the salient features of brain MRI, followed by PCA, which reduces the dimensions of the features. These reduced feature vectors also shrink the memory storage consumption by 99.5%. At last, an advanced classification technique based on LS-SVM is applied to brain MR image classification using reduced features. For improving the efficiency, LS-SVM is used with non-linear radial basis function (RBF) kernel. The proposed algorithm intelligently determines the optimized values of the hyper-parameters of the RBF kernel and also applied k-fold stratified cross validation to enhance the generalization of the system. The method was tested by 340 patients' benchmark datasets of T1-weighted and T2-weighted scans. From the analysis of experimental results and performance comparisons, it is observed that the proposed medical decision support system outperformed all other modern classifiers and achieves 100% accuracy rate (specificity/sensitivity 100%/100%). Furthermore, in terms of computation time, the proposed technique is significantly faster than the recent well-known methods, and it improves the efficiency by 71%, 3%, and 4% on feature extraction stage, feature reduction stage, and classification stage, respectively. These results indicate that the proposed well-trained machine learning system has the potential to make accurate predictions about brain abnormalities from the individual subjects, therefore, it can be used as a significant tool in clinical practice.

Analysis of swallowing sounds using hidden Markov models.

PubMed

Aboofazeli, Mohammad; Moussavi, Zahra

2008-04-01

In recent years, acoustical analysis of the swallowing mechanism has received considerable attention due to its diagnostic potentials. This paper presents a hidden Markov model (HMM) based method for the swallowing sound segmentation and classification. Swallowing sound signals of 15 healthy and 11 dysphagic subjects were studied. The signals were divided into sequences of 25 ms segments each of which were represented by seven features. The sequences of features were modeled by HMMs. Trained HMMs were used for segmentation of the swallowing sounds into three distinct phases, i.e., initial quiet period, initial discrete sounds (IDS) and bolus transit sounds (BTS). Among the seven features, accuracy of segmentation by the HMM based on multi-scale product of wavelet coefficients was higher than that of the other HMMs and the linear prediction coefficient (LPC)-based HMM showed the weakest performance. In addition, HMMs were used for classification of the swallowing sounds of healthy subjects and dysphagic patients. Classification accuracy of different HMM configurations was investigated. When we increased the number of states of the HMMs from 4 to 8, the classification error gradually decreased. In most cases, classification error for N=9 was higher than that of N=8. Among the seven features used, root mean square (RMS) and waveform fractal dimension (WFD) showed the best performance in the HMM-based classification of swallowing sounds. When the sequences of the features of IDS segment were modeled separately, the accuracy reached up to 85.5%. As a second stage classification, a screening algorithm was used which correctly classified all the subjects but one healthy subject when RMS was used as characteristic feature of the swallowing sounds and the number of states was set to N=8.

Spelling in Adolescents with Dyslexia: Errors and Modes of Assessment

ERIC Educational Resources Information Center

Tops, Wim; Callens, Maaike; Bijn, Evi; Brysbaert, Marc

2014-01-01

In this study we focused on the spelling of high-functioning students with dyslexia. We made a detailed classification of the errors in a word and sentence dictation task made by 100 students with dyslexia and 100 matched control students. All participants were in the first year of their bachelor's studies and had Dutch as mother tongue. Three…

Estimation of a cover-type change matrix from error-prone data

Treesearch

Steen Magnussen

2009-01-01

Coregistration and classification errors seriously compromise per-pixel estimates of land cover change. A more robust estimation of change is proposed in which adjacent pixels are grouped into 3x3 clusters and treated as a unit of observation. A complete change matrix is recovered in a two-step process. The diagonal elements of a change matrix are recovered from...

North American vegetation model for land-use planning in a changing climate: A solution to large classification problems

Treesearch

Gerald E. Rehfeldt; Nicholas L. Crookston; Cuauhtemoc Saenz-Romero; Elizabeth M. Campbell

2012-01-01

Data points intensively sampling 46 North American biomes were used to predict the geographic distribution of biomes from climate variables using the Random Forests classification tree. Techniques were incorporated to accommodate a large number of classes and to predict the future occurrence of climates beyond the contemporary climatic range of the biomes. Errors of...

Feasibility of Equivalent Dipole Models for Electroencephalogram-Based Brain Computer Interfaces.

PubMed

Schimpf, Paul H

2017-09-15

This article examines the localization errors of equivalent dipolar sources inverted from the surface electroencephalogram in order to determine the feasibility of using their location as classification parameters for non-invasive brain computer interfaces. Inverse localization errors are examined for two head models: a model represented by four concentric spheres and a realistic model based on medical imagery. It is shown that the spherical model results in localization ambiguity such that a number of dipolar sources, with different azimuths and varying orientations, provide a near match to the electroencephalogram of the best equivalent source. No such ambiguity exists for the elevation of inverted sources, indicating that for spherical head models, only the elevation of inverted sources (and not the azimuth) can be expected to provide meaningful classification parameters for brain-computer interfaces. In a realistic head model, all three parameters of the inverted source location are found to be reliable, providing a more robust set of parameters. In both cases, the residual error hypersurfaces demonstrate local minima, indicating that a search for the best-matching sources should be global. Source localization error vs. signal-to-noise ratio is also demonstrated for both head models.

The Influence of Guided Error-Based Learning on Motor Skills Self-Efficacy and Achievement.

PubMed

Chien, Kuei-Pin; Chen, Sufen

2018-01-01

The authors investigated the role of errors in motor skills teaching, specifically the influence of errors on skills self-efficacy and achievement. The participants were 75 undergraduate students enrolled in pétanque courses. The experimental group (guided error-based learning, n = 37) received a 6-week period of instruction based on the students' errors, whereas the control group (correct motion instruction, n = 38) received a 6-week period of instruction emphasizing correct motor skills. The experimental group had significantly higher scores in motor skills self-efficacy and outcomes than did the control group. Novices' errors reflect their schema in motor skills learning, which provides a basis for instructors to implement student-centered instruction and to facilitate the learning process. Guided error-based learning can effectively enhance beginners' skills self-efficacy and achievement in precision sports such as pétanque.

Quantitative CT analysis for the preoperative prediction of pathologic grade in pancreatic neuroendocrine tumors

NASA Astrophysics Data System (ADS)

Chakraborty, Jayasree; Pulvirenti, Alessandra; Yamashita, Rikiya; Midya, Abhishek; Gönen, Mithat; Klimstra, David S.; Reidy, Diane L.; Allen, Peter J.; Do, Richard K. G.; Simpson, Amber L.

2018-02-01

Pancreatic neuroendocrine tumors (PanNETs) account for approximately 5% of all pancreatic tumors, affecting one individual per million each year.1 PanNETs are difficult to treat due to biological variability from benign to highly malignant, indolent to very aggressive. The World Health Organization classifies PanNETs into three categories based on cell proliferative rate, usually detected using the Ki67 index and cell morphology: low-grade (G1), intermediate-grade (G2) and high-grade (G3) tumors. Knowledge of grade prior to treatment would select patients for optimal therapy: G1/G2 tumors respond well to somatostatin analogs and targeted or cytotoxic drugs whereas G3 tumors would be targeted with platinum or alkylating agents.2, 3 Grade assessment is based on the pathologic examination of the surgical specimen, biopsy or ne-needle aspiration; however, heterogeneity in the proliferative index can lead to sampling errors.4 Based on studies relating qualitatively assessed shape and enhancement characteristics on CT imaging to tumor grade in PanNET,5 we propose objective classification of PanNET grade with quantitative analysis of CT images. Fifty-five patients were included in our retrospective analysis. A pathologist graded the tumors. Texture and shape-based features were extracted from CT. Random forest and naive Bayes classifiers were compared for the classification of G1/G2 and G3 PanNETs. The best area under the receiver operating characteristic curve (AUC) of 0:74 and accuracy of 71:64% was achieved with texture features. The shape-based features achieved an AUC of 0:70 and accuracy of 78:73%.

Predictive modeling of respiratory tumor motion for real-time prediction of baseline shifts

NASA Astrophysics Data System (ADS)

Balasubramanian, A.; Shamsuddin, R.; Prabhakaran, B.; Sawant, A.

2017-03-01

Baseline shifts in respiratory patterns can result in significant spatiotemporal changes in patient anatomy (compared to that captured during simulation), in turn, causing geometric and dosimetric errors in the administration of thoracic and abdominal radiotherapy. We propose predictive modeling of the tumor motion trajectories for predicting a baseline shift ahead of its occurrence. The key idea is to use the features of the tumor motion trajectory over a 1 min window, and predict the occurrence of a baseline shift in the 5 s that immediately follow (lookahead window). In this study, we explored a preliminary trend-based analysis with multi-class annotations as well as a more focused binary classification analysis. In both analyses, a number of different inter-fraction and intra-fraction training strategies were studied, both offline as well as online, along with data sufficiency and skew compensation for class imbalances. The performance of different training strategies were compared across multiple machine learning classification algorithms, including nearest neighbor, Naïve Bayes, linear discriminant and ensemble Adaboost. The prediction performance is evaluated using metrics such as accuracy, precision, recall and the area under the curve (AUC) for repeater operating characteristics curve. The key results of the trend-based analysis indicate that (i) intra-fraction training strategies achieve highest prediction accuracies (90.5-91.4%) (ii) the predictive modeling yields lowest accuracies (50-60%) when the training data does not include any information from the test patient; (iii) the prediction latencies are as low as a few hundred milliseconds, and thus conducive for real-time prediction. The binary classification performance is promising, indicated by high AUCs (0.96-0.98). It also confirms the utility of prior data from previous patients, and also the necessity of training the classifier on some initial data from the new patient for reasonable prediction performance. The ability to predict a baseline shift with a sufficient look-ahead window will enable clinical systems or even human users to hold the treatment beam in such situations, thereby reducing the probability of serious geometric and dosimetric errors.

Predictive modeling of respiratory tumor motion for real-time prediction of baseline shifts

PubMed Central

Balasubramanian, A; Shamsuddin, R; Prabhakaran, B; Sawant, A

2017-01-01

Baseline shifts in respiratory patterns can result in significant spatiotemporal changes in patient anatomy (compared to that captured during simulation), in turn, causing geometric and dosimetric errors in the administration of thoracic and abdominal radiotherapy. We propose predictive modeling of the tumor motion trajectories for predicting a baseline shift ahead of its occurrence. The key idea is to use the features of the tumor motion trajectory over a 1 min window, and predict the occurrence of a baseline shift in the 5 s that immediately follow (lookahead window). In this study, we explored a preliminary trend-based analysis with multi-class annotations as well as a more focused binary classification analysis. In both analyses, a number of different inter-fraction and intra-fraction training strategies were studied, both offline as well as online, along with data sufficiency and skew compensation for class imbalances. The performance of different training strategies were compared across multiple machine learning classification algorithms, including nearest neighbor, Naïve Bayes, linear discriminant and ensemble Adaboost. The prediction performance is evaluated using metrics such as accuracy, precision, recall and the area under the curve (AUC) for repeater operating characteristics curve. The key results of the trend-based analysis indicate that (i) intra-fraction training strategies achieve highest prediction accuracies (90.5–91.4%); (ii) the predictive modeling yields lowest accuracies (50–60%) when the training data does not include any information from the test patient; (iii) the prediction latencies are as low as a few hundred milliseconds, and thus conducive for real-time prediction. The binary classification performance is promising, indicated by high AUCs (0.96–0.98). It also confirms the utility of prior data from previous patients, and also the necessity of training the classifier on some initial data from the new patient for reasonable prediction performance. The ability to predict a baseline shift with a sufficient lookahead window will enable clinical systems or even human users to hold the treatment beam in such situations, thereby reducing the probability of serious geometric and dosimetric errors. PMID:28075331

Predictive modeling of respiratory tumor motion for real-time prediction of baseline shifts.

PubMed

Balasubramanian, A; Shamsuddin, R; Prabhakaran, B; Sawant, A

2017-03-07

Baseline shifts in respiratory patterns can result in significant spatiotemporal changes in patient anatomy (compared to that captured during simulation), in turn, causing geometric and dosimetric errors in the administration of thoracic and abdominal radiotherapy. We propose predictive modeling of the tumor motion trajectories for predicting a baseline shift ahead of its occurrence. The key idea is to use the features of the tumor motion trajectory over a 1 min window, and predict the occurrence of a baseline shift in the 5 s that immediately follow (lookahead window). In this study, we explored a preliminary trend-based analysis with multi-class annotations as well as a more focused binary classification analysis. In both analyses, a number of different inter-fraction and intra-fraction training strategies were studied, both offline as well as online, along with data sufficiency and skew compensation for class imbalances. The performance of different training strategies were compared across multiple machine learning classification algorithms, including nearest neighbor, Naïve Bayes, linear discriminant and ensemble Adaboost. The prediction performance is evaluated using metrics such as accuracy, precision, recall and the area under the curve (AUC) for repeater operating characteristics curve. The key results of the trend-based analysis indicate that (i) intra-fraction training strategies achieve highest prediction accuracies (90.5-91.4%); (ii) the predictive modeling yields lowest accuracies (50-60%) when the training data does not include any information from the test patient; (iii) the prediction latencies are as low as a few hundred milliseconds, and thus conducive for real-time prediction. The binary classification performance is promising, indicated by high AUCs (0.96-0.98). It also confirms the utility of prior data from previous patients, and also the necessity of training the classifier on some initial data from the new patient for reasonable prediction performance. The ability to predict a baseline shift with a sufficient look-ahead window will enable clinical systems or even human users to hold the treatment beam in such situations, thereby reducing the probability of serious geometric and dosimetric errors.

Identification of terrain cover using the optimum polarimetric classifier

NASA Technical Reports Server (NTRS)

Kong, J. A.; Swartz, A. A.; Yueh, H. A.; Novak, L. M.; Shin, R. T.

1988-01-01

A systematic approach for the identification of terrain media such as vegetation canopy, forest, and snow-covered fields is developed using the optimum polarimetric classifier. The covariance matrices for various terrain cover are computed from theoretical models of random medium by evaluating the scattering matrix elements. The optimal classification scheme makes use of a quadratic distance measure and is applied to classify a vegetation canopy consisting of both trees and grass. Experimentally measured data are used to validate the classification scheme. Analytical and Monte Carlo simulated classification errors using the fully polarimetric feature vector are compared with classification based on single features which include the phase difference between the VV and HH polarization returns. It is shown that the full polarimetric results are optimal and provide better classification performance than single feature measurements.

Classifying nursing errors in clinical management within an Australian hospital.

PubMed

Tran, D T; Johnson, M

2010-12-01

Although many classification systems relating to patient safety exist, no taxonomy was identified that classified nursing errors in clinical management. To develop a classification system for nursing errors relating to clinical management (NECM taxonomy) and to describe contributing factors and patient consequences. We analysed 241 (11%) self-reported incidents relating to clinical management in nursing in a metropolitan hospital. Descriptive analysis of numeric data and content analysis of text data were undertaken to derive the NECM taxonomy, contributing factors and consequences for patients. Clinical management incidents represented 1.63 incidents per 1000 occupied bed days. The four themes of the NECM taxonomy were nursing care process (67%), communication (22%), administrative process (5%), and knowledge and skill (6%). Half of the incidents did not cause any patient harm. Contributing factors (n=111) included the following: patient clinical, social conditions and behaviours (27%); resources (22%); environment and workload (18%); other health professionals (15%); communication (13%); and nurse's knowledge and experience (5%). The NECM taxonomy provides direction to clinicians and managers on areas in clinical management that are most vulnerable to error, and therefore, priorities for system change management. Any nurses who wish to classify nursing errors relating to clinical management could use these types of errors. This study informs further research into risk management behaviour, and self-assessment tools for clinicians. Globally, nurses need to continue to monitor and act upon patient safety issues. © 2010 The Authors. International Nursing Review © 2010 International Council of Nurses.

In-vivo determination of chewing patterns using FBG and artificial neural networks

NASA Astrophysics Data System (ADS)

Pegorini, Vinicius; Zen Karam, Leandro; Rocha Pitta, Christiano S.; Ribeiro, Richardson; Simioni Assmann, Tangriani; Cardozo da Silva, Jean Carlos; Bertotti, Fábio L.; Kalinowski, Hypolito J.; Cardoso, Rafael

2015-09-01

This paper reports the process of pattern classification of the chewing process of ruminants. We propose a simplified signal processing scheme for optical fiber Bragg grating (FBG) sensors based on machine learning techniques. The FBG sensors measure the biomechanical forces during jaw movements and an artificial neural network is responsible for the classification of the associated chewing pattern. In this study, three patterns associated to dietary supplement, hay and ryegrass were considered. Additionally, two other important events for ingestive behavior studies were monitored, rumination and idle period. Experimental results show that the proposed approach for pattern classification has been capable of differentiating the materials involved in the chewing process with a small classification error.

Accuracy assessment, using stratified plurality sampling, of portions of a LANDSAT classification of the Arctic National Wildlife Refuge Coastal Plain

NASA Technical Reports Server (NTRS)

Card, Don H.; Strong, Laurence L.

1989-01-01

An application of a classification accuracy assessment procedure is described for a vegetation and land cover map prepared by digital image processing of LANDSAT multispectral scanner data. A statistical sampling procedure called Stratified Plurality Sampling was used to assess the accuracy of portions of a map of the Arctic National Wildlife Refuge coastal plain. Results are tabulated as percent correct classification overall as well as per category with associated confidence intervals. Although values of percent correct were disappointingly low for most categories, the study was useful in highlighting sources of classification error and demonstrating shortcomings of the plurality sampling method.

Hyperspectral image classification based on local binary patterns and PCANet

NASA Astrophysics Data System (ADS)

Yang, Huizhen; Gao, Feng; Dong, Junyu; Yang, Yang

2018-04-01

Hyperspectral image classification has been well acknowledged as one of the challenging tasks of hyperspectral data processing. In this paper, we propose a novel hyperspectral image classification framework based on local binary pattern (LBP) features and PCANet. In the proposed method, linear prediction error (LPE) is first employed to select a subset of informative bands, and LBP is utilized to extract texture features. Then, spectral and texture features are stacked into a high dimensional vectors. Next, the extracted features of a specified position are transformed to a 2-D image. The obtained images of all pixels are fed into PCANet for classification. Experimental results on real hyperspectral dataset demonstrate the effectiveness of the proposed method.

Influence of nuclei segmentation on breast cancer malignancy classification

NASA Astrophysics Data System (ADS)

Jelen, Lukasz; Fevens, Thomas; Krzyzak, Adam

2009-02-01

Breast Cancer is one of the most deadly cancers affecting middle-aged women. Accurate diagnosis and prognosis are crucial to reduce the high death rate. Nowadays there are numerous diagnostic tools for breast cancer diagnosis. In this paper we discuss a role of nuclear segmentation from fine needle aspiration biopsy (FNA) slides and its influence on malignancy classification. Classification of malignancy plays a very important role during the diagnosis process of breast cancer. Out of all cancer diagnostic tools, FNA slides provide the most valuable information about the cancer malignancy grade which helps to choose an appropriate treatment. This process involves assessing numerous nuclear features and therefore precise segmentation of nuclei is very important. In this work we compare three powerful segmentation approaches and test their impact on the classification of breast cancer malignancy. The studied approaches involve level set segmentation, fuzzy c-means segmentation and textural segmentation based on co-occurrence matrix. Segmented nuclei were used to extract nuclear features for malignancy classification. For classification purposes four different classifiers were trained and tested with previously extracted features. The compared classifiers are Multilayer Perceptron (MLP), Self-Organizing Maps (SOM), Principal Component-based Neural Network (PCA) and Support Vector Machines (SVM). The presented results show that level set segmentation yields the best results over the three compared approaches and leads to a good feature extraction with a lowest average error rate of 6.51% over four different classifiers. The best performance was recorded for multilayer perceptron with an error rate of 3.07% using fuzzy c-means segmentation.

Beyond Error Patterns: A Sociocultural View of Fraction Comparison Errors in Students with Mathematical Learning Disabilities

ERIC Educational Resources Information Center

Lewis, Katherine E.

2016-01-01

Although many students struggle with fractions, students with mathematical learning disabilities (MLDs) experience pervasive difficulties because of neurological differences in how they process numerical information. These students make errors that are qualitatively different than their typically achieving and low-achieving peers. This study…

A real-time heat strain risk classifier using heart rate and skin temperature.

PubMed

Buller, Mark J; Latzka, William A; Yokota, Miyo; Tharion, William J; Moran, Daniel S

2008-12-01

Heat injury is a real concern to workers engaged in physically demanding tasks in high heat strain environments. Several real-time physiological monitoring systems exist that can provide indices of heat strain, e.g. physiological strain index (PSI), and provide alerts to medical personnel. However, these systems depend on core temperature measurement using expensive, ingestible thermometer pills. Seeking a better solution, we suggest the use of a model which can identify the probability that individuals are 'at risk' from heat injury using non-invasive measures. The intent is for the system to identify individuals who need monitoring more closely or who should apply heat strain mitigation strategies. We generated a model that can identify 'at risk' (PSI 7.5) workers from measures of heart rate and chest skin temperature. The model was built using data from six previously published exercise studies in which some subjects wore chemical protective equipment. The model has an overall classification error rate of 10% with one false negative error (2.7%), and outperforms an earlier model and a least squares regression model with classification errors of 21% and 14%, respectively. Additionally, the model allows the classification criteria to be adjusted based on the task and acceptable level of risk. We conclude that the model could be a valuable part of a multi-faceted heat strain management system.

Feature extraction and classification algorithms for high dimensional data

NASA Technical Reports Server (NTRS)

Lee, Chulhee; Landgrebe, David

1993-01-01

Feature extraction and classification algorithms for high dimensional data are investigated. Developments with regard to sensors for Earth observation are moving in the direction of providing much higher dimensional multispectral imagery than is now possible. In analyzing such high dimensional data, processing time becomes an important factor. With large increases in dimensionality and the number of classes, processing time will increase significantly. To address this problem, a multistage classification scheme is proposed which reduces the processing time substantially by eliminating unlikely classes from further consideration at each stage. Several truncation criteria are developed and the relationship between thresholds and the error caused by the truncation is investigated. Next an approach to feature extraction for classification is proposed based directly on the decision boundaries. It is shown that all the features needed for classification can be extracted from decision boundaries. A characteristic of the proposed method arises by noting that only a portion of the decision boundary is effective in discriminating between classes, and the concept of the effective decision boundary is introduced. The proposed feature extraction algorithm has several desirable properties: it predicts the minimum number of features necessary to achieve the same classification accuracy as in the original space for a given pattern recognition problem; and it finds the necessary feature vectors. The proposed algorithm does not deteriorate under the circumstances of equal means or equal covariances as some previous algorithms do. In addition, the decision boundary feature extraction algorithm can be used both for parametric and non-parametric classifiers. Finally, some problems encountered in analyzing high dimensional data are studied and possible solutions are proposed. First, the increased importance of the second order statistics in analyzing high dimensional data is recognized. By investigating the characteristics of high dimensional data, the reason why the second order statistics must be taken into account in high dimensional data is suggested. Recognizing the importance of the second order statistics, there is a need to represent the second order statistics. A method to visualize statistics using a color code is proposed. By representing statistics using color coding, one can easily extract and compare the first and the second statistics.

Automated Segmentation Errors When Using Optical Coherence Tomography to Measure Retinal Nerve Fiber Layer Thickness in Glaucoma.

PubMed

Mansberger, Steven L; Menda, Shivali A; Fortune, Brad A; Gardiner, Stuart K; Demirel, Shaban

2017-02-01

To characterize the error of optical coherence tomography (OCT) measurements of retinal nerve fiber layer (RNFL) thickness when using automated retinal layer segmentation algorithms without manual refinement. Cross-sectional study. This study was set in a glaucoma clinical practice, and the dataset included 3490 scans from 412 eyes of 213 individuals with a diagnosis of glaucoma or glaucoma suspect. We used spectral domain OCT (Spectralis) to measure RNFL thickness in a 6-degree peripapillary circle, and exported the native "automated segmentation only" results. In addition, we exported the results after "manual refinement" to correct errors in the automated segmentation of the anterior (internal limiting membrane) and the posterior boundary of the RNFL. Our outcome measures included differences in RNFL thickness and glaucoma classification (i.e., normal, borderline, or outside normal limits) between scans with automated segmentation only and scans using manual refinement. Automated segmentation only resulted in a thinner global RNFL thickness (1.6 μm thinner, P < .001) when compared to manual refinement. When adjusted by operator, a multivariate model showed increased differences with decreasing RNFL thickness (P < .001), decreasing scan quality (P < .001), and increasing age (P < .03). Manual refinement changed 298 of 3486 (8.5%) of scans to a different global glaucoma classification, wherein 146 of 617 (23.7%) of borderline classifications became normal. Superior and inferior temporal clock hours had the largest differences. Automated segmentation without manual refinement resulted in reduced global RNFL thickness and overestimated the classification of glaucoma. Differences increased in eyes with a thinner RNFL thickness, older age, and decreased scan quality. Operators should inspect and manually refine OCT retinal layer segmentation when assessing RNFL thickness in the management of patients with glaucoma. Copyright © 2016 Elsevier Inc. All rights reserved.

Modeling the Time-Varying Nature of Student Exceptionality Classification on Achievement Growth

ERIC Educational Resources Information Center

Nese, Joseph F. T.; Stevens, Joseph J.; Schulte, Ann C.; Tindal, Gerald; Elliott, Stephen N.

2017-01-01

Our purpose was to examine different approaches to modeling the time-varying nature of exceptionality classification. Using longitudinal data from one state's mathematics achievement test for 28,829 students in Grades 3 to 8, we describe the reclassification rate within special education and between general and special education, and compare four…

Compensatory neurofuzzy model for discrete data classification in biomedical

NASA Astrophysics Data System (ADS)

Ceylan, Rahime

2015-03-01

Biomedical data is separated to two main sections: signals and discrete data. So, studies in this area are about biomedical signal classification or biomedical discrete data classification. There are artificial intelligence models which are relevant to classification of ECG, EMG or EEG signals. In same way, in literature, many models exist for classification of discrete data taken as value of samples which can be results of blood analysis or biopsy in medical process. Each algorithm could not achieve high accuracy rate on classification of signal and discrete data. In this study, compensatory neurofuzzy network model is presented for classification of discrete data in biomedical pattern recognition area. The compensatory neurofuzzy network has a hybrid and binary classifier. In this system, the parameters of fuzzy systems are updated by backpropagation algorithm. The realized classifier model is conducted to two benchmark datasets (Wisconsin Breast Cancer dataset and Pima Indian Diabetes dataset). Experimental studies show that compensatory neurofuzzy network model achieved 96.11% accuracy rate in classification of breast cancer dataset and 69.08% accuracy rate was obtained in experiments made on diabetes dataset with only 10 iterations.

A graph lattice approach to maintaining and learning dense collections of subgraphs as image features.

PubMed

Saund, Eric

2013-10-01

Effective object and scene classification and indexing depend on extraction of informative image features. This paper shows how large families of complex image features in the form of subgraphs can be built out of simpler ones through construction of a graph lattice—a hierarchy of related subgraphs linked in a lattice. Robustness is achieved by matching many overlapping and redundant subgraphs, which allows the use of inexpensive exact graph matching, instead of relying on expensive error-tolerant graph matching to a minimal set of ideal model graphs. Efficiency in exact matching is gained by exploitation of the graph lattice data structure. Additionally, the graph lattice enables methods for adaptively growing a feature space of subgraphs tailored to observed data. We develop the approach in the domain of rectilinear line art, specifically for the practical problem of document forms recognition. We are especially interested in methods that require only one or very few labeled training examples per category. We demonstrate two approaches to using the subgraph features for this purpose. Using a bag-of-words feature vector we achieve essentially single-instance learning on a benchmark forms database, following an unsupervised clustering stage. Further performance gains are achieved on a more difficult dataset using a feature voting method and feature selection procedure.

3D Tracking via Shoe Sensing.

PubMed

Li, Fangmin; Liu, Guo; Liu, Jian; Chen, Xiaochuang; Ma, Xiaolin

2016-10-28

Most location-based services are based on a global positioning system (GPS), which only works well in outdoor environments. Compared to outdoor environments, indoor localization has created more buzz in recent years as people spent most of their time indoors working at offices and shopping at malls, etc. Existing solutions mainly rely on inertial sensors (i.e., accelerometer and gyroscope) embedded in mobile devices, which are usually not accurate enough to be useful due to the mobile devices' random movements while people are walking. In this paper, we propose the use of shoe sensing (i.e., sensors attached to shoes) to achieve 3D indoor positioning. Specifically, a short-time energy-based approach is used to extract the gait pattern. Moreover, in order to improve the accuracy of vertical distance estimation while the person is climbing upstairs, a state classification is designed to distinguish the walking status including plane motion (i.e., normal walking and jogging horizontally), walking upstairs, and walking downstairs. Furthermore, we also provide a mechanism to reduce the vertical distance accumulation error. Experimental results show that we can achieve nearly 100% accuracy when extracting gait patterns from walking/jogging with a low-cost shoe sensor, and can also achieve 3D indoor real-time positioning with high accuracy.

Discriminative Hierarchical K-Means Tree for Large-Scale Image Classification.

PubMed

Chen, Shizhi; Yang, Xiaodong; Tian, Yingli

2015-09-01

A key challenge in large-scale image classification is how to achieve efficiency in terms of both computation and memory without compromising classification accuracy. The learning-based classifiers achieve the state-of-the-art accuracies, but have been criticized for the computational complexity that grows linearly with the number of classes. The nonparametric nearest neighbor (NN)-based classifiers naturally handle large numbers of categories, but incur prohibitively expensive computation and memory costs. In this brief, we present a novel classification scheme, i.e., discriminative hierarchical K-means tree (D-HKTree), which combines the advantages of both learning-based and NN-based classifiers. The complexity of the D-HKTree only grows sublinearly with the number of categories, which is much better than the recent hierarchical support vector machines-based methods. The memory requirement is the order of magnitude less than the recent Naïve Bayesian NN-based approaches. The proposed D-HKTree classification scheme is evaluated on several challenging benchmark databases and achieves the state-of-the-art accuracies, while with significantly lower computation cost and memory requirement.

Brain fingerprinting classification concealed information test detects US Navy military medical information with P300

PubMed Central

Farwell, Lawrence A.; Richardson, Drew C.; Richardson, Graham M.; Furedy, John J.

2014-01-01

A classification concealed information test (CIT) used the “brain fingerprinting” method of applying P300 event-related potential (ERP) in detecting information that is (1) acquired in real life and (2) unique to US Navy experts in military medicine. Military medicine experts and non-experts were asked to push buttons in response to three types of text stimuli. Targets contain known information relevant to military medicine, are identified to subjects as relevant, and require pushing one button. Subjects are told to push another button to all other stimuli. Probes contain concealed information relevant to military medicine, and are not identified to subjects. Irrelevants contain equally plausible, but incorrect/irrelevant information. Error rate was 0%. Median and mean statistical confidences for individual determinations were 99.9% with no indeterminates (results lacking sufficiently high statistical confidence to be classified). We compared error rate and statistical confidence for determinations of both information present and information absent produced by classification CIT (Is a probe ERP more similar to a target or to an irrelevant ERP?) vs. comparison CIT (Does a probe produce a larger ERP than an irrelevant?) using P300 plus the late negative component (LNP; together, P300-MERMER). Comparison CIT produced a significantly higher error rate (20%) and lower statistical confidences: mean 67%; information-absent mean was 28.9%, less than chance (50%). We compared analysis using P300 alone with the P300 + LNP. P300 alone produced the same 0% error rate but significantly lower statistical confidences. These findings add to the evidence that the brain fingerprinting methods as described here provide sufficient conditions to produce less than 1% error rate and greater than 95% median statistical confidence in a CIT on information obtained in the course of real life that is characteristic of individuals with specific training, expertise, or organizational affiliation. PMID:25565941

Morbidity Assessment in Surgery: Refinement Proposal Based on a Concept of Perioperative Adverse Events

PubMed Central

Kazaryan, Airazat M.; Røsok, Bård I.; Edwin, Bjørn

2013-01-01

Background. Morbidity is a cornerstone assessing surgical treatment; nevertheless surgeons have not reached extensive consensus on this problem. Methods and Findings. Clavien, Dindo, and Strasberg with coauthors (1992, 2004, 2009, and 2010) made significant efforts to the standardization of surgical morbidity (Clavien-Dindo-Strasberg classification, last revision, the Accordion classification). However, this classification includes only postoperative complications and has two principal shortcomings: disregard of intraoperative events and confusing terminology. Postoperative events have a major impact on patient well-being. However, intraoperative events should also be recorded and reported even if they do not evidently affect the patient's postoperative well-being. The term surgical complication applied in the Clavien-Dindo-Strasberg classification may be regarded as an incident resulting in a complication caused by technical failure of surgery, in contrast to the so-called medical complications. Therefore, the term surgical complication contributes to misinterpretation of perioperative morbidity. The term perioperative adverse events comprising both intraoperative unfavourable incidents and postoperative complications could be regarded as better alternative. In 2005, Satava suggested a simple grading to evaluate intraoperative surgical errors. Based on that approach, we have elaborated a 3-grade classification of intraoperative incidents so that it can be used to grade intraoperative events of any type of surgery. Refinements have been made to the Accordion classification of postoperative complications. Interpretation. The proposed systematization of perioperative adverse events utilizing the combined application of two appraisal tools, that is, the elaborated classification of intraoperative incidents on the basis of the Satava approach to surgical error evaluation together with the modified Accordion classification of postoperative complication, appears to be an effective tool for comprehensive assessment of surgical outcomes. This concept was validated in regard to various surgical procedures. Broad implementation of this approach will promote the development of surgical science and practice. PMID:23762627

Entropy-based gene ranking without selection bias for the predictive classification of microarray data.

PubMed

Furlanello, Cesare; Serafini, Maria; Merler, Stefano; Jurman, Giuseppe

2003-11-06

We describe the E-RFE method for gene ranking, which is useful for the identification of markers in the predictive classification of array data. The method supports a practical modeling scheme designed to avoid the construction of classification rules based on the selection of too small gene subsets (an effect known as the selection bias, in which the estimated predictive errors are too optimistic due to testing on samples already considered in the feature selection process). With E-RFE, we speed up the recursive feature elimination (RFE) with SVM classifiers by eliminating chunks of uninteresting genes using an entropy measure of the SVM weights distribution. An optimal subset of genes is selected according to a two-strata model evaluation procedure: modeling is replicated by an external stratified-partition resampling scheme, and, within each run, an internal K-fold cross-validation is used for E-RFE ranking. Also, the optimal number of genes can be estimated according to the saturation of Zipf's law profiles. Without a decrease of classification accuracy, E-RFE allows a speed-up factor of 100 with respect to standard RFE, while improving on alternative parametric RFE reduction strategies. Thus, a process for gene selection and error estimation is made practical, ensuring control of the selection bias, and providing additional diagnostic indicators of gene importance.

DMSP SSJ4 Data Restoration, Classification, and On-Line Data Access

NASA Technical Reports Server (NTRS)

Wing, Simon; Bredekamp, Joseph H. (Technical Monitor)

2000-01-01

Compress and clean raw data file for permanent storage We have identified various error conditions/types and developed algorithms to get rid of these errors/noises, including the more complicated noise in the newer data sets. (status = 100% complete). Internet access of compacted raw data. It is now possible to access the raw data via our web site, http://www.jhuapl.edu/Aurora/index.html. The software to read and plot the compacted raw data is also available from the same web site. The users can now download the raw data, read, plot, or manipulate the data as they wish on their own computer. The users are able to access the cleaned data sets. Internet access of the color spectrograms. This task has also been completed. It is now possible to access the spectrograms from the web site mentioned above. Improve the particle precipitation region classification. The algorithm for doing this task has been developed and implemented. As a result, the accuracies improved. Now the web site routinely distributes the results of applying the new algorithm to the cleaned data set. Mark the classification region on the spectrograms. The software to mark the classification region in the spectrograms has been completed. This is also available from our web site.

Malingering in Toxic Exposure. Classification Accuracy of Reliable Digit Span and WAIS-III Digit Span Scaled Scores

ERIC Educational Resources Information Center

Greve, Kevin W.; Springer, Steven; Bianchini, Kevin J.; Black, F. William; Heinly, Matthew T.; Love, Jeffrey M.; Swift, Douglas A.; Ciota, Megan A.

2007-01-01

This study examined the sensitivity and false-positive error rate of reliable digit span (RDS) and the WAIS-III Digit Span (DS) scaled score in persons alleging toxic exposure and determined whether error rates differed from published rates in traumatic brain injury (TBI) and chronic pain (CP). Data were obtained from the files of 123 persons…

The potential for intelligent decision support systems to improve the quality and consistency of medication reviews.

PubMed

Bindoff, I; Stafford, A; Peterson, G; Kang, B H; Tenni, P

2012-08-01

Drug-related problems (DRPs) are of serious concern worldwide, particularly for the elderly who often take many medications simultaneously. Medication reviews have been demonstrated to improve medication usage, leading to reductions in DRPs and potential savings in healthcare costs. However, medication reviews are not always of a consistently high standard, and there is often room for improvement in the quality of their findings. Our aim was to produce computerized intelligent decision support software that can improve the consistency and quality of medication review reports, by helping to ensure that DRPs relevant to a patient are overlooked less frequently. A system that largely achieved this goal was previously published, but refinements have been made. This paper examines the results of both the earlier and newer systems. Two prototype multiple-classification ripple-down rules medication review systems were built, the second being a refinement of the first. Each of the systems was trained incrementally using a human medication review expert. The resultant knowledge bases were analysed and compared, showing factors such as accuracy, time taken to train, and potential errors avoided. The two systems performed well, achieving accuracies of approximately 80% and 90%, after being trained on only a small number of cases (126 and 244 cases, respectively). Through analysis of the available data, it was estimated that without the system intervening, the expert training the first prototype would have missed approximately 36% of potentially relevant DRPs, and the second 43%. However, the system appeared to prevent the majority of these potential expert errors by correctly identifying the DRPs for them, leaving only an estimated 8% error rate for the first expert and 4% for the second. These intelligent decision support systems have shown a clear potential to substantially improve the quality and consistency of medication reviews, which should in turn translate into improved medication usage if they were implemented into routine use. © 2011 Blackwell Publishing Ltd.

Software errors and complexity: An empirical investigation

NASA Technical Reports Server (NTRS)

Basili, Victor R.; Perricone, Berry T.

1983-01-01

The distributions and relationships derived from the change data collected during the development of a medium scale satellite software project show that meaningful results can be obtained which allow an insight into software traits and the environment in which it is developed. Modified and new modules were shown to behave similarly. An abstract classification scheme for errors which allows a better understanding of the overall traits of a software project is also shown. Finally, various size and complexity metrics are examined with respect to errors detected within the software yielding some interesting results.

Software errors and complexity: An empirical investigation

NASA Technical Reports Server (NTRS)

Basili, V. R.; Perricone, B. T.

1982-01-01

The distributions and relationships derived from the change data collected during the development of a medium scale satellite software project show that meaningful results can be obtained which allow an insight into software traits and the environment in which it is developed. Modified and new modules were shown to behave similarly. An abstract classification scheme for errors which allows a better understanding of the overall traits of a software project is also shown. Finally, various size and complexity metrics are examined with respect to errors detected within the software yielding some interesting results.

Empirically Estimable Classification Bounds Based on a Nonparametric Divergence Measure

PubMed Central

Berisha, Visar; Wisler, Alan; Hero, Alfred O.; Spanias, Andreas

2015-01-01

Information divergence functions play a critical role in statistics and information theory. In this paper we show that a non-parametric f-divergence measure can be used to provide improved bounds on the minimum binary classification probability of error for the case when the training and test data are drawn from the same distribution and for the case where there exists some mismatch between training and test distributions. We confirm the theoretical results by designing feature selection algorithms using the criteria from these bounds and by evaluating the algorithms on a series of pathological speech classification tasks. PMID:26807014

Comparisons of neural networks to standard techniques for image classification and correlation

NASA Technical Reports Server (NTRS)

Paola, Justin D.; Schowengerdt, Robert A.

1994-01-01

Neural network techniques for multispectral image classification and spatial pattern detection are compared to the standard techniques of maximum-likelihood classification and spatial correlation. The neural network produced a more accurate classification than maximum-likelihood of a Landsat scene of Tucson, Arizona. Some of the errors in the maximum-likelihood classification are illustrated using decision region and class probability density plots. As expected, the main drawback to the neural network method is the long time required for the training stage. The network was trained using several different hidden layer sizes to optimize both the classification accuracy and training speed, and it was found that one node per class was optimal. The performance improved when 3x3 local windows of image data were entered into the net. This modification introduces texture into the classification without explicit calculation of a texture measure. Larger windows were successfully used for the detection of spatial features in Landsat and Magellan synthetic aperture radar imagery.

Implications of Error Analysis Studies for Academic Interventions

ERIC Educational Resources Information Center

Mather, Nancy; Wendling, Barbara J.

2017-01-01

We reviewed 13 studies that focused on analyzing student errors on achievement tests from the Kaufman Test of Educational Achievement-Third edition (KTEA-3). The intent was to determine what instructional implications could be derived from in-depth error analysis. As we reviewed these studies, several themes emerged. We explain how a careful…

Analysis and application of classification methods of complex carbonate reservoirs

NASA Astrophysics Data System (ADS)

Li, Xiongyan; Qin, Ruibao; Ping, Haitao; Wei, Dan; Liu, Xiaomei

2018-06-01

There are abundant carbonate reservoirs from the Cenozoic to Mesozoic era in the Middle East. Due to variation in sedimentary environment and diagenetic process of carbonate reservoirs, several porosity types coexist in carbonate reservoirs. As a result, because of the complex lithologies and pore types as well as the impact of microfractures, the pore structure is very complicated. Therefore, it is difficult to accurately calculate the reservoir parameters. In order to accurately evaluate carbonate reservoirs, based on the pore structure evaluation of carbonate reservoirs, the classification methods of carbonate reservoirs are analyzed based on capillary pressure curves and flow units. Based on the capillary pressure curves, although the carbonate reservoirs can be classified, the relationship between porosity and permeability after classification is not ideal. On the basis of the flow units, the high-precision functional relationship between porosity and permeability after classification can be established. Therefore, the carbonate reservoirs can be quantitatively evaluated based on the classification of flow units. In the dolomite reservoirs, the average absolute error of calculated permeability decreases from 15.13 to 7.44 mD. Similarly, the average absolute error of calculated permeability of limestone reservoirs is reduced from 20.33 to 7.37 mD. Only by accurately characterizing pore structures and classifying reservoir types, reservoir parameters could be calculated accurately. Therefore, characterizing pore structures and classifying reservoir types are very important to accurate evaluation of complex carbonate reservoirs in the Middle East.

Early math and reading achievement are associated with the error positivity.

PubMed

Kim, Matthew H; Grammer, Jennie K; Marulis, Loren M; Carrasco, Melisa; Morrison, Frederick J; Gehring, William J

2016-12-01

Executive functioning (EF) and motivation are associated with academic achievement and error-related ERPs. The present study explores whether early academic skills predict variability in the error-related negativity (ERN) and error positivity (Pe). Data from 113 three- to seven-year-old children in a Go/No-Go task revealed that stronger early reading and math skills predicted a larger Pe. Closer examination revealed that this relation was quadratic and significant for children performing at or near grade level, but not significant for above-average achievers. Early academics did not predict the ERN. These findings suggest that the Pe - which reflects individual differences in motivational processes as well as attention - may be associated with early academic achievement. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.

Automated Cancer Registry Notifications: Validation of a Medical Text Analytics System for Identifying Patients with Cancer from a State-Wide Pathology Repository

PubMed Central

Nguyen, Anthony N; Moore, Julie; O'Dwyer, John; Philpot, Shoni

2016-01-01

The paper assesses the utility of Medtex on automating Cancer Registry notifications from narrative histology and cytology reports from the Queensland state-wide pathology information system. A corpus of 45.3 million pathology HL7 messages (including 119,581 histology and cytology reports) from a Queensland pathology repository for the year of 2009 was analysed by Medtex for cancer notification. Reports analysed by Medtex were consolidated at a patient level and compared against patients with notifiable cancers from the Queensland Oncology Repository (QOR). A stratified random sample of 1,000 patients was manually reviewed by a cancer clinical coder to analyse agreements and discrepancies. Sensitivity of 96.5% (95% confidence interval: 94.5-97.8%), specificity of 96.5% (95.3-97.4%) and positive predictive value of 83.7% (79.6-86.8%) were achieved for identifying cancer notifiable patients. Medtex achieved high sensitivity and specificity across the breadth of cancers, report types, pathology laboratories and pathologists throughout the State of Queensland. The high sensitivity also resulted in the identification of cancer patients that were not found in the QOR. High sensitivity was at the expense of positive predictive value; however, these cases may be considered as lower priority to Cancer Registries as they can be quickly reviewed. Error analysis revealed that system errors tended to be tumour stream dependent. Medtex is proving to be a promising medical text analytic system. High value cancer information can be generated through intelligent data classification and extraction on large volumes of unstructured pathology reports. PMID:28269893

Automated Cancer Registry Notifications: Validation of a Medical Text Analytics System for Identifying Patients with Cancer from a State-Wide Pathology Repository.

PubMed

Nguyen, Anthony N; Moore, Julie; O'Dwyer, John; Philpot, Shoni

2016-01-01

The paper assesses the utility of Medtex on automating Cancer Registry notifications from narrative histology and cytology reports from the Queensland state-wide pathology information system. A corpus of 45.3 million pathology HL7 messages (including 119,581 histology and cytology reports) from a Queensland pathology repository for the year of 2009 was analysed by Medtex for cancer notification. Reports analysed by Medtex were consolidated at a patient level and compared against patients with notifiable cancers from the Queensland Oncology Repository (QOR). A stratified random sample of 1,000 patients was manually reviewed by a cancer clinical coder to analyse agreements and discrepancies. Sensitivity of 96.5% (95% confidence interval: 94.5-97.8%), specificity of 96.5% (95.3-97.4%) and positive predictive value of 83.7% (79.6-86.8%) were achieved for identifying cancer notifiable patients. Medtex achieved high sensitivity and specificity across the breadth of cancers, report types, pathology laboratories and pathologists throughout the State of Queensland. The high sensitivity also resulted in the identification of cancer patients that were not found in the QOR. High sensitivity was at the expense of positive predictive value; however, these cases may be considered as lower priority to Cancer Registries as they can be quickly reviewed. Error analysis revealed that system errors tended to be tumour stream dependent. Medtex is proving to be a promising medical text analytic system. High value cancer information can be generated through intelligent data classification and extraction on large volumes of unstructured pathology reports.

LiDAR point classification based on sparse representation

NASA Astrophysics Data System (ADS)

Li, Nan; Pfeifer, Norbert; Liu, Chun

2017-04-01

In order to combine the initial spatial structure and features of LiDAR data for accurate classification. The LiDAR data is represented as a 4-order tensor. Sparse representation for classification(SRC) method is used for LiDAR tensor classification. It turns out SRC need only a few of training samples from each class, meanwhile can achieve good classification result. Multiple features are extracted from raw LiDAR points to generate a high-dimensional vector at each point. Then the LiDAR tensor is built by the spatial distribution and feature vectors of the point neighborhood. The entries of LiDAR tensor are accessed via four indexes. Each index is called mode: three spatial modes in direction X ,Y ,Z and one feature mode. Sparse representation for classification(SRC) method is proposed in this paper. The sparsity algorithm is to find the best represent the test sample by sparse linear combination of training samples from a dictionary. To explore the sparsity of LiDAR tensor, the tucker decomposition is used. It decomposes a tensor into a core tensor multiplied by a matrix along each mode. Those matrices could be considered as the principal components in each mode. The entries of core tensor show the level of interaction between the different components. Therefore, the LiDAR tensor can be approximately represented by a sparse tensor multiplied by a matrix selected from a dictionary along each mode. The matrices decomposed from training samples are arranged as initial elements in the dictionary. By dictionary learning, a reconstructive and discriminative structure dictionary along each mode is built. The overall structure dictionary composes of class-specified sub-dictionaries. Then the sparse core tensor is calculated by tensor OMP(Orthogonal Matching Pursuit) method based on dictionaries along each mode. It is expected that original tensor should be well recovered by sub-dictionary associated with relevant class, while entries in the sparse tensor associated with other classed should be nearly zero. Therefore, SRC use the reconstruction error associated with each class to do data classification. A section of airborne LiDAR points of Vienna city is used and classified into 6classes: ground, roofs, vegetation, covered ground, walls and other points. Only 6 training samples from each class are taken. For the final classification result, ground and covered ground are merged into one same class(ground). The classification accuracy for ground is 94.60%, roof is 95.47%, vegetation is 85.55%, wall is 76.17%, other object is 20.39%.

Systematic sparse matrix error control for linear scaling electronic structure calculations.

PubMed

Rubensson, Emanuel H; Sałek, Paweł

2005-11-30

Efficient truncation criteria used in multiatom blocked sparse matrix operations for ab initio calculations are proposed. As system size increases, so does the need to stay on top of errors and still achieve high performance. A variant of a blocked sparse matrix algebra to achieve strict error control with good performance is proposed. The presented idea is that the condition to drop a certain submatrix should depend not only on the magnitude of that particular submatrix, but also on which other submatrices that are dropped. The decision to remove a certain submatrix is based on the contribution the removal would cause to the error in the chosen norm. We study the effect of an accumulated truncation error in iterative algorithms like trace correcting density matrix purification. One way to reduce the initial exponential growth of this error is presented. The presented error control for a sparse blocked matrix toolbox allows for achieving optimal performance by performing only necessary operations needed to maintain the requested level of accuracy. Copyright 2005 Wiley Periodicals, Inc.

Improved EEG Event Classification Using Differential Energy.

PubMed

Harati, A; Golmohammadi, M; Lopez, S; Obeid, I; Picone, J

2015-12-01

Feature extraction for automatic classification of EEG signals typically relies on time frequency representations of the signal. Techniques such as cepstral-based filter banks or wavelets are popular analysis techniques in many signal processing applications including EEG classification. In this paper, we present a comparison of a variety of approaches to estimating and postprocessing features. To further aid in discrimination of periodic signals from aperiodic signals, we add a differential energy term. We evaluate our approaches on the TUH EEG Corpus, which is the largest publicly available EEG corpus and an exceedingly challenging task due to the clinical nature of the data. We demonstrate that a variant of a standard filter bank-based approach, coupled with first and second derivatives, provides a substantial reduction in the overall error rate. The combination of differential energy and derivatives produces a 24 % absolute reduction in the error rate and improves our ability to discriminate between signal events and background noise. This relatively simple approach proves to be comparable to other popular feature extraction approaches such as wavelets, but is much more computationally efficient.

Comparison of remote sensing image processing techniques to identify tornado damage areas from Landsat TM data

USGS Publications Warehouse

Myint, S.W.; Yuan, M.; Cerveny, R.S.; Giri, C.P.

2008-01-01

Remote sensing techniques have been shown effective for large-scale damage surveys after a hazardous event in both near real-time or post-event analyses. The paper aims to compare accuracy of common imaging processing techniques to detect tornado damage tracks from Landsat TM data. We employed the direct change detection approach using two sets of images acquired before and after the tornado event to produce a principal component composite images and a set of image difference bands. Techniques in the comparison include supervised classification, unsupervised classification, and objectoriented classification approach with a nearest neighbor classifier. Accuracy assessment is based on Kappa coefficient calculated from error matrices which cross tabulate correctly identified cells on the TM image and commission and omission errors in the result. Overall, the Object-oriented Approach exhibits the highest degree of accuracy in tornado damage detection. PCA and Image Differencing methods show comparable outcomes. While selected PCs can improve detection accuracy 5 to 10%, the Object-oriented Approach performs significantly better with 15-20% higher accuracy than the other two techniques. ?? 2008 by MDPI.

Benchmark data on the separability among crops in the southern San Joaquin Valley of California

NASA Technical Reports Server (NTRS)

Morse, A.; Card, D. H.

1984-01-01

Landsat MSS data were input to a discriminant analysis of 21 crops on each of eight dates in 1979 using a total of 4,142 fields in southern Fresno County, California. The 21 crops, which together account for over 70 percent of the agricultural acreage in the southern San Joaquin Valley, were analyzed to quantify the spectral separability, defined as omission error, between all pairs of crops. On each date the fields were segregated into six groups based on the mean value of the MSS7/MSS5 ratio, which is correlated with green biomass. Discriminant analysis was run on each group on each date. The resulting contingency tables offer information that can be profitably used in conjunction with crop calendars to pick the best dates for a classification. The tables show expected percent correct classification and error rates for all the crops. The patterns in the contingency tables show that the percent correct classification for crops generally increases with the amount of greenness in the fields being classified. However, there are exceptions to this general rule, notably grain.

Comparison of Remote Sensing Image Processing Techniques to Identify Tornado Damage Areas from Landsat TM Data

PubMed Central

Myint, Soe W.; Yuan, May; Cerveny, Randall S.; Giri, Chandra P.

2008-01-01

Remote sensing techniques have been shown effective for large-scale damage surveys after a hazardous event in both near real-time or post-event analyses. The paper aims to compare accuracy of common imaging processing techniques to detect tornado damage tracks from Landsat TM data. We employed the direct change detection approach using two sets of images acquired before and after the tornado event to produce a principal component composite images and a set of image difference bands. Techniques in the comparison include supervised classification, unsupervised classification, and object-oriented classification approach with a nearest neighbor classifier. Accuracy assessment is based on Kappa coefficient calculated from error matrices which cross tabulate correctly identified cells on the TM image and commission and omission errors in the result. Overall, the Object-oriented Approach exhibits the highest degree of accuracy in tornado damage detection. PCA and Image Differencing methods show comparable outcomes. While selected PCs can improve detection accuracy 5 to 10%, the Object-oriented Approach performs significantly better with 15-20% higher accuracy than the other two techniques. PMID:27879757

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.

Remote sensing of submerged aquatic vegetation in lower Chesapeake Bay - A comparison of Landsat MSS to TM imagery

NASA Technical Reports Server (NTRS)

Ackleson, S. G.; Klemas, V.

1987-01-01

Landsat MSS and TM imagery, obtained simultaneously over Guinea Marsh, VA, as analyzed and compares for its ability to detect submerged aquatic vegetation (SAV). An unsupervised clustering algorithm was applied to each image, where the input classification parameters are defined as functions of apparent sensor noise. Class confidence and accuracy were computed for all water areas by comparing the classified images, pixel-by-pixel, to rasterized SAV distributions derived from color aerial photography. To illustrate the effect of water depth on classification error, areas of depth greater than 1.9 m were masked, and class confidence and accuracy recalculated. A single-scattering radiative-transfer model is used to illustrate how percent canopy cover and water depth affect the volume reflectance from a water column containing SAV. For a submerged canopy that is morphologically and optically similar to Zostera marina inhabiting Lower Chesapeake Bay, dense canopies may be isolated by masking optically deep water. For less dense canopies, the effect of increasing water depth is to increase the apparent percent crown cover, which may result in classification error.

Notes on Accuracy of Finite-Volume Discretization Schemes on Irregular Grids

NASA Technical Reports Server (NTRS)

Diskin, Boris; Thomas, James L.

2011-01-01

Truncation-error analysis is a reliable tool in predicting convergence rates of discretization errors on regular smooth grids. However, it is often misleading in application to finite-volume discretization schemes on irregular (e.g., unstructured) grids. Convergence of truncation errors severely degrades on general irregular grids; a design-order convergence can be achieved only on grids with a certain degree of geometric regularity. Such degradation of truncation-error convergence does not necessarily imply a lower-order convergence of discretization errors. In these notes, irregular-grid computations demonstrate that the design-order discretization-error convergence can be achieved even when truncation errors exhibit a lower-order convergence or, in some cases, do not converge at all.

Development and validation of Aviation Causal Contributors for Error Reporting Systems (ACCERS).

PubMed

Baker, David P; Krokos, Kelley J

2007-04-01

This investigation sought to develop a reliable and valid classification system for identifying and classifying the underlying causes of pilot errors reported under the Aviation Safety Action Program (ASAP). ASAP is a voluntary safety program that air carriers may establish to study pilot and crew performance on the line. In ASAP programs, similar to the Aviation Safety Reporting System, pilots self-report incidents by filing a short text description of the event. The identification of contributors to errors is critical if organizations are to improve human performance, yet it is difficult for analysts to extract this information from text narratives. A taxonomy was needed that could be used by pilots to classify the causes of errors. After completing a thorough literature review, pilot interviews and a card-sorting task were conducted in Studies 1 and 2 to develop the initial structure of the Aviation Causal Contributors for Event Reporting Systems (ACCERS) taxonomy. The reliability and utility of ACCERS was then tested in studies 3a and 3b by having pilots independently classify the primary and secondary causes of ASAP reports. The results provided initial evidence for the internal and external validity of ACCERS. Pilots were found to demonstrate adequate levels of agreement with respect to their category classifications. ACCERS appears to be a useful system for studying human error captured under pilot ASAP reports. Future work should focus on how ACCERS is organized and whether it can be used or modified to classify human error in ASAP programs for other aviation-related job categories such as dispatchers. Potential applications of this research include systems in which individuals self-report errors and that attempt to extract and classify the causes of those events.

Automated spectral classification and the GAIA project

NASA Technical Reports Server (NTRS)

Lasala, Jerry; Kurtz, Michael J.

1995-01-01

Two dimensional spectral types for each of the stars observed in the global astrometric interferometer for astrophysics (GAIA) mission would provide additional information for the galactic structure and stellar evolution studies, as well as helping in the identification of unusual objects and populations. The classification of the large quantity generated spectra requires that automated techniques are implemented. Approaches for the automatic classification are reviewed, and a metric-distance method is discussed. In tests, the metric-distance method produced spectral types with mean errors comparable to those of human classifiers working at similar resolution. Data and equipment requirements for an automated classification survey, are discussed. A program of auxiliary observations is proposed to yield spectral types and radial velocities for the GAIA-observed stars.

Speaker normalization and adaptation using second-order connectionist networks.

PubMed

Watrous, R L

1993-01-01

A method for speaker normalization and adaption using connectionist networks is developed. A speaker-specific linear transformation of observations of the speech signal is computed using second-order network units. Classification is accomplished by a multilayer feedforward network that operates on the normalized speech data. The network is adapted for a new talker by modifying the transformation parameters while leaving the classifier fixed. This is accomplished by backpropagating classification error through the classifier to the second-order transformation units. This method was evaluated for the classification of ten vowels for 76 speakers using the first two formant values of the Peterson-Barney data. The results suggest that rapid speaker adaptation resulting in high classification accuracy can be accomplished by this method.

How Achievement Error Patterns of Students with Mild Intellectual Disability Differ from Low IQ and Low Achievement Students without Diagnoses

ERIC Educational Resources Information Center

Root, Melissa M.; Marchis, Lavinia; White, Erica; Courville, Troy; Choi, Dowon; Bray, Melissa A.; Pan, Xingyu; Wayte, Jessica

2017-01-01

This study investigated the differences in error factor scores on the Kaufman Test of Educational Achievement-Third Edition between individuals with mild intellectual disabilities (Mild IDs), those with low achievement scores but average intelligence, and those with low intelligence but without a Mild ID diagnosis. The two control groups were…

Errors in imaging patients in the emergency setting

PubMed Central

Reginelli, Alfonso; Lo Re, Giuseppe; Midiri, Federico; Muzj, Carlo; Romano, Luigia; Brunese, Luca

2016-01-01

Emergency and trauma care produces a “perfect storm” for radiological errors: uncooperative patients, inadequate histories, time-critical decisions, concurrent tasks and often junior personnel working after hours in busy emergency departments. The main cause of diagnostic errors in the emergency department is the failure to correctly interpret radiographs, and the majority of diagnoses missed on radiographs are fractures. Missed diagnoses potentially have important consequences for patients, clinicians and radiologists. Radiologists play a pivotal role in the diagnostic assessment of polytrauma patients and of patients with non-traumatic craniothoracoabdominal emergencies, and key elements to reduce errors in the emergency setting are knowledge, experience and the correct application of imaging protocols. This article aims to highlight the definition and classification of errors in radiology, the causes of errors in emergency radiology and the spectrum of diagnostic errors in radiography, ultrasonography and CT in the emergency setting. PMID:26838955

Errors in imaging patients in the emergency setting.

PubMed

Pinto, Antonio; Reginelli, Alfonso; Pinto, Fabio; Lo Re, Giuseppe; Midiri, Federico; Muzj, Carlo; Romano, Luigia; Brunese, Luca

2016-01-01

Emergency and trauma care produces a "perfect storm" for radiological errors: uncooperative patients, inadequate histories, time-critical decisions, concurrent tasks and often junior personnel working after hours in busy emergency departments. The main cause of diagnostic errors in the emergency department is the failure to correctly interpret radiographs, and the majority of diagnoses missed on radiographs are fractures. Missed diagnoses potentially have important consequences for patients, clinicians and radiologists. Radiologists play a pivotal role in the diagnostic assessment of polytrauma patients and of patients with non-traumatic craniothoracoabdominal emergencies, and key elements to reduce errors in the emergency setting are knowledge, experience and the correct application of imaging protocols. This article aims to highlight the definition and classification of errors in radiology, the causes of errors in emergency radiology and the spectrum of diagnostic errors in radiography, ultrasonography and CT in the emergency setting.

An ensemble-of-classifiers based approach for early diagnosis of Alzheimer's disease: classification using structural features of brain images.

PubMed

Farhan, Saima; Fahiem, Muhammad Abuzar; Tauseef, Huma

2014-01-01

Structural brain imaging is playing a vital role in identification of changes that occur in brain associated with Alzheimer's disease. This paper proposes an automated image processing based approach for the identification of AD from MRI of the brain. The proposed approach is novel in a sense that it has higher specificity/accuracy values despite the use of smaller feature set as compared to existing approaches. Moreover, the proposed approach is capable of identifying AD patients in early stages. The dataset selected consists of 85 age and gender matched individuals from OASIS database. The features selected are volume of GM, WM, and CSF and size of hippocampus. Three different classification models (SVM, MLP, and J48) are used for identification of patients and controls. In addition, an ensemble of classifiers, based on majority voting, is adopted to overcome the error caused by an independent base classifier. Ten-fold cross validation strategy is applied for the evaluation of our scheme. Moreover, to evaluate the performance of proposed approach, individual features and combination of features are fed to individual classifiers and ensemble based classifier. Using size of left hippocampus as feature, the accuracy achieved with ensemble of classifiers is 93.75%, with 100% specificity and 87.5% sensitivity.

Psychological state estimation from physiological recordings during robot-assisted gait rehabilitation.

PubMed

Koenig, Alexander; Omlin, Ximena; Zimmerli, Lukas; Sapa, Mark; Krewer, Carmen; Bolliger, Marc; Müller, Friedemann; Riener, Robert

2011-01-01

Robot-assisted treadmill training is an established intervention used to improve walking ability in patients with neurological disorders. Although it has been shown that attention to the task is a key factor for successful rehabilitation, the psychological state of patients during robot-assisted gait therapy is often neglected. We presented 17 nondisabled subjects and 10 patients with neurological disorders a virtual-reality task with varying difficulty levels to induce feelings of being bored, excited, and overstressed. We developed an approach to automatically estimate and classify a patient's psychological state, i.e., his or her mental engagement, in real time during gait training. We used psychophysiological measurements to obtain an objective measure of the current psychological state. Automatic classification was performed by a neural network. We found that heart rate, skin conductance responses, and skin temperature can be used as markers for psychological states in the presence of physical effort induced by walking. The classifier achieved a classification error of 1.4% for nondisabled subjects and 2.1% for patients with neurological disorders. Using our new method, we processed the psychological state data in real time. Our method is a first step toward real-time auto-adaptive gait training with potential to improve rehabilitation results by optimally challenging patients at all times during exercise.

Retrospective analysis of the Draize test for serious eye damage/eye irritation: importance of understanding the in vivo endpoints under UN GHS/EU CLP for the development and evaluation of in vitro test methods.

PubMed

Adriaens, Els; Barroso, João; Eskes, Chantra; Hoffmann, Sebastian; McNamee, Pauline; Alépée, Nathalie; Bessou-Touya, Sandrine; De Smedt, Ann; De Wever, Bart; Pfannenbecker, Uwe; Tailhardat, Magalie; Zuang, Valérie

2014-03-01

For more than two decades, scientists have been trying to replace the regulatory in vivo Draize eye test by in vitro methods, but so far only partial replacement has been achieved. In order to better understand the reasons for this, historical in vivo rabbit data were analysed in detail and resampled with the purpose of (1) revealing which of the in vivo endpoints are most important in driving United Nations Globally Harmonized System/European Union Regulation on Classification, Labelling and Packaging (UN GHS/EU CLP) classification for serious eye damage/eye irritation and (2) evaluating the method's within-test variability for proposing acceptable and justifiable target values of sensitivity and specificity for alternative methods and their combinations in testing strategies. Among the Cat 1 chemicals evaluated, 36-65 % (depending on the database) were classified based only on persistence of effects, with the remaining being classified mostly based on severe corneal effects. Iritis was found to rarely drive the classification (<4 % of both Cat 1 and Cat 2 chemicals). The two most important endpoints driving Cat 2 classification are conjunctiva redness (75-81 %) and corneal opacity (54-75 %). The resampling analyses demonstrated an overall probability of at least 11 % that chemicals classified as Cat 1 by the Draize eye test could be equally identified as Cat 2 and of about 12 % for Cat 2 chemicals to be equally identified as No Cat. On the other hand, the over-classification error for No Cat and Cat 2 was negligible (<1 %), which strongly suggests a high over-predictive power of the Draize eye test. Moreover, our analyses of the classification drivers suggest a critical revision of the UN GHS/EU CLP decision criteria for the classification of chemicals based on Draize eye test data, in particular Cat 1 based only on persistence of conjunctiva effects or corneal opacity scores of 4. In order to successfully replace the regulatory in vivo Draize eye test, it will be important to recognise these uncertainties and to have in vitro tools to address the most important in vivo endpoints identified in this paper.

Conditional Standard Errors of Measurement for Composite Scores Using IRT

ERIC Educational Resources Information Center

Kolen, Michael J.; Wang, Tianyou; Lee, Won-Chan

2012-01-01

Composite scores are often formed from test scores on educational achievement test batteries to provide a single index of achievement over two or more content areas or two or more item types on that test. Composite scores are subject to measurement error, and as with scores on individual tests, the amount of error variability typically depends on…

Reliability, Validity, and Classification Accuracy of the DSM-5 Diagnostic Criteria for Gambling Disorder and Comparison to DSM-IV.

PubMed

Stinchfield, Randy; McCready, John; Turner, Nigel E; Jimenez-Murcia, Susana; Petry, Nancy M; Grant, Jon; Welte, John; Chapman, Heather; Winters, Ken C

2016-09-01

The DSM-5 was published in 2013 and it included two substantive revisions for gambling disorder (GD). These changes are the reduction in the threshold from five to four criteria and elimination of the illegal activities criterion. The purpose of this study was to twofold. First, to assess the reliability, validity and classification accuracy of the DSM-5 diagnostic criteria for GD. Second, to compare the DSM-5-DSM-IV on reliability, validity, and classification accuracy, including an examination of the effect of the elimination of the illegal acts criterion on diagnostic accuracy. To compare DSM-5 and DSM-IV, eight datasets from three different countries (Canada, USA, and Spain; total N = 3247) were used. All datasets were based on similar research methods. Participants were recruited from outpatient gambling treatment services to represent the group with a GD and from the community to represent the group without a GD. All participants were administered a standardized measure of diagnostic criteria. The DSM-5 yielded satisfactory reliability, validity and classification accuracy. In comparing the DSM-5 to the DSM-IV, most comparisons of reliability, validity and classification accuracy showed more similarities than differences. There was evidence of modest improvements in classification accuracy for DSM-5 over DSM-IV, particularly in reduction of false negative errors. This reduction in false negative errors was largely a function of lowering the cut score from five to four and this revision is an improvement over DSM-IV. From a statistical standpoint, eliminating the illegal acts criterion did not make a significant impact on diagnostic accuracy. From a clinical standpoint, illegal acts can still be addressed in the context of the DSM-5 criterion of lying to others.

Multiple category-lot quality assurance sampling: a new classification system with application to schistosomiasis control.

PubMed

Olives, Casey; Valadez, Joseph J; Brooker, Simon J; Pagano, Marcello

2012-01-01

Originally a binary classifier, Lot Quality Assurance Sampling (LQAS) has proven to be a useful tool for classification of the prevalence of Schistosoma mansoni into multiple categories (≤10%, >10 and <50%, ≥50%), and semi-curtailed sampling has been shown to effectively reduce the number of observations needed to reach a decision. To date the statistical underpinnings for Multiple Category-LQAS (MC-LQAS) have not received full treatment. We explore the analytical properties of MC-LQAS, and validate its use for the classification of S. mansoni prevalence in multiple settings in East Africa. We outline MC-LQAS design principles and formulae for operating characteristic curves. In addition, we derive the average sample number for MC-LQAS when utilizing semi-curtailed sampling and introduce curtailed sampling in this setting. We also assess the performance of MC-LQAS designs with maximum sample sizes of n=15 and n=25 via a weighted kappa-statistic using S. mansoni data collected in 388 schools from four studies in East Africa. Overall performance of MC-LQAS classification was high (kappa-statistic of 0.87). In three of the studies, the kappa-statistic for a design with n=15 was greater than 0.75. In the fourth study, where these designs performed poorly (kappa-statistic less than 0.50), the majority of observations fell in regions where potential error is known to be high. Employment of semi-curtailed and curtailed sampling further reduced the sample size by as many as 0.5 and 3.5 observations per school, respectively, without increasing classification error. This work provides the needed analytics to understand the properties of MC-LQAS for assessing the prevalance of S. mansoni and shows that in most settings a sample size of 15 children provides a reliable classification of schools.

The presence of English and Spanish dyslexia in the Web

NASA Astrophysics Data System (ADS)

Rello, Luz; Baeza-Yates, Ricardo

2012-09-01

In this study we present a lower bound of the prevalence of dyslexia in the Web for English and Spanish. On the basis of analysis of corpora written by dyslexic people, we propose a classification of the different kinds of dyslexic errors. A representative data set of dyslexic words is used to calculate this lower bound in web pages containing English and Spanish dyslexic errors. We also present an analysis of dyslexic errors in major Internet domains, social media sites, and throughout English- and Spanish-speaking countries. To show the independence of our estimations from the presence of other kinds of errors, we compare them with the overall lexical quality of the Web and with the error rate of noncorrected corpora. The presence of dyslexic errors in the Web motivates work in web accessibility for dyslexic users.

Nineteen hundred seventy three significant accomplishments. [Landsat satellite data applications

NASA Technical Reports Server (NTRS)

1974-01-01

Data collected by the Skylab remote sensing satellites was used to develop applications techniques and to combine automatic data classification with statistical clustering methods. Continuing research was concentrated in the correlation and registration of data products and in the definition of the atmospheric effects on remote sensing. The causes of errors encountered in the automated classification of agricultural data are identified. Other applications in forestry, geography, environmental geology, and land use are discussed.

Man-machine interfaces in LACIE/ERIPS

NASA Technical Reports Server (NTRS)

Duprey, B. B. (Principal Investigator)

1979-01-01

One of the most important aspects of the interactive portion of the LACIE/ERIPS software system is the way in which the analysis and decision-making capabilities of a human being are integrated with the speed and accuracy of a computer to produce a powerful analysis system. The three major man-machine interfaces in the system are (1) the use of menus for communications between the software and the interactive user; (2) the checkpoint/restart facility to recreate in one job the internal environment achieved in an earlier one; and (3) the error recovery capability which would normally cause job termination. This interactive system, which executes on an IBM 360/75 mainframe, was adapted for use in noninteractive (batch) mode. A case study is presented to show how the interfaces work in practice by defining some fields based on an image screen display, noting the field definitions, and obtaining a film product of the classification map.

Near Infrared Spectroscopy Detection and Quantification of Herbal Medicines Adulterated with Sibutramine.

PubMed

da Silva, Neirivaldo Cavalcante; Honorato, Ricardo Saldanha; Pimentel, Maria Fernanda; Garrigues, Salvador; Cervera, Maria Luisa; de la Guardia, Miguel

2015-09-01

There is an increasing demand for herbal medicines in weight loss treatment. Some synthetic chemicals, such as sibutramine (SB), have been detected as adulterants in herbal formulations. In this study, two strategies using near infrared (NIR) spectroscopy have been developed to evaluate potential adulteration of herbal medicines with SB: a qualitative screening approach and a quantitative methodology based on multivariate calibration. Samples were composed by products commercialized as herbal medicines, as well as by laboratory adulterated samples. Spectra were obtained in the range of 14,000-4000 per cm. Using PLS-DA, a correct classification of 100% was achieved for the external validation set. In the quantitative approach, the root mean squares error of prediction (RMSEP), for both PLS and MLR models, was 0.2% w/w. The results prove the potential of NIR spectroscopy and multivariate calibration in quantifying sibutramine in adulterated herbal medicines samples. © 2015 American Academy of Forensic Sciences.

2D segmentation of intervertebral discs and its degree of degeneration from T2-weighted magnetic resonance images

NASA Astrophysics Data System (ADS)

Castro-Mateos, Isaac; Pozo, José Maria; Lazary, Aron; Frangi, Alejandro F.

2014-03-01

Low back pain (LBP) is a disorder suffered by a large population around the world. A key factor causing this illness is Intervertebral Disc (IVD) degeneration, whose early diagnosis could help in preventing this widespread condition. Clinicians base their diagnosis on visual inspection of 2D slices of Magnetic Resonance (MR) images, which is subject to large interobserver variability. In this work, an automatic classification method is presented, which provides the Pfirrmann degree of degeneration from a mid-sagittal MR slice. The proposed method utilizes Active Contour Models, with a new geometrical energy, to achieve an initial segmentation, which is further improved using fuzzy C-means. Then, IVDs are classified according to their degree of degeneration. This classification is attained by employing Adaboost on five specific features: the mean and the variance of the probability map of the nucleus using two different approaches and the eccentricity of the fitting ellipse to the contour of the IVD. The classification method was evaluated using a cohort of 150 intervertebral discs assessed by three experts, resulting in a mean specificity (93%) and sensitivity (83%) similar to the one provided by every expert with respect to the most voted value. The segmentation accuracy was evaluated using the Dice Similarity Index (DSI) and Root Mean Square Error (RMSE) of the point-to-contour distance. The mean DSI ± 2 standard deviation was 91:7% ±5:6%, the mean RMSE was 0:82mm and the 95 percentile was 1:36mm. These results were found accurate when compared to the state-of-the-art.

Fast classification and compositional analysis of cornstover fractions using Fourier transform near-infrared techniques.

PubMed

Philip Ye, X; Liu, Lu; Hayes, Douglas; Womac, Alvin; Hong, Kunlun; Sokhansanj, Shahab

2008-10-01

The objectives of this research were to determine the variation of chemical composition across botanical fractions of cornstover, and to probe the potential of Fourier transform near-infrared (FT-NIR) techniques in qualitatively classifying separated cornstover fractions and in quantitatively analyzing chemical compositions of cornstover by developing calibration models to predict chemical compositions of cornstover based on FT-NIR spectra. Large variations of cornstover chemical composition for wide calibration ranges, which is required by a reliable calibration model, were achieved by manually separating the cornstover samples into six botanical fractions, and their chemical compositions were determined by conventional wet chemical analyses, which proved that chemical composition varies significantly among different botanical fractions of cornstover. Different botanic fractions, having total saccharide content in descending order, are husk, sheath, pith, rind, leaf, and node. Based on FT-NIR spectra acquired on the biomass, classification by Soft Independent Modeling of Class Analogy (SIMCA) was employed to conduct qualitative classification of cornstover fractions, and partial least square (PLS) regression was used for quantitative chemical composition analysis. SIMCA was successfully demonstrated in classifying botanical fractions of cornstover. The developed PLS model yielded root mean square error of prediction (RMSEP %w/w) of 0.92, 1.03, 0.17, 0.27, 0.21, 1.12, and 0.57 for glucan, xylan, galactan, arabinan, mannan, lignin, and ash, respectively. The results showed the potential of FT-NIR techniques in combination with multivariate analysis to be utilized by biomass feedstock suppliers, bioethanol manufacturers, and bio-power producers in order to better manage bioenergy feedstocks and enhance bioconversion.

Feature extraction based on extended multi-attribute profiles and sparse autoencoder for remote sensing image classification

NASA Astrophysics Data System (ADS)

Teffahi, Hanane; Yao, Hongxun; Belabid, Nasreddine; Chaib, Souleyman

2018-02-01

The satellite images with very high spatial resolution have been recently widely used in image classification topic as it has become challenging task in remote sensing field. Due to a number of limitations such as the redundancy of features and the high dimensionality of the data, different classification methods have been proposed for remote sensing images classification particularly the methods using feature extraction techniques. This paper propose a simple efficient method exploiting the capability of extended multi-attribute profiles (EMAP) with sparse autoencoder (SAE) for remote sensing image classification. The proposed method is used to classify various remote sensing datasets including hyperspectral and multispectral images by extracting spatial and spectral features based on the combination of EMAP and SAE by linking them to kernel support vector machine (SVM) for classification. Experiments on new hyperspectral image "Huston data" and multispectral image "Washington DC data" shows that this new scheme can achieve better performance of feature learning than the primitive features, traditional classifiers and ordinary autoencoder and has huge potential to achieve higher accuracy for classification in short running time.

Quantitative evaluation of variations in rule-based classifications of land cover in urban neighbourhoods using WorldView-2 imagery.

PubMed

Belgiu, Mariana; Dr Guţ, Lucian; Strobl, Josef

2014-01-01

The increasing availability of high resolution imagery has triggered the need for automated image analysis techniques, with reduced human intervention and reproducible analysis procedures. The knowledge gained in the past might be of use to achieving this goal, if systematically organized into libraries which would guide the image analysis procedure. In this study we aimed at evaluating the variability of digital classifications carried out by three experts who were all assigned the same interpretation task. Besides the three classifications performed by independent operators, we developed an additional rule-based classification that relied on the image classifications best practices found in the literature, and used it as a surrogate for libraries of object characteristics. The results showed statistically significant differences among all operators who classified the same reference imagery. The classifications carried out by the experts achieved satisfactory results when transferred to another area for extracting the same classes of interest, without modification of the developed rules.

Quantitative evaluation of variations in rule-based classifications of land cover in urban neighbourhoods using WorldView-2 imagery

PubMed Central

Belgiu, Mariana; Drǎguţ, Lucian; Strobl, Josef

2014-01-01

The increasing availability of high resolution imagery has triggered the need for automated image analysis techniques, with reduced human intervention and reproducible analysis procedures. The knowledge gained in the past might be of use to achieving this goal, if systematically organized into libraries which would guide the image analysis procedure. In this study we aimed at evaluating the variability of digital classifications carried out by three experts who were all assigned the same interpretation task. Besides the three classifications performed by independent operators, we developed an additional rule-based classification that relied on the image classifications best practices found in the literature, and used it as a surrogate for libraries of object characteristics. The results showed statistically significant differences among all operators who classified the same reference imagery. The classifications carried out by the experts achieved satisfactory results when transferred to another area for extracting the same classes of interest, without modification of the developed rules. PMID:24623959

Quantitative evaluation of variations in rule-based classifications of land cover in urban neighbourhoods using WorldView-2 imagery

NASA Astrophysics Data System (ADS)

Belgiu, Mariana; ǎguţ, Lucian, , Dr; Strobl, Josef

2014-01-01

The increasing availability of high resolution imagery has triggered the need for automated image analysis techniques, with reduced human intervention and reproducible analysis procedures. The knowledge gained in the past might be of use to achieving this goal, if systematically organized into libraries which would guide the image analysis procedure. In this study we aimed at evaluating the variability of digital classifications carried out by three experts who were all assigned the same interpretation task. Besides the three classifications performed by independent operators, we developed an additional rule-based classification that relied on the image classifications best practices found in the literature, and used it as a surrogate for libraries of object characteristics. The results showed statistically significant differences among all operators who classified the same reference imagery. The classifications carried out by the experts achieved satisfactory results when transferred to another area for extracting the same classes of interest, without modification of the developed rules.

Test of spectral/spatial classifier

NASA Technical Reports Server (NTRS)

Landgrebe, D. A. (Principal Investigator); Kast, J. L.; Davis, B. J.

1977-01-01

The author has identified the following significant results. The supervised ECHO processor (which utilizes class statistics for object identification) successfully exploits the redundancy of states characteristic of sampled imagery of ground scenes to achieve better classification accuracy, reduce the number of classifications required, and reduce the variability of classification results. The nonsupervised ECHO processor (which identifies objects without the benefit of class statistics) successfully reduces the number of classifications required and the variability of the classification results.

Biological Gender Differences in Students' Errors on Mathematics Achievement Tests

ERIC Educational Resources Information Center

Stewart, Christie; Root, Melissa M.; Koriakin, Taylor; Choi, Dowon; Luria, Sarah R.; Bray, Melissa A.; Sassu, Kari; Maykel, Cheryl; O'Rourke, Patricia; Courville, Troy

2017-01-01

This study investigated developmental gender differences in mathematics achievement, using the child and adolescent portion (ages 6-19 years) of the Kaufman Test of Educational Achievement-Third Edition (KTEA-3). Participants were divided into two age categories: 6 to 11 and 12 to 19. Error categories within the Math Concepts & Applications…

Error Patterns with Fraction Calculations at Fourth Grade as a Function of Students' Mathematics Achievement Status.

PubMed

Schumacher, Robin F; Malone, Amelia S

2017-09-01

The goal of the present study was to describe fraction-calculation errors among 4 th -grade students and determine whether error patterns differed as a function of problem type (addition vs. subtraction; like vs. unlike denominators), orientation (horizontal vs. vertical), or mathematics-achievement status (low- vs. average- vs. high-achieving). We specifically addressed whether mathematics-achievement status was related to students' tendency to operate with whole number bias. We extended this focus by comparing low-performing students' errors in two instructional settings that focused on two different types of fraction understandings: core instruction that focused on part-whole understanding vs. small-group tutoring that focused on magnitude understanding. Results showed students across the sample were more likely to operate with whole number bias on problems with unlike denominators. Students with low or average achievement (who only participated in core instruction) were more likely to operate with whole number bias than students with low achievement who participated in small-group tutoring. We suggest instruction should emphasize magnitude understanding to sufficiently increase fraction understanding for all students in the upper elementary grades.

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.

Inattention in primary school is not good for your future school achievement-A pattern classification study.

PubMed

Lundervold, Astri J; Bøe, Tormod; Lundervold, Arvid

2017-01-01

Inattention in childhood is associated with academic problems later in life. The contribution of specific aspects of inattentive behaviour is, however, less known. We investigated feature importance of primary school teachers' reports on nine aspects of inattentive behaviour, gender and age in predicting future academic achievement. Primary school teachers of n = 2491 children (7-9 years) rated nine items reflecting different aspects of inattentive behaviour in 2002. A mean academic achievement score from the previous semester in high school (2012) was available for each youth from an official school register. All scores were at a categorical level. Feature importances were assessed by using multinominal logistic regression, classification and regression trees analysis, and a random forest algorithm. Finally, a comprehensive pattern classification procedure using k-fold cross-validation was implemented. Overall, inattention was rated as more severe in boys, who also obtained lower academic achievement scores in high school than girls. Problems related to sustained attention and distractibility were together with age and gender defined as the most important features to predict future achievement scores. Using these four features as input to a collection of classifiers employing k-fold cross-validation for prediction of academic achievement level, we obtained classification accuracy, precision and recall that were clearly better than chance levels. Primary school teachers' reports of problems related to sustained attention and distractibility were identified as the two most important features of inattentive behaviour predicting academic achievement in high school. Identification and follow-up procedures of primary school children showing these characteristics should be prioritised to prevent future academic failure.

Content-based multiple bitstream image transmission over noisy channels.

PubMed

Cao, Lei; Chen, Chang Wen

2002-01-01

In this paper, we propose a novel combined source and channel coding scheme for image transmission over noisy channels. The main feature of the proposed scheme is a systematic decomposition of image sources so that unequal error protection can be applied according to not only bit error sensitivity but also visual content importance. The wavelet transform is adopted to hierarchically decompose the image. The association between the wavelet coefficients and what they represent spatially in the original image is fully exploited so that wavelet blocks are classified based on their corresponding image content. The classification produces wavelet blocks in each class with similar content and statistics, therefore enables high performance source compression using the set partitioning in hierarchical trees (SPIHT) algorithm. To combat the channel noise, an unequal error protection strategy with rate-compatible punctured convolutional/cyclic redundancy check (RCPC/CRC) codes is implemented based on the bit contribution to both peak signal-to-noise ratio (PSNR) and visual quality. At the receiving end, a postprocessing method making use of the SPIHT decoding structure and the classification map is developed to restore the degradation due to the residual error after channel decoding. Experimental results show that the proposed scheme is indeed able to provide protection both for the bits that are more sensitive to errors and for the more important visual content under a noisy transmission environment. In particular, the reconstructed images illustrate consistently better visual quality than using the single-bitstream-based schemes.

Robust Image Regression Based on the Extended Matrix Variate Power Exponential Distribution of Dependent Noise.

PubMed

Luo, Lei; Yang, Jian; Qian, Jianjun; Tai, Ying; Lu, Gui-Fu

2017-09-01

Dealing with partial occlusion or illumination is one of the most challenging problems in image representation and classification. In this problem, the characterization of the representation error plays a crucial role. In most current approaches, the error matrix needs to be stretched into a vector and each element is assumed to be independently corrupted. This ignores the dependence between the elements of error. In this paper, it is assumed that the error image caused by partial occlusion or illumination changes is a random matrix variate and follows the extended matrix variate power exponential distribution. This has the heavy tailed regions and can be used to describe a matrix pattern of l×m dimensional observations that are not independent. This paper reveals the essence of the proposed distribution: it actually alleviates the correlations between pixels in an error matrix E and makes E approximately Gaussian. On the basis of this distribution, we derive a Schatten p -norm-based matrix regression model with L q regularization. Alternating direction method of multipliers is applied to solve this model. To get a closed-form solution in each step of the algorithm, two singular value function thresholding operators are introduced. In addition, the extended Schatten p -norm is utilized to characterize the distance between the test samples and classes in the design of the classifier. Extensive experimental results for image reconstruction and classification with structural noise demonstrate that the proposed algorithm works much more robustly than some existing regression-based methods.

Assessing the accuracy of the International Classification of Diseases codes to identify abusive head trauma: a feasibility study.

PubMed

Berger, Rachel P; Parks, Sharyn; Fromkin, Janet; Rubin, Pamela; Pecora, Peter J

2015-04-01

To assess the accuracy of an International Classification of Diseases (ICD) code-based operational case definition for abusive head trauma (AHT). Subjects were children <5 years of age evaluated for AHT by a hospital-based Child Protection Team (CPT) at a tertiary care paediatric hospital with a completely electronic medical record (EMR) system. Subjects were designated as non-AHT traumatic brain injury (TBI) or AHT based on whether the CPT determined that the injuries were due to AHT. The sensitivity and specificity of the ICD-based definition were calculated. There were 223 children evaluated for AHT: 117 AHT and 106 non-AHT TBI. The sensitivity and specificity of the ICD-based operational case definition were 92% (95% CI 85.8 to 96.2) and 96% (95% CI 92.3 to 99.7), respectively. All errors in sensitivity and three of the four specificity errors were due to coder error; one specificity error was a physician error. In a paediatric tertiary care hospital with an EMR system, the accuracy of an ICD-based case definition for AHT was high. Additional studies are needed to assess the accuracy of this definition in all types of hospitals in which children with AHT are cared for. Published by the BMJ Publishing Group Limited. For permission to use (where not already granted under a licence) please go to http://group.bmj.com/group/rights-licensing/permissions.

Modeling habitat dynamics accounting for possible misclassification

USGS Publications Warehouse

Veran, Sophie; Kleiner, Kevin J.; Choquet, Remi; Collazo, Jaime; Nichols, James D.

2012-01-01

Land cover data are widely used in ecology as land cover change is a major component of changes affecting ecological systems. Landscape change estimates are characterized by classification errors. Researchers have used error matrices to adjust estimates of areal extent, but estimation of land cover change is more difficult and more challenging, with error in classification being confused with change. We modeled land cover dynamics for a discrete set of habitat states. The approach accounts for state uncertainty to produce unbiased estimates of habitat transition probabilities using ground information to inform error rates. We consider the case when true and observed habitat states are available for the same geographic unit (pixel) and when true and observed states are obtained at one level of resolution, but transition probabilities estimated at a different level of resolution (aggregations of pixels). Simulation results showed a strong bias when estimating transition probabilities if misclassification was not accounted for. Scaling-up does not necessarily decrease the bias and can even increase it. Analyses of land cover data in the Southeast region of the USA showed that land change patterns appeared distorted if misclassification was not accounted for: rate of habitat turnover was artificially increased and habitat composition appeared more homogeneous. Not properly accounting for land cover misclassification can produce misleading inferences about habitat state and dynamics and also misleading predictions about species distributions based on habitat. Our models that explicitly account for state uncertainty should be useful in obtaining more accurate inferences about change from data that include errors.

Underwater target classification using wavelet packets and neural networks.

PubMed

Azimi-Sadjadi, M R; Yao, D; Huang, Q; Dobeck, G J

2000-01-01

In this paper, a new subband-based classification scheme is developed for classifying underwater mines and mine-like targets from the acoustic backscattered signals. The system consists of a feature extractor using wavelet packets in conjunction with linear predictive coding (LPC), a feature selection scheme, and a backpropagation neural-network classifier. The data set used for this study consists of the backscattered signals from six different objects: two mine-like targets and four nontargets for several aspect angles. Simulation results on ten different noisy realizations and for signal-to-noise ratio (SNR) of 12 dB are presented. The receiver operating characteristic (ROC) curve of the classifier generated based on these results demonstrated excellent classification performance of the system. The generalization ability of the trained network was demonstrated by computing the error and classification rate statistics on a large data set. A multiaspect fusion scheme was also adopted in order to further improve the classification performance.

The effect of the atmosphere on the classification of satellite observations to identify surface features

NASA Technical Reports Server (NTRS)

Fraser, R. S.; Bahethi, O. P.; Al-Abbas, A. H.

1977-01-01

The effect of differences in atmospheric turbidity on the classification of Landsat 1 observations of a rural scene is presented. The observations are classified by an unsupervised clustering technique. These clusters serve as a training set for use of a maximum-likelihood algorithm. The measured radiances in each of the four spectral bands are then changed by amounts measured by Landsat 1. These changes can be associated with a decrease in atmospheric turbidity by a factor of 1.3. The classification of 22% of the pixels changes as a result of the modification. The modified observations are then reclassified as an independent set. Only 3% of the pixels have a different classification than the unmodified set. Hence, if classification errors of rural areas are not to exceed 15%, a new training set has to be developed whenever the difference in turbidity between the training and test sets reaches unity.

Multinomial mixture model with heterogeneous classification probabilities

USGS Publications Warehouse

Holland, M.D.; Gray, B.R.

2011-01-01

Royle and Link (Ecology 86(9):2505-2512, 2005) proposed an analytical method that allowed estimation of multinomial distribution parameters and classification probabilities from categorical data measured with error. While useful, we demonstrate algebraically and by simulations that this method yields biased multinomial parameter estimates when the probabilities of correct category classifications vary among sampling units. We address this shortcoming by treating these probabilities as logit-normal random variables within a Bayesian framework. We use Markov chain Monte Carlo to compute Bayes estimates from a simulated sample from the posterior distribution. Based on simulations, this elaborated Royle-Link model yields nearly unbiased estimates of multinomial and correct classification probability estimates when classification probabilities are allowed to vary according to the normal distribution on the logit scale or according to the Beta distribution. The method is illustrated using categorical submersed aquatic vegetation data. ?? 2010 Springer Science+Business Media, LLC.

Stretchy binary classification.

PubMed

Toh, Kar-Ann; Lin, Zhiping; Sun, Lei; Li, Zhengguo

2018-01-01

In this article, we introduce an analytic formulation for compressive binary classification. The formulation seeks to solve the least ℓ p -norm of the parameter vector subject to a classification error constraint. An analytic and stretchable estimation is conjectured where the estimation can be viewed as an extension of the pseudoinverse with left and right constructions. Our variance analysis indicates that the estimation based on the left pseudoinverse is unbiased and the estimation based on the right pseudoinverse is biased. Sparseness can be obtained for the biased estimation under certain mild conditions. The proposed estimation is investigated numerically using both synthetic and real-world data. Copyright © 2017 Elsevier Ltd. All rights reserved.

[Effects of residents' care needs classification (and misclassification) in nursing homes: the example of SOSIA classification].

PubMed

Nebuloni, G; Di Giulio, P; Gregori, D; Sandonà, P; Berchialla, P; Foltran, F; Renga, G

2011-01-01

Since 2003, the Lombardy region has introduced a case-mix reimbursement system for nursing homes based on the SOSIA form which classifies residents into eight classes of frailty. In the present study the agreement between SOSIA classification and other well documented instruments, including Barthel Index, Mini Mental State Examination and Clinical Dementia Rating Scale is evaluated in 100 nursing home residents. Only 50% of residents with severe dementia have been recognized as seriously impaired when assessed with SOSIA form; since misclassification errors underestimate residents' care needs, they determine an insufficient reimbursement limiting nursing home possibility to offer care appropriate for the case-mix.

Effect of filtration of signals of brain activity on quality of recognition of brain activity patterns using artificial intelligence methods

NASA Astrophysics Data System (ADS)

Hramov, Alexander E.; Frolov, Nikita S.; Musatov, Vyachaslav Yu.

2018-02-01

In present work we studied features of the human brain states classification, corresponding to the real movements of hands and legs. For this purpose we used supervised learning algorithm based on feed-forward artificial neural networks (ANNs) with error back-propagation along with the support vector machine (SVM) method. We compared the quality of operator movements classification by means of EEG signals obtained experimentally in the absence of preliminary processing and after filtration in different ranges up to 25 Hz. It was shown that low-frequency filtering of multichannel EEG data significantly improved accuracy of operator movements classification.

GDF v2.0, an enhanced version of GDF

NASA Astrophysics Data System (ADS)

Tsoulos, Ioannis G.; Gavrilis, Dimitris; Dermatas, Evangelos

2007-12-01

An improved version of the function estimation program GDF is presented. The main enhancements of the new version include: multi-output function estimation, capability of defining custom functions in the grammar and selection of the error function. The new version has been evaluated on a series of classification and regression datasets, that are widely used for the evaluation of such methods. It is compared to two known neural networks and outperforms them in 5 (out of 10) datasets. Program summaryTitle of program: GDF v2.0 Catalogue identifier: ADXC_v2_0 Program summary URL:http://cpc.cs.qub.ac.uk/summaries/ADXC_v2_0.html Program obtainable from: CPC Program Library, Queen's University, Belfast, N. Ireland Licensing provisions: Standard CPC licence, http://cpc.cs.qub.ac.uk/licence/licence.html No. of lines in distributed program, including test data, etc.: 98 147 No. of bytes in distributed program, including test data, etc.: 2 040 684 Distribution format: tar.gz Programming language: GNU C++ Computer: The program is designed to be portable in all systems running the GNU C++ compiler Operating system: Linux, Solaris, FreeBSD RAM: 200000 bytes Classification: 4.9 Does the new version supersede the previous version?: Yes Nature of problem: The technique of function estimation tries to discover from a series of input data a functional form that best describes them. This can be performed with the use of parametric models, whose parameters can adapt according to the input data. Solution method: Functional forms are being created by genetic programming which are approximations for the symbolic regression problem. Reasons for new version: The GDF package was extended in order to be more flexible and user customizable than the old package. The user can extend the package by defining his own error functions and he can extend the grammar of the package by adding new functions to the function repertoire. Also, the new version can perform function estimation of multi-output functions and it can be used for classification problems. Summary of revisions: The following features have been added to the package GDF: Multi-output function approximation. The package can now approximate any function f:R→R. This feature gives also to the package the capability of performing classification and not only regression. User defined function can be added to the repertoire of the grammar, extending the regression capabilities of the package. This feature is limited to 3 functions, but easily this number can be increased. Capability of selecting the error function. The package offers now to the user apart from the mean square error other error functions such as: mean absolute square error, maximum square error. Also, user defined error functions can be added to the set of error functions. More verbose output. The main program displays more information to the user as well as the default values for the parameters. Also, the package gives to the user the capability to define an output file, where the output of the gdf program for the testing set will be stored after the termination of the process. Additional comments: A technical report describing the revisions, experiments and test runs is packaged with the source code. Running time: Depending on the train data.

Ground truth management system to support multispectral scanner /MSS/ digital analysis

NASA Technical Reports Server (NTRS)

Coiner, J. C.; Ungar, S. G.

1977-01-01

A computerized geographic information system for management of ground truth has been designed and implemented to relate MSS classification results to in situ observations. The ground truth system transforms, generalizes and rectifies ground observations to conform to the pixel size and shape of high resolution MSS aircraft data. These observations can then be aggregated for comparison to lower resolution sensor data. Construction of a digital ground truth array allows direct pixel by pixel comparison between classification results of MSS data and ground truth. By making comparisons, analysts can identify spatial distribution of error within the MSS data as well as usual figures of merit for the classifications. Use of the ground truth system permits investigators to compare a variety of environmental or anthropogenic data, such as soil color or tillage patterns, with classification results and allows direct inclusion of such data into classification operations. To illustrate the system, examples from classification of simulated Thematic Mapper data for agricultural test sites in North Dakota and Kansas are provided.

A Robust Unified Approach to Analyzing Methylation and Gene Expression Data

PubMed Central

Khalili, Abbas; Huang, Tim; Lin, Shili

2009-01-01

Microarray technology has made it possible to investigate expression levels, and more recently methylation signatures, of thousands of genes simultaneously, in a biological sample. Since more and more data from different biological systems or technological platforms are being generated at an incredible rate, there is an increasing need to develop statistical methods that are applicable to multiple data types and platforms. Motivated by such a need, a flexible finite mixture model that is applicable to methylation, gene expression, and potentially data from other biological systems, is proposed. Two major thrusts of this approach are to allow for a variable number of components in the mixture to capture non-biological variation and small biases, and to use a robust procedure for parameter estimation and probe classification. The method was applied to the analysis of methylation signatures of three breast cancer cell lines. It was also tested on three sets of expression microarray data to study its power and type I error rates. Comparison with a number of existing methods in the literature yielded very encouraging results; lower type I error rates and comparable/better power were achieved based on the limited study. Furthermore, the method also leads to more biologically interpretable results for the three breast cancer cell lines. PMID:20161265

Applications of remote sensing, volume 1

NASA Technical Reports Server (NTRS)

Landgrebe, D. A. (Principal Investigator)

1977-01-01

The author has identified the following significant results. ECHO successfully exploits the redundancy of states characteristics of sampled imagery of ground scenes to achieve better classification accuracy, reduce the number of classifications required, and reduce the variability of classification results. The information required to produce ECHO classifications are cell size, cell homogeneity, cell-to-field annexation parameters, input data, and a class conditional marginal density statistics deck.

Global terrain classification using Multiple-Error-Removed Improved-Terrain (MERIT) to address susceptibility of landslides and other geohazards

NASA Astrophysics Data System (ADS)

Iwahashi, J.; Yamazaki, D.; Matsuoka, M.; Thamarux, P.; Herrick, J.; Yong, A.; Mital, U.

2017-12-01

A seamless model of landform classifications with regional accuracy will be a powerful platform for geophysical studies that forecast geologic hazards. Spatial variability as a function of landform on a global scale was captured in the automated classifications of Iwahashi and Pike (2007) and additional developments are presented here that incorporate more accurate depictions using higher-resolution elevation data than the original 1-km scale Shuttle Radar Topography Mission digital elevation model (DEM). We create polygon-based terrain classifications globally by using the 280-m DEM interpolated from the Multi-Error-Removed Improved-Terrain DEM (MERIT; Yamazaki et al., 2017). The multi-scale pixel-image analysis method, known as Multi-resolution Segmentation (Baatz and Schäpe, 2000), is first used to classify the terrains based on geometric signatures (slope and local convexity) calculated from the 280-m DEM. Next, we apply the machine learning method of "k-means clustering" to prepare the polygon-based classification at the globe-scale using slope, local convexity and surface texture. We then group the divisions with similar properties by hierarchical clustering and other statistical analyses using geological and geomorphological data of the area where landslides and earthquakes are frequent (e.g. Japan and California). We find the 280-m DEM resolution is only partially sufficient for classifying plains. We nevertheless observe that the categories correspond to reported landslide and liquefaction features at the global scale, suggesting that our model is an appropriate platform to forecast ground failure. To predict seismic amplification, we estimate site conditions using the time-averaged shear-wave velocity in the upper 30-m (VS30) measurements compiled by Yong et al. (2016) and the terrain model developed by Yong (2016; Y16). We plan to test our method on finer resolution DEMs and report our findings to obtain a more globally consistent terrain model as there are known errors in DEM derivatives at higher-resolutions. We expect the improvement in DEM resolution (4 times greater detail) and the combination of regional and global coverage will yield a consistent dataset of polygons that have the potential to improve relations to the Y16 estimates significantly.

Disregarding population specificity: its influence on the sex assessment methods from the tibia.

PubMed

Kotěrová, Anežka; Velemínská, Jana; Dupej, Ján; Brzobohatá, Hana; Pilný, Aleš; Brůžek, Jaroslav

2017-01-01

Forensic anthropology has developed classification techniques for sex estimation of unknown skeletal remains, for example population-specific discriminant function analyses. These methods were designed for populations that lived mostly in the late nineteenth and twentieth centuries. Their level of reliability or misclassification is important for practical use in today's forensic practice; it is, however, unknown. We addressed the question of what the likelihood of errors would be if population specificity of discriminant functions of the tibia were disregarded. Moreover, five classification functions in a Czech sample were proposed (accuracies 82.1-87.5 %, sex bias ranged from -1.3 to -5.4 %). We measured ten variables traditionally used for sex assessment of the tibia on a sample of 30 male and 26 female models from recent Czech population. To estimate the classification accuracy and error (misclassification) rates ignoring population specificity, we selected published classification functions of tibia for the Portuguese, south European, and the North American populations. These functions were applied on the dimensions of the Czech population. Comparing the classification success of the reference and the tested Czech sample showed that females from Czech population were significantly overestimated and mostly misclassified as males. Overall accuracy of sex assessment significantly decreased (53.6-69.7 %), sex bias -29.4-100 %, which is most probably caused by secular trend and the generally high variability of body size. Results indicate that the discriminant functions, developed for skeletal series representing geographically and chronologically diverse populations, are not applicable in current forensic investigations. Finally, implications and recommendations for future research are discussed.

Decision Making for Borderline Cases in Pass/Fail Clinical Anatomy Courses: The Practical Value of the Standard Error of Measurement and Likelihood Ratio in a Diagnostic Test

ERIC Educational Resources Information Center

Severo, Milton; Silva-Pereira, Fernanda; Ferreira, Maria Amelia

2013-01-01

Several studies have shown that the standard error of measurement (SEM) can be used as an additional “safety net” to reduce the frequency of false-positive or false-negative student grading classifications. Practical examinations in clinical anatomy are often used as diagnostic tests to admit students to course final examinations. The aim of this…

Texture operator for snow particle classification into snowflake and graupel

NASA Astrophysics Data System (ADS)

Nurzyńska, Karolina; Kubo, Mamoru; Muramoto, Ken-ichiro

2012-11-01

In order to improve the estimation of precipitation, the coefficients of Z-R relation should be determined for each snow type. Therefore, it is necessary to identify the type of falling snow. Consequently, this research addresses a problem of snow particle classification into snowflake and graupel in an automatic manner (as these types are the most common in the study region). Having correctly classified precipitation events, it is believed that it will be possible to estimate the related parameters accurately. The automatic classification system presented here describes the images with texture operators. Some of them are well-known from the literature: first order features, co-occurrence matrix, grey-tone difference matrix, run length matrix, and local binary pattern, but also a novel approach to design simple local statistic operators is introduced. In this work the following texture operators are defined: mean histogram, min-max histogram, and mean-variance histogram. Moreover, building a feature vector, which is based on the structure created in many from mentioned algorithms is also suggested. For classification, the k-nearest neighbourhood classifier was applied. The results showed that it is possible to achieve correct classification accuracy above 80% by most of the techniques. The best result of 86.06%, was achieved for operator built from a structure achieved in the middle stage of the co-occurrence matrix calculation. Next, it was noticed that describing an image with two texture operators does not improve the classification results considerably. In the best case the correct classification efficiency was 87.89% for a pair of texture operators created from local binary pattern and structure build in a middle stage of grey-tone difference matrix calculation. This also suggests that the information gathered by each texture operator is redundant. Therefore, the principal component analysis was applied in order to remove the unnecessary information and additionally reduce the length of the feature vectors. The improvement of the correct classification efficiency for up to 100% is possible for methods: min-max histogram, texture operator built from structure achieved in a middle stage of co-occurrence matrix calculation, texture operator built from a structure achieved in a middle stage of grey-tone difference matrix creation, and texture operator based on a histogram, when the feature vector stores 99% of initial information.

Spatio-Temporal EEG Models for Brain Interfaces

PubMed Central

Gonzalez-Navarro, P.; Moghadamfalahi, M.; Akcakaya, M.; Erdogmus, D.

2016-01-01

Multichannel electroencephalography (EEG) is widely used in non-invasive brain computer interfaces (BCIs) for user intent inference. EEG can be assumed to be a Gaussian process with unknown mean and autocovariance, and the estimation of parameters is required for BCI inference. However, the relatively high dimensionality of the EEG feature vectors with respect to the number of labeled observations lead to rank deficient covariance matrix estimates. In this manuscript, to overcome ill-conditioned covariance estimation, we propose a structure for the covariance matrices of the multichannel EEG signals. Specifically, we assume that these covariances can be modeled as a Kronecker product of temporal and spatial covariances. Our results over the experimental data collected from the users of a letter-by-letter typing BCI show that with less number of parameter estimations, the system can achieve higher classification accuracies compared to a method that uses full unstructured covariance estimation. Moreover, in order to illustrate that the proposed Kronecker product structure could enable shortening the BCI calibration data collection sessions, using Cramer-Rao bound analysis on simulated data, we demonstrate that a model with structured covariance matrices will achieve the same estimation error as a model with no covariance structure using fewer labeled EEG observations. PMID:27713590

Use of scan overlap redundancy to enhance multispectral aircraft scanner data

NASA Technical Reports Server (NTRS)

Lindenlaub, J. C.; Keat, J.

1973-01-01

Two criteria were suggested for optimizing the resolution error versus signal-to-noise-ratio tradeoff. The first criterion uses equal weighting coefficients and chooses n, the number of lines averaged, so as to make the average resolution error equal to the noise error. The second criterion adjusts both the number and relative sizes of the weighting coefficients so as to minimize the total error (resolution error plus noise error). The optimum set of coefficients depends upon the geometry of the resolution element, the number of redundant scan lines, the scan line increment, and the original signal-to-noise ratio of the channel. Programs were developed to find the optimum number and relative weights of the averaging coefficients. A working definition of signal-to-noise ratio was given and used to try line averaging on a typical set of data. Line averaging was evaluated only with respect to its effect on classification accuracy.

Reducing error and improving efficiency during vascular interventional radiology: implementation of a preprocedural team rehearsal.

PubMed

Morbi, Abigail H M; Hamady, Mohamad S; Riga, Celia V; Kashef, Elika; Pearch, Ben J; Vincent, Charles; Moorthy, Krishna; Vats, Amit; Cheshire, Nicholas J W; Bicknell, Colin D

2012-08-01

To determine the type and frequency of errors during vascular interventional radiology (VIR) and design and implement an intervention to reduce error and improve efficiency in this setting. Ethical guidance was sought from the Research Services Department at Imperial College London. Informed consent was not obtained. Field notes were recorded during 55 VIR procedures by a single observer. Two blinded assessors identified failures from field notes and categorized them into one or more errors by using a 22-part classification system. The potential to cause harm, disruption to procedural flow, and preventability of each failure was determined. A preprocedural team rehearsal (PPTR) was then designed and implemented to target frequent preventable potential failures. Thirty-three procedures were observed subsequently to determine the efficacy of the PPTR. Nonparametric statistical analysis was used to determine the effect of intervention on potential failure rates, potential to cause harm and procedural flow disruption scores (Mann-Whitney U test), and number of preventable failures (Fisher exact test). Before intervention, 1197 potential failures were recorded, of which 54.6% were preventable. A total of 2040 errors were deemed to have occurred to produce these failures. Planning error (19.7%), staff absence (16.2%), equipment unavailability (12.2%), communication error (11.2%), and lack of safety consciousness (6.1%) were the most frequent errors, accounting for 65.4% of the total. After intervention, 352 potential failures were recorded. Classification resulted in 477 errors. Preventable failures decreased from 54.6% to 27.3% (P < .001) with implementation of PPTR. Potential failure rates per hour decreased from 18.8 to 9.2 (P < .001), with no increase in potential to cause harm or procedural flow disruption per failure. Failures during VIR procedures are largely because of ineffective planning, communication error, and equipment difficulties, rather than a result of technical or patient-related issues. Many of these potential failures are preventable. A PPTR is an effective means of targeting frequent preventable failures, reducing procedural delays and improving patient safety.

Bug Distribution and Statistical Pattern Classification.

ERIC Educational Resources Information Center

Tatsuoka, Kikumi K.; Tatsuoka, Maurice M.

1987-01-01

The rule space model permits measurement of cognitive skill acquisition and error diagnosis. Further discussion introduces Bayesian hypothesis testing and bug distribution. An illustration involves an artificial intelligence approach to testing fractions and arithmetic. (Author/GDC)

A model for the statistical description of analytical errors occurring in clinical chemical laboratories with time.

PubMed

Hyvärinen, A

1985-01-01

The main purpose of the present study was to describe the statistical behaviour of daily analytical errors in the dimensions of place and time, providing a statistical basis for realistic estimates of the analytical error, and hence allowing the importance of the error and the relative contributions of its different sources to be re-evaluated. The observation material consists of creatinine and glucose results for control sera measured in daily routine quality control in five laboratories for a period of one year. The observation data were processed and computed by means of an automated data processing system. Graphic representations of time series of daily observations, as well as their means and dispersion limits when grouped over various time intervals, were investigated. For partition of the total variation several two-way analyses of variance were done with laboratory and various time classifications as factors. Pooled sets of observations were tested for normality of distribution and for consistency of variances, and the distribution characteristics of error variation in different categories of place and time were compared. Errors were found from the time series to vary typically between days. Due to irregular fluctuations in general and particular seasonal effects in creatinine, stable estimates of means or of dispersions for errors in individual laboratories could not be easily obtained over short periods of time but only from data sets pooled over long intervals (preferably at least one year). Pooled estimates of proportions of intralaboratory variation were relatively low (less than 33%) when the variation was pooled within days. However, when the variation was pooled over longer intervals this proportion increased considerably, even to a maximum of 89-98% (95-98% in each method category) when an outlying laboratory in glucose was omitted, with a concomitant decrease in the interaction component (representing laboratory-dependent variation with time). This indicates that a substantial part of the variation comes from intralaboratory variation with time rather than from constant interlaboratory differences. Normality and consistency of statistical distributions were best achieved in the long-term intralaboratory sets of the data, under which conditions the statistical estimates of error variability were also most characteristic of the individual laboratories rather than necessarily being similar to one another. Mixing of data from different laboratories may give heterogeneous and nonparametric distributions and hence is not advisable.(ABSTRACT TRUNCATED AT 400 WORDS)

Assessment of Metronidazole Susceptibility in Helicobacter pylori: Statistical Validation and Error Rate Analysis of Breakpoints Determined by the Disk Diffusion Test

PubMed Central

Chaves, Sandra; Gadanho, Mário; Tenreiro, Rogério; Cabrita, José

1999-01-01

Metronidazole susceptibility of 100 Helicobacter pylori strains was assessed by determining the inhibition zone diameters by disk diffusion test and the MICs by agar dilution and PDM Epsilometer test (E test). Linear regression analysis was performed, allowing the definition of significant linear relations, and revealed correlations of disk diffusion results with both E-test and agar dilution results (r2 = 0.88 and 0.81, respectively). No significant differences (P = 0.84) were found between MICs defined by E test and those defined by agar dilution, taken as a standard. Reproducibility comparison between E-test and disk diffusion tests showed that they are equivalent and with good precision. Two interpretative susceptibility schemes (with or without an intermediate class) were compared by an interpretative error rate analysis method. The susceptibility classification scheme that included the intermediate category was retained, and breakpoints were assessed for diffusion assay with 5-μg metronidazole disks. Strains with inhibition zone diameters less than 16 mm were defined as resistant (MIC > 8 μg/ml), those with zone diameters equal to or greater than 16 mm but less than 21 mm were considered intermediate (4 μg/ml < MIC ≤ 8 μg/ml), and those with zone diameters of 21 mm or greater were regarded as susceptible (MIC ≤ 4 μg/ml). Error rate analysis applied to this classification scheme showed occurrence frequencies of 1% for major errors and 7% for minor errors, when the results were compared to those obtained by agar dilution. No very major errors were detected, suggesting that disk diffusion might be a good alternative for determining the metronidazole sensitivity of H. pylori strains. PMID:10203543

Real-time, resource-constrained object classification on a micro-air vehicle

NASA Astrophysics Data System (ADS)

Buck, Louis; Ray, Laura

2013-12-01

A real-time embedded object classification algorithm is developed through the novel combination of binary feature descriptors, a bag-of-visual-words object model and the cortico-striatal loop (CSL) learning algorithm. The BRIEF, ORB and FREAK binary descriptors are tested and compared to SIFT descriptors with regard to their respective classification accuracies, execution times, and memory requirements when used with CSL on a 12.6 g ARM Cortex embedded processor running at 800 MHz. Additionally, the effect of x2 feature mapping and opponent-color representations used with these descriptors is examined. These tests are performed on four data sets of varying sizes and difficulty, and the BRIEF descriptor is found to yield the best combination of speed and classification accuracy. Its use with CSL achieves accuracies between 67% and 95% of those achieved with SIFT descriptors and allows for the embedded classification of a 128x192 pixel image in 0.15 seconds, 60 times faster than classification with SIFT. X2 mapping is found to provide substantial improvements in classification accuracy for all of the descriptors at little cost, while opponent-color descriptors are offer accuracy improvements only on colorful datasets.

Predictive models to assess risk of type 2 diabetes, hypertension and comorbidity: machine-learning algorithms and validation using national health data from Kuwait--a cohort study.

PubMed

Farran, Bassam; Channanath, Arshad Mohamed; Behbehani, Kazem; Thanaraj, Thangavel Alphonse

2013-05-14

We build classification models and risk assessment tools for diabetes, hypertension and comorbidity using machine-learning algorithms on data from Kuwait. We model the increased proneness in diabetic patients to develop hypertension and vice versa. We ascertain the importance of ethnicity (and natives vs expatriate migrants) and of using regional data in risk assessment. Retrospective cohort study. Four machine-learning techniques were used: logistic regression, k-nearest neighbours (k-NN), multifactor dimensionality reduction and support vector machines. The study uses fivefold cross validation to obtain generalisation accuracies and errors. Kuwait Health Network (KHN) that integrates data from primary health centres and hospitals in Kuwait. 270 172 hospital visitors (of which, 89 858 are diabetic, 58 745 hypertensive and 30 522 comorbid) comprising Kuwaiti natives, Asian and Arab expatriates. Incident type 2 diabetes, hypertension and comorbidity. Classification accuracies of >85% (for diabetes) and >90% (for hypertension) are achieved using only simple non-laboratory-based parameters. Risk assessment tools based on k-NN classification models are able to assign 'high' risk to 75% of diabetic patients and to 94% of hypertensive patients. Only 5% of diabetic patients are seen assigned 'low' risk. Asian-specific models and assessments perform even better. Pathological conditions of diabetes in the general population or in hypertensive population and those of hypertension are modelled. Two-stage aggregate classification models and risk assessment tools, built combining both the component models on diabetes (or on hypertension), perform better than individual models. Data on diabetes, hypertension and comorbidity from the cosmopolitan State of Kuwait are available for the first time. This enabled us to apply four different case-control models to assess risks. These tools aid in the preliminary non-intrusive assessment of the population. Ethnicity is seen significant to the predictive models. Risk assessments need to be developed using regional data as we demonstrate the applicability of the American Diabetes Association online calculator on data from Kuwait.

Automatic evidence quality prediction to support evidence-based decision making.

PubMed

Sarker, Abeed; Mollá, Diego; Paris, Cécile

2015-06-01

Evidence-based medicine practice requires practitioners to obtain the best available medical evidence, and appraise the quality of the evidence when making clinical decisions. Primarily due to the plethora of electronically available data from the medical literature, the manual appraisal of the quality of evidence is a time-consuming process. We present a fully automatic approach for predicting the quality of medical evidence in order to aid practitioners at point-of-care. Our approach extracts relevant information from medical article abstracts and utilises data from a specialised corpus to apply supervised machine learning for the prediction of the quality grades. Following an in-depth analysis of the usefulness of features (e.g., publication types of articles), they are extracted from the text via rule-based approaches and from the meta-data associated with the articles, and then applied in the supervised classification model. We propose the use of a highly scalable and portable approach using a sequence of high precision classifiers, and introduce a simple evaluation metric called average error distance (AED) that simplifies the comparison of systems. We also perform elaborate human evaluations to compare the performance of our system against human judgments. We test and evaluate our approaches on a publicly available, specialised, annotated corpus containing 1132 evidence-based recommendations. Our rule-based approach performs exceptionally well at the automatic extraction of publication types of articles, with F-scores of up to 0.99 for high-quality publication types. For evidence quality classification, our approach obtains an accuracy of 63.84% and an AED of 0.271. The human evaluations show that the performance of our system, in terms of AED and accuracy, is comparable to the performance of humans on the same data. The experiments suggest that our structured text classification framework achieves evaluation results comparable to those of human performance. Our overall classification approach and evaluation technique are also highly portable and can be used for various evidence grading scales. Copyright © 2015 Elsevier B.V. All rights reserved.

Investigation on changes in complex vegetation coverage using multi-temporal landsat data of Western Black Sea region--a case study.

PubMed

Coban, Huseyin Oguz; Koc, Ayhan; Eker, Mehmet

2010-01-01

Previous studies have been able to successfully detect changes in gently-sloping forested areas with low-diversity and homogeneous vegetation cover using medium-resolution satellite data such as landsat. The aim of the present study is to examine the capacity of multi-temporal landsat data to identify changes in forested areas with mixed vegetation and generally located on steep slopes or non-uniform topography landsat thematic mapper (TM) and landsat enhanced thematic mapperplus (ETM+) data for the years 1987-2000 was used to detect changes within a 19,500 ha forested area in the Western Black sea region of Turkey. The data comply with the forest cover type maps previously created for forest management plans of the research area. The methods used to detect changes were: post-classification comparison, image differencing, image rationing and NDVI (Normalized Difference Vegetation Index) differencing methods. Following the supervised classification process, error matrices were used to evaluate the accuracy of classified images obtained. The overall accuracy has been calculated as 87.59% for 1987 image and as 91.81% for 2000 image. General kappa statistics have been calculated as 0.8543 and 0.9038 for 1987 and 2000, respectively. The changes identified via the post-classification comparison method were compared with other change detetion methods. Maximum coherence was found to be 74.95% at 4/3 band rate. The NDVI difference and 3rd band difference methods achieved the same coherence with slight variations. The results suggest that landsat satellite data accurately conveys the temporal changes which occur on steeply-sloping forested areas with a mixed structure, providing a limited amount of detail but with a high level of accuracy. Moreover it has been decided that the post-classification comparison method can meet the needs of forestry activities better than other methods as it provides information about the direction of these changes.

Detection and Classification of Whale Acoustic Signals

NASA Astrophysics Data System (ADS)

Xian, Yin

This dissertation focuses on two vital challenges in relation to whale acoustic signals: detection and classification. In detection, we evaluated the influence of the uncertain ocean environment on the spectrogram-based detector, and derived the likelihood ratio of the proposed Short Time Fourier Transform detector. Experimental results showed that the proposed detector outperforms detectors based on the spectrogram. The proposed detector is more sensitive to environmental changes because it includes phase information. In classification, our focus is on finding a robust and sparse representation of whale vocalizations. Because whale vocalizations can be modeled as polynomial phase signals, we can represent the whale calls by their polynomial phase coefficients. In this dissertation, we used the Weyl transform to capture chirp rate information, and used a two dimensional feature set to represent whale vocalizations globally. Experimental results showed that our Weyl feature set outperforms chirplet coefficients and MFCC (Mel Frequency Cepstral Coefficients) when applied to our collected data. Since whale vocalizations can be represented by polynomial phase coefficients, it is plausible that the signals lie on a manifold parameterized by these coefficients. We also studied the intrinsic structure of high dimensional whale data by exploiting its geometry. Experimental results showed that nonlinear mappings such as Laplacian Eigenmap and ISOMAP outperform linear mappings such as PCA and MDS, suggesting that the whale acoustic data is nonlinear. We also explored deep learning algorithms on whale acoustic data. We built each layer as convolutions with either a PCA filter bank (PCANet) or a DCT filter bank (DCTNet). With the DCT filter bank, each layer has different a time-frequency scale representation, and from this, one can extract different physical information. Experimental results showed that our PCANet and DCTNet achieve high classification rate on the whale vocalization data set. The word error rate of the DCTNet feature is similar to the MFSC in speech recognition tasks, suggesting that the convolutional network is able to reveal acoustic content of speech signals.

Continuous robust sound event classification using time-frequency features and deep learning

PubMed Central

Song, Yan; Xiao, Wei; Phan, Huy

2017-01-01

The automatic detection and recognition of sound events by computers is a requirement for a number of emerging sensing and human computer interaction technologies. Recent advances in this field have been achieved by machine learning classifiers working in conjunction with time-frequency feature representations. This combination has achieved excellent accuracy for classification of discrete sounds. The ability to recognise sounds under real-world noisy conditions, called robust sound event classification, is an especially challenging task that has attracted recent research attention. Another aspect of real-word conditions is the classification of continuous, occluded or overlapping sounds, rather than classification of short isolated sound recordings. This paper addresses the classification of noise-corrupted, occluded, overlapped, continuous sound recordings. It first proposes a standard evaluation task for such sounds based upon a common existing method for evaluating isolated sound classification. It then benchmarks several high performing isolated sound classifiers to operate with continuous sound data by incorporating an energy-based event detection front end. Results are reported for each tested system using the new task, to provide the first analysis of their performance for continuous sound event detection. In addition it proposes and evaluates a novel Bayesian-inspired front end for the segmentation and detection of continuous sound recordings prior to classification. PMID:28892478

Continuous robust sound event classification using time-frequency features and deep learning.

PubMed

McLoughlin, Ian; Zhang, Haomin; Xie, Zhipeng; Song, Yan; Xiao, Wei; Phan, Huy

2017-01-01

The automatic detection and recognition of sound events by computers is a requirement for a number of emerging sensing and human computer interaction technologies. Recent advances in this field have been achieved by machine learning classifiers working in conjunction with time-frequency feature representations. This combination has achieved excellent accuracy for classification of discrete sounds. The ability to recognise sounds under real-world noisy conditions, called robust sound event classification, is an especially challenging task that has attracted recent research attention. Another aspect of real-word conditions is the classification of continuous, occluded or overlapping sounds, rather than classification of short isolated sound recordings. This paper addresses the classification of noise-corrupted, occluded, overlapped, continuous sound recordings. It first proposes a standard evaluation task for such sounds based upon a common existing method for evaluating isolated sound classification. It then benchmarks several high performing isolated sound classifiers to operate with continuous sound data by incorporating an energy-based event detection front end. Results are reported for each tested system using the new task, to provide the first analysis of their performance for continuous sound event detection. In addition it proposes and evaluates a novel Bayesian-inspired front end for the segmentation and detection of continuous sound recordings prior to classification.

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.

PDF text classification to leverage information extraction from publication reports.

PubMed

Bui, Duy Duc An; Del Fiol, Guilherme; Jonnalagadda, Siddhartha

2016-06-01

Data extraction from original study reports is a time-consuming, error-prone process in systematic review development. Information extraction (IE) systems have the potential to assist humans in the extraction task, however majority of IE systems were not designed to work on Portable Document Format (PDF) document, an important and common extraction source for systematic review. In a PDF document, narrative content is often mixed with publication metadata or semi-structured text, which add challenges to the underlining natural language processing algorithm. Our goal is to categorize PDF texts for strategic use by IE systems. We used an open-source tool to extract raw texts from a PDF document and developed a text classification algorithm that follows a multi-pass sieve framework to automatically classify PDF text snippets (for brevity, texts) into TITLE, ABSTRACT, BODYTEXT, SEMISTRUCTURE, and METADATA categories. To validate the algorithm, we developed a gold standard of PDF reports that were included in the development of previous systematic reviews by the Cochrane Collaboration. In a two-step procedure, we evaluated (1) classification performance, and compared it with machine learning classifier, and (2) the effects of the algorithm on an IE system that extracts clinical outcome mentions. The multi-pass sieve algorithm achieved an accuracy of 92.6%, which was 9.7% (p<0.001) higher than the best performing machine learning classifier that used a logistic regression algorithm. F-measure improvements were observed in the classification of TITLE (+15.6%), ABSTRACT (+54.2%), BODYTEXT (+3.7%), SEMISTRUCTURE (+34%), and MEDADATA (+14.2%). In addition, use of the algorithm to filter semi-structured texts and publication metadata improved performance of the outcome extraction system (F-measure +4.1%, p=0.002). It also reduced of number of sentences to be processed by 44.9% (p<0.001), which corresponds to a processing time reduction of 50% (p=0.005). The rule-based multi-pass sieve framework can be used effectively in categorizing texts extracted from PDF documents. Text classification is an important prerequisite step to leverage information extraction from PDF documents. Copyright © 2016 Elsevier Inc. All rights reserved.

A SVM framework for fault detection of the braking system in a high speed train

NASA Astrophysics Data System (ADS)

Liu, Jie; Li, Yan-Fu; Zio, Enrico

2017-03-01

In April 2015, the number of operating High Speed Trains (HSTs) in the world has reached 3603. An efficient, effective and very reliable braking system is evidently very critical for trains running at a speed around 300 km/h. Failure of a highly reliable braking system is a rare event and, consequently, informative recorded data on fault conditions are scarce. This renders the fault detection problem a classification problem with highly unbalanced data. In this paper, a Support Vector Machine (SVM) framework, including feature selection, feature vector selection, model construction and decision boundary optimization, is proposed for tackling this problem. Feature vector selection can largely reduce the data size and, thus, the computational burden. The constructed model is a modified version of the least square SVM, in which a higher cost is assigned to the error of classification of faulty conditions than the error of classification of normal conditions. The proposed framework is successfully validated on a number of public unbalanced datasets. Then, it is applied for the fault detection of braking systems in HST: in comparison with several SVM approaches for unbalanced datasets, the proposed framework gives better results.

Semi-supervised anomaly detection - towards model-independent searches of new physics

NASA Astrophysics Data System (ADS)

Kuusela, Mikael; Vatanen, Tommi; Malmi, Eric; Raiko, Tapani; Aaltonen, Timo; Nagai, Yoshikazu

2012-06-01

Most classification algorithms used in high energy physics fall under the category of supervised machine learning. Such methods require a training set containing both signal and background events and are prone to classification errors should this training data be systematically inaccurate for example due to the assumed MC model. To complement such model-dependent searches, we propose an algorithm based on semi-supervised anomaly detection techniques, which does not require a MC training sample for the signal data. We first model the background using a multivariate Gaussian mixture model. We then search for deviations from this model by fitting to the observations a mixture of the background model and a number of additional Gaussians. This allows us to perform pattern recognition of any anomalous excess over the background. We show by a comparison to neural network classifiers that such an approach is a lot more robust against misspecification of the signal MC than supervised classification. In cases where there is an unexpected signal, a neural network might fail to correctly identify it, while anomaly detection does not suffer from such a limitation. On the other hand, when there are no systematic errors in the training data, both methods perform comparably.

A Q-backpropagated time delay neural network for diagnosing severity of gait disturbances in Parkinson's disease.

PubMed

Nancy Jane, Y; Khanna Nehemiah, H; Arputharaj, Kannan

2016-04-01

Parkinson's disease (PD) is a movement disorder that affects the patient's nervous system and health-care applications mostly uses wearable sensors to collect these data. Since these sensors generate time stamped data, analyzing gait disturbances in PD becomes challenging task. The objective of this paper is to develop an effective clinical decision-making system (CDMS) that aids the physician in diagnosing the severity of gait disturbances in PD affected patients. This paper presents a Q-backpropagated time delay neural network (Q-BTDNN) classifier that builds a temporal classification model, which performs the task of classification and prediction in CDMS. The proposed Q-learning induced backpropagation (Q-BP) training algorithm trains the Q-BTDNN by generating a reinforced error signal. The network's weights are adjusted through backpropagating the generated error signal. For experimentation, the proposed work uses a PD gait database, which contains gait measures collected through wearable sensors from three different PD research studies. The experimental result proves the efficiency of Q-BP in terms of its improved classification accuracy of 91.49%, 92.19% and 90.91% with three datasets accordingly compared to other neural network training algorithms. Copyright © 2016 Elsevier Inc. All rights reserved.

Bayesian logistic regression approaches to predict incorrect DRG assignment.

PubMed

Suleiman, Mani; Demirhan, Haydar; Boyd, Leanne; Girosi, Federico; Aksakalli, Vural

2018-05-07

Episodes of care involving similar diagnoses and treatments and requiring similar levels of resource utilisation are grouped to the same Diagnosis-Related Group (DRG). In jurisdictions which implement DRG based payment systems, DRGs are a major determinant of funding for inpatient care. Hence, service providers often dedicate auditing staff to the task of checking that episodes have been coded to the correct DRG. The use of statistical models to estimate an episode's probability of DRG error can significantly improve the efficiency of clinical coding audits. This study implements Bayesian logistic regression models with weakly informative prior distributions to estimate the likelihood that episodes require a DRG revision, comparing these models with each other and to classical maximum likelihood estimates. All Bayesian approaches had more stable model parameters than maximum likelihood. The best performing Bayesian model improved overall classification per- formance by 6% compared to maximum likelihood, with a 34% gain compared to random classification, respectively. We found that the original DRG, coder and the day of coding all have a significant effect on the likelihood of DRG error. Use of Bayesian approaches has improved model parameter stability and classification accuracy. This method has already lead to improved audit efficiency in an operational capacity.

Gaia eclipsing binary and multiple systems. Supervised classification and self-organizing maps

NASA Astrophysics Data System (ADS)

Süveges, M.; Barblan, F.; Lecoeur-Taïbi, I.; Prša, A.; Holl, B.; Eyer, L.; Kochoska, A.; Mowlavi, N.; Rimoldini, L.

2017-07-01

Context. Large surveys producing tera- and petabyte-scale databases require machine-learning and knowledge discovery methods to deal with the overwhelming quantity of data and the difficulties of extracting concise, meaningful information with reliable assessment of its uncertainty. This study investigates the potential of a few machine-learning methods for the automated analysis of eclipsing binaries in the data of such surveys. Aims: We aim to aid the extraction of samples of eclipsing binaries from such databases and to provide basic information about the objects. We intend to estimate class labels according to two different, well-known classification systems, one based on the light curve morphology (EA/EB/EW classes) and the other based on the physical characteristics of the binary system (system morphology classes; detached through overcontact systems). Furthermore, we explore low-dimensional surfaces along which the light curves of eclipsing binaries are concentrated, and consider their use in the characterization of the binary systems and in the exploration of biases of the full unknown Gaia data with respect to the training sets. Methods: We have explored the performance of principal component analysis (PCA), linear discriminant analysis (LDA), Random Forest classification and self-organizing maps (SOM) for the above aims. We pre-processed the photometric time series by combining a double Gaussian profile fit and a constrained smoothing spline, in order to de-noise and interpolate the observed light curves. We achieved further denoising, and selected the most important variability elements from the light curves using PCA. Supervised classification was performed using Random Forest and LDA based on the PC decomposition, while SOM gives a continuous 2-dimensional manifold of the light curves arranged by a few important features. We estimated the uncertainty of the supervised methods due to the specific finite training set using ensembles of models constructed on randomized training sets. Results: We obtain excellent results (about 5% global error rate) with classification into light curve morphology classes on the Hipparcos data. The classification into system morphology classes using the Catalog and Atlas of Eclipsing binaries (CALEB) has a higher error rate (about 10.5%), most importantly due to the (sometimes strong) similarity of the photometric light curves originating from physically different systems. When trained on CALEB and then applied to Kepler-detected eclipsing binaries subsampled according to Gaia observing times, LDA and SOM provide tractable, easy-to-visualize subspaces of the full (functional) space of light curves that summarize the most important phenomenological elements of the individual light curves. The sequence of light curves ordered by their first linear discriminant coefficient is compared to results obtained using local linear embedding. The SOM method proves able to find a 2-dimensional embedded surface in the space of the light curves which separates the system morphology classes in its different regions, and also identifies a few other phenomena, such as the asymmetry of the light curves due to spots, eccentric systems, and systems with a single eclipse. Furthermore, when data from other surveys are projected to the same SOM surface, the resulting map yields a good overview of the general biases and distortions due to differences in time sampling or population.

Association of medication errors with drug classifications, clinical units, and consequence of errors: Are they related?

PubMed

Muroi, Maki; Shen, Jay J; Angosta, Alona

2017-02-01

Registered nurses (RNs) play an important role in safe medication administration and patient safety. This study examined a total of 1276 medication error (ME) incident reports made by RNs in hospital inpatient settings in the southwestern region of the United States. The most common drug class associated with MEs was cardiovascular drugs (24.7%). Among this class, anticoagulants had the most errors (11.3%). The antimicrobials was the second most common drug class associated with errors (19.1%) and vancomycin was the most common antimicrobial that caused errors in this category (6.1%). MEs occurred more frequently in the medical-surgical and intensive care units than any other hospital units. Ten percent of MEs reached the patients with harm and 11% reached the patients with increased monitoring. Understanding the contributing factors related to MEs, addressing and eliminating risk of errors across hospital units, and providing education and resources for nurses may help reduce MEs. Copyright © 2016 Elsevier Inc. All rights reserved.

Classification Management. Journal of the National Classification Management Society, Volume 18, 1982,

DTIC Science & Technology

1983-01-01

changes. Concurrently, CIA formed and AD HOC esting to step back and look at the U.S. security Intelligence Community Working Group to re...administrative error; to prevent embarrassment to expected damage will be. If you foresee the dam- a person, organization, or agency; to restrain com- age...the decision will be to classify the informa- petition; or to pTevent or delay the public release of tion. But note that in this thought process, you

Validation of tool mark analysis of cut costal cartilage.

PubMed

Love, Jennifer C; Derrick, Sharon M; Wiersema, Jason M; Peters, Charles

2012-03-01

This study was designed to establish the potential error rate associated with the generally accepted method of tool mark analysis of cut marks in costal cartilage. Three knives with different blade types were used to make experimental cut marks in costal cartilage of pigs. Each cut surface was cast, and each cast was examined by three analysts working independently. The presence of striations, regularity of striations, and presence of a primary and secondary striation pattern were recorded for each cast. The distance between each striation was measured. The results showed that striations were not consistently impressed on the cut surface by the blade's cutting edge. Also, blade type classification by the presence or absence of striations led to a 65% misclassification rate. Use of the classification tree and cross-validation methods and inclusion of the mean interstriation distance decreased the error rate to c. 50%. © 2011 American Academy of Forensic Sciences.

Automatic and semi-automatic approaches for arteriolar-to-venular computation in retinal photographs

NASA Astrophysics Data System (ADS)

Mendonça, Ana Maria; Remeseiro, Beatriz; Dashtbozorg, Behdad; Campilho, Aurélio

2017-03-01

The Arteriolar-to-Venular Ratio (AVR) is a popular dimensionless measure which allows the assessment of patients' condition for the early diagnosis of different diseases, including hypertension and diabetic retinopathy. This paper presents two new approaches for AVR computation in retinal photographs which include a sequence of automated processing steps: vessel segmentation, caliber measurement, optic disc segmentation, artery/vein classification, region of interest delineation, and AVR calculation. Both approaches have been tested on the INSPIRE-AVR dataset, and compared with a ground-truth provided by two medical specialists. The obtained results demonstrate the reliability of the fully automatic approach which provides AVR ratios very similar to at least one of the observers. Furthermore, the semi-automatic approach, which includes the manual modification of the artery/vein classification if needed, allows to significantly reduce the error to a level below the human error.

Bayes classification of terrain cover using normalized polarimetric data

NASA Technical Reports Server (NTRS)

Yueh, H. A.; Swartz, A. A.; Kong, J. A.; Shin, R. T.; Novak, L. M.

1988-01-01

The normalized polarimetric classifier (NPC) which uses only the relative magnitudes and phases of the polarimetric data is proposed for discrimination of terrain elements. The probability density functions (PDFs) of polarimetric data are assumed to have a complex Gaussian distribution, and the marginal PDF of the normalized polarimetric data is derived by adopting the Euclidean norm as the normalization function. The general form of the distance measure for the NPC is also obtained. It is demonstrated that for polarimetric data with an arbitrary PDF, the distance measure of NPC will be independent of the normalization function selected even when the classifier is mistrained. A complex Gaussian distribution is assumed for the polarimetric data consisting of grass and tree regions. The probability of error for the NPC is compared with those of several other single-feature classifiers. The classification error of NPCs is shown to be independent of the normalization function.

Automated Detection of Clinically Significant Prostate Cancer in mp-MRI Images Based on an End-to-End Deep Neural Network.

PubMed

Wang, Zhiwei; Liu, Chaoyue; Cheng, Danpeng; Wang, Liang; Yang, Xin; Cheng, Kwang-Ting

2018-05-01

Automated methods for detecting clinically significant (CS) prostate cancer (PCa) in multi-parameter magnetic resonance images (mp-MRI) are of high demand. Existing methods typically employ several separate steps, each of which is optimized individually without considering the error tolerance of other steps. As a result, they could either involve unnecessary computational cost or suffer from errors accumulated over steps. In this paper, we present an automated CS PCa detection system, where all steps are optimized jointly in an end-to-end trainable deep neural network. The proposed neural network consists of concatenated subnets: 1) a novel tissue deformation network (TDN) for automated prostate detection and multimodal registration and 2) a dual-path convolutional neural network (CNN) for CS PCa detection. Three types of loss functions, i.e., classification loss, inconsistency loss, and overlap loss, are employed for optimizing all parameters of the proposed TDN and CNN. In the training phase, the two nets mutually affect each other and effectively guide registration and extraction of representative CS PCa-relevant features to achieve results with sufficient accuracy. The entire network is trained in a weakly supervised manner by providing only image-level annotations (i.e., presence/absence of PCa) without exact priors of lesions' locations. Compared with most existing systems which require supervised labels, e.g., manual delineation of PCa lesions, it is much more convenient for clinical usage. Comprehensive evaluation based on fivefold cross validation using 360 patient data demonstrates that our system achieves a high accuracy for CS PCa detection, i.e., a sensitivity of 0.6374 and 0.8978 at 0.1 and 1 false positives per normal/benign patient.

Research on Classification of Chinese Text Data Based on SVM

NASA Astrophysics Data System (ADS)

Lin, Yuan; Yu, Hongzhi; Wan, Fucheng; Xu, Tao

2017-09-01

Data Mining has important application value in today’s industry and academia. Text classification is a very important technology in data mining. At present, there are many mature algorithms for text classification. KNN, NB, AB, SVM, decision tree and other classification methods all show good classification performance. Support Vector Machine’ (SVM) classification method is a good classifier in machine learning research. This paper will study the classification effect based on the SVM method in the Chinese text data, and use the support vector machine method in the chinese text to achieve the classify chinese text, and to able to combination of academia and practical application.

The intercrater plains of Mercury and the Moon: Their nature, origin and role in terrestrial planet evolution. Measurement and errors of crater statistics. Ph.D. Thesis

NASA Technical Reports Server (NTRS)

Leake, M. A.

1982-01-01

Planetary imagery techniques, errors in measurement or degradation assignment, and statistical formulas are presented with respect to cratering data. Base map photograph preparation, measurement of crater diameters and sampled area, and instruments used are discussed. Possible uncertainties, such as Sun angle, scale factors, degradation classification, and biases in crater recognition are discussed. The mathematical formulas used in crater statistics are presented.

Radiomic machine-learning classifiers for prognostic biomarkers of advanced nasopharyngeal carcinoma.

PubMed

Zhang, Bin; He, Xin; Ouyang, Fusheng; Gu, Dongsheng; Dong, Yuhao; Zhang, Lu; Mo, Xiaokai; Huang, Wenhui; Tian, Jie; Zhang, Shuixing

2017-09-10

We aimed to identify optimal machine-learning methods for radiomics-based prediction of local failure and distant failure in advanced nasopharyngeal carcinoma (NPC). We enrolled 110 patients with advanced NPC. A total of 970 radiomic features were extracted from MRI images for each patient. Six feature selection methods and nine classification methods were evaluated in terms of their performance. We applied the 10-fold cross-validation as the criterion for feature selection and classification. We repeated each combination for 50 times to obtain the mean area under the curve (AUC) and test error. We observed that the combination methods Random Forest (RF) + RF (AUC, 0.8464 ± 0.0069; test error, 0.3135 ± 0.0088) had the highest prognostic performance, followed by RF + Adaptive Boosting (AdaBoost) (AUC, 0.8204 ± 0.0095; test error, 0.3384 ± 0.0097), and Sure Independence Screening (SIS) + Linear Support Vector Machines (LSVM) (AUC, 0.7883 ± 0.0096; test error, 0.3985 ± 0.0100). Our radiomics study identified optimal machine-learning methods for the radiomics-based prediction of local failure and distant failure in advanced NPC, which could enhance the applications of radiomics in precision oncology and clinical practice. Copyright © 2017 Elsevier B.V. All rights reserved.

Inattention in primary school is not good for your future school achievement—A pattern classification study

PubMed Central

Bøe, Tormod; Lundervold, Arvid

2017-01-01

Inattention in childhood is associated with academic problems later in life. The contribution of specific aspects of inattentive behaviour is, however, less known. We investigated feature importance of primary school teachers’ reports on nine aspects of inattentive behaviour, gender and age in predicting future academic achievement. Primary school teachers of n = 2491 children (7–9 years) rated nine items reflecting different aspects of inattentive behaviour in 2002. A mean academic achievement score from the previous semester in high school (2012) was available for each youth from an official school register. All scores were at a categorical level. Feature importances were assessed by using multinominal logistic regression, classification and regression trees analysis, and a random forest algorithm. Finally, a comprehensive pattern classification procedure using k-fold cross-validation was implemented. Overall, inattention was rated as more severe in boys, who also obtained lower academic achievement scores in high school than girls. Problems related to sustained attention and distractibility were together with age and gender defined as the most important features to predict future achievement scores. Using these four features as input to a collection of classifiers employing k-fold cross-validation for prediction of academic achievement level, we obtained classification accuracy, precision and recall that were clearly better than chance levels. Primary school teachers’ reports of problems related to sustained attention and distractibility were identified as the two most important features of inattentive behaviour predicting academic achievement in high school. Identification and follow-up procedures of primary school children showing these characteristics should be prioritised to prevent future academic failure. PMID:29182663

Refractive Errors and Academic Achievements of Primary School Children.

PubMed

Joseph, Lucyamma

2014-01-01

The current study was conducted among school children of selected schools of Thiruvananthapuram district of Kerala. It was designed to investigate the effect of refractive errors on academic achievement of primary school children. Experimental method was used in the study and the study used a sample of 185 children. An equated sample without myopia were selected as control group. Academic achievement tests based on the study syllabus were prepared and administered to both groups. The children with myopia were given corrective devices such as glasses prescribed by the ophthalmologist. After five months academic achievement tests were again given to both groups and the results of the scores between two groups as well as the scores before and after correction of errors were compared, which showed a significant influence of myopia on academic achievement and examination anxiety of children.

Investigating error structure of shuttle radar topography mission elevation data product

NASA Astrophysics Data System (ADS)

Becek, Kazimierz

2008-08-01

An attempt was made to experimentally assess the instrumental component of error of the C-band SRTM (SRTM). This was achieved by comparing elevation data of 302 runways from airports all over the world with the shuttle radar topography mission data product (SRTM). It was found that the rms of the instrumental error is about +/-1.55 m. Modeling of the remaining SRTM error sources, including terrain relief and pixel size, shows that downsampling from 30 m to 90 m (1 to 3 arc-sec pixels) worsened SRTM vertical accuracy threefold. It is suspected that the proximity of large metallic objects is a source of large SRTM errors. The achieved error estimates allow a pixel-based accuracy assessment of the SRTM elevation data product to be constructed. Vegetation-induced errors were not considered in this work.

High Dimensional Classification Using Features Annealed Independence Rules.

PubMed

Fan, Jianqing; Fan, Yingying

2008-01-01

Classification using high-dimensional features arises frequently in many contemporary statistical studies such as tumor classification using microarray or other high-throughput data. The impact of dimensionality on classifications is largely poorly understood. In a seminal paper, Bickel and Levina (2004) show that the Fisher discriminant performs poorly due to diverging spectra and they propose to use the independence rule to overcome the problem. We first demonstrate that even for the independence classification rule, classification using all the features can be as bad as the random guessing due to noise accumulation in estimating population centroids in high-dimensional feature space. In fact, we demonstrate further that almost all linear discriminants can perform as bad as the random guessing. Thus, it is paramountly important to select a subset of important features for high-dimensional classification, resulting in Features Annealed Independence Rules (FAIR). The conditions under which all the important features can be selected by the two-sample t-statistic are established. The choice of the optimal number of features, or equivalently, the threshold value of the test statistics are proposed based on an upper bound of the classification error. Simulation studies and real data analysis support our theoretical results and demonstrate convincingly the advantage of our new classification procedure.

A label distance maximum-based classifier for multi-label learning.

PubMed

Liu, Xiaoli; Bao, Hang; Zhao, Dazhe; Cao, Peng

2015-01-01

Multi-label classification is useful in many bioinformatics tasks such as gene function prediction and protein site localization. This paper presents an improved neural network algorithm, Max Label Distance Back Propagation Algorithm for Multi-Label Classification. The method was formulated by modifying the total error function of the standard BP by adding a penalty term, which was realized by maximizing the distance between the positive and negative labels. Extensive experiments were conducted to compare this method against state-of-the-art multi-label methods on three popular bioinformatic benchmark datasets. The results illustrated that this proposed method is more effective for bioinformatic multi-label classification compared to commonly used techniques.

A novel onset detection technique for brain-computer interfaces using sound-production related cognitive tasks in simulated-online system

NASA Astrophysics Data System (ADS)

Song, YoungJae; Sepulveda, Francisco

2017-02-01

Objective. Self-paced EEG-based BCIs (SP-BCIs) have traditionally been avoided due to two sources of uncertainty: (1) precisely when an intentional command is sent by the brain, i.e., the command onset detection problem, and (2) how different the intentional command is when compared to non-specific (or idle) states. Performance evaluation is also a problem and there are no suitable standard metrics available. In this paper we attempted to tackle these issues. Approach. Self-paced covert sound-production cognitive tasks (i.e., high pitch and siren-like sounds) were used to distinguish between intentional commands (IC) and idle states. The IC states were chosen for their ease of execution and negligible overlap with common cognitive states. Band power and a digital wavelet transform were used for feature extraction, and the Davies-Bouldin index was used for feature selection. Classification was performed using linear discriminant analysis. Main results. Performance was evaluated under offline and simulated-online conditions. For the latter, a performance score called true-false-positive (TFP) rate, ranging from 0 (poor) to 100 (perfect), was created to take into account both classification performance and onset timing errors. Averaging the results from the best performing IC task for all seven participants, an 77.7% true-positive (TP) rate was achieved in offline testing. For simulated-online analysis the best IC average TFP score was 76.67% (87.61% TP rate, 4.05% false-positive rate). Significance. Results were promising when compared to previous IC onset detection studies using motor imagery, in which best TP rates were reported as 72.0% and 79.7%, and which, crucially, did not take timing errors into account. Moreover, based on our literature review, there is no previous covert sound-production onset detection system for spBCIs. Results showed that the proposed onset detection technique and TFP performance metric have good potential for use in SP-BCIs.

Automated confidence ranked classification of randomized controlled trial articles: an aid to evidence-based medicine

PubMed Central

Smalheiser, Neil R; McDonagh, Marian S; Yu, Clement; Adams, Clive E; Davis, John M; Yu, Philip S

2015-01-01

Objective: For many literature review tasks, including systematic review (SR) and other aspects of evidence-based medicine, it is important to know whether an article describes a randomized controlled trial (RCT). Current manual annotation is not complete or flexible enough for the SR process. In this work, highly accurate machine learning predictive models were built that include confidence predictions of whether an article is an RCT. Materials and Methods: The LibSVM classifier was used with forward selection of potential feature sets on a large human-related subset of MEDLINE to create a classification model requiring only the citation, abstract, and MeSH terms for each article. Results: The model achieved an area under the receiver operating characteristic curve of 0.973 and mean squared error of 0.013 on the held out year 2011 data. Accurate confidence estimates were confirmed on a manually reviewed set of test articles. A second model not requiring MeSH terms was also created, and performs almost as well. Discussion: Both models accurately rank and predict article RCT confidence. Using the model and the manually reviewed samples, it is estimated that about 8000 (3%) additional RCTs can be identified in MEDLINE, and that 5% of articles tagged as RCTs in Medline may not be identified. Conclusion: Retagging human-related studies with a continuously valued RCT confidence is potentially more useful for article ranking and review than a simple yes/no prediction. The automated RCT tagging tool should offer significant savings of time and effort during the process of writing SRs, and is a key component of a multistep text mining pipeline that we are building to streamline SR workflow. In addition, the model may be useful for identifying errors in MEDLINE publication types. The RCT confidence predictions described here have been made available to users as a web service with a user query form front end at: http://arrowsmith.psych.uic.edu/cgi-bin/arrowsmith_uic/RCT_Tagger.cgi. PMID:25656516

Lacie phase 1 Classification and Mensuration Subsystem (CAMS) rework experiment

NASA Technical Reports Server (NTRS)

Chhikara, R. S.; Hsu, E. M.; Liszcz, C. J.

1976-01-01

An experiment was designed to test the ability of the Classification and Mensuration Subsystem rework operations to improve wheat proportion estimates for segments that had been processed previously. Sites selected for the experiment included three in Kansas and three in Texas, with the remaining five distributed in Montana and North and South Dakota. The acquisition dates were selected to be representative of imagery available in actual operations. No more than one acquisition per biophase were used, and biophases were determined by actual crop calendars. All sites were worked by each of four Analyst-Interpreter/Data Processing Analyst Teams who reviewed the initial processing of each segment and accepted or reworked it for an estimate of the proportion of small grains in the segment. Classification results, acquisitions and classification errors and performance results between CAMS regular and ITS rework are tabulated.

Sample Errors Call Into Question Conclusions Regarding Same-Sex Married Parents: A Comment on "Family Structure and Child Health: Does the Sex Composition of Parents Matter?"

PubMed

Paul Sullins, D

2017-12-01

Because of classification errors reported by the National Center for Health Statistics, an estimated 42 % of the same-sex married partners in the sample for this study are misclassified different-sex married partners, thus calling into question findings regarding same-sex married parents. Including biological parentage as a control variable suppresses same-sex/different-sex differences, thus obscuring the data error. Parentage is not appropriate as a control because it correlates nearly perfectly (+.97, gamma) with the same-sex/different-sex distinction and is invariant for the category of joint biological parents.

Image Augmentation for Object Image Classification Based On Combination of Pre-Trained CNN and SVM

NASA Astrophysics Data System (ADS)

Shima, Yoshihiro

2018-04-01

Neural networks are a powerful means of classifying object images. The proposed image category classification method for object images combines convolutional neural networks (CNNs) and support vector machines (SVMs). A pre-trained CNN, called Alex-Net, is used as a pattern-feature extractor. Alex-Net is pre-trained for the large-scale object-image dataset ImageNet. Instead of training, Alex-Net, pre-trained for ImageNet is used. An SVM is used as trainable classifier. The feature vectors are passed to the SVM from Alex-Net. The STL-10 dataset are used as object images. The number of classes is ten. Training and test samples are clearly split. STL-10 object images are trained by the SVM with data augmentation. We use the pattern transformation method with the cosine function. We also apply some augmentation method such as rotation, skewing and elastic distortion. By using the cosine function, the original patterns were left-justified, right-justified, top-justified, or bottom-justified. Patterns were also center-justified and enlarged. Test error rate is decreased by 0.435 percentage points from 16.055% by augmentation with cosine transformation. Error rates are increased by other augmentation method such as rotation, skewing and elastic distortion, compared without augmentation. Number of augmented data is 30 times that of the original STL-10 5K training samples. Experimental test error rate for the test 8k STL-10 object images was 15.620%, which shows that image augmentation is effective for image category classification.

Automated detection of cloud and cloud-shadow in single-date Landsat imagery using neural networks and spatial post-processing

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

Hughes, Michael J.; Hayes, Daniel J

2014-01-01

Use of Landsat data to answer ecological questions is contingent on the effective removal of cloud and cloud shadow from satellite images. We develop a novel algorithm to identify and classify clouds and cloud shadow, \\textsc{sparcs}: Spacial Procedures for Automated Removal of Cloud and Shadow. The method uses neural networks to determine cloud, cloud-shadow, water, snow/ice, and clear-sky membership of each pixel in a Landsat scene, and then applies a set of procedures to enforce spatial rules. In a comparison to FMask, a high-quality cloud and cloud-shadow classification algorithm currently available, \\textsc{sparcs} performs favorably, with similar omission errors for cloudsmore » (0.8% and 0.9%, respectively), substantially lower omission error for cloud-shadow (8.3% and 1.1%), and fewer errors of commission (7.8% and 5.0%). Additionally, textsc{sparcs} provides a measure of uncertainty in its classification that can be exploited by other processes that use the cloud and cloud-shadow detection. To illustrate this, we present an application that constructs obstruction-free composites of images acquired on different dates in support of algorithms detecting vegetation change.« less

Discrimination of Aspergillus isolates at the species and strain level by matrix-assisted laser desorption/ionization time-of-flight mass spectrometry fingerprinting.

PubMed

Hettick, Justin M; Green, Brett J; Buskirk, Amanda D; Kashon, Michael L; Slaven, James E; Janotka, Erika; Blachere, Francoise M; Schmechel, Detlef; Beezhold, Donald H

2008-09-15

Matrix-assisted laser desorption/ionization time-of-flight mass spectrometry (MALDI-TOF MS) was used to generate highly reproducible mass spectral fingerprints for 12 species of fungi of the genus Aspergillus and 5 different strains of Aspergillus flavus. Prior to MALDI-TOF MS analysis, the fungi were subjected to three 1-min bead beating cycles in an acetonitrile/trifluoroacetic acid solvent. The mass spectra contain abundant peaks in the range of 5 to 20kDa and may be used to discriminate between species unambiguously. A discriminant analysis using all peaks from the MALDI-TOF MS data yielded error rates for classification of 0 and 18.75% for resubstitution and cross-validation methods, respectively. If a subset of 28 significant peaks is chosen, resubstitution and cross-validation error rates are 0%. Discriminant analysis of the MALDI-TOF MS data for 5 strains of A. flavus using all peaks yielded error rates for classification of 0 and 5% for resubstitution and cross-validation methods, respectively. These data indicate that MALDI-TOF MS data may be used for unambiguous identification of members of the genus Aspergillus at both the species and strain levels.

Identifying medication error chains from critical incident reports: a new analytic approach.

PubMed

Huckels-Baumgart, Saskia; Manser, Tanja

2014-10-01

Research into the distribution of medication errors usually focuses on isolated stages within the medication use process. Our study aimed to provide a novel process-oriented approach to medication incident analysis focusing on medication error chains. Our study was conducted across a 900-bed teaching hospital in Switzerland. All reported 1,591 medication errors 2009-2012 were categorized using the Medication Error Index NCC MERP and the WHO Classification for Patient Safety Methodology. In order to identify medication error chains, each reported medication incident was allocated to the relevant stage of the hospital medication use process. Only 25.8% of the reported medication errors were detected before they propagated through the medication use process. The majority of medication errors (74.2%) formed an error chain encompassing two or more stages. The most frequent error chain comprised preparation up to and including medication administration (45.2%). "Non-consideration of documentation/prescribing" during the drug preparation was the most frequent contributor for "wrong dose" during the administration of medication. Medication error chains provide important insights for detecting and stopping medication errors before they reach the patient. Existing and new safety barriers need to be extended to interrupt error chains and to improve patient safety. © 2014, The American College of Clinical Pharmacology.

Methods for data classification

DOEpatents

Garrity, George [Okemos, MI; Lilburn, Timothy G [Front Royal, VA

2011-10-11

The present invention provides methods for classifying data and uncovering and correcting annotation errors. In particular, the present invention provides a self-organizing, self-correcting algorithm for use in classifying data. Additionally, the present invention provides a method for classifying biological taxa.

Determining Fuzzy Membership for Sentiment Classification: A Three-Layer Sentiment Propagation Model

PubMed Central

Zhao, Chuanjun; Wang, Suge; Li, Deyu

2016-01-01

Enormous quantities of review documents exist in forums, blogs, twitter accounts, and shopping web sites. Analysis of the sentiment information hidden in these review documents is very useful for consumers and manufacturers. The sentiment orientation and sentiment intensity of a review can be described in more detail by using a sentiment score than by using bipolar sentiment polarity. Existing methods for calculating review sentiment scores frequently use a sentiment lexicon or the locations of features in a sentence, a paragraph, and a document. In order to achieve more accurate sentiment scores of review documents, a three-layer sentiment propagation model (TLSPM) is proposed that uses three kinds of interrelations, those among documents, topics, and words. First, we use nine relationship pairwise matrices between documents, topics, and words. In TLSPM, we suppose that sentiment neighbors tend to have the same sentiment polarity and similar sentiment intensity in the sentiment propagation network. Then, we implement the sentiment propagation processes among the documents, topics, and words in turn. Finally, we can obtain the steady sentiment scores of documents by a continuous iteration process. Intuition might suggest that documents with strong sentiment intensity make larger contributions to classification than those with weak sentiment intensity. Therefore, we use the fuzzy membership of documents obtained by TLSPM as the weight of the text to train a fuzzy support vector machine model (FSVM). As compared with a support vector machine (SVM) and four other fuzzy membership determination methods, the results show that FSVM trained with TLSPM can enhance the effectiveness of sentiment classification. In addition, FSVM trained with TLSPM can reduce the mean square error (MSE) on seven sentiment rating prediction data sets. PMID:27846225

A Corpus-Based Approach for Automatic Thai Unknown Word Recognition Using Boosting Techniques

NASA Astrophysics Data System (ADS)

Techo, Jakkrit; Nattee, Cholwich; Theeramunkong, Thanaruk

While classification techniques can be applied for automatic unknown word recognition in a language without word boundary, it faces with the problem of unbalanced datasets where the number of positive unknown word candidates is dominantly smaller than that of negative candidates. To solve this problem, this paper presents a corpus-based approach that introduces a so-called group-based ranking evaluation technique into ensemble learning in order to generate a sequence of classification models that later collaborate to select the most probable unknown word from multiple candidates. Given a classification model, the group-based ranking evaluation (GRE) is applied to construct a training dataset for learning the succeeding model, by weighing each of its candidates according to their ranks and correctness when the candidates of an unknown word are considered as one group. A number of experiments have been conducted on a large Thai medical text to evaluate performance of the proposed group-based ranking evaluation approach, namely V-GRE, compared to the conventional naïve Bayes classifier and our vanilla version without ensemble learning. As the result, the proposed method achieves an accuracy of 90.93±0.50% when the first rank is selected while it gains 97.26±0.26% when the top-ten candidates are considered, that is 8.45% and 6.79% improvement over the conventional record-based naïve Bayes classifier and the vanilla version. Another result on applying only best features show 93.93±0.22% and up to 98.85±0.15% accuracy for top-1 and top-10, respectively. They are 3.97% and 9.78% improvement over naive Bayes and the vanilla version. Finally, an error analysis is given.

Stop! border ahead: Automatic detection of subthalamic exit during deep brain stimulation surgery.

PubMed

Valsky, Dan; Marmor-Levin, Odeya; Deffains, Marc; Eitan, Renana; Blackwell, Kim T; Bergman, Hagai; Israel, Zvi

2017-01-01

Microelectrode recordings along preplanned trajectories are often used for accurate definition of the subthalamic nucleus (STN) borders during deep brain stimulation (DBS) surgery for Parkinson's disease. Usually, the demarcation of the STN borders is performed manually by a neurophysiologist. The exact detection of the borders is difficult, especially detecting the transition between the STN and the substantia nigra pars reticulata. Consequently, demarcation may be inaccurate, leading to suboptimal location of the DBS lead and inadequate clinical outcomes. We present machine-learning classification procedures that use microelectrode recording power spectra and allow for real-time, high-accuracy discrimination between the STN and substantia nigra pars reticulata. A support vector machine procedure was tested on microelectrode recordings from 58 trajectories that included both STN and substantia nigra pars reticulata that achieved a 97.6% consistency with human expert classification (evaluated by 10-fold cross-validation). We used the same data set as a training set to find the optimal parameters for a hidden Markov model using both microelectrode recording features and trajectory history to enable real-time classification of the ventral STN border (STN exit). Seventy-three additional trajectories were used to test the reliability of the learned statistical model in identifying the exit from the STN. The hidden Markov model procedure identified the STN exit with an error of 0.04 ± 0.18 mm and detection reliability (error < 1 mm) of 94%. The results indicate that robust, accurate, and automatic real-time electrophysiological detection of the ventral STN border is feasible. © 2016 International Parkinson and Movement Disorder Society. © 2016 International Parkinson and Movement Disorder Society.

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

Yan, H; Chen, Z; Nath, R

Purpose: kV fluoroscopic imaging combined with MV treatment beam imaging has been investigated for intrafractional motion monitoring and correction. It is, however, subject to additional kV imaging dose to normal tissue. To balance tracking accuracy and imaging dose, we previously proposed an adaptive imaging strategy to dynamically decide future imaging type and moments based on motion tracking uncertainty. kV imaging may be used continuously for maximal accuracy or only when the position uncertainty (probability of out of threshold) is high if a preset imaging dose limit is considered. In this work, we propose more accurate methods to estimate tracking uncertaintymore » through analyzing acquired data in real-time. Methods: We simulated motion tracking process based on a previously developed imaging framework (MV + initial seconds of kV imaging) using real-time breathing data from 42 patients. Motion tracking errors for each time point were collected together with the time point’s corresponding features, such as tumor motion speed and 2D tracking error of previous time points, etc. We tested three methods for error uncertainty estimation based on the features: conditional probability distribution, logistic regression modeling, and support vector machine (SVM) classification to detect errors exceeding a threshold. Results: For conditional probability distribution, polynomial regressions on three features (previous tracking error, prediction quality, and cosine of the angle between the trajectory and the treatment beam) showed strong correlation with the variation (uncertainty) of the mean 3D tracking error and its standard deviation: R-square = 0.94 and 0.90, respectively. The logistic regression and SVM classification successfully identified about 95% of tracking errors exceeding 2.5mm threshold. Conclusion: The proposed methods can reliably estimate the motion tracking uncertainty in real-time, which can be used to guide adaptive additional imaging to confirm the tumor is within the margin or initialize motion compensation if it is out of the margin.« less

Diagnostic Classification Models and Multidimensional Adaptive Testing: A Commentary on Rupp and Templin

ERIC Educational Resources Information Center

Frey, Andreas; Carstensen, Claus H.

2009-01-01

On a general level, the objective of diagnostic classifications models (DCMs) lies in a classification of individuals regarding multiple latent skills. In this article, the authors show that this objective can be achieved by multidimensional adaptive testing (MAT) as well. The authors discuss whether or not the restricted applicability of DCMs can…

Real-time Neuroimaging and Cognitive Monitoring Using Wearable Dry EEG

PubMed Central

Mullen, Tim R.; Kothe, Christian A.E.; Chi, Mike; Ojeda, Alejandro; Kerth, Trevor; Makeig, Scott; Jung, Tzyy-Ping; Cauwenberghs, Gert

2015-01-01

Goal We present and evaluate a wearable high-density dry electrode EEG system and an open-source software framework for online neuroimaging and state classification. Methods The system integrates a 64-channel dry EEG form-factor with wireless data streaming for online analysis. A real-time software framework is applied, including adaptive artifact rejection, cortical source localization, multivariate effective connectivity inference, data visualization, and cognitive state classification from connectivity features using a constrained logistic regression approach (ProxConn). We evaluate the system identification methods on simulated 64-channel EEG data. Then we evaluate system performance, using ProxConn and a benchmark ERP method, in classifying response errors in 9 subjects using the dry EEG system. Results Simulations yielded high accuracy (AUC=0.97±0.021) for real-time cortical connectivity estimation. Response error classification using cortical effective connectivity (sdDTF) was significantly above chance with similar performance (AUC) for cLORETA (0.74±0.09) and LCMV (0.72±0.08) source localization. Cortical ERP-based classification was equivalent to ProxConn for cLORETA (0.74±0.16) but significantly better for LCMV (0.82±0.12). Conclusion We demonstrated the feasibility for real-time cortical connectivity analysis and cognitive state classification from high-density wearable dry EEG. Significance This paper is the first validated application of these methods to 64-channel dry EEG. The work addresses a need for robust real-time measurement and interpretation of complex brain activity in the dynamic environment of the wearable setting. Such advances can have broad impact in research, medicine, and brain-computer interfaces. The pipelines are made freely available in the open-source SIFT and BCILAB toolboxes. PMID:26415149

Camouflage target reconnaissance based on hyperspectral imaging technology

NASA Astrophysics Data System (ADS)

Hua, Wenshen; Guo, Tong; Liu, Xun

2015-08-01

Efficient camouflaged target reconnaissance technology makes great influence on modern warfare. Hyperspectral images can provide large spectral range and high spectral resolution, which are invaluable in discriminating between camouflaged targets and backgrounds. Hyperspectral target detection and classification technology are utilized to achieve single class and multi-class camouflaged targets reconnaissance respectively. Constrained energy minimization (CEM), a widely used algorithm in hyperspectral target detection, is employed to achieve one class camouflage target reconnaissance. Then, support vector machine (SVM), a classification method, is proposed to achieve multi-class camouflage target reconnaissance. Experiments have been conducted to demonstrate the efficiency of the proposed method.

Material identification in x-ray microscopy and micro CT using multi-layer, multi-color scintillation detectors

PubMed Central

Modgil, Dimple; Rigie, David S.; Wang, Yuxin; Xiao, Xianghui; Vargas, Phillip A.; La Rivière, Patrick J.

2015-01-01

We demonstrate that a dual-layer, dual-color scintillator construct for microscopic CT, originally proposed to increase sensitivity in synchrotron imaging, can also be used to perform material quantification and classification when coupled with polychromatic illumination. We consider two different approaches to data handling: (1) a data-domain material decomposition whose estimation performance can be characterized by the Cramer-Rao Lower Bound formalism but which requires careful calibration and (2) an image-domain material classification approach that is more robust to calibration errors. The data-domain analysis indicates that useful levels of SNR (>5) could be achieved in one second or less at typical bending magnet fluxes for relatively large amounts of contrast (several mm path length, such as in a fluid flow experiment) and at typical undulator fluxes for small amount of contrast (tens of microns path length, such as an angiography experiment). The tools introduced could of course be used to study and optimize parameters for a wider range of potential applications. The image domain approach was analyzed in terms of its ability to distinguish different elemental stains by characterizing the angle between the lines traced out in a two-dimensional space of effective attenuation coefficient in the front and back layer images. This approach was implemented at a synchrotron and the results were consistent with simulation predictions. PMID:26422059

Review of Cuttability Indices and A New Rockmass Classification Approach for Selection of Surface Miners

NASA Astrophysics Data System (ADS)

Dey, Kaushik; Ghose, A. K.

2011-09-01

Rock excavation is carried out either by drilling and blasting or using rock-cutting machines like rippers, bucket wheel excavators, surface miners, road headers etc. Economics of mechanised rock excavation by rock-cutting machines largely depends on the achieved production rates. Thus, assessment of the performance (productivity) is important prior to deploying a rock-cutting machine. In doing so, several researchers have classified rockmass in different ways and have developed cuttability indices to correlate machine performance directly. However, most of these indices were developed to assess the performance of road headers/tunnel-boring machines apart from a few that were developed in the earlier days when the ripper was a popular excavating equipment. Presently, around 400 surface miners are in operation around the world amongst which, 105 are in India. Until now, no rockmass classification system is available to assess the performance of surface miners. Surface miners are being deployed largely on trial and error basis or based on the performance charts provided by the manufacturer. In this context, it is logical to establish a suitable cuttability index to predict the performance of surface miners. In this present paper, the existing cuttability indices are reviewed and a new cuttability indexes proposed. A new relationship is also developed to predict the output from surface miners using the proposed cuttability index.

Material identification in x-ray microscopy and micro CT using multi-layer, multi-color scintillation detectors

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

Modgil, Dimple; Rigie, David S.; Wang, Yuxin

We demonstrate that a dual-layer, dual-color scintillator construct for microscopic CT, originally proposed to increase sensitivity in synchrotron imaging, can also be used to perform material quantification and classification when coupled with polychromatic illumination. We consider two different approaches to data handling: (1) a data-domain material decomposition whose estimation performance can be characterized by the Cramer-Rao lower bound formalism but which requires careful calibration and (2) an image-domain material classification approach that is more robust to calibration errors. The data-domain analysis indicates that useful levels of SNR (>5) could be achieved in one second or less at typical bending magnetmore » fluxes for relatively large amounts of contrast (several mm path length, such as in a fluid flow experiment) and at typical undulator fluxes for small amount of contrast (tens of microns path length, such as an angiography experiment). The tools introduced could of course be used to study and optimize parameters for a wider range of potential applications. The image domain approach was analyzed in terms of its ability to distinguish different elemental stains by characterizing the angle between the lines traced out in a two-dimensional space of effective attenuation coefficient in the front and back layer images. As a result, this approach was implemented at a synchrotron and the results were consistent with simulation predictions.« less

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

DOE PAGES

James, Conrad D.; Aimone, James B.; Miner, Nadine E.; ...

2017-01-04

In this study, biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classesmore » such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.« less

Quantifying Differences and Similarities in Whole-Brain White Matter Architecture Using Local Connectome Fingerprints

PubMed Central

Singh, Aarti; Poczos, Barnabas; Erickson, Kirk I.; Tseng, Wen-Yih I.; Verstynen, Timothy D.

2016-01-01

Quantifying differences or similarities in connectomes has been a challenge due to the immense complexity of global brain networks. Here we introduce a noninvasive method that uses diffusion MRI to characterize whole-brain white matter architecture as a single local connectome fingerprint that allows for a direct comparison between structural connectomes. In four independently acquired data sets with repeated scans (total N = 213), we show that the local connectome fingerprint is highly specific to an individual, allowing for an accurate self-versus-others classification that achieved 100% accuracy across 17,398 identification tests. The estimated classification error was approximately one thousand times smaller than fingerprints derived from diffusivity-based measures or region-to-region connectivity patterns for repeat scans acquired within 3 months. The local connectome fingerprint also revealed neuroplasticity within an individual reflected as a decreasing trend in self-similarity across time, whereas this change was not observed in the diffusivity measures. Moreover, the local connectome fingerprint can be used as a phenotypic marker, revealing 12.51% similarity between monozygotic twins, 5.14% between dizygotic twins, and 4.51% between none-twin siblings, relative to differences between unrelated subjects. This novel approach opens a new door for probing the influence of pathological, genetic, social, or environmental factors on the unique configuration of the human connectome. PMID:27846212

A historical survey of algorithms and hardware architectures for neural-inspired and neuromorphic computing applications

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

James, Conrad D.; Aimone, James B.; Miner, Nadine E.

In this study, biological neural networks continue to inspire new developments in algorithms and microelectronic hardware to solve challenging data processing and classification problems. Here in this research, we survey the history of neural-inspired and neuromorphic computing in order to examine the complex and intertwined trajectories of the mathematical theory and hardware developed in this field. Early research focused on adapting existing hardware to emulate the pattern recognition capabilities of living organisms. Contributions from psychologists, mathematicians, engineers, neuroscientists, and other professions were crucial to maturing the field from narrowly-tailored demonstrations to more generalizable systems capable of addressing difficult problem classesmore » such as object detection and speech recognition. Algorithms that leverage fundamental principles found in neuroscience such as hierarchical structure, temporal integration, and robustness to error have been developed, and some of these approaches are achieving world-leading performance on particular data classification tasks. Additionally, novel microelectronic hardware is being developed to perform logic and to serve as memory in neuromorphic computing systems with optimized system integration and improved energy efficiency. Key to such advancements was the incorporation of new discoveries in neuroscience research, the transition away from strict structural replication and towards the functional replication of neural systems, and the use of mathematical theory frameworks to guide algorithm and hardware developments.« less

Material identification in x-ray microscopy and micro CT using multi-layer, multi-color scintillation detectors

DOE PAGES

Modgil, Dimple; Rigie, David S.; Wang, Yuxin; ...

2015-09-30

We demonstrate that a dual-layer, dual-color scintillator construct for microscopic CT, originally proposed to increase sensitivity in synchrotron imaging, can also be used to perform material quantification and classification when coupled with polychromatic illumination. We consider two different approaches to data handling: (1) a data-domain material decomposition whose estimation performance can be characterized by the Cramer-Rao lower bound formalism but which requires careful calibration and (2) an image-domain material classification approach that is more robust to calibration errors. The data-domain analysis indicates that useful levels of SNR (>5) could be achieved in one second or less at typical bending magnetmore » fluxes for relatively large amounts of contrast (several mm path length, such as in a fluid flow experiment) and at typical undulator fluxes for small amount of contrast (tens of microns path length, such as an angiography experiment). The tools introduced could of course be used to study and optimize parameters for a wider range of potential applications. The image domain approach was analyzed in terms of its ability to distinguish different elemental stains by characterizing the angle between the lines traced out in a two-dimensional space of effective attenuation coefficient in the front and back layer images. As a result, this approach was implemented at a synchrotron and the results were consistent with simulation predictions.« less

Two fast and accurate heuristic RBF learning rules for data classification.

PubMed

Rouhani, Modjtaba; Javan, Dawood S

2016-03-01

This paper presents new Radial Basis Function (RBF) learning methods for classification problems. The proposed methods use some heuristics to determine the spreads, the centers and the number of hidden neurons of network in such a way that the higher efficiency is achieved by fewer numbers of neurons, while the learning algorithm remains fast and simple. To retain network size limited, neurons are added to network recursively until termination condition is met. Each neuron covers some of train data. The termination condition is to cover all training data or to reach the maximum number of neurons. In each step, the center and spread of the new neuron are selected based on maximization of its coverage. Maximization of coverage of the neurons leads to a network with fewer neurons and indeed lower VC dimension and better generalization property. Using power exponential distribution function as the activation function of hidden neurons, and in the light of new learning approaches, it is proved that all data became linearly separable in the space of hidden layer outputs which implies that there exist linear output layer weights with zero training error. The proposed methods are applied to some well-known datasets and the simulation results, compared with SVM and some other leading RBF learning methods, show their satisfactory and comparable performance. Copyright © 2015 Elsevier Ltd. All rights reserved.

Recognition of medical errors’ reporting system dimensions in educational hospitals

PubMed Central

Yarmohammadian, Mohammad H.; Mohammadinia, Leila; Tavakoli, Nahid; Ghalriz, Parvin; Haghshenas, Abbas

2014-01-01

Introduction and Objective: Nowadays medical errors are one of the serious issues in the health-care system and carry to account of the patient's safety threat. The most important step for achieving safety promotion is identifying errors and their causes in order to recognize, correct and omit them. Concerning about repeating medical errors and harms, which were received via theses errors concluded to designing and establishing medical error reporting systems for hospitals and centers that are presenting therapeutic services. The aim of this study is the recognition of medical errors’ reporting system dimensions in educational hospitals. Materials and Methods: This research is a descriptive-analytical and qualities’ study, which has been carried out in Shahid Beheshti educational therapeutic center in Isfahan during 2012. In this study, relevant information was collected through 15 face to face interviews. That each of interviews take place in about 1hr and creation of five focused discussion groups through 45 min for each section, they were composed of Metron, educational supervisor, health officer, health education, and all of the head nurses. Concluded data interviews and discussion sessions were coded, then achieved results were extracted in the presence of clear-sighted persons and after their feedback perception, they were categorized. In order to make sure of information correctness, tables were presented to the research's interviewers and final the corrections were confirmed based on their view. Finding: The extracted information from interviews and discussion groups have been divided into nine main categories after content analyzing and subject coding and their subsets have been completely expressed. Achieved dimensions are composed of nine domains of medical error concept, error cases according to nurses’ prospection, medical error reporting barriers, employees’ motivational factors for error reporting, purposes of medical error reporting system, error reporting's challenges and opportunities, a desired system characteristics, and the quality of error experiences’ transmission in the health-care system. Conclusion: Although, appropriate achievements have been assured in Shahid Beheshti Hospital, but it seems necessary that in order to immune promotion not only in this hospital, but in the other organizations, necessary infrastructures have been provided for an error reporting system performance. An appropriate medical error reporting system could be educated and prevent the occurrence of repeated errors. PMID:25250342

Quality assurance of chemical ingredient classification for the National Drug File - Reference Terminology.

PubMed

Zheng, Ling; Yumak, Hasan; Chen, Ling; Ochs, Christopher; Geller, James; Kapusnik-Uner, Joan; Perl, Yehoshua

2017-09-01

The National Drug File - Reference Terminology (NDF-RT) is a large and complex drug terminology consisting of several classification hierarchies on top of an extensive collection of drug concepts. These hierarchies provide important information about clinical drugs, e.g., their chemical ingredients, mechanisms of action, dosage form and physiological effects. Within NDF-RT such information is represented using tens of thousands of roles connecting drugs to classifications. In previous studies, we have introduced various kinds of Abstraction Networks to summarize the content and structure of terminologies in order to facilitate their visual comprehension, and support quality assurance of terminologies. However, these previous kinds of Abstraction Networks are not appropriate for summarizing the NDF-RT classification hierarchies, due to its unique structure. In this paper, we present the novel Ingredient Abstraction Network (IAbN) to summarize, visualize and support the audit of NDF-RT's Chemical Ingredients hierarchy and its associated drugs. A common theme in our quality assurance framework is to use characterizations of sets of concepts, revealed by the Abstraction Network structure, to capture concepts, the modeling of which is more complex than for other concepts. For the IAbN, we characterize drug ingredient concepts as more complex if they belong to IAbN groups with multiple parent groups. We show that such concepts have a statistically significantly higher rate of errors than a control sample and identify two especially common patterns of errors. Copyright © 2017 Elsevier Inc. All rights reserved.

A Quantile Mapping Bias Correction Method Based on Hydroclimatic Classification of the Guiana Shield

PubMed Central

Ringard, Justine; Seyler, Frederique; Linguet, Laurent

2017-01-01

Satellite precipitation products (SPPs) provide alternative precipitation data for regions with sparse rain gauge measurements. However, SPPs are subject to different types of error that need correction. Most SPP bias correction methods use the statistical properties of the rain gauge data to adjust the corresponding SPP data. The statistical adjustment does not make it possible to correct the pixels of SPP data for which there is no rain gauge data. The solution proposed in this article is to correct the daily SPP data for the Guiana Shield using a novel two set approach, without taking into account the daily gauge data of the pixel to be corrected, but the daily gauge data from surrounding pixels. In this case, a spatial analysis must be involved. The first step defines hydroclimatic areas using a spatial classification that considers precipitation data with the same temporal distributions. The second step uses the Quantile Mapping bias correction method to correct the daily SPP data contained within each hydroclimatic area. We validate the results by comparing the corrected SPP data and daily rain gauge measurements using relative RMSE and relative bias statistical errors. The results show that analysis scale variation reduces rBIAS and rRMSE significantly. The spatial classification avoids mixing rainfall data with different temporal characteristics in each hydroclimatic area, and the defined bias correction parameters are more realistic and appropriate. This study demonstrates that hydroclimatic classification is relevant for implementing bias correction methods at the local scale. PMID:28621723

A Quantile Mapping Bias Correction Method Based on Hydroclimatic Classification of the Guiana Shield.

PubMed

Ringard, Justine; Seyler, Frederique; Linguet, Laurent

2017-06-16

Satellite precipitation products (SPPs) provide alternative precipitation data for regions with sparse rain gauge measurements. However, SPPs are subject to different types of error that need correction. Most SPP bias correction methods use the statistical properties of the rain gauge data to adjust the corresponding SPP data. The statistical adjustment does not make it possible to correct the pixels of SPP data for which there is no rain gauge data. The solution proposed in this article is to correct the daily SPP data for the Guiana Shield using a novel two set approach, without taking into account the daily gauge data of the pixel to be corrected, but the daily gauge data from surrounding pixels. In this case, a spatial analysis must be involved. The first step defines hydroclimatic areas using a spatial classification that considers precipitation data with the same temporal distributions. The second step uses the Quantile Mapping bias correction method to correct the daily SPP data contained within each hydroclimatic area. We validate the results by comparing the corrected SPP data and daily rain gauge measurements using relative RMSE and relative bias statistical errors. The results show that analysis scale variation reduces rBIAS and rRMSE significantly. The spatial classification avoids mixing rainfall data with different temporal characteristics in each hydroclimatic area, and the defined bias correction parameters are more realistic and appropriate. This study demonstrates that hydroclimatic classification is relevant for implementing bias correction methods at the local scale.

An investigation of the usability of sound recognition for source separation of packaging wastes in reverse vending machines.

PubMed

Korucu, M Kemal; Kaplan, Özgür; Büyük, Osman; Güllü, M Kemal

2016-10-01

In this study, we investigate the usability of sound recognition for source separation of packaging wastes in reverse vending machines (RVMs). For this purpose, an experimental setup equipped with a sound recording mechanism was prepared. Packaging waste sounds generated by three physical impacts such as free falling, pneumatic hitting and hydraulic crushing were separately recorded using two different microphones. To classify the waste types and sizes based on sound features of the wastes, a support vector machine (SVM) and a hidden Markov model (HMM) based sound classification systems were developed. In the basic experimental setup in which only free falling impact type was considered, SVM and HMM systems provided 100% classification accuracy for both microphones. In the expanded experimental setup which includes all three impact types, material type classification accuracies were 96.5% for dynamic microphone and 97.7% for condenser microphone. When both the material type and the size of the wastes were classified, the accuracy was 88.6% for the microphones. The modeling studies indicated that hydraulic crushing impact type recordings were very noisy for an effective sound recognition application. In the detailed analysis of the recognition errors, it was observed that most of the errors occurred in the hitting impact type. According to the experimental results, it can be said that the proposed novel approach for the separation of packaging wastes could provide a high classification performance for RVMs. Copyright © 2016 Elsevier Ltd. All rights reserved.