Improving Spectral Image Classification through Band-Ratio Optimization and Pixel Clustering

NASA Astrophysics Data System (ADS)

O'Neill, M.; Burt, C.; McKenna, I.; Kimblin, C.

2017-12-01

The Underground Nuclear Explosion Signatures Experiment (UNESE) seeks to characterize non-prompt observables from underground nuclear explosions (UNE). As part of this effort, we evaluated the ability of DigitalGlobe's WorldView-3 (WV3) to detect and map UNE signatures. WV3 is the current state-of-the-art, commercial, multispectral imaging satellite; however, it has relatively limited spectral and spatial resolutions. These limitations impede image classifiers from detecting targets that are spatially small and lack distinct spectral features. In order to improve classification results, we developed custom algorithms to reduce false positive rates while increasing true positive rates via a band-ratio optimization and pixel clustering front-end. The clusters resulting from these algorithms were processed with standard spectral image classifiers such as Mixture-Tuned Matched Filter (MTMF) and Adaptive Coherence Estimator (ACE). WV3 and AVIRIS data of Cuprite, Nevada, were used as a validation data set. These data were processed with a standard classification approach using MTMF and ACE algorithms. They were also processed using the custom front-end prior to the standard approach. A comparison of the results shows that the custom front-end significantly increases the true positive rate and decreases the false positive rate.This work was done by National Security Technologies, LLC, under Contract No. DE-AC52-06NA25946 with the U.S. Department of Energy. DOE/NV/25946-3283.

Environment-specific noise suppression for improved speech intelligibility by cochlear implant users.

PubMed

Hu, Yi; Loizou, Philipos C

2010-06-01

Attempts to develop noise-suppression algorithms that can significantly improve speech intelligibility in noise by cochlear implant (CI) users have met with limited success. This is partly because algorithms were sought that would work equally well in all listening situations. Accomplishing this has been quite challenging given the variability in the temporal/spectral characteristics of real-world maskers. A different approach is taken in the present study focused on the development of environment-specific noise suppression algorithms. The proposed algorithm selects a subset of the envelope amplitudes for stimulation based on the signal-to-noise ratio (SNR) of each channel. Binary classifiers, trained using data collected from a particular noisy environment, are first used to classify the mixture envelopes of each channel as either target-dominated (SNR>or=0 dB) or masker-dominated (SNR<0 dB). Only target-dominated channels are subsequently selected for stimulation. Results with CI listeners indicated substantial improvements (by nearly 44 percentage points at 5 dB SNR) in intelligibility with the proposed algorithm when tested with sentences embedded in three real-world maskers. The present study demonstrated that the environment-specific approach to noise reduction has the potential to restore speech intelligibility in noise to a level near to that attained in quiet.

Aid decision algorithms to estimate the risk in congenital heart surgery.

PubMed

Ruiz-Fernández, Daniel; Monsalve Torra, Ana; Soriano-Payá, Antonio; Marín-Alonso, Oscar; Triana Palencia, Eddy

2016-04-01

In this paper, we have tested the suitability of using different artificial intelligence-based algorithms for decision support when classifying the risk of congenital heart surgery. In this sense, classification of those surgical risks provides enormous benefits as the a priori estimation of surgical outcomes depending on either the type of disease or the type of repair, and other elements that influence the final result. This preventive estimation may help to avoid future complications, or even death. We have evaluated four machine learning algorithms to achieve our objective: multilayer perceptron, self-organizing map, radial basis function networks and decision trees. The architectures implemented have the aim of classifying among three types of surgical risk: low complexity, medium complexity and high complexity. Accuracy outcomes achieved range between 80% and 99%, being the multilayer perceptron method the one that offered a higher hit ratio. According to the results, it is feasible to develop a clinical decision support system using the evaluated algorithms. Such system would help cardiology specialists, paediatricians and surgeons to forecast the level of risk related to a congenital heart disease surgery. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Chaotic Particle Swarm Optimization with Mutation for Classification

PubMed Central

Assarzadeh, Zahra; Naghsh-Nilchi, Ahmad Reza

2015-01-01

In this paper, a chaotic particle swarm optimization with mutation-based classifier particle swarm optimization is proposed to classify patterns of different classes in the feature space. The introduced mutation operators and chaotic sequences allows us to overcome the problem of early convergence into a local minima associated with particle swarm optimization algorithms. That is, the mutation operator sharpens the convergence and it tunes the best possible solution. Furthermore, to remove the irrelevant data and reduce the dimensionality of medical datasets, a feature selection approach using binary version of the proposed particle swarm optimization is introduced. In order to demonstrate the effectiveness of our proposed classifier, mutation-based classifier particle swarm optimization, it is checked out with three sets of data classifications namely, Wisconsin diagnostic breast cancer, Wisconsin breast cancer and heart-statlog, with different feature vector dimensions. The proposed algorithm is compared with different classifier algorithms including k-nearest neighbor, as a conventional classifier, particle swarm-classifier, genetic algorithm, and Imperialist competitive algorithm-classifier, as more sophisticated ones. The performance of each classifier was evaluated by calculating the accuracy, sensitivity, specificity and Matthews's correlation coefficient. The experimental results show that the mutation-based classifier particle swarm optimization unequivocally performs better than all the compared algorithms. PMID:25709937

Model of a Frame of Dynamic Routing and Its Equilibrium

NASA Astrophysics Data System (ADS)

Zhang, Shu; Yuan, Yuan; Xu, Jian

Dynamic routing algorithm based on the shortest path principle is criticized due to the oscillation induced by such routing scheme. In the present work, we propose the model of TCP/RED algorithm by a new frame of dynamic routing, based on the measurement of occupation ratio of router buffer for different links, which only requires the information of the queue size at the buffer of the router, to stabilize the system. We classify several types of equilibrium and employ the numerical method to study the stability of the steady state. Our numerical results show that the careful selection of the parameters characterizing the dynamic routing algorithm can stabilize the system in some cases.

An Effective Big Data Supervised Imbalanced Classification Approach for Ortholog Detection in Related Yeast Species

PubMed Central

Galpert, Deborah; del Río, Sara; Herrera, Francisco; Ancede-Gallardo, Evys; Antunes, Agostinho; Agüero-Chapin, Guillermin

2015-01-01

Orthology detection requires more effective scaling algorithms. In this paper, a set of gene pair features based on similarity measures (alignment scores, sequence length, gene membership to conserved regions, and physicochemical profiles) are combined in a supervised pairwise ortholog detection approach to improve effectiveness considering low ortholog ratios in relation to the possible pairwise comparison between two genomes. In this scenario, big data supervised classifiers managing imbalance between ortholog and nonortholog pair classes allow for an effective scaling solution built from two genomes and extended to other genome pairs. The supervised approach was compared with RBH, RSD, and OMA algorithms by using the following yeast genome pairs: Saccharomyces cerevisiae-Kluyveromyces lactis, Saccharomyces cerevisiae-Candida glabrata, and Saccharomyces cerevisiae-Schizosaccharomyces pombe as benchmark datasets. Because of the large amount of imbalanced data, the building and testing of the supervised model were only possible by using big data supervised classifiers managing imbalance. Evaluation metrics taking low ortholog ratios into account were applied. From the effectiveness perspective, MapReduce Random Oversampling combined with Spark SVM outperformed RBH, RSD, and OMA, probably because of the consideration of gene pair features beyond alignment similarities combined with the advances in big data supervised classification. PMID:26605337

An Effective Big Data Supervised Imbalanced Classification Approach for Ortholog Detection in Related Yeast Species.

PubMed

Galpert, Deborah; Del Río, Sara; Herrera, Francisco; Ancede-Gallardo, Evys; Antunes, Agostinho; Agüero-Chapin, Guillermin

2015-01-01

Orthology detection requires more effective scaling algorithms. In this paper, a set of gene pair features based on similarity measures (alignment scores, sequence length, gene membership to conserved regions, and physicochemical profiles) are combined in a supervised pairwise ortholog detection approach to improve effectiveness considering low ortholog ratios in relation to the possible pairwise comparison between two genomes. In this scenario, big data supervised classifiers managing imbalance between ortholog and nonortholog pair classes allow for an effective scaling solution built from two genomes and extended to other genome pairs. The supervised approach was compared with RBH, RSD, and OMA algorithms by using the following yeast genome pairs: Saccharomyces cerevisiae-Kluyveromyces lactis, Saccharomyces cerevisiae-Candida glabrata, and Saccharomyces cerevisiae-Schizosaccharomyces pombe as benchmark datasets. Because of the large amount of imbalanced data, the building and testing of the supervised model were only possible by using big data supervised classifiers managing imbalance. Evaluation metrics taking low ortholog ratios into account were applied. From the effectiveness perspective, MapReduce Random Oversampling combined with Spark SVM outperformed RBH, RSD, and OMA, probably because of the consideration of gene pair features beyond alignment similarities combined with the advances in big data supervised classification.

Comparing the performance of meta-classifiers—a case study on selected imbalanced data sets relevant for prediction of liver toxicity

NASA Astrophysics Data System (ADS)

Jain, Sankalp; Kotsampasakou, Eleni; Ecker, Gerhard F.

2018-05-01

Cheminformatics datasets used in classification problems, especially those related to biological or physicochemical properties, are often imbalanced. This presents a major challenge in development of in silico prediction models, as the traditional machine learning algorithms are known to work best on balanced datasets. The class imbalance introduces a bias in the performance of these algorithms due to their preference towards the majority class. Here, we present a comparison of the performance of seven different meta-classifiers for their ability to handle imbalanced datasets, whereby Random Forest is used as base-classifier. Four different datasets that are directly (cholestasis) or indirectly (via inhibition of organic anion transporting polypeptide 1B1 and 1B3) related to liver toxicity were chosen for this purpose. The imbalance ratio in these datasets ranges between 4:1 and 20:1 for negative and positive classes, respectively. Three different sets of molecular descriptors for model development were used, and their performance was assessed in 10-fold cross-validation and on an independent validation set. Stratified bagging, MetaCost and CostSensitiveClassifier were found to be the best performing among all the methods. While MetaCost and CostSensitiveClassifier provided better sensitivity values, Stratified Bagging resulted in high balanced accuracies.

Comparing the performance of meta-classifiers—a case study on selected imbalanced data sets relevant for prediction of liver toxicity

NASA Astrophysics Data System (ADS)

Jain, Sankalp; Kotsampasakou, Eleni; Ecker, Gerhard F.

2018-04-01

Cheminformatics datasets used in classification problems, especially those related to biological or physicochemical properties, are often imbalanced. This presents a major challenge in development of in silico prediction models, as the traditional machine learning algorithms are known to work best on balanced datasets. The class imbalance introduces a bias in the performance of these algorithms due to their preference towards the majority class. Here, we present a comparison of the performance of seven different meta-classifiers for their ability to handle imbalanced datasets, whereby Random Forest is used as base-classifier. Four different datasets that are directly (cholestasis) or indirectly (via inhibition of organic anion transporting polypeptide 1B1 and 1B3) related to liver toxicity were chosen for this purpose. The imbalance ratio in these datasets ranges between 4:1 and 20:1 for negative and positive classes, respectively. Three different sets of molecular descriptors for model development were used, and their performance was assessed in 10-fold cross-validation and on an independent validation set. Stratified bagging, MetaCost and CostSensitiveClassifier were found to be the best performing among all the methods. While MetaCost and CostSensitiveClassifier provided better sensitivity values, Stratified Bagging resulted in high balanced accuracies.

Qualitative analysis of pure and adulterated canola oil via SIMCA

NASA Astrophysics Data System (ADS)

Basri, Katrul Nadia; Khir, Mohd Fared Abdul; Rani, Rozina Abdul; Sharif, Zaiton; Rusop, M.; Zoolfakar, Ahmad Sabirin

2018-05-01

This paper demonstrates the utilization of near infrared (NIR) spectroscopy to classify pure and adulterated sample of canola oil. Soft Independent Modeling Class Analogies (SIMCA) algorithm was implemented to discriminate the samples to its classes. Spectral data obtained was divided using Kennard Stone algorithm into training and validation dataset by a fixed ratio of 7:3. The model accuracy obtained based on the model built is 0.99 whereas the sensitivity and precision are 0.92 and 1.00. The result showed the classification model is robust to perform qualitative analysis of canola oil for future application.

Utilizing gamma band to improve mental task based brain-computer interface design.

PubMed

Palaniappan, Ramaswamy

2006-09-01

A common method for designing brain-computer Interface (BCI) is to use electroencephalogram (EEG) signals extracted during mental tasks. In these BCI designs, features from EEG such as power and asymmetry ratios from delta, theta, alpha, and beta bands have been used in classifying different mental tasks. In this paper, the performance of the mental task based BCI design is improved by using spectral power and asymmetry ratios from gamma (24-37 Hz) band in addition to the lower frequency bands. In the experimental study, EEG signals extracted during five mental tasks from four subjects were used. Elman neural network (ENN) trained by the resilient backpropagation algorithm was used to classify the power and asymmetry ratios from EEG into different combinations of two mental tasks. The results indicated that ((1) the classification performance and training time of the BCI design were improved through the use of additional gamma band features; (2) classification performances were nearly invariant to the number of ENN hidden units or feature extraction method.

An algorithm that improves speech intelligibility in noise for normal-hearing listeners.

PubMed

Kim, Gibak; Lu, Yang; Hu, Yi; Loizou, Philipos C

2009-09-01

Traditional noise-suppression algorithms have been shown to improve speech quality, but not speech intelligibility. Motivated by prior intelligibility studies of speech synthesized using the ideal binary mask, an algorithm is proposed that decomposes the input signal into time-frequency (T-F) units and makes binary decisions, based on a Bayesian classifier, as to whether each T-F unit is dominated by the target or the masker. Speech corrupted at low signal-to-noise ratio (SNR) levels (-5 and 0 dB) using different types of maskers is synthesized by this algorithm and presented to normal-hearing listeners for identification. Results indicated substantial improvements in intelligibility (over 60% points in -5 dB babble) over that attained by human listeners with unprocessed stimuli. The findings from this study suggest that algorithms that can estimate reliably the SNR in each T-F unit can improve speech intelligibility.

Toward real-time quantification of fluorescence molecular probes using target/background ratio for guiding biopsy and endoscopic therapy of esophageal neoplasia.

PubMed

Jiang, Yang; Gong, Yuanzheng; Rubenstein, Joel H; Wang, Thomas D; Seibel, Eric J

2017-04-01

Multimodal endoscopy using fluorescence molecular probes is a promising method of surveying the entire esophagus to detect cancer progression. Using the fluorescence ratio of a target compared to a surrounding background, a quantitative value is diagnostic for progression from Barrett's esophagus to high-grade dysplasia (HGD) and esophageal adenocarcinoma (EAC). However, current quantification of fluorescent images is done only after the endoscopic procedure. We developed a Chan-Vese-based algorithm to segment fluorescence targets, and subsequent morphological operations to generate background, thus calculating target/background (T/B) ratios, potentially to provide real-time guidance for biopsy and endoscopic therapy. With an initial processing speed of 2 fps and by calculating the T/B ratio for each frame, our method provides quasireal-time quantification of the molecular probe labeling to the endoscopist. Furthermore, an automatic computer-aided diagnosis algorithm can be applied to the recorded endoscopic video, and the overall T/B ratio is calculated for each patient. The receiver operating characteristic curve was employed to determine the threshold for classification of HGD/EAC using leave-one-out cross-validation. With 92% sensitivity and 75% specificity to classify HGD/EAC, our automatic algorithm shows promising results for a surveillance procedure to help manage esophageal cancer and other cancers inspected by endoscopy.

Prediction of breast cancer risk using a machine learning approach embedded with a locality preserving projection algorithm.

PubMed

Heidari, Morteza; Khuzani, Abolfazl Zargari; Hollingsworth, Alan B; Danala, Gopichandh; Mirniaharikandehei, Seyedehnafiseh; Qiu, Yuchen; Liu, Hong; Zheng, Bin

2018-01-30

In order to automatically identify a set of effective mammographic image features and build an optimal breast cancer risk stratification model, this study aims to investigate advantages of applying a machine learning approach embedded with a locally preserving projection (LPP) based feature combination and regeneration algorithm to predict short-term breast cancer risk. A dataset involving negative mammograms acquired from 500 women was assembled. This dataset was divided into two age-matched classes of 250 high risk cases in which cancer was detected in the next subsequent mammography screening and 250 low risk cases, which remained negative. First, a computer-aided image processing scheme was applied to segment fibro-glandular tissue depicted on mammograms and initially compute 44 features related to the bilateral asymmetry of mammographic tissue density distribution between left and right breasts. Next, a multi-feature fusion based machine learning classifier was built to predict the risk of cancer detection in the next mammography screening. A leave-one-case-out (LOCO) cross-validation method was applied to train and test the machine learning classifier embedded with a LLP algorithm, which generated a new operational vector with 4 features using a maximal variance approach in each LOCO process. Results showed a 9.7% increase in risk prediction accuracy when using this LPP-embedded machine learning approach. An increased trend of adjusted odds ratios was also detected in which odds ratios increased from 1.0 to 11.2. This study demonstrated that applying the LPP algorithm effectively reduced feature dimensionality, and yielded higher and potentially more robust performance in predicting short-term breast cancer risk.

Prediction of breast cancer risk using a machine learning approach embedded with a locality preserving projection algorithm

NASA Astrophysics Data System (ADS)

Heidari, Morteza; Zargari Khuzani, Abolfazl; Hollingsworth, Alan B.; Danala, Gopichandh; Mirniaharikandehei, Seyedehnafiseh; Qiu, Yuchen; Liu, Hong; Zheng, Bin

2018-02-01

In order to automatically identify a set of effective mammographic image features and build an optimal breast cancer risk stratification model, this study aims to investigate advantages of applying a machine learning approach embedded with a locally preserving projection (LPP) based feature combination and regeneration algorithm to predict short-term breast cancer risk. A dataset involving negative mammograms acquired from 500 women was assembled. This dataset was divided into two age-matched classes of 250 high risk cases in which cancer was detected in the next subsequent mammography screening and 250 low risk cases, which remained negative. First, a computer-aided image processing scheme was applied to segment fibro-glandular tissue depicted on mammograms and initially compute 44 features related to the bilateral asymmetry of mammographic tissue density distribution between left and right breasts. Next, a multi-feature fusion based machine learning classifier was built to predict the risk of cancer detection in the next mammography screening. A leave-one-case-out (LOCO) cross-validation method was applied to train and test the machine learning classifier embedded with a LLP algorithm, which generated a new operational vector with 4 features using a maximal variance approach in each LOCO process. Results showed a 9.7% increase in risk prediction accuracy when using this LPP-embedded machine learning approach. An increased trend of adjusted odds ratios was also detected in which odds ratios increased from 1.0 to 11.2. This study demonstrated that applying the LPP algorithm effectively reduced feature dimensionality, and yielded higher and potentially more robust performance in predicting short-term breast cancer risk.

A Pulse Coupled Neural Network Segmentation Algorithm for Reflectance Confocal Images of Epithelial Tissue

PubMed Central

Malik, Bilal H.; Jabbour, Joey M.; Maitland, Kristen C.

2015-01-01

Automatic segmentation of nuclei in reflectance confocal microscopy images is critical for visualization and rapid quantification of nuclear-to-cytoplasmic ratio, a useful indicator of epithelial precancer. Reflectance confocal microscopy can provide three-dimensional imaging of epithelial tissue in vivo with sub-cellular resolution. Changes in nuclear density or nuclear-to-cytoplasmic ratio as a function of depth obtained from confocal images can be used to determine the presence or stage of epithelial cancers. However, low nuclear to background contrast, low resolution at greater imaging depths, and significant variation in reflectance signal of nuclei complicate segmentation required for quantification of nuclear-to-cytoplasmic ratio. Here, we present an automated segmentation method to segment nuclei in reflectance confocal images using a pulse coupled neural network algorithm, specifically a spiking cortical model, and an artificial neural network classifier. The segmentation algorithm was applied to an image model of nuclei with varying nuclear to background contrast. Greater than 90% of simulated nuclei were detected for contrast of 2.0 or greater. Confocal images of porcine and human oral mucosa were used to evaluate application to epithelial tissue. Segmentation accuracy was assessed using manual segmentation of nuclei as the gold standard. PMID:25816131

Fuzzy classifier based support vector regression framework for Poisson ratio determination

NASA Astrophysics Data System (ADS)

Asoodeh, Mojtaba; Bagheripour, Parisa

2013-09-01

Poisson ratio is considered as one of the most important rock mechanical properties of hydrocarbon reservoirs. Determination of this parameter through laboratory measurement is time, cost, and labor intensive. Furthermore, laboratory measurements do not provide continuous data along the reservoir intervals. Hence, a fast, accurate, and inexpensive way of determining Poisson ratio which produces continuous data over the whole reservoir interval is desirable. For this purpose, support vector regression (SVR) method based on statistical learning theory (SLT) was employed as a supervised learning algorithm to estimate Poisson ratio from conventional well log data. SVR is capable of accurately extracting the implicit knowledge contained in conventional well logs and converting the gained knowledge into Poisson ratio data. Structural risk minimization (SRM) principle which is embedded in the SVR structure in addition to empirical risk minimization (EMR) principle provides a robust model for finding quantitative formulation between conventional well log data and Poisson ratio. Although satisfying results were obtained from an individual SVR model, it had flaws of overestimation in low Poisson ratios and underestimation in high Poisson ratios. These errors were eliminated through implementation of fuzzy classifier based SVR (FCBSVR). The FCBSVR significantly improved accuracy of the final prediction. This strategy was successfully applied to data from carbonate reservoir rocks of an Iranian Oil Field. Results indicated that SVR predicted Poisson ratio values are in good agreement with measured values.

Automated detection and classification of major retinal vessels for determination of diameter ratio of arteries and veins

NASA Astrophysics Data System (ADS)

Muramatsu, Chisako; Hatanaka, Yuji; Iwase, Tatsuhiko; Hara, Takeshi; Fujita, Hiroshi

2010-03-01

Abnormalities of retinal vasculatures can indicate health conditions in the body, such as the high blood pressure and diabetes. Providing automatically determined width ratio of arteries and veins (A/V ratio) on retinal fundus images may help physicians in the diagnosis of hypertensive retinopathy, which may cause blindness. The purpose of this study was to detect major retinal vessels and classify them into arteries and veins for the determination of A/V ratio. Images used in this study were obtained from DRIVE database, which consists of 20 cases each for training and testing vessel detection algorithms. Starting with the reference standard of vasculature segmentation provided in the database, major arteries and veins each in the upper and lower temporal regions were manually selected for establishing the gold standard. We applied the black top-hat transformation and double-ring filter to detect retinal blood vessels. From the extracted vessels, large vessels extending from the optic disc to temporal regions were selected as target vessels for calculation of A/V ratio. Image features were extracted from the vessel segments from quarter-disc to one disc diameter from the edge of optic discs. The target segments in the training cases were classified into arteries and veins by using the linear discriminant analysis, and the selected parameters were applied to those in the test cases. Out of 40 pairs, 30 pairs (75%) of arteries and veins in the 20 test cases were correctly classified. The result can be used for the automated calculation of A/V ratio.

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.

Hybrid ANN optimized artificial fish swarm algorithm based classifier for classification of suspicious lesions in breast DCE-MRI

NASA Astrophysics Data System (ADS)

Janaki Sathya, D.; Geetha, K.

2017-12-01

Automatic mass or lesion classification systems are developed to aid in distinguishing between malignant and benign lesions present in the breast DCE-MR images, the systems need to improve both the sensitivity and specificity of DCE-MR image interpretation in order to be successful for clinical use. A new classifier (a set of features together with a classification method) based on artificial neural networks trained using artificial fish swarm optimization (AFSO) algorithm is proposed in this paper. The basic idea behind the proposed classifier is to use AFSO algorithm for searching the best combination of synaptic weights for the neural network. An optimal set of features based on the statistical textural features is presented. The investigational outcomes of the proposed suspicious lesion classifier algorithm therefore confirm that the resulting classifier performs better than other such classifiers reported in the literature. Therefore this classifier demonstrates that the improvement in both the sensitivity and specificity are possible through automated image analysis.

Application of machine learning algorithms to the study of noise artifacts in gravitational-wave data

NASA Astrophysics Data System (ADS)

Biswas, Rahul; Blackburn, Lindy; Cao, Junwei; Essick, Reed; Hodge, Kari Alison; Katsavounidis, Erotokritos; Kim, Kyungmin; Kim, Young-Min; Le Bigot, Eric-Olivier; Lee, Chang-Hwan; Oh, John J.; Oh, Sang Hoon; Son, Edwin J.; Tao, Ye; Vaulin, Ruslan; Wang, Xiaoge

2013-09-01

The sensitivity of searches for astrophysical transients in data from the Laser Interferometer Gravitational-wave Observatory (LIGO) is generally limited by the presence of transient, non-Gaussian noise artifacts, which occur at a high enough rate such that accidental coincidence across multiple detectors is non-negligible. These “glitches” can easily be mistaken for transient gravitational-wave signals, and their robust identification and removal will help any search for astrophysical gravitational waves. We apply machine-learning algorithms (MLAs) to the problem, using data from auxiliary channels within the LIGO detectors that monitor degrees of freedom unaffected by astrophysical signals. Noise sources may produce artifacts in these auxiliary channels as well as the gravitational-wave channel. The number of auxiliary-channel parameters describing these disturbances may also be extremely large; high dimensionality is an area where MLAs are particularly well suited. We demonstrate the feasibility and applicability of three different MLAs: artificial neural networks, support vector machines, and random forests. These classifiers identify and remove a substantial fraction of the glitches present in two different data sets: four weeks of LIGO’s fourth science run and one week of LIGO’s sixth science run. We observe that all three algorithms agree on which events are glitches to within 10% for the sixth-science-run data, and support this by showing that the different optimization criteria used by each classifier generate the same decision surface, based on a likelihood-ratio statistic. Furthermore, we find that all classifiers obtain similar performance to the benchmark algorithm, the ordered veto list, which is optimized to detect pairwise correlations between transients in LIGO auxiliary channels and glitches in the gravitational-wave data. This suggests that most of the useful information currently extracted from the auxiliary channels is already described by this model. Future performance gains are thus likely to involve additional sources of information, rather than improvements in the classification algorithms themselves. We discuss several plausible sources of such new information as well as the ways of propagating it through the classifiers into gravitational-wave searches.

Sitting Posture Monitoring System Based on a Low-Cost Load Cell Using Machine Learning

PubMed Central

Roh, Jongryun; Park, Hyeong-jun; Lee, Kwang Jin; Hyeong, Joonho; Kim, Sayup

2018-01-01

Sitting posture monitoring systems (SPMSs) help assess the posture of a seated person in real-time and improve sitting posture. To date, SPMS studies reported have required many sensors mounted on the backrest plate and seat plate of a chair. The present study, therefore, developed a system that measures a total of six sitting postures including the posture that applied a load to the backrest plate, with four load cells mounted only on the seat plate. Various machine learning algorithms were applied to the body weight ratio measured by the developed SPMS to identify the method that most accurately classified the actual sitting posture of the seated person. After classifying the sitting postures using several classifiers, average and maximum classification rates of 97.20% and 97.94%, respectively, were obtained from nine subjects with a support vector machine using the radial basis function kernel; the results obtained by this classifier showed a statistically significant difference from the results of multiple classifications using other classifiers. The proposed SPMS was able to classify six sitting postures including the posture with loading on the backrest and showed the possibility of classifying the sitting posture even though the number of sensors is reduced. PMID:29329261

Novel probabilistic neuroclassifier

NASA Astrophysics Data System (ADS)

Hong, Jiang; Serpen, Gursel

2003-09-01

A novel probabilistic potential function neural network classifier algorithm to deal with classes which are multi-modally distributed and formed from sets of disjoint pattern clusters is proposed in this paper. The proposed classifier has a number of desirable properties which distinguish it from other neural network classifiers. A complete description of the algorithm in terms of its architecture and the pseudocode is presented. Simulation analysis of the newly proposed neuro-classifier algorithm on a set of benchmark problems is presented. Benchmark problems tested include IRIS, Sonar, Vowel Recognition, Two-Spiral, Wisconsin Breast Cancer, Cleveland Heart Disease and Thyroid Gland Disease. Simulation results indicate that the proposed neuro-classifier performs consistently better for a subset of problems for which other neural classifiers perform relatively poorly.

AdaBoost-based algorithm for network intrusion detection.

PubMed

Hu, Weiming; Hu, Wei; Maybank, Steve

2008-04-01

Network intrusion detection aims at distinguishing the attacks on the Internet from normal use of the Internet. It is an indispensable part of the information security system. Due to the variety of network behaviors and the rapid development of attack fashions, it is necessary to develop fast machine-learning-based intrusion detection algorithms with high detection rates and low false-alarm rates. In this correspondence, we propose an intrusion detection algorithm based on the AdaBoost algorithm. In the algorithm, decision stumps are used as weak classifiers. The decision rules are provided for both categorical and continuous features. By combining the weak classifiers for continuous features and the weak classifiers for categorical features into a strong classifier, the relations between these two different types of features are handled naturally, without any forced conversions between continuous and categorical features. Adaptable initial weights and a simple strategy for avoiding overfitting are adopted to improve the performance of the algorithm. Experimental results show that our algorithm has low computational complexity and error rates, as compared with algorithms of higher computational complexity, as tested on the benchmark sample data.

Controlling for Frailty in Pharmacoepidemiologic Studies of Older Adults: Validation of an Existing Medicare Claims-based Algorithm.

PubMed

Cuthbertson, Carmen C; Kucharska-Newton, Anna; Faurot, Keturah R; Stürmer, Til; Jonsson Funk, Michele; Palta, Priya; Windham, B Gwen; Thai, Sydney; Lund, Jennifer L

2018-07-01

Frailty is a geriatric syndrome characterized by weakness and weight loss and is associated with adverse health outcomes. It is often an unmeasured confounder in pharmacoepidemiologic and comparative effectiveness studies using administrative claims data. Among the Atherosclerosis Risk in Communities (ARIC) Study Visit 5 participants (2011-2013; n = 3,146), we conducted a validation study to compare a Medicare claims-based algorithm of dependency in activities of daily living (or dependency) developed as a proxy for frailty with a reference standard measure of phenotypic frailty. We applied the algorithm to the ARIC participants' claims data to generate a predicted probability of dependency. Using the claims-based algorithm, we estimated the C-statistic for predicting phenotypic frailty. We further categorized participants by their predicted probability of dependency (<5%, 5% to <20%, and ≥20%) and estimated associations with difficulties in physical abilities, falls, and mortality. The claims-based algorithm showed good discrimination of phenotypic frailty (C-statistic = 0.71; 95% confidence interval [CI] = 0.67, 0.74). Participants classified with a high predicted probability of dependency (≥20%) had higher prevalence of falls and difficulty in physical ability, and a greater risk of 1-year all-cause mortality (hazard ratio = 5.7 [95% CI = 2.5, 13]) than participants classified with a low predicted probability (<5%). Sensitivity and specificity varied across predicted probability of dependency thresholds. The Medicare claims-based algorithm showed good discrimination of phenotypic frailty and high predictive ability with adverse health outcomes. This algorithm can be used in future Medicare claims analyses to reduce confounding by frailty and improve study validity.

A review and experimental study on the application of classifiers and evolutionary algorithms in EEG-based brain-machine interface systems

NASA Astrophysics Data System (ADS)

Tahernezhad-Javazm, Farajollah; Azimirad, Vahid; Shoaran, Maryam

2018-04-01

Objective. Considering the importance and the near-future development of noninvasive brain-machine interface (BMI) systems, this paper presents a comprehensive theoretical-experimental survey on the classification and evolutionary methods for BMI-based systems in which EEG signals are used. Approach. The paper is divided into two main parts. In the first part, a wide range of different types of the base and combinatorial classifiers including boosting and bagging classifiers and evolutionary algorithms are reviewed and investigated. In the second part, these classifiers and evolutionary algorithms are assessed and compared based on two types of relatively widely used BMI systems, sensory motor rhythm-BMI and event-related potentials-BMI. Moreover, in the second part, some of the improved evolutionary algorithms as well as bi-objective algorithms are experimentally assessed and compared. Main results. In this study two databases are used, and cross-validation accuracy (CVA) and stability to data volume (SDV) are considered as the evaluation criteria for the classifiers. According to the experimental results on both databases, regarding the base classifiers, linear discriminant analysis and support vector machines with respect to CVA evaluation metric, and naive Bayes with respect to SDV demonstrated the best performances. Among the combinatorial classifiers, four classifiers, Bagg-DT (bagging decision tree), LogitBoost, and GentleBoost with respect to CVA, and Bagging-LR (bagging logistic regression) and AdaBoost (adaptive boosting) with respect to SDV had the best performances. Finally, regarding the evolutionary algorithms, single-objective invasive weed optimization (IWO) and bi-objective nondominated sorting IWO algorithms demonstrated the best performances. Significance. We present a general survey on the base and the combinatorial classification methods for EEG signals (sensory motor rhythm and event-related potentials) as well as their optimization methods through the evolutionary algorithms. In addition, experimental and statistical significance tests are carried out to study the applicability and effectiveness of the reviewed methods.

Towards reducing the impacts of unwanted movements on identification of motion intentions.

PubMed

Li, Xiangxin; Chen, Shixiong; Zhang, Haoshi; Samuel, Oluwarotimi Williams; Wang, Hui; Fang, Peng; Zhang, Xiufeng; Li, Guanglin

2016-06-01

Surface electromyogram (sEMG) has been extensively used as a control signal in prosthesis devices. However, it is still a great challenge to make multifunctional myoelectric prostheses clinically available due to a number of critical issues associated with existing EMG based control strategy. One such issue would be the effect of unwanted movements (UMs) that are inadvertently done by users on the performance of movement classification in EMG pattern recognition based algorithms. Since UMs are not considered in training a classifier, they would decay the performance of a trained classifier in identifying the target movements (TMs), which would cause some undesired actions in control of multifunctional prostheses. In this study, the impact of UMs was systemically investigated in both able-bodied subjects and transradial amputees. Our results showed that the UMs would be unevenly classified into all classes of the TMs. To reduce the impact of the UMs on the performance of a classifier, a new training strategy that would categorize all possible UMs into a new movement class was proposed and a metric called Reject Ratio that is a measure of how many UMs is rejected by a trained classifier was adopted. The results showed that the average Reject Ratio across all the participants was greater than 91%, meanwhile the average classification accuracy of TMs was above 99% when UMs occurred. This suggests that the proposed training strategy could greatly reduce the impact of UMs on the performance of the trained classifier in identifying the TMs and may enhance the robustness of myoelectric control in clinical applications. Copyright © 2016 Elsevier Ltd. All rights reserved.

Feature Selection and Effective Classifiers.

ERIC Educational Resources Information Center

Deogun, Jitender S.; Choubey, Suresh K.; Raghavan, Vijay V.; Sever, Hayri

1998-01-01

Develops and analyzes four algorithms for feature selection in the context of rough set methodology. Experimental results confirm the expected relationship between the time complexity of these algorithms and the classification accuracy of the resulting upper classifiers. When compared, results of upper classifiers perform better than lower…

Non-proliferative diabetic retinopathy symptoms detection and classification using neural network.

PubMed

Al-Jarrah, Mohammad A; Shatnawi, Hadeel

2017-08-01

Diabetic retinopathy (DR) causes blindness in the working age for people with diabetes in most countries. The increasing number of people with diabetes worldwide suggests that DR will continue to be major contributors to vision loss. Early detection of retinopathy progress in individuals with diabetes is critical for preventing visual loss. Non-proliferative DR (NPDR) is an early stage of DR. Moreover, NPDR can be classified into mild, moderate and severe. This paper proposes a novel morphology-based algorithm for detecting retinal lesions and classifying each case. First, the proposed algorithm detects the three DR lesions, namely haemorrhages, microaneurysms and exudates. Second, we defined and extracted a set of features from detected lesions. The set of selected feature emulates what physicians looked for in classifying NPDR case. Finally, we designed an artificial neural network (ANN) classifier with three layers to classify NPDR to normal, mild, moderate and severe. Bayesian regularisation and resilient backpropagation algorithms are used to train ANN. The accuracy for the proposed classifiers based on Bayesian regularisation and resilient backpropagation algorithms are 96.6 and 89.9, respectively. The obtained results are compared with results of the recent published classifier. Our proposed classifier outperforms the best in terms of sensitivity and specificity.

Classification of case-II waters using hyperspectral (HICO) data over North Indian Ocean

NASA Astrophysics Data System (ADS)

Srinivasa Rao, N.; Ramarao, E. P.; Srinivas, K.; Deka, P. C.

2016-05-01

State of the art Ocean color algorithms are proven for retrieving the ocean constituents (chlorophyll-a, CDOM and Suspended Sediments) in case-I waters. However, these algorithms could not perform well at case-II waters because of the optical complexity. Hyperspectral data is found to be promising to classify the case-II waters. The aim of this study is to propose the spectral bands for future Ocean color sensors to classify the case-II waters. Study has been performed with Rrs's of HICO at estuaries of the river Indus and GBM of North Indian Ocean. Appropriate field samples are not available to validate and propose empirical models to retrieve concentrations. The sensor HICO is not currently operational to plan validation exercise. Aqua MODIS data at case-I and Case-II waters are used as complementary to in- situ. Analysis of Spectral reflectance curves suggests the band ratios of Rrs 484 nm and Rrs 581 nm, Rrs 490 nm and Rrs 426 nm to classify the Chlorophyll -a and CDOM respectively. Rrs 610 nm gives the best scope for suspended sediment retrieval. The work suggests the need for ocean color sensors with central wavelength's of 426, 484, 490, 581 and 610 nm to estimate the concentrations of Chl-a, Suspended Sediments and CDOM in case-II waters.

Advances in Doppler recognition for ground moving target indication

NASA Astrophysics Data System (ADS)

Kealey, Paul G.; Jahangir, Mohammed

2006-05-01

Ground Moving Target Indication (GMTI) radar provides a day/night, all-weather, wide-area surveillance capability to detect moving vehicles and personnel. Current GMTI radar sensors are limited to only detecting and tracking targets. The exploitation of GMTI data would be greatly enhanced by a capability to recognize accurately the detections as significant classes of target. Doppler classification exploits the differential internal motion of targets, e.g. due to the tracks, limbs and rotors. Recently, the QinetiQ Bayesian Doppler classifier has been extended to include a helicopter class in addition to wheeled, tracked and personnel classes. This paper presents the performance for these four classes using a traditional low-resolution GMTI surveillance waveform with an experimental radar system. We have determined the utility of an "unknown output decision" for enhancing the accuracy of the declared target classes. A confidence method has been derived, using a threshold of the difference in certainties, to assign uncertain classifications into an "unknown class". The trade-off between fraction of targets declared and accuracy of the classifier has been measured. To determine the operating envelope of a Doppler classification algorithm requires a detailed understanding of the Signal-to-Noise Ratio (SNR) performance of the algorithm. In this study the SNR dependence of the QinetiQ classifier has been determined.

Semantic segmentation of mFISH images using convolutional networks.

PubMed

Pardo, Esteban; Morgado, José Mário T; Malpica, Norberto

2018-04-30

Multicolor in situ hybridization (mFISH) is a karyotyping technique used to detect major chromosomal alterations using fluorescent probes and imaging techniques. Manual interpretation of mFISH images is a time consuming step that can be automated using machine learning; in previous works, pixel or patch wise classification was employed, overlooking spatial information which can help identify chromosomes. In this work, we propose a fully convolutional semantic segmentation network for the interpretation of mFISH images, which uses both spatial and spectral information to classify each pixel in an end-to-end fashion. The semantic segmentation network developed was tested on samples extracted from a public dataset using cross validation. Despite having no labeling information of the image it was tested on, our algorithm yielded an average correct classification ratio (CCR) of 87.41%. Previously, this level of accuracy was only achieved with state of the art algorithms when classifying pixels from the same image in which the classifier has been trained. These results provide evidence that fully convolutional semantic segmentation networks may be employed in the computer aided diagnosis of genetic diseases with improved performance over the current image analysis methods. © 2018 International Society for Advancement of Cytometry. © 2018 International Society for Advancement of Cytometry.

A Modified Decision Tree Algorithm Based on Genetic Algorithm for Mobile User Classification Problem

PubMed Central

Liu, Dong-sheng; Fan, Shu-jiang

2014-01-01

In order to offer mobile customers better service, we should classify the mobile user firstly. Aimed at the limitations of previous classification methods, this paper puts forward a modified decision tree algorithm for mobile user classification, which introduced genetic algorithm to optimize the results of the decision tree algorithm. We also take the context information as a classification attributes for the mobile user and we classify the context into public context and private context classes. Then we analyze the processes and operators of the algorithm. At last, we make an experiment on the mobile user with the algorithm, we can classify the mobile user into Basic service user, E-service user, Plus service user, and Total service user classes and we can also get some rules about the mobile user. Compared to C4.5 decision tree algorithm and SVM algorithm, the algorithm we proposed in this paper has higher accuracy and more simplicity. PMID:24688389

LDA boost classification: boosting by topics

NASA Astrophysics Data System (ADS)

Lei, La; Qiao, Guo; Qimin, Cao; Qitao, Li

2012-12-01

AdaBoost is an efficacious classification algorithm especially in text categorization (TC) tasks. The methodology of setting up a classifier committee and voting on the documents for classification can achieve high categorization precision. However, traditional Vector Space Model can easily lead to the curse of dimensionality and feature sparsity problems; so it affects classification performance seriously. This article proposed a novel classification algorithm called LDABoost based on boosting ideology which uses Latent Dirichlet Allocation (LDA) to modeling the feature space. Instead of using words or phrase, LDABoost use latent topics as the features. In this way, the feature dimension is significantly reduced. Improved Naïve Bayes (NB) is designed as the weaker classifier which keeps the efficiency advantage of classic NB algorithm and has higher precision. Moreover, a two-stage iterative weighted method called Cute Integration in this article is proposed for improving the accuracy by integrating weak classifiers into strong classifier in a more rational way. Mutual Information is used as metrics of weights allocation. The voting information and the categorization decision made by basis classifiers are fully utilized for generating the strong classifier. Experimental results reveals LDABoost making categorization in a low-dimensional space, it has higher accuracy than traditional AdaBoost algorithms and many other classic classification algorithms. Moreover, its runtime consumption is lower than different versions of AdaBoost, TC algorithms based on support vector machine and Neural Networks.

Probability Density Functions for the CALIPSO Lidar Version 4 Cloud-Aerosol Discrimination (CAD) Algorithm

NASA Astrophysics Data System (ADS)

Liu, Z.; Kar, J.; Zeng, S.; Tackett, J. L.; Vaughan, M.; Trepte, C. R.; Omar, A. H.; Hu, Y.; Winker, D. M.

2017-12-01

In the CALIPSO retrieval algorithm, detection layers in the lidar measurements is followed by their classification as a "cloud" or "aerosol" using 5-dimensional probability density functions (PDFs). The five dimensions are the mean attenuated backscatter at 532 nm, the layer integrated total attenuated color ratio, the mid-layer altitude, integrated volume depolarization ratio and latitude. The new version 4 (V4) level 2 (L2) data products, released in November 2016, are the first major revision to the L2 product suite since May 2010. Significant calibration changes in the V4 level 1 data necessitated substantial revisions to the V4 L2 CAD algorithm. Accordingly, a new set of PDFs was generated to derive the V4 L2 data products. The V4 CAD algorithm is now applied to layers detected in the stratosphere, where volcanic layers and occasional cloud and smoke layers are observed. Previously, these layers were designated as `stratospheric', and not further classified. The V4 CAD algorithm is also applied to all layers detected at single shot (333 m) resolution. In prior data releases, single shot detections were uniformly classified as clouds. The CAD PDFs used in the earlier releases were generated using a full year (2008) of CALIPSO measurements. Because the CAD algorithm was not applied to stratospheric features, the properties of these layers were not incorporated into the PDFs. When building the V4 PDFs, the 2008 data were augmented with additional data from June 2011, and all stratospheric features were included. The Nabro and Puyehue-Cordon volcanos erupted in June 2011, and volcanic aerosol layers were observed in the upper troposphere and lower stratosphere in both the northern and southern hemispheres. The June 2011 data thus provides the stratospheric aerosol properties needed for comprehensive PDF generation. In contrast to earlier versions of the PDFs, which were generated based solely on observed distributions, construction of the V4 PDFs considered the typical optical and physical properties of feature subtypes, and thus provide a more comprehensive physical basis for discrimination. As a result of the changes made, the V4 CAD provides better performance and more reliable confidence levels. We describe the generation of V4 PDFs and present characterization and performance of the new CAD algorithm.

Filtering high resolution hyperspectral imagery and analyzing it for quantification of water quality parameters and aquatic vegetation

NASA Astrophysics Data System (ADS)

Pande-Chhetri, Roshan

High resolution hyperspectral imagery (airborne or ground-based) is gaining momentum as a useful analytical tool in various fields including agriculture and aquatic systems. These images are often contaminated with stripes and noise resulting in lower signal-to-noise ratio, especially in aquatic regions where signal is naturally low. This research investigates effective methods for filtering high spatial resolution hyperspectral imagery and use of the imagery in water quality parameter estimation and aquatic vegetation classification. The striping pattern of the hyperspectral imagery is non-parametric and difficult to filter. In this research, a de-striping algorithm based on wavelet analysis and adaptive Fourier domain normalization was examined. The result of this algorithm was found superior to other available algorithms and yielded highest Peak Signal to Noise Ratio improvement. The algorithm was implemented on individual image bands and on selected bands of the Maximum Noise Fraction (MNF) transformed images. The results showed that image filtering in the MNF domain was efficient and produced best results. The study investigated methods of analyzing hyperspectral imagery to estimate water quality parameters and to map aquatic vegetation in case-2 waters. Ground-based hyperspectral imagery was analyzed to determine chlorophyll-a (Chl-a) concentrations in aquaculture ponds. Two-band and three-band indices were implemented and the effect of using submerged reflectance targets was evaluated. Laboratory measured values were found to be in strong correlation with two-band and three-band spectral indices computed from the hyperspectral image. Coefficients of determination (R2) values were found to be 0.833 and 0.862 without submerged targets and stronger values of 0.975 and 0.982 were obtained using submerged targets. Airborne hyperspectral images were used to detect and classify aquatic vegetation in a black river estuarine system. Image normalization for water surface reflectance and water depths was conducted and non-parametric classifiers such as ANN, SVM and SAM were tested and compared. Quality assessment indicated better classification and detection when non-parametric classifiers were applied to normalized or depth invariant transform images. Best classification accuracy of 73% was achieved when ANN is applied on normalized image and best detection accuracy of around 92% was obtained when SVM or SAM was applied on depth invariant images.

A fast automatic recognition and location algorithm for fetal genital organs in ultrasound images.

PubMed

Tang, Sheng; Chen, Si-ping

2009-09-01

Severe sex ratio imbalance at birth is now becoming an important issue in several Asian countries. Its leading immediate cause is prenatal sex-selective abortion following illegal sex identification by ultrasound scanning. In this paper, a fast automatic recognition and location algorithm for fetal genital organs is proposed as an effective method to help prevent ultrasound technicians from unethically and illegally identifying the sex of the fetus. This automatic recognition algorithm can be divided into two stages. In the 'rough' stage, a few pixels in the image, which are likely to represent the genital organs, are automatically chosen as points of interest (POIs) according to certain salient characteristics of fetal genital organs. In the 'fine' stage, a specifically supervised learning framework, which fuses an effective feature data preprocessing mechanism into the multiple classifier architecture, is applied to every POI. The basic classifiers in the framework are selected from three widely used classifiers: radial basis function network, backpropagation network, and support vector machine. The classification results of all the POIs are then synthesized to determine whether the fetal genital organ is present in the image, and to locate the genital organ within the positive image. Experiments were designed and carried out based on an image dataset comprising 658 positive images (images with fetal genital organs) and 500 negative images (images without fetal genital organs). The experimental results showed true positive (TP) and true negative (TN) results from 80.5% (265 from 329) and 83.0% (415 from 500) of samples, respectively. The average computation time was 453 ms per image.

A unified classifier for robust face recognition based on combining multiple subspace algorithms

NASA Astrophysics Data System (ADS)

Ijaz Bajwa, Usama; Ahmad Taj, Imtiaz; Waqas Anwar, Muhammad

2012-10-01

Face recognition being the fastest growing biometric technology has expanded manifold in the last few years. Various new algorithms and commercial systems have been proposed and developed. However, none of the proposed or developed algorithm is a complete solution because it may work very well on one set of images with say illumination changes but may not work properly on another set of image variations like expression variations. This study is motivated by the fact that any single classifier cannot claim to show generally better performance against all facial image variations. To overcome this shortcoming and achieve generality, combining several classifiers using various strategies has been studied extensively also incorporating the question of suitability of any classifier for this task. The study is based on the outcome of a comprehensive comparative analysis conducted on a combination of six subspace extraction algorithms and four distance metrics on three facial databases. The analysis leads to the selection of the most suitable classifiers which performs better on one task or the other. These classifiers are then combined together onto an ensemble classifier by two different strategies of weighted sum and re-ranking. The results of the ensemble classifier show that these strategies can be effectively used to construct a single classifier that can successfully handle varying facial image conditions of illumination, aging and facial expressions.

Learning-based 3T brain MRI segmentation with guidance from 7T MRI labeling.

PubMed

Deng, Minghui; Yu, Renping; Wang, Li; Shi, Feng; Yap, Pew-Thian; Shen, Dinggang

2016-12-01

Segmentation of brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is crucial for brain structural measurement and disease diagnosis. Learning-based segmentation methods depend largely on the availability of good training ground truth. However, the commonly used 3T MR images are of insufficient image quality and often exhibit poor intensity contrast between WM, GM, and CSF. Therefore, they are not ideal for providing good ground truth label data for training learning-based methods. Recent advances in ultrahigh field 7T imaging make it possible to acquire images with excellent intensity contrast and signal-to-noise ratio. In this paper, the authors propose an algorithm based on random forest for segmenting 3T MR images by training a series of classifiers based on reliable labels obtained semiautomatically from 7T MR images. The proposed algorithm iteratively refines the probability maps of WM, GM, and CSF via a cascade of random forest classifiers for improved tissue segmentation. The proposed method was validated on two datasets, i.e., 10 subjects collected at their institution and 797 3T MR images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 94.52% ± 0.9%, 89.49% ± 1.83%, and 79.97% ± 4.32% for WM, GM, and CSF, respectively, which are significantly better than the state-of-the-art methods (p-values < 0.021). For the ADNI dataset, the group difference comparisons indicate that the proposed algorithm outperforms state-of-the-art segmentation methods. The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation. © 2016 American Association of Physicists in Medicine.

Learning-based 3T brain MRI segmentation with guidance from 7T MRI labeling.

PubMed

Deng, Minghui; Yu, Renping; Wang, Li; Shi, Feng; Yap, Pew-Thian; Shen, Dinggang

2016-12-01

Segmentation of brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is crucial for brain structural measurement and disease diagnosis. Learning-based segmentation methods depend largely on the availability of good training ground truth. However, the commonly used 3T MR images are of insufficient image quality and often exhibit poor intensity contrast between WM, GM, and CSF. Therefore, they are not ideal for providing good ground truth label data for training learning-based methods. Recent advances in ultrahigh field 7T imaging make it possible to acquire images with excellent intensity contrast and signal-to-noise ratio. In this paper, the authors propose an algorithm based on random forest for segmenting 3T MR images by training a series of classifiers based on reliable labels obtained semiautomatically from 7T MR images. The proposed algorithm iteratively refines the probability maps of WM, GM, and CSF via a cascade of random forest classifiers for improved tissue segmentation. The proposed method was validated on two datasets, i.e., 10 subjects collected at their institution and 797 3T MR images from the Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset. Specifically, for the mean Dice ratio of all 10 subjects, the proposed method achieved 94.52% ± 0.9%, 89.49% ± 1.83%, and 79.97% ± 4.32% for WM, GM, and CSF, respectively, which are significantly better than the state-of-the-art methods (p-values < 0.021). For the ADNI dataset, the group difference comparisons indicate that the proposed algorithm outperforms state-of-the-art segmentation methods. The authors have developed and validated a novel fully automated method for 3T brain MR image segmentation.

Walking Objectively Measured: Classifying Accelerometer Data with GPS and Travel Diaries

PubMed Central

Kang, Bumjoon; Moudon, Anne V.; Hurvitz, Philip M.; Reichley, Lucas; Saelens, Brian E.

2013-01-01

Purpose This study developed and tested an algorithm to classify accelerometer data as walking or non-walking using either GPS or travel diary data within a large sample of adults under free-living conditions. Methods Participants wore an accelerometer and a GPS unit, and concurrently completed a travel diary for 7 consecutive days. Physical activity (PA) bouts were identified using accelerometry count sequences. PA bouts were then classified as walking or non-walking based on a decision-tree algorithm consisting of 7 classification scenarios. Algorithm reliability was examined relative to two independent analysts’ classification of a 100-bout verification sample. The algorithm was then applied to the entire set of PA bouts. Results The 706 participants’ (mean age 51 years, 62% female, 80% non-Hispanic white, 70% college graduate or higher) yielded 4,702 person-days of data and had a total of 13,971 PA bouts. The algorithm showed a mean agreement of 95% with the independent analysts. It classified physical activity into 8,170 (58.5 %) walking bouts and 5,337 (38.2%) non-walking bouts; 464 (3.3%) bouts were not classified for lack of GPS and diary data. Nearly 70% of the walking bouts and 68% of the non-walking bouts were classified using only the objective accelerometer and GPS data. Travel diary data helped classify 30% of all bouts with no GPS data. The mean duration of PA bouts classified as walking was 15.2 min (SD=12.9). On average, participants had 1.7 walking bouts and 25.4 total walking minutes per day. Conclusions GPS and travel diary information can be helpful in classifying most accelerometer-derived PA bouts into walking or non-walking behavior. PMID:23439414

The effect of lossy image compression on image classification

NASA Technical Reports Server (NTRS)

Paola, Justin D.; Schowengerdt, Robert A.

1995-01-01

We have classified four different images, under various levels of JPEG compression, using the following classification algorithms: minimum-distance, maximum-likelihood, and neural network. The training site accuracy and percent difference from the original classification were tabulated for each image compression level, with maximum-likelihood showing the poorest results. In general, as compression ratio increased, the classification retained its overall appearance, but much of the pixel-to-pixel detail was eliminated. We also examined the effect of compression on spatial pattern detection using a neural network.

Link Scheduling Algorithm with Interference Prediction for Multiple Mobile WBANs

PubMed Central

Le, Thien T. T.

2017-01-01

As wireless body area networks (WBANs) become a key element in electronic healthcare (e-healthcare) systems, the coexistence of multiple mobile WBANs is becoming an issue. The network performance is negatively affected by the unpredictable movement of the human body. In such an environment, inter-WBAN interference can be caused by the overlapping transmission range of nearby WBANs. We propose a link scheduling algorithm with interference prediction (LSIP) for multiple mobile WBANs, which allows multiple mobile WBANs to transmit at the same time without causing inter-WBAN interference. In the LSIP, a superframe includes the contention access phase using carrier sense multiple access with collision avoidance (CSMA/CA) and the scheduled phase using time division multiple access (TDMA) for non-interfering nodes and interfering nodes, respectively. For interference prediction, we define a parameter called interference duration as the duration during which disparate WBANs interfere with each other. The Bayesian model is used to estimate and classify the interference using a signal to interference plus noise ratio (SINR) and the number of neighboring WBANs. The simulation results show that the proposed LSIP algorithm improves the packet delivery ratio and throughput significantly with acceptable delay. PMID:28956827

Optical biopsy using fluorescence spectroscopy for prostate cancer diagnosis

NASA Astrophysics Data System (ADS)

Wu, Binlin; Gao, Xin; Smith, Jason; Bailin, Jacob

2017-02-01

Native fluorescence spectra are acquired from fresh normal and cancerous human prostate tissues. The fluorescence data are analyzed using a multivariate analysis algorithm such as non-negative matrix factorization. The nonnegative spectral components are retrieved and attributed to the native fluorophores such as collagen, reduced nicotinamide adenine dinucleotide (NADH), and flavin adenine dinucleotide (FAD) in tissue. The retrieved weights of the components, e.g. NADH and FAD are used to estimate the relative concentrations of the native fluorophores and the redox ratio. A machine learning algorithm such as support vector machine (SVM) is used for classification to distinguish normal and cancerous tissue samples based on either the relative concentrations of NADH and FAD or the redox ratio alone. The classification performance is shown based on statistical measures such as sensitivity, specificity, and accuracy, along with the area under receiver operating characteristic (ROC) curve. A cross validation method such as leave-one-out is used to evaluate the predictive performance of the SVM classifier to avoid bias due to overfitting.

AUTOCLASSIFICATION OF THE VARIABLE 3XMM SOURCES USING THE RANDOM FOREST MACHINE LEARNING ALGORITHM

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

Farrell, Sean A.; Murphy, Tara; Lo, Kitty K., E-mail: s.farrell@physics.usyd.edu.au

In the current era of large surveys and massive data sets, autoclassification of astrophysical sources using intelligent algorithms is becoming increasingly important. In this paper we present the catalog of variable sources in the Third XMM-Newton Serendipitous Source catalog (3XMM) autoclassified using the Random Forest machine learning algorithm. We used a sample of manually classified variable sources from the second data release of the XMM-Newton catalogs (2XMMi-DR2) to train the classifier, obtaining an accuracy of ∼92%. We also evaluated the effectiveness of identifying spurious detections using a sample of spurious sources, achieving an accuracy of ∼95%. Manual investigation of amore » random sample of classified sources confirmed these accuracy levels and showed that the Random Forest machine learning algorithm is highly effective at automatically classifying 3XMM sources. Here we present the catalog of classified 3XMM variable sources. We also present three previously unidentified unusual sources that were flagged as outlier sources by the algorithm: a new candidate supergiant fast X-ray transient, a 400 s X-ray pulsar, and an eclipsing 5 hr binary system coincident with a known Cepheid.« less

A Novel Optical/digital Processing System for Pattern Recognition

NASA Technical Reports Server (NTRS)

Boone, Bradley G.; Shukla, Oodaye B.

1993-01-01

This paper describes two processing algorithms that can be implemented optically: the Radon transform and angular correlation. These two algorithms can be combined in one optical processor to extract all the basic geometric and amplitude features from objects embedded in video imagery. We show that the internal amplitude structure of objects is recovered by the Radon transform, which is a well-known result, but, in addition, we show simulation results that calculate angular correlation, a simple but unique algorithm that extracts object boundaries from suitably threshold images from which length, width, area, aspect ratio, and orientation can be derived. In addition to circumventing scale and rotation distortions, these simulations indicate that the features derived from the angular correlation algorithm are relatively insensitive to tracking shifts and image noise. Some optical architecture concepts, including one based on micro-optical lenslet arrays, have been developed to implement these algorithms. Simulation test and evaluation using simple synthetic object data will be described, including results of a study that uses object boundaries (derivable from angular correlation) to classify simple objects using a neural network.

Hip and Wrist Accelerometer Algorithms for Free-Living Behavior Classification.

PubMed

Ellis, Katherine; Kerr, Jacqueline; Godbole, Suneeta; Staudenmayer, John; Lanckriet, Gert

2016-05-01

Accelerometers are a valuable tool for objective measurement of physical activity (PA). Wrist-worn devices may improve compliance over standard hip placement, but more research is needed to evaluate their validity for measuring PA in free-living settings. Traditional cut-point methods for accelerometers can be inaccurate and need testing in free living with wrist-worn devices. In this study, we developed and tested the performance of machine learning (ML) algorithms for classifying PA types from both hip and wrist accelerometer data. Forty overweight or obese women (mean age = 55.2 ± 15.3 yr; BMI = 32.0 ± 3.7) wore two ActiGraph GT3X+ accelerometers (right hip, nondominant wrist; ActiGraph, Pensacola, FL) for seven free-living days. Wearable cameras captured ground truth activity labels. A classifier consisting of a random forest and hidden Markov model classified the accelerometer data into four activities (sitting, standing, walking/running, and riding in a vehicle). Free-living wrist and hip ML classifiers were compared with each other, with traditional accelerometer cut points, and with an algorithm developed in a laboratory setting. The ML classifier obtained average values of 89.4% and 84.6% balanced accuracy over the four activities using the hip and wrist accelerometer, respectively. In our data set with average values of 28.4 min of walking or running per day, the ML classifier predicted average values of 28.5 and 24.5 min of walking or running using the hip and wrist accelerometer, respectively. Intensity-based cut points and the laboratory algorithm significantly underestimated walking minutes. Our results demonstrate the superior performance of our PA-type classification algorithm, particularly in comparison with traditional cut points. Although the hip algorithm performed better, additional compliance achieved with wrist devices might justify using a slightly lower performing algorithm.

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

PubMed

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

2009-01-01

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

[Hyperspectral remote sensing image classification based on SVM optimized by clonal selection].

PubMed

Liu, Qing-Jie; Jing, Lin-Hai; Wang, Meng-Fei; Lin, Qi-Zhong

2013-03-01

Model selection for support vector machine (SVM) involving kernel and the margin parameter values selection is usually time-consuming, impacts training efficiency of SVM model and final classification accuracies of SVM hyperspectral remote sensing image classifier greatly. Firstly, based on combinatorial optimization theory and cross-validation method, artificial immune clonal selection algorithm is introduced to the optimal selection of SVM (CSSVM) kernel parameter a and margin parameter C to improve the training efficiency of SVM model. Then an experiment of classifying AVIRIS in India Pine site of USA was performed for testing the novel CSSVM, as well as a traditional SVM classifier with general Grid Searching cross-validation method (GSSVM) for comparison. And then, evaluation indexes including SVM model training time, classification overall accuracy (OA) and Kappa index of both CSSVM and GSSVM were all analyzed quantitatively. It is demonstrated that OA of CSSVM on test samples and whole image are 85.1% and 81.58, the differences from that of GSSVM are both within 0.08% respectively; And Kappa indexes reach 0.8213 and 0.7728, the differences from that of GSSVM are both within 0.001; While the ratio of model training time of CSSVM and GSSVM is between 1/6 and 1/10. Therefore, CSSVM is fast and accurate algorithm for hyperspectral image classification and is superior to GSSVM.

Development of algorithms for detecting citrus canker based on hyperspectral reflectance imaging.

PubMed

Li, Jiangbo; Rao, Xiuqin; Ying, Yibin

2012-01-15

Automated discrimination of fruits with canker from other fruit with normal surface and different type of peel defects has become a helpful task to enhance the competitiveness and profitability of the citrus industry. Over the last several years, hyperspectral imaging technology has received increasing attention in the agricultural products inspection field. This paper studied the feasibility of classification of citrus canker from other peel conditions including normal surface and nine peel defects by hyperspectal imaging. A combination algorithm based on principal component analysis and the two-band ratio (Q(687/630)) method was proposed. Since fewer wavelengths were desired in order to develop a rapid multispectral imaging system, the canker classification performance of the two-band ratio (Q(687/630)) method alone was also evaluated. The proposed combination approach and two-band ratio method alone resulted in overall classification accuracy for training set samples and test set samples of 99.5%, 84.5% and 98.2%, 82.9%, respectively. The proposed combination approach was more efficient for classifying canker against various conditions under reflectance hyperspectral imagery. However, the two-band ratio (Q(687/630)) method alone also demonstrated effectiveness in discriminating citrus canker from normal fruit and other peel diseases except for copper burn and anthracnose. Copyright © 2011 Society of Chemical Industry.

Applying a machine learning model using a locally preserving projection based feature regeneration algorithm to predict breast cancer risk

NASA Astrophysics Data System (ADS)

Heidari, Morteza; Zargari Khuzani, Abolfazl; Danala, Gopichandh; Mirniaharikandehei, Seyedehnafiseh; Qian, Wei; Zheng, Bin

2018-03-01

Both conventional and deep machine learning has been used to develop decision-support tools applied in medical imaging informatics. In order to take advantages of both conventional and deep learning approach, this study aims to investigate feasibility of applying a locally preserving projection (LPP) based feature regeneration algorithm to build a new machine learning classifier model to predict short-term breast cancer risk. First, a computer-aided image processing scheme was used to segment and quantify breast fibro-glandular tissue volume. Next, initially computed 44 image features related to the bilateral mammographic tissue density asymmetry were extracted. Then, an LLP-based feature combination method was applied to regenerate a new operational feature vector using a maximal variance approach. Last, a k-nearest neighborhood (KNN) algorithm based machine learning classifier using the LPP-generated new feature vectors was developed to predict breast cancer risk. A testing dataset involving negative mammograms acquired from 500 women was used. Among them, 250 were positive and 250 remained negative in the next subsequent mammography screening. Applying to this dataset, LLP-generated feature vector reduced the number of features from 44 to 4. Using a leave-onecase-out validation method, area under ROC curve produced by the KNN classifier significantly increased from 0.62 to 0.68 (p < 0.05) and odds ratio was 4.60 with a 95% confidence interval of [3.16, 6.70]. Study demonstrated that this new LPP-based feature regeneration approach enabled to produce an optimal feature vector and yield improved performance in assisting to predict risk of women having breast cancer detected in the next subsequent mammography screening.

An energy ratio feature extraction method for optical fiber vibration signal

NASA Astrophysics Data System (ADS)

Sheng, Zhiyong; Zhang, Xinyan; Wang, Yanping; Hou, Weiming; Yang, Dan

2018-03-01

The intrusion events in the optical fiber pre-warning system (OFPS) are divided into two types which are harmful intrusion event and harmless interference event. At present, the signal feature extraction methods of these two types of events are usually designed from the view of the time domain. However, the differences of time-domain characteristics for different harmful intrusion events are not obvious, which cannot reflect the diversity of them in detail. We find that the spectrum distribution of different intrusion signals has obvious differences. For this reason, the intrusion signal is transformed into the frequency domain. In this paper, an energy ratio feature extraction method of harmful intrusion event is drawn on. Firstly, the intrusion signals are pre-processed and the power spectral density (PSD) is calculated. Then, the energy ratio of different frequency bands is calculated, and the corresponding feature vector of each type of intrusion event is further formed. The linear discriminant analysis (LDA) classifier is used to identify the harmful intrusion events in the paper. Experimental results show that the algorithm improves the recognition rate of the intrusion signal, and further verifies the feasibility and validity of the algorithm.

A Dual-Wavelength Radar Technique to Detect Hydrometeor Phases

NASA Technical Reports Server (NTRS)

Liao, Liang; Meneghini, Robert

2016-01-01

This study is aimed at investigating the feasibility of a Ku- and Ka-band space/air-borne dual wavelength radar algorithm to discriminate various phase states of precipitating hydrometeors. A phase-state classification algorithm has been developed from the radar measurements of snow, mixed-phase and rain obtained from stratiform storms. The algorithm, presented in the form of the look-up table that links the Ku-band radar reflectivities and dual-frequency ratio (DFR) to the phase states of hydrometeors, is checked by applying it to the measurements of the Jet Propulsion Laboratory, California Institute of Technology, Airborne Precipitation Radar Second Generation (APR-2). In creating the statistically-based phase look-up table, the attenuation corrected (or true) radar reflectivity factors are employed, leading to better accuracy in determining the hydrometeor phase. In practice, however, the true radar reflectivities are not always available before the phase states of the hydrometeors are determined. Therefore, it is desirable to make use of the measured radar reflectivities in classifying the phase states. To do this, a phase-identification procedure is proposed that uses only measured radar reflectivities. The procedure is then tested using APR-2 airborne radar data. Analysis of the classification results in stratiform rain indicates that the regions of snow, mixed-phase and rain derived from the phase-identification algorithm coincide reasonably well with those determined from the measured radar reflectivities and linear depolarization ratio (LDR).

Neural network-based brain tissue segmentation in MR images using extracted features from intraframe coding in H.264

NASA Astrophysics Data System (ADS)

Jafari, Mehdi; Kasaei, Shohreh

2012-01-01

Automatic brain tissue segmentation is a crucial task in diagnosis and treatment of medical images. This paper presents a new algorithm to segment different brain tissues, such as white matter (WM), gray matter (GM), cerebral spinal fluid (CSF), background (BKG), and tumor tissues. The proposed technique uses the modified intraframe coding yielded from H.264/(AVC), for feature extraction. Extracted features are then imposed to an artificial back propagation neural network (BPN) classifier to assign each block to its appropriate class. Since the newest coding standard, H.264/AVC, has the highest compression ratio, it decreases the dimension of extracted features and thus yields to a more accurate classifier with low computational complexity. The performance of the BPN classifier is evaluated using the classification accuracy and computational complexity terms. The results show that the proposed technique is more robust and effective with low computational complexity compared to other recent works.

Neural network-based brain tissue segmentation in MR images using extracted features from intraframe coding in H.264

NASA Astrophysics Data System (ADS)

Jafari, Mehdi; Kasaei, Shohreh

2011-12-01

Automatic brain tissue segmentation is a crucial task in diagnosis and treatment of medical images. This paper presents a new algorithm to segment different brain tissues, such as white matter (WM), gray matter (GM), cerebral spinal fluid (CSF), background (BKG), and tumor tissues. The proposed technique uses the modified intraframe coding yielded from H.264/(AVC), for feature extraction. Extracted features are then imposed to an artificial back propagation neural network (BPN) classifier to assign each block to its appropriate class. Since the newest coding standard, H.264/AVC, has the highest compression ratio, it decreases the dimension of extracted features and thus yields to a more accurate classifier with low computational complexity. The performance of the BPN classifier is evaluated using the classification accuracy and computational complexity terms. The results show that the proposed technique is more robust and effective with low computational complexity compared to other recent works.

Efficient Fingercode Classification

NASA Astrophysics Data System (ADS)

Sun, Hong-Wei; Law, Kwok-Yan; Gollmann, Dieter; Chung, Siu-Leung; Li, Jian-Bin; Sun, Jia-Guang

In this paper, we present an efficient fingerprint classification algorithm which is an essential component in many critical security application systems e. g. systems in the e-government and e-finance domains. Fingerprint identification is one of the most important security requirements in homeland security systems such as personnel screening and anti-money laundering. The problem of fingerprint identification involves searching (matching) the fingerprint of a person against each of the fingerprints of all registered persons. To enhance performance and reliability, a common approach is to reduce the search space by firstly classifying the fingerprints and then performing the search in the respective class. Jain et al. proposed a fingerprint classification algorithm based on a two-stage classifier, which uses a K-nearest neighbor classifier in its first stage. The fingerprint classification algorithm is based on the fingercode representation which is an encoding of fingerprints that has been demonstrated to be an effective fingerprint biometric scheme because of its ability to capture both local and global details in a fingerprint image. We enhance this approach by improving the efficiency of the K-nearest neighbor classifier for fingercode-based fingerprint classification. Our research firstly investigates the various fast search algorithms in vector quantization (VQ) and the potential application in fingerprint classification, and then proposes two efficient algorithms based on the pyramid-based search algorithms in VQ. Experimental results on DB1 of FVC 2004 demonstrate that our algorithms can outperform the full search algorithm and the original pyramid-based search algorithms in terms of computational efficiency without sacrificing accuracy.

Chemometric Analysis of Gas Chromatography – Mass Spectrometry Data using Fast Retention Time Alignment via a Total Ion Current Shift Function

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

Nadeau, Jeremy S.; Wright, Bob W.; Synovec, Robert E.

2010-04-15

A critical comparison of methods for correcting severely retention time shifted gas chromatography-mass spectrometry (GC-MS) data is presented. The method reported herein is an adaptation to the Piecewise Alignment Algorithm to quickly align severely shifted one-dimensional (1D) total ion current (TIC) data, then applying these shifts to broadly align all mass channels throughout the separation, referred to as a TIC shift function (SF). The maximum shift varied from (-) 5 s in the beginning of the chromatographic separation to (+) 20 s toward the end of the separation, equivalent to a maximum shift of over 5 peak widths. Implementing themore » TIC shift function (TIC SF) prior to Fisher Ratio (F-Ratio) feature selection and then principal component analysis (PCA) was found to be a viable approach to classify complex chromatograms, that in this study were obtained from GC-MS separations of three gasoline samples serving as complex test mixtures, referred to as types C, M and S. The reported alignment algorithm via the TIC SF approach corrects for large dynamic shifting in the data as well as subtle peak-to-peak shifts. The benefits of the overall TIC SF alignment and feature selection approach were quantified using the degree-of-class separation (DCS) metric of the PCA scores plots using the type C and M samples, since they were the most similar, and thus the most challenging samples to properly classify. The DCS values showed an increase from an initial value of essentially zero for the unaligned GC-TIC data to a value of 7.9 following alignment; however, the DCS was unchanged by feature selection using F-Ratios for the GC-TIC data. The full mass spectral data provided an increase to a final DCS of 13.7 after alignment and two-dimensional (2D) F-Ratio feature selection.« less

Recognition of pornographic web pages by classifying texts and images.

PubMed

Hu, Weiming; Wu, Ou; Chen, Zhouyao; Fu, Zhouyu; Maybank, Steve

2007-06-01

With the rapid development of the World Wide Web, people benefit more and more from the sharing of information. However, Web pages with obscene, harmful, or illegal content can be easily accessed. It is important to recognize such unsuitable, offensive, or pornographic Web pages. In this paper, a novel framework for recognizing pornographic Web pages is described. A C4.5 decision tree is used to divide Web pages, according to content representations, into continuous text pages, discrete text pages, and image pages. These three categories of Web pages are handled, respectively, by a continuous text classifier, a discrete text classifier, and an algorithm that fuses the results from the image classifier and the discrete text classifier. In the continuous text classifier, statistical and semantic features are used to recognize pornographic texts. In the discrete text classifier, the naive Bayes rule is used to calculate the probability that a discrete text is pornographic. In the image classifier, the object's contour-based features are extracted to recognize pornographic images. In the text and image fusion algorithm, the Bayes theory is used to combine the recognition results from images and texts. Experimental results demonstrate that the continuous text classifier outperforms the traditional keyword-statistics-based classifier, the contour-based image classifier outperforms the traditional skin-region-based image classifier, the results obtained by our fusion algorithm outperform those by either of the individual classifiers, and our framework can be adapted to different categories of Web pages.

A Random Forest-based ensemble method for activity recognition.

PubMed

Feng, Zengtao; Mo, Lingfei; Li, Meng

2015-01-01

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

An assessment of support vector machines for land cover classification

USGS Publications Warehouse

Huang, C.; Davis, L.S.; Townshend, J.R.G.

2002-01-01

The support vector machine (SVM) is a group of theoretically superior machine learning algorithms. It was found competitive with the best available machine learning algorithms in classifying high-dimensional data sets. This paper gives an introduction to the theoretical development of the SVM and an experimental evaluation of its accuracy, stability and training speed in deriving land cover classifications from satellite images. The SVM was compared to three other popular classifiers, including the maximum likelihood classifier (MLC), neural network classifiers (NNC) and decision tree classifiers (DTC). The impacts of kernel configuration on the performance of the SVM and of the selection of training data and input variables on the four classifiers were also evaluated in this experiment.

Textual and visual content-based anti-phishing: a Bayesian approach.

PubMed

Zhang, Haijun; Liu, Gang; Chow, Tommy W S; Liu, Wenyin

2011-10-01

A novel framework using a Bayesian approach for content-based phishing web page detection is presented. Our model takes into account textual and visual contents to measure the similarity between the protected web page and suspicious web pages. A text classifier, an image classifier, and an algorithm fusing the results from classifiers are introduced. An outstanding feature of this paper is the exploration of a Bayesian model to estimate the matching threshold. This is required in the classifier for determining the class of the web page and identifying whether the web page is phishing or not. In the text classifier, the naive Bayes rule is used to calculate the probability that a web page is phishing. In the image classifier, the earth mover's distance is employed to measure the visual similarity, and our Bayesian model is designed to determine the threshold. In the data fusion algorithm, the Bayes theory is used to synthesize the classification results from textual and visual content. The effectiveness of our proposed approach was examined in a large-scale dataset collected from real phishing cases. Experimental results demonstrated that the text classifier and the image classifier we designed deliver promising results, the fusion algorithm outperforms either of the individual classifiers, and our model can be adapted to different phishing cases. © 2011 IEEE

Improving Classification of Cancer and Mining Biomarkers from Gene Expression Profiles Using Hybrid Optimization Algorithms and Fuzzy Support Vector Machine

PubMed Central

Moteghaed, Niloofar Yousefi; Maghooli, Keivan; Garshasbi, Masoud

2018-01-01

Background: Gene expression data are characteristically high dimensional with a small sample size in contrast to the feature size and variability inherent in biological processes that contribute to difficulties in analysis. Selection of highly discriminative features decreases the computational cost and complexity of the classifier and improves its reliability for prediction of a new class of samples. Methods: The present study used hybrid particle swarm optimization and genetic algorithms for gene selection and a fuzzy support vector machine (SVM) as the classifier. Fuzzy logic is used to infer the importance of each sample in the training phase and decrease the outlier sensitivity of the system to increase the ability to generalize the classifier. A decision-tree algorithm was applied to the most frequent genes to develop a set of rules for each type of cancer. This improved the abilities of the algorithm by finding the best parameters for the classifier during the training phase without the need for trial-and-error by the user. The proposed approach was tested on four benchmark gene expression profiles. Results: Good results have been demonstrated for the proposed algorithm. The classification accuracy for leukemia data is 100%, for colon cancer is 96.67% and for breast cancer is 98%. The results show that the best kernel used in training the SVM classifier is the radial basis function. Conclusions: The experimental results show that the proposed algorithm can decrease the dimensionality of the dataset, determine the most informative gene subset, and improve classification accuracy using the optimal parameters of the classifier with no user interface. PMID:29535919

A Novel Machine Vision System for the Inspection of Micro-Spray Nozzle

PubMed Central

Huang, Kuo-Yi; Ye, Yu-Ting

2015-01-01

In this study, we present an application of neural network and image processing techniques for detecting the defects of an internal micro-spray nozzle. The defect regions were segmented by Canny edge detection, a randomized algorithm for detecting circles and a circle inspection (CI) algorithm. The gray level co-occurrence matrix (GLCM) was further used to evaluate the texture features of the segmented region. These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures. A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles. The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%. PMID:26131678

A Novel Machine Vision System for the Inspection of Micro-Spray Nozzle.

PubMed

Huang, Kuo-Yi; Ye, Yu-Ting

2015-06-29

In this study, we present an application of neural network and image processing techniques for detecting the defects of an internal micro-spray nozzle. The defect regions were segmented by Canny edge detection, a randomized algorithm for detecting circles and a circle inspection (CI) algorithm. The gray level co-occurrence matrix (GLCM) was further used to evaluate the texture features of the segmented region. These texture features (contrast, entropy, energy), color features (mean and variance of gray level) and geometric features (distance variance, mean diameter and diameter ratio) were used in the classification procedures. A back-propagation neural network classifier was employed to detect the defects of micro-spray nozzles. The methodology presented herein effectively works for detecting micro-spray nozzle defects to an accuracy of 90.71%.

Neural system for heartbeats recognition using genetically integrated ensemble of classifiers.

PubMed

Osowski, Stanislaw; Siwek, Krzysztof; Siroic, Robert

2011-03-01

This paper presents the application of genetic algorithm for the integration of neural classifiers combined in the ensemble for the accurate recognition of heartbeat types on the basis of ECG registration. The idea presented in this paper is that using many classifiers arranged in the form of ensemble leads to the increased accuracy of the recognition. In such ensemble the important problem is the integration of all classifiers into one effective classification system. This paper proposes the use of genetic algorithm. It was shown that application of the genetic algorithm is very efficient and allows to reduce significantly the total error of heartbeat recognition. This was confirmed by the numerical experiments performed on the MIT BIH Arrhythmia Database. Copyright © 2011 Elsevier Ltd. All rights reserved.

Optimization of Support Vector Machine (SVM) for Object Classification

NASA Technical Reports Server (NTRS)

Scholten, Matthew; Dhingra, Neil; Lu, Thomas T.; Chao, Tien-Hsin

2012-01-01

The Support Vector Machine (SVM) is a powerful algorithm, useful in classifying data into species. The SVMs implemented in this research were used as classifiers for the final stage in a Multistage Automatic Target Recognition (ATR) system. A single kernel SVM known as SVMlight, and a modified version known as a SVM with K-Means Clustering were used. These SVM algorithms were tested as classifiers under varying conditions. Image noise levels varied, and the orientation of the targets changed. The classifiers were then optimized to demonstrate their maximum potential as classifiers. Results demonstrate the reliability of SVM as a method for classification. From trial to trial, SVM produces consistent results.

An algorithm of the wildfire classification by its acoustic emission spectrum using Wireless Sensor Networks

NASA Astrophysics Data System (ADS)

Khamukhin, A. A.; Demin, A. Y.; Sonkin, D. M.; Bertoldo, S.; Perona, G.; Kretova, V.

2017-01-01

Crown fires are extremely dangerous as the speed of their distribution is dozen times higher compared to surface fires. Therefore, it is important to classify the fire type as early as possible. A method for forest fires classification exploits their computed acoustic emission spectrum compared with a set of samples of the typical fire acoustic emission spectrum stored in the database. This method implies acquisition acoustic data using Wireless Sensors Networks (WSNs) and their analysis in a central processing and a control center. The paper deals with an algorithm which can be directly implemented on a sensor network node that will allow reducing considerably the network traffic and increasing its efficiency. It is hereby suggested to use the sum of the squares ratio, with regard to amplitudes of low and high frequencies of the wildfire acoustic emission spectrum, as the indicator of a forest fire type. It is shown that the value of the crown fires indicator is several times higher than that of the surface ones. This allows classifying the fire types (crown, surface) in a short time interval and transmitting a fire type indicator code alongside with an alarm signal through the network.

Supervised Machine Learning Algorithms Can Classify Open-Text Feedback of Doctor Performance With Human-Level Accuracy

PubMed Central

2017-01-01

Background Machine learning techniques may be an effective and efficient way to classify open-text reports on doctor’s activity for the purposes of quality assurance, safety, and continuing professional development. Objective The objective of the study was to evaluate the accuracy of machine learning algorithms trained to classify open-text reports of doctor performance and to assess the potential for classifications to identify significant differences in doctors’ professional performance in the United Kingdom. Methods We used 1636 open-text comments (34,283 words) relating to the performance of 548 doctors collected from a survey of clinicians’ colleagues using the General Medical Council Colleague Questionnaire (GMC-CQ). We coded 77.75% (1272/1636) of the comments into 5 global themes (innovation, interpersonal skills, popularity, professionalism, and respect) using a qualitative framework. We trained 8 machine learning algorithms to classify comments and assessed their performance using several training samples. We evaluated doctor performance using the GMC-CQ and compared scores between doctors with different classifications using t tests. Results Individual algorithm performance was high (range F score=.68 to .83). Interrater agreement between the algorithms and the human coder was highest for codes relating to “popular” (recall=.97), “innovator” (recall=.98), and “respected” (recall=.87) codes and was lower for the “interpersonal” (recall=.80) and “professional” (recall=.82) codes. A 10-fold cross-validation demonstrated similar performance in each analysis. When combined together into an ensemble of multiple algorithms, mean human-computer interrater agreement was .88. Comments that were classified as “respected,” “professional,” and “interpersonal” related to higher doctor scores on the GMC-CQ compared with comments that were not classified (P<.05). Scores did not vary between doctors who were rated as popular or innovative and those who were not rated at all (P>.05). Conclusions Machine learning algorithms can classify open-text feedback of doctor performance into multiple themes derived by human raters with high performance. Colleague open-text comments that signal respect, professionalism, and being interpersonal may be key indicators of doctor’s performance. PMID:28298265

Progressive Classification Using Support Vector Machines

NASA Technical Reports Server (NTRS)

Wagstaff, Kiri; Kocurek, Michael

2009-01-01

An algorithm for progressive classification of data, analogous to progressive rendering of images, makes it possible to compromise between speed and accuracy. This algorithm uses support vector machines (SVMs) to classify data. An SVM is a machine learning algorithm that builds a mathematical model of the desired classification concept by identifying the critical data points, called support vectors. Coarse approximations to the concept require only a few support vectors, while precise, highly accurate models require far more support vectors. Once the model has been constructed, the SVM can be applied to new observations. The cost of classifying a new observation is proportional to the number of support vectors in the model. When computational resources are limited, an SVM of the appropriate complexity can be produced. However, if the constraints are not known when the model is constructed, or if they can change over time, a method for adaptively responding to the current resource constraints is required. This capability is particularly relevant for spacecraft (or any other real-time systems) that perform onboard data analysis. The new algorithm enables the fast, interactive application of an SVM classifier to a new set of data. The classification process achieved by this algorithm is characterized as progressive because a coarse approximation to the true classification is generated rapidly and thereafter iteratively refined. The algorithm uses two SVMs: (1) a fast, approximate one and (2) slow, highly accurate one. New data are initially classified by the fast SVM, producing a baseline approximate classification. For each classified data point, the algorithm calculates a confidence index that indicates the likelihood that it was classified correctly in the first pass. Next, the data points are sorted by their confidence indices and progressively reclassified by the slower, more accurate SVM, starting with the items most likely to be incorrectly classified. The user can halt this reclassification process at any point, thereby obtaining the best possible result for a given amount of computation time. Alternatively, the results can be displayed as they are generated, providing the user with real-time feedback about the current accuracy of classification.

Supervised Machine Learning Algorithms Can Classify Open-Text Feedback of Doctor Performance With Human-Level Accuracy.

PubMed

Gibbons, Chris; Richards, Suzanne; Valderas, Jose Maria; Campbell, John

2017-03-15

Machine learning techniques may be an effective and efficient way to classify open-text reports on doctor's activity for the purposes of quality assurance, safety, and continuing professional development. The objective of the study was to evaluate the accuracy of machine learning algorithms trained to classify open-text reports of doctor performance and to assess the potential for classifications to identify significant differences in doctors' professional performance in the United Kingdom. We used 1636 open-text comments (34,283 words) relating to the performance of 548 doctors collected from a survey of clinicians' colleagues using the General Medical Council Colleague Questionnaire (GMC-CQ). We coded 77.75% (1272/1636) of the comments into 5 global themes (innovation, interpersonal skills, popularity, professionalism, and respect) using a qualitative framework. We trained 8 machine learning algorithms to classify comments and assessed their performance using several training samples. We evaluated doctor performance using the GMC-CQ and compared scores between doctors with different classifications using t tests. Individual algorithm performance was high (range F score=.68 to .83). Interrater agreement between the algorithms and the human coder was highest for codes relating to "popular" (recall=.97), "innovator" (recall=.98), and "respected" (recall=.87) codes and was lower for the "interpersonal" (recall=.80) and "professional" (recall=.82) codes. A 10-fold cross-validation demonstrated similar performance in each analysis. When combined together into an ensemble of multiple algorithms, mean human-computer interrater agreement was .88. Comments that were classified as "respected," "professional," and "interpersonal" related to higher doctor scores on the GMC-CQ compared with comments that were not classified (P<.05). Scores did not vary between doctors who were rated as popular or innovative and those who were not rated at all (P>.05). Machine learning algorithms can classify open-text feedback of doctor performance into multiple themes derived by human raters with high performance. Colleague open-text comments that signal respect, professionalism, and being interpersonal may be key indicators of doctor's performance. ©Chris Gibbons, Suzanne Richards, Jose Maria Valderas, John Campbell. Originally published in the Journal of Medical Internet Research (http://www.jmir.org), 15.03.2017.

A review of classification algorithms for EEG-based brain–computer interfaces: a 10 year update

NASA Astrophysics Data System (ADS)

Lotte, F.; Bougrain, L.; Cichocki, A.; Clerc, M.; Congedo, M.; Rakotomamonjy, A.; Yger, F.

2018-06-01

Objective. Most current electroencephalography (EEG)-based brain–computer interfaces (BCIs) are based on machine learning algorithms. There is a large diversity of classifier types that are used in this field, as described in our 2007 review paper. Now, approximately ten years after this review publication, many new algorithms have been developed and tested to classify EEG signals in BCIs. The time is therefore ripe for an updated review of EEG classification algorithms for BCIs. Approach. We surveyed the BCI and machine learning literature from 2007 to 2017 to identify the new classification approaches that have been investigated to design BCIs. We synthesize these studies in order to present such algorithms, to report how they were used for BCIs, what were the outcomes, and to identify their pros and cons. Main results. We found that the recently designed classification algorithms for EEG-based BCIs can be divided into four main categories: adaptive classifiers, matrix and tensor classifiers, transfer learning and deep learning, plus a few other miscellaneous classifiers. Among these, adaptive classifiers were demonstrated to be generally superior to static ones, even with unsupervised adaptation. Transfer learning can also prove useful although the benefits of transfer learning remain unpredictable. Riemannian geometry-based methods have reached state-of-the-art performances on multiple BCI problems and deserve to be explored more thoroughly, along with tensor-based methods. Shrinkage linear discriminant analysis and random forests also appear particularly useful for small training samples settings. On the other hand, deep learning methods have not yet shown convincing improvement over state-of-the-art BCI methods. Significance. This paper provides a comprehensive overview of the modern classification algorithms used in EEG-based BCIs, presents the principles of these methods and guidelines on when and how to use them. It also identifies a number of challenges to further advance EEG classification in BCI.

Contextual classification on a CDC Flexible Processor system. [for photomapped remote sensing data

NASA Technical Reports Server (NTRS)

Smith, B. W.; Siegel, H. J.; Swain, P. H.

1981-01-01

A potential hardware organization for the Flexible Processor Array is presented. An algorithm that implements a contextual classifier for remote sensing data analysis is given, along with uniprocessor classification algorithms. The Flexible Processor algorithm is provided, as are simulated timings for contextual classifiers run on the Flexible Processor Array and another system. The timings are analyzed for context neighborhoods of sizes three and nine.

Accessing primary care Big Data: the development of a software algorithm to explore the rich content of consultation records.

PubMed

MacRae, J; Darlow, B; McBain, L; Jones, O; Stubbe, M; Turner, N; Dowell, A

2015-08-21

To develop a natural language processing software inference algorithm to classify the content of primary care consultations using electronic health record Big Data and subsequently test the algorithm's ability to estimate the prevalence and burden of childhood respiratory illness in primary care. Algorithm development and validation study. To classify consultations, the algorithm is designed to interrogate clinical narrative entered as free text, diagnostic (Read) codes created and medications prescribed on the day of the consultation. Thirty-six consenting primary care practices from a mixed urban and semirural region of New Zealand. Three independent sets of 1200 child consultation records were randomly extracted from a data set of all general practitioner consultations in participating practices between 1 January 2008-31 December 2013 for children under 18 years of age (n=754,242). Each consultation record within these sets was independently classified by two expert clinicians as respiratory or non-respiratory, and subclassified according to respiratory diagnostic categories to create three 'gold standard' sets of classified records. These three gold standard record sets were used to train, test and validate the algorithm. Sensitivity, specificity, positive predictive value and F-measure were calculated to illustrate the algorithm's ability to replicate judgements of expert clinicians within the 1200 record gold standard validation set. The algorithm was able to identify respiratory consultations in the 1200 record validation set with a sensitivity of 0.72 (95% CI 0.67 to 0.78) and a specificity of 0.95 (95% CI 0.93 to 0.98). The positive predictive value of algorithm respiratory classification was 0.93 (95% CI 0.89 to 0.97). The positive predictive value of the algorithm classifying consultations as being related to specific respiratory diagnostic categories ranged from 0.68 (95% CI 0.40 to 1.00; other respiratory conditions) to 0.91 (95% CI 0.79 to 1.00; throat infections). A software inference algorithm that uses primary care Big Data can accurately classify the content of clinical consultations. This algorithm will enable accurate estimation of the prevalence of childhood respiratory illness in primary care and resultant service utilisation. The methodology can also be applied to other areas of clinical care. 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.

Multi-objective evolutionary algorithms for fuzzy classification in survival prediction.

PubMed

Jiménez, Fernando; Sánchez, Gracia; Juárez, José M

2014-03-01

This paper presents a novel rule-based fuzzy classification methodology for survival/mortality prediction in severe burnt patients. Due to the ethical aspects involved in this medical scenario, physicians tend not to accept a computer-based evaluation unless they understand why and how such a recommendation is given. Therefore, any fuzzy classifier model must be both accurate and interpretable. The proposed methodology is a three-step process: (1) multi-objective constrained optimization of a patient's data set, using Pareto-based elitist multi-objective evolutionary algorithms to maximize accuracy and minimize the complexity (number of rules) of classifiers, subject to interpretability constraints; this step produces a set of alternative (Pareto) classifiers; (2) linguistic labeling, which assigns a linguistic label to each fuzzy set of the classifiers; this step is essential to the interpretability of the classifiers; (3) decision making, whereby a classifier is chosen, if it is satisfactory, according to the preferences of the decision maker. If no classifier is satisfactory for the decision maker, the process starts again in step (1) with a different input parameter set. The performance of three multi-objective evolutionary algorithms, niched pre-selection multi-objective algorithm, elitist Pareto-based multi-objective evolutionary algorithm for diversity reinforcement (ENORA) and the non-dominated sorting genetic algorithm (NSGA-II), was tested using a patient's data set from an intensive care burn unit and a standard machine learning data set from an standard machine learning repository. The results are compared using the hypervolume multi-objective metric. Besides, the results have been compared with other non-evolutionary techniques and validated with a multi-objective cross-validation technique. Our proposal improves the classification rate obtained by other non-evolutionary techniques (decision trees, artificial neural networks, Naive Bayes, and case-based reasoning) obtaining with ENORA a classification rate of 0.9298, specificity of 0.9385, and sensitivity of 0.9364, with 14.2 interpretable fuzzy rules on average. Our proposal improves the accuracy and interpretability of the classifiers, compared with other non-evolutionary techniques. We also conclude that ENORA outperforms niched pre-selection and NSGA-II algorithms. Moreover, given that our multi-objective evolutionary methodology is non-combinational based on real parameter optimization, the time cost is significantly reduced compared with other evolutionary approaches existing in literature based on combinational optimization. Copyright © 2014 Elsevier B.V. All rights reserved.

Modulation Classification of Satellite Communication Signals Using Cumulants and Neural Networks

NASA Technical Reports Server (NTRS)

Smith, Aaron; Evans, Michael; Downey, Joseph

2017-01-01

National Aeronautics and Space Administration (NASA)'s future communication architecture is evaluating cognitive technologies and increased system intelligence. These technologies are expected to reduce the operational complexity of the network, increase science data return, and reduce interference to self and others. In order to increase situational awareness, signal classification algorithms could be applied to identify users and distinguish sources of interference. A significant amount of previous work has been done in the area of automatic signal classification for military and commercial applications. As a preliminary step, we seek to develop a system with the ability to discern signals typically encountered in satellite communication. Proposed is an automatic modulation classifier which utilizes higher order statistics (cumulants) and an estimate of the signal-to-noise ratio. These features are extracted from baseband symbols and then processed by a neural network for classification. The modulation types considered are phase-shift keying (PSK), amplitude and phase-shift keying (APSK),and quadrature amplitude modulation (QAM). Physical layer properties specific to the Digital Video Broadcasting - Satellite- Second Generation (DVB-S2) standard, such as pilots and variable ring ratios, are also considered. This paper will provide simulation results of a candidate modulation classifier, and performance will be evaluated over a range of signal-to-noise ratios, frequency offsets, and nonlinear amplifier distortions.

A cDNA microarray gene expression data classifier for clinical diagnostics based on graph theory.

PubMed

Benso, Alfredo; Di Carlo, Stefano; Politano, Gianfranco

2011-01-01

Despite great advances in discovering cancer molecular profiles, the proper application of microarray technology to routine clinical diagnostics is still a challenge. Current practices in the classification of microarrays' data show two main limitations: the reliability of the training data sets used to build the classifiers, and the classifiers' performances, especially when the sample to be classified does not belong to any of the available classes. In this case, state-of-the-art algorithms usually produce a high rate of false positives that, in real diagnostic applications, are unacceptable. To address this problem, this paper presents a new cDNA microarray data classification algorithm based on graph theory and is able to overcome most of the limitations of known classification methodologies. The classifier works by analyzing gene expression data organized in an innovative data structure based on graphs, where vertices correspond to genes and edges to gene expression relationships. To demonstrate the novelty of the proposed approach, the authors present an experimental performance comparison between the proposed classifier and several state-of-the-art classification algorithms.

Performance evaluation of various classifiers for color prediction of rice paddy plant leaf

NASA Astrophysics Data System (ADS)

Singh, Amandeep; Singh, Maninder Lal

2016-11-01

The food industry is one of the industries that uses machine vision for a nondestructive quality evaluation of the produce. These quality measuring systems and softwares are precalculated on the basis of various image-processing algorithms which generally use a particular type of classifier. These classifiers play a vital role in making the algorithms so intelligent that it can contribute its best while performing the said quality evaluations by translating the human perception into machine vision and hence machine learning. The crop of interest is rice, and the color of this crop indicates the health status of the plant. An enormous number of classifiers are available to solve the purpose of color prediction, but choosing the best among them is the focus of this paper. Performance of a total of 60 classifiers has been analyzed from the application point of view, and the results have been discussed. The motivation comes from the idea of providing a set of classifiers with excellent performance and implementing them on a single algorithm for the improvement of machine vision learning and, hence, associated applications.

a Hadoop-Based Algorithm of Generating dem Grid from Point Cloud Data

NASA Astrophysics Data System (ADS)

Jian, X.; Xiao, X.; Chengfang, H.; Zhizhong, Z.; Zhaohui, W.; Dengzhong, Z.

2015-04-01

Airborne LiDAR technology has proven to be the most powerful tools to obtain high-density, high-accuracy and significantly detailed surface information of terrain and surface objects within a short time, and from which the Digital Elevation Model of high quality can be extracted. Point cloud data generated from the pre-processed data should be classified by segmentation algorithms, so as to differ the terrain points from disorganized points, then followed by a procedure of interpolating the selected points to turn points into DEM data. The whole procedure takes a long time and huge computing resource due to high-density, that is concentrated on by a number of researches. Hadoop is a distributed system infrastructure developed by the Apache Foundation, which contains a highly fault-tolerant distributed file system (HDFS) with high transmission rate and a parallel programming model (Map/Reduce). Such a framework is appropriate for DEM generation algorithms to improve efficiency. Point cloud data of Dongting Lake acquired by Riegl LMS-Q680i laser scanner was utilized as the original data to generate DEM by a Hadoop-based algorithms implemented in Linux, then followed by another traditional procedure programmed by C++ as the comparative experiment. Then the algorithm's efficiency, coding complexity, and performance-cost ratio were discussed for the comparison. The results demonstrate that the algorithm's speed depends on size of point set and density of DEM grid, and the non-Hadoop implementation can achieve a high performance when memory is big enough, but the multiple Hadoop implementation can achieve a higher performance-cost ratio, while point set is of vast quantities on the other hand.

Heterogeneous Ensemble Combination Search Using Genetic Algorithm for Class Imbalanced Data Classification.

PubMed

Haque, Mohammad Nazmul; Noman, Nasimul; Berretta, Regina; Moscato, Pablo

2016-01-01

Classification of datasets with imbalanced sample distributions has always been a challenge. In general, a popular approach for enhancing classification performance is the construction of an ensemble of classifiers. However, the performance of an ensemble is dependent on the choice of constituent base classifiers. Therefore, we propose a genetic algorithm-based search method for finding the optimum combination from a pool of base classifiers to form a heterogeneous ensemble. The algorithm, called GA-EoC, utilises 10 fold-cross validation on training data for evaluating the quality of each candidate ensembles. In order to combine the base classifiers decision into ensemble's output, we used the simple and widely used majority voting approach. The proposed algorithm, along with the random sub-sampling approach to balance the class distribution, has been used for classifying class-imbalanced datasets. Additionally, if a feature set was not available, we used the (α, β) - k Feature Set method to select a better subset of features for classification. We have tested GA-EoC with three benchmarking datasets from the UCI-Machine Learning repository, one Alzheimer's disease dataset and a subset of the PubFig database of Columbia University. In general, the performance of the proposed method on the chosen datasets is robust and better than that of the constituent base classifiers and many other well-known ensembles. Based on our empirical study we claim that a genetic algorithm is a superior and reliable approach to heterogeneous ensemble construction and we expect that the proposed GA-EoC would perform consistently in other cases.

Heterogeneous Ensemble Combination Search Using Genetic Algorithm for Class Imbalanced Data Classification

PubMed Central

Haque, Mohammad Nazmul; Noman, Nasimul; Berretta, Regina; Moscato, Pablo

2016-01-01

Classification of datasets with imbalanced sample distributions has always been a challenge. In general, a popular approach for enhancing classification performance is the construction of an ensemble of classifiers. However, the performance of an ensemble is dependent on the choice of constituent base classifiers. Therefore, we propose a genetic algorithm-based search method for finding the optimum combination from a pool of base classifiers to form a heterogeneous ensemble. The algorithm, called GA-EoC, utilises 10 fold-cross validation on training data for evaluating the quality of each candidate ensembles. In order to combine the base classifiers decision into ensemble’s output, we used the simple and widely used majority voting approach. The proposed algorithm, along with the random sub-sampling approach to balance the class distribution, has been used for classifying class-imbalanced datasets. Additionally, if a feature set was not available, we used the (α, β) − k Feature Set method to select a better subset of features for classification. We have tested GA-EoC with three benchmarking datasets from the UCI-Machine Learning repository, one Alzheimer’s disease dataset and a subset of the PubFig database of Columbia University. In general, the performance of the proposed method on the chosen datasets is robust and better than that of the constituent base classifiers and many other well-known ensembles. Based on our empirical study we claim that a genetic algorithm is a superior and reliable approach to heterogeneous ensemble construction and we expect that the proposed GA-EoC would perform consistently in other cases. PMID:26764911

An algorithm for generating modular hierarchical neural network classifiers: a step toward larger scale applications

NASA Astrophysics Data System (ADS)

Roverso, Davide

2003-08-01

Many-class learning is the problem of training a classifier to discriminate among a large number of target classes. Together with the problem of dealing with high-dimensional patterns (i.e. a high-dimensional input space), the many class problem (i.e. a high-dimensional output space) is a major obstacle to be faced when scaling-up classifier systems and algorithms from small pilot applications to large full-scale applications. The Autonomous Recursive Task Decomposition (ARTD) algorithm is here proposed as a solution to the problem of many-class learning. Example applications of ARTD to neural classifier training are also presented. In these examples, improvements in training time are shown to range from 4-fold to more than 30-fold in pattern classification tasks of both static and dynamic character.

Automatic morphological classification of galaxy images

PubMed Central

Shamir, Lior

2009-01-01

We describe an image analysis supervised learning algorithm that can automatically classify galaxy images. The algorithm is first trained using a manually classified images of elliptical, spiral, and edge-on galaxies. A large set of image features is extracted from each image, and the most informative features are selected using Fisher scores. Test images can then be classified using a simple Weighted Nearest Neighbor rule such that the Fisher scores are used as the feature weights. Experimental results show that galaxy images from Galaxy Zoo can be classified automatically to spiral, elliptical and edge-on galaxies with accuracy of ~90% compared to classifications carried out by the author. Full compilable source code of the algorithm is available for free download, and its general-purpose nature makes it suitable for other uses that involve automatic image analysis of celestial objects. PMID:20161594

Cupping artifact correction and automated classification for high-resolution dedicated breast CT images.

PubMed

Yang, Xiaofeng; Wu, Shengyong; Sechopoulos, Ioannis; Fei, Baowei

2012-10-01

To develop and test an automated algorithm to classify the different tissues present in dedicated breast CT images. The original CT images are first corrected to overcome cupping artifacts, and then a multiscale bilateral filter is used to reduce noise while keeping edge information on the images. As skin and glandular tissues have similar CT values on breast CT images, morphologic processing is used to identify the skin mask based on its position information. A modified fuzzy C-means (FCM) classification method is then used to classify breast tissue as fat and glandular tissue. By combining the results of the skin mask with the FCM, the breast tissue is classified as skin, fat, and glandular tissue. To evaluate the authors' classification method, the authors use Dice overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on eight patient images. The correction method was able to correct the cupping artifacts and improve the quality of the breast CT images. For glandular tissue, the overlap ratios between the authors' automatic classification and manual segmentation were 91.6% ± 2.0%. A cupping artifact correction method and an automatic classification method were applied and evaluated for high-resolution dedicated breast CT images. Breast tissue classification can provide quantitative measurements regarding breast composition, density, and tissue distribution.

EEG channels reduction using PCA to increase XGBoost's accuracy for stroke detection

NASA Astrophysics Data System (ADS)

Fitriah, N.; Wijaya, S. K.; Fanany, M. I.; Badri, C.; Rezal, M.

2017-07-01

In Indonesia, based on the result of Basic Health Research 2013, the number of stroke patients had increased from 8.3 ‰ (2007) to 12.1 ‰ (2013). These days, some researchers are using electroencephalography (EEG) result as another option to detect the stroke disease besides CT Scan image as the gold standard. A previous study on the data of stroke and healthy patients in National Brain Center Hospital (RS PON) used Brain Symmetry Index (BSI), Delta-Alpha Ratio (DAR), and Delta-Theta-Alpha-Beta Ratio (DTABR) as the features for classification by an Extreme Learning Machine (ELM). The study got 85% accuracy with sensitivity above 86 % for acute ischemic stroke detection. Using EEG data means dealing with many data dimensions, and it can reduce the accuracy of classifier (the curse of dimensionality). Principal Component Analysis (PCA) could reduce dimensionality and computation cost without decreasing classification accuracy. XGBoost, as the scalable tree boosting classifier, can solve real-world scale problems (Higgs Boson and Allstate dataset) with using a minimal amount of resources. This paper reuses the same data from RS PON and features from previous research, preprocessed with PCA and classified with XGBoost, to increase the accuracy with fewer electrodes. The specific fewer electrodes improved the accuracy of stroke detection. Our future work will examine the other algorithm besides PCA to get higher accuracy with less number of channels.

Cupping artifact correction and automated classification for high-resolution dedicated breast CT images

PubMed Central

Yang, Xiaofeng; Wu, Shengyong; Sechopoulos, Ioannis; Fei, Baowei

2012-01-01

Purpose: To develop and test an automated algorithm to classify the different tissues present in dedicated breast CT images. Methods: The original CT images are first corrected to overcome cupping artifacts, and then a multiscale bilateral filter is used to reduce noise while keeping edge information on the images. As skin and glandular tissues have similar CT values on breast CT images, morphologic processing is used to identify the skin mask based on its position information. A modified fuzzy C-means (FCM) classification method is then used to classify breast tissue as fat and glandular tissue. By combining the results of the skin mask with the FCM, the breast tissue is classified as skin, fat, and glandular tissue. To evaluate the authors’ classification method, the authors use Dice overlap ratios to compare the results of the automated classification to those obtained by manual segmentation on eight patient images. Results: The correction method was able to correct the cupping artifacts and improve the quality of the breast CT images. For glandular tissue, the overlap ratios between the authors’ automatic classification and manual segmentation were 91.6% ± 2.0%. Conclusions: A cupping artifact correction method and an automatic classification method were applied and evaluated for high-resolution dedicated breast CT images. Breast tissue classification can provide quantitative measurements regarding breast composition, density, and tissue distribution. PMID:23039675

Vision-based posture recognition using an ensemble classifier and a vote filter

NASA Astrophysics Data System (ADS)

Ji, Peng; Wu, Changcheng; Xu, Xiaonong; Song, Aiguo; Li, Huijun

2016-10-01

Posture recognition is a very important Human-Robot Interaction (HRI) way. To segment effective posture from an image, we propose an improved region grow algorithm which combining with the Single Gauss Color Model. The experiment shows that the improved region grow algorithm can get the complete and accurate posture than traditional Single Gauss Model and region grow algorithm, and it can eliminate the similar region from the background at the same time. In the posture recognition part, and in order to improve the recognition rate, we propose a CNN ensemble classifier, and in order to reduce the misjudgments during a continuous gesture control, a vote filter is proposed and applied to the sequence of recognition results. Comparing with CNN classifier, the CNN ensemble classifier we proposed can yield a 96.27% recognition rate, which is better than that of CNN classifier, and the proposed vote filter can improve the recognition result and reduce the misjudgments during the consecutive gesture switch.

Testing of the Support Vector Machine for Binary-Class Classification

NASA Technical Reports Server (NTRS)

Scholten, Matthew

2011-01-01

The Support Vector Machine is a powerful algorithm, useful in classifying data in to species. The Support Vector Machines implemented in this research were used as classifiers for the final stage in a Multistage Autonomous Target Recognition system. A single kernel SVM known as SVMlight, and a modified version known as a Support Vector Machine with K-Means Clustering were used. These SVM algorithms were tested as classifiers under varying conditions. Image noise levels varied, and the orientation of the targets changed. The classifiers were then optimized to demonstrate their maximum potential as classifiers. Results demonstrate the reliability of SMV as a method for classification. From trial to trial, SVM produces consistent results

Use of a machine learning algorithm to classify expertise: analysis of hand motion patterns during a simulated surgical task.

PubMed

Watson, Robert A

2014-08-01

To test the hypothesis that machine learning algorithms increase the predictive power to classify surgical expertise using surgeons' hand motion patterns. In 2012 at the University of North Carolina at Chapel Hill, 14 surgical attendings and 10 first- and second-year surgical residents each performed two bench model venous anastomoses. During the simulated tasks, the participants wore an inertial measurement unit on the dorsum of their dominant (right) hand to capture their hand motion patterns. The pattern from each bench model task performed was preprocessed into a symbolic time series and labeled as expert (attending) or novice (resident). The labeled hand motion patterns were processed and used to train a Support Vector Machine (SVM) classification algorithm. The trained algorithm was then tested for discriminative/predictive power against unlabeled (blinded) hand motion patterns from tasks not used in the training. The Lempel-Ziv (LZ) complexity metric was also measured from each hand motion pattern, with an optimal threshold calculated to separately classify the patterns. The LZ metric classified unlabeled (blinded) hand motion patterns into expert and novice groups with an accuracy of 70% (sensitivity 64%, specificity 80%). The SVM algorithm had an accuracy of 83% (sensitivity 86%, specificity 80%). The results confirmed the hypothesis. The SVM algorithm increased the predictive power to classify blinded surgical hand motion patterns into expert versus novice groups. With further development, the system used in this study could become a viable tool for low-cost, objective assessment of procedural proficiency in a competency-based curriculum.

Imbalanced class learning in epigenetics.

PubMed

Haque, M Muksitul; Skinner, Michael K; Holder, Lawrence B

2014-07-01

In machine learning, one of the important criteria for higher classification accuracy is a balanced dataset. Datasets with a large ratio between minority and majority classes face hindrance in learning using any classifier. Datasets having a magnitude difference in number of instances between the target concept result in an imbalanced class distribution. Such datasets can range from biological data, sensor data, medical diagnostics, or any other domain where labeling any instances of the minority class can be time-consuming or costly or the data may not be easily available. The current study investigates a number of imbalanced class algorithms for solving the imbalanced class distribution present in epigenetic datasets. Epigenetic (DNA methylation) datasets inherently come with few differentially DNA methylated regions (DMR) and with a higher number of non-DMR sites. For this class imbalance problem, a number of algorithms are compared, including the TAN+AdaBoost algorithm. Experiments performed on four epigenetic datasets and several known datasets show that an imbalanced dataset can have similar accuracy as a regular learner on a balanced dataset.

New Dandelion Algorithm Optimizes Extreme Learning Machine for Biomedical Classification Problems

PubMed Central

Li, Xiguang; Zhao, Liang; Gong, Changqing; Liu, Xiaojing

2017-01-01

Inspired by the behavior of dandelion sowing, a new novel swarm intelligence algorithm, namely, dandelion algorithm (DA), is proposed for global optimization of complex functions in this paper. In DA, the dandelion population will be divided into two subpopulations, and different subpopulations will undergo different sowing behaviors. Moreover, another sowing method is designed to jump out of local optimum. In order to demonstrate the validation of DA, we compare the proposed algorithm with other existing algorithms, including bat algorithm, particle swarm optimization, and enhanced fireworks algorithm. Simulations show that the proposed algorithm seems much superior to other algorithms. At the same time, the proposed algorithm can be applied to optimize extreme learning machine (ELM) for biomedical classification problems, and the effect is considerable. At last, we use different fusion methods to form different fusion classifiers, and the fusion classifiers can achieve higher accuracy and better stability to some extent. PMID:29085425

Determination of target detection limits in hyperspectral data using band selection and dimensionality reduction

NASA Astrophysics Data System (ADS)

Gross, W.; Boehler, J.; Twizer, K.; Kedem, B.; Lenz, A.; Kneubuehler, M.; Wellig, P.; Oechslin, R.; Schilling, H.; Rotman, S.; Middelmann, W.

2016-10-01

Hyperspectral remote sensing data can be used for civil and military applications to robustly detect and classify target objects. High spectral resolution of hyperspectral data can compensate for the comparatively low spatial resolution, which allows for detection and classification of small targets, even below image resolution. Hyperspectral data sets are prone to considerable spectral redundancy, affecting and limiting data processing and algorithm performance. As a consequence, data reduction strategies become increasingly important, especially in view of near-real-time data analysis. The goal of this paper is to analyze different strategies for hyperspectral band selection algorithms and their effect on subpixel classification for different target and background materials. Airborne hyperspectral data is used in combination with linear target simulation procedures to create a representative amount of target-to-background ratios for evaluation of detection limits. Data from two different airborne hyperspectral sensors, AISA Eagle and Hawk, are used to evaluate transferability of band selection when using different sensors. The same target objects were recorded to compare the calculated detection limits. To determine subpixel classification results, pure pixels from the target materials are extracted and used to simulate mixed pixels with selected background materials. Target signatures are linearly combined with different background materials in varying ratios. The commonly used classification algorithms Adaptive Coherence Estimator (ACE) is used to compare the detection limit for the original data with several band selection and data reduction strategies. The evaluation of the classification results is done by assuming a fixed false alarm ratio and calculating the mean target-to-background ratio of correctly detected pixels. The results allow drawing conclusions about specific band combinations for certain target and background combinations. Additionally, generally useful wavelength ranges are determined and the optimal amount of principal components is analyzed.

Particle swarm optimization-based automatic parameter selection for deep neural networks and its applications in large-scale and high-dimensional data

PubMed Central

2017-01-01

In this paper, we propose a new automatic hyperparameter selection approach for determining the optimal network configuration (network structure and hyperparameters) for deep neural networks using particle swarm optimization (PSO) in combination with a steepest gradient descent algorithm. In the proposed approach, network configurations were coded as a set of real-number m-dimensional vectors as the individuals of the PSO algorithm in the search procedure. During the search procedure, the PSO algorithm is employed to search for optimal network configurations via the particles moving in a finite search space, and the steepest gradient descent algorithm is used to train the DNN classifier with a few training epochs (to find a local optimal solution) during the population evaluation of PSO. After the optimization scheme, the steepest gradient descent algorithm is performed with more epochs and the final solutions (pbest and gbest) of the PSO algorithm to train a final ensemble model and individual DNN classifiers, respectively. The local search ability of the steepest gradient descent algorithm and the global search capabilities of the PSO algorithm are exploited to determine an optimal solution that is close to the global optimum. We constructed several experiments on hand-written characters and biological activity prediction datasets to show that the DNN classifiers trained by the network configurations expressed by the final solutions of the PSO algorithm, employed to construct an ensemble model and individual classifier, outperform the random approach in terms of the generalization performance. Therefore, the proposed approach can be regarded an alternative tool for automatic network structure and parameter selection for deep neural networks. PMID:29236718

Improved adaptive splitting and selection: the hybrid training method of a classifier based on a feature space partitioning.

PubMed

Jackowski, Konrad; Krawczyk, Bartosz; Woźniak, Michał

2014-05-01

Currently, methods of combined classification are the focus of intense research. A properly designed group of combined classifiers exploiting knowledge gathered in a pool of elementary classifiers can successfully outperform a single classifier. There are two essential issues to consider when creating combined classifiers: how to establish the most comprehensive pool and how to design a fusion model that allows for taking full advantage of the collected knowledge. In this work, we address the issues and propose an AdaSS+, training algorithm dedicated for the compound classifier system that effectively exploits local specialization of the elementary classifiers. An effective training procedure consists of two phases. The first phase detects the classifier competencies and adjusts the respective fusion parameters. The second phase boosts classification accuracy by elevating the degree of local specialization. The quality of the proposed algorithms are evaluated on the basis of a wide range of computer experiments that show that AdaSS+ can outperform the original method and several reference classifiers.

Reduction from cost-sensitive ordinal ranking to weighted binary classification.

PubMed

Lin, Hsuan-Tien; Li, Ling

2012-05-01

We present a reduction framework from ordinal ranking to binary classification. The framework consists of three steps: extracting extended examples from the original examples, learning a binary classifier on the extended examples with any binary classification algorithm, and constructing a ranker from the binary classifier. Based on the framework, we show that a weighted 0/1 loss of the binary classifier upper-bounds the mislabeling cost of the ranker, both error-wise and regret-wise. Our framework allows not only the design of good ordinal ranking algorithms based on well-tuned binary classification approaches, but also the derivation of new generalization bounds for ordinal ranking from known bounds for binary classification. In addition, our framework unifies many existing ordinal ranking algorithms, such as perceptron ranking and support vector ordinal regression. When compared empirically on benchmark data sets, some of our newly designed algorithms enjoy advantages in terms of both training speed and generalization performance over existing algorithms. In addition, the newly designed algorithms lead to better cost-sensitive ordinal ranking performance, as well as improved listwise ranking performance.

[MicroRNA Target Prediction Based on Support Vector Machine Ensemble Classification Algorithm of Under-sampling Technique].

PubMed

Chen, Zhiru; Hong, Wenxue

2016-02-01

Considering the low accuracy of prediction in the positive samples and poor overall classification effects caused by unbalanced sample data of MicroRNA (miRNA) target, we proposes a support vector machine (SVM)-integration of under-sampling and weight (IUSM) algorithm in this paper, an under-sampling based on the ensemble learning algorithm. The algorithm adopts SVM as learning algorithm and AdaBoost as integration framework, and embeds clustering-based under-sampling into the iterative process, aiming at reducing the degree of unbalanced distribution of positive and negative samples. Meanwhile, in the process of adaptive weight adjustment of the samples, the SVM-IUSM algorithm eliminates the abnormal ones in negative samples with robust sample weights smoothing mechanism so as to avoid over-learning. Finally, the prediction of miRNA target integrated classifier is achieved with the combination of multiple weak classifiers through the voting mechanism. The experiment revealed that the SVM-IUSW, compared with other algorithms on unbalanced dataset collection, could not only improve the accuracy of positive targets and the overall effect of classification, but also enhance the generalization ability of miRNA target classifier.

Quantum ensembles of quantum classifiers.

PubMed

Schuld, Maria; Petruccione, Francesco

2018-02-09

Quantum machine learning witnesses an increasing amount of quantum algorithms for data-driven decision making, a problem with potential applications ranging from automated image recognition to medical diagnosis. Many of those algorithms are implementations of quantum classifiers, or models for the classification of data inputs with a quantum computer. Following the success of collective decision making with ensembles in classical machine learning, this paper introduces the concept of quantum ensembles of quantum classifiers. Creating the ensemble corresponds to a state preparation routine, after which the quantum classifiers are evaluated in parallel and their combined decision is accessed by a single-qubit measurement. This framework naturally allows for exponentially large ensembles in which - similar to Bayesian learning - the individual classifiers do not have to be trained. As an example, we analyse an exponentially large quantum ensemble in which each classifier is weighed according to its performance in classifying the training data, leading to new results for quantum as well as classical machine learning.

Comparison of Different EHG Feature Selection Methods for the Detection of Preterm Labor

PubMed Central

Alamedine, D.; Khalil, M.; Marque, C.

2013-01-01

Numerous types of linear and nonlinear features have been extracted from the electrohysterogram (EHG) in order to classify labor and pregnancy contractions. As a result, the number of available features is now very large. The goal of this study is to reduce the number of features by selecting only the relevant ones which are useful for solving the classification problem. This paper presents three methods for feature subset selection that can be applied to choose the best subsets for classifying labor and pregnancy contractions: an algorithm using the Jeffrey divergence (JD) distance, a sequential forward selection (SFS) algorithm, and a binary particle swarm optimization (BPSO) algorithm. The two last methods are based on a classifier and were tested with three types of classifiers. These methods have allowed us to identify common features which are relevant for contraction classification. PMID:24454536

Vehicle Classification Using an Imbalanced Dataset Based on a Single Magnetic Sensor.

PubMed

Xu, Chang; Wang, Yingguan; Bao, Xinghe; Li, Fengrong

2018-05-24

This paper aims to improve the accuracy of automatic vehicle classifiers for imbalanced datasets. Classification is made through utilizing a single anisotropic magnetoresistive sensor, with the models of vehicles involved being classified into hatchbacks, sedans, buses, and multi-purpose vehicles (MPVs). Using time domain and frequency domain features in combination with three common classification algorithms in pattern recognition, we develop a novel feature extraction method for vehicle classification. These three common classification algorithms are the k-nearest neighbor, the support vector machine, and the back-propagation neural network. Nevertheless, a problem remains with the original vehicle magnetic dataset collected being imbalanced, and may lead to inaccurate classification results. With this in mind, we propose an approach called SMOTE, which can further boost the performance of classifiers. Experimental results show that the k-nearest neighbor (KNN) classifier with the SMOTE algorithm can reach a classification accuracy of 95.46%, thus minimizing the effect of the imbalance.

Machine Learning Algorithms for Automatic Classification of Marmoset Vocalizations

PubMed Central

Ribeiro, Sidarta; Pereira, Danillo R.; Papa, João P.; de Albuquerque, Victor Hugo C.

2016-01-01

Automatic classification of vocalization type could potentially become a useful tool for acoustic the monitoring of captive colonies of highly vocal primates. However, for classification to be useful in practice, a reliable algorithm that can be successfully trained on small datasets is necessary. In this work, we consider seven different classification algorithms with the goal of finding a robust classifier that can be successfully trained on small datasets. We found good classification performance (accuracy > 0.83 and F1-score > 0.84) using the Optimum Path Forest classifier. Dataset and algorithms are made publicly available. PMID:27654941

Comparison of Genetic Algorithm, Particle Swarm Optimization and Biogeography-based Optimization for Feature Selection to Classify Clusters of Microcalcifications

NASA Astrophysics Data System (ADS)

Khehra, Baljit Singh; Pharwaha, Amar Partap Singh

2017-04-01

Ductal carcinoma in situ (DCIS) is one type of breast cancer. Clusters of microcalcifications (MCCs) are symptoms of DCIS that are recognized by mammography. Selection of robust features vector is the process of selecting an optimal subset of features from a large number of available features in a given problem domain after the feature extraction and before any classification scheme. Feature selection reduces the feature space that improves the performance of classifier and decreases the computational burden imposed by using many features on classifier. Selection of an optimal subset of features from a large number of available features in a given problem domain is a difficult search problem. For n features, the total numbers of possible subsets of features are 2n. Thus, selection of an optimal subset of features problem belongs to the category of NP-hard problems. In this paper, an attempt is made to find the optimal subset of MCCs features from all possible subsets of features using genetic algorithm (GA), particle swarm optimization (PSO) and biogeography-based optimization (BBO). For simulation, a total of 380 benign and malignant MCCs samples have been selected from mammogram images of DDSM database. A total of 50 features extracted from benign and malignant MCCs samples are used in this study. In these algorithms, fitness function is correct classification rate of classifier. Support vector machine is used as a classifier. From experimental results, it is also observed that the performance of PSO-based and BBO-based algorithms to select an optimal subset of features for classifying MCCs as benign or malignant is better as compared to GA-based algorithm.

Neural net classification of liver ultrasonogram for quantitative evaluation of diffuse liver disease

NASA Astrophysics Data System (ADS)

Lee, Dong Hyuk; Kim, JongHyo; Kim, Hee C.; Lee, Yong W.; Min, Byong Goo

1997-04-01

There have been a number of studies on the quantitative evaluation of diffuse liver disease by using texture analysis technique. However, the previous studies have been focused on the classification between only normal and abnormal pattern based on textural properties, resulting in lack of clinically useful information about the progressive status of liver disease. Considering our collaborative research experience with clinical experts, we judged that not only texture information but also several shape properties are necessary in order to successfully classify between various states of disease with liver ultrasonogram. Nine image parameters were selected experimentally. One of these was texture parameter and others were shape parameters measured as length, area and curvature. We have developed a neural-net algorithm that classifies liver ultrasonogram into 9 categories of liver disease: 3 main category and 3 sub-steps for each. Nine parameters were collected semi- automatically from the user by using graphical user interface tool, and then processed to give a grade for each parameter. Classifying algorithm consists of two steps. At the first step, each parameter was graded into pre-defined levels using neural network. in the next step, neural network classifier determined disease status using graded nine parameters. We implemented a PC based computer-assist diagnosis workstation and installed it in radiology department of Seoul National University Hospital. Using this workstation we collected 662 cases during 6 months. Some of these were used for training and others were used for evaluating accuracy of the developed algorithm. As a conclusion, a liver ultrasonogram classifying algorithm was developed using both texture and shape parameters and neural network classifier. Preliminary results indicate that the proposed algorithm is useful for evaluation of diffuse liver disease.

Active Learning with Irrelevant Examples

NASA Technical Reports Server (NTRS)

Wagstaff, Kiri; Mazzoni, Dominic

2009-01-01

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

Health condition identification of multi-stage planetary gearboxes using a mRVM-based method

NASA Astrophysics Data System (ADS)

Lei, Yaguo; Liu, Zongyao; Wu, Xionghui; Li, Naipeng; Chen, Wu; Lin, Jing

2015-08-01

Multi-stage planetary gearboxes are widely applied in aerospace, automotive and heavy industries. Their key components, such as gears and bearings, can easily suffer from damage due to tough working environment. Health condition identification of planetary gearboxes aims to prevent accidents and save costs. This paper proposes a method based on multiclass relevance vector machine (mRVM) to identify health condition of multi-stage planetary gearboxes. In this method, a mRVM algorithm is adopted as a classifier, and two features, i.e. accumulative amplitudes of carrier orders (AACO) and energy ratio based on difference spectra (ERDS), are used as the input of the classifier to classify different health conditions of multi-stage planetary gearboxes. To test the proposed method, seven health conditions of a two-stage planetary gearbox are considered and vibration data is acquired from the planetary gearbox under different motor speeds and loading conditions. The results of three tests based on different data show that the proposed method obtains an improved identification performance and robustness compared with the existing method.

Automatic discrimination of fine roots in minirhizotron images.

PubMed

Zeng, Guang; Birchfield, Stanley T; Wells, Christina E

2008-01-01

Minirhizotrons provide detailed information on the production, life history and mortality of fine roots. However, manual processing of minirhizotron images is time-consuming, limiting the number and size of experiments that can reasonably be analysed. Previously, an algorithm was developed to automatically detect and measure individual roots in minirhizotron images. Here, species-specific root classifiers were developed to discriminate detected roots from bright background artifacts. Classifiers were developed from training images of peach (Prunus persica), freeman maple (Acer x freemanii) and sweetbay magnolia (Magnolia virginiana) using the Adaboost algorithm. True- and false-positive rates for classifiers were estimated using receiver operating characteristic curves. Classifiers gave true positive rates of 89-94% and false positive rates of 3-7% when applied to nontraining images of the species for which they were developed. The application of a classifier trained on one species to images from another species resulted in little or no reduction in accuracy. These results suggest that a single root classifier can be used to distinguish roots from background objects across multiple minirhizotron experiments. By incorporating root detection and discrimination algorithms into an open-source minirhizotron image analysis application, many analysis tasks that are currently performed by hand can be automated.

Overview of existing algorithms for emotion classification. Uncertainties in evaluations of accuracies.

NASA Astrophysics Data System (ADS)

Avetisyan, H.; Bruna, O.; Holub, J.

2016-11-01

A numerous techniques and algorithms are dedicated to extract emotions from input data. In our investigation it was stated that emotion-detection approaches can be classified into 3 following types: Keyword based / lexical-based, learning based, and hybrid. The most commonly used techniques, such as keyword-spotting method, Support Vector Machines, Naïve Bayes Classifier, Hidden Markov Model and hybrid algorithms, have impressive results in this sphere and can reach more than 90% determining accuracy.

Deferred discrimination algorithm (nibbling) for target filter management

NASA Astrophysics Data System (ADS)

Caulfield, H. John; Johnson, John L.

1999-07-01

A new method of classifying objects is presented. Rather than trying to form the classifier in one step or in one training algorithm, it is done in a series of small steps, or nibbles. This leads to an efficient and versatile system that is trained in series with single one-shot examples but applied in parallel, is implemented with single layer perceptrons, yet maintains its fully sequential hierarchical structure. Based on the nibbling algorithm, a basic new method of target reference filter management is described.

Fast clustering algorithm for large ECG data sets based on CS theory in combination with PCA and K-NN methods.

PubMed

Balouchestani, Mohammadreza; Krishnan, Sridhar

2014-01-01

Long-term recording of Electrocardiogram (ECG) signals plays an important role in health care systems for diagnostic and treatment purposes of heart diseases. Clustering and classification of collecting data are essential parts for detecting concealed information of P-QRS-T waves in the long-term ECG recording. Currently used algorithms do have their share of drawbacks: 1) clustering and classification cannot be done in real time; 2) they suffer from huge energy consumption and load of sampling. These drawbacks motivated us in developing novel optimized clustering algorithm which could easily scan large ECG datasets for establishing low power long-term ECG recording. In this paper, we present an advanced K-means clustering algorithm based on Compressed Sensing (CS) theory as a random sampling procedure. Then, two dimensionality reduction methods: Principal Component Analysis (PCA) and Linear Correlation Coefficient (LCC) followed by sorting the data using the K-Nearest Neighbours (K-NN) and Probabilistic Neural Network (PNN) classifiers are applied to the proposed algorithm. We show our algorithm based on PCA features in combination with K-NN classifier shows better performance than other methods. The proposed algorithm outperforms existing algorithms by increasing 11% classification accuracy. In addition, the proposed algorithm illustrates classification accuracy for K-NN and PNN classifiers, and a Receiver Operating Characteristics (ROC) area of 99.98%, 99.83%, and 99.75% respectively.

Accuracy and efficiency of area classifications based on tree tally

Treesearch

Michael S. Williams; Hans T. Schreuder; Raymond L. Czaplewski

2001-01-01

Inventory data are often used to estimate the area of the land base that is classified as a specific condition class. Examples include areas classified as old-growth forest, private ownership, or suitable habitat for a given species. Many inventory programs rely on classification algorithms of varying complexity to determine condition class. These algorithms can be...

Automatic analysis and classification of surface electromyography.

PubMed

Abou-Chadi, F E; Nashar, A; Saad, M

2001-01-01

In this paper, parametric modeling of surface electromyography (EMG) algorithms that facilitates automatic SEMG feature extraction and artificial neural networks (ANN) are combined for providing an integrated system for the automatic analysis and diagnosis of myopathic disorders. Three paradigms of ANN were investigated: the multilayer backpropagation algorithm, the self-organizing feature map algorithm and a probabilistic neural network model. The performance of the three classifiers was compared with that of the old Fisher linear discriminant (FLD) classifiers. The results have shown that the three ANN models give higher performance. The percentage of correct classification reaches 90%. Poorer diagnostic performance was obtained from the FLD classifier. The system presented here indicates that surface EMG, when properly processed, can be used to provide the physician with a diagnostic assist device.

Medical subdomain classification of clinical notes using a machine learning-based natural language processing approach.

PubMed

Weng, Wei-Hung; Wagholikar, Kavishwar B; McCray, Alexa T; Szolovits, Peter; Chueh, Henry C

2017-12-01

The medical subdomain of a clinical note, such as cardiology or neurology, is useful content-derived metadata for developing machine learning downstream applications. To classify the medical subdomain of a note accurately, we have constructed a machine learning-based natural language processing (NLP) pipeline and developed medical subdomain classifiers based on the content of the note. We constructed the pipeline using the clinical NLP system, clinical Text Analysis and Knowledge Extraction System (cTAKES), the Unified Medical Language System (UMLS) Metathesaurus, Semantic Network, and learning algorithms to extract features from two datasets - clinical notes from Integrating Data for Analysis, Anonymization, and Sharing (iDASH) data repository (n = 431) and Massachusetts General Hospital (MGH) (n = 91,237), and built medical subdomain classifiers with different combinations of data representation methods and supervised learning algorithms. We evaluated the performance of classifiers and their portability across the two datasets. The convolutional recurrent neural network with neural word embeddings trained-medical subdomain classifier yielded the best performance measurement on iDASH and MGH datasets with area under receiver operating characteristic curve (AUC) of 0.975 and 0.991, and F1 scores of 0.845 and 0.870, respectively. Considering better clinical interpretability, linear support vector machine-trained medical subdomain classifier using hybrid bag-of-words and clinically relevant UMLS concepts as the feature representation, with term frequency-inverse document frequency (tf-idf)-weighting, outperformed other shallow learning classifiers on iDASH and MGH datasets with AUC of 0.957 and 0.964, and F1 scores of 0.932 and 0.934 respectively. We trained classifiers on one dataset, applied to the other dataset and yielded the threshold of F1 score of 0.7 in classifiers for half of the medical subdomains we studied. Our study shows that a supervised learning-based NLP approach is useful to develop medical subdomain classifiers. The deep learning algorithm with distributed word representation yields better performance yet shallow learning algorithms with the word and concept representation achieves comparable performance with better clinical interpretability. Portable classifiers may also be used across datasets from different institutions.

Semiautomated tremor detection using a combined cross-correlation and neural network approach

USGS Publications Warehouse

Horstmann, Tobias; Harrington, Rebecca M.; Cochran, Elizabeth S.

2013-01-01

Despite observations of tectonic tremor in many locations around the globe, the emergent phase arrivals, low‒amplitude waveforms, and variable event durations make automatic detection a nontrivial task. In this study, we employ a new method to identify tremor in large data sets using a semiautomated technique. The method first reduces the data volume with an envelope cross‒correlation technique, followed by a Self‒Organizing Map (SOM) algorithm to identify and classify event types. The method detects tremor in an automated fashion after calibrating for a specific data set, hence we refer to it as being “semiautomated”. We apply the semiautomated detection algorithm to a newly acquired data set of waveforms from a temporary deployment of 13 seismometers near Cholame, California, from May 2010 to July 2011. We manually identify tremor events in a 3 week long test data set and compare to the SOM output and find a detection accuracy of 79.5%. Detection accuracy improves with increasing signal‒to‒noise ratios and number of available stations. We find detection completeness of 96% for tremor events with signal‒to‒noise ratios above 3 and optimal results when data from at least 10 stations are available. We compare the SOM algorithm to the envelope correlation method of Wech and Creager and find the SOM performs significantly better, at least for the data set examined here. Using the SOM algorithm, we detect 2606 tremor events with a cumulative signal duration of nearly 55 h during the 13 month deployment. Overall, the SOM algorithm is shown to be a flexible new method that utilizes characteristics of the waveforms to identify tremor from noise or other seismic signals.

Semiautomated tremor detection using a combined cross-correlation and neural network approach

NASA Astrophysics Data System (ADS)

Horstmann, T.; Harrington, R. M.; Cochran, E. S.

2013-09-01

Despite observations of tectonic tremor in many locations around the globe, the emergent phase arrivals, low-amplitude waveforms, and variable event durations make automatic detection a nontrivial task. In this study, we employ a new method to identify tremor in large data sets using a semiautomated technique. The method first reduces the data volume with an envelope cross-correlation technique, followed by a Self-Organizing Map (SOM) algorithm to identify and classify event types. The method detects tremor in an automated fashion after calibrating for a specific data set, hence we refer to it as being "semiautomated". We apply the semiautomated detection algorithm to a newly acquired data set of waveforms from a temporary deployment of 13 seismometers near Cholame, California, from May 2010 to July 2011. We manually identify tremor events in a 3 week long test data set and compare to the SOM output and find a detection accuracy of 79.5%. Detection accuracy improves with increasing signal-to-noise ratios and number of available stations. We find detection completeness of 96% for tremor events with signal-to-noise ratios above 3 and optimal results when data from at least 10 stations are available. We compare the SOM algorithm to the envelope correlation method of Wech and Creager and find the SOM performs significantly better, at least for the data set examined here. Using the SOM algorithm, we detect 2606 tremor events with a cumulative signal duration of nearly 55 h during the 13 month deployment. Overall, the SOM algorithm is shown to be a flexible new method that utilizes characteristics of the waveforms to identify tremor from noise or other seismic signals.

Effective and extensible feature extraction method using genetic algorithm-based frequency-domain feature search for epileptic EEG multiclassification

PubMed Central

Wen, Tingxi; Zhang, Zhongnan

2017-01-01

Abstract In this paper, genetic algorithm-based frequency-domain feature search (GAFDS) method is proposed for the electroencephalogram (EEG) analysis of epilepsy. In this method, frequency-domain features are first searched and then combined with nonlinear features. Subsequently, these features are selected and optimized to classify EEG signals. The extracted features are analyzed experimentally. The features extracted by GAFDS show remarkable independence, and they are superior to the nonlinear features in terms of the ratio of interclass distance and intraclass distance. Moreover, the proposed feature search method can search for features of instantaneous frequency in a signal after Hilbert transformation. The classification results achieved using these features are reasonable; thus, GAFDS exhibits good extensibility. Multiple classical classifiers (i.e., k-nearest neighbor, linear discriminant analysis, decision tree, AdaBoost, multilayer perceptron, and Naïve Bayes) achieve satisfactory classification accuracies by using the features generated by the GAFDS method and the optimized feature selection. The accuracies for 2-classification and 3-classification problems may reach up to 99% and 97%, respectively. Results of several cross-validation experiments illustrate that GAFDS is effective in the extraction of effective features for EEG classification. Therefore, the proposed feature selection and optimization model can improve classification accuracy. PMID:28489789

Effective and extensible feature extraction method using genetic algorithm-based frequency-domain feature search for epileptic EEG multiclassification.

PubMed

Wen, Tingxi; Zhang, Zhongnan

2017-05-01

In this paper, genetic algorithm-based frequency-domain feature search (GAFDS) method is proposed for the electroencephalogram (EEG) analysis of epilepsy. In this method, frequency-domain features are first searched and then combined with nonlinear features. Subsequently, these features are selected and optimized to classify EEG signals. The extracted features are analyzed experimentally. The features extracted by GAFDS show remarkable independence, and they are superior to the nonlinear features in terms of the ratio of interclass distance and intraclass distance. Moreover, the proposed feature search method can search for features of instantaneous frequency in a signal after Hilbert transformation. The classification results achieved using these features are reasonable; thus, GAFDS exhibits good extensibility. Multiple classical classifiers (i.e., k-nearest neighbor, linear discriminant analysis, decision tree, AdaBoost, multilayer perceptron, and Naïve Bayes) achieve satisfactory classification accuracies by using the features generated by the GAFDS method and the optimized feature selection. The accuracies for 2-classification and 3-classification problems may reach up to 99% and 97%, respectively. Results of several cross-validation experiments illustrate that GAFDS is effective in the extraction of effective features for EEG classification. Therefore, the proposed feature selection and optimization model can improve classification accuracy.

Application of Machine Learning Algorithms to the Study of Noise Artifacts in Gravitational-Wave Data

NASA Technical Reports Server (NTRS)

Biswas, Rahul; Blackburn, Lindy L.; Cao, Junwei; Essick, Reed; Hodge, Kari Alison; Katsavounidis, Erotokritos; Kim, Kyungmin; Young-Min, Kim; Le Bigot, Eric-Olivier; Lee, Chang-Hwan;

Unobtrusive Multi-Static Serial LiDAR Imager (UMSLI) First Generation Shape-Matching Based Classifier for 2D Contours

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

Cao, Zheng; Ouyang, Bing; Principe, Jose

A multi-static serial LiDAR system prototype was developed under DE-EE0006787 to detect, classify, and record interactions of marine life with marine hydrokinetic generation equipment. This software implements a shape-matching based classifier algorithm for the underwater automated detection of marine life for that system. In addition to applying shape descriptors, the algorithm also adopts information theoretical learning based affine shape registration, improving point correspondences found by shape descriptors as well as the final similarity measure.

Automatic identification of high impact articles in PubMed to support clinical decision making.

PubMed

Bian, Jiantao; Morid, Mohammad Amin; Jonnalagadda, Siddhartha; Luo, Gang; Del Fiol, Guilherme

2017-09-01

The practice of evidence-based medicine involves integrating the latest best available evidence into patient care decisions. Yet, critical barriers exist for clinicians' retrieval of evidence that is relevant for a particular patient from primary sources such as randomized controlled trials and meta-analyses. To help address those barriers, we investigated machine learning algorithms that find clinical studies with high clinical impact from PubMed®. Our machine learning algorithms use a variety of features including bibliometric features (e.g., citation count), social media attention, journal impact factors, and citation metadata. The algorithms were developed and evaluated with a gold standard composed of 502 high impact clinical studies that are referenced in 11 clinical evidence-based guidelines on the treatment of various diseases. We tested the following hypotheses: (1) our high impact classifier outperforms a state-of-the-art classifier based on citation metadata and citation terms, and PubMed's® relevance sort algorithm; and (2) the performance of our high impact classifier does not decrease significantly after removing proprietary features such as citation count. The mean top 20 precision of our high impact classifier was 34% versus 11% for the state-of-the-art classifier and 4% for PubMed's® relevance sort (p=0.009); and the performance of our high impact classifier did not decrease significantly after removing proprietary features (mean top 20 precision=34% vs. 36%; p=0.085). The high impact classifier, using features such as bibliometrics, social media attention and MEDLINE® metadata, outperformed previous approaches and is a promising alternative to identifying high impact studies for clinical decision support. Copyright © 2017 Elsevier Inc. All rights reserved.

An Efficient Statistical Computation Technique for Health Care Big Data using R

NASA Astrophysics Data System (ADS)

Sushma Rani, N.; Srinivasa Rao, P., Dr; Parimala, P.

2017-08-01

Due to the changes in living conditions and other factors many critical health related problems are arising. The diagnosis of the problem at earlier stages will increase the chances of survival and fast recovery. This reduces the time of recovery and the cost associated for the treatment. One such medical related issue is cancer and breast cancer has been identified as the second leading cause of cancer death. If detected in the early stage it can be cured. Once a patient is detected with breast cancer tumor, it should be classified whether it is cancerous or non-cancerous. So the paper uses k-nearest neighbors(KNN) algorithm which is one of the simplest machine learning algorithms and is an instance-based learning algorithm to classify the data. Day-to -day new records are added which leds to increase in the data to be classified and this tends to be big data problem. The algorithm is implemented in R whichis the most popular platform applied to machine learning algorithms for statistical computing. Experimentation is conducted by using various classification evaluation metric onvarious values of k. The results show that the KNN algorithm out performes better than existing models.

Automated target classification in high resolution dual frequency sonar imagery

NASA Astrophysics Data System (ADS)

Aridgides, Tom; Fernández, Manuel

2007-04-01

An improved computer-aided-detection / computer-aided-classification (CAD/CAC) processing string has been developed. The classified objects of 2 distinct strings are fused using the classification confidence values and their expansions as features, and using "summing" or log-likelihood-ratio-test (LLRT) based fusion rules. The utility of the overall processing strings and their fusion was demonstrated with new high-resolution dual frequency sonar imagery. Three significant fusion algorithm improvements were made. First, a nonlinear 2nd order (Volterra) feature LLRT fusion algorithm was developed. Second, a Box-Cox nonlinear feature LLRT fusion algorithm was developed. The Box-Cox transformation consists of raising the features to a to-be-determined power. Third, a repeated application of a subset feature selection / feature orthogonalization / Volterra feature LLRT fusion block was utilized. It was shown that cascaded Volterra feature LLRT fusion of the CAD/CAC processing strings outperforms summing, baseline single-stage Volterra and Box-Cox feature LLRT algorithms, yielding significant improvements over the best single CAD/CAC processing string results, and providing the capability to correctly call the majority of targets while maintaining a very low false alarm rate. Additionally, the robustness of cascaded Volterra feature fusion was demonstrated, by showing that the algorithm yields similar performance with the training and test sets.

"How do you know those particles are from cigarettes?": An algorithm to help differentiate second-hand tobacco smoke from background sources of household fine particulate matter.

PubMed

Dobson, Ruaraidh; Semple, Sean

2018-06-18

Second-hand smoke (SHS) at home is a target for public health interventions, such as air quality feedback interventions using low-cost particle monitors. However, these monitors also detect fine particles generated from non-SHS sources. The Dylos DC1700 reports particle counts in the coarse and fine size ranges. As tobacco smoke produces far more fine particles than coarse ones, and tobacco is generally the greatest source of particulate pollution in a smoking home, the ratio of coarse to fine particles may provide a useful method to identify the presence of SHS in homes. An algorithm was developed to differentiate smoking from smoke-free homes. Particle concentration data from 116 smoking homes and 25 non-smoking homes were used to test this algorithm. The algorithm correctly classified the smoking status of 135 of the 141 homes (96%), comparing favourably with a test of mean mass concentration. Applying this algorithm to Dylos particle count measurements may help identify the presence of SHS in homes or other indoor environments. Future research should adapt it to detect individual smoking periods within a 24 h or longer measurement period. Copyright © 2018 Elsevier Inc. All rights reserved.

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

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

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

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

Identification of Anisomerous Motor Imagery EEG Signals Based on Complex Algorithms

PubMed Central

Zhang, Zhiwen; Duan, Feng; Zhou, Xin; Meng, Zixuan

2017-01-01

Motor imagery (MI) electroencephalograph (EEG) signals are widely applied in brain-computer interface (BCI). However, classified MI states are limited, and their classification accuracy rates are low because of the characteristics of nonlinearity and nonstationarity. This study proposes a novel MI pattern recognition system that is based on complex algorithms for classifying MI EEG signals. In electrooculogram (EOG) artifact preprocessing, band-pass filtering is performed to obtain the frequency band of MI-related signals, and then, canonical correlation analysis (CCA) combined with wavelet threshold denoising (WTD) is used for EOG artifact preprocessing. We propose a regularized common spatial pattern (R-CSP) algorithm for EEG feature extraction by incorporating the principle of generic learning. A new classifier combining the K-nearest neighbor (KNN) and support vector machine (SVM) approaches is used to classify four anisomerous states, namely, imaginary movements with the left hand, right foot, and right shoulder and the resting state. The highest classification accuracy rate is 92.5%, and the average classification accuracy rate is 87%. The proposed complex algorithm identification method can significantly improve the identification rate of the minority samples and the overall classification performance. PMID:28874909

Extraction and classification of 3D objects from volumetric CT data

NASA Astrophysics Data System (ADS)

Song, Samuel M.; Kwon, Junghyun; Ely, Austin; Enyeart, John; Johnson, Chad; Lee, Jongkyu; Kim, Namho; Boyd, Douglas P.

2016-05-01

We propose an Automatic Threat Detection (ATD) algorithm for Explosive Detection System (EDS) using our multistage Segmentation Carving (SC) followed by Support Vector Machine (SVM) classifier. The multi-stage Segmentation and Carving (SC) step extracts all suspect 3-D objects. The feature vector is then constructed for all extracted objects and the feature vector is classified by the Support Vector Machine (SVM) previously learned using a set of ground truth threat and benign objects. The learned SVM classifier has shown to be effective in classification of different types of threat materials. The proposed ATD algorithm robustly deals with CT data that are prone to artifacts due to scatter, beam hardening as well as other systematic idiosyncrasies of the CT data. Furthermore, the proposed ATD algorithm is amenable for including newly emerging threat materials as well as for accommodating data from newly developing sensor technologies. Efficacy of the proposed ATD algorithm with the SVM classifier is demonstrated by the Receiver Operating Characteristics (ROC) curve that relates Probability of Detection (PD) as a function of Probability of False Alarm (PFA). The tests performed using CT data of passenger bags shows excellent performance characteristics.

Classifying spatially heterogeneous wetland communities using machine learning algorithms and spectral and textural features.

PubMed

Szantoi, Zoltan; Escobedo, Francisco J; Abd-Elrahman, Amr; Pearlstine, Leonard; Dewitt, Bon; Smith, Scot

2015-05-01

Mapping of wetlands (marsh vs. swamp vs. upland) is a common remote sensing application.Yet, discriminating between similar freshwater communities such as graminoid/sedge fromremotely sensed imagery is more difficult. Most of this activity has been performed using medium to low resolution imagery. There are only a few studies using highspatial resolutionimagery and machine learning image classification algorithms for mapping heterogeneouswetland plantcommunities. This study addresses this void by analyzing whether machine learning classifierssuch as decisiontrees (DT) and artificial neural networks (ANN) can accurately classify graminoid/sedgecommunities usinghigh resolution aerial imagery and image texture data in the Everglades National Park, Florida.In addition tospectral bands, the normalized difference vegetation index, and first- and second-order texturefeatures derivedfrom the near-infrared band were analyzed. Classifier accuracies were assessed using confusiontablesand the calculated kappa coefficients of the resulting maps. The results indicated that an ANN(multilayerperceptron based on backpropagation) algorithm produced a statistically significantly higheraccuracy(82.04%) than the DT (QUEST) algorithm (80.48%) or the maximum likelihood (80.56%)classifier (α<0.05). Findings show that using multiple window sizes provided the best results. First-ordertexture featuresalso provided computational advantages and results that were not significantly different fromthose usingsecond-order texture features.

Spectral classifier design with ensemble classifiers and misclassification-rejection: application to elastic-scattering spectroscopy for detection of colonic neoplasia.

PubMed

Rodriguez-Diaz, Eladio; Castanon, David A; Singh, Satish K; Bigio, Irving J

2011-06-01

Optical spectroscopy has shown potential as a real-time, in vivo, diagnostic tool for identifying neoplasia during endoscopy. We present the development of a diagnostic algorithm to classify elastic-scattering spectroscopy (ESS) spectra as either neoplastic or non-neoplastic. The algorithm is based on pattern recognition methods, including ensemble classifiers, in which members of the ensemble are trained on different regions of the ESS spectrum, and misclassification-rejection, where the algorithm identifies and refrains from classifying samples that are at higher risk of being misclassified. These "rejected" samples can be reexamined by simply repositioning the probe to obtain additional optical readings or ultimately by sending the polyp for histopathological assessment, as per standard practice. Prospective validation using separate training and testing sets result in a baseline performance of sensitivity = .83, specificity = .79, using the standard framework of feature extraction (principal component analysis) followed by classification (with linear support vector machines). With the developed algorithm, performance improves to Se ∼ 0.90, Sp ∼ 0.90, at a cost of rejecting 20-33% of the samples. These results are on par with a panel of expert pathologists. For colonoscopic prevention of colorectal cancer, our system could reduce biopsy risk and cost, obviate retrieval of non-neoplastic polyps, decrease procedure time, and improve assessment of cancer risk.

Spectral classifier design with ensemble classifiers and misclassification-rejection: application to elastic-scattering spectroscopy for detection of colonic neoplasia

PubMed Central

Rodriguez-Diaz, Eladio; Castanon, David A.; Singh, Satish K.; Bigio, Irving J.

2011-01-01

Optical spectroscopy has shown potential as a real-time, in vivo, diagnostic tool for identifying neoplasia during endoscopy. We present the development of a diagnostic algorithm to classify elastic-scattering spectroscopy (ESS) spectra as either neoplastic or non-neoplastic. The algorithm is based on pattern recognition methods, including ensemble classifiers, in which members of the ensemble are trained on different regions of the ESS spectrum, and misclassification-rejection, where the algorithm identifies and refrains from classifying samples that are at higher risk of being misclassified. These “rejected” samples can be reexamined by simply repositioning the probe to obtain additional optical readings or ultimately by sending the polyp for histopathological assessment, as per standard practice. Prospective validation using separate training and testing sets result in a baseline performance of sensitivity = .83, specificity = .79, using the standard framework of feature extraction (principal component analysis) followed by classification (with linear support vector machines). With the developed algorithm, performance improves to Se ∼ 0.90, Sp ∼ 0.90, at a cost of rejecting 20–33% of the samples. These results are on par with a panel of expert pathologists. For colonoscopic prevention of colorectal cancer, our system could reduce biopsy risk and cost, obviate retrieval of non-neoplastic polyps, decrease procedure time, and improve assessment of cancer risk. PMID:21721830

Classifying Imbalanced Data Streams via Dynamic Feature Group Weighting with Importance Sampling.

PubMed

Wu, Ke; Edwards, Andrea; Fan, Wei; Gao, Jing; Zhang, Kun

2014-04-01

Data stream classification and imbalanced data learning are two important areas of data mining research. Each has been well studied to date with many interesting algorithms developed. However, only a few approaches reported in literature address the intersection of these two fields due to their complex interplay. In this work, we proposed an importance sampling driven, dynamic feature group weighting framework (DFGW-IS) for classifying data streams of imbalanced distribution. Two components are tightly incorporated into the proposed approach to address the intrinsic characteristics of concept-drifting, imbalanced streaming data. Specifically, the ever-evolving concepts are tackled by a weighted ensemble trained on a set of feature groups with each sub-classifier (i.e. a single classifier or an ensemble) weighed by its discriminative power and stable level. The un-even class distribution, on the other hand, is typically battled by the sub-classifier built in a specific feature group with the underlying distribution rebalanced by the importance sampling technique. We derived the theoretical upper bound for the generalization error of the proposed algorithm. We also studied the empirical performance of our method on a set of benchmark synthetic and real world data, and significant improvement has been achieved over the competing algorithms in terms of standard evaluation metrics and parallel running time. Algorithm implementations and datasets are available upon request.

Proposed hybrid-classifier ensemble algorithm to map snow cover area

NASA Astrophysics Data System (ADS)

Nijhawan, Rahul; Raman, Balasubramanian; Das, Josodhir

2018-01-01

Metaclassification ensemble approach is known to improve the prediction performance of snow-covered area. The methodology adopted in this case is based on neural network along with four state-of-art machine learning algorithms: support vector machine, artificial neural networks, spectral angle mapper, K-mean clustering, and a snow index: normalized difference snow index. An AdaBoost ensemble algorithm related to decision tree for snow-cover mapping is also proposed. According to available literature, these methods have been rarely used for snow-cover mapping. Employing the above techniques, a study was conducted for Raktavarn and Chaturangi Bamak glaciers, Uttarakhand, Himalaya using multispectral Landsat 7 ETM+ (enhanced thematic mapper) image. The study also compares the results with those obtained from statistical combination methods (majority rule and belief functions) and accuracies of individual classifiers. Accuracy assessment is performed by computing the quantity and allocation disagreement, analyzing statistic measures (accuracy, precision, specificity, AUC, and sensitivity) and receiver operating characteristic curves. A total of 225 combinations of parameters for individual classifiers were trained and tested on the dataset and results were compared with the proposed approach. It was observed that the proposed methodology produced the highest classification accuracy (95.21%), close to (94.01%) that was produced by the proposed AdaBoost ensemble algorithm. From the sets of observations, it was concluded that the ensemble of classifiers produced better results compared to individual classifiers.

Seizures in the elderly: development and validation of a diagnostic algorithm.

PubMed

Dupont, Sophie; Verny, Marc; Harston, Sandrine; Cartz-Piver, Leslie; Schück, Stéphane; Martin, Jennifer; Puisieux, François; Alecu, Cosmin; Vespignani, Hervé; Marchal, Cécile; Derambure, Philippe

2010-05-01

Seizures are frequent in the elderly, but their diagnosis can be challenging. The objective of this work was to develop and validate an expert-based algorithm for the diagnosis of seizures in elderly people. A multidisciplinary group of neurologists and geriatricians developed a diagnostic algorithm using a combination of selected clinical, electroencephalographical and radiological criteria. The algorithm was validated by multicentre retrospective analysis of data of patients referred for specific symptoms and classified by the experts as epileptic patients or not. The algorithm was applied to all the patients, and the diagnosis provided by the algorithm was compared to the clinical diagnosis of the experts. Twenty-nine clinical, electroencephalographical and radiological criteria were selected for the algorithm. According to criteria combination, seizures were classified in four levels of diagnosis: certain, highly probable, possible or improbable. To validate the algorithm, the medical records of 269 elderly patients were analyzed (138 with epileptic seizures, 131 with non-epileptic manifestations). Patients were mainly referred for a transient focal deficit (40%), confusion (38%), unconsciousness (27%). The algorithm best classified certain and probable seizures versus possible and improbable seizures, with 86.2% sensitivity and 67.2% specificity. Using logistical regression, 2 simplified models were developed, the first with 13 criteria (Se 85.5%, Sp 90.1%), and the second with 7 criteria only (Se 84.8%, Sp 88.6%). In conclusion, the present study validated the use of a revised diagnostic algorithm to help diagnosis epileptic seizures in the elderly. A prospective study is planned to further validate this algorithm. Copyright 2010 Elsevier B.V. All rights reserved.

Combination of mass spectrometry-based targeted lipidomics and supervised machine learning algorithms in detecting adulterated admixtures of white rice.

PubMed

Lim, Dong Kyu; Long, Nguyen Phuoc; Mo, Changyeun; Dong, Ziyuan; Cui, Lingmei; Kim, Giyoung; Kwon, Sung Won

2017-10-01

The mixing of extraneous ingredients with original products is a common adulteration practice in food and herbal medicines. In particular, authenticity of white rice and its corresponding blended products has become a key issue in food industry. Accordingly, our current study aimed to develop and evaluate a novel discrimination method by combining targeted lipidomics with powerful supervised learning methods, and eventually introduce a platform to verify the authenticity of white rice. A total of 30 cultivars were collected, and 330 representative samples of white rice from Korea and China as well as seven mixing ratios were examined. Random forests (RF), support vector machines (SVM) with a radial basis function kernel, C5.0, model averaged neural network, and k-nearest neighbor classifiers were used for the classification. We achieved desired results, and the classifiers effectively differentiated white rice from Korea to blended samples with high prediction accuracy for the contamination ratio as low as five percent. In addition, RF and SVM classifiers were generally superior to and more robust than the other techniques. Our approach demonstrated that the relative differences in lysoGPLs can be successfully utilized to detect the adulterated mixing of white rice originating from different countries. In conclusion, the present study introduces a novel and high-throughput platform that can be applied to authenticate adulterated admixtures from original white rice samples. Copyright © 2017 Elsevier Ltd. All rights reserved.

Dementia diagnoses from clinical and neuropsychological data compared: the Cache County study.

PubMed

Tschanz, J T; Welsh-Bohmer, K A; Skoog, I; West, N; Norton, M C; Wyse, B W; Nickles, R; Breitner, J C

2000-03-28

To validate a neuropsychological algorithm for dementia diagnosis. We developed a neuropsychological algorithm in a sample of 1,023 elderly residents of Cache County, UT. We compared algorithmic and clinical dementia diagnoses both based on DSM-III-R criteria. The algorithm diagnosed dementia when there was impairment in memory and at least one other cognitive domain. We also tested a variant of the algorithm that incorporated functional measures that were based on structured informant reports. Of 1,023 participants, 87% could be classified by the basic algorithm, 94% when functional measures were considered. There was good concordance between basic psychometric and clinical diagnoses (79% agreement, kappa = 0.57). This improved after incorporating functional measures (90% agreement, kappa = 0.76). Neuropsychological algorithms may reasonably classify individuals on dementia status across a range of severity levels and ages and may provide a useful adjunct to clinical diagnoses in population studies.

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.

Applying Cost-Sensitive Extreme Learning Machine and Dissimilarity Integration to Gene Expression Data Classification.

PubMed

Liu, Yanqiu; Lu, Huijuan; Yan, Ke; Xia, Haixia; An, Chunlin

2016-01-01

Embedding cost-sensitive factors into the classifiers increases the classification stability and reduces the classification costs for classifying high-scale, redundant, and imbalanced datasets, such as the gene expression data. In this study, we extend our previous work, that is, Dissimilar ELM (D-ELM), by introducing misclassification costs into the classifier. We name the proposed algorithm as the cost-sensitive D-ELM (CS-D-ELM). Furthermore, we embed rejection cost into the CS-D-ELM to increase the classification stability of the proposed algorithm. Experimental results show that the rejection cost embedded CS-D-ELM algorithm effectively reduces the average and overall cost of the classification process, while the classification accuracy still remains competitive. The proposed method can be extended to classification problems of other redundant and imbalanced data.

Comparison of artificial intelligence classifiers for SIP attack data

NASA Astrophysics Data System (ADS)

Safarik, Jakub; Slachta, Jiri

2016-05-01

Honeypot application is a source of valuable data about attacks on the network. We run several SIP honeypots in various computer networks, which are separated geographically and logically. Each honeypot runs on public IP address and uses standard SIP PBX ports. All information gathered via honeypot is periodically sent to the centralized server. This server classifies all attack data by neural network algorithm. The paper describes optimizations of a neural network classifier, which lower the classification error. The article contains the comparison of two neural network algorithm used for the classification of validation data. The first is the original implementation of the neural network described in recent work; the second neural network uses further optimizations like input normalization or cross-entropy cost function. We also use other implementations of neural networks and machine learning classification algorithms. The comparison test their capabilities on validation data to find the optimal classifier. The article result shows promise for further development of an accurate SIP attack classification engine.

Statistical process control using optimized neural networks: a case study.

PubMed

Addeh, Jalil; Ebrahimzadeh, Ata; Azarbad, Milad; Ranaee, Vahid

2014-09-01

The most common statistical process control (SPC) tools employed for monitoring process changes are control charts. A control chart demonstrates that the process has altered by generating an out-of-control signal. This study investigates the design of an accurate system for the control chart patterns (CCPs) recognition in two aspects. First, an efficient system is introduced that includes two main modules: feature extraction module and classifier module. In the feature extraction module, a proper set of shape features and statistical feature are proposed as the efficient characteristics of the patterns. In the classifier module, several neural networks, such as multilayer perceptron, probabilistic neural network and radial basis function are investigated. Based on an experimental study, the best classifier is chosen in order to recognize the CCPs. Second, a hybrid heuristic recognition system is introduced based on cuckoo optimization algorithm (COA) algorithm to improve the generalization performance of the classifier. The simulation results show that the proposed algorithm has high recognition accuracy. Copyright © 2013 ISA. Published by Elsevier Ltd. All rights reserved.

Fluorescence intensity positivity classification of Hep-2 cells images using fuzzy logic

NASA Astrophysics Data System (ADS)

Sazali, Dayang Farzana Abang; Janier, Josefina Barnachea; May, Zazilah Bt.

2014-10-01

Indirect Immunofluorescence (IIF) is a good standard used for antinuclear autoantibody (ANA) test using Hep-2 cells to determine specific diseases. Different classifier algorithm methods have been proposed in previous works however, there still no valid set as a standard to classify the fluorescence intensity. This paper presents the use of fuzzy logic to classify the fluorescence intensity and to determine the positivity of the Hep-2 cell serum samples. The fuzzy algorithm involves the image pre-processing by filtering the noises and smoothen the image, converting the red, green and blue (RGB) color space of images to luminosity layer, chromaticity layer "a" and "b" (LAB) color space where the mean value of the lightness and chromaticity layer "a" was extracted and classified by using fuzzy logic algorithm based on the standard score ranges of antinuclear autoantibody (ANA) fluorescence intensity. Using 100 data sets of positive and intermediate fluorescence intensity for testing the performance measurements, the fuzzy logic obtained an accuracy of intermediate and positive class as 85% and 87% respectively.

Ensemble Methods for Classification of Physical Activities from Wrist Accelerometry.

PubMed

Chowdhury, Alok Kumar; Tjondronegoro, Dian; Chandran, Vinod; Trost, Stewart G

2017-09-01

To investigate whether the use of ensemble learning algorithms improve physical activity recognition accuracy compared to the single classifier algorithms, and to compare the classification accuracy achieved by three conventional ensemble machine learning methods (bagging, boosting, random forest) and a custom ensemble model comprising four algorithms commonly used for activity recognition (binary decision tree, k nearest neighbor, support vector machine, and neural network). The study used three independent data sets that included wrist-worn accelerometer data. For each data set, a four-step classification framework consisting of data preprocessing, feature extraction, normalization and feature selection, and classifier training and testing was implemented. For the custom ensemble, decisions from the single classifiers were aggregated using three decision fusion methods: weighted majority vote, naïve Bayes combination, and behavior knowledge space combination. Classifiers were cross-validated using leave-one subject out cross-validation and compared on the basis of average F1 scores. In all three data sets, ensemble learning methods consistently outperformed the individual classifiers. Among the conventional ensemble methods, random forest models provided consistently high activity recognition; however, the custom ensemble model using weighted majority voting demonstrated the highest classification accuracy in two of the three data sets. Combining multiple individual classifiers using conventional or custom ensemble learning methods can improve activity recognition accuracy from wrist-worn accelerometer data.

Ensemble Clustering Classification compete SVM and One-Class classifiers applied on plant microRNAs Data.

PubMed

Yousef, Malik; Khalifa, Waleed; AbedAllah, Loai

2016-12-22

The performance of many learning and data mining algorithms depends critically on suitable metrics to assess efficiency over the input space. Learning a suitable metric from examples may, therefore, be the key to successful application of these algorithms. We have demonstrated that the k-nearest neighbor (kNN) classification can be significantly improved by learning a distance metric from labeled examples. The clustering ensemble is used to define the distance between points in respect to how they co-cluster. This distance is then used within the framework of the kNN algorithm to define a classifier named ensemble clustering kNN classifier (EC-kNN). In many instances in our experiments we achieved highest accuracy while SVM failed to perform as well. In this study, we compare the performance of a two-class classifier using EC-kNN with different one-class and two-class classifiers. The comparison was applied to seven different plant microRNA species considering eight feature selection methods. In this study, the averaged results show that ECkNN outperforms all other methods employed here and previously published results for the same data. In conclusion, this study shows that the chosen classifier shows high performance when the distance metric is carefully chosen.

Ensemble Clustering Classification Applied to Competing SVM and One-Class Classifiers Exemplified by Plant MicroRNAs Data.

PubMed

Yousef, Malik; Khalifa, Waleed; AbdAllah, Loai

2016-12-01

The performance of many learning and data mining algorithms depends critically on suitable metrics to assess efficiency over the input space. Learning a suitable metric from examples may, therefore, be the key to successful application of these algorithms. We have demonstrated that the k-nearest neighbor (kNN) classification can be significantly improved by learning a distance metric from labeled examples. The clustering ensemble is used to define the distance between points in respect to how they co-cluster. This distance is then used within the framework of the kNN algorithm to define a classifier named ensemble clustering kNN classifier (EC-kNN). In many instances in our experiments we achieved highest accuracy while SVM failed to perform as well. In this study, we compare the performance of a two-class classifier using EC-kNN with different one-class and two-class classifiers. The comparison was applied to seven different plant microRNA species considering eight feature selection methods. In this study, the averaged results show that EC-kNN outperforms all other methods employed here and previously published results for the same data. In conclusion, this study shows that the chosen classifier shows high performance when the distance metric is carefully chosen.

Learnable despeckling framework for optical coherence tomography images

NASA Astrophysics Data System (ADS)

Adabi, Saba; Rashedi, Elaheh; Clayton, Anne; Mohebbi-Kalkhoran, Hamed; Chen, Xue-wen; Conforto, Silvia; Nasiriavanaki, Mohammadreza

2018-01-01

Optical coherence tomography (OCT) is a prevalent, interferometric, high-resolution imaging method with broad biomedical applications. Nonetheless, OCT images suffer from an artifact called speckle, which degrades the image quality. Digital filters offer an opportunity for image improvement in clinical OCT devices, where hardware modification to enhance images is expensive. To reduce speckle, a wide variety of digital filters have been proposed; selecting the most appropriate filter for an OCT image/image set is a challenging decision, especially in dermatology applications of OCT where a different variety of tissues are imaged. To tackle this challenge, we propose an expandable learnable despeckling framework, we call LDF. LDF decides which speckle reduction algorithm is most effective on a given image by learning a figure of merit (FOM) as a single quantitative image assessment measure. LDF is learnable, which means when implemented on an OCT machine, each given image/image set is retrained and its performance is improved. Also, LDF is expandable, meaning that any despeckling algorithm can easily be added to it. The architecture of LDF includes two main parts: (i) an autoencoder neural network and (ii) filter classifier. The autoencoder learns the FOM based on several quality assessment measures obtained from the OCT image including signal-to-noise ratio, contrast-to-noise ratio, equivalent number of looks, edge preservation index, and mean structural similarity index. Subsequently, the filter classifier identifies the most efficient filter from the following categories: (a) sliding window filters including median, mean, and symmetric nearest neighborhood, (b) adaptive statistical-based filters including Wiener, homomorphic Lee, and Kuwahara, and (c) edge preserved patch or pixel correlation-based filters including nonlocal mean, total variation, and block matching three-dimensional filtering.

Beyond where to how: a machine learning approach for sensing mobility contexts using smartphone sensors.

PubMed

Guinness, Robert E

2015-04-28

This paper presents the results of research on the use of smartphone sensors (namely, GPS and accelerometers), geospatial information (points of interest, such as bus stops and train stations) and machine learning (ML) to sense mobility contexts. Our goal is to develop techniques to continuously and automatically detect a smartphone user's mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time (<5 s). We investigated a wide range of supervised learning techniques for classification, including decision trees (DT), support vector machines (SVM), naive Bayes classifiers (NB), Bayesian networks (BN), logistic regression (LR), artificial neural networks (ANN) and several instance-based classifiers (KStar, LWLand IBk). Applying ten-fold cross-validation, the best performers in terms of correct classification rate (i.e., recall) were DT (96.5%), BN (90.9%), LWL (95.5%) and KStar (95.6%). In particular, the DT-algorithm RandomForest exhibited the best overall performance. After a feature selection process for a subset of algorithms, the performance was improved slightly. Furthermore, after tuning the parameters of RandomForest, performance improved to above 97.5%. Lastly, we measured the computational complexity of the classifiers, in terms of central processing unit (CPU) time needed for classification, to provide a rough comparison between the algorithms in terms of battery usage requirements. As a result, the classifiers can be ranked from lowest to highest complexity (i.e., computational cost) as follows: SVM, ANN, LR, BN, DT, NB, IBk, LWL and KStar. The instance-based classifiers take considerably more computational time than the non-instance-based classifiers, whereas the slowest non-instance-based classifier (NB) required about five-times the amount of CPU time as the fastest classifier (SVM). The above results suggest that DT algorithms are excellent candidates for detecting mobility contexts in smartphones, both in terms of performance and computational complexity.

Beyond Where to How: A Machine Learning Approach for Sensing Mobility Contexts Using Smartphone Sensors †

PubMed Central

Guinness, Robert E.

2015-01-01

This paper presents the results of research on the use of smartphone sensors (namely, GPS and accelerometers), geospatial information (points of interest, such as bus stops and train stations) and machine learning (ML) to sense mobility contexts. Our goal is to develop techniques to continuously and automatically detect a smartphone user's mobility activities, including walking, running, driving and using a bus or train, in real-time or near-real-time (<5 s). We investigated a wide range of supervised learning techniques for classification, including decision trees (DT), support vector machines (SVM), naive Bayes classifiers (NB), Bayesian networks (BN), logistic regression (LR), artificial neural networks (ANN) and several instance-based classifiers (KStar, LWLand IBk). Applying ten-fold cross-validation, the best performers in terms of correct classification rate (i.e., recall) were DT (96.5%), BN (90.9%), LWL (95.5%) and KStar (95.6%). In particular, the DT-algorithm RandomForest exhibited the best overall performance. After a feature selection process for a subset of algorithms, the performance was improved slightly. Furthermore, after tuning the parameters of RandomForest, performance improved to above 97.5%. Lastly, we measured the computational complexity of the classifiers, in terms of central processing unit (CPU) time needed for classification, to provide a rough comparison between the algorithms in terms of battery usage requirements. As a result, the classifiers can be ranked from lowest to highest complexity (i.e., computational cost) as follows: SVM, ANN, LR, BN, DT, NB, IBk, LWL and KStar. The instance-based classifiers take considerably more computational time than the non-instance-based classifiers, whereas the slowest non-instance-based classifier (NB) required about five-times the amount of CPU time as the fastest classifier (SVM). The above results suggest that DT algorithms are excellent candidates for detecting mobility contexts in smartphones, both in terms of performance and computational complexity. PMID:25928060

Toward Improving Electrocardiogram (ECG) Biometric Verification using Mobile Sensors: A Two-Stage Classifier Approach

PubMed Central

Tan, Robin; Perkowski, Marek

2017-01-01

Electrocardiogram (ECG) signals sensed from mobile devices pertain the potential for biometric identity recognition applicable in remote access control systems where enhanced data security is demanding. In this study, we propose a new algorithm that consists of a two-stage classifier combining random forest and wavelet distance measure through a probabilistic threshold schema, to improve the effectiveness and robustness of a biometric recognition system using ECG data acquired from a biosensor integrated into mobile devices. The proposed algorithm is evaluated using a mixed dataset from 184 subjects under different health conditions. The proposed two-stage classifier achieves a total of 99.52% subject verification accuracy, better than the 98.33% accuracy from random forest alone and 96.31% accuracy from wavelet distance measure algorithm alone. These results demonstrate the superiority of the proposed algorithm for biometric identification, hence supporting its practicality in areas such as cloud data security, cyber-security or remote healthcare systems. PMID:28230745

Toward Improving Electrocardiogram (ECG) Biometric Verification using Mobile Sensors: A Two-Stage Classifier Approach.

PubMed

Tan, Robin; Perkowski, Marek

2017-02-20

Electrocardiogram (ECG) signals sensed from mobile devices pertain the potential for biometric identity recognition applicable in remote access control systems where enhanced data security is demanding. In this study, we propose a new algorithm that consists of a two-stage classifier combining random forest and wavelet distance measure through a probabilistic threshold schema, to improve the effectiveness and robustness of a biometric recognition system using ECG data acquired from a biosensor integrated into mobile devices. The proposed algorithm is evaluated using a mixed dataset from 184 subjects under different health conditions. The proposed two-stage classifier achieves a total of 99.52% subject verification accuracy, better than the 98.33% accuracy from random forest alone and 96.31% accuracy from wavelet distance measure algorithm alone. These results demonstrate the superiority of the proposed algorithm for biometric identification, hence supporting its practicality in areas such as cloud data security, cyber-security or remote healthcare systems.

Leukocyte Recognition Using EM-Algorithm

NASA Astrophysics Data System (ADS)

Colunga, Mario Chirinos; Siordia, Oscar Sánchez; Maybank, Stephen J.

This document describes a method for classifying images of blood cells. Three different classes of cells are used: Band Neutrophils, Eosinophils and Lymphocytes. The image pattern is projected down to a lower dimensional sub space using PCA; the probability density function for each class is modeled with a Gaussian mixture using the EM-Algorithm. A new cell image is classified using the maximum a posteriori decision rule.

Comparison of machine learning and semi-quantification algorithms for (I123)FP-CIT classification: the beginning of the end for semi-quantification?

PubMed

Taylor, Jonathan Christopher; Fenner, John Wesley

2017-11-29

Semi-quantification methods are well established in the clinic for assisted reporting of (I123) Ioflupane images. Arguably, these are limited diagnostic tools. Recent research has demonstrated the potential for improved classification performance offered by machine learning algorithms. A direct comparison between methods is required to establish whether a move towards widespread clinical adoption of machine learning algorithms is justified. This study compared three machine learning algorithms with that of a range of semi-quantification methods, using the Parkinson's Progression Markers Initiative (PPMI) research database and a locally derived clinical database for validation. Machine learning algorithms were based on support vector machine classifiers with three different sets of features: Voxel intensities Principal components of image voxel intensities Striatal binding radios from the putamen and caudate. Semi-quantification methods were based on striatal binding ratios (SBRs) from both putamina, with and without consideration of the caudates. Normal limits for the SBRs were defined through four different methods: Minimum of age-matched controls Mean minus 1/1.5/2 standard deviations from age-matched controls Linear regression of normal patient data against age (minus 1/1.5/2 standard errors) Selection of the optimum operating point on the receiver operator characteristic curve from normal and abnormal training data Each machine learning and semi-quantification technique was evaluated with stratified, nested 10-fold cross-validation, repeated 10 times. The mean accuracy of the semi-quantitative methods for classification of local data into Parkinsonian and non-Parkinsonian groups varied from 0.78 to 0.87, contrasting with 0.89 to 0.95 for classifying PPMI data into healthy controls and Parkinson's disease groups. The machine learning algorithms gave mean accuracies between 0.88 to 0.92 and 0.95 to 0.97 for local and PPMI data respectively. Classification performance was lower for the local database than the research database for both semi-quantitative and machine learning algorithms. However, for both databases, the machine learning methods generated equal or higher mean accuracies (with lower variance) than any of the semi-quantification approaches. The gain in performance from using machine learning algorithms as compared to semi-quantification was relatively small and may be insufficient, when considered in isolation, to offer significant advantages in the clinical context.

Cloud classification from satellite data using a fuzzy sets algorithm: A polar example

NASA Technical Reports Server (NTRS)

Key, J. R.; Maslanik, J. A.; Barry, R. G.

1988-01-01

Where spatial boundaries between phenomena are diffuse, classification methods which construct mutually exclusive clusters seem inappropriate. The Fuzzy c-means (FCM) algorithm assigns each observation to all clusters, with membership values as a function of distance to the cluster center. The FCM algorithm is applied to AVHRR data for the purpose of classifying polar clouds and surfaces. Careful analysis of the fuzzy sets can provide information on which spectral channels are best suited to the classification of particular features, and can help determine likely areas of misclassification. General agreement in the resulting classes and cloud fraction was found between the FCM algorithm, a manual classification, and an unsupervised maximum likelihood classifier.

Ensemble Classifiers for Predicting HIV-1 Resistance from Three Rule-Based Genotypic Resistance Interpretation Systems.

PubMed

Raposo, Letícia M; Nobre, Flavio F

2017-08-30

Resistance to antiretrovirals (ARVs) is a major problem faced by HIV-infected individuals. Different rule-based algorithms were developed to infer HIV-1 susceptibility to antiretrovirals from genotypic data. However, there is discordance between them, resulting in difficulties for clinical decisions about which treatment to use. Here, we developed ensemble classifiers integrating three interpretation algorithms: Agence Nationale de Recherche sur le SIDA (ANRS), Rega, and the genotypic resistance interpretation system from Stanford HIV Drug Resistance Database (HIVdb). Three approaches were applied to develop a classifier with a single resistance profile: stacked generalization, a simple plurality vote scheme and the selection of the interpretation system with the best performance. The strategies were compared with the Friedman's test and the performance of the classifiers was evaluated using the F-measure, sensitivity and specificity values. We found that the three strategies had similar performances for the selected antiretrovirals. For some cases, the stacking technique with naïve Bayes as the learning algorithm showed a statistically superior F-measure. This study demonstrates that ensemble classifiers can be an alternative tool for clinical decision-making since they provide a single resistance profile from the most commonly used resistance interpretation systems.

Enhancement web proxy cache performance using Wrapper Feature Selection methods with NB and J48

NASA Astrophysics Data System (ADS)

Mahmoud Al-Qudah, Dua'a.; Funke Olanrewaju, Rashidah; Wong Azman, Amelia

2017-11-01

Web proxy cache technique reduces response time by storing a copy of pages between client and server sides. If requested pages are cached in the proxy, there is no need to access the server. Due to the limited size and excessive cost of cache compared to the other storages, cache replacement algorithm is used to determine evict page when the cache is full. On the other hand, the conventional algorithms for replacement such as Least Recently Use (LRU), First in First Out (FIFO), Least Frequently Use (LFU), Randomized Policy etc. may discard important pages just before use. Furthermore, using conventional algorithm cannot be well optimized since it requires some decision to intelligently evict a page before replacement. Hence, most researchers propose an integration among intelligent classifiers and replacement algorithm to improves replacement algorithms performance. This research proposes using automated wrapper feature selection methods to choose the best subset of features that are relevant and influence classifiers prediction accuracy. The result present that using wrapper feature selection methods namely: Best First (BFS), Incremental Wrapper subset selection(IWSS)embedded NB and particle swarm optimization(PSO)reduce number of features and have a good impact on reducing computation time. Using PSO enhance NB classifier accuracy by 1.1%, 0.43% and 0.22% over using NB with all features, using BFS and using IWSS embedded NB respectively. PSO rises J48 accuracy by 0.03%, 1.91 and 0.04% over using J48 classifier with all features, using IWSS-embedded NB and using BFS respectively. While using IWSS embedded NB fastest NB and J48 classifiers much more than BFS and PSO. However, it reduces computation time of NB by 0.1383 and reduce computation time of J48 by 2.998.

Fuzzy hidden Markov chains segmentation for volume determination and quantitation in PET.

PubMed

Hatt, M; Lamare, F; Boussion, N; Turzo, A; Collet, C; Salzenstein, F; Roux, C; Jarritt, P; Carson, K; Cheze-Le Rest, C; Visvikis, D

2007-06-21

Accurate volume of interest (VOI) estimation in PET is crucial in different oncology applications such as response to therapy evaluation and radiotherapy treatment planning. The objective of our study was to evaluate the performance of the proposed algorithm for automatic lesion volume delineation; namely the fuzzy hidden Markov chains (FHMC), with that of current state of the art in clinical practice threshold based techniques. As the classical hidden Markov chain (HMC) algorithm, FHMC takes into account noise, voxel intensity and spatial correlation, in order to classify a voxel as background or functional VOI. However the novelty of the fuzzy model consists of the inclusion of an estimation of imprecision, which should subsequently lead to a better modelling of the 'fuzzy' nature of the object of interest boundaries in emission tomography data. The performance of the algorithms has been assessed on both simulated and acquired datasets of the IEC phantom, covering a large range of spherical lesion sizes (from 10 to 37 mm), contrast ratios (4:1 and 8:1) and image noise levels. Both lesion activity recovery and VOI determination tasks were assessed in reconstructed images using two different voxel sizes (8 mm3 and 64 mm3). In order to account for both the functional volume location and its size, the concept of % classification errors was introduced in the evaluation of volume segmentation using the simulated datasets. Results reveal that FHMC performs substantially better than the threshold based methodology for functional volume determination or activity concentration recovery considering a contrast ratio of 4:1 and lesion sizes of <28 mm. Furthermore differences between classification and volume estimation errors evaluated were smaller for the segmented volumes provided by the FHMC algorithm. Finally, the performance of the automatic algorithms was less susceptible to image noise levels in comparison to the threshold based techniques. The analysis of both simulated and acquired datasets led to similar results and conclusions as far as the performance of segmentation algorithms under evaluation is concerned.

Multiobjective GAs, quantitative indices, and pattern classification.

PubMed

Bandyopadhyay, Sanghamitra; Pal, Sankar K; Aruna, B

2004-10-01

The concept of multiobjective optimization (MOO) has been integrated with variable length chromosomes for the development of a nonparametric genetic classifier which can overcome the problems, like overfitting/overlearning and ignoring smaller classes, as faced by single objective classifiers. The classifier can efficiently approximate any kind of linear and/or nonlinear class boundaries of a data set using an appropriate number of hyperplanes. While designing the classifier the aim is to simultaneously minimize the number of misclassified training points and the number of hyperplanes, and to maximize the product of class wise recognition scores. The concepts of validation set (in addition to training and test sets) and validation functional are introduced in the multiobjective classifier for selecting a solution from a set of nondominated solutions provided by the MOO algorithm. This genetic classifier incorporates elitism and some domain specific constraints in the search process, and is called the CEMOGA-Classifier (constrained elitist multiobjective genetic algorithm based classifier). Two new quantitative indices, namely, the purity and minimal spacing, are developed for evaluating the performance of different MOO techniques. These are used, along with classification accuracy, required number of hyperplanes and the computation time, to compare the CEMOGA-Classifier with other related ones.

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.

Improved target detection algorithm using Fukunaga-Koontz transform and distance classifier correlation filter

NASA Astrophysics Data System (ADS)

Bal, A.; Alam, M. S.; Aslan, M. S.

2006-05-01

Often sensor ego-motion or fast target movement causes the target to temporarily go out of the field-of-view leading to reappearing target detection problem in target tracking applications. Since the target goes out of the current frame and reenters at a later frame, the reentering location and variations in rotation, scale, and other 3D orientations of the target are not known thus complicating the detection algorithm has been developed using Fukunaga-Koontz Transform (FKT) and distance classifier correlation filter (DCCF). The detection algorithm uses target and background information, extracted from training samples, to detect possible candidate target images. The detected candidate target images are then introduced into the second algorithm, DCCF, called clutter rejection module, to determine the target coordinates are detected and tracking algorithm is initiated. The performance of the proposed FKT-DCCF based target detection algorithm has been tested using real-world forward looking infrared (FLIR) video sequences.

Adaboost multi-view face detection based on YCgCr skin color model

NASA Astrophysics Data System (ADS)

Lan, Qi; Xu, Zhiyong

2016-09-01

Traditional Adaboost face detection algorithm uses Haar-like features training face classifiers, whose detection error rate is low in the face region. While under the complex background, the classifiers will make wrong detection easily to the background regions with the similar faces gray level distribution, which leads to the error detection rate of traditional Adaboost algorithm is high. As one of the most important features of a face, skin in YCgCr color space has good clustering. We can fast exclude the non-face areas through the skin color model. Therefore, combining with the advantages of the Adaboost algorithm and skin color detection algorithm, this paper proposes Adaboost face detection algorithm method that bases on YCgCr skin color model. Experiments show that, compared with traditional algorithm, the method we proposed has improved significantly in the detection accuracy and errors.

Enhancement of Fast Face Detection Algorithm Based on a Cascade of Decision Trees

NASA Astrophysics Data System (ADS)

Khryashchev, V. V.; Lebedev, A. A.; Priorov, A. L.

2017-05-01

Face detection algorithm based on a cascade of ensembles of decision trees (CEDT) is presented. The new approach allows detecting faces other than the front position through the use of multiple classifiers. Each classifier is trained for a specific range of angles of the rotation head. The results showed a high rate of productivity for CEDT on images with standard size. The algorithm increases the area under the ROC-curve of 13% compared to a standard Viola-Jones face detection algorithm. Final realization of given algorithm consist of 5 different cascades for frontal/non-frontal faces. One more thing which we take from the simulation results is a low computational complexity of CEDT algorithm in comparison with standard Viola-Jones approach. This could prove important in the embedded system and mobile device industries because it can reduce the cost of hardware and make battery life longer.

Improved Approximation Algorithms for Item Pricing with Bounded Degree and Valuation

NASA Astrophysics Data System (ADS)

Hamane, Ryoso; Itoh, Toshiya

When a store sells items to customers, the store wishes to decide the prices of the items to maximize its profit. If the store sells the items with low (resp. high) prices, the customers buy more (resp. less) items, which provides less profit to the store. It would be hard for the store to decide the prices of items. Assume that a store has a set V of n items and there is a set C of m customers who wish to buy those items. The goal of the store is to decide the price of each item to maximize its profit. We refer to this maximization problem as an item pricing problem. We classify the item pricing problems according to how many items the store can sell or how the customers valuate the items. If the store can sell every item i with unlimited (resp. limited) amount, we refer to this as unlimited supply (resp. limited supply). We say that the item pricing problem is single-minded if each customer j∈C wishes to buy a set ej⊆V of items and assigns valuation w(ej)≥0. For the single-minded item pricing problems (in unlimited supply), Balcan and Blum regarded them as weighted k-hypergraphs and gave several approximation algorithms. In this paper, we focus on the (pseudo) degree of k-hypergraphs and the valuation ratio, i. e., the ratio between the smallest and the largest valuations. Then for the single-minded item pricing problems (in unlimited supply), we show improved approximation algorithms (for k-hypergraphs, general graphs, bipartite graphs, etc.) with respect to the maximum (pseudo) degree and the valuation ratio.

Brain amyloidosis ascertainment from cognitive, imaging, and peripheral blood protein measures

PubMed Central

Hwang, Kristy S.; Avila, David; Elashoff, David; Kohannim, Omid; Teng, Edmond; Sokolow, Sophie; Jack, Clifford R.; Jagust, William J.; Shaw, Leslie; Trojanowski, John Q.; Weiner, Michael W.; Thompson, Paul M.

2015-01-01

Background: The goal of this study was to identify a clinical biomarker signature of brain amyloidosis in the Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) mild cognitive impairment (MCI) cohort. Methods: We developed a multimodal biomarker classifier for predicting brain amyloidosis using cognitive, imaging, and peripheral blood protein ADNI1 MCI data. We used CSF β-amyloid 1–42 (Aβ42) ≤192 pg/mL as proxy measure for Pittsburgh compound B (PiB)-PET standard uptake value ratio ≥1.5. We trained our classifier in the subcohort with CSF Aβ42 but no PiB-PET data and tested its performance in the subcohort with PiB-PET but no CSF Aβ42 data. We also examined the utility of our biomarker signature for predicting disease progression from MCI to Alzheimer dementia. Results: The CSF training classifier selected Mini-Mental State Examination, Trails B, Auditory Verbal Learning Test delayed recall, education, APOE genotype, interleukin 6 receptor, clusterin, and ApoE protein, and achieved leave-one-out accuracy of 85% (area under the curve [AUC] = 0.8). The PiB testing classifier achieved an AUC of 0.72, and when classifier self-tuning was allowed, AUC = 0.74. The 36-month disease-progression classifier achieved AUC = 0.75 and accuracy = 71%. Conclusions: Automated classifiers based on cognitive and peripheral blood protein variables can identify the presence of brain amyloidosis with a modest level of accuracy. Such methods could have implications for clinical trial design and enrollment in the near future. Classification of evidence: This study provides Class II evidence that a classification algorithm based on cognitive, imaging, and peripheral blood protein measures identifies patients with brain amyloid on PiB-PET with moderate accuracy (sensitivity 68%, specificity 78%). PMID:25609767

Brain amyloidosis ascertainment from cognitive, imaging, and peripheral blood protein measures.

PubMed

Apostolova, Liana G; Hwang, Kristy S; Avila, David; Elashoff, David; Kohannim, Omid; Teng, Edmond; Sokolow, Sophie; Jack, Clifford R; Jagust, William J; Shaw, Leslie; Trojanowski, John Q; Weiner, Michael W; Thompson, Paul M

2015-02-17

The goal of this study was to identify a clinical biomarker signature of brain amyloidosis in the Alzheimer's Disease Neuroimaging Initiative 1 (ADNI1) mild cognitive impairment (MCI) cohort. We developed a multimodal biomarker classifier for predicting brain amyloidosis using cognitive, imaging, and peripheral blood protein ADNI1 MCI data. We used CSF β-amyloid 1-42 (Aβ42) ≤ 192 pg/mL as proxy measure for Pittsburgh compound B (PiB)-PET standard uptake value ratio ≥ 1.5. We trained our classifier in the subcohort with CSF Aβ42 but no PiB-PET data and tested its performance in the subcohort with PiB-PET but no CSF Aβ42 data. We also examined the utility of our biomarker signature for predicting disease progression from MCI to Alzheimer dementia. The CSF training classifier selected Mini-Mental State Examination, Trails B, Auditory Verbal Learning Test delayed recall, education, APOE genotype, interleukin 6 receptor, clusterin, and ApoE protein, and achieved leave-one-out accuracy of 85% (area under the curve [AUC] = 0.8). The PiB testing classifier achieved an AUC of 0.72, and when classifier self-tuning was allowed, AUC = 0.74. The 36-month disease-progression classifier achieved AUC = 0.75 and accuracy = 71%. Automated classifiers based on cognitive and peripheral blood protein variables can identify the presence of brain amyloidosis with a modest level of accuracy. Such methods could have implications for clinical trial design and enrollment in the near future. This study provides Class II evidence that a classification algorithm based on cognitive, imaging, and peripheral blood protein measures identifies patients with brain amyloid on PiB-PET with moderate accuracy (sensitivity 68%, specificity 78%). © 2015 American Academy of Neurology.

Locating Encrypted Data Hidden Among Non-Encrypted Data Using Statistical Tools

DTIC Science & Technology

2007-03-01

length of a compressed sequence). If a bit sequence can be significantly compressed , then it is not random. Lempel - Ziv Compression Test This test...communication, targeting, and a host other of tasks. This software will most assuredly contain classified data or algorithms requiring protection in...containing the classified data and algorithms . As the program is executed the solider would have access to the common unclassified tasks, however, to

Classifier-Guided Sampling for Complex Energy System Optimization

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

Backlund, Peter B.; Eddy, John P.

2015-09-01

This report documents the results of a Laboratory Directed Research and Development (LDRD) effort enti tled "Classifier - Guided Sampling for Complex Energy System Optimization" that was conducted during FY 2014 and FY 2015. The goal of this proj ect was to develop, implement, and test major improvements to the classifier - guided sampling (CGS) algorithm. CGS is type of evolutionary algorithm for perform ing search and optimization over a set of discrete design variables in the face of one or more objective functions. E xisting evolutionary algorithms, such as genetic algorithms , may require a large number of omore » bjecti ve function evaluations to identify optimal or near - optimal solutions . Reducing the number of evaluations can result in significant time savings, especially if the objective function is computationally expensive. CGS reduce s the evaluation count by us ing a Bayesian network classifier to filter out non - promising candidate designs , prior to evaluation, based on their posterior probabilit ies . In this project, b oth the single - objective and multi - objective version s of the CGS are developed and tested on a set of benchm ark problems. As a domain - specific case study, CGS is used to design a microgrid for use in islanded mode during an extended bulk power grid outage.« less

Gaussian diffusion sinogram inpainting for X-ray CT metal artifact reduction.

PubMed

Peng, Chengtao; Qiu, Bensheng; Li, Ming; Guan, Yihui; Zhang, Cheng; Wu, Zhongyi; Zheng, Jian

2017-01-05

Metal objects implanted in the bodies of patients usually generate severe streaking artifacts in reconstructed images of X-ray computed tomography, which degrade the image quality and affect the diagnosis of disease. Therefore, it is essential to reduce these artifacts to meet the clinical demands. In this work, we propose a Gaussian diffusion sinogram inpainting metal artifact reduction algorithm based on prior images to reduce these artifacts for fan-beam computed tomography reconstruction. In this algorithm, prior information that originated from a tissue-classified prior image is used for the inpainting of metal-corrupted projections, and it is incorporated into a Gaussian diffusion function. The prior knowledge is particularly designed to locate the diffusion position and improve the sparsity of the subtraction sinogram, which is obtained by subtracting the prior sinogram of the metal regions from the original sinogram. The sinogram inpainting algorithm is implemented through an approach of diffusing prior energy and is then solved by gradient descent. The performance of the proposed metal artifact reduction algorithm is compared with two conventional metal artifact reduction algorithms, namely the interpolation metal artifact reduction algorithm and normalized metal artifact reduction algorithm. The experimental datasets used included both simulated and clinical datasets. By evaluating the results subjectively, the proposed metal artifact reduction algorithm causes fewer secondary artifacts than the two conventional metal artifact reduction algorithms, which lead to severe secondary artifacts resulting from impertinent interpolation and normalization. Additionally, the objective evaluation shows the proposed approach has the smallest normalized mean absolute deviation and the highest signal-to-noise ratio, indicating that the proposed method has produced the image with the best quality. No matter for the simulated datasets or the clinical datasets, the proposed algorithm has reduced the metal artifacts apparently.

Efficient audio signal processing for embedded systems

NASA Astrophysics Data System (ADS)

Chiu, Leung Kin

As mobile platforms continue to pack on more computational power, electronics manufacturers start to differentiate their products by enhancing the audio features. However, consumers also demand smaller devices that could operate for longer time, hence imposing design constraints. In this research, we investigate two design strategies that would allow us to efficiently process audio signals on embedded systems such as mobile phones and portable electronics. In the first strategy, we exploit properties of the human auditory system to process audio signals. We designed a sound enhancement algorithm to make piezoelectric loudspeakers sound ”richer" and "fuller." Piezoelectric speakers have a small form factor but exhibit poor response in the low-frequency region. In the algorithm, we combine psychoacoustic bass extension and dynamic range compression to improve the perceived bass coming out from the tiny speakers. We also developed an audio energy reduction algorithm for loudspeaker power management. The perceptually transparent algorithm extends the battery life of mobile devices and prevents thermal damage in speakers. This method is similar to audio compression algorithms, which encode audio signals in such a ways that the compression artifacts are not easily perceivable. Instead of reducing the storage space, however, we suppress the audio contents that are below the hearing threshold, therefore reducing the signal energy. In the second strategy, we use low-power analog circuits to process the signal before digitizing it. We designed an analog front-end for sound detection and implemented it on a field programmable analog array (FPAA). The system is an example of an analog-to-information converter. The sound classifier front-end can be used in a wide range of applications because programmable floating-gate transistors are employed to store classifier weights. Moreover, we incorporated a feature selection algorithm to simplify the analog front-end. A machine learning algorithm AdaBoost is used to select the most relevant features for a particular sound detection application. In this classifier architecture, we combine simple "base" analog classifiers to form a strong one. We also designed the circuits to implement the AdaBoost-based analog classifier.

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

PubMed

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

2012-10-01

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

Texture segmentation by genetic programming.

PubMed

Song, Andy; Ciesielski, Vic

2008-01-01

This paper describes a texture segmentation method using genetic programming (GP), which is one of the most powerful evolutionary computation algorithms. By choosing an appropriate representation texture, classifiers can be evolved without computing texture features. Due to the absence of time-consuming feature extraction, the evolved classifiers enable the development of the proposed texture segmentation algorithm. This GP based method can achieve a segmentation speed that is significantly higher than that of conventional methods. This method does not require a human expert to manually construct models for texture feature extraction. In an analysis of the evolved classifiers, it can be seen that these GP classifiers are not arbitrary. Certain textural regularities are captured by these classifiers to discriminate different textures. GP has been shown in this study as a feasible and a powerful approach for texture classification and segmentation, which are generally considered as complex vision tasks.

Classification of breast cancer cytological specimen using convolutional neural network

NASA Astrophysics Data System (ADS)

Żejmo, Michał; Kowal, Marek; Korbicz, Józef; Monczak, Roman

2017-01-01

The paper presents a deep learning approach for automatic classification of breast tumors based on fine needle cytology. The main aim of the system is to distinguish benign from malignant cases based on microscopic images. Experiment was carried out on cytological samples derived from 50 patients (25 benign cases + 25 malignant cases) diagnosed in Regional Hospital in Zielona Góra. To classify microscopic images, we used convolutional neural networks (CNN) of two types: GoogLeNet and AlexNet. Due to the very large size of images of cytological specimen (on average 200000 × 100000 pixels), they were divided into smaller patches of size 256 × 256 pixels. Breast cancer classification usually is based on morphometric features of nuclei. Therefore, training and validation patches were selected using Support Vector Machine (SVM) so that suitable amount of cell material was depicted. Neural classifiers were tuned using GPU accelerated implementation of gradient descent algorithm. Training error was defined as a cross-entropy classification loss. Classification accuracy was defined as the percentage ratio of successfully classified validation patches to the total number of validation patches. The best accuracy rate of 83% was obtained by GoogLeNet model. We observed that more misclassified patches belong to malignant cases.

Incremental learning of concept drift in nonstationary environments.

PubMed

Elwell, Ryan; Polikar, Robi

2011-10-01

We introduce an ensemble of classifiers-based approach for incremental learning of concept drift, characterized by nonstationary environments (NSEs), where the underlying data distributions change over time. The proposed algorithm, named Learn(++). NSE, learns from consecutive batches of data without making any assumptions on the nature or rate of drift; it can learn from such environments that experience constant or variable rate of drift, addition or deletion of concept classes, as well as cyclical drift. The algorithm learns incrementally, as other members of the Learn(++) family of algorithms, that is, without requiring access to previously seen data. Learn(++). NSE trains one new classifier for each batch of data it receives, and combines these classifiers using a dynamically weighted majority voting. The novelty of the approach is in determining the voting weights, based on each classifier's time-adjusted accuracy on current and past environments. This approach allows the algorithm to recognize, and act accordingly, to the changes in underlying data distributions, as well as to a possible reoccurrence of an earlier distribution. We evaluate the algorithm on several synthetic datasets designed to simulate a variety of nonstationary environments, as well as a real-world weather prediction dataset. Comparisons with several other approaches are also included. Results indicate that Learn(++). NSE can track the changing environments very closely, regardless of the type of concept drift. To allow future use, comparison and benchmarking by interested researchers, we also release our data used in this paper. © 2011 IEEE

On Algorithms for Generating Computationally Simple Piecewise Linear Classifiers

DTIC Science & Technology

1989-05-01

suffers. - Waveform classification, e.g. speech recognition, seismic analysis (i.e. discrimination between earthquakes and nuclear explosions), target...assuming Gaussian distributions (B-G) d) Bayes classifier with probability densities estimated with the k-N-N method (B- kNN ) e) The -arest neighbour...range of classifiers are chosen including a fast, easy computable and often used classifier (B-G), reliable and complex classifiers (B- kNN and NNR

Classifying epileptic EEG signals with delay permutation entropy and Multi-Scale K-means.

PubMed

Zhu, Guohun; Li, Yan; Wen, Peng Paul; Wang, Shuaifang

2015-01-01

Most epileptic EEG classification algorithms are supervised and require large training datasets, that hinder their use in real time applications. This chapter proposes an unsupervised Multi-Scale K-means (MSK-means) MSK-means algorithm to distinguish epileptic EEG signals and identify epileptic zones. The random initialization of the K-means algorithm can lead to wrong clusters. Based on the characteristics of EEGs, the MSK-means MSK-means algorithm initializes the coarse-scale centroid of a cluster with a suitable scale factor. In this chapter, the MSK-means algorithm is proved theoretically superior to the K-means algorithm on efficiency. In addition, three classifiers: the K-means, MSK-means MSK-means and support vector machine (SVM), are used to identify seizure and localize epileptogenic zone using delay permutation entropy features. The experimental results demonstrate that identifying seizure with the MSK-means algorithm and delay permutation entropy achieves 4. 7 % higher accuracy than that of K-means, and 0. 7 % higher accuracy than that of the SVM.

Human activity recognition based on feature selection in smart home using back-propagation algorithm.

PubMed

Fang, Hongqing; He, Lei; Si, Hao; Liu, Peng; Xie, Xiaolei

2014-09-01

In this paper, Back-propagation(BP) algorithm has been used to train the feed forward neural network for human activity recognition in smart home environments, and inter-class distance method for feature selection of observed motion sensor events is discussed and tested. And then, the human activity recognition performances of neural network using BP algorithm have been evaluated and compared with other probabilistic algorithms: Naïve Bayes(NB) classifier and Hidden Markov Model(HMM). The results show that different feature datasets yield different activity recognition accuracy. The selection of unsuitable feature datasets increases the computational complexity and degrades the activity recognition accuracy. Furthermore, neural network using BP algorithm has relatively better human activity recognition performances than NB classifier and HMM. Copyright © 2014 ISA. Published by Elsevier Ltd. All rights reserved.

A comparison of unsupervised classification procedures on LANDSAT MSS data for an area of complex surface conditions in Basilicata, Southern Italy

NASA Technical Reports Server (NTRS)

Justice, C.; Townshend, J. (Principal Investigator)

1981-01-01

Two unsupervised classification procedures were applied to ratioed and unratioed LANDSAT multispectral scanner data of an area of spatially complex vegetation and terrain. An objective accuracy assessment was undertaken on each classification and comparison was made of the classification accuracies. The two unsupervised procedures use the same clustering algorithm. By on procedure the entire area is clustered and by the other a representative sample of the area is clustered and the resulting statistics are extrapolated to the remaining area using a maximum likelihood classifier. Explanation is given of the major steps in the classification procedures including image preprocessing; classification; interpretation of cluster classes; and accuracy assessment. Of the four classifications undertaken, the monocluster block approach on the unratioed data gave the highest accuracy of 80% for five coarse cover classes. This accuracy was increased to 84% by applying a 3 x 3 contextual filter to the classified image. A detailed description and partial explanation is provided for the major misclassification. The classification of the unratioed data produced higher percentage accuracies than for the ratioed data and the monocluster block approach gave higher accuracies than clustering the entire area. The moncluster block approach was additionally the most economical in terms of computing time.

Selection of Norway spruce somatic embryos by computer vision

NASA Astrophysics Data System (ADS)

Hamalainen, Jari J.; Jokinen, Kari J.

1993-05-01

A computer vision system was developed for the classification of plant somatic embryos. The embryos are in a Petri dish that is transferred with constant speed and they are recognized as they pass a line scan camera. A classification algorithm needs to be installed for every plant species. This paper describes an algorithm for the recognition of Norway spruce (Picea abies) embryos. A short review of conifer micropropagation by somatic embryogenesis is also given. The recognition algorithm is based on features calculated from the boundary of the object. Only part of the boundary corresponding to the developing cotyledons (2 - 15) and the straight sides of the embryo are used for recognition. An index of the length of the cotyledons describes the developmental stage of the embryo. The testing set for classifier performance consisted of 118 embryos and 478 nonembryos. With the classification tolerances chosen 69% of the objects classified as embryos by a human classifier were selected and 31$% rejected. Less than 1% of the nonembryos were classified as embryos. The basic features developed can probably be easily adapted for the recognition of other conifer somatic embryos.

Hierarchical Learning of Tree Classifiers for Large-Scale Plant Species Identification.

PubMed

Fan, Jianping; Zhou, Ning; Peng, Jinye; Gao, Ling

2015-11-01

In this paper, a hierarchical multi-task structural learning algorithm is developed to support large-scale plant species identification, where a visual tree is constructed for organizing large numbers of plant species in a coarse-to-fine fashion and determining the inter-related learning tasks automatically. For a given parent node on the visual tree, it contains a set of sibling coarse-grained categories of plant species or sibling fine-grained plant species, and a multi-task structural learning algorithm is developed to train their inter-related classifiers jointly for enhancing their discrimination power. The inter-level relationship constraint, e.g., a plant image must first be assigned to a parent node (high-level non-leaf node) correctly if it can further be assigned to the most relevant child node (low-level non-leaf node or leaf node) on the visual tree, is formally defined and leveraged to learn more discriminative tree classifiers over the visual tree. Our experimental results have demonstrated the effectiveness of our hierarchical multi-task structural learning algorithm on training more discriminative tree classifiers for large-scale plant species identification.

PPCM: Combing multiple classifiers to improve protein-protein interaction prediction

DOE PAGES

Yao, Jianzhuang; Guo, Hong; Yang, Xiaohan

2015-08-01

Determining protein-protein interaction (PPI) in biological systems is of considerable importance, and prediction of PPI has become a popular research area. Although different classifiers have been developed for PPI prediction, no single classifier seems to be able to predict PPI with high confidence. We postulated that by combining individual classifiers the accuracy of PPI prediction could be improved. We developed a method called protein-protein interaction prediction classifiers merger (PPCM), and this method combines output from two PPI prediction tools, GO2PPI and Phyloprof, using Random Forests algorithm. The performance of PPCM was tested by area under the curve (AUC) using anmore » assembled Gold Standard database that contains both positive and negative PPI pairs. Our AUC test showed that PPCM significantly improved the PPI prediction accuracy over the corresponding individual classifiers. We found that additional classifiers incorporated into PPCM could lead to further improvement in the PPI prediction accuracy. Furthermore, cross species PPCM could achieve competitive and even better prediction accuracy compared to the single species PPCM. This study established a robust pipeline for PPI prediction by integrating multiple classifiers using Random Forests algorithm. Ultimately, this pipeline will be useful for predicting PPI in nonmodel species.« less

Support vector machine as a binary classifier for automated object detection in remotely sensed data

NASA Astrophysics Data System (ADS)

Wardaya, P. D.

2014-02-01

In the present paper, author proposes the application of Support Vector Machine (SVM) for the analysis of satellite imagery. One of the advantages of SVM is that, with limited training data, it may generate comparable or even better results than the other methods. The SVM algorithm is used for automated object detection and characterization. Specifically, the SVM is applied in its basic nature as a binary classifier where it classifies two classes namely, object and background. The algorithm aims at effectively detecting an object from its background with the minimum training data. The synthetic image containing noises is used for algorithm testing. Furthermore, it is implemented to perform remote sensing image analysis such as identification of Island vegetation, water body, and oil spill from the satellite imagery. It is indicated that SVM provides the fast and accurate analysis with the acceptable result.

Methods for Real-Time Prediction of the Mode of Travel Using Smartphone-Based GPS and Accelerometer Data

PubMed Central

Martin, Bryan D.; Wolfson, Julian; Adomavicius, Gediminas; Fan, Yingling

2017-01-01

We propose and compare combinations of several methods for classifying transportation activity data from smartphone GPS and accelerometer sensors. We have two main objectives. First, we aim to classify our data as accurately as possible. Second, we aim to reduce the dimensionality of the data as much as possible in order to reduce the computational burden of the classification. We combine dimension reduction and classification algorithms and compare them with a metric that balances accuracy and dimensionality. In doing so, we develop a classification algorithm that accurately classifies five different modes of transportation (i.e., walking, biking, car, bus and rail) while being computationally simple enough to run on a typical smartphone. Further, we use data that required no behavioral changes from the smartphone users to collect. Our best classification model uses the random forest algorithm to achieve 96.8% accuracy. PMID:28885550

Methods for Real-Time Prediction of the Mode of Travel Using Smartphone-Based GPS and Accelerometer Data.

PubMed

Martin, Bryan D; Addona, Vittorio; Wolfson, Julian; Adomavicius, Gediminas; Fan, Yingling

2017-09-08

We propose and compare combinations of several methods for classifying transportation activity data from smartphone GPS and accelerometer sensors. We have two main objectives. First, we aim to classify our data as accurately as possible. Second, we aim to reduce the dimensionality of the data as much as possible in order to reduce the computational burden of the classification. We combine dimension reduction and classification algorithms and compare them with a metric that balances accuracy and dimensionality. In doing so, we develop a classification algorithm that accurately classifies five different modes of transportation (i.e., walking, biking, car, bus and rail) while being computationally simple enough to run on a typical smartphone. Further, we use data that required no behavioral changes from the smartphone users to collect. Our best classification model uses the random forest algorithm to achieve 96.8% accuracy.

A novel algorithm for simplification of complex gene classifiers in cancer

PubMed Central

Wilson, Raphael A.; Teng, Ling; Bachmeyer, Karen M.; Bissonnette, Mei Lin Z.; Husain, Aliya N.; Parham, David M.; Triche, Timothy J.; Wing, Michele R.; Gastier-Foster, Julie M.; Barr, Frederic G.; Hawkins, Douglas S.; Anderson, James R.; Skapek, Stephen X.; Volchenboum, Samuel L.

2013-01-01

The clinical application of complex molecular classifiers as diagnostic or prognostic tools has been limited by the time and cost needed to apply them to patients. Using an existing fifty-gene expression signature known to separate two molecular subtypes of the pediatric cancer rhabdomyosarcoma, we show that an exhaustive iterative search algorithm can distill this complex classifier down to two or three features with equal discrimination. We validated the two-gene signatures using three separate and distinct data sets, including one that uses degraded RNA extracted from formalin-fixed, paraffin-embedded material. Finally, to demonstrate the generalizability of our algorithm, we applied it to a lung cancer data set to find minimal gene signatures that can distinguish survival. Our approach can easily be generalized and coupled to existing technical platforms to facilitate the discovery of simplified signatures that are ready for routine clinical use. PMID:23913937

PixelLearn

NASA Technical Reports Server (NTRS)

Mazzoni, Dominic; Wagstaff, Kiri; Bornstein, Benjamin; Tang, Nghia; Roden, Joseph

2006-01-01

PixelLearn is an integrated user-interface computer program for classifying pixels in scientific images. Heretofore, training a machine-learning algorithm to classify pixels in images has been tedious and difficult. PixelLearn provides a graphical user interface that makes it faster and more intuitive, leading to more interactive exploration of image data sets. PixelLearn also provides image-enhancement controls to make it easier to see subtle details in images. PixelLearn opens images or sets of images in a variety of common scientific file formats and enables the user to interact with several supervised or unsupervised machine-learning pixel-classifying algorithms while the user continues to browse through the images. The machinelearning algorithms in PixelLearn use advanced clustering and classification methods that enable accuracy much higher than is achievable by most other software previously available for this purpose. PixelLearn is written in portable C++ and runs natively on computers running Linux, Windows, or Mac OS X.

Testing the Potential of Vegetation Indices for Land Use/cover Classification Using High Resolution Data

NASA Astrophysics Data System (ADS)

Karakacan Kuzucu, A.; Bektas Balcik, F.

2017-11-01

Accurate and reliable land use/land cover (LULC) information obtained by remote sensing technology is necessary in many applications such as environmental monitoring, agricultural management, urban planning, hydrological applications, soil management, vegetation condition study and suitability analysis. But this information still remains a challenge especially in heterogeneous landscapes covering urban and rural areas due to spectrally similar LULC features. In parallel with technological developments, supplementary data such as satellite-derived spectral indices have begun to be used as additional bands in classification to produce data with high accuracy. The aim of this research is to test the potential of spectral vegetation indices combination with supervised classification methods and to extract reliable LULC information from SPOT 7 multispectral imagery. The Normalized Difference Vegetation Index (NDVI), the Ratio Vegetation Index (RATIO), the Soil Adjusted Vegetation Index (SAVI) were the three vegetation indices used in this study. The classical maximum likelihood classifier (MLC) and support vector machine (SVM) algorithm were applied to classify SPOT 7 image. Catalca is selected region located in the north west of the Istanbul in Turkey, which has complex landscape covering artificial surface, forest and natural area, agricultural field, quarry/mining area, pasture/scrubland and water body. Accuracy assessment of all classified images was performed through overall accuracy and kappa coefficient. The results indicated that the incorporation of these three different vegetation indices decrease the classification accuracy for the MLC and SVM classification. In addition, the maximum likelihood classification slightly outperformed the support vector machine classification approach in both overall accuracy and kappa statistics.

Integrating concept ontology and multitask learning to achieve more effective classifier training for multilevel image annotation.

PubMed

Fan, Jianping; Gao, Yuli; Luo, Hangzai

2008-03-01

In this paper, we have developed a new scheme for achieving multilevel annotations of large-scale images automatically. To achieve more sufficient representation of various visual properties of the images, both the global visual features and the local visual features are extracted for image content representation. To tackle the problem of huge intraconcept visual diversity, multiple types of kernels are integrated to characterize the diverse visual similarity relationships between the images more precisely, and a multiple kernel learning algorithm is developed for SVM image classifier training. To address the problem of huge interconcept visual similarity, a novel multitask learning algorithm is developed to learn the correlated classifiers for the sibling image concepts under the same parent concept and enhance their discrimination and adaptation power significantly. To tackle the problem of huge intraconcept visual diversity for the image concepts at the higher levels of the concept ontology, a novel hierarchical boosting algorithm is developed to learn their ensemble classifiers hierarchically. In order to assist users on selecting more effective hypotheses for image classifier training, we have developed a novel hyperbolic framework for large-scale image visualization and interactive hypotheses assessment. Our experiments on large-scale image collections have also obtained very positive results.

Massively parallel unsupervised single-particle cryo-EM data clustering via statistical manifold learning

PubMed Central

Wu, Jiayi; Ma, Yong-Bei; Congdon, Charles; Brett, Bevin; Chen, Shuobing; Xu, Yaofang; Ouyang, Qi

2017-01-01

Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM) data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR) in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM). We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC) environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization. PMID:28786986

Massively parallel unsupervised single-particle cryo-EM data clustering via statistical manifold learning.

PubMed

Wu, Jiayi; Ma, Yong-Bei; Congdon, Charles; Brett, Bevin; Chen, Shuobing; Xu, Yaofang; Ouyang, Qi; Mao, Youdong

2017-01-01

Structural heterogeneity in single-particle cryo-electron microscopy (cryo-EM) data represents a major challenge for high-resolution structure determination. Unsupervised classification may serve as the first step in the assessment of structural heterogeneity. However, traditional algorithms for unsupervised classification, such as K-means clustering and maximum likelihood optimization, may classify images into wrong classes with decreasing signal-to-noise-ratio (SNR) in the image data, yet demand increased computational costs. Overcoming these limitations requires further development of clustering algorithms for high-performance cryo-EM data processing. Here we introduce an unsupervised single-particle clustering algorithm derived from a statistical manifold learning framework called generative topographic mapping (GTM). We show that unsupervised GTM clustering improves classification accuracy by about 40% in the absence of input references for data with lower SNRs. Applications to several experimental datasets suggest that our algorithm can detect subtle structural differences among classes via a hierarchical clustering strategy. After code optimization over a high-performance computing (HPC) environment, our software implementation was able to generate thousands of reference-free class averages within hours in a massively parallel fashion, which allows a significant improvement on ab initio 3D reconstruction and assists in the computational purification of homogeneous datasets for high-resolution visualization.

Multi-pass encoding of hyperspectral imagery with spectral quality control

NASA Astrophysics Data System (ADS)

Wasson, Steven; Walker, William

2015-05-01

Multi-pass encoding is a technique employed in the field of video compression that maximizes the quality of an encoded video sequence within the constraints of a specified bit rate. This paper presents research where multi-pass encoding is extended to the field of hyperspectral image compression. Unlike video, which is primarily intended to be viewed by a human observer, hyperspectral imagery is processed by computational algorithms that generally attempt to classify the pixel spectra within the imagery. As such, these algorithms are more sensitive to distortion in the spectral dimension of the image than they are to perceptual distortion in the spatial dimension. The compression algorithm developed for this research, which uses the Karhunen-Loeve transform for spectral decorrelation followed by a modified H.264/Advanced Video Coding (AVC) encoder, maintains a user-specified spectral quality level while maximizing the compression ratio throughout the encoding process. The compression performance may be considered near-lossless in certain scenarios. For qualitative purposes, this paper presents the performance of the compression algorithm for several Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and Hyperion datasets using spectral angle as the spectral quality assessment function. Specifically, the compression performance is illustrated in the form of rate-distortion curves that plot spectral angle versus bits per pixel per band (bpppb).

Algorithms for detecting antibodies to HIV-1: results from a rural Ugandan cohort.

PubMed

Nunn, A J; Biryahwaho, B; Downing, R G; van der Groen, G; Ojwiya, A; Mulder, D W

1993-08-01

To evaluate an algorithm using two enzyme immunoassays (EIA) for anti-HIV-1 antibodies in a rural African population and to assess alternative simplified algorithms. Sera obtained from 7895 individuals in a rural population survey were tested using an algorithm based on two different EIA systems: Recombigen HIV-1 EIA and Wellcozyme HIV-1 Recombinant. Alternative algorithms were assessed using negative or confirmed positive sera. None of the 227 sera classified as unequivocably negative by the two assays were positive by Western blot. Of 192 sera unequivocably positive by both assays, four were seronegative by Western blot. The possibility of technical error cannot be ruled out in three of these. One of the alternative algorithms assessed classified all borderline or discordant assay results as negative had a specificity of 100% and a sensitivity of 98.4%. The cost of this algorithm is one-third that of the conventional algorithm. Our evaluation suggests that high specificity and sensitivity can be obtained without using Western blot and at a considerable reduction in cost.

A distributed approach for optimizing cascaded classifier topologies in real-time stream mining systems.

PubMed

Foo, Brian; van der Schaar, Mihaela

2010-11-01

In this paper, we discuss distributed optimization techniques for configuring classifiers in a real-time, informationally-distributed stream mining system. Due to the large volume of streaming data, stream mining systems must often cope with overload, which can lead to poor performance and intolerable processing delay for real-time applications. Furthermore, optimizing over an entire system of classifiers is a difficult task since changing the filtering process at one classifier can impact both the feature values of data arriving at classifiers further downstream and thus, the classification performance achieved by an ensemble of classifiers, as well as the end-to-end processing delay. To address this problem, this paper makes three main contributions: 1) Based on classification and queuing theoretic models, we propose a utility metric that captures both the performance and the delay of a binary filtering classifier system. 2) We introduce a low-complexity framework for estimating the system utility by observing, estimating, and/or exchanging parameters between the inter-related classifiers deployed across the system. 3) We provide distributed algorithms to reconfigure the system, and analyze the algorithms based on their convergence properties, optimality, information exchange overhead, and rate of adaptation to non-stationary data sources. We provide results using different video classifier systems.

Automated detection of tuberculosis on sputum smeared slides using stepwise classification

NASA Astrophysics Data System (ADS)

Divekar, Ajay; Pangilinan, Corina; Coetzee, Gerrit; Sondh, Tarlochan; Lure, Fleming Y. M.; Kennedy, Sean

2012-03-01

Routine visual slide screening for identification of tuberculosis (TB) bacilli in stained sputum slides under microscope system is a tedious labor-intensive task and can miss up to 50% of TB. Based on the Shannon cofactor expansion on Boolean function for classification, a stepwise classification (SWC) algorithm is developed to remove different types of false positives, one type at a time, and to increase the detection of TB bacilli at different concentrations. Both bacilli and non-bacilli objects are first analyzed and classified into several different categories including scanty positive, high concentration positive, and several non-bacilli categories: small bright objects, beaded, dim elongated objects, etc. The morphological and contrast features are extracted based on aprior clinical knowledge. The SWC is composed of several individual classifiers. Individual classifier to increase the bacilli counts utilizes an adaptive algorithm based on a microbiologist's statistical heuristic decision process. Individual classifier to reduce false positive is developed through minimization from a binary decision tree to classify different types of true and false positive based on feature vectors. Finally, the detection algorithm is was tested on 102 independent confirmed negative and 74 positive cases. A multi-class task analysis shows high accordance rate for negative, scanty, and high-concentration as 88.24%, 56.00%, and 97.96%, respectively. A binary-class task analysis using a receiver operating characteristics method with the area under the curve (Az) is also utilized to analyze the performance of this detection algorithm, showing the superior detection performance on the high-concentration cases (Az=0.913) and cases mixed with high-concentration and scanty cases (Az=0.878).

A low computation cost method for seizure prediction.

PubMed

Zhang, Yanli; Zhou, Weidong; Yuan, Qi; Wu, Qi

2014-10-01

The dynamic changes of electroencephalograph (EEG) signals in the period prior to epileptic seizures play a major role in the seizure prediction. This paper proposes a low computation seizure prediction algorithm that combines a fractal dimension with a machine learning algorithm. The presented seizure prediction algorithm extracts the Higuchi fractal dimension (HFD) of EEG signals as features to classify the patient's preictal or interictal state with Bayesian linear discriminant analysis (BLDA) as a classifier. The outputs of BLDA are smoothed by a Kalman filter for reducing possible sporadic and isolated false alarms and then the final prediction results are produced using a thresholding procedure. The algorithm was evaluated on the intracranial EEG recordings of 21 patients in the Freiburg EEG database. For seizure occurrence period of 30 min and 50 min, our algorithm obtained an average sensitivity of 86.95% and 89.33%, an average false prediction rate of 0.20/h, and an average prediction time of 24.47 min and 39.39 min, respectively. The results confirm that the changes of HFD can serve as a precursor of ictal activities and be used for distinguishing between interictal and preictal epochs. Both HFD and BLDA classifier have a low computational complexity. All of these make the proposed algorithm suitable for real-time seizure prediction. Copyright © 2014 Elsevier B.V. All rights reserved.

Classifying publications from the clinical and translational science award program along the translational research spectrum: a machine learning approach.

PubMed

Surkis, Alisa; Hogle, Janice A; DiazGranados, Deborah; Hunt, Joe D; Mazmanian, Paul E; Connors, Emily; Westaby, Kate; Whipple, Elizabeth C; Adamus, Trisha; Mueller, Meridith; Aphinyanaphongs, Yindalon

2016-08-05

Translational research is a key area of focus of the National Institutes of Health (NIH), as demonstrated by the substantial investment in the Clinical and Translational Science Award (CTSA) program. The goal of the CTSA program is to accelerate the translation of discoveries from the bench to the bedside and into communities. Different classification systems have been used to capture the spectrum of basic to clinical to population health research, with substantial differences in the number of categories and their definitions. Evaluation of the effectiveness of the CTSA program and of translational research in general is hampered by the lack of rigor in these definitions and their application. This study adds rigor to the classification process by creating a checklist to evaluate publications across the translational spectrum and operationalizes these classifications by building machine learning-based text classifiers to categorize these publications. Based on collaboratively developed definitions, we created a detailed checklist for categories along the translational spectrum from T0 to T4. We applied the checklist to CTSA-linked publications to construct a set of coded publications for use in training machine learning-based text classifiers to classify publications within these categories. The training sets combined T1/T2 and T3/T4 categories due to low frequency of these publication types compared to the frequency of T0 publications. We then compared classifier performance across different algorithms and feature sets and applied the classifiers to all publications in PubMed indexed to CTSA grants. To validate the algorithm, we manually classified the articles with the top 100 scores from each classifier. The definitions and checklist facilitated classification and resulted in good inter-rater reliability for coding publications for the training set. Very good performance was achieved for the classifiers as represented by the area under the receiver operating curves (AUC), with an AUC of 0.94 for the T0 classifier, 0.84 for T1/T2, and 0.92 for T3/T4. The combination of definitions agreed upon by five CTSA hubs, a checklist that facilitates more uniform definition interpretation, and algorithms that perform well in classifying publications along the translational spectrum provide a basis for establishing and applying uniform definitions of translational research categories. The classification algorithms allow publication analyses that would not be feasible with manual classification, such as assessing the distribution and trends of publications across the CTSA network and comparing the categories of publications and their citations to assess knowledge transfer across the translational research spectrum.

Multiple Kernel Sparse Representation based Orthogonal Discriminative Projection and Its Cost-Sensitive Extension.

PubMed

Zhang, Guoqing; Sun, Huaijiang; Xia, Guiyu; Sun, Quansen

2016-07-07

Sparse representation based classification (SRC) has been developed and shown great potential for real-world application. Based on SRC, Yang et al. [10] devised a SRC steered discriminative projection (SRC-DP) method. However, as a linear algorithm, SRC-DP cannot handle the data with highly nonlinear distribution. Kernel sparse representation-based classifier (KSRC) is a non-linear extension of SRC and can remedy the drawback of SRC. KSRC requires the use of a predetermined kernel function and selection of the kernel function and its parameters is difficult. Recently, multiple kernel learning for SRC (MKL-SRC) [22] has been proposed to learn a kernel from a set of base kernels. However, MKL-SRC only considers the within-class reconstruction residual while ignoring the between-class relationship, when learning the kernel weights. In this paper, we propose a novel multiple kernel sparse representation-based classifier (MKSRC), and then we use it as a criterion to design a multiple kernel sparse representation based orthogonal discriminative projection method (MK-SR-ODP). The proposed algorithm aims at learning a projection matrix and a corresponding kernel from the given base kernels such that in the low dimension subspace the between-class reconstruction residual is maximized and the within-class reconstruction residual is minimized. Furthermore, to achieve a minimum overall loss by performing recognition in the learned low-dimensional subspace, we introduce cost information into the dimensionality reduction method. The solutions for the proposed method can be efficiently found based on trace ratio optimization method [33]. Extensive experimental results demonstrate the superiority of the proposed algorithm when compared with the state-of-the-art methods.

Minimalist ensemble algorithms for genome-wide protein localization prediction.

PubMed

Lin, Jhih-Rong; Mondal, Ananda Mohan; Liu, Rong; Hu, Jianjun

2012-07-03

Computational prediction of protein subcellular localization can greatly help to elucidate its functions. Despite the existence of dozens of protein localization prediction algorithms, the prediction accuracy and coverage are still low. Several ensemble algorithms have been proposed to improve the prediction performance, which usually include as many as 10 or more individual localization algorithms. However, their performance is still limited by the running complexity and redundancy among individual prediction algorithms. This paper proposed a novel method for rational design of minimalist ensemble algorithms for practical genome-wide protein subcellular localization prediction. The algorithm is based on combining a feature selection based filter and a logistic regression classifier. Using a novel concept of contribution scores, we analyzed issues of algorithm redundancy, consensus mistakes, and algorithm complementarity in designing ensemble algorithms. We applied the proposed minimalist logistic regression (LR) ensemble algorithm to two genome-wide datasets of Yeast and Human and compared its performance with current ensemble algorithms. Experimental results showed that the minimalist ensemble algorithm can achieve high prediction accuracy with only 1/3 to 1/2 of individual predictors of current ensemble algorithms, which greatly reduces computational complexity and running time. It was found that the high performance ensemble algorithms are usually composed of the predictors that together cover most of available features. Compared to the best individual predictor, our ensemble algorithm improved the prediction accuracy from AUC score of 0.558 to 0.707 for the Yeast dataset and from 0.628 to 0.646 for the Human dataset. Compared with popular weighted voting based ensemble algorithms, our classifier-based ensemble algorithms achieved much better performance without suffering from inclusion of too many individual predictors. We proposed a method for rational design of minimalist ensemble algorithms using feature selection and classifiers. The proposed minimalist ensemble algorithm based on logistic regression can achieve equal or better prediction performance while using only half or one-third of individual predictors compared to other ensemble algorithms. The results also suggested that meta-predictors that take advantage of a variety of features by combining individual predictors tend to achieve the best performance. The LR ensemble server and related benchmark datasets are available at http://mleg.cse.sc.edu/LRensemble/cgi-bin/predict.cgi.

Minimalist ensemble algorithms for genome-wide protein localization prediction

PubMed Central

2012-01-01

Background Computational prediction of protein subcellular localization can greatly help to elucidate its functions. Despite the existence of dozens of protein localization prediction algorithms, the prediction accuracy and coverage are still low. Several ensemble algorithms have been proposed to improve the prediction performance, which usually include as many as 10 or more individual localization algorithms. However, their performance is still limited by the running complexity and redundancy among individual prediction algorithms. Results This paper proposed a novel method for rational design of minimalist ensemble algorithms for practical genome-wide protein subcellular localization prediction. The algorithm is based on combining a feature selection based filter and a logistic regression classifier. Using a novel concept of contribution scores, we analyzed issues of algorithm redundancy, consensus mistakes, and algorithm complementarity in designing ensemble algorithms. We applied the proposed minimalist logistic regression (LR) ensemble algorithm to two genome-wide datasets of Yeast and Human and compared its performance with current ensemble algorithms. Experimental results showed that the minimalist ensemble algorithm can achieve high prediction accuracy with only 1/3 to 1/2 of individual predictors of current ensemble algorithms, which greatly reduces computational complexity and running time. It was found that the high performance ensemble algorithms are usually composed of the predictors that together cover most of available features. Compared to the best individual predictor, our ensemble algorithm improved the prediction accuracy from AUC score of 0.558 to 0.707 for the Yeast dataset and from 0.628 to 0.646 for the Human dataset. Compared with popular weighted voting based ensemble algorithms, our classifier-based ensemble algorithms achieved much better performance without suffering from inclusion of too many individual predictors. Conclusions We proposed a method for rational design of minimalist ensemble algorithms using feature selection and classifiers. The proposed minimalist ensemble algorithm based on logistic regression can achieve equal or better prediction performance while using only half or one-third of individual predictors compared to other ensemble algorithms. The results also suggested that meta-predictors that take advantage of a variety of features by combining individual predictors tend to achieve the best performance. The LR ensemble server and related benchmark datasets are available at http://mleg.cse.sc.edu/LRensemble/cgi-bin/predict.cgi. PMID:22759391

Localization Algorithms of Underwater Wireless Sensor Networks: A Survey

PubMed Central

Han, Guangjie; Jiang, Jinfang; Shu, Lei; Xu, Yongjun; Wang, Feng

2012-01-01

In Underwater Wireless Sensor Networks (UWSNs), localization is one of most important technologies since it plays a critical role in many applications. Motivated by widespread adoption of localization, in this paper, we present a comprehensive survey of localization algorithms. First, we classify localization algorithms into three categories based on sensor nodes’ mobility: stationary localization algorithms, mobile localization algorithms and hybrid localization algorithms. Moreover, we compare the localization algorithms in detail and analyze future research directions of localization algorithms in UWSNs. PMID:22438752

Application of the pessimistic pruning to increase the accuracy of C4.5 algorithm in diagnosing chronic kidney disease

NASA Astrophysics Data System (ADS)

Muslim, M. A.; Herowati, A. J.; Sugiharti, E.; Prasetiyo, B.

2018-03-01

A technique to dig valuable information buried or hidden in data collection which is so big to be found an interesting patterns that was previously unknown is called data mining. Data mining has been applied in the healthcare industry. One technique used data mining is classification. The decision tree included in the classification of data mining and algorithm developed by decision tree is C4.5 algorithm. A classifier is designed using applying pessimistic pruning in C4.5 algorithm in diagnosing chronic kidney disease. Pessimistic pruning use to identify and remove branches that are not needed, this is done to avoid overfitting the decision tree generated by the C4.5 algorithm. In this paper, the result obtained using these classifiers are presented and discussed. Using pessimistic pruning shows increase accuracy of C4.5 algorithm of 1.5% from 95% to 96.5% in diagnosing of chronic kidney disease.

Automatic tissue characterization from ultrasound imagery

NASA Astrophysics Data System (ADS)

Kadah, Yasser M.; Farag, Aly A.; Youssef, Abou-Bakr M.; Badawi, Ahmed M.

1993-08-01

In this work, feature extraction algorithms are proposed to extract the tissue characterization parameters from liver images. Then the resulting parameter set is further processed to obtain the minimum number of parameters representing the most discriminating pattern space for classification. This preprocessing step was applied to over 120 pathology-investigated cases to obtain the learning data for designing the classifier. The extracted features are divided into independent training and test sets and are used to construct both statistical and neural classifiers. The optimal criteria for these classifiers are set to have minimum error, ease of implementation and learning, and the flexibility for future modifications. Various algorithms for implementing various classification techniques are presented and tested on the data. The best performance was obtained using a single layer tensor model functional link network. Also, the voting k-nearest neighbor classifier provided comparably good diagnostic rates.

A novel approach for dimension reduction of microarray.

PubMed

Aziz, Rabia; Verma, C K; Srivastava, Namita

2017-12-01

This paper proposes a new hybrid search technique for feature (gene) selection (FS) using Independent component analysis (ICA) and Artificial Bee Colony (ABC) called ICA+ABC, to select informative genes based on a Naïve Bayes (NB) algorithm. An important trait of this technique is the optimization of ICA feature vector using ABC. ICA+ABC is a hybrid search algorithm that combines the benefits of extraction approach, to reduce the size of data and wrapper approach, to optimize the reduced feature vectors. This hybrid search technique is facilitated by evaluating the performance of ICA+ABC on six standard gene expression datasets of classification. Extensive experiments were conducted to compare the performance of ICA+ABC with the results obtained from recently published Minimum Redundancy Maximum Relevance (mRMR) +ABC algorithm for NB classifier. Also to check the performance that how ICA+ABC works as feature selection with NB classifier, compared the combination of ICA with popular filter techniques and with other similar bio inspired algorithm such as Genetic Algorithm (GA) and Particle Swarm Optimization (PSO). The result shows that ICA+ABC has a significant ability to generate small subsets of genes from the ICA feature vector, that significantly improve the classification accuracy of NB classifier compared to other previously suggested methods. Copyright © 2017 Elsevier Ltd. All rights reserved.

Land cover and land use mapping of the iSimangaliso Wetland Park, South Africa: comparison of oblique and orthogonal random forest algorithms

NASA Astrophysics Data System (ADS)

Bassa, Zaakirah; Bob, Urmilla; Szantoi, Zoltan; Ismail, Riyad

2016-01-01

In recent years, the popularity of tree-based ensemble methods for land cover classification has increased significantly. Using WorldView-2 image data, we evaluate the potential of the oblique random forest algorithm (oRF) to classify a highly heterogeneous protected area. In contrast to the random forest (RF) algorithm, the oRF algorithm builds multivariate trees by learning the optimal split using a supervised model. The oRF binary algorithm is adapted to a multiclass land cover and land use application using both the "one-against-one" and "one-against-all" combination approaches. Results show that the oRF algorithms are capable of achieving high classification accuracies (>80%). However, there was no statistical difference in classification accuracies obtained by the oRF algorithms and the more popular RF algorithm. For all the algorithms, user accuracies (UAs) and producer accuracies (PAs) >80% were recorded for most of the classes. Both the RF and oRF algorithms poorly classified the indigenous forest class as indicated by the low UAs and PAs. Finally, the results from this study advocate and support the utility of the oRF algorithm for land cover and land use mapping of protected areas using WorldView-2 image data.

Using Gaussian mixture models to detect and classify dolphin whistles and pulses.

PubMed

Peso Parada, Pablo; Cardenal-López, Antonio

2014-06-01

In recent years, a number of automatic detection systems for free-ranging cetaceans have been proposed that aim to detect not just surfaced, but also submerged, individuals. These systems are typically based on pattern-recognition techniques applied to underwater acoustic recordings. Using a Gaussian mixture model, a classification system was developed that detects sounds in recordings and classifies them as one of four types: background noise, whistles, pulses, and combined whistles and pulses. The classifier was tested using a database of underwater recordings made off the Spanish coast during 2011. Using cepstral-coefficient-based parameterization, a sound detection rate of 87.5% was achieved for a 23.6% classification error rate. To improve these results, two parameters computed using the multiple signal classification algorithm and an unpredictability measure were included in the classifier. These parameters, which helped to classify the segments containing whistles, increased the detection rate to 90.3% and reduced the classification error rate to 18.1%. Finally, the potential of the multiple signal classification algorithm and unpredictability measure for estimating whistle contours and classifying cetacean species was also explored, with promising results.

WND-CHARM: Multi-purpose image classification using compound image transforms

PubMed Central

Orlov, Nikita; Shamir, Lior; Macura, Tomasz; Johnston, Josiah; Eckley, D. Mark; Goldberg, Ilya G.

2008-01-01

We describe a multi-purpose image classifier that can be applied to a wide variety of image classification tasks without modifications or fine-tuning, and yet provide classification accuracy comparable to state-of-the-art task-specific image classifiers. The proposed image classifier first extracts a large set of 1025 image features including polynomial decompositions, high contrast features, pixel statistics, and textures. These features are computed on the raw image, transforms of the image, and transforms of transforms of the image. The feature values are then used to classify test images into a set of pre-defined image classes. This classifier was tested on several different problems including biological image classification and face recognition. Although we cannot make a claim of universality, our experimental results show that this classifier performs as well or better than classifiers developed specifically for these image classification tasks. Our classifier’s high performance on a variety of classification problems is attributed to (i) a large set of features extracted from images; and (ii) an effective feature selection and weighting algorithm sensitive to specific image classification problems. The algorithms are available for free download from openmicroscopy.org. PMID:18958301

Online boosting for vehicle detection.

PubMed

Chang, Wen-Chung; Cho, Chih-Wei

2010-06-01

This paper presents a real-time vision-based vehicle detection system employing an online boosting algorithm. It is an online AdaBoost approach for a cascade of strong classifiers instead of a single strong classifier. Most existing cascades of classifiers must be trained offline and cannot effectively be updated when online tuning is required. The idea is to develop a cascade of strong classifiers for vehicle detection that is capable of being online trained in response to changing traffic environments. To make the online algorithm tractable, the proposed system must efficiently tune parameters based on incoming images and up-to-date performance of each weak classifier. The proposed online boosting method can improve system adaptability and accuracy to deal with novel types of vehicles and unfamiliar environments, whereas existing offline methods rely much more on extensive training processes to reach comparable results and cannot further be updated online. Our approach has been successfully validated in real traffic environments by performing experiments with an onboard charge-coupled-device camera in a roadway vehicle.

Classification of ligand molecules in PDB with fast heuristic graph match algorithm COMPLIG.

PubMed

Saito, Mihoko; Takemura, Naomi; Shirai, Tsuyoshi

2012-12-14

A fast heuristic graph-matching algorithm, COMPLIG, was devised to classify the small-molecule ligands in the Protein Data Bank (PDB), which are currently not properly classified on structure basis. By concurrently classifying proteins and ligands, we determined the most appropriate parameter for categorizing ligands to be more than 60% identity of atoms and bonds between molecules, and we classified 11,585 types of ligands into 1946 clusters. Although the large clusters were composed of nucleotides or amino acids, a significant presence of drug compounds was also observed. Application of the system to classify the natural ligand status of human proteins in the current database suggested that, at most, 37% of the experimental structures of human proteins were in complex with natural ligands. However, protein homology- and/or ligand similarity-based modeling was implied to provide models of natural interactions for an additional 28% of the total, which might be used to increase the knowledge of intrinsic protein-metabolite interactions. Copyright © 2012 Elsevier Ltd. All rights reserved.

Classifier fusion for VoIP attacks classification

NASA Astrophysics Data System (ADS)

Safarik, Jakub; Rezac, Filip

2017-05-01

SIP is one of the most successful protocols in the field of IP telephony communication. It establishes and manages VoIP calls. As the number of SIP implementation rises, we can expect a higher number of attacks on the communication system in the near future. This work aims at malicious SIP traffic classification. A number of various machine learning algorithms have been developed for attack classification. The paper presents a comparison of current research and the use of classifier fusion method leading to a potential decrease in classification error rate. Use of classifier combination makes a more robust solution without difficulties that may affect single algorithms. Different voting schemes, combination rules, and classifiers are discussed to improve the overall performance. All classifiers have been trained on real malicious traffic. The concept of traffic monitoring depends on the network of honeypot nodes. These honeypots run in several networks spread in different locations. Separation of honeypots allows us to gain an independent and trustworthy attack information.

Effects of cultural characteristics on building an emotion classifier through facial expression analysis

NASA Astrophysics Data System (ADS)

da Silva, Flávio Altinier Maximiano; Pedrini, Helio

2015-03-01

Facial expressions are an important demonstration of humanity's humors and emotions. Algorithms capable of recognizing facial expressions and associating them with emotions were developed and employed to compare the expressions that different cultural groups use to show their emotions. Static pictures of predominantly occidental and oriental subjects from public datasets were used to train machine learning algorithms, whereas local binary patterns, histogram of oriented gradients (HOGs), and Gabor filters were employed to describe the facial expressions for six different basic emotions. The most consistent combination, formed by the association of HOG filter and support vector machines, was then used to classify the other cultural group: there was a strong drop in accuracy, meaning that the subtle differences of facial expressions of each culture affected the classifier performance. Finally, a classifier was trained with images from both occidental and oriental subjects and its accuracy was higher on multicultural data, evidencing the need of a multicultural training set to build an efficient classifier.

Prediction of chemical biodegradability using support vector classifier optimized with differential evolution.

PubMed

Cao, Qi; Leung, K M

2014-09-22

Reliable computer models for the prediction of chemical biodegradability from molecular descriptors and fingerprints are very important for making health and environmental decisions. Coupling of the differential evolution (DE) algorithm with the support vector classifier (SVC) in order to optimize the main parameters of the classifier resulted in an improved classifier called the DE-SVC, which is introduced in this paper for use in chemical biodegradability studies. The DE-SVC was applied to predict the biodegradation of chemicals on the basis of extensive sample data sets and known structural features of molecules. Our optimization experiments showed that DE can efficiently find the proper parameters of the SVC. The resulting classifier possesses strong robustness and reliability compared with grid search, genetic algorithm, and particle swarm optimization methods. The classification experiments conducted here showed that the DE-SVC exhibits better classification performance than models previously used for such studies. It is a more effective and efficient prediction model for chemical biodegradability.

A Smartphone Indoor Localization Algorithm Based on WLAN Location Fingerprinting with Feature Extraction and Clustering.

PubMed

Luo, Junhai; Fu, Liang

2017-06-09

With the development of communication technology, the demand for location-based services is growing rapidly. This paper presents an algorithm for indoor localization based on Received Signal Strength (RSS), which is collected from Access Points (APs). The proposed localization algorithm contains the offline information acquisition phase and online positioning phase. Firstly, the AP selection algorithm is reviewed and improved based on the stability of signals to remove useless AP; secondly, Kernel Principal Component Analysis (KPCA) is analyzed and used to remove the data redundancy and maintain useful characteristics for nonlinear feature extraction; thirdly, the Affinity Propagation Clustering (APC) algorithm utilizes RSS values to classify data samples and narrow the positioning range. In the online positioning phase, the classified data will be matched with the testing data to determine the position area, and the Maximum Likelihood (ML) estimate will be employed for precise positioning. Eventually, the proposed algorithm is implemented in a real-world environment for performance evaluation. Experimental results demonstrate that the proposed algorithm improves the accuracy and computational complexity.

Classifier Subset Selection for the Stacked Generalization Method Applied to Emotion Recognition in Speech

PubMed Central

Álvarez, Aitor; Sierra, Basilio; Arruti, Andoni; López-Gil, Juan-Miguel; Garay-Vitoria, Nestor

2015-01-01

In this paper, a new supervised classification paradigm, called classifier subset selection for stacked generalization (CSS stacking), is presented to deal with speech emotion recognition. The new approach consists of an improvement of a bi-level multi-classifier system known as stacking generalization by means of an integration of an estimation of distribution algorithm (EDA) in the first layer to select the optimal subset from the standard base classifiers. The good performance of the proposed new paradigm was demonstrated over different configurations and datasets. First, several CSS stacking classifiers were constructed on the RekEmozio dataset, using some specific standard base classifiers and a total of 123 spectral, quality and prosodic features computed using in-house feature extraction algorithms. These initial CSS stacking classifiers were compared to other multi-classifier systems and the employed standard classifiers built on the same set of speech features. Then, new CSS stacking classifiers were built on RekEmozio using a different set of both acoustic parameters (extended version of the Geneva Minimalistic Acoustic Parameter Set (eGeMAPS)) and standard classifiers and employing the best meta-classifier of the initial experiments. The performance of these two CSS stacking classifiers was evaluated and compared. Finally, the new paradigm was tested on the well-known Berlin Emotional Speech database. We compared the performance of single, standard stacking and CSS stacking systems using the same parametrization of the second phase. All of the classifications were performed at the categorical level, including the six primary emotions plus the neutral one. PMID:26712757

Visual based laser speckle pattern recognition method for structural health monitoring

NASA Astrophysics Data System (ADS)

Park, Kyeongtaek; Torbol, Marco

2017-04-01

This study performed the system identification of a target structure by analyzing the laser speckle pattern taken by a camera. The laser speckle pattern is generated by the diffuse reflection of the laser beam on a rough surface of the target structure. The camera, equipped with a red filter, records the scattered speckle particles of the laser light in real time and the raw speckle image of the pixel data is fed to the graphic processing unit (GPU) in the system. The algorithm for laser speckle contrast analysis (LASCA) computes: the laser speckle contrast images and the laser speckle flow images. The k-mean clustering algorithm is used to classify the pixels in each frame and the clusters' centroids, which function as virtual sensors, track the displacement between different frames in time domain. The fast Fourier transform (FFT) and the frequency domain decomposition (FDD) compute the modal properties of the structure: natural frequencies and damping ratios. This study takes advantage of the large scale computational capability of GPU. The algorithm is written in Compute Unifies Device Architecture (CUDA C) that allows the processing of speckle images in real time.

A fresh look at functional link neural network for motor imagery-based brain-computer interface.

PubMed

Hettiarachchi, Imali T; Babaei, Toktam; Nguyen, Thanh; Lim, Chee P; Nahavandi, Saeid

2018-05-04

Artificial neural networks (ANNs) are one of the widely used classifiers in the brain-computer interface (BCI) systems-based on noninvasive electroencephalography (EEG) signals. Among the different ANN architectures, the most commonly applied for BCI classifiers is the multilayer perceptron (MLP). When appropriately designed with optimal number of neuron layers and number of neurons per layer, the ANN can act as a universal approximator. However, due to the low signal-to-noise ratio of EEG signal data, overtraining problem may become an inherent issue, causing these universal approximators to fail in real-time applications. In this study we introduce a higher order neural network, namely the functional link neural network (FLNN) as a classifier for motor imagery (MI)-based BCI systems, to remedy the drawbacks in MLP. We compare the proposed method with competing classifiers such as linear decomposition analysis, naïve Bayes, k-nearest neighbours, support vector machine and three MLP architectures. Two multi-class benchmark datasets from the BCI competitions are used. Common spatial pattern algorithm is utilized for feature extraction to build classification models. FLNN reports the highest average Kappa value over multiple subjects for both the BCI competition datasets, under similarly preprocessed data and extracted features. Further, statistical comparison results over multiple subjects show that the proposed FLNN classification method yields the best performance among the competing classifiers. Findings from this study imply that the proposed method, which has less computational complexity compared to the MLP, can be implemented effectively in practical MI-based BCI systems. Copyright © 2018 Elsevier B.V. All rights reserved.

Automatic Recognition of Acute Myelogenous Leukemia in Blood Microscopic Images Using K-means Clustering and Support Vector Machine.

PubMed

Kazemi, Fatemeh; Najafabadi, Tooraj Abbasian; Araabi, Babak Nadjar

2016-01-01

Acute myelogenous leukemia (AML) is a subtype of acute leukemia, which is characterized by the accumulation of myeloid blasts in the bone marrow. Careful microscopic examination of stained blood smear or bone marrow aspirate is still the most significant diagnostic methodology for initial AML screening and considered as the first step toward diagnosis. It is time-consuming and due to the elusive nature of the signs and symptoms of AML; wrong diagnosis may occur by pathologists. Therefore, the need for automation of leukemia detection has arisen. In this paper, an automatic technique for identification and detection of AML and its prevalent subtypes, i.e., M2-M5 is presented. At first, microscopic images are acquired from blood smears of patients with AML and normal cases. After applying image preprocessing, color segmentation strategy is applied for segmenting white blood cells from other blood components and then discriminative features, i.e., irregularity, nucleus-cytoplasm ratio, Hausdorff dimension, shape, color, and texture features are extracted from the entire nucleus in the whole images containing multiple nuclei. Images are classified to cancerous and noncancerous images by binary support vector machine (SVM) classifier with 10-fold cross validation technique. Classifier performance is evaluated by three parameters, i.e., sensitivity, specificity, and accuracy. Cancerous images are also classified into their prevalent subtypes by multi-SVM classifier. The results show that the proposed algorithm has achieved an acceptable performance for diagnosis of AML and its common subtypes. Therefore, it can be used as an assistant diagnostic tool for pathologists.

K-mean clustering algorithm for processing signals from compound semiconductor detectors

NASA Astrophysics Data System (ADS)

Tada, Tsutomu; Hitomi, Keitaro; Wu, Yan; Kim, Seong-Yun; Yamazaki, Hiromichi; Ishii, Keizo

2011-12-01

The K-mean clustering algorithm was employed for processing signal waveforms from TlBr detectors. The signal waveforms were classified based on its shape reflecting the charge collection process in the detector. The classified signal waveforms were processed individually to suppress the pulse height variation of signals due to the charge collection loss. The obtained energy resolution of a 137Cs spectrum measured with a 0.5 mm thick TlBr detector was 1.3% FWHM by employing 500 clusters.

Adaptive sleep-wake discrimination for wearable devices.

PubMed

Karlen, Walter; Floreano, Dario

2011-04-01

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

Fuzzy Nonlinear Proximal Support Vector Machine for Land Extraction Based on Remote Sensing Image

PubMed Central

Zhong, Xiaomei; Li, Jianping; Dou, Huacheng; Deng, Shijun; Wang, Guofei; Jiang, Yu; Wang, Yongjie; Zhou, Zebing; Wang, Li; Yan, Fei

2013-01-01

Currently, remote sensing technologies were widely employed in the dynamic monitoring of the land. This paper presented an algorithm named fuzzy nonlinear proximal support vector machine (FNPSVM) by basing on ETM+ remote sensing image. This algorithm is applied to extract various types of lands of the city Da’an in northern China. Two multi-category strategies, namely “one-against-one” and “one-against-rest” for this algorithm were described in detail and then compared. A fuzzy membership function was presented to reduce the effects of noises or outliers on the data samples. The approaches of feature extraction, feature selection, and several key parameter settings were also given. Numerous experiments were carried out to evaluate its performances including various accuracies (overall accuracies and kappa coefficient), stability, training speed, and classification speed. The FNPSVM classifier was compared to the other three classifiers including the maximum likelihood classifier (MLC), back propagation neural network (BPN), and the proximal support vector machine (PSVM) under different training conditions. The impacts of the selection of training samples, testing samples and features on the four classifiers were also evaluated in these experiments. PMID:23936016

Classification of fMRI resting-state maps using machine learning techniques: A comparative study

NASA Astrophysics Data System (ADS)

Gallos, Ioannis; Siettos, Constantinos

2017-11-01

We compare the efficiency of Principal Component Analysis (PCA) and nonlinear learning manifold algorithms (ISOMAP and Diffusion maps) for classifying brain maps between groups of schizophrenia patients and healthy from fMRI scans during a resting-state experiment. After a standard pre-processing pipeline, we applied spatial Independent component analysis (ICA) to reduce (a) noise and (b) spatial-temporal dimensionality of fMRI maps. On the cross-correlation matrix of the ICA components, we applied PCA, ISOMAP and Diffusion Maps to find an embedded low-dimensional space. Finally, support-vector-machines (SVM) and k-NN algorithms were used to evaluate the performance of the algorithms in classifying between the two groups.

False alarm reduction by the And-ing of multiple multivariate Gaussian classifiers

NASA Astrophysics Data System (ADS)

Dobeck, Gerald J.; Cobb, J. Tory

2003-09-01

The high-resolution sonar is one of the principal sensors used by the Navy to detect and classify sea mines in minehunting operations. For such sonar systems, substantial effort has been devoted to the development of automated detection and classification (D/C) algorithms. These have been spurred by several factors including (1) aids for operators to reduce work overload, (2) more optimal use of all available data, and (3) the introduction of unmanned minehunting systems. The environments where sea mines are typically laid (harbor areas, shipping lanes, and the littorals) give rise to many false alarms caused by natural, biologic, and man-made clutter. The objective of the automated D/C algorithms is to eliminate most of these false alarms while still maintaining a very high probability of mine detection and classification (PdPc). In recent years, the benefits of fusing the outputs of multiple D/C algorithms have been studied. We refer to this as Algorithm Fusion. The results have been remarkable, including reliable robustness to new environments. This paper describes a method for training several multivariate Gaussian classifiers such that their And-ing dramatically reduces false alarms while maintaining a high probability of classification. This training approach is referred to as the Focused- Training method. This work extends our 2001-2002 work where the Focused-Training method was used with three other types of classifiers: the Attractor-based K-Nearest Neighbor Neural Network (a type of radial-basis, probabilistic neural network), the Optimal Discrimination Filter Classifier (based linear discrimination theory), and the Quadratic Penalty Function Support Vector Machine (QPFSVM). Although our experience has been gained in the area of sea mine detection and classification, the principles described herein are general and can be applied to a wide range of pattern recognition and automatic target recognition (ATR) problems.

Random forests ensemble classifier trained with data resampling strategy to improve cardiac arrhythmia diagnosis.

PubMed

Ozçift, Akin

2011-05-01

Supervised classification algorithms are commonly used in the designing of computer-aided diagnosis systems. In this study, we present a resampling strategy based Random Forests (RF) ensemble classifier to improve diagnosis of cardiac arrhythmia. Random forests is an ensemble classifier that consists of many decision trees and outputs the class that is the mode of the class's output by individual trees. In this way, an RF ensemble classifier performs better than a single tree from classification performance point of view. In general, multiclass datasets having unbalanced distribution of sample sizes are difficult to analyze in terms of class discrimination. Cardiac arrhythmia is such a dataset that has multiple classes with small sample sizes and it is therefore adequate to test our resampling based training strategy. The dataset contains 452 samples in fourteen types of arrhythmias and eleven of these classes have sample sizes less than 15. Our diagnosis strategy consists of two parts: (i) a correlation based feature selection algorithm is used to select relevant features from cardiac arrhythmia dataset. (ii) RF machine learning algorithm is used to evaluate the performance of selected features with and without simple random sampling to evaluate the efficiency of proposed training strategy. The resultant accuracy of the classifier is found to be 90.0% and this is a quite high diagnosis performance for cardiac arrhythmia. Furthermore, three case studies, i.e., thyroid, cardiotocography and audiology, are used to benchmark the effectiveness of the proposed method. The results of experiments demonstrated the efficiency of random sampling strategy in training RF ensemble classification algorithm. Copyright © 2011 Elsevier Ltd. All rights reserved.

A multiscale curvature algorithm for classifying discrete return LiDAR in forested environments

Treesearch

Jeffrey S. Evans; Andrew T. Hudak

2007-01-01

One prerequisite to the use of light detection and ranging (LiDAR) across disciplines is differentiating ground from nonground returns. The objective was to automatically and objectively classify points within unclassified LiDAR point clouds, with few model parameters and minimal postprocessing. Presented is an automated method for classifying LiDAR returns as ground...

Support vector machines

NASA Technical Reports Server (NTRS)

Garay, Michael J.; Mazzoni, Dominic; Davies, Roger; Wagstaff, Kiri

2004-01-01

Support Vector Machines (SVMs) are a type of supervised learning algorith,, other examples of which are Artificial Neural Networks (ANNs), Decision Trees, and Naive Bayesian Classifiers. Supervised learning algorithms are used to classify objects labled by a 'supervisor' - typically a human 'expert.'.

Incorporating spatial context into statistical classification of multidimensional image data

NASA Technical Reports Server (NTRS)

Bauer, M. E. (Principal Investigator); Tilton, J. C.; Swain, P. H.

1981-01-01

Compound decision theory is employed to develop a general statistical model for classifying image data using spatial context. The classification algorithm developed from this model exploits the tendency of certain ground-cover classes to occur more frequently in some spatial contexts than in others. A key input to this contextural classifier is a quantitative characterization of this tendency: the context function. Several methods for estimating the context function are explored, and two complementary methods are recommended. The contextural classifier is shown to produce substantial improvements in classification accuracy compared to the accuracy produced by a non-contextural uniform-priors maximum likelihood classifier when these methods of estimating the context function are used. An approximate algorithm, which cuts computational requirements by over one-half, is presented. The search for an optimal implementation is furthered by an exploration of the relative merits of using spectral classes or information classes for classification and/or context function estimation.

Comparative Analysis of Document level Text Classification Algorithms using R

NASA Astrophysics Data System (ADS)

Syamala, Maganti; Nalini, N. J., Dr; Maguluri, Lakshamanaphaneendra; Ragupathy, R., Dr.

2017-08-01

From the past few decades there has been tremendous volumes of data available in Internet either in structured or unstructured form. Also, there is an exponential growth of information on Internet, so there is an emergent need of text classifiers. Text mining is an interdisciplinary field which draws attention on information retrieval, data mining, machine learning, statistics and computational linguistics. And to handle this situation, a wide range of supervised learning algorithms has been introduced. Among all these K-Nearest Neighbor(KNN) is efficient and simplest classifier in text classification family. But KNN suffers from imbalanced class distribution and noisy term features. So, to cope up with this challenge we use document based centroid dimensionality reduction(CentroidDR) using R Programming. By combining these two text classification techniques, KNN and Centroid classifiers, we propose a scalable and effective flat classifier, called MCenKNN which works well substantially better than CenKNN.

A Theoretical Analysis of Why Hybrid Ensembles Work.

PubMed

Hsu, Kuo-Wei

2017-01-01

Inspired by the group decision making process, ensembles or combinations of classifiers have been found favorable in a wide variety of application domains. Some researchers propose to use the mixture of two different types of classification algorithms to create a hybrid ensemble. Why does such an ensemble work? The question remains. Following the concept of diversity, which is one of the fundamental elements of the success of ensembles, we conduct a theoretical analysis of why hybrid ensembles work, connecting using different algorithms to accuracy gain. We also conduct experiments on classification performance of hybrid ensembles of classifiers created by decision tree and naïve Bayes classification algorithms, each of which is a top data mining algorithm and often used to create non-hybrid ensembles. Therefore, through this paper, we provide a complement to the theoretical foundation of creating and using hybrid ensembles.

Evaluation and reformulation of the maximum peak height algorithm (MPH) and application in a hypertrophic lagoon

NASA Astrophysics Data System (ADS)

Pitarch, Jaime; Ruiz-Verdú, Antonio; Sendra, María. D.; Santoleri, Rosalia

2017-02-01

We studied the performance of the MERIS maximum peak height (MPH) algorithm in the retrieval of chlorophyll-a concentration (CHL), using a matchup data set of Bottom-of-Rayleigh Reflectances (BRR) and CHL from a hypertrophic lake (Albufera de Valencia). The MPH algorithm produced a slight underestimation of CHL in the pixels classified as cyanobacteria (83% of the total) and a strong overestimation in those classified as eukaryotic phytoplankton (17%). In situ biomass data showed that the binary classification of MPH was not appropriate for mixed phytoplankton populations, producing also unrealistic discontinuities in the CHL maps. We recalibrated MPH using our matchup data set and found that a single calibration curve of third degree fitted equally well to all matchups regardless of how they were classified. As a modification to the former approach, we incorporated the Phycocyanin Index (PCI) in the formula, thus taking into account the gradient of phytoplankton composition, which reduced the CHL retrieval errors. By using in situ biomass data, we also proved that PCI was indeed an indicator of cyanobacterial dominance. We applied our recalibration of the MPH algorithm to the whole MERIS data set (2002-2012). Results highlight the usefulness of the MPH algorithm as a tool to monitor eutrophication. The relevance of this fact is higher since MPH does not require a complete atmospheric correction, which often fails over such waters. An adequate flagging or correction of sun glint is advisable though, since the MPH algorithm was sensitive to sun glint.

Ant-cuckoo colony optimization for feature selection in digital mammogram.

PubMed

Jona, J B; Nagaveni, N

2014-01-15

Digital mammogram is the only effective screening method to detect the breast cancer. Gray Level Co-occurrence Matrix (GLCM) textural features are extracted from the mammogram. All the features are not essential to detect the mammogram. Therefore identifying the relevant feature is the aim of this work. Feature selection improves the classification rate and accuracy of any classifier. In this study, a new hybrid metaheuristic named Ant-Cuckoo Colony Optimization a hybrid of Ant Colony Optimization (ACO) and Cuckoo Search (CS) is proposed for feature selection in Digital Mammogram. ACO is a good metaheuristic optimization technique but the drawback of this algorithm is that the ant will walk through the path where the pheromone density is high which makes the whole process slow hence CS is employed to carry out the local search of ACO. Support Vector Machine (SVM) classifier with Radial Basis Kernal Function (RBF) is done along with the ACO to classify the normal mammogram from the abnormal mammogram. Experiments are conducted in miniMIAS database. The performance of the new hybrid algorithm is compared with the ACO and PSO algorithm. The results show that the hybrid Ant-Cuckoo Colony Optimization algorithm is more accurate than the other techniques.

Spatial Statistics for Tumor Cell Counting and Classification

NASA Astrophysics Data System (ADS)

Wirjadi, Oliver; Kim, Yoo-Jin; Breuel, Thomas

To count and classify cells in histological sections is a standard task in histology. One example is the grading of meningiomas, benign tumors of the meninges, which requires to assess the fraction of proliferating cells in an image. As this process is very time consuming when performed manually, automation is required. To address such problems, we propose a novel application of Markov point process methods in computer vision, leading to algorithms for computing the locations of circular objects in images. In contrast to previous algorithms using such spatial statistics methods in image analysis, the present one is fully trainable. This is achieved by combining point process methods with statistical classifiers. Using simulated data, the method proposed in this paper will be shown to be more accurate and more robust to noise than standard image processing methods. On the publicly available SIMCEP benchmark for cell image analysis algorithms, the cell count performance of the present paper is significantly more accurate than results published elsewhere, especially when cells form dense clusters. Furthermore, the proposed system performs as well as a state-of-the-art algorithm for the computer-aided histological grading of meningiomas when combined with a simple k-nearest neighbor classifier for identifying proliferating cells.

Feature Augmentation via Nonparametrics and Selection (FANS) in High-Dimensional Classification.

PubMed

Fan, Jianqing; Feng, Yang; Jiang, Jiancheng; Tong, Xin

We propose a high dimensional classification method that involves nonparametric feature augmentation. Knowing that marginal density ratios are the most powerful univariate classifiers, we use the ratio estimates to transform the original feature measurements. Subsequently, penalized logistic regression is invoked, taking as input the newly transformed or augmented features. This procedure trains models equipped with local complexity and global simplicity, thereby avoiding the curse of dimensionality while creating a flexible nonlinear decision boundary. The resulting method is called Feature Augmentation via Nonparametrics and Selection (FANS). We motivate FANS by generalizing the Naive Bayes model, writing the log ratio of joint densities as a linear combination of those of marginal densities. It is related to generalized additive models, but has better interpretability and computability. Risk bounds are developed for FANS. In numerical analysis, FANS is compared with competing methods, so as to provide a guideline on its best application domain. Real data analysis demonstrates that FANS performs very competitively on benchmark email spam and gene expression data sets. Moreover, FANS is implemented by an extremely fast algorithm through parallel computing.

Feature Augmentation via Nonparametrics and Selection (FANS) in High-Dimensional Classification

PubMed Central

Feng, Yang; Jiang, Jiancheng; Tong, Xin

2015-01-01

We propose a high dimensional classification method that involves nonparametric feature augmentation. Knowing that marginal density ratios are the most powerful univariate classifiers, we use the ratio estimates to transform the original feature measurements. Subsequently, penalized logistic regression is invoked, taking as input the newly transformed or augmented features. This procedure trains models equipped with local complexity and global simplicity, thereby avoiding the curse of dimensionality while creating a flexible nonlinear decision boundary. The resulting method is called Feature Augmentation via Nonparametrics and Selection (FANS). We motivate FANS by generalizing the Naive Bayes model, writing the log ratio of joint densities as a linear combination of those of marginal densities. It is related to generalized additive models, but has better interpretability and computability. Risk bounds are developed for FANS. In numerical analysis, FANS is compared with competing methods, so as to provide a guideline on its best application domain. Real data analysis demonstrates that FANS performs very competitively on benchmark email spam and gene expression data sets. Moreover, FANS is implemented by an extremely fast algorithm through parallel computing. PMID:27185970

Assessment of target detection limits in hyperspectral data

NASA Astrophysics Data System (ADS)

Gross, W.; Boehler, J.; Schilling, H.; Middelmann, W.; Weyermann, J.; Wellig, P.; Oechslin, R.; Kneubuehler, M.

2015-10-01

Hyperspectral remote sensing data can be used for civil and military applications to detect and classify target objects that cannot be reliably separated using broadband sensors. The comparably low spatial resolution is compensated by the fact that small targets, even below image resolution, can still be classified. The goal of this paper is to determine the target size to spatial resolution ratio for successful classification of different target and background materials. Airborne hyperspectral data is used to simulate data with known mixture ratios and to estimate the detection threshold for given false alarm rates. The data was collected in July 2014 over Greding, Germany, using airborne aisaEAGLE and aisaHAWK hyperspectral sensors. On the ground, various target materials were placed on natural background. The targets were four quadratic molton patches with an edge length of 7 meters in the colors black, white, grey and green. Also, two different types of polyethylene (camouflage nets) with an edge length of approximately 5.5 meters were deployed. Synthetic data is generated from the original data using spectral mixtures. Target signatures are linearly combined with different background materials in specific ratios. The simulated mixtures are appended to the original data and the target areas are removed for evaluation. Commonly used classification algorithms, e.g. Matched Filtering, Adaptive Cosine Estimator are used to determine the detection limit. Fixed false alarm rates are employed to find and analyze certain regions where false alarms usually occur first. A combination of 18 targets and 12 backgrounds is analyzed for three VNIR and two SWIR data sets of the same area.

Hydrologic classification of rivers based on cluster analysis of dimensionless hydrologic signatures: Applications for environmental instream flows

NASA Astrophysics Data System (ADS)

Praskievicz, S. J.; Luo, C.

2017-12-01

Classification of rivers is useful for a variety of purposes, such as generating and testing hypotheses about watershed controls on hydrology, predicting hydrologic variables for ungaged rivers, and setting goals for river management. In this research, we present a bottom-up (based on machine learning) river classification designed to investigate the underlying physical processes governing rivers' hydrologic regimes. The classification was developed for the entire state of Alabama, based on 248 United States Geological Survey (USGS) stream gages that met criteria for length and completeness of records. Five dimensionless hydrologic signatures were derived for each gage: slope of the flow duration curve (indicator of flow variability), baseflow index (ratio of baseflow to average streamflow), rising limb density (number of rising limbs per unit time), runoff ratio (ratio of long-term average streamflow to long-term average precipitation), and streamflow elasticity (sensitivity of streamflow to precipitation). We used a Bayesian clustering algorithm to classify the gages, based on the five hydrologic signatures, into distinct hydrologic regimes. We then used classification and regression trees (CART) to predict each gaged river's membership in different hydrologic regimes based on climatic and watershed variables. Using existing geospatial data, we applied the CART analysis to classify ungaged streams in Alabama, with the National Hydrography Dataset Plus (NHDPlus) catchment (average area 3 km2) as the unit of classification. The results of the classification can be used for meeting management and conservation objectives in Alabama, such as developing statewide standards for environmental instream flows. Such hydrologic classification approaches are promising for contributing to process-based understanding of river systems.

Automatic classification of protein structures using physicochemical parameters.

PubMed

Mohan, Abhilash; Rao, M Divya; Sunderrajan, Shruthi; Pennathur, Gautam

2014-09-01

Protein classification is the first step to functional annotation; SCOP and Pfam databases are currently the most relevant protein classification schemes. However, the disproportion in the number of three dimensional (3D) protein structures generated versus their classification into relevant superfamilies/families emphasizes the need for automated classification schemes. Predicting function of novel proteins based on sequence information alone has proven to be a major challenge. The present study focuses on the use of physicochemical parameters in conjunction with machine learning algorithms (Naive Bayes, Decision Trees, Random Forest and Support Vector Machines) to classify proteins into their respective SCOP superfamily/Pfam family, using sequence derived information. Spectrophores™, a 1D descriptor of the 3D molecular field surrounding a structure was used as a benchmark to compare the performance of the physicochemical parameters. The machine learning algorithms were modified to select features based on information gain for each SCOP superfamily/Pfam family. The effect of combining physicochemical parameters and spectrophores on classification accuracy (CA) was studied. Machine learning algorithms trained with the physicochemical parameters consistently classified SCOP superfamilies and Pfam families with a classification accuracy above 90%, while spectrophores performed with a CA of around 85%. Feature selection improved classification accuracy for both physicochemical parameters and spectrophores based machine learning algorithms. Combining both attributes resulted in a marginal loss of performance. Physicochemical parameters were able to classify proteins from both schemes with classification accuracy ranging from 90-96%. These results suggest the usefulness of this method in classifying proteins from amino acid sequences.

Assessing the Ability of Vegetation Indices to Identify Shallow Subsurface Water Flow Pathways from Hyperspectral Imagery Using Machine Learning: Methodology

NASA Astrophysics Data System (ADS)

Byers, J. M.; Doctor, K.

2017-12-01

A common application of the satellite and airborne acquired hyperspectral imagery in the visible and NIR spectrum is the assessment of vegetation. Various absorption features of plants related to both water and chlorophyll content can be used to measure the vigor and access to underlying water sources of the vegetation. The typical strategy is to form hand-crafted features from the hyperspectral data cube by selecting two wavelengths to form difference or ratio images in the pixel space. The new image attempts to provide greater contrast for some feature of the vegetation. The Normalized Difference Vegetation Index (NDVI) is a widely used example formed from the ratio of differences and sums at two different wavelengths. There are dozens of these indices that are ostensibly formed using insights about the underlying physics of the spectral absorption with claims to efficacy in representing various properties of vegetation. In the language of machine learning these vegetation indices are features that can be used as a useful data representation within an algorithm. In this work we use a powerful approach from machine learning, probabilistic graphical models (PGM), to balance the competing needs of using existing hydrological classifications of terrain while finding statistically reliable features within hyperspectral data for identifying the generative process of the data. The algorithm in its simplest form is called a Naïve Bayes (NB) classifier and can be constructed in a data-driven estimation procedure of the conditional probability distributions that form the PGM. The Naïve Bayes model assumes that all vegetation indices (VI) are independent of one another given the hydrological class label. We seek to test its validity in a pilot study of detecting subsurface water flow pathways from VI. A more sophisticated PGM will also be explored called a tree-augmented NB that accounts for the probabilistic dependence between VI features. This methodology provides a general approach for classifying hydrological structures from hyperspectral data.

MEMS-based sensing and algorithm development for fall detection and gait analysis

NASA Astrophysics Data System (ADS)

Gupta, Piyush; Ramirez, Gabriel; Lie, Donald Y. C.; Dallas, Tim; Banister, Ron E.; Dentino, Andrew

2010-02-01

Falls by the elderly are highly detrimental to health, frequently resulting in injury, high medical costs, and even death. Using a MEMS-based sensing system, algorithms are being developed for detecting falls and monitoring the gait of elderly and disabled persons. In this study, wireless sensors utilize Zigbee protocols were incorporated into planar shoe insoles and a waist mounted device. The insole contains four sensors to measure pressure applied by the foot. A MEMS based tri-axial accelerometer is embedded in the insert and a second one is utilized by the waist mounted device. The primary fall detection algorithm is derived from the waist accelerometer. The differential acceleration is calculated from samples received in 1.5s time intervals. This differential acceleration provides the quantification via an energy index. From this index one may ascertain different gait and identify fall events. Once a pre-determined index threshold is exceeded, the algorithm will classify an event as a fall or a stumble. The secondary algorithm is derived from frequency analysis techniques. The analysis consists of wavelet transforms conducted on the waist accelerometer data. The insole pressure data is then used to underline discrepancies in the transforms, providing more accurate data for classifying gait and/or detecting falls. The range of the transform amplitude in the fourth iteration of a Daubechies-6 transform was found sufficient to detect and classify fall events.

A Robust Step Detection Algorithm and Walking Distance Estimation Based on Daily Wrist Activity Recognition Using a Smart Band.

PubMed

Trong Bui, Duong; Nguyen, Nhan Duc; Jeong, Gu-Min

2018-06-25

Human activity recognition and pedestrian dead reckoning are an interesting field because of their importance utilities in daily life healthcare. Currently, these fields are facing many challenges, one of which is the lack of a robust algorithm with high performance. This paper proposes a new method to implement a robust step detection and adaptive distance estimation algorithm based on the classification of five daily wrist activities during walking at various speeds using a smart band. The key idea is that the non-parametric adaptive distance estimator is performed after two activity classifiers and a robust step detector. In this study, two classifiers perform two phases of recognizing five wrist activities during walking. Then, a robust step detection algorithm, which is integrated with an adaptive threshold, peak and valley correction algorithm, is applied to the classified activities to detect the walking steps. In addition, the misclassification activities are fed back to the previous layer. Finally, three adaptive distance estimators, which are based on a non-parametric model of the average walking speed, calculate the length of each strike. The experimental results show that the average classification accuracy is about 99%, and the accuracy of the step detection is 98.7%. The error of the estimated distance is 2.2⁻4.2% depending on the type of wrist activities.

Adaptive sequential Bayesian classification using Page's test

NASA Astrophysics Data System (ADS)

Lynch, Robert S., Jr.; Willett, Peter K.

2002-03-01

In this paper, the previously introduced Mean-Field Bayesian Data Reduction Algorithm is extended for adaptive sequential hypothesis testing utilizing Page's test. In general, Page's test is well understood as a method of detecting a permanent change in distribution associated with a sequence of observations. However, the relationship between detecting a change in distribution utilizing Page's test with that of classification and feature fusion is not well understood. Thus, the contribution of this work is based on developing a method of classifying an unlabeled vector of fused features (i.e., detect a change to an active statistical state) as quickly as possible given an acceptable mean time between false alerts. In this case, the developed classification test can be thought of as equivalent to performing a sequential probability ratio test repeatedly until a class is decided, with the lower log-threshold of each test being set to zero and the upper log-threshold being determined by the expected distance between false alerts. It is of interest to estimate the delay (or, related stopping time) to a classification decision (the number of time samples it takes to classify the target), and the mean time between false alerts, as a function of feature selection and fusion by the Mean-Field Bayesian Data Reduction Algorithm. Results are demonstrated by plotting the delay to declaring the target class versus the mean time between false alerts, and are shown using both different numbers of simulated training data and different numbers of relevant features for each class.

Comparative study of classification algorithms for damage classification in smart composite laminates

NASA Astrophysics Data System (ADS)

Khan, Asif; Ryoo, Chang-Kyung; Kim, Heung Soo

2017-04-01

This paper presents a comparative study of different classification algorithms for the classification of various types of inter-ply delaminations in smart composite laminates. Improved layerwise theory is used to model delamination at different interfaces along the thickness and longitudinal directions of the smart composite laminate. The input-output data obtained through surface bonded piezoelectric sensor and actuator is analyzed by the system identification algorithm to get the system parameters. The identified parameters for the healthy and delaminated structure are supplied as input data to the classification algorithms. The classification algorithms considered in this study are ZeroR, Classification via regression, Naïve Bayes, Multilayer Perceptron, Sequential Minimal Optimization, Multiclass-Classifier, and Decision tree (J48). The open source software of Waikato Environment for Knowledge Analysis (WEKA) is used to evaluate the classification performance of the classifiers mentioned above via 75-25 holdout and leave-one-sample-out cross-validation regarding classification accuracy, precision, recall, kappa statistic and ROC Area.

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

PubMed

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

2011-02-01

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

Structure and weights optimisation of a modified Elman network emotion classifier using hybrid computational intelligence algorithms: a comparative study

NASA Astrophysics Data System (ADS)

Sheikhan, Mansour; Abbasnezhad Arabi, Mahdi; Gharavian, Davood

2015-10-01

Artificial neural networks are efficient models in pattern recognition applications, but their performance is dependent on employing suitable structure and connection weights. This study used a hybrid method for obtaining the optimal weight set and architecture of a recurrent neural emotion classifier based on gravitational search algorithm (GSA) and its binary version (BGSA), respectively. By considering the features of speech signal that were related to prosody, voice quality, and spectrum, a rich feature set was constructed. To select more efficient features, a fast feature selection method was employed. The performance of the proposed hybrid GSA-BGSA method was compared with similar hybrid methods based on particle swarm optimisation (PSO) algorithm and its binary version, PSO and discrete firefly algorithm, and hybrid of error back-propagation and genetic algorithm that were used for optimisation. Experimental tests on Berlin emotional database demonstrated the superior performance of the proposed method using a lighter network structure.

Mixture of learners for cancer stem cell detection using CD13 and H and E stained images

NASA Astrophysics Data System (ADS)

Oǧuz, Oǧuzhan; Akbaş, Cem Emre; Mallah, Maen; Taşdemir, Kasım.; Akhan Güzelcan, Ece; Muenzenmayer, Christian; Wittenberg, Thomas; Üner, Ayşegül; Cetin, A. E.; ćetin Atalay, Rengül

2016-03-01

In this article, algorithms for cancer stem cell (CSC) detection in liver cancer tissue images are developed. Conventionally, a pathologist examines of cancer cell morphologies under microscope. Computer aided diagnosis systems (CAD) aims to help pathologists in this tedious and repetitive work. The first algorithm locates CSCs in CD13 stained liver tissue images. The method has also an online learning algorithm to improve the accuracy of detection. The second family of algorithms classify the cancer tissues stained with H and E which is clinically routine and cost effective than immunohistochemistry (IHC) procedure. The algorithms utilize 1D-SIFT and Eigen-analysis based feature sets as descriptors. Normal and cancerous tissues can be classified with 92.1% accuracy in H and E stained images. Classification accuracy of low and high-grade cancerous tissue images is 70.4%. Therefore, this study paves the way for diagnosing the cancerous tissue and grading the level of it using H and E stained microscopic tissue images.

Diagnostic Accuracy Comparison of Artificial Immune Algorithms for Primary Headaches.

PubMed

Çelik, Ufuk; Yurtay, Nilüfer; Koç, Emine Rabia; Tepe, Nermin; Güllüoğlu, Halil; Ertaş, Mustafa

2015-01-01

The present study evaluated the diagnostic accuracy of immune system algorithms with the aim of classifying the primary types of headache that are not related to any organic etiology. They are divided into four types: migraine, tension, cluster, and other primary headaches. After we took this main objective into consideration, three different neurologists were required to fill in the medical records of 850 patients into our web-based expert system hosted on our project web site. In the evaluation process, Artificial Immune Systems (AIS) were used as the classification algorithms. The AIS are classification algorithms that are inspired by the biological immune system mechanism that involves significant and distinct capabilities. These algorithms simulate the specialties of the immune system such as discrimination, learning, and the memorizing process in order to be used for classification, optimization, or pattern recognition. According to the results, the accuracy level of the classifier used in this study reached a success continuum ranging from 95% to 99%, except for the inconvenient one that yielded 71% accuracy.

Methods to Develop an Electronic Medical Record Phenotype Algorithm to Compare the Risk of Coronary Artery Disease across 3 Chronic Disease Cohorts.

PubMed

Liao, Katherine P; Ananthakrishnan, Ashwin N; Kumar, Vishesh; Xia, Zongqi; Cagan, Andrew; Gainer, Vivian S; Goryachev, Sergey; Chen, Pei; Savova, Guergana K; Agniel, Denis; Churchill, Susanne; Lee, Jaeyoung; Murphy, Shawn N; Plenge, Robert M; Szolovits, Peter; Kohane, Isaac; Shaw, Stanley Y; Karlson, Elizabeth W; Cai, Tianxi

2015-01-01

Typically, algorithms to classify phenotypes using electronic medical record (EMR) data were developed to perform well in a specific patient population. There is increasing interest in analyses which can allow study of a specific outcome across different diseases. Such a study in the EMR would require an algorithm that can be applied across different patient populations. Our objectives were: (1) to develop an algorithm that would enable the study of coronary artery disease (CAD) across diverse patient populations; (2) to study the impact of adding narrative data extracted using natural language processing (NLP) in the algorithm. Additionally, we demonstrate how to implement CAD algorithm to compare risk across 3 chronic diseases in a preliminary study. We studied 3 established EMR based patient cohorts: diabetes mellitus (DM, n = 65,099), inflammatory bowel disease (IBD, n = 10,974), and rheumatoid arthritis (RA, n = 4,453) from two large academic centers. We developed a CAD algorithm using NLP in addition to structured data (e.g. ICD9 codes) in the RA cohort and validated it in the DM and IBD cohorts. The CAD algorithm using NLP in addition to structured data achieved specificity >95% with a positive predictive value (PPV) 90% in the training (RA) and validation sets (IBD and DM). The addition of NLP data improved the sensitivity for all cohorts, classifying an additional 17% of CAD subjects in IBD and 10% in DM while maintaining PPV of 90%. The algorithm classified 16,488 DM (26.1%), 457 IBD (4.2%), and 245 RA (5.0%) with CAD. In a cross-sectional analysis, CAD risk was 63% lower in RA and 68% lower in IBD compared to DM (p<0.0001) after adjusting for traditional cardiovascular risk factors. We developed and validated a CAD algorithm that performed well across diverse patient populations. The addition of NLP into the CAD algorithm improved the sensitivity of the algorithm, particularly in cohorts where the prevalence of CAD was low. Preliminary data suggest that CAD risk was significantly lower in RA and IBD compared to DM.

Methods to Develop an Electronic Medical Record Phenotype Algorithm to Compare the Risk of Coronary Artery Disease across 3 Chronic Disease Cohorts

PubMed Central

Liao, Katherine P.; Ananthakrishnan, Ashwin N.; Kumar, Vishesh; Xia, Zongqi; Cagan, Andrew; Gainer, Vivian S.; Goryachev, Sergey; Chen, Pei; Savova, Guergana K.; Agniel, Denis; Churchill, Susanne; Lee, Jaeyoung; Murphy, Shawn N.; Plenge, Robert M.; Szolovits, Peter; Kohane, Isaac; Shaw, Stanley Y.; Karlson, Elizabeth W.; Cai, Tianxi

2015-01-01

Background Typically, algorithms to classify phenotypes using electronic medical record (EMR) data were developed to perform well in a specific patient population. There is increasing interest in analyses which can allow study of a specific outcome across different diseases. Such a study in the EMR would require an algorithm that can be applied across different patient populations. Our objectives were: (1) to develop an algorithm that would enable the study of coronary artery disease (CAD) across diverse patient populations; (2) to study the impact of adding narrative data extracted using natural language processing (NLP) in the algorithm. Additionally, we demonstrate how to implement CAD algorithm to compare risk across 3 chronic diseases in a preliminary study. Methods and Results We studied 3 established EMR based patient cohorts: diabetes mellitus (DM, n = 65,099), inflammatory bowel disease (IBD, n = 10,974), and rheumatoid arthritis (RA, n = 4,453) from two large academic centers. We developed a CAD algorithm using NLP in addition to structured data (e.g. ICD9 codes) in the RA cohort and validated it in the DM and IBD cohorts. The CAD algorithm using NLP in addition to structured data achieved specificity >95% with a positive predictive value (PPV) 90% in the training (RA) and validation sets (IBD and DM). The addition of NLP data improved the sensitivity for all cohorts, classifying an additional 17% of CAD subjects in IBD and 10% in DM while maintaining PPV of 90%. The algorithm classified 16,488 DM (26.1%), 457 IBD (4.2%), and 245 RA (5.0%) with CAD. In a cross-sectional analysis, CAD risk was 63% lower in RA and 68% lower in IBD compared to DM (p<0.0001) after adjusting for traditional cardiovascular risk factors. Conclusions We developed and validated a CAD algorithm that performed well across diverse patient populations. The addition of NLP into the CAD algorithm improved the sensitivity of the algorithm, particularly in cohorts where the prevalence of CAD was low. Preliminary data suggest that CAD risk was significantly lower in RA and IBD compared to DM. PMID:26301417

Algorithmic Puzzles: History, Taxonomies, and Applications in Human Problem Solving

ERIC Educational Resources Information Center

Levitin, Anany

2017-01-01

The paper concerns an important but underappreciated genre of algorithmic puzzles, explaining what these puzzles are, reviewing milestones in their long history, and giving two different ways to classify them. Also covered are major applications of algorithmic puzzles in cognitive science research, with an emphasis on insight problem solving, and…

Challenges in congenital syphilis surveillance: how are congenital syphilis investigations classified?

PubMed

Introcaso, Camille E; Gruber, DeAnn; Bradley, Heather; Peterman, Thomas A; Ewell, Joy; Wendell, Debbie; Foxhood, Joseph; Su, John R; Weinstock, Hillard S; Markowitz, Lauri E

2013-09-01

Congenital syphilis is a serious, preventable, and nationally notifiable disease. Despite the existence of a surveillance case definition, congenital syphilis is sometimes classified differently using an algorithm on the Centers for Disease Control and Prevention's case reporting form. We reviewed Louisiana's congenital syphilis electronic reporting system for investigations of infants born from January 2010 to October 2011, abstracted data required for classification, and applied the surveillance definition and the algorithm. We calculated the sensitivities and specificities of the algorithm and Louisiana's classification using the surveillance definition as the surveillance gold standard. Among 349 congenital syphilis investigations, the surveillance definition identified 62 cases. The algorithm had a sensitivity of 91.9% and a specificity of 64.1%. Louisiana's classification had a sensitivity of 50% and a specificity of 91.3% compared with the surveillance definition. The differences between the algorithm and the surveillance definition led to misclassification of congenital syphilis cases. The algorithm should match the surveillance definition. Other state and local health departments should assure that their reported cases meet the surveillance definition.

Infrared dim-small target tracking via singular value decomposition and improved Kernelized correlation filter

NASA Astrophysics Data System (ADS)

Qian, Kun; Zhou, Huixin; Rong, Shenghui; Wang, Bingjian; Cheng, Kuanhong

2017-05-01

Infrared small target tracking plays an important role in applications including military reconnaissance, early warning and terminal guidance. In this paper, an effective algorithm based on the Singular Value Decomposition (SVD) and the improved Kernelized Correlation Filter (KCF) is presented for infrared small target tracking. Firstly, the super performance of the SVD-based algorithm is that it takes advantage of the target's global information and obtains a background estimation of an infrared image. A dim target is enhanced by subtracting the corresponding estimated background with update from the original image. Secondly, the KCF algorithm is combined with Gaussian Curvature Filter (GCF) to eliminate the excursion problem. The GCF technology is adopted to preserve the edge and eliminate the noise of the base sample in the KCF algorithm, helping to calculate the classifier parameter for a small target. At last, the target position is estimated with a response map, which is obtained via the kernelized classifier. Experimental results demonstrate that the presented algorithm performs favorably in terms of efficiency and accuracy, compared with several state-of-the-art algorithms.

Successive Projections Algorithm-Multivariable Linear Regression Classifier for the Detection of Contaminants on Chicken Carcasses in Hyperspectral Images

NASA Astrophysics Data System (ADS)

Wu, W.; Chen, G. Y.; Kang, R.; Xia, J. C.; Huang, Y. P.; Chen, K. J.

2017-07-01

During slaughtering and further processing, chicken carcasses are inevitably contaminated by microbial pathogen contaminants. Due to food safety concerns, many countries implement a zero-tolerance policy that forbids the placement of visibly contaminated carcasses in ice-water chiller tanks during processing. Manual detection of contaminants is labor consuming and imprecise. Here, a successive projections algorithm (SPA)-multivariable linear regression (MLR) classifier based on an optimal performance threshold was developed for automatic detection of contaminants on chicken carcasses. Hyperspectral images were obtained using a hyperspectral imaging system. A regression model of the classifier was established by MLR based on twelve characteristic wavelengths (505, 537, 561, 562, 564, 575, 604, 627, 656, 665, 670, and 689 nm) selected by SPA , and the optimal threshold T = 1 was obtained from the receiver operating characteristic (ROC) analysis. The SPA-MLR classifier provided the best detection results when compared with the SPA-partial least squares (PLS) regression classifier and the SPA-least squares supported vector machine (LS-SVM) classifier. The true positive rate (TPR) of 100% and the false positive rate (FPR) of 0.392% indicate that the SPA-MLR classifier can utilize spatial and spectral information to effectively detect contaminants on chicken carcasses.

Finger language recognition based on ensemble artificial neural network learning using armband EMG sensors.

PubMed

Kim, Seongjung; Kim, Jongman; Ahn, Soonjae; Kim, Youngho

2018-04-18

Deaf people use sign or finger languages for communication, but these methods of communication are very specialized. For this reason, the deaf can suffer from social inequalities and financial losses due to their communication restrictions. In this study, we developed a finger language recognition algorithm based on an ensemble artificial neural network (E-ANN) using an armband system with 8-channel electromyography (EMG) sensors. The developed algorithm was composed of signal acquisition, filtering, segmentation, feature extraction and an E-ANN based classifier that was evaluated with the Korean finger language (14 consonants, 17 vowels and 7 numbers) in 17 subjects. E-ANN was categorized according to the number of classifiers (1 to 10) and size of training data (50 to 1500). The accuracy of the E-ANN-based classifier was obtained by 5-fold cross validation and compared with an artificial neural network (ANN)-based classifier. As the number of classifiers (1 to 8) and size of training data (50 to 300) increased, the average accuracy of the E-ANN-based classifier increased and the standard deviation decreased. The optimal E-ANN was composed with eight classifiers and 300 size of training data, and the accuracy of the E-ANN was significantly higher than that of the general ANN.

Unified framework for triaxial accelerometer-based fall event detection and classification using cumulants and hierarchical decision tree classifier.

PubMed

Kambhampati, Satya Samyukta; Singh, Vishal; Manikandan, M Sabarimalai; Ramkumar, Barathram

2015-08-01

In this Letter, the authors present a unified framework for fall event detection and classification using the cumulants extracted from the acceleration (ACC) signals acquired using a single waist-mounted triaxial accelerometer. The main objective of this Letter is to find suitable representative cumulants and classifiers in effectively detecting and classifying different types of fall and non-fall events. It was discovered that the first level of the proposed hierarchical decision tree algorithm implements fall detection using fifth-order cumulants and support vector machine (SVM) classifier. In the second level, the fall event classification algorithm uses the fifth-order cumulants and SVM. Finally, human activity classification is performed using the second-order cumulants and SVM. The detection and classification results are compared with those of the decision tree, naive Bayes, multilayer perceptron and SVM classifiers with different types of time-domain features including the second-, third-, fourth- and fifth-order cumulants and the signal magnitude vector and signal magnitude area. The experimental results demonstrate that the second- and fifth-order cumulant features and SVM classifier can achieve optimal detection and classification rates of above 95%, as well as the lowest false alarm rate of 1.03%.

A Novel Anti-classification Approach for Knowledge Protection.

PubMed

Lin, Chen-Yi; Chen, Tung-Shou; Tsai, Hui-Fang; Lee, Wei-Bin; Hsu, Tien-Yu; Kao, Yuan-Hung

2015-10-01

Classification is the problem of identifying a set of categories where new data belong, on the basis of a set of training data whose category membership is known. Its application is wide-spread, such as the medical science domain. The issue of the classification knowledge protection has been paid attention increasingly in recent years because of the popularity of cloud environments. In the paper, we propose a Shaking Sorted-Sampling (triple-S) algorithm for protecting the classification knowledge of a dataset. The triple-S algorithm sorts the data of an original dataset according to the projection results of the principal components analysis so that the features of the adjacent data are similar. Then, we generate noise data with incorrect classes and add those data to the original dataset. In addition, we develop an effective positioning strategy, determining the added positions of noise data in the original dataset, to ensure the restoration of the original dataset after removing those noise data. The experimental results show that the disturbance effect of the triple-S algorithm on the CLC, MySVM, and LibSVM classifiers increases when the noise data ratio increases. In addition, compared with existing methods, the disturbance effect of the triple-S algorithm is more significant on MySVM and LibSVM when a certain amount of the noise data added to the original dataset is reached.

Using Machine Learning for Advanced Anomaly Detection and Classification

NASA Astrophysics Data System (ADS)

Lane, B.; Poole, M.; Camp, M.; Murray-Krezan, J.

2016-09-01

Machine Learning (ML) techniques have successfully been used in a wide variety of applications to automatically detect and potentially classify changes in activity, or a series of activities by utilizing large amounts data, sometimes even seemingly-unrelated data. The amount of data being collected, processed, and stored in the Space Situational Awareness (SSA) domain has grown at an exponential rate and is now better suited for ML. This paper describes development of advanced algorithms to deliver significant improvements in characterization of deep space objects and indication and warning (I&W) using a global network of telescopes that are collecting photometric data on a multitude of space-based objects. The Phase II Air Force Research Laboratory (AFRL) Small Business Innovative Research (SBIR) project Autonomous Characterization Algorithms for Change Detection and Characterization (ACDC), contracted to ExoAnalytic Solutions Inc. is providing the ability to detect and identify photometric signature changes due to potential space object changes (e.g. stability, tumble rate, aspect ratio), and correlate observed changes to potential behavioral changes using a variety of techniques, including supervised learning. Furthermore, these algorithms run in real-time on data being collected and processed by the ExoAnalytic Space Operations Center (EspOC), providing timely alerts and warnings while dynamically creating collection requirements to the EspOC for the algorithms that generate higher fidelity I&W. This paper will discuss the recently implemented ACDC algorithms, including the general design approach and results to date. The usage of supervised algorithms, such as Support Vector Machines, Neural Networks, k-Nearest Neighbors, etc., and unsupervised algorithms, for example k-means, Principle Component Analysis, Hierarchical Clustering, etc., and the implementations of these algorithms is explored. Results of applying these algorithms to EspOC data both in an off-line "pattern of life" analysis as well as using the algorithms on-line in real-time, meaning as data is collected, will be presented. Finally, future work in applying ML for SSA will be discussed.

Parallel processing implementations of a contextual classifier for multispectral remote sensing data

NASA Technical Reports Server (NTRS)

Siegel, H. J.; Swain, P. H.; Smith, B. W.

1980-01-01

Contextual classifiers are being developed as a method to exploit the spatial/spectral context of a pixel to achieve accurate classification. Classification algorithms such as the contextual classifier typically require large amounts of computation time. One way to reduce the execution time of these tasks is through the use of parallelism. The applicability of the CDC flexible processor system and of a proposed multimicroprocessor system (PASM) for implementing contextual classifiers is examined.

Boomerang: A method for recursive reclassification.

PubMed

Devlin, Sean M; Ostrovnaya, Irina; Gönen, Mithat

2016-09-01

While there are many validated prognostic classifiers used in practice, often their accuracy is modest and heterogeneity in clinical outcomes exists in one or more risk subgroups. Newly available markers, such as genomic mutations, may be used to improve the accuracy of an existing classifier by reclassifying patients from a heterogenous group into a higher or lower risk category. The statistical tools typically applied to develop the initial classifiers are not easily adapted toward this reclassification goal. In this article, we develop a new method designed to refine an existing prognostic classifier by incorporating new markers. The two-stage algorithm called Boomerang first searches for modifications of the existing classifier that increase the overall predictive accuracy and then merges to a prespecified number of risk groups. Resampling techniques are proposed to assess the improvement in predictive accuracy when an independent validation data set is not available. The performance of the algorithm is assessed under various simulation scenarios where the marker frequency, degree of censoring, and total sample size are varied. The results suggest that the method selects few false positive markers and is able to improve the predictive accuracy of the classifier in many settings. Lastly, the method is illustrated on an acute myeloid leukemia data set where a new refined classifier incorporates four new mutations into the existing three category classifier and is validated on an independent data set. © 2016, The International Biometric Society.

Boomerang: A Method for Recursive Reclassification

PubMed Central

Devlin, Sean M.; Ostrovnaya, Irina; Gönen, Mithat

2016-01-01

Summary While there are many validated prognostic classifiers used in practice, often their accuracy is modest and heterogeneity in clinical outcomes exists in one or more risk subgroups. Newly available markers, such as genomic mutations, may be used to improve the accuracy of an existing classifier by reclassifying patients from a heterogenous group into a higher or lower risk category. The statistical tools typically applied to develop the initial classifiers are not easily adapted towards this reclassification goal. In this paper, we develop a new method designed to refine an existing prognostic classifier by incorporating new markers. The two-stage algorithm called Boomerang first searches for modifications of the existing classifier that increase the overall predictive accuracy and then merges to a pre-specified number of risk groups. Resampling techniques are proposed to assess the improvement in predictive accuracy when an independent validation data set is not available. The performance of the algorithm is assessed under various simulation scenarios where the marker frequency, degree of censoring, and total sample size are varied. The results suggest that the method selects few false positive markers and is able to improve the predictive accuracy of the classifier in many settings. Lastly, the method is illustrated on an acute myeloid leukemia dataset where a new refined classifier incorporates four new mutations into the existing three category classifier and is validated on an independent dataset. PMID:26754051

Comparative study of classification algorithms for immunosignaturing data

PubMed Central

2012-01-01

Background High-throughput technologies such as DNA, RNA, protein, antibody and peptide microarrays are often used to examine differences across drug treatments, diseases, transgenic animals, and others. Typically one trains a classification system by gathering large amounts of probe-level data, selecting informative features, and classifies test samples using a small number of features. As new microarrays are invented, classification systems that worked well for other array types may not be ideal. Expression microarrays, arguably one of the most prevalent array types, have been used for years to help develop classification algorithms. Many biological assumptions are built into classifiers that were designed for these types of data. One of the more problematic is the assumption of independence, both at the probe level and again at the biological level. Probes for RNA transcripts are designed to bind single transcripts. At the biological level, many genes have dependencies across transcriptional pathways where co-regulation of transcriptional units may make many genes appear as being completely dependent. Thus, algorithms that perform well for gene expression data may not be suitable when other technologies with different binding characteristics exist. The immunosignaturing microarray is based on complex mixtures of antibodies binding to arrays of random sequence peptides. It relies on many-to-many binding of antibodies to the random sequence peptides. Each peptide can bind multiple antibodies and each antibody can bind multiple peptides. This technology has been shown to be highly reproducible and appears promising for diagnosing a variety of disease states. However, it is not clear what is the optimal classification algorithm for analyzing this new type of data. Results We characterized several classification algorithms to analyze immunosignaturing data. We selected several datasets that range from easy to difficult to classify, from simple monoclonal binding to complex binding patterns in asthma patients. We then classified the biological samples using 17 different classification algorithms. Using a wide variety of assessment criteria, we found ‘Naïve Bayes’ far more useful than other widely used methods due to its simplicity, robustness, speed and accuracy. Conclusions ‘Naïve Bayes’ algorithm appears to accommodate the complex patterns hidden within multilayered immunosignaturing microarray data due to its fundamental mathematical properties. PMID:22720696

Classifying injury narratives of large administrative databases for surveillance-A practical approach combining machine learning ensembles and human review.

PubMed

Marucci-Wellman, Helen R; Corns, Helen L; Lehto, Mark R

2017-01-01

Injury narratives are now available real time and include useful information for injury surveillance and prevention. However, manual classification of the cause or events leading to injury found in large batches of narratives, such as workers compensation claims databases, can be prohibitive. In this study we compare the utility of four machine learning algorithms (Naïve Bayes, Single word and Bi-gram models, Support Vector Machine and Logistic Regression) for classifying narratives into Bureau of Labor Statistics Occupational Injury and Illness event leading to injury classifications for a large workers compensation database. These algorithms are known to do well classifying narrative text and are fairly easy to implement with off-the-shelf software packages such as Python. We propose human-machine learning ensemble approaches which maximize the power and accuracy of the algorithms for machine-assigned codes and allow for strategic filtering of rare, emerging or ambiguous narratives for manual review. We compare human-machine approaches based on filtering on the prediction strength of the classifier vs. agreement between algorithms. Regularized Logistic Regression (LR) was the best performing algorithm alone. Using this algorithm and filtering out the bottom 30% of predictions for manual review resulted in high accuracy (overall sensitivity/positive predictive value of 0.89) of the final machine-human coded dataset. The best pairings of algorithms included Naïve Bayes with Support Vector Machine whereby the triple ensemble NB SW =NB BI-GRAM =SVM had very high performance (0.93 overall sensitivity/positive predictive value and high accuracy (i.e. high sensitivity and positive predictive values)) across both large and small categories leaving 41% of the narratives for manual review. Integrating LR into this ensemble mix improved performance only slightly. For large administrative datasets we propose incorporation of methods based on human-machine pairings such as we have done here, utilizing readily-available off-the-shelf machine learning techniques and resulting in only a fraction of narratives that require manual review. Human-machine ensemble methods are likely to improve performance over total manual coding. Copyright © 2016 The Authors. Published by Elsevier Ltd.. All rights reserved.

A Theoretical Analysis of Why Hybrid Ensembles Work

PubMed Central

2017-01-01

Inspired by the group decision making process, ensembles or combinations of classifiers have been found favorable in a wide variety of application domains. Some researchers propose to use the mixture of two different types of classification algorithms to create a hybrid ensemble. Why does such an ensemble work? The question remains. Following the concept of diversity, which is one of the fundamental elements of the success of ensembles, we conduct a theoretical analysis of why hybrid ensembles work, connecting using different algorithms to accuracy gain. We also conduct experiments on classification performance of hybrid ensembles of classifiers created by decision tree and naïve Bayes classification algorithms, each of which is a top data mining algorithm and often used to create non-hybrid ensembles. Therefore, through this paper, we provide a complement to the theoretical foundation of creating and using hybrid ensembles. PMID:28255296

An intelligent identification algorithm for the monoclonal picking instrument

NASA Astrophysics Data System (ADS)

Yan, Hua; Zhang, Rongfu; Yuan, Xujun; Wang, Qun

2017-11-01

The traditional colony selection is mainly operated by manual mode, which takes on low efficiency and strong subjectivity. Therefore, it is important to develop an automatic monoclonal-picking instrument. The critical stage of the automatic monoclonal-picking and intelligent optimal selection is intelligent identification algorithm. An auto-screening algorithm based on Support Vector Machine (SVM) is proposed in this paper, which uses the supervised learning method, which combined with the colony morphological characteristics to classify the colony accurately. Furthermore, through the basic morphological features of the colony, system can figure out a series of morphological parameters step by step. Through the establishment of maximal margin classifier, and based on the analysis of the growth trend of the colony, the selection of the monoclonal colony was carried out. The experimental results showed that the auto-screening algorithm could screen out the regular colony from the other, which meets the requirement of various parameters.

Classification of Odours for Mobile Robots Using an Ensemble of Linear Classifiers

NASA Astrophysics Data System (ADS)

Trincavelli, Marco; Coradeschi, Silvia; Loutfi, Amy

2009-05-01

This paper investigates the classification of odours using an electronic nose mounted on a mobile robot. The samples are collected as the robot explores the environment. Under such conditions, the sensor response differs from typical three phase sampling processes. In this paper, we focus particularly on the classification problem and how it is influenced by the movement of the robot. To cope with these influences, an algorithm consisting of an ensemble of classifiers is presented. Experimental results show that this algorithm increases classification performance compared to other traditional classification methods.

Classifying BCI signals from novice users with extreme learning machine

NASA Astrophysics Data System (ADS)

Rodríguez-Bermúdez, Germán; Bueno-Crespo, Andrés; José Martinez-Albaladejo, F.

2017-07-01

Brain computer interface (BCI) allows to control external devices only with the electrical activity of the brain. In order to improve the system, several approaches have been proposed. However it is usual to test algorithms with standard BCI signals from experts users or from repositories available on Internet. In this work, extreme learning machine (ELM) has been tested with signals from 5 novel users to compare with standard classification algorithms. Experimental results show that ELM is a suitable method to classify electroencephalogram signals from novice users.

Quantum Support Vector Machine for Big Data Classification

NASA Astrophysics Data System (ADS)

Rebentrost, Patrick; Mohseni, Masoud; Lloyd, Seth

2014-09-01

Supervised machine learning is the classification of new data based on already classified training examples. In this work, we show that the support vector machine, an optimized binary classifier, can be implemented on a quantum computer, with complexity logarithmic in the size of the vectors and the number of training examples. In cases where classical sampling algorithms require polynomial time, an exponential speedup is obtained. At the core of this quantum big data algorithm is a nonsparse matrix exponentiation technique for efficiently performing a matrix inversion of the training data inner-product (kernel) matrix.

Adiabatic Quantum Anomaly Detection and Machine Learning

NASA Astrophysics Data System (ADS)

Pudenz, Kristen; Lidar, Daniel

2012-02-01

We present methods of anomaly detection and machine learning using adiabatic quantum computing. The machine learning algorithm is a boosting approach which seeks to optimally combine somewhat accurate classification functions to create a unified classifier which is much more accurate than its components. This algorithm then becomes the first part of the larger anomaly detection algorithm. In the anomaly detection routine, we first use adiabatic quantum computing to train two classifiers which detect two sets, the overlap of which forms the anomaly class. We call this the learning phase. Then, in the testing phase, the two learned classification functions are combined to form the final Hamiltonian for an adiabatic quantum computation, the low energy states of which represent the anomalies in a binary vector space.

Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images

PubMed Central

Srinivasan, Pratul P.; Kim, Leo A.; Mettu, Priyatham S.; Cousins, Scott W.; Comer, Grant M.; Izatt, Joseph A.; Farsiu, Sina

2014-01-01

We present a novel fully automated algorithm for the detection of retinal diseases via optical coherence tomography (OCT) imaging. Our algorithm utilizes multiscale histograms of oriented gradient descriptors as feature vectors of a support vector machine based classifier. The spectral domain OCT data sets used for cross-validation consisted of volumetric scans acquired from 45 subjects: 15 normal subjects, 15 patients with dry age-related macular degeneration (AMD), and 15 patients with diabetic macular edema (DME). Our classifier correctly identified 100% of cases with AMD, 100% cases with DME, and 86.67% cases of normal subjects. This algorithm is a potentially impactful tool for the remote diagnosis of ophthalmic diseases. PMID:25360373

Generalization Analysis of Fredholm Kernel Regularized Classifiers.

PubMed

Gong, Tieliang; Xu, Zongben; Chen, Hong

2017-07-01

Recently, a new framework, Fredholm learning, was proposed for semisupervised learning problems based on solving a regularized Fredholm integral equation. It allows a natural way to incorporate unlabeled data into learning algorithms to improve their prediction performance. Despite rapid progress on implementable algorithms with theoretical guarantees, the generalization ability of Fredholm kernel learning has not been studied. In this letter, we focus on investigating the generalization performance of a family of classification algorithms, referred to as Fredholm kernel regularized classifiers. We prove that the corresponding learning rate can achieve [Formula: see text] ([Formula: see text] is the number of labeled samples) in a limiting case. In addition, a representer theorem is provided for the proposed regularized scheme, which underlies its applications.

Ensemble of One-Class Classifiers for Personal Risk Detection Based on Wearable Sensor Data.

PubMed

Rodríguez, Jorge; Barrera-Animas, Ari Y; Trejo, Luis A; Medina-Pérez, Miguel Angel; Monroy, Raúl

2016-09-29

This study introduces the One-Class K-means with Randomly-projected features Algorithm (OCKRA). OCKRA is an ensemble of one-class classifiers built over multiple projections of a dataset according to random feature subsets. Algorithms found in the literature spread over a wide range of applications where ensembles of one-class classifiers have been satisfactorily applied; however, none is oriented to the area under our study: personal risk detection. OCKRA has been designed with the aim of improving the detection performance in the problem posed by the Personal RIsk DEtection(PRIDE) dataset. PRIDE was built based on 23 test subjects, where the data for each user were captured using a set of sensors embedded in a wearable band. The performance of OCKRA was compared against support vector machine and three versions of the Parzen window classifier. On average, experimental results show that OCKRA outperformed the other classifiers for at least 0.53% of the area under the curve (AUC). In addition, OCKRA achieved an AUC above 90% for more than 57% of the users.

Ensemble of One-Class Classifiers for Personal Risk Detection Based on Wearable Sensor Data

PubMed Central

Rodríguez, Jorge; Barrera-Animas, Ari Y.; Trejo, Luis A.; Medina-Pérez, Miguel Angel; Monroy, Raúl

2016-01-01

This study introduces the One-Class K-means with Randomly-projected features Algorithm (OCKRA). OCKRA is an ensemble of one-class classifiers built over multiple projections of a dataset according to random feature subsets. Algorithms found in the literature spread over a wide range of applications where ensembles of one-class classifiers have been satisfactorily applied; however, none is oriented to the area under our study: personal risk detection. OCKRA has been designed with the aim of improving the detection performance in the problem posed by the Personal RIsk DEtection(PRIDE) dataset. PRIDE was built based on 23 test subjects, where the data for each user were captured using a set of sensors embedded in a wearable band. The performance of OCKRA was compared against support vector machine and three versions of the Parzen window classifier. On average, experimental results show that OCKRA outperformed the other classifiers for at least 0.53% of the area under the curve (AUC). In addition, OCKRA achieved an AUC above 90% for more than 57% of the users. PMID:27690054

A comparative analysis of swarm intelligence techniques for feature selection in cancer classification.

PubMed

Gunavathi, Chellamuthu; Premalatha, Kandasamy

2014-01-01

Feature selection in cancer classification is a central area of research in the field of bioinformatics and used to select the informative genes from thousands of genes of the microarray. The genes are ranked based on T-statistics, signal-to-noise ratio (SNR), and F-test values. The swarm intelligence (SI) technique finds the informative genes from the top-m ranked genes. These selected genes are used for classification. In this paper the shuffled frog leaping with Lévy flight (SFLLF) is proposed for feature selection. In SFLLF, the Lévy flight is included to avoid premature convergence of shuffled frog leaping (SFL) algorithm. The SI techniques such as particle swarm optimization (PSO), cuckoo search (CS), SFL, and SFLLF are used for feature selection which identifies informative genes for classification. The k-nearest neighbour (k-NN) technique is used to classify the samples. The proposed work is applied on 10 different benchmark datasets and examined with SI techniques. The experimental results show that the results obtained from k-NN classifier through SFLLF feature selection method outperform PSO, CS, and SFL.

Automated detection of pulmonary nodules in CT images with support vector machines

NASA Astrophysics Data System (ADS)

Liu, Lu; Liu, Wanyu; Sun, Xiaoming

2008-10-01

Many methods have been proposed to avoid radiologists fail to diagnose small pulmonary nodules. Recently, support vector machines (SVMs) had received an increasing attention for pattern recognition. In this paper, we present a computerized system aimed at pulmonary nodules detection; it identifies the lung field, extracts a set of candidate regions with a high sensitivity ratio and then classifies candidates by the use of SVMs. The Computer Aided Diagnosis (CAD) system presented in this paper supports the diagnosis of pulmonary nodules from Computed Tomography (CT) images as inflammation, tuberculoma, granuloma..sclerosing hemangioma, and malignant tumor. Five texture feature sets were extracted for each lesion, while a genetic algorithm based feature selection method was applied to identify the most robust features. The selected feature set was fed into an ensemble of SVMs classifiers. The achieved classification performance was 100%, 92.75% and 90.23% in the training, validation and testing set, respectively. It is concluded that computerized analysis of medical images in combination with artificial intelligence can be used in clinical practice and may contribute to more efficient diagnosis.

Network intrusion detection based on a general regression neural network optimized by an improved artificial immune algorithm.

PubMed

Wu, Jianfa; Peng, Dahao; Li, Zhuping; Zhao, Li; Ling, Huanzhang

2015-01-01

To effectively and accurately detect and classify network intrusion data, this paper introduces a general regression neural network (GRNN) based on the artificial immune algorithm with elitist strategies (AIAE). The elitist archive and elitist crossover were combined with the artificial immune algorithm (AIA) to produce the AIAE-GRNN algorithm, with the aim of improving its adaptivity and accuracy. In this paper, the mean square errors (MSEs) were considered the affinity function. The AIAE was used to optimize the smooth factors of the GRNN; then, the optimal smooth factor was solved and substituted into the trained GRNN. Thus, the intrusive data were classified. The paper selected a GRNN that was separately optimized using a genetic algorithm (GA), particle swarm optimization (PSO), and fuzzy C-mean clustering (FCM) to enable a comparison of these approaches. As shown in the results, the AIAE-GRNN achieves a higher classification accuracy than PSO-GRNN, but the running time of AIAE-GRNN is long, which was proved first. FCM and GA-GRNN were eliminated because of their deficiencies in terms of accuracy and convergence. To improve the running speed, the paper adopted principal component analysis (PCA) to reduce the dimensions of the intrusive data. With the reduction in dimensionality, the PCA-AIAE-GRNN decreases in accuracy less and has better convergence than the PCA-PSO-GRNN, and the running speed of the PCA-AIAE-GRNN was relatively improved. The experimental results show that the AIAE-GRNN has a higher robustness and accuracy than the other algorithms considered and can thus be used to classify the intrusive data.

Wheezing recognition algorithm using recordings of respiratory sounds at the mouth in a pediatric population.

PubMed

Bokov, Plamen; Mahut, Bruno; Flaud, Patrice; Delclaux, Christophe

2016-03-01

Respiratory diseases in children are a common reason for physician visits. A diagnostic difficulty arises when parents hear wheezing that is no longer present during the medical consultation. Thus, an outpatient objective tool for recognition of wheezing is of clinical value. We developed a wheezing recognition algorithm from recorded respiratory sounds with a Smartphone placed near the mouth. A total of 186 recordings were obtained in a pediatric emergency department, mostly in toddlers (mean age 20 months). After exclusion of recordings with artefacts and those with a single clinical operator auscultation, 95 recordings with the agreement of two operators on auscultation diagnosis (27 with wheezing and 68 without) were subjected to a two phase algorithm (signal analysis and pattern classifier using machine learning algorithms) to classify records. The best performance (71.4% sensitivity and 88.9% specificity) was observed with a Support Vector Machine-based algorithm. We further tested the algorithm over a set of 39 recordings having a single operator and found a fair agreement (kappa=0.28, CI95% [0.12, 0.45]) between the algorithm and the operator. The main advantage of such an algorithm is its use in contact-free sound recording, thus valuable in the pediatric population. Copyright © 2016 Elsevier Ltd. All rights reserved.

Large unbalanced credit scoring using Lasso-logistic regression ensemble.

PubMed

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data.

Toward an efficient Photometric Supernova Classifier

NASA Astrophysics Data System (ADS)

McClain, Bradley

2018-01-01

The Sloan Digital Sky Survey Supernova Survey (SDSS) discovered more than 1,000 Type Ia Supernovae, yet less than half of these have spectroscopic measurements. As wide-field imaging telescopes such as The Dark Energy Survey (DES) and the Panoramic Survey Telescope and Rapid Response System (Pan-STARRS) discover more supernovae, the need for accurate and computationally cheap photometric classifiers increases. My goal is to use a photometric classification algorithm based on Sncosmo, a python library for supernova cosmology analysis, to reclassify previously identified Hubble SN and other non-spectroscopically confirmed surveys. My results will be compared to other photometric classifiers such as PSNID and STARDUST. In the near future, I expect to have the algorithm validated with simulated data, optimized for efficiency, and applied with high performance computing to real data.

A scaling transformation for classifier output based on likelihood ratio: Applications to a CAD workstation for diagnosis of breast cancer

PubMed Central

Horsch, Karla; Pesce, Lorenzo L.; Giger, Maryellen L.; Metz, Charles E.; Jiang, Yulei

2012-01-01

Purpose: The authors developed scaling methods that monotonically transform the output of one classifier to the “scale” of another. Such transformations affect the distribution of classifier output while leaving the ROC curve unchanged. In particular, they investigated transformations between radiologists and computer classifiers, with the goal of addressing the problem of comparing and interpreting case-specific values of output from two classifiers. Methods: Using both simulated and radiologists’ rating data of breast imaging cases, the authors investigated a likelihood-ratio-scaling transformation, based on “matching” classifier likelihood ratios. For comparison, three other scaling transformations were investigated that were based on matching classifier true positive fraction, false positive fraction, or cumulative distribution function, respectively. The authors explored modifying the computer output to reflect the scale of the radiologist, as well as modifying the radiologist’s ratings to reflect the scale of the computer. They also evaluated how dataset size affects the transformations. Results: When ROC curves of two classifiers differed substantially, the four transformations were found to be quite different. The likelihood-ratio scaling transformation was found to vary widely from radiologist to radiologist. Similar results were found for the other transformations. Our simulations explored the effect of database sizes on the accuracy of the estimation of our scaling transformations. Conclusions: The likelihood-ratio-scaling transformation that the authors have developed and evaluated was shown to be capable of transforming computer and radiologist outputs to a common scale reliably, thereby allowing the comparison of the computer and radiologist outputs on the basis of a clinically relevant statistic. PMID:22559651

Cost-sensitive AdaBoost algorithm for ordinal regression based on extreme learning machine.

PubMed

Riccardi, Annalisa; Fernández-Navarro, Francisco; Carloni, Sante

2014-10-01

In this paper, the well known stagewise additive modeling using a multiclass exponential (SAMME) boosting algorithm is extended to address problems where there exists a natural order in the targets using a cost-sensitive approach. The proposed ensemble model uses an extreme learning machine (ELM) model as a base classifier (with the Gaussian kernel and the additional regularization parameter). The closed form of the derived weighted least squares problem is provided, and it is employed to estimate analytically the parameters connecting the hidden layer to the output layer at each iteration of the boosting algorithm. Compared to the state-of-the-art boosting algorithms, in particular those using ELM as base classifier, the suggested technique does not require the generation of a new training dataset at each iteration. The adoption of the weighted least squares formulation of the problem has been presented as an unbiased and alternative approach to the already existing ELM boosting techniques. Moreover, the addition of a cost model for weighting the patterns, according to the order of the targets, enables the classifier to tackle ordinal regression problems further. The proposed method has been validated by an experimental study by comparing it with already existing ensemble methods and ELM techniques for ordinal regression, showing competitive results.

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

PubMed Central

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

2017-01-01

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

Empirical Testing of an Algorithm for Defining Somatization in Children

PubMed Central

Eisman, Howard D.; Fogel, Joshua; Lazarovich, Regina; Pustilnik, Inna

2007-01-01

Introduction A previous article proposed an algorithm for defining somatization in children by classifying them into three categories: well, medically ill, and somatizer; the authors suggested further empirical validation of the algorithm (Postilnik et al., 2006). We use the Child Behavior Checklist (CBCL) to provide this empirical validation. Method Parents of children seen in pediatric clinics completed the CBCL (n=126). The physicians of these children completed specially-designed questionnaires. The sample comprised of 62 boys and 64 girls (age range 2 to 15 years). Classification categories included: well (n=53), medically ill (n=55), and somatizer (n=18). Analysis of variance (ANOVA) was used for statistical comparisons. Discriminant function analysis was conducted with the CBCL subscales. Results There were significant differences between the classification categories for the somatic complaints (p=<0.001), social problems (p=0.004), thought problems (p=0.01), attention problems (0.006), and internalizing (p=0.003) subscales and also total (p=0.001), and total-t (p=0.001) scales of the CBCL. Discriminant function analysis showed that 78% of somatizers and 66% of well were accurately classified, while only 35% of medically ill were accurately classified. Conclusion The somatization classification algorithm proposed by Postilnik et al. (2006) shows promise for classification of children and adolescents with somatic symptoms. PMID:18421368

The Performance of Short-Term Heart Rate Variability in the Detection of Congestive Heart Failure

PubMed Central

Barros, Allan Kardec; Ohnishi, Noboru

2016-01-01

Congestive heart failure (CHF) is a cardiac disease associated with the decreasing capacity of the cardiac output. It has been shown that the CHF is the main cause of the cardiac death around the world. Some works proposed to discriminate CHF subjects from healthy subjects using either electrocardiogram (ECG) or heart rate variability (HRV) from long-term recordings. In this work, we propose an alternative framework to discriminate CHF from healthy subjects by using HRV short-term intervals based on 256 RR continuous samples. Our framework uses a matching pursuit algorithm based on Gabor functions. From the selected Gabor functions, we derived a set of features that are inputted into a hybrid framework which uses a genetic algorithm and k-nearest neighbour classifier to select a subset of features that has the best classification performance. The performance of the framework is analyzed using both Fantasia and CHF database from Physionet archives which are, respectively, composed of 40 healthy volunteers and 29 subjects. From a set of nonstandard 16 features, the proposed framework reaches an overall accuracy of 100% with five features. Our results suggest that the application of hybrid frameworks whose classifier algorithms are based on genetic algorithms has outperformed well-known classifier methods. PMID:27891509

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

Wurtz, R.; Kaplan, A.

Pulse shape discrimination (PSD) is a variety of statistical classifier. Fully-­realized statistical classifiers rely on a comprehensive set of tools for designing, building, and implementing. PSD advances rely on improvements to the implemented algorithm. PSD advances can be improved by using conventional statistical classifier or machine learning methods. This paper provides the reader with a glossary of classifier-­building elements and their functions in a fully-­designed and operational classifier framework that can be used to discover opportunities for improving PSD classifier projects. This paper recommends reporting the PSD classifier’s receiver operating characteristic (ROC) curve and its behavior at a gamma rejectionmore » rate (GRR) relevant for realistic applications.« less

Hyperspectral imaging detection of decayed honey peaches based on their chlorophyll content.

PubMed

Sun, Ye; Wang, Yihang; Xiao, Hui; Gu, Xinzhe; Pan, Leiqing; Tu, Kang

2017-11-15

Honey peach is a very common but highly perishable market fruit. When pathogens infect fruit, chlorophyll as one of the important components related to fruit quality, decreased significantly. Here, the feasibility of hyperspectral imaging to determine the chlorophyll content thus distinguishing diseased peaches was investigated. Three optimal wavelengths (617nm, 675nm, and 818nm) were selected according to chlorophyll content via successive projections algorithm. Partial least square regression models were established to determine chlorophyll content. Three band ratios were obtained using these optimal wavelengths, which improved spatial details, but also integrates the information of chemical composition from spectral characteristics. The band ratio values were suitable to classify the diseased peaches with 98.75% accuracy and clearly show the spatial distribution of diseased parts. This study provides a new perspective for the selection of optimal wavelengths of hyperspectral imaging via chlorophyll content, thus enabling the detection of fungal diseases in peaches. Copyright © 2017 Elsevier Ltd. All rights reserved.

Gene Expression Ratios Lead to Accurate and Translatable Predictors of DR5 Agonism across Multiple Tumor Lineages.

PubMed

Reddy, Anupama; Growney, Joseph D; Wilson, Nick S; Emery, Caroline M; Johnson, Jennifer A; Ward, Rebecca; Monaco, Kelli A; Korn, Joshua; Monahan, John E; Stump, Mark D; Mapa, Felipa A; Wilson, Christopher J; Steiger, Janine; Ledell, Jebediah; Rickles, Richard J; Myer, Vic E; Ettenberg, Seth A; Schlegel, Robert; Sellers, William R; Huet, Heather A; Lehár, Joseph

2015-01-01

Death Receptor 5 (DR5) agonists demonstrate anti-tumor activity in preclinical models but have yet to demonstrate robust clinical responses. A key limitation may be the lack of patient selection strategies to identify those most likely to respond to treatment. To overcome this limitation, we screened a DR5 agonist Nanobody across >600 cell lines representing 21 tumor lineages and assessed molecular features associated with response. High expression of DR5 and Casp8 were significantly associated with sensitivity, but their expression thresholds were difficult to translate due to low dynamic ranges. To address the translational challenge of establishing thresholds of gene expression, we developed a classifier based on ratios of genes that predicted response across lineages. The ratio classifier outperformed the DR5+Casp8 classifier, as well as standard approaches for feature selection and classification using genes, instead of ratios. This classifier was independently validated using 11 primary patient-derived pancreatic xenograft models showing perfect predictions as well as a striking linearity between prediction probability and anti-tumor response. A network analysis of the genes in the ratio classifier captured important biological relationships mediating drug response, specifically identifying key positive and negative regulators of DR5 mediated apoptosis, including DR5, CASP8, BID, cFLIP, XIAP and PEA15. Importantly, the ratio classifier shows translatability across gene expression platforms (from Affymetrix microarrays to RNA-seq) and across model systems (in vitro to in vivo). Our approach of using gene expression ratios presents a robust and novel method for constructing translatable biomarkers of compound response, which can also probe the underlying biology of treatment response.

Gene Expression Ratios Lead to Accurate and Translatable Predictors of DR5 Agonism across Multiple Tumor Lineages

PubMed Central

Reddy, Anupama; Growney, Joseph D.; Wilson, Nick S.; Emery, Caroline M.; Johnson, Jennifer A.; Ward, Rebecca; Monaco, Kelli A.; Korn, Joshua; Monahan, John E.; Stump, Mark D.; Mapa, Felipa A.; Wilson, Christopher J.; Steiger, Janine; Ledell, Jebediah; Rickles, Richard J.; Myer, Vic E.; Ettenberg, Seth A.; Schlegel, Robert; Sellers, William R.

2015-01-01

Death Receptor 5 (DR5) agonists demonstrate anti-tumor activity in preclinical models but have yet to demonstrate robust clinical responses. A key limitation may be the lack of patient selection strategies to identify those most likely to respond to treatment. To overcome this limitation, we screened a DR5 agonist Nanobody across >600 cell lines representing 21 tumor lineages and assessed molecular features associated with response. High expression of DR5 and Casp8 were significantly associated with sensitivity, but their expression thresholds were difficult to translate due to low dynamic ranges. To address the translational challenge of establishing thresholds of gene expression, we developed a classifier based on ratios of genes that predicted response across lineages. The ratio classifier outperformed the DR5+Casp8 classifier, as well as standard approaches for feature selection and classification using genes, instead of ratios. This classifier was independently validated using 11 primary patient-derived pancreatic xenograft models showing perfect predictions as well as a striking linearity between prediction probability and anti-tumor response. A network analysis of the genes in the ratio classifier captured important biological relationships mediating drug response, specifically identifying key positive and negative regulators of DR5 mediated apoptosis, including DR5, CASP8, BID, cFLIP, XIAP and PEA15. Importantly, the ratio classifier shows translatability across gene expression platforms (from Affymetrix microarrays to RNA-seq) and across model systems (in vitro to in vivo). Our approach of using gene expression ratios presents a robust and novel method for constructing translatable biomarkers of compound response, which can also probe the underlying biology of treatment response. PMID:26378449

An integrated classifier for computer-aided diagnosis of colorectal polyps based on random forest and location index strategies

NASA Astrophysics Data System (ADS)

Hu, Yifan; Han, Hao; Zhu, Wei; Li, Lihong; Pickhardt, Perry J.; Liang, Zhengrong

2016-03-01

Feature classification plays an important role in differentiation or computer-aided diagnosis (CADx) of suspicious lesions. As a widely used ensemble learning algorithm for classification, random forest (RF) has a distinguished performance for CADx. Our recent study has shown that the location index (LI), which is derived from the well-known kNN (k nearest neighbor) and wkNN (weighted k nearest neighbor) classifier [1], has also a distinguished role in the classification for CADx. Therefore, in this paper, based on the property that the LI will achieve a very high accuracy, we design an algorithm to integrate the LI into RF for improved or higher value of AUC (area under the curve of receiver operating characteristics -- ROC). Experiments were performed by the use of a database of 153 lesions (polyps), including 116 neoplastic lesions and 37 hyperplastic lesions, with comparison to the existing classifiers of RF and wkNN, respectively. A noticeable gain by the proposed integrated classifier was quantified by the AUC measure.

A new approach to enhance the performance of decision tree for classifying gene expression data.

PubMed

Hassan, Md; Kotagiri, Ramamohanarao

2013-12-20

Gene expression data classification is a challenging task due to the large dimensionality and very small number of samples. Decision tree is one of the popular machine learning approaches to address such classification problems. However, the existing decision tree algorithms use a single gene feature at each node to split the data into its child nodes and hence might suffer from poor performance specially when classifying gene expression dataset. By using a new decision tree algorithm where, each node of the tree consists of more than one gene, we enhance the classification performance of traditional decision tree classifiers. Our method selects suitable genes that are combined using a linear function to form a derived composite feature. To determine the structure of the tree we use the area under the Receiver Operating Characteristics curve (AUC). Experimental analysis demonstrates higher classification accuracy using the new decision tree compared to the other existing decision trees in literature. We experimentally compare the effect of our scheme against other well known decision tree techniques. Experiments show that our algorithm can substantially boost the classification performance of the decision tree.

Detection of lettuce discoloration using hyperspectral reflectance imaging

USDA-ARS?s Scientific Manuscript database

Rapid visible/near-infrared (VNIR) hyperspectral imaging methods, employing both a single waveband algorithm and multi-spectral algorithms, were developed in order to classify the discoloration of lettuce. Reflectance spectra for sound and discolored lettuce surfaces were extracted from hyperspectra...

Quantification of biological tissue and construction of patient equivalent phantom (skull and chest) for infants (1-5 years old)

NASA Astrophysics Data System (ADS)

Alves, A. F.; Pina, D. R.; Bacchim Neto, F. A.; Ribeiro, S. M.; Miranda, J. R. A.

2014-03-01

Our main purpose in this study was to quantify biological tissue in computed tomography (CT) examinations with the aim of developing a skull and a chest patient equivalent phantom (PEP), both specific to infants, aged between 1 and 5 years old. This type of phantom is widely used in the development of optimization procedures for radiographic techniques, especially in computed radiography (CR) systems. In order to classify and quantify the biological tissue, we used a computational algorithm developed in Matlab ®. The algorithm performed a histogram of each CT slice followed by a Gaussian fitting of each tissue type. The algorithm determined the mean thickness for the biological tissues (bone, soft, fat, and lung) and also converted them into the corresponding thicknesses of the simulator material (aluminum, PMMA, and air). We retrospectively analyzed 148 CT examinations of infant patients, 56 for skull exams and 92 were for chest. The results provided sufficient data to construct a phantom to simulate the infant chest and skull in the posterior-anterior or anterior-posterior (PA/AP) view. Both patient equivalent phantoms developed in this study can be used to assess physical variables such as noise power spectrum (NPS) and signal to noise ratio (SNR) or perform dosimetric control specific to pediatric protocols.

A MAP-based image interpolation method via Viterbi decoding of Markov chains of interpolation functions.

PubMed

Vedadi, Farhang; Shirani, Shahram

2014-01-01

A new method of image resolution up-conversion (image interpolation) based on maximum a posteriori sequence estimation is proposed. Instead of making a hard decision about the value of each missing pixel, we estimate the missing pixels in groups. At each missing pixel of the high resolution (HR) image, we consider an ensemble of candidate interpolation methods (interpolation functions). The interpolation functions are interpreted as states of a Markov model. In other words, the proposed method undergoes state transitions from one missing pixel position to the next. Accordingly, the interpolation problem is translated to the problem of estimating the optimal sequence of interpolation functions corresponding to the sequence of missing HR pixel positions. We derive a parameter-free probabilistic model for this to-be-estimated sequence of interpolation functions. Then, we solve the estimation problem using a trellis representation and the Viterbi algorithm. Using directional interpolation functions and sequence estimation techniques, we classify the new algorithm as an adaptive directional interpolation using soft-decision estimation techniques. Experimental results show that the proposed algorithm yields images with higher or comparable peak signal-to-noise ratios compared with some benchmark interpolation methods in the literature while being efficient in terms of implementation and complexity considerations.

Automated segmentation of geographic atrophy in fundus autofluorescence images using supervised pixel classification.

PubMed

Hu, Zhihong; Medioni, Gerard G; Hernandez, Matthias; Sadda, Srinivas R

2015-01-01

Geographic atrophy (GA) is a manifestation of the advanced or late stage of age-related macular degeneration (AMD). AMD is the leading cause of blindness in people over the age of 65 in the western world. The purpose of this study is to develop a fully automated supervised pixel classification approach for segmenting GA, including uni- and multifocal patches in fundus autofluorescene (FAF) images. The image features include region-wise intensity measures, gray-level co-occurrence matrix measures, and Gaussian filter banks. A [Formula: see text]-nearest-neighbor pixel classifier is applied to obtain a GA probability map, representing the likelihood that the image pixel belongs to GA. Sixteen randomly chosen FAF images were obtained from 16 subjects with GA. The algorithm-defined GA regions are compared with manual delineation performed by a certified image reading center grader. Eight-fold cross-validation is applied to evaluate the algorithm performance. The mean overlap ratio (OR), area correlation (Pearson's [Formula: see text]), accuracy (ACC), true positive rate (TPR), specificity (SPC), positive predictive value (PPV), and false discovery rate (FDR) between the algorithm- and manually defined GA regions are [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], [Formula: see text], and [Formula: see text], respectively.

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.

An algorithm for monitoring the traffic on a less-travelled road using multi-modal sensor suite

NASA Astrophysics Data System (ADS)

Damarla, Thyagaraju; Chatters, Gary; Liss, Brian; Vu, Hao; Sabatier, James M.

2014-06-01

We conducted an experiment to correlate the information gathered by a suite of hard sensors with the information on social networks such as Twitter, Facebook, etc. The experiment consisting of monitoring traffic on a well- traveled road and on a road inside a facility. The sensors suite selected mainly consists of sensors that require low power for operation and last a longtime. The output of each sensor is analyzed to classify the targets as ground vehicles, humans, and airborne targets. The algorithm is also used to count the number of targets belonging to each type so the sensor can store the information for anomaly detection. In this paper, we describe the classifier algorithms used for acoustic, seismic, and passive infrared (PIR) sensor data.

A new algorithm for reducing the workload of experts in performing systematic reviews.

PubMed

Matwin, Stan; Kouznetsov, Alexandre; Inkpen, Diana; Frunza, Oana; O'Blenis, Peter

2010-01-01

To determine whether a factorized version of the complement naïve Bayes (FCNB) classifier can reduce the time spent by experts reviewing journal articles for inclusion in systematic reviews of drug class efficacy for disease treatment. The proposed classifier was evaluated on a test collection built from 15 systematic drug class reviews used in previous work. The FCNB classifier was constructed to classify each article as containing high-quality, drug class-specific evidence or not. Weight engineering (WE) techniques were added to reduce underestimation for Medical Subject Headings (MeSH)-based and Publication Type (PubType)-based features. Cross-validation experiments were performed to evaluate the classifier's parameters and performance. Work saved over sampling (WSS) at no less than a 95% recall was used as the main measure of performance. The minimum workload reduction for a systematic review for one topic, achieved with a FCNB/WE classifier, was 8.5%; the maximum was 62.2% and the average over the 15 topics was 33.5%. This is 15.0% higher than the average workload reduction obtained using a voting perceptron-based automated citation classification system. The FCNB/WE classifier is simple, easy to implement, and produces significantly better results in reducing the workload than previously achieved. The results support it being a useful algorithm for machine-learning-based automation of systematic reviews of drug class efficacy for disease treatment.

Onboard Classifiers for Science Event Detection on a Remote Sensing Spacecraft

NASA Technical Reports Server (NTRS)

Castano, Rebecca; Mazzoni, Dominic; Tang, Nghia; Greeley, Ron; Doggett, Thomas; Cichy, Ben; Chien, Steve; Davies, Ashley

2006-01-01

Typically, data collected by a spacecraft is downlinked to Earth and pre-processed before any analysis is performed. We have developed classifiers that can be used onboard a spacecraft to identify high priority data for downlink to Earth, providing a method for maximizing the use of a potentially bandwidth limited downlink channel. Onboard analysis can also enable rapid reaction to dynamic events, such as flooding, volcanic eruptions or sea ice break-up. Four classifiers were developed to identify cryosphere events using hyperspectral images. These classifiers include a manually constructed classifier, a Support Vector Machine (SVM), a Decision Tree and a classifier derived by searching over combinations of thresholded band ratios. Each of the classifiers was designed to run in the computationally constrained operating environment of the spacecraft. A set of scenes was hand-labeled to provide training and testing data. Performance results on the test data indicate that the SVM and manual classifiers outperformed the Decision Tree and band-ratio classifiers with the SVM yielding slightly better classifications than the manual classifier.

Adaptive Bayes classifiers for remotely sensed data

NASA Technical Reports Server (NTRS)

Raulston, H. S.; Pace, M. O.; Gonzalez, R. C.

1975-01-01

An algorithm is developed for a learning, adaptive, statistical pattern classifier for remotely sensed data. The estimation procedure consists of two steps: (1) an optimal stochastic approximation of the parameters of interest, and (2) a projection of the parameters in time and space. The results reported are for Gaussian data in which the mean vector of each class may vary with time or position after the classifier is trained.

Ensemble candidate classification for the LOTAAS pulsar survey

NASA Astrophysics Data System (ADS)

Tan, C. M.; Lyon, R. J.; Stappers, B. W.; Cooper, S.; Hessels, J. W. T.; Kondratiev, V. I.; Michilli, D.; Sanidas, S.

2018-03-01

One of the biggest challenges arising from modern large-scale pulsar surveys is the number of candidates generated. Here, we implemented several improvements to the machine learning (ML) classifier previously used by the LOFAR Tied-Array All-Sky Survey (LOTAAS) to look for new pulsars via filtering the candidates obtained during periodicity searches. To assist the ML algorithm, we have introduced new features which capture the frequency and time evolution of the signal and improved the signal-to-noise calculation accounting for broad profiles. We enhanced the ML classifier by including a third class characterizing RFI instances, allowing candidates arising from RFI to be isolated, reducing the false positive return rate. We also introduced a new training data set used by the ML algorithm that includes a large sample of pulsars misclassified by the previous classifier. Lastly, we developed an ensemble classifier comprised of five different Decision Trees. Taken together these updates improve the pulsar recall rate by 2.5 per cent, while also improving the ability to identify pulsars with wide pulse profiles, often misclassified by the previous classifier. The new ensemble classifier is also able to reduce the percentage of false positive candidates identified from each LOTAAS pointing from 2.5 per cent (˜500 candidates) to 1.1 per cent (˜220 candidates).

Comparison of GOES Cloud Classification Algorithms Employing Explicit and Implicit Physics

NASA Technical Reports Server (NTRS)

Bankert, Richard L.; Mitrescu, Cristian; Miller, Steven D.; Wade, Robert H.

2009-01-01

Cloud-type classification based on multispectral satellite imagery data has been widely researched and demonstrated to be useful for distinguishing a variety of classes using a wide range of methods. The research described here is a comparison of the classifier output from two very different algorithms applied to Geostationary Operational Environmental Satellite (GOES) data over the course of one year. The first algorithm employs spectral channel thresholding and additional physically based tests. The second algorithm was developed through a supervised learning method with characteristic features of expertly labeled image samples used as training data for a 1-nearest-neighbor classification. The latter's ability to identify classes is also based in physics, but those relationships are embedded implicitly within the algorithm. A pixel-to-pixel comparison analysis was done for hourly daytime scenes within a region in the northeastern Pacific Ocean. Considerable agreement was found in this analysis, with many of the mismatches or disagreements providing insight to the strengths and limitations of each classifier. Depending upon user needs, a rule-based or other postprocessing system that combines the output from the two algorithms could provide the most reliable cloud-type classification.

Automated extraction and classification of time-frequency contours in humpback vocalizations.

PubMed

Ou, Hui; Au, Whitlow W L; Zurk, Lisa M; Lammers, Marc O

2013-01-01

A time-frequency contour extraction and classification algorithm was created to analyze humpback whale vocalizations. The algorithm automatically extracted contours of whale vocalization units by searching for gray-level discontinuities in the spectrogram images. The unit-to-unit similarity was quantified by cross-correlating the contour lines. A library of distinctive humpback units was then generated by applying an unsupervised, cluster-based learning algorithm. The purpose of this study was to provide a fast and automated feature selection tool to describe the vocal signatures of animal groups. This approach could benefit a variety of applications such as species description, identification, and evolution of song structures. The algorithm was tested on humpback whale song data recorded at various locations in Hawaii from 2002 to 2003. Results presented in this paper showed low probability of false alarm (0%-4%) under noisy environments with small boat vessels and snapping shrimp. The classification algorithm was tested on a controlled set of 30 units forming six unit types, and all the units were correctly classified. In a case study on humpback data collected in the Auau Chanel, Hawaii, in 2002, the algorithm extracted 951 units, which were classified into 12 distinctive types.

Development of the Landsat Data Continuity Mission Cloud Cover Assessment Algorithms

USGS Publications Warehouse

Scaramuzza, Pat; Bouchard, M.A.; Dwyer, John L.

2012-01-01

The upcoming launch of the Operational Land Imager (OLI) will start the next era of the Landsat program. However, the Automated Cloud-Cover Assessment (CCA) (ACCA) algorithm used on Landsat 7 requires a thermal band and is thus not suited for OLI. There will be a thermal instrument on the Landsat Data Continuity Mission (LDCM)-the Thermal Infrared Sensor-which may not be available during all OLI collections. This illustrates a need for CCA for LDCM in the absence of thermal data. To research possibilities for full-resolution OLI cloud assessment, a global data set of 207 Landsat 7 scenes with manually generated cloud masks was created. It was used to evaluate the ACCA algorithm, showing that the algorithm correctly classified 79.9% of a standard test subset of 3.95 109 pixels. The data set was also used to develop and validate two successor algorithms for use with OLI data-one derived from an off-the-shelf machine learning package and one based on ACCA but enhanced by a simple neural network. These comprehensive CCA algorithms were shown to correctly classify pixels as cloudy or clear 88.5% and 89.7% of the time, respectively.

Machine learning algorithms for meteorological event classification in the coastal area using in-situ data

NASA Astrophysics Data System (ADS)

Sokolov, Anton; Gengembre, Cyril; Dmitriev, Egor; Delbarre, Hervé

2017-04-01

The problem is considered of classification of local atmospheric meteorological events in the coastal area such as sea breezes, fogs and storms. The in-situ meteorological data as wind speed and direction, temperature, humidity and turbulence are used as predictors. Local atmospheric events of 2013-2014 were analysed manually to train classification algorithms in the coastal area of English Channel in Dunkirk (France). Then, ultrasonic anemometer data and LIDAR wind profiler data were used as predictors. A few algorithms were applied to determine meteorological events by local data such as a decision tree, the nearest neighbour classifier, a support vector machine. The comparison of classification algorithms was carried out, the most important predictors for each event type were determined. It was shown that in more than 80 percent of the cases machine learning algorithms detect the meteorological class correctly. We expect that this methodology could be applied also to classify events by climatological in-situ data or by modelling data. It allows estimating frequencies of each event in perspective of climate change.

Artificial Intelligence Methods Applied to Parameter Detection of Atrial Fibrillation

NASA Astrophysics Data System (ADS)

Arotaritei, D.; Rotariu, C.

2015-09-01

In this paper we present a novel method to develop an atrial fibrillation (AF) based on statistical descriptors and hybrid neuro-fuzzy and crisp system. The inference of system produce rules of type if-then-else that care extracted to construct a binary decision system: normal of atrial fibrillation. We use TPR (Turning Point Ratio), SE (Shannon Entropy) and RMSSD (Root Mean Square of Successive Differences) along with a new descriptor, Teager- Kaiser energy, in order to improve the accuracy of detection. The descriptors are calculated over a sliding window that produce very large number of vectors (massive dataset) used by classifier. The length of window is a crisp descriptor meanwhile the rest of descriptors are interval-valued type. The parameters of hybrid system are adapted using Genetic Algorithm (GA) algorithm with fitness single objective target: highest values for sensibility and sensitivity. The rules are extracted and they are part of the decision system. The proposed method was tested using the Physionet MIT-BIH Atrial Fibrillation Database and the experimental results revealed a good accuracy of AF detection in terms of sensitivity and specificity (above 90%).

Exploring three faint source detections methods for aperture synthesis radio images

NASA Astrophysics Data System (ADS)

Peracaula, M.; Torrent, A.; Masias, M.; Lladó, X.; Freixenet, J.; Martí, J.; Sánchez-Sutil, J. R.; Muñoz-Arjonilla, A. J.; Paredes, J. M.

2015-04-01

Wide-field radio interferometric images often contain a large population of faint compact sources. Due to their low intensity/noise ratio, these objects can be easily missed by automated detection methods, which have been classically based on thresholding techniques after local noise estimation. The aim of this paper is to present and analyse the performance of several alternative or complementary techniques to thresholding. We compare three different algorithms to increase the detection rate of faint objects. The first technique consists of combining wavelet decomposition with local thresholding. The second technique is based on the structural behaviour of the neighbourhood of each pixel. Finally, the third algorithm uses local features extracted from a bank of filters and a boosting classifier to perform the detections. The methods' performances are evaluated using simulations and radio mosaics from the Giant Metrewave Radio Telescope and the Australia Telescope Compact Array. We show that the new methods perform better than well-known state of the art methods such as SEXTRACTOR, SAD and DUCHAMP at detecting faint sources of radio interferometric images.

Training set optimization and classifier performance in a top-down diabetic retinopathy screening system

NASA Astrophysics Data System (ADS)

Wigdahl, J.; Agurto, C.; Murray, V.; Barriga, S.; Soliz, P.

2013-03-01

Diabetic retinopathy (DR) affects more than 4.4 million Americans age 40 and over. Automatic screening for DR has shown to be an efficient and cost-effective way to lower the burden on the healthcare system, by triaging diabetic patients and ensuring timely care for those presenting with DR. Several supervised algorithms have been developed to detect pathologies related to DR, but little work has been done in determining the size of the training set that optimizes an algorithm's performance. In this paper we analyze the effect of the training sample size on the performance of a top-down DR screening algorithm for different types of statistical classifiers. Results are based on partial least squares (PLS), support vector machines (SVM), k-nearest neighbor (kNN), and Naïve Bayes classifiers. Our dataset consisted of digital retinal images collected from a total of 745 cases (595 controls, 150 with DR). We varied the number of normal controls in the training set, while keeping the number of DR samples constant, and repeated the procedure 10 times using randomized training sets to avoid bias. Results show increasing performance in terms of area under the ROC curve (AUC) when the number of DR subjects in the training set increased, with similar trends for each of the classifiers. Of these, PLS and k-NN had the highest average AUC. Lower standard deviation and a flattening of the AUC curve gives evidence that there is a limit to the learning ability of the classifiers and an optimal number of cases to train on.

Assessing the similarity of surface linguistic features related to epilepsy across pediatric hospitals.

PubMed

Connolly, Brian; Matykiewicz, Pawel; Bretonnel Cohen, K; Standridge, Shannon M; Glauser, Tracy A; Dlugos, Dennis J; Koh, Susan; Tham, Eric; Pestian, John

2014-01-01

The constant progress in computational linguistic methods provides amazing opportunities for discovering information in clinical text and enables the clinical scientist to explore novel approaches to care. However, these new approaches need evaluation. We describe an automated system to compare descriptions of epilepsy patients at three different organizations: Cincinnati Children's Hospital, the Children's Hospital Colorado, and the Children's Hospital of Philadelphia. To our knowledge, there have been no similar previous studies. In this work, a support vector machine (SVM)-based natural language processing (NLP) algorithm is trained to classify epilepsy progress notes as belonging to a patient with a specific type of epilepsy from a particular hospital. The same SVM is then used to classify notes from another hospital. Our null hypothesis is that an NLP algorithm cannot be trained using epilepsy-specific notes from one hospital and subsequently used to classify notes from another hospital better than a random baseline classifier. The hypothesis is tested using epilepsy progress notes from the three hospitals. We are able to reject the null hypothesis at the 95% level. It is also found that classification was improved by including notes from a second hospital in the SVM training sample. With a reasonably uniform epilepsy vocabulary and an NLP-based algorithm able to use this uniformity to classify epilepsy progress notes across different hospitals, we can pursue automated comparisons of patient conditions, treatments, and diagnoses across different healthcare settings. 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.

Large Unbalanced Credit Scoring Using Lasso-Logistic Regression Ensemble

PubMed Central

Wang, Hong; Xu, Qingsong; Zhou, Lifeng

2015-01-01

Recently, various ensemble learning methods with different base classifiers have been proposed for credit scoring problems. However, for various reasons, there has been little research using logistic regression as the base classifier. In this paper, given large unbalanced data, we consider the plausibility of ensemble learning using regularized logistic regression as the base classifier to deal with credit scoring problems. In this research, the data is first balanced and diversified by clustering and bagging algorithms. Then we apply a Lasso-logistic regression learning ensemble to evaluate the credit risks. We show that the proposed algorithm outperforms popular credit scoring models such as decision tree, Lasso-logistic regression and random forests in terms of AUC and F-measure. We also provide two importance measures for the proposed model to identify important variables in the data. PMID:25706988

The IPAC Image Subtraction and Discovery Pipeline for the Intermediate Palomar Transient Factory

NASA Astrophysics Data System (ADS)

Masci, Frank J.; Laher, Russ R.; Rebbapragada, Umaa D.; Doran, Gary B.; Miller, Adam A.; Bellm, Eric; Kasliwal, Mansi; Ofek, Eran O.; Surace, Jason; Shupe, David L.; Grillmair, Carl J.; Jackson, Ed; Barlow, Tom; Yan, Lin; Cao, Yi; Cenko, S. Bradley; Storrie-Lombardi, Lisa J.; Helou, George; Prince, Thomas A.; Kulkarni, Shrinivas R.

2017-01-01

We describe the near real-time transient-source discovery engine for the intermediate Palomar Transient Factory (iPTF), currently in operations at the Infrared Processing and Analysis Center (IPAC), Caltech. We coin this system the IPAC/iPTF Discovery Engine (or IDE). We review the algorithms used for PSF-matching, image subtraction, detection, photometry, and machine-learned (ML) vetting of extracted transient candidates. We also review the performance of our ML classifier. For a limiting signal-to-noise ratio of 4 in relatively unconfused regions, bogus candidates from processing artifacts and imperfect image subtractions outnumber real transients by ≃10:1. This can be considerably higher for image data with inaccurate astrometric and/or PSF-matching solutions. Despite this occasionally high contamination rate, the ML classifier is able to identify real transients with an efficiency (or completeness) of ≃97% for a maximum tolerable false-positive rate of 1% when classifying raw candidates. All subtraction-image metrics, source features, ML probability-based real-bogus scores, contextual metadata from other surveys, and possible associations with known Solar System objects are stored in a relational database for retrieval by the various science working groups. We review our efforts in mitigating false-positives and our experience in optimizing the overall system in response to the multitude of science projects underway with iPTF.

The IPAC Image Subtraction and Discovery Pipeline for the Intermediate Palomar Transient Factory

NASA Technical Reports Server (NTRS)

Masci, Frank J.; Laher, Russ R.; Rebbapragada, Umaa D.; Doran, Gary B.; Miller, Adam A.; Bellm, Eric; Kasliwal, Mansi; Ofek, Eran O.; Surace, Jason; Shupe, David L.;

Comparison Between Supervised and Unsupervised Classifications of Neuronal Cell Types: A Case Study

PubMed Central

Guerra, Luis; McGarry, Laura M; Robles, Víctor; Bielza, Concha; Larrañaga, Pedro; Yuste, Rafael

2011-01-01

In the study of neural circuits, it becomes essential to discern the different neuronal cell types that build the circuit. Traditionally, neuronal cell types have been classified using qualitative descriptors. More recently, several attempts have been made to classify neurons quantitatively, using unsupervised clustering methods. While useful, these algorithms do not take advantage of previous information known to the investigator, which could improve the classification task. For neocortical GABAergic interneurons, the problem to discern among different cell types is particularly difficult and better methods are needed to perform objective classifications. Here we explore the use of supervised classification algorithms to classify neurons based on their morphological features, using a database of 128 pyramidal cells and 199 interneurons from mouse neocortex. To evaluate the performance of different algorithms we used, as a “benchmark,” the test to automatically distinguish between pyramidal cells and interneurons, defining “ground truth” by the presence or absence of an apical dendrite. We compared hierarchical clustering with a battery of different supervised classification algorithms, finding that supervised classifications outperformed hierarchical clustering. In addition, the selection of subsets of distinguishing features enhanced the classification accuracy for both sets of algorithms. The analysis of selected variables indicates that dendritic features were most useful to distinguish pyramidal cells from interneurons when compared with somatic and axonal morphological variables. We conclude that supervised classification algorithms are better matched to the general problem of distinguishing neuronal cell types when some information on these cell groups, in our case being pyramidal or interneuron, is known a priori. As a spin-off of this methodological study, we provide several methods to automatically distinguish neocortical pyramidal cells from interneurons, based on their morphologies. © 2010 Wiley Periodicals, Inc. Develop Neurobiol 71: 71–82, 2011 PMID:21154911

Network Intrusion Detection Based on a General Regression Neural Network Optimized by an Improved Artificial Immune Algorithm

PubMed Central

Wu, Jianfa; Peng, Dahao; Li, Zhuping; Zhao, Li; Ling, Huanzhang

2015-01-01

To effectively and accurately detect and classify network intrusion data, this paper introduces a general regression neural network (GRNN) based on the artificial immune algorithm with elitist strategies (AIAE). The elitist archive and elitist crossover were combined with the artificial immune algorithm (AIA) to produce the AIAE-GRNN algorithm, with the aim of improving its adaptivity and accuracy. In this paper, the mean square errors (MSEs) were considered the affinity function. The AIAE was used to optimize the smooth factors of the GRNN; then, the optimal smooth factor was solved and substituted into the trained GRNN. Thus, the intrusive data were classified. The paper selected a GRNN that was separately optimized using a genetic algorithm (GA), particle swarm optimization (PSO), and fuzzy C-mean clustering (FCM) to enable a comparison of these approaches. As shown in the results, the AIAE-GRNN achieves a higher classification accuracy than PSO-GRNN, but the running time of AIAE-GRNN is long, which was proved first. FCM and GA-GRNN were eliminated because of their deficiencies in terms of accuracy and convergence. To improve the running speed, the paper adopted principal component analysis (PCA) to reduce the dimensions of the intrusive data. With the reduction in dimensionality, the PCA-AIAE-GRNN decreases in accuracy less and has better convergence than the PCA-PSO-GRNN, and the running speed of the PCA-AIAE-GRNN was relatively improved. The experimental results show that the AIAE-GRNN has a higher robustness and accuracy than the other algorithms considered and can thus be used to classify the intrusive data. PMID:25807466

Generating compact classifier systems using a simple artificial immune system.

PubMed

Leung, Kevin; Cheong, France; Cheong, Christopher

2007-10-01

Current artificial immune system (AIS) classifiers have two major problems: 1) their populations of B-cells can grow to huge proportions, and 2) optimizing one B-cell (part of the classifier) at a time does not necessarily guarantee that the B-cell pool (the whole classifier) will be optimized. In this paper, the design of a new AIS algorithm and classifier system called simple AIS is described. It is different from traditional AIS classifiers in that it takes only one B-cell, instead of a B-cell pool, to represent the classifier. This approach ensures global optimization of the whole system, and in addition, no population control mechanism is needed. The classifier was tested on seven benchmark data sets using different classification techniques and was found to be very competitive when compared to other classifiers.

Efficient quantitative assessment of facial paralysis using iris segmentation and active contour-based key points detection with hybrid classifier.

PubMed

Barbosa, Jocelyn; Lee, Kyubum; Lee, Sunwon; Lodhi, Bilal; Cho, Jae-Gu; Seo, Woo-Keun; Kang, Jaewoo

2016-03-12

Facial palsy or paralysis (FP) is a symptom that loses voluntary muscles movement in one side of the human face, which could be very devastating in the part of the patients. Traditional methods are solely dependent to clinician's judgment and therefore time consuming and subjective in nature. Hence, a quantitative assessment system becomes apparently invaluable for physicians to begin the rehabilitation process; and to produce a reliable and robust method is challenging and still underway. We introduce a novel approach for a quantitative assessment of facial paralysis that tackles classification problem for FP type and degree of severity. Specifically, a novel method of quantitative assessment is presented: an algorithm that extracts the human iris and detects facial landmarks; and a hybrid approach combining the rule-based and machine learning algorithm to analyze and prognosticate facial paralysis using the captured images. A method combining the optimized Daugman's algorithm and Localized Active Contour (LAC) model is proposed to efficiently extract the iris and facial landmark or key points. To improve the performance of LAC, appropriate parameters of initial evolving curve for facial features' segmentation are automatically selected. The symmetry score is measured by the ratio between features extracted from the two sides of the face. Hybrid classifiers (i.e. rule-based with regularized logistic regression) were employed for discriminating healthy and unhealthy subjects, FP type classification, and for facial paralysis grading based on House-Brackmann (H-B) scale. Quantitative analysis was performed to evaluate the performance of the proposed approach. Experiments show that the proposed method demonstrates its efficiency. Facial movement feature extraction on facial images based on iris segmentation and LAC-based key point detection along with a hybrid classifier provides a more efficient way of addressing classification problem on facial palsy type and degree of severity. Combining iris segmentation and key point-based method has several merits that are essential for our real application. Aside from the facial key points, iris segmentation provides significant contribution as it describes the changes of the iris exposure while performing some facial expressions. It reveals the significant difference between the healthy side and the severe palsy side when raising eyebrows with both eyes directed upward, and can model the typical changes in the iris region.

D Semantic Labeling of ALS Data Based on Domain Adaption by Transferring and Fusing Random Forest Models

NASA Astrophysics Data System (ADS)

Wu, J.; Yao, W.; Zhang, J.; Li, Y.

2018-04-01

Labeling 3D point cloud data with traditional supervised learning methods requires considerable labelled samples, the collection of which is cost and time expensive. This work focuses on adopting domain adaption concept to transfer existing trained random forest classifiers (based on source domain) to new data scenes (target domain), which aims at reducing the dependence of accurate 3D semantic labeling in point clouds on training samples from the new data scene. Firstly, two random forest classifiers were firstly trained with existing samples previously collected for other data. They were different from each other by using two different decision tree construction algorithms: C4.5 with information gain ratio and CART with Gini index. Secondly, four random forest classifiers adapted to the target domain are derived through transferring each tree in the source random forest models with two types of operations: structure expansion and reduction-SER and structure transfer-STRUT. Finally, points in target domain are labelled by fusing the four newly derived random forest classifiers using weights of evidence based fusion model. To validate our method, experimental analysis was conducted using 3 datasets: one is used as the source domain data (Vaihingen data for 3D Semantic Labelling); another two are used as the target domain data from two cities in China (Jinmen city and Dunhuang city). Overall accuracies of 85.5 % and 83.3 % for 3D labelling were achieved for Jinmen city and Dunhuang city data respectively, with only 1/3 newly labelled samples compared to the cases without domain adaption.

DNABIT Compress - Genome compression algorithm.

PubMed

Rajarajeswari, Pothuraju; Apparao, Allam

2011-01-22

Data compression is concerned with how information is organized in data. Efficient storage means removal of redundancy from the data being stored in the DNA molecule. Data compression algorithms remove redundancy and are used to understand biologically important molecules. We present a compression algorithm, "DNABIT Compress" for DNA sequences based on a novel algorithm of assigning binary bits for smaller segments of DNA bases to compress both repetitive and non repetitive DNA sequence. Our proposed algorithm achieves the best compression ratio for DNA sequences for larger genome. Significantly better compression results show that "DNABIT Compress" algorithm is the best among the remaining compression algorithms. While achieving the best compression ratios for DNA sequences (Genomes),our new DNABIT Compress algorithm significantly improves the running time of all previous DNA compression programs. Assigning binary bits (Unique BIT CODE) for (Exact Repeats, Reverse Repeats) fragments of DNA sequence is also a unique concept introduced in this algorithm for the first time in DNA compression. This proposed new algorithm could achieve the best compression ratio as much as 1.58 bits/bases where the existing best methods could not achieve a ratio less than 1.72 bits/bases.

Algorithms for Image Analysis and Combination of Pattern Classifiers with Application to Medical Diagnosis

NASA Astrophysics Data System (ADS)

Georgiou, Harris

2009-10-01

Medical Informatics and the application of modern signal processing in the assistance of the diagnostic process in medical imaging is one of the more recent and active research areas today. This thesis addresses a variety of issues related to the general problem of medical image analysis, specifically in mammography, and presents a series of algorithms and design approaches for all the intermediate levels of a modern system for computer-aided diagnosis (CAD). The diagnostic problem is analyzed with a systematic approach, first defining the imaging characteristics and features that are relevant to probable pathology in mammo-grams. Next, these features are quantified and fused into new, integrated radio-logical systems that exhibit embedded digital signal processing, in order to improve the final result and minimize the radiological dose for the patient. In a higher level, special algorithms are designed for detecting and encoding these clinically interest-ing imaging features, in order to be used as input to advanced pattern classifiers and machine learning models. Finally, these approaches are extended in multi-classifier models under the scope of Game Theory and optimum collective deci-sion, in order to produce efficient solutions for combining classifiers with minimum computational costs for advanced diagnostic systems. The material covered in this thesis is related to a total of 18 published papers, 6 in scientific journals and 12 in international conferences.

Compositing multitemporal remote sensing data sets

USGS Publications Warehouse

Qi, J.; Huete, A.R.; Hood, J.; Kerr, Y.

1993-01-01

To eliminate cloud and atmosphere-affected pixels, the compositing of multi temporal remote sensing data sets is done by selecting the maximum vale of the normalized different vegetation index (NDVI) within a compositing period. The NDVI classifier, however, is strongly affected by surface type and anisotropic properties, sensor viewing geometries, and atmospheric conditions. Consequently, the composited, multi temporal, remote sensing data contain substantial noise from these external conditions. Consequently, the composited, multi temporal, remote sensing data contain substantial noise from these external effects. To improve the accuracy of compositing products, two key approaches can be taken: one is to refine the compositing classifier (NDVI) and the other is to improve existing compositing algorithms. In this project, an alternative classifier was developed and an alternative pixel selection criterion was proposed for compositing. The new classifier and the alternative compositing algorithm were applied to an advanced very high resolution radiometer data set of different biome types in the United States. The results were compared with the maximum value compositing and the best index slope extraction algorithms. The new approaches greatly reduced the high frequency noises related to the external factors and repainted more reliable data. The results suggest that the geometric-optical canopy properties of specific biomes may be needed in compositing. Limitations of the new approaches include the dependency of pixel selection on the length of the composite period and data discontinuity.

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.

Spatial and spectral analysis of corneal epithelium injury using hyperspectral images

NASA Astrophysics Data System (ADS)

Md Noor, Siti Salwa; Michael, Kaleena; Marshall, Stephen; Ren, Jinchang

2017-12-01

Eye assessment is essential in preventing blindness. Currently, the existing methods to assess corneal epithelium injury are complex and require expert knowledge. Hence, we have introduced a non-invasive technique using hyperspectral imaging (HSI) and an image analysis algorithm of corneal epithelium injury. Three groups of images were compared and analyzed, namely healthy eyes, injured eyes, and injured eyes with stain. Dimensionality reduction using principal component analysis (PCA) was applied to reduce massive data and redundancies. The first 10 principal components (PCs) were selected for further processing. The mean vector of 10 PCs with 45 pairs of all combinations was computed and sent to two classifiers. A quadratic Bayes normal classifier (QDC) and a support vector classifier (SVC) were used in this study to discriminate the eleven eyes into three groups. As a result, the combined classifier of QDC and SVC showed optimal performance with 2D PCA features (2DPCA-QDSVC) and was utilized to classify normal and abnormal tissues, using color image segmentation. The result was compared with human segmentation. The outcome showed that the proposed algorithm produced extremely promising results to assist the clinician in quantifying a cornea injury.

Real-time 3D human pose recognition from reconstructed volume via voxel classifiers

NASA Astrophysics Data System (ADS)

Yoo, ByungIn; Choi, Changkyu; Han, Jae-Joon; Lee, Changkyo; Kim, Wonjun; Suh, Sungjoo; Park, Dusik; Kim, Junmo

2014-03-01

This paper presents a human pose recognition method which simultaneously reconstructs a human volume based on ensemble of voxel classifiers from a single depth image in real-time. The human pose recognition is a difficult task since a single depth camera can capture only visible surfaces of a human body. In order to recognize invisible (self-occluded) surfaces of a human body, the proposed algorithm employs voxel classifiers trained with multi-layered synthetic voxels. Specifically, ray-casting onto a volumetric human model generates a synthetic voxel, where voxel consists of a 3D position and ID corresponding to the body part. The synthesized volumetric data which contain both visible and invisible body voxels are utilized to train the voxel classifiers. As a result, the voxel classifiers not only identify the visible voxels but also reconstruct the 3D positions and the IDs of the invisible voxels. The experimental results show improved performance on estimating the human poses due to the capability of inferring the invisible human body voxels. It is expected that the proposed algorithm can be applied to many fields such as telepresence, gaming, virtual fitting, wellness business, and real 3D contents control on real 3D displays.

Advanced methods in NDE using machine learning approaches

NASA Astrophysics Data System (ADS)

Wunderlich, Christian; Tschöpe, Constanze; Duckhorn, Frank

2018-04-01

Machine learning (ML) methods and algorithms have been applied recently with great success in quality control and predictive maintenance. Its goal to build new and/or leverage existing algorithms to learn from training data and give accurate predictions, or to find patterns, particularly with new and unseen similar data, fits perfectly to Non-Destructive Evaluation. The advantages of ML in NDE are obvious in such tasks as pattern recognition in acoustic signals or automated processing of images from X-ray, Ultrasonics or optical methods. Fraunhofer IKTS is using machine learning algorithms in acoustic signal analysis. The approach had been applied to such a variety of tasks in quality assessment. The principal approach is based on acoustic signal processing with a primary and secondary analysis step followed by a cognitive system to create model data. Already in the second analysis steps unsupervised learning algorithms as principal component analysis are used to simplify data structures. In the cognitive part of the software further unsupervised and supervised learning algorithms will be trained. Later the sensor signals from unknown samples can be recognized and classified automatically by the algorithms trained before. Recently the IKTS team was able to transfer the software for signal processing and pattern recognition to a small printed circuit board (PCB). Still, algorithms will be trained on an ordinary PC; however, trained algorithms run on the Digital Signal Processor and the FPGA chip. The identical approach will be used for pattern recognition in image analysis of OCT pictures. Some key requirements have to be fulfilled, however. A sufficiently large set of training data, a high signal-to-noise ratio, and an optimized and exact fixation of components are required. The automated testing can be done subsequently by the machine. By integrating the test data of many components along the value chain further optimization including lifetime and durability prediction based on big data becomes possible, even if components are used in different versions or configurations. This is the promise behind German Industry 4.0.

Evaluation of registration, compression and classification algorithms. Volume 1: Results

NASA Technical Reports Server (NTRS)

Jayroe, R.; Atkinson, R.; Callas, L.; Hodges, J.; Gaggini, B.; Peterson, J.

1979-01-01

The registration, compression, and classification algorithms were selected on the basis that such a group would include most of the different and commonly used approaches. The results of the investigation indicate clearcut, cost effective choices for registering, compressing, and classifying multispectral imagery.

Word recognition using a lexicon constrained by first/last character decisions

NASA Astrophysics Data System (ADS)

Zhao, Sheila X.; Srihari, Sargur N.

1995-03-01

In lexicon based recognition of machine-printed word images, the size of the lexicon can be quite extensive. The recognition performance is closely related to the size of the lexicon. Recognition performance drops quickly when lexicon size increases. Here, we present an algorithm to improve the word recognition performance by reducing the size of the given lexicon. The algorithm utilizes the information provided by the first and last characters of a word to reduce the size of the given lexicon. Given a word image and a lexicon that contains the word in the image, the first and last characters are segmented and then recognized by a character classifier. The possible candidates based on the results given by the classifier are selected, which give us the sub-lexicon. Then a word shape analysis algorithm is applied to produce the final ranking of the given lexicon. The algorithm was tested on a set of machine- printed gray-scale word images which includes a wide range of print types and qualities.

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

Stinnett, Jacob; Sullivan, Clair J.; Xiong, Hao

Low-resolution isotope identifiers are widely deployed for nuclear security purposes, but these detectors currently demonstrate problems in making correct identifications in many typical usage scenarios. While there are many hardware alternatives and improvements that can be made, performance on existing low resolution isotope identifiers should be able to be improved by developing new identification algorithms. We have developed a wavelet-based peak extraction algorithm and an implementation of a Bayesian classifier for automated peak-based identification. The peak extraction algorithm has been extended to compute uncertainties in the peak area calculations. To build empirical joint probability distributions of the peak areas andmore » uncertainties, a large set of spectra were simulated in MCNP6 and processed with the wavelet-based feature extraction algorithm. Kernel density estimation was then used to create a new component of the likelihood function in the Bayesian classifier. Furthermore, identification performance is demonstrated on a variety of real low-resolution spectra, including Category I quantities of special nuclear material.« less

Using Machine Learning and Natural Language Processing Algorithms to Automate the Evaluation of Clinical Decision Support in Electronic Medical Record Systems.

PubMed

Szlosek, Donald A; Ferrett, Jonathan

2016-01-01

As the number of clinical decision support systems (CDSSs) incorporated into electronic medical records (EMRs) increases, so does the need to evaluate their effectiveness. The use of medical record review and similar manual methods for evaluating decision rules is laborious and inefficient. The authors use machine learning and Natural Language Processing (NLP) algorithms to accurately evaluate a clinical decision support rule through an EMR system, and they compare it against manual evaluation. Modeled after the EMR system EPIC at Maine Medical Center, we developed a dummy data set containing physician notes in free text for 3,621 artificial patients records undergoing a head computed tomography (CT) scan for mild traumatic brain injury after the incorporation of an electronic best practice approach. We validated the accuracy of the Best Practice Advisories (BPA) using three machine learning algorithms-C-Support Vector Classification (SVC), Decision Tree Classifier (DecisionTreeClassifier), k-nearest neighbors classifier (KNeighborsClassifier)-by comparing their accuracy for adjudicating the occurrence of a mild traumatic brain injury against manual review. We then used the best of the three algorithms to evaluate the effectiveness of the BPA, and we compared the algorithm's evaluation of the BPA to that of manual review. The electronic best practice approach was found to have a sensitivity of 98.8 percent (96.83-100.0), specificity of 10.3 percent, PPV = 7.3 percent, and NPV = 99.2 percent when reviewed manually by abstractors. Though all the machine learning algorithms were observed to have a high level of prediction, the SVC displayed the highest with a sensitivity 93.33 percent (92.49-98.84), specificity of 97.62 percent (96.53-98.38), PPV = 50.00, NPV = 99.83. The SVC algorithm was observed to have a sensitivity of 97.9 percent (94.7-99.86), specificity 10.30 percent, PPV 7.25 percent, and NPV 99.2 percent for evaluating the best practice approach, after accounting for 17 cases (0.66 percent) where the patient records had to be reviewed manually due to the NPL systems inability to capture the proper diagnosis. CDSSs incorporated into EMRs can be evaluated in an automatic fashion by using NLP and machine learning techniques.

A novel evaluation of two related and two independent algorithms for eye movement classification during reading.

PubMed

Friedman, Lee; Rigas, Ioannis; Abdulin, Evgeny; Komogortsev, Oleg V

2018-05-15

Nystrӧm and Holmqvist have published a method for the classification of eye movements during reading (ONH) (Nyström & Holmqvist, 2010). When we applied this algorithm to our data, the results were not satisfactory, so we modified the algorithm (now the MNH) to better classify our data. The changes included: (1) reducing the amount of signal filtering, (2) excluding a new type of noise, (3) removing several adaptive thresholds and replacing them with fixed thresholds, (4) changing the way that the start and end of each saccade was determined, (5) employing a new algorithm for detecting PSOs, and (6) allowing a fixation period to either begin or end with noise. A new method for the evaluation of classification algorithms is presented. It was designed to provide comprehensive feedback to an algorithm developer, in a time-efficient manner, about the types and numbers of classification errors that an algorithm produces. This evaluation was conducted by three expert raters independently, across 20 randomly chosen recordings, each classified by both algorithms. The MNH made many fewer errors in determining when saccades start and end, and it also detected some fixations and saccades that the ONH did not. The MNH fails to detect very small saccades. We also evaluated two additional algorithms: the EyeLink Parser and a more current, machine-learning-based algorithm. The EyeLink Parser tended to find more saccades that ended too early than did the other methods, and we found numerous problems with the output of the machine-learning-based algorithm.

A Hybrid Color Space for Skin Detection Using Genetic Algorithm Heuristic Search and Principal Component Analysis Technique

PubMed Central

2015-01-01

Color is one of the most prominent features of an image and used in many skin and face detection applications. Color space transformation is widely used by researchers to improve face and skin detection performance. Despite the substantial research efforts in this area, choosing a proper color space in terms of skin and face classification performance which can address issues like illumination variations, various camera characteristics and diversity in skin color tones has remained an open issue. This research proposes a new three-dimensional hybrid color space termed SKN by employing the Genetic Algorithm heuristic and Principal Component Analysis to find the optimal representation of human skin color in over seventeen existing color spaces. Genetic Algorithm heuristic is used to find the optimal color component combination setup in terms of skin detection accuracy while the Principal Component Analysis projects the optimal Genetic Algorithm solution to a less complex dimension. Pixel wise skin detection was used to evaluate the performance of the proposed color space. We have employed four classifiers including Random Forest, Naïve Bayes, Support Vector Machine and Multilayer Perceptron in order to generate the human skin color predictive model. The proposed color space was compared to some existing color spaces and shows superior results in terms of pixel-wise skin detection accuracy. Experimental results show that by using Random Forest classifier, the proposed SKN color space obtained an average F-score and True Positive Rate of 0.953 and False Positive Rate of 0.0482 which outperformed the existing color spaces in terms of pixel wise skin detection accuracy. The results also indicate that among the classifiers used in this study, Random Forest is the most suitable classifier for pixel wise skin detection applications. PMID:26267377

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

PubMed Central

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

2016-01-01

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

Combining Passive Microwave Rain Rate Retrieval with Visible and Infrared Cloud Classification.

NASA Astrophysics Data System (ADS)

Miller, Shawn William

The relation between cloud type and rain rate has been investigated here from different approaches. Previous studies and intercomparisons have indicated that no single passive microwave rain rate algorithm is an optimal choice for all types of precipitating systems. Motivated by the upcoming Tropical Rainfall Measuring Mission (TRMM), an algorithm which combines visible and infrared cloud classification with passive microwave rain rate estimation was developed and analyzed in a preliminary manner using data from the Tropical Ocean Global Atmosphere-Coupled Ocean Atmosphere Response Experiment (TOGA-COARE). Overall correlation with radar rain rate measurements across five case studies showed substantial improvement in the combined algorithm approach when compared to the use of any single microwave algorithm. An automated neural network cloud classifier for use over both land and ocean was independently developed and tested on Advanced Very High Resolution Radiometer (AVHRR) data. The global classifier achieved strict accuracy for 82% of the test samples, while a more localized version achieved strict accuracy for 89% of its own test set. These numbers provide hope for the eventual development of a global automated cloud classifier for use throughout the tropics and the temperate zones. The localized classifier was used in conjunction with gridded 15-minute averaged radar rain rates at 8km resolution produced from the current operational network of National Weather Service (NWS) radars, to investigate the relation between cloud type and rain rate over three regions of the continental United States and adjacent waters. The results indicate a substantially lower amount of available moisture in the Front Range of the Rocky Mountains than in the Midwest or in the eastern Gulf of Mexico.

Is diabetes mellitus correctly registered and classified in primary care? A population-based study in Catalonia, Spain.

PubMed

Mata-Cases, Manel; Mauricio, Dídac; Real, Jordi; Bolíbar, Bonaventura; Franch-Nadal, Josep

2016-11-01

To assess the prevalence of miscoding, misclassification, misdiagnosis and under-registration of diabetes mellitus (DM) in primary health care in Catalonia (Spain), and to explore use of automated algorithms to identify them. In this cross-sectional, retrospective study using an anonymized electronic general practice database, data were collected from patients or users with a diabetes-related code or from patients with no DM or prediabetes code but treated with antidiabetic drugs (unregistered DM). Decision algorithms were designed to classify the true diagnosis of type 1 DM (T1DM), type 2 DM (T2DM), and undetermined DM (UDM), and to classify unregistered DM patients treated with antidiabetic drugs. Data were collected from a total of 376,278 subjects with a DM ICD-10 code, and from 8707 patients with no DM or prediabetes code but treated with antidiabetic drugs. After application of the algorithms, 13.9% of patients with T1DM were identified as misclassified, and were probably T2DM; 80.9% of patients with UDM were reclassified as T2DM, and 19.1% of them were misdiagnosed as DM when they probably had prediabetes. The overall prevalence of miscoding (multiple codes or UDM) was 2.2%. Finally, 55.2% of subjects with unregistered DM were classified as prediabetes, 35.7% as T2DM, 8.5% as UDM treated with insulin, and 0.6% as T1DM. The prevalence of inappropriate codification or classification and under-registration of DM is relevant in primary care. Implementation of algorithms could automatically flag cases that need review and would substantially decrease the risk of inappropriate registration or coding. Copyright © 2016 SEEN. Publicado por Elsevier España, S.L.U. All rights reserved.

Sub-Volumetric Classification and Visualization of Emphysema Using a Multi-Threshold Method and Neural Network

NASA Astrophysics Data System (ADS)

Tan, Kok Liang; Tanaka, Toshiyuki; Nakamura, Hidetoshi; Shirahata, Toru; Sugiura, Hiroaki

Chronic Obstructive Pulmonary Disease is a disease in which the airways and tiny air sacs (alveoli) inside the lung are partially obstructed or destroyed. Emphysema is what occurs as more and more of the walls between air sacs get destroyed. The goal of this paper is to produce a more practical emphysema-quantification algorithm that has higher correlation with the parameters of pulmonary function tests compared to classical methods. The use of the threshold range from approximately -900 Hounsfield Unit to -990 Hounsfield Unit for extracting emphysema from CT has been reported in many papers. From our experiments, we realize that a threshold which is optimal for a particular CT data set might not be optimal for other CT data sets due to the subtle radiographic variations in the CT images. Consequently, we propose a multi-threshold method that utilizes ten thresholds between and including -900 Hounsfield Unit and -990 Hounsfield Unit for identifying the different potential emphysematous regions in the lung. Subsequently, we divide the lung into eight sub-volumes. From each sub-volume, we calculate the ratio of the voxels with the intensity below a certain threshold. The respective ratios of the voxels below the ten thresholds are employed as the features for classifying the sub-volumes into four emphysema severity classes. Neural network is used as the classifier. The neural network is trained using 80 training sub-volumes. The performance of the classifier is assessed by classifying 248 test sub-volumes of the lung obtained from 31 subjects. Actual diagnoses of the sub-volumes are hand-annotated and consensus-classified by radiologists. The four-class classification accuracy of the proposed method is 89.82%. The sub-volumetric classification results produced in this study encompass not only the information of emphysema severity but also the distribution of emphysema severity from the top to the bottom of the lung. We hypothesize that besides emphysema severity, the distribution of emphysema severity in the lung also plays an important role in the assessment of the overall functionality of the lung. We confirm our hypothesis by showing that the proposed sub-volumetric classification results correlate with the parameters of pulmonary function tests better than classical methods. We also visualize emphysema using a technique called the transparent lung model.

Machine Learning for Biological Trajectory Classification Applications

NASA Technical Reports Server (NTRS)

Sbalzarini, Ivo F.; Theriot, Julie; Koumoutsakos, Petros

2002-01-01

Machine-learning techniques, including clustering algorithms, support vector machines and hidden Markov models, are applied to the task of classifying trajectories of moving keratocyte cells. The different algorithms axe compared to each other as well as to expert and non-expert test persons, using concepts from signal-detection theory. The algorithms performed very well as compared to humans, suggesting a robust tool for trajectory classification in biological applications.

Comparison and optimization of in silico algorithms for predicting the pathogenicity of sodium channel variants in epilepsy.

PubMed

Holland, Katherine D; Bouley, Thomas M; Horn, Paul S

2017-07-01

Variants in neuronal voltage-gated sodium channel α-subunits genes SCN1A, SCN2A, and SCN8A are common in early onset epileptic encephalopathies and other autosomal dominant childhood epilepsy syndromes. However, in clinical practice, missense variants are often classified as variants of uncertain significance when missense variants are identified but heritability cannot be determined. Genetic testing reports often include results of computational tests to estimate pathogenicity and the frequency of that variant in population-based databases. The objective of this work was to enhance clinicians' understanding of results by (1) determining how effectively computational algorithms predict epileptogenicity of sodium channel (SCN) missense variants; (2) optimizing their predictive capabilities; and (3) determining if epilepsy-associated SCN variants are present in population-based databases. This will help clinicians better understand the results of indeterminate SCN test results in people with epilepsy. Pathogenic, likely pathogenic, and benign variants in SCNs were identified using databases of sodium channel variants. Benign variants were also identified from population-based databases. Eight algorithms commonly used to predict pathogenicity were compared. In addition, logistic regression was used to determine if a combination of algorithms could better predict pathogenicity. Based on American College of Medical Genetic Criteria, 440 variants were classified as pathogenic or likely pathogenic and 84 were classified as benign or likely benign. Twenty-eight variants previously associated with epilepsy were present in population-based gene databases. The output provided by most computational algorithms had a high sensitivity but low specificity with an accuracy of 0.52-0.77. Accuracy could be improved by adjusting the threshold for pathogenicity. Using this adjustment, the Mendelian Clinically Applicable Pathogenicity (M-CAP) algorithm had an accuracy of 0.90 and a combination of algorithms increased the accuracy to 0.92. Potentially pathogenic variants are present in population-based sources. Most computational algorithms overestimate pathogenicity; however, a weighted combination of several algorithms increased classification accuracy to >0.90. Wiley Periodicals, Inc. © 2017 International League Against Epilepsy.

Automated detection of diabetic retinopathy lesions on ultrawidefield pseudocolour images.

PubMed

Wang, Kang; Jayadev, Chaitra; Nittala, Muneeswar G; Velaga, Swetha B; Ramachandra, Chaithanya A; Bhaskaranand, Malavika; Bhat, Sandeep; Solanki, Kaushal; Sadda, SriniVas R

2018-03-01

We examined the sensitivity and specificity of an automated algorithm for detecting referral-warranted diabetic retinopathy (DR) on Optos ultrawidefield (UWF) pseudocolour images. Patients with diabetes were recruited for UWF imaging. A total of 383 subjects (754 eyes) were enrolled. Nonproliferative DR graded to be moderate or higher on the 5-level International Clinical Diabetic Retinopathy (ICDR) severity scale was considered as grounds for referral. The software automatically detected DR lesions using the previously trained classifiers and classified each image in the test set as referral-warranted or not warranted. Sensitivity, specificity and the area under the receiver operating curve (AUROC) of the algorithm were computed. The automated algorithm achieved a 91.7%/90.3% sensitivity (95% CI 90.1-93.9/80.4-89.4) with a 50.0%/53.6% specificity (95% CI 31.7-72.8/36.5-71.4) for detecting referral-warranted retinopathy at the patient/eye levels, respectively; the AUROC was 0.873/0.851 (95% CI 0.819-0.922/0.804-0.894). Diabetic retinopathy (DR) lesions were detected from Optos pseudocolour UWF images using an automated algorithm. Images were classified as referral-warranted DR with a high degree of sensitivity and moderate specificity. Automated analysis of UWF images could be of value in DR screening programmes and could allow for more complete and accurate disease staging. © 2017 Acta Ophthalmologica Scandinavica Foundation. Published by John Wiley & Sons Ltd.

HD-MTL: Hierarchical Deep Multi-Task Learning for Large-Scale Visual Recognition.

PubMed

Fan, Jianping; Zhao, Tianyi; Kuang, Zhenzhong; Zheng, Yu; Zhang, Ji; Yu, Jun; Peng, Jinye

2017-02-09

In this paper, a hierarchical deep multi-task learning (HD-MTL) algorithm is developed to support large-scale visual recognition (e.g., recognizing thousands or even tens of thousands of atomic object classes automatically). First, multiple sets of multi-level deep features are extracted from different layers of deep convolutional neural networks (deep CNNs), and they are used to achieve more effective accomplishment of the coarseto- fine tasks for hierarchical visual recognition. A visual tree is then learned by assigning the visually-similar atomic object classes with similar learning complexities into the same group, which can provide a good environment for determining the interrelated learning tasks automatically. By leveraging the inter-task relatedness (inter-class similarities) to learn more discriminative group-specific deep representations, our deep multi-task learning algorithm can train more discriminative node classifiers for distinguishing the visually-similar atomic object classes effectively. Our hierarchical deep multi-task learning (HD-MTL) algorithm can integrate two discriminative regularization terms to control the inter-level error propagation effectively, and it can provide an end-to-end approach for jointly learning more representative deep CNNs (for image representation) and more discriminative tree classifier (for large-scale visual recognition) and updating them simultaneously. Our incremental deep learning algorithms can effectively adapt both the deep CNNs and the tree classifier to the new training images and the new object classes. Our experimental results have demonstrated that our HD-MTL algorithm can achieve very competitive results on improving the accuracy rates for large-scale visual recognition.

Vibration Sensor-Based Bearing Fault Diagnosis Using Ellipsoid-ARTMAP and Differential Evolution Algorithms

PubMed Central

Liu, Chang; Wang, Guofeng; Xie, Qinglu; Zhang, Yanchao

2014-01-01

Effective fault classification of rolling element bearings provides an important basis for ensuring safe operation of rotating machinery. In this paper, a novel vibration sensor-based fault diagnosis method using an Ellipsoid-ARTMAP network (EAM) and a differential evolution (DE) algorithm is proposed. The original features are firstly extracted from vibration signals based on wavelet packet decomposition. Then, a minimum-redundancy maximum-relevancy algorithm is introduced to select the most prominent features so as to decrease feature dimensions. Finally, a DE-based EAM (DE-EAM) classifier is constructed to realize the fault diagnosis. The major characteristic of EAM is that the sample distribution of each category is realized by using a hyper-ellipsoid node and smoothing operation algorithm. Therefore, it can depict the decision boundary of disperse samples accurately and effectively avoid over-fitting phenomena. To optimize EAM network parameters, the DE algorithm is presented and two objectives, including both classification accuracy and nodes number, are simultaneously introduced as the fitness functions. Meanwhile, an exponential criterion is proposed to realize final selection of the optimal parameters. To prove the effectiveness of the proposed method, the vibration signals of four types of rolling element bearings under different loads were collected. Moreover, to improve the robustness of the classifier evaluation, a two-fold cross validation scheme is adopted and the order of feature samples is randomly arranged ten times within each fold. The results show that DE-EAM classifier can recognize the fault categories of the rolling element bearings reliably and accurately. PMID:24936949

Classification of biosensor time series using dynamic time warping: applications in screening cancer cells with characteristic biomarkers.

PubMed

Rai, Shesh N; Trainor, Patrick J; Khosravi, Farhad; Kloecker, Goetz; Panchapakesan, Balaji

2016-01-01

The development of biosensors that produce time series data will facilitate improvements in biomedical diagnostics and in personalized medicine. The time series produced by these devices often contains characteristic features arising from biochemical interactions between the sample and the sensor. To use such characteristic features for determining sample class, similarity-based classifiers can be utilized. However, the construction of such classifiers is complicated by the variability in the time domains of such series that renders the traditional distance metrics such as Euclidean distance ineffective in distinguishing between biological variance and time domain variance. The dynamic time warping (DTW) algorithm is a sequence alignment algorithm that can be used to align two or more series to facilitate quantifying similarity. In this article, we evaluated the performance of DTW distance-based similarity classifiers for classifying time series that mimics electrical signals produced by nanotube biosensors. Simulation studies demonstrated the positive performance of such classifiers in discriminating between time series containing characteristic features that are obscured by noise in the intensity and time domains. We then applied a DTW distance-based k -nearest neighbors classifier to distinguish the presence/absence of mesenchymal biomarker in cancer cells in buffy coats in a blinded test. Using a train-test approach, we find that the classifier had high sensitivity (90.9%) and specificity (81.8%) in differentiating between EpCAM-positive MCF7 cells spiked in buffy coats and those in plain buffy coats.

voomDDA: discovery of diagnostic biomarkers and classification of RNA-seq data.

PubMed

Zararsiz, Gokmen; Goksuluk, Dincer; Klaus, Bernd; Korkmaz, Selcuk; Eldem, Vahap; Karabulut, Erdem; Ozturk, Ahmet

2017-01-01

RNA-Seq is a recent and efficient technique that uses the capabilities of next-generation sequencing technology for characterizing and quantifying transcriptomes. One important task using gene-expression data is to identify a small subset of genes that can be used to build diagnostic classifiers particularly for cancer diseases. Microarray based classifiers are not directly applicable to RNA-Seq data due to its discrete nature. Overdispersion is another problem that requires careful modeling of mean and variance relationship of the RNA-Seq data. In this study, we present voomDDA classifiers: variance modeling at the observational level (voom) extensions of the nearest shrunken centroids (NSC) and the diagonal discriminant classifiers. VoomNSC is one of these classifiers and brings voom and NSC approaches together for the purpose of gene-expression based classification. For this purpose, we propose weighted statistics and put these weighted statistics into the NSC algorithm. The VoomNSC is a sparse classifier that models the mean-variance relationship using the voom method and incorporates voom's precision weights into the NSC classifier via weighted statistics. A comprehensive simulation study was designed and four real datasets are used for performance assessment. The overall results indicate that voomNSC performs as the sparsest classifier. It also provides the most accurate results together with power-transformed Poisson linear discriminant analysis, rlog transformed support vector machines and random forests algorithms. In addition to prediction purposes, the voomNSC classifier can be used to identify the potential diagnostic biomarkers for a condition of interest. Through this work, statistical learning methods proposed for microarrays can be reused for RNA-Seq data. An interactive web application is freely available at http://www.biosoft.hacettepe.edu.tr/voomDDA/.

Classifying threats with a 14-MeV neutron interrogation system.

PubMed

Strellis, Dan; Gozani, Tsahi

2005-01-01

SeaPODDS (Sea Portable Drug Detection System) is a non-intrusive tool for detecting concealed threats in hidden compartments of maritime vessels. This system consists of an electronic neutron generator, a gamma-ray detector, a data acquisition computer, and a laptop computer user-interface. Although initially developed to detect narcotics, recent algorithm developments have shown that the system is capable of correctly classifying a threat into one of four distinct categories: narcotic, explosive, chemical weapon, or radiological dispersion device (RDD). Detection of narcotics, explosives, and chemical weapons is based on gamma-ray signatures unique to the chemical elements. Elements are identified by their characteristic prompt gamma-rays induced by fast and thermal neutrons. Detection of RDD is accomplished by detecting gamma-rays emitted by common radioisotopes and nuclear reactor fission products. The algorithm phenomenology for classifying threats into the proper categories is presented here.

Global Optimization Ensemble Model for Classification Methods

PubMed Central

Anwar, Hina; Qamar, Usman; Muzaffar Qureshi, Abdul Wahab

2014-01-01

Supervised learning is the process of data mining for deducing rules from training datasets. A broad array of supervised learning algorithms exists, every one of them with its own advantages and drawbacks. There are some basic issues that affect the accuracy of classifier while solving a supervised learning problem, like bias-variance tradeoff, dimensionality of input space, and noise in the input data space. All these problems affect the accuracy of classifier and are the reason that there is no global optimal method for classification. There is not any generalized improvement method that can increase the accuracy of any classifier while addressing all the problems stated above. This paper proposes a global optimization ensemble model for classification methods (GMC) that can improve the overall accuracy for supervised learning problems. The experimental results on various public datasets showed that the proposed model improved the accuracy of the classification models from 1% to 30% depending upon the algorithm complexity. PMID:24883382

Textual and shape-based feature extraction and neuro-fuzzy classifier for nuclear track recognition

NASA Astrophysics Data System (ADS)

Khayat, Omid; Afarideh, Hossein

2013-04-01

Track counting algorithms as one of the fundamental principles of nuclear science have been emphasized in the recent years. Accurate measurement of nuclear tracks on solid-state nuclear track detectors is the aim of track counting systems. Commonly track counting systems comprise a hardware system for the task of imaging and software for analysing the track images. In this paper, a track recognition algorithm based on 12 defined textual and shape-based features and a neuro-fuzzy classifier is proposed. Features are defined so as to discern the tracks from the background and small objects. Then, according to the defined features, tracks are detected using a trained neuro-fuzzy system. Features and the classifier are finally validated via 100 Alpha track images and 40 training samples. It is shown that principle textual and shape-based features concomitantly yield a high rate of track detection compared with the single-feature based methods.

Deep Convolutional Neural Networks for Classifying Body Constitution Based on Face Image.

PubMed

Huan, Er-Yang; Wen, Gui-Hua; Zhang, Shi-Jun; Li, Dan-Yang; Hu, Yang; Chang, Tian-Yuan; Wang, Qing; Huang, Bing-Lin

2017-01-01

Body constitution classification is the basis and core content of traditional Chinese medicine constitution research. It is to extract the relevant laws from the complex constitution phenomenon and finally build the constitution classification system. Traditional identification methods have the disadvantages of inefficiency and low accuracy, for instance, questionnaires. This paper proposed a body constitution recognition algorithm based on deep convolutional neural network, which can classify individual constitution types according to face images. The proposed model first uses the convolutional neural network to extract the features of face image and then combines the extracted features with the color features. Finally, the fusion features are input to the Softmax classifier to get the classification result. Different comparison experiments show that the algorithm proposed in this paper can achieve the accuracy of 65.29% about the constitution classification. And its performance was accepted by Chinese medicine practitioners.

ECG Based Heart Arrhythmia Detection Using Wavelet Coherence and Bat Algorithm

NASA Astrophysics Data System (ADS)

Kora, Padmavathi; Sri Rama Krishna, K.

2016-12-01

Atrial fibrillation (AF) is a type of heart abnormality, during the AF electrical discharges in the atrium are rapid, results in abnormal heart beat. The morphology of ECG changes due to the abnormalities in the heart. This paper consists of three major steps for the detection of heart diseases: signal pre-processing, feature extraction and classification. Feature extraction is the key process in detecting the heart abnormality. Most of the ECG detection systems depend on the time domain features for cardiac signal classification. In this paper we proposed a wavelet coherence (WTC) technique for ECG signal analysis. The WTC calculates the similarity between two waveforms in frequency domain. Parameters extracted from WTC function is used as the features of the ECG signal. These features are optimized using Bat algorithm. The Levenberg Marquardt neural network classifier is used to classify the optimized features. The performance of the classifier can be improved with the optimized features.

Self-similarity Clustering Event Detection Based on Triggers Guidance

NASA Astrophysics Data System (ADS)

Zhang, Xianfei; Li, Bicheng; Tian, Yuxuan

Traditional method of Event Detection and Characterization (EDC) regards event detection task as classification problem. It makes words as samples to train classifier, which can lead to positive and negative samples of classifier imbalance. Meanwhile, there is data sparseness problem of this method when the corpus is small. This paper doesn't classify event using word as samples, but cluster event in judging event types. It adopts self-similarity to convergence the value of K in K-means algorithm by the guidance of event triggers, and optimizes clustering algorithm. Then, combining with named entity and its comparative position information, the new method further make sure the pinpoint type of event. The new method avoids depending on template of event in tradition methods, and its result of event detection can well be used in automatic text summarization, text retrieval, and topic detection and tracking.

Foliage discrimination using a rotating ladar

NASA Technical Reports Server (NTRS)

Castano, A.; Matthies, L.

2003-01-01

We present a real time algorithm that detects foliage using range from a rotating laser. Objects not classified as foliage are conservatively labeled as non-driving obstacles. In contrast to related work that uses range statistics to classify objects, we exploit the expected localities and continuities of an obstacle, in both space and time. Also, instead of attempting to find a single accurate discriminating factor for every ladar return, we hypothesize the class of some few returns and then spread the confidence (and classification) to other returns using the locality constraints. The Urbie robot is presently using this algorithm to descriminate drivable grass from obstacles during outdoor autonomous navigation tasks.

A Genetic Algorithm for Learning Significant Phrase Patterns in Radiology Reports

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

Patton, Robert M; Potok, Thomas E; Beckerman, Barbara G

2009-01-01

Radiologists disagree with each other over the characteristics and features of what constitutes a normal mammogram and the terminology to use in the associated radiology report. Recently, the focus has been on classifying abnormal or suspicious reports, but even this process needs further layers of clustering and gradation, so that individual lesions can be more effectively classified. Using a genetic algorithm, the approach described here successfully learns phrase patterns for two distinct classes of radiology reports (normal and abnormal). These patterns can then be used as a basis for automatically analyzing, categorizing, clustering, or retrieving relevant radiology reports for themore » user.« less

Constructing better classifier ensemble based on weighted accuracy and diversity measure.

PubMed

Zeng, Xiaodong; Wong, Derek F; Chao, Lidia S

2014-01-01

A weighted accuracy and diversity (WAD) method is presented, a novel measure used to evaluate the quality of the classifier ensemble, assisting in the ensemble selection task. The proposed measure is motivated by a commonly accepted hypothesis; that is, a robust classifier ensemble should not only be accurate but also different from every other member. In fact, accuracy and diversity are mutual restraint factors; that is, an ensemble with high accuracy may have low diversity, and an overly diverse ensemble may negatively affect accuracy. This study proposes a method to find the balance between accuracy and diversity that enhances the predictive ability of an ensemble for unknown data. The quality assessment for an ensemble is performed such that the final score is achieved by computing the harmonic mean of accuracy and diversity, where two weight parameters are used to balance them. The measure is compared to two representative measures, Kappa-Error and GenDiv, and two threshold measures that consider only accuracy or diversity, with two heuristic search algorithms, genetic algorithm, and forward hill-climbing algorithm, in ensemble selection tasks performed on 15 UCI benchmark datasets. The empirical results demonstrate that the WAD measure is superior to others in most cases.

Learning accurate very fast decision trees from uncertain data streams

NASA Astrophysics Data System (ADS)

Liang, Chunquan; Zhang, Yang; Shi, Peng; Hu, Zhengguo

2015-12-01

Most existing works on data stream classification assume the streaming data is precise and definite. Such assumption, however, does not always hold in practice, since data uncertainty is ubiquitous in data stream applications due to imprecise measurement, missing values, privacy protection, etc. The goal of this paper is to learn accurate decision tree models from uncertain data streams for classification analysis. On the basis of very fast decision tree (VFDT) algorithms, we proposed an algorithm for constructing an uncertain VFDT tree with classifiers at tree leaves (uVFDTc). The uVFDTc algorithm can exploit uncertain information effectively and efficiently in both the learning and the classification phases. In the learning phase, it uses Hoeffding bound theory to learn from uncertain data streams and yield fast and reasonable decision trees. In the classification phase, at tree leaves it uses uncertain naive Bayes (UNB) classifiers to improve the classification performance. Experimental results on both synthetic and real-life datasets demonstrate the strong ability of uVFDTc to classify uncertain data streams. The use of UNB at tree leaves has improved the performance of uVFDTc, especially the any-time property, the benefit of exploiting uncertain information, and the robustness against uncertainty.

Building Change Detection from Bi-Temporal Dense-Matching Point Clouds and Aerial Images.

PubMed

Pang, Shiyan; Hu, Xiangyun; Cai, Zhongliang; Gong, Jinqi; Zhang, Mi

2018-03-24

In this work, a novel building change detection method from bi-temporal dense-matching point clouds and aerial images is proposed to address two major problems, namely, the robust acquisition of the changed objects above ground and the automatic classification of changed objects into buildings or non-buildings. For the acquisition of changed objects above ground, the change detection problem is converted into a binary classification, in which the changed area above ground is regarded as the foreground and the other area as the background. For the gridded points of each period, the graph cuts algorithm is adopted to classify the points into foreground and background, followed by the region-growing algorithm to form candidate changed building objects. A novel structural feature that was extracted from aerial images is constructed to classify the candidate changed building objects into buildings and non-buildings. The changed building objects are further classified as "newly built", "taller", "demolished", and "lower" by combining the classification and the digital surface models of two periods. Finally, three typical areas from a large dataset are used to validate the proposed method. Numerous experiments demonstrate the effectiveness of the proposed algorithm.

Constructing Better Classifier Ensemble Based on Weighted Accuracy and Diversity Measure

PubMed Central

Chao, Lidia S.

2014-01-01

A weighted accuracy and diversity (WAD) method is presented, a novel measure used to evaluate the quality of the classifier ensemble, assisting in the ensemble selection task. The proposed measure is motivated by a commonly accepted hypothesis; that is, a robust classifier ensemble should not only be accurate but also different from every other member. In fact, accuracy and diversity are mutual restraint factors; that is, an ensemble with high accuracy may have low diversity, and an overly diverse ensemble may negatively affect accuracy. This study proposes a method to find the balance between accuracy and diversity that enhances the predictive ability of an ensemble for unknown data. The quality assessment for an ensemble is performed such that the final score is achieved by computing the harmonic mean of accuracy and diversity, where two weight parameters are used to balance them. The measure is compared to two representative measures, Kappa-Error and GenDiv, and two threshold measures that consider only accuracy or diversity, with two heuristic search algorithms, genetic algorithm, and forward hill-climbing algorithm, in ensemble selection tasks performed on 15 UCI benchmark datasets. The empirical results demonstrate that the WAD measure is superior to others in most cases. PMID:24672402

Joint Sparse Recovery With Semisupervised MUSIC

NASA Astrophysics Data System (ADS)

Wen, Zaidao; Hou, Biao; Jiao, Licheng

2017-05-01

Discrete multiple signal classification (MUSIC) with its low computational cost and mild condition requirement becomes a significant noniterative algorithm for joint sparse recovery (JSR). However, it fails in rank defective problem caused by coherent or limited amount of multiple measurement vectors (MMVs). In this letter, we provide a novel sight to address this problem by interpreting JSR as a binary classification problem with respect to atoms. Meanwhile, MUSIC essentially constructs a supervised classifier based on the labeled MMVs so that its performance will heavily depend on the quality and quantity of these training samples. From this viewpoint, we develop a semisupervised MUSIC (SS-MUSIC) in the spirit of machine learning, which declares that the insufficient supervised information in the training samples can be compensated from those unlabeled atoms. Instead of constructing a classifier in a fully supervised manner, we iteratively refine a semisupervised classifier by exploiting the labeled MMVs and some reliable unlabeled atoms simultaneously. Through this way, the required conditions and iterations can be greatly relaxed and reduced. Numerical experimental results demonstrate that SS-MUSIC can achieve much better recovery performances than other MUSIC extended algorithms as well as some typical greedy algorithms for JSR in terms of iterations and recovery probability.

DNABIT Compress – Genome compression algorithm

PubMed Central

Rajarajeswari, Pothuraju; Apparao, Allam

2011-01-01

Data compression is concerned with how information is organized in data. Efficient storage means removal of redundancy from the data being stored in the DNA molecule. Data compression algorithms remove redundancy and are used to understand biologically important molecules. We present a compression algorithm, “DNABIT Compress” for DNA sequences based on a novel algorithm of assigning binary bits for smaller segments of DNA bases to compress both repetitive and non repetitive DNA sequence. Our proposed algorithm achieves the best compression ratio for DNA sequences for larger genome. Significantly better compression results show that “DNABIT Compress” algorithm is the best among the remaining compression algorithms. While achieving the best compression ratios for DNA sequences (Genomes),our new DNABIT Compress algorithm significantly improves the running time of all previous DNA compression programs. Assigning binary bits (Unique BIT CODE) for (Exact Repeats, Reverse Repeats) fragments of DNA sequence is also a unique concept introduced in this algorithm for the first time in DNA compression. This proposed new algorithm could achieve the best compression ratio as much as 1.58 bits/bases where the existing best methods could not achieve a ratio less than 1.72 bits/bases. PMID:21383923

Automatic determination of the artery vein ratio in retinal images

NASA Astrophysics Data System (ADS)

Niemeijer, Meindert; van Ginneken, Bram; Abràmoff, Michael D.

2010-03-01

A lower ratio between the width of the arteries and veins (Arteriolar-to-Venular diameter Ratio, AVR) on the retina, is well established to be predictive of stroke and other cardiovascular events in adults, as well as an increased risk of retinopathy of prematurity in premature infants. This work presents an automatic method that detects the location of the optic disc, determines the appropriate region of interest (ROI), classifies the vessels in the ROI into arteries and veins, measures their widths and calculates the AVR. After vessel segmentation and vessel width determination the optic disc is located and the system eliminates all vessels outside the AVR measurement ROI. The remaining vessels are thinned, vessel crossing and bifurcation points are removed leaving a set of vessel segments containing centerline pixels. Features are extracted from each centerline pixel that are used to assign them a soft label indicating the likelihood the pixel is part of a vein. As all centerline pixels in a connected segment should be the same type, the median soft label is assigned to each centerline pixel in the segment. Next artery vein pairs are matched using an iterative algorithm and the widths of the vessels is used to calculate the AVR. We train and test the algorithm using a set of 25 high resolution digital color fundus photographs a reference standard that indicates for the major vessels in the images whether they are an artery or a vein. We compared the AVR values produced by our system with those determined using a computer assisted method in 15 high resolution digital color fundus photographs and obtained a correlation coefficient of 0.881.

Automatic threshold selection for multi-class open set recognition

NASA Astrophysics Data System (ADS)

Scherreik, Matthew; Rigling, Brian

2017-05-01

Multi-class open set recognition is the problem of supervised classification with additional unknown classes encountered after a model has been trained. An open set classifer often has two core components. The first component is a base classifier which estimates the most likely class of a given example. The second component consists of open set logic which estimates if the example is truly a member of the candidate class. Such a system is operated in a feed-forward fashion. That is, a candidate label is first estimated by the base classifier, and the true membership of the example to the candidate class is estimated afterward. Previous works have developed an iterative threshold selection algorithm for rejecting examples from classes which were not present at training time. In those studies, a Platt-calibrated SVM was used as the base classifier, and the thresholds were applied to class posterior probabilities for rejection. In this work, we investigate the effectiveness of other base classifiers when paired with the threshold selection algorithm and compare their performance with the original SVM solution.

Developing a radiomics framework for classifying non-small cell lung carcinoma subtypes

NASA Astrophysics Data System (ADS)

Yu, Dongdong; Zang, Yali; Dong, Di; Zhou, Mu; Gevaert, Olivier; Fang, Mengjie; Shi, Jingyun; Tian, Jie

2017-03-01

Patient-targeted treatment of non-small cell lung carcinoma (NSCLC) has been well documented according to the histologic subtypes over the past decade. In parallel, recent development of quantitative image biomarkers has recently been highlighted as important diagnostic tools to facilitate histological subtype classification. In this study, we present a radiomics analysis that classifies the adenocarcinoma (ADC) and squamous cell carcinoma (SqCC). We extract 52-dimensional, CT-based features (7 statistical features and 45 image texture features) to represent each nodule. We evaluate our approach on a clinical dataset including 324 ADCs and 110 SqCCs patients with CT image scans. Classification of these features is performed with four different machine-learning classifiers including Support Vector Machines with Radial Basis Function kernel (RBF-SVM), Random forest (RF), K-nearest neighbor (KNN), and RUSBoost algorithms. To improve the classifiers' performance, optimal feature subset is selected from the original feature set by using an iterative forward inclusion and backward eliminating algorithm. Extensive experimental results demonstrate that radiomics features achieve encouraging classification results on both complete feature set (AUC=0.89) and optimal feature subset (AUC=0.91).

An ensemble of SVM classifiers based on gene pairs.

PubMed

Tong, Muchenxuan; Liu, Kun-Hong; Xu, Chungui; Ju, Wenbin

2013-07-01

In this paper, a genetic algorithm (GA) based ensemble support vector machine (SVM) classifier built on gene pairs (GA-ESP) is proposed. The SVMs (base classifiers of the ensemble system) are trained on different informative gene pairs. These gene pairs are selected by the top scoring pair (TSP) criterion. Each of these pairs projects the original microarray expression onto a 2-D space. Extensive permutation of gene pairs may reveal more useful information and potentially lead to an ensemble classifier with satisfactory accuracy and interpretability. GA is further applied to select an optimized combination of base classifiers. The effectiveness of the GA-ESP classifier is evaluated on both binary-class and multi-class datasets. Copyright © 2013 Elsevier Ltd. All rights reserved.

A decision support system using combined-classifier for high-speed data stream in smart grid

NASA Astrophysics Data System (ADS)

Yang, Hang; Li, Peng; He, Zhian; Guo, Xiaobin; Fong, Simon; Chen, Huajun

2016-11-01

Large volume of high-speed streaming data is generated by big power grids continuously. In order to detect and avoid power grid failure, decision support systems (DSSs) are commonly adopted in power grid enterprises. Among all the decision-making algorithms, incremental decision tree is the most widely used one. In this paper, we propose a combined classifier that is a composite of a cache-based classifier (CBC) and a main tree classifier (MTC). We integrate this classifier into a stream processing engine on top of the DSS such that high-speed steaming data can be transformed into operational intelligence efficiently. Experimental results show that our proposed classifier can return more accurate answers than other existing ones.

Using Chou's pseudo amino acid composition based on approximate entropy and an ensemble of AdaBoost classifiers to predict protein subnuclear location.

PubMed

Jiang, Xiaoying; Wei, Rong; Zhao, Yanjun; Zhang, Tongliang

2008-05-01

The knowledge of subnuclear localization in eukaryotic cells is essential for understanding the life function of nucleus. Developing prediction methods and tools for proteins subnuclear localization become important research fields in protein science for special characteristics in cell nuclear. In this study, a novel approach has been proposed to predict protein subnuclear localization. Sample of protein is represented by Pseudo Amino Acid (PseAA) composition based on approximate entropy (ApEn) concept, which reflects the complexity of time series. A novel ensemble classifier is designed incorporating three AdaBoost classifiers. The base classifier algorithms in three AdaBoost are decision stumps, fuzzy K nearest neighbors classifier, and radial basis-support vector machines, respectively. Different PseAA compositions are used as input data of different AdaBoost classifier in ensemble. Genetic algorithm is used to optimize the dimension and weight factor of PseAA composition. Two datasets often used in published works are used to validate the performance of the proposed approach. The obtained results of Jackknife cross-validation test are higher and more balance than them of other methods on same datasets. The promising results indicate that the proposed approach is effective and practical. It might become a useful tool in protein subnuclear localization. The software in Matlab and supplementary materials are available freely by contacting the corresponding author.

Recognition of acute lymphoblastic leukemia cells in microscopic images using k-means clustering and support vector machine classifier.

PubMed

Amin, Morteza Moradi; Kermani, Saeed; Talebi, Ardeshir; Oghli, Mostafa Ghelich

2015-01-01

Acute lymphoblastic leukemia is the most common form of pediatric cancer which is categorized into three L1, L2, and L3 and could be detected through screening of blood and bone marrow smears by pathologists. Due to being time-consuming and tediousness of the procedure, a computer-based system is acquired for convenient detection of Acute lymphoblastic leukemia. Microscopic images are acquired from blood and bone marrow smears of patients with Acute lymphoblastic leukemia and normal cases. After applying image preprocessing, cells nuclei are segmented by k-means algorithm. Then geometric and statistical features are extracted from nuclei and finally these cells are classified to cancerous and noncancerous cells by means of support vector machine classifier with 10-fold cross validation. These cells are also classified into their sub-types by multi-Support vector machine classifier. Classifier is evaluated by these parameters: Sensitivity, specificity, and accuracy which values for cancerous and noncancerous cells 98%, 95%, and 97%, respectively. These parameters are also used for evaluation of cell sub-types which values in mean 84.3%, 97.3%, and 95.6%, respectively. The results show that proposed algorithm could achieve an acceptable performance for the diagnosis of Acute lymphoblastic leukemia and its sub-types and can be used as an assistant diagnostic tool for pathologists.

Classification of pollen species using autofluorescence image analysis.

PubMed

Mitsumoto, Kotaro; Yabusaki, Katsumi; Aoyagi, Hideki

2009-01-01

A new method to classify pollen species was developed by monitoring autofluorescence images of pollen grains. The pollens of nine species were selected, and their autofluorescence images were captured by a microscope equipped with a digital camera. The pollen size and the ratio of the blue to red pollen autofluorescence spectra (the B/R ratio) were calculated by image processing. The B/R ratios and pollen size varied among the species. Furthermore, the scatter-plot of pollen size versus the B/R ratio showed that pollen could be classified to the species level using both parameters. The pollen size and B/R ratio were confirmed by means of particle flow image analysis and the fluorescence spectra, respectively. These results suggest that a flow system capable of measuring both scattered light and the autofluorescence of particles could classify and count pollen grains in real time.

Automatic Classification Using Supervised Learning in a Medical Document Filtering Application.

ERIC Educational Resources Information Center

Mostafa, J.; Lam, W.

2000-01-01

Presents a multilevel model of the information filtering process that permits document classification. Evaluates a document classification approach based on a supervised learning algorithm, measures the accuracy of the algorithm in a neural network that was trained to classify medical documents on cell biology, and discusses filtering…

Classification of natural formations based on their optical characteristics using small volumes of samples

NASA Astrophysics Data System (ADS)

Abramovich, N. S.; Kovalev, A. A.; Plyuta, V. Y.

1986-02-01

A computer algorithm has been developed to classify the spectral bands of natural scenes on Earth according to their optical characteristics. The algorithm is written in FORTRAN-IV and can be used in spectral data processing programs requiring small data loads. The spectral classifications of some different types of green vegetable canopies are given in order to illustrate the effectiveness of the algorithm.

Heart rate variability (HRV): an indicator of stress

NASA Astrophysics Data System (ADS)

Kaur, Balvinder; Durek, Joseph J.; O'Kane, Barbara L.; Tran, Nhien; Moses, Sophia; Luthra, Megha; Ikonomidou, Vasiliki N.

2014-05-01

Heart rate variability (HRV) can be an important indicator of several conditions that affect the autonomic nervous system, including traumatic brain injury, post-traumatic stress disorder and peripheral neuropathy [3], [4], [10] & [11]. Recent work has shown that some of the HRV features can potentially be used for distinguishing a subject's normal mental state from a stressed one [4], [13] & [14]. In all of these past works, although processing is done in both frequency and time domains, few classification algorithms have been explored for classifying normal from stressed RRintervals. In this paper we used 30 s intervals from the Electrocardiogram (ECG) time series collected during normal and stressed conditions, produced by means of a modified version of the Trier social stress test, to compute HRV-driven features and subsequently applied a set of classification algorithms to distinguish stressed from normal conditions. To classify RR-intervals, we explored classification algorithms that are commonly used for medical applications, namely 1) logistic regression (LR) [16] and 2) linear discriminant analysis (LDA) [6]. Classification performance for various levels of stress over the entire test was quantified using precision, accuracy, sensitivity and specificity measures. Results from both classifiers were then compared to find an optimal classifier and HRV features for stress detection. This work, performed under an IRB-approved protocol, not only provides a method for developing models and classifiers based on human data, but also provides a foundation for a stress indicator tool based on HRV. Further, these classification tools will not only benefit many civilian applications for detecting stress, but also security and military applications for screening such as: border patrol, stress detection for deception [3],[17], and wounded-warrior triage [12].

Implementation of spectral clustering on microarray data of carcinoma using k-means algorithm

NASA Astrophysics Data System (ADS)

Frisca, Bustamam, Alhadi; Siswantining, Titin

2017-03-01

Clustering is one of data analysis methods that aims to classify data which have similar characteristics in the same group. Spectral clustering is one of the most popular modern clustering algorithms. As an effective clustering technique, spectral clustering method emerged from the concepts of spectral graph theory. Spectral clustering method needs partitioning algorithm. There are some partitioning methods including PAM, SOM, Fuzzy c-means, and k-means. Based on the research that has been done by Capital and Choudhury in 2013, when using Euclidian distance k-means algorithm provide better accuracy than PAM algorithm. So in this paper we use k-means as our partition algorithm. The major advantage of spectral clustering is in reducing data dimension, especially in this case to reduce the dimension of large microarray dataset. Microarray data is a small-sized chip made of a glass plate containing thousands and even tens of thousands kinds of genes in the DNA fragments derived from doubling cDNA. Application of microarray data is widely used to detect cancer, for the example is carcinoma, in which cancer cells express the abnormalities in his genes. The purpose of this research is to classify the data that have high similarity in the same group and the data that have low similarity in the others. In this research, Carcinoma microarray data using 7457 genes. The result of partitioning using k-means algorithm is two clusters.

Application of fuzzy C-Means Algorithm for Determining Field of Interest in Information System Study STTH Medan

NASA Astrophysics Data System (ADS)

Rahman Syahputra, Edy; Agustina Dalimunthe, Yulia; Irvan

2017-12-01

Many students are confused in choosing their own field of specialization, ultimately choosing areas of specialization that are incompatible with a variety of reasons such as just following a friend or because of the area of interest of many choices without knowing whether they have Competencies in the chosen field of interest. This research aims to apply Clustering method with Fuzzy C-means algorithm to classify students in the chosen interest field. The Fuzzy C-Means algorithm is one of the easiest and often used algorithms in data grouping techniques because it makes efficient estimates and does not require many parameters. Several studies have led to the conclusion that the Fuzzy C-Means algorithm can be used to group data based on certain attributes. In this research will be used Fuzzy C-Means algorithm to classify student data based on the value of core subjects in the selection of specialization field. This study also tested the accuracy of the Fuzzy C-Means algorithm in the determination of interest area. The study was conducted on the STT-Harapan Medan Information System Study program, and the object of research is the value of all students of STT-Harapan Medan Information System Study Program 2012. From this research, it is expected to get the specialization field, according to the students' ability based on the prerequisite principal value.

A new strategy for snow-cover mapping using remote sensing data and ensemble based systems techniques

NASA Astrophysics Data System (ADS)

Roberge, S.; Chokmani, K.; De Sève, D.

2012-04-01

The snow cover plays an important role in the hydrological cycle of Quebec (Eastern Canada). Consequently, evaluating its spatial extent interests the authorities responsible for the management of water resources, especially hydropower companies. The main objective of this study is the development of a snow-cover mapping strategy using remote sensing data and ensemble based systems techniques. Planned to be tested in a near real-time operational mode, this snow-cover mapping strategy has the advantage to provide the probability of a pixel to be snow covered and its uncertainty. Ensemble systems are made of two key components. First, a method is needed to build an ensemble of classifiers that is diverse as much as possible. Second, an approach is required to combine the outputs of individual classifiers that make up the ensemble in such a way that correct decisions are amplified, and incorrect ones are cancelled out. In this study, we demonstrate the potential of ensemble systems to snow-cover mapping using remote sensing data. The chosen classifier is a sequential thresholds algorithm using NOAA-AVHRR data adapted to conditions over Eastern Canada. Its special feature is the use of a combination of six sequential thresholds varying according to the day in the winter season. Two versions of the snow-cover mapping algorithm have been developed: one is specific for autumn (from October 1st to December 31st) and the other for spring (from March 16th to May 31st). In order to build the ensemble based system, different versions of the algorithm are created by varying randomly its parameters. One hundred of the versions are included in the ensemble. The probability of a pixel to be snow, no-snow or cloud covered corresponds to the amount of votes the pixel has been classified as such by all classifiers. The overall performance of ensemble based mapping is compared to the overall performance of the chosen classifier, and also with ground observations at meteorological stations.

AVNM: A Voting based Novel Mathematical Rule for Image Classification.

PubMed

Vidyarthi, Ankit; Mittal, Namita

2016-12-01

In machine learning, the accuracy of the system depends upon classification result. Classification accuracy plays an imperative role in various domains. Non-parametric classifier like K-Nearest Neighbor (KNN) is the most widely used classifier for pattern analysis. Besides its easiness, simplicity and effectiveness characteristics, the main problem associated with KNN classifier is the selection of a number of nearest neighbors i.e. "k" for computation. At present, it is hard to find the optimal value of "k" using any statistical algorithm, which gives perfect accuracy in terms of low misclassification error rate. Motivated by the prescribed problem, a new sample space reduction weighted voting mathematical rule (AVNM) is proposed for classification in machine learning. The proposed AVNM rule is also non-parametric in nature like KNN. AVNM uses the weighted voting mechanism with sample space reduction to learn and examine the predicted class label for unidentified sample. AVNM is free from any initial selection of predefined variable and neighbor selection as found in KNN algorithm. The proposed classifier also reduces the effect of outliers. To verify the performance of the proposed AVNM classifier, experiments are made on 10 standard datasets taken from UCI database and one manually created dataset. The experimental result shows that the proposed AVNM rule outperforms the KNN classifier and its variants. Experimentation results based on confusion matrix accuracy parameter proves higher accuracy value with AVNM rule. The proposed AVNM rule is based on sample space reduction mechanism for identification of an optimal number of nearest neighbor selections. AVNM results in better classification accuracy and minimum error rate as compared with the state-of-art algorithm, KNN, and its variants. The proposed rule automates the selection of nearest neighbor selection and improves classification rate for UCI dataset and manually created dataset. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Detailed Quantitative Classifications of Galaxy Morphology

NASA Astrophysics Data System (ADS)

Nair, Preethi

2018-01-01

Understanding the physical processes responsible for the growth of galaxies is one of the key challenges in extragalactic astronomy. The assembly history of a galaxy is imprinted in a galaxy’s detailed morphology. The bulge-to-total ratio of galaxies, the presence or absence of bars, rings, spiral arms, tidal tails etc, all have implications for the past merger, star formation, and feedback history of a galaxy. However, current quantitative galaxy classification schemes are only useful for broad binning. They cannot classify or exploit the wide variety of galaxy structures seen in nature. Therefore, comparisons of observations with theoretical predictions of secular structure formation have only been conducted on small samples of visually classified galaxies. However large samples are needed to disentangle the complex physical processes of galaxy formation. With the advent of large surveys, like the Sloan Digital Sky Survey (SDSS) and the upcoming Large Synoptic Survey Telescope (LSST) and WFIRST, the problem of statistics will be resolved. However, the need for a robust quantitative classification scheme will still remain. Here I will present early results on promising machine learning algorithms that are providing detailed classifications, identifying bars, rings, multi-armed spiral galaxies, and Hubble type.

Accelerometry-based gait analysis, an additional objective approach to screen subjects at risk for falling.

PubMed

Senden, R; Savelberg, H H C M; Grimm, B; Heyligers, I C; Meijer, K

2012-06-01

This study investigated whether the Tinetti scale, as a subjective measure for fall risk, is associated with objectively measured gait characteristics. It is studied whether gait parameters are different for groups that are stratified for fall risk using the Tinetti scale. Moreover, the discriminative power of gait parameters to classify elderly according to the Tinetti scale is investigated. Gait of 50 elderly with a Tinneti>24 and 50 elderly with a Tinetti≤24 was analyzed using acceleration-based gait analysis. Validated algorithms were used to derive spatio-temporal gait parameters, harmonic ratio, inter-stride amplitude variability and root mean square (RMS) from the accelerometer data. Clear differences in gait were found between the groups. All gait parameters correlated with the Tinetti scale (r-range: 0.20-0.73). Only walking speed, step length and RMS showed moderate to strong correlations and high discriminative power to classify elderly according to the Tinetti scale. It is concluded that subtle gait changes that have previously been related to fall risk are not captured by the subjective assessment. It is therefore worthwhile to include objective gait assessment in fall risk screening. Copyright © 2012 Elsevier B.V. All rights reserved.

Bilayer segmentation of webcam videos using tree-based classifiers.

PubMed

Yin, Pei; Criminisi, Antonio; Winn, John; Essa, Irfan

2011-01-01

This paper presents an automatic segmentation algorithm for video frames captured by a (monocular) webcam that closely approximates depth segmentation from a stereo camera. The frames are segmented into foreground and background layers that comprise a subject (participant) and other objects and individuals. The algorithm produces correct segmentations even in the presence of large background motion with a nearly stationary foreground. This research makes three key contributions: First, we introduce a novel motion representation, referred to as "motons," inspired by research in object recognition. Second, we propose estimating the segmentation likelihood from the spatial context of motion. The estimation is efficiently learned by random forests. Third, we introduce a general taxonomy of tree-based classifiers that facilitates both theoretical and experimental comparisons of several known classification algorithms and generates new ones. In our bilayer segmentation algorithm, diverse visual cues such as motion, motion context, color, contrast, and spatial priors are fused by means of a conditional random field (CRF) model. Segmentation is then achieved by binary min-cut. Experiments on many sequences of our videochat application demonstrate that our algorithm, which requires no initialization, is effective in a variety of scenes, and the segmentation results are comparable to those obtained by stereo systems.

Using human brain activity to guide machine learning.

PubMed

Fong, Ruth C; Scheirer, Walter J; Cox, David D

2018-03-29

Machine learning is a field of computer science that builds algorithms that learn. In many cases, machine learning algorithms are used to recreate a human ability like adding a caption to a photo, driving a car, or playing a game. While the human brain has long served as a source of inspiration for machine learning, little effort has been made to directly use data collected from working brains as a guide for machine learning algorithms. Here we demonstrate a new paradigm of "neurally-weighted" machine learning, which takes fMRI measurements of human brain activity from subjects viewing images, and infuses these data into the training process of an object recognition learning algorithm to make it more consistent with the human brain. After training, these neurally-weighted classifiers are able to classify images without requiring any additional neural data. We show that our neural-weighting approach can lead to large performance gains when used with traditional machine vision features, as well as to significant improvements with already high-performing convolutional neural network features. The effectiveness of this approach points to a path forward for a new class of hybrid machine learning algorithms which take both inspiration and direct constraints from neuronal data.

Quantifying Void Ratio in Granular Materials Using Voronoi Tessellation

NASA Technical Reports Server (NTRS)

Alshibli, Khalid A.; El-Saidany, Hany A.; Rose, M. Franklin (Technical Monitor)

2000-01-01

Voronoi technique was used to calculate the local void ratio distribution of granular materials. It was implemented in an application-oriented image processing and analysis algorithm capable of extracting object edges, separating adjacent particles, obtaining the centroid of each particle, generating Voronoi polygons, and calculating the local void ratio. Details of the algorithm capabilities and features are presented. Verification calculations included performing manual digitization of synthetic images using Oda's method and Voronoi polygon system. The developed algorithm yielded very accurate measurements of the local void ratio distribution. Voronoi tessellation has the advantage, compared to Oda's method, of offering a well-defined polygon generation criterion that can be implemented in an algorithm to automatically calculate local void ratio of particulate materials.

Online Adaboost-Based Parameterized Methods for Dynamic Distributed Network Intrusion Detection.

PubMed

Hu, Weiming; Gao, Jun; Wang, Yanguo; Wu, Ou; Maybank, Stephen

2014-01-01

Current network intrusion detection systems lack adaptability to the frequently changing network environments. Furthermore, intrusion detection in the new distributed architectures is now a major requirement. In this paper, we propose two online Adaboost-based intrusion detection algorithms. In the first algorithm, a traditional online Adaboost process is used where decision stumps are used as weak classifiers. In the second algorithm, an improved online Adaboost process is proposed, and online Gaussian mixture models (GMMs) are used as weak classifiers. We further propose a distributed intrusion detection framework, in which a local parameterized detection model is constructed in each node using the online Adaboost algorithm. A global detection model is constructed in each node by combining the local parametric models using a small number of samples in the node. This combination is achieved using an algorithm based on particle swarm optimization (PSO) and support vector machines. The global model in each node is used to detect intrusions. Experimental results show that the improved online Adaboost process with GMMs obtains a higher detection rate and a lower false alarm rate than the traditional online Adaboost process that uses decision stumps. Both the algorithms outperform existing intrusion detection algorithms. It is also shown that our PSO, and SVM-based algorithm effectively combines the local detection models into the global model in each node; the global model in a node can handle the intrusion types that are found in other nodes, without sharing the samples of these intrusion types.

Performance of Activity Classification Algorithms in Free-living Older Adults

PubMed Central

Sasaki, Jeffer Eidi; Hickey, Amanda; Staudenmayer, John; John, Dinesh; Kent, Jane A.; Freedson, Patty S.

2015-01-01

Purpose To compare activity type classification rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in older adults. Methods Thirty-five older adults (21F and 14M ; 70.8 ± 4.9 y) performed selected activities in the laboratory while wearing three ActiGraph GT3X+ activity monitors (dominant hip, wrist, and ankle). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants also wore the GT3X+ in free-living settings and were directly observed for 2-3 hours. Time- and frequency- domain features from acceleration signals of each monitor were used to train Random Forest (RF) and Support Vector Machine (SVM) models to classify five activity types: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on lab data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20 s signal sampling windows. Classification accuracy rates of both types of algorithms were tested on free-living data using a leave-one-out technique. Results Overall classification accuracy rates for the algorithms developed from lab data were between 49% (wrist) to 55% (ankle) for the SVMLab algorithms, and 49% (wrist) to 54% (ankle) for RFLab algorithms. The classification accuracy rates for SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 67% (ankle), respectively. Conclusion Our algorithms developed on free-living accelerometer data were more accurate in classifying activity type in free-living older adults than our algorithms developed on laboratory accelerometer data. Future studies should consider using free-living accelerometer data to train machine-learning algorithms in older adults. PMID:26673129

Performance of Activity Classification Algorithms in Free-Living Older Adults.

PubMed

Sasaki, Jeffer Eidi; Hickey, Amanda M; Staudenmayer, John W; John, Dinesh; Kent, Jane A; Freedson, Patty S

2016-05-01

The objective of this study is to compare activity type classification rates of machine learning algorithms trained on laboratory versus free-living accelerometer data in older adults. Thirty-five older adults (21 females and 14 males, 70.8 ± 4.9 yr) performed selected activities in the laboratory while wearing three ActiGraph GT3X+ activity monitors (in the dominant hip, wrist, and ankle; ActiGraph, LLC, Pensacola, FL). Monitors were initialized to collect raw acceleration data at a sampling rate of 80 Hz. Fifteen of the participants also wore GT3X+ in free-living settings and were directly observed for 2-3 h. Time- and frequency-domain features from acceleration signals of each monitor were used to train random forest (RF) and support vector machine (SVM) models to classify five activity types: sedentary, standing, household, locomotion, and recreational activities. All algorithms were trained on laboratory data (RFLab and SVMLab) and free-living data (RFFL and SVMFL) using 20-s signal sampling windows. Classification accuracy rates of both types of algorithms were tested on free-living data using a leave-one-out technique. Overall classification accuracy rates for the algorithms developed from laboratory data were between 49% (wrist) and 55% (ankle) for the SVMLab algorithms and 49% (wrist) to 54% (ankle) for the RFLab algorithms. The classification accuracy rates for SVMFL and RFFL algorithms ranged from 58% (wrist) to 69% (ankle) and from 61% (wrist) to 67% (ankle), respectively. Our algorithms developed on free-living accelerometer data were more accurate in classifying the activity type in free-living older adults than those on our algorithms developed on laboratory accelerometer data. Future studies should consider using free-living accelerometer data to train machine learning algorithms in older adults.

Data-driven advice for applying machine learning to bioinformatics problems

PubMed Central

Olson, Randal S.; La Cava, William; Mustahsan, Zairah; Varik, Akshay; Moore, Jason H.

2017-01-01

As the bioinformatics field grows, it must keep pace not only with new data but with new algorithms. Here we contribute a thorough analysis of 13 state-of-the-art, commonly used machine learning algorithms on a set of 165 publicly available classification problems in order to provide data-driven algorithm recommendations to current researchers. We present a number of statistical and visual comparisons of algorithm performance and quantify the effect of model selection and algorithm tuning for each algorithm and dataset. The analysis culminates in the recommendation of five algorithms with hyperparameters that maximize classifier performance across the tested problems, as well as general guidelines for applying machine learning to supervised classification problems. PMID:29218881

Determination of astrophysical parameters of quasars within the Gaia mission

NASA Astrophysics Data System (ADS)

Delchambre, L.

2018-01-01

We describe methods designed to determine the astrophysical parameters of quasars based on spectra coming from the red and blue spectrophotometers of the Gaia satellite. These methods principally rely on two already published algorithms that are the weighted principal component analysis and the weighted phase correlation. The presented approach benefits from a fast implementation, an intuitive interpretation as well as strong diagnostic tools on the potential errors that may arise during predictions. The production of a semi-empirical library of spectra as they will be observed by Gaia is also covered and subsequently used for validation purpose. We detail the pre-processing that is necessary in order for these spectra to be fully exploitable by our algorithms along with the procedures that are used to predict the redshifts of the quasars, their continuum slopes, the total equivalent width of their emission lines and whether these are broad absorption line (BAL) quasars or not. Performances of these procedures were assessed in comparison with the extremely randomized trees learning method and were proven to provide better results on the redshift predictions and on the ratio of correctly classified observations though the probability of detection of BAL quasars remains restricted by the low resolution of these spectra as well as by their limited signal-to-noise ratio. Finally, the triggering of some warning flags allows us to obtain an extremely pure subset of redshift predictions where approximately 99 per cent of the observations come along with absolute errors that are below 0.1.

Physical activity classification using the GENEA wrist-worn accelerometer.

PubMed

Zhang, Shaoyan; Rowlands, Alex V; Murray, Peter; Hurst, Tina L

2012-04-01

Most accelerometer-based activity monitors are worn on the waist or lower back for assessment of habitual physical activity. Output is in arbitrary counts that can be classified by activity intensity according to published thresholds. The purpose of this study was to develop methods to classify physical activities into walking, running, household, or sedentary activities based on raw acceleration data from the GENEA (Gravity Estimator of Normal Everyday Activity) and compare classification accuracy from a wrist-worn GENEA with a waist-worn GENEA. Sixty participants (age = 49.4 ± 6.5 yr, body mass index = 24.6 ± 3.4 kg·m⁻²) completed an ordered series of 10-12 semistructured activities in the laboratory and outdoor environment. Throughout, three GENEA accelerometers were worn: one at the waist, one on the left wrist, and one on the right wrist. Acceleration data were collected at 80 Hz. Features obtained from both fast Fourier transform and wavelet decomposition were extracted, and machine learning algorithms were used to classify four types of daily activities including sedentary, household, walking, and running activities. The computational results demonstrated that the algorithm we developed can accurately classify certain types of daily activities, with high overall classification accuracy for both waist-worn GENEA (0.99) and wrist-worn GENEA (right wrist = 0.97, left wrist = 0.96). We have successfully developed algorithms suitable for use with wrist-worn accelerometers for detecting certain types of physical activities; the performance is comparable to waist-worn accelerometers for assessment of physical activity.

Automated tissue classification of intracardiac optical coherence tomography images (Conference Presentation)

NASA Astrophysics Data System (ADS)

Gan, Yu; Tsay, David; Amir, Syed B.; Marboe, Charles C.; Hendon, Christine P.

2016-03-01

Remodeling of the myocardium is associated with increased risk of arrhythmia and heart failure. Our objective is to automatically identify regions of fibrotic myocardium, dense collagen, and adipose tissue, which can serve as a way to guide radiofrequency ablation therapy or endomyocardial biopsies. Using computer vision and machine learning, we present an automated algorithm to classify tissue compositions from cardiac optical coherence tomography (OCT) images. Three dimensional OCT volumes were obtained from 15 human hearts ex vivo within 48 hours of donor death (source, NDRI). We first segmented B-scans using a graph searching method. We estimated the boundary of each region by minimizing a cost function, which consisted of intensity, gradient, and contour smoothness. Then, features, including texture analysis, optical properties, and statistics of high moments, were extracted. We used a statistical model, relevance vector machine, and trained this model with abovementioned features to classify tissue compositions. To validate our method, we applied our algorithm to 77 volumes. The datasets for validation were manually segmented and classified by two investigators who were blind to our algorithm results and identified the tissues based on trichrome histology and pathology. The difference between automated and manual segmentation was 51.78 +/- 50.96 μm. Experiments showed that the attenuation coefficients of dense collagen were significantly different from other tissue types (P < 0.05, ANOVA). Importantly, myocardial fibrosis tissues were different from normal myocardium in entropy and kurtosis. The tissue types were classified with an accuracy of 84%. The results show good agreements with histology.

Sea ice type maps from Alaska synthetic aperture radar facility imagery: An assessment

NASA Technical Reports Server (NTRS)

Fetterer, Florence M.; Gineris, Denise; Kwok, Ronald

1994-01-01

Synthetic aperture radar (SAR) imagery received at the Alaskan SAR Facility is routinely and automatically classified on the Geophysical Processor System (GPS) to create ice type maps. We evaluated the wintertime performance of the GPS classification algorithm by comparing ice type percentages from supervised classification with percentages from the algorithm. The root mean square (RMS) difference for multiyear ice is about 6%, while the inconsistency in supervised classification is about 3%. The algorithm separates first-year from multiyear ice well, although it sometimes fails to correctly classify new ice and open water owing to the wide distribution of backscatter for these classes. Our results imply a high degree of accuracy and consistency in the growing archive of multiyear and first-year ice distribution maps. These results have implications for heat and mass balance studies which are furthered by the ability to accurately characterize ice type distributions over a large part of the Arctic.

Evaluation of an Algorithm to Predict Menstrual-Cycle Phase at the Time of Injury.

PubMed

Tourville, Timothy W; Shultz, Sandra J; Vacek, Pamela M; Knudsen, Emily J; Bernstein, Ira M; Tourville, Kelly J; Hardy, Daniel M; Johnson, Robert J; Slauterbeck, James R; Beynnon, Bruce D

2016-01-01

Women are 2 to 8 times more likely to sustain an anterior cruciate ligament (ACL) injury than men, and previous studies indicated an increased risk for injury during the preovulatory phase of the menstrual cycle (MC). However, investigations of risk rely on retrospective classification of MC phase, and no tools for this have been validated. To evaluate the accuracy of an algorithm for retrospectively classifying MC phase at the time of a mock injury based on MC history and salivary progesterone (P4) concentration. Descriptive laboratory study. Research laboratory. Thirty-one healthy female collegiate athletes (age range, 18-24 years) provided serum or saliva (or both) samples at 8 visits over 1 complete MC. Self-reported MC information was obtained on a randomized date (1-45 days) after mock injury, which is the typical timeframe in which researchers have access to ACL-injured study participants. The MC phase was classified using the algorithm as applied in a stand-alone computational fashion and also by 4 clinical experts using the algorithm and additional subjective hormonal history information to help inform their decision. To assess algorithm accuracy, phase classifications were compared with the actual MC phase at the time of mock injury (ascertained using urinary luteinizing hormone tests and serial serum P4 samples). Clinical expert and computed classifications were compared using κ statistics. Fourteen participants (45%) experienced anovulatory cycles. The algorithm correctly classified MC phase for 23 participants (74%): 22 (76%) of 29 who were preovulatory/anovulatory and 1 (50%) of 2 who were postovulatory. Agreement between expert and algorithm classifications ranged from 80.6% (κ = 0.50) to 93% (κ = 0.83). Classifications based on same-day saliva sample and optimal P4 threshold were the same as those based on MC history alone (87.1% correct). Algorithm accuracy varied during the MC but at no time were both sensitivity and specificity levels acceptable. These findings raise concerns about the accuracy of previous retrospective MC-phase classification systems, particularly in a population with a high occurrence of anovulatory cycles.

Evolutionary optimization of radial basis function classifiers for data mining applications.

PubMed

Buchtala, Oliver; Klimek, Manuel; Sick, Bernhard

2005-10-01

In many data mining applications that address classification problems, feature and model selection are considered as key tasks. That is, appropriate input features of the classifier must be selected from a given (and often large) set of possible features and structure parameters of the classifier must be adapted with respect to these features and a given data set. This paper describes an evolutionary algorithm (EA) that performs feature and model selection simultaneously for radial basis function (RBF) classifiers. In order to reduce the optimization effort, various techniques are integrated that accelerate and improve the EA significantly: hybrid training of RBF networks, lazy evaluation, consideration of soft constraints by means of penalty terms, and temperature-based adaptive control of the EA. The feasibility and the benefits of the approach are demonstrated by means of four data mining problems: intrusion detection in computer networks, biometric signature verification, customer acquisition with direct marketing methods, and optimization of chemical production processes. It is shown that, compared to earlier EA-based RBF optimization techniques, the runtime is reduced by up to 99% while error rates are lowered by up to 86%, depending on the application. The algorithm is independent of specific applications so that many ideas and solutions can be transferred to other classifier paradigms.

The SIST-M: Predictive validity of a brief structured Clinical Dementia Rating interview

PubMed Central

Okereke, Olivia I.; Pantoja-Galicia, Norberto; Copeland, Maura; Hyman, Bradley T.; Wanggaard, Taylor; Albert, Marilyn S.; Betensky, Rebecca A.; Blacker, Deborah

2011-01-01

Background We previously established reliability and cross-sectional validity of the SIST-M (Structured Interview and Scoring Tool–Massachusetts Alzheimer's Disease Research Center), a shortened version of an instrument shown to predict progression to Alzheimer disease (AD), even among persons with very mild cognitive impairment (vMCI). Objective To test predictive validity of the SIST-M. Methods Participants were 342 community-dwelling, non-demented older adults in a longitudinal study. Baseline Clinical Dementia Rating (CDR) ratings were determined by either: 1) clinician interviews or 2) a previously developed computer algorithm based on 60 questions (of a possible 131) extracted from clinician interviews. We developed age+gender+education-adjusted Cox proportional hazards models using CDR-sum-of-boxes (CDR-SB) as the predictor, where CDR-SB was determined by either clinician interview or algorithm; models were run for the full sample (n=342) and among those jointly classified as vMCI using clinician- and algorithm-based CDR ratings (n=156). We directly compared predictive accuracy using time-dependent Receiver Operating Characteristic (ROC) curves. Results AD hazard ratios (HRs) were similar for clinician-based and algorithm-based CDR-SB: for a 1-point increment in CDR-SB, respective HRs (95% CI)=3.1 (2.5,3.9) and 2.8 (2.2,3.5); among those with vMCI, respective HRs (95% CI) were 2.2 (1.6,3.2) and 2.1 (1.5,3.0). Similarly high predictive accuracy was achieved: the concordance probability (weighted average of the area-under-the-ROC curves) over follow-up was 0.78 vs. 0.76 using clinician-based vs. algorithm-based CDR-SB. Conclusion CDR scores based on items from this shortened interview had high predictive ability for AD – comparable to that using a lengthy clinical interview. PMID:21986342

Comparing ensemble learning methods based on decision tree classifiers for protein fold recognition.

PubMed

Bardsiri, Mahshid Khatibi; Eftekhari, Mahdi

2014-01-01

In this paper, some methods for ensemble learning of protein fold recognition based on a decision tree (DT) are compared and contrasted against each other over three datasets taken from the literature. According to previously reported studies, the features of the datasets are divided into some groups. Then, for each of these groups, three ensemble classifiers, namely, random forest, rotation forest and AdaBoost.M1 are employed. Also, some fusion methods are introduced for combining the ensemble classifiers obtained in the previous step. After this step, three classifiers are produced based on the combination of classifiers of types random forest, rotation forest and AdaBoost.M1. Finally, the three different classifiers achieved are combined to make an overall classifier. Experimental results show that the overall classifier obtained by the genetic algorithm (GA) weighting fusion method, is the best one in comparison to previously applied methods in terms of classification accuracy.

Discovering Fine-grained Sentiment in Suicide Notes

PubMed Central

Wang, Wenbo; Chen, Lu; Tan, Ming; Wang, Shaojun; Sheth, Amit P.

2012-01-01

This paper presents our solution for the i2b2 sentiment classification challenge. Our hybrid system consists of machine learning and rule-based classifiers. For the machine learning classifier, we investigate a variety of lexical, syntactic and knowledge-based features, and show how much these features contribute to the performance of the classifier through experiments. For the rule-based classifier, we propose an algorithm to automatically extract effective syntactic and lexical patterns from training examples. The experimental results show that the rule-based classifier outperforms the baseline machine learning classifier using unigram features. By combining the machine learning classifier and the rule-based classifier, the hybrid system gains a better trade-off between precision and recall, and yields the highest micro-averaged F-measure (0.5038), which is better than the mean (0.4875) and median (0.5027) micro-average F-measures among all participating teams. PMID:22879770

Applying machine-learning techniques to Twitter data for automatic hazard-event classification.

NASA Astrophysics Data System (ADS)

Filgueira, R.; Bee, E. J.; Diaz-Doce, D.; Poole, J., Sr.; Singh, A.

2017-12-01

The constant flow of information offered by tweets provides valuable information about all sorts of events at a high temporal and spatial resolution. Over the past year we have been analyzing in real-time geological hazards/phenomenon, such as earthquakes, volcanic eruptions, landslides, floods or the aurora, as part of the GeoSocial project, by geo-locating tweets filtered by keywords in a web-map. However, not all the filtered tweets are related with hazard/phenomenon events. This work explores two classification techniques for automatic hazard-event categorization based on tweets about the "Aurora". First, tweets were filtered using aurora-related keywords, removing stop words and selecting the ones written in English. For classifying the remaining between "aurora-event" or "no-aurora-event" categories, we compared two state-of-art techniques: Support Vector Machine (SVM) and Deep Convolutional Neural Networks (CNN) algorithms. Both approaches belong to the family of supervised learning algorithms, which make predictions based on labelled training dataset. Therefore, we created a training dataset by tagging 1200 tweets between both categories. The general form of SVM is used to separate two classes by a function (kernel). We compared the performance of four different kernels (Linear Regression, Logistic Regression, Multinomial Naïve Bayesian and Stochastic Gradient Descent) provided by Scikit-Learn library using our training dataset to build the SVM classifier. The results shown that the Logistic Regression (LR) gets the best accuracy (87%). So, we selected the SVM-LR classifier to categorise a large collection of tweets using the "dispel4py" framework.Later, we developed a CNN classifier, where the first layer embeds words into low-dimensional vectors. The next layer performs convolutions over the embedded word vectors. Results from the convolutional layer are max-pooled into a long feature vector, which is classified using a softmax layer. The CNN's accuracy is lower (83%) than the SVM-LR, since the algorithm needs a bigger training dataset to increase its accuracy. We used TensorFlow framework for applying CNN classifier to the same collection of tweets.In future we will modify both classifiers to work with other geo-hazards, use larger training datasets and apply them in real-time.

Analysis of miRNA expression profile based on SVM algorithm

NASA Astrophysics Data System (ADS)

Ting-ting, Dai; Chang-ji, Shan; Yan-shou, Dong; Yi-duo, Bian

2018-05-01

Based on mirna expression spectrum data set, a new data mining algorithm - tSVM - KNN (t statistic with support vector machine - k nearest neighbor) is proposed. the idea of the algorithm is: firstly, the feature selection of the data set is carried out by the unified measurement method; Secondly, SVM - KNN algorithm, which combines support vector machine (SVM) and k - nearest neighbor (k - nearest neighbor) is used as classifier. Simulation results show that SVM - KNN algorithm has better classification ability than SVM and KNN alone. Tsvm - KNN algorithm only needs 5 mirnas to obtain 96.08 % classification accuracy in terms of the number of mirna " tags" and recognition accuracy. compared with similar algorithms, tsvm - KNN algorithm has obvious advantages.

Error minimizing algorithms for nearest eighbor classifiers

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

Porter, Reid B; Hush, Don; Zimmer, G. Beate

2011-01-03

Stack Filters define a large class of discrete nonlinear filter first introd uced in image and signal processing for noise removal. In recent years we have suggested their application to classification problems, and investigated their relationship to other types of discrete classifiers such as Decision Trees. In this paper we focus on a continuous domain version of Stack Filter Classifiers which we call Ordered Hypothesis Machines (OHM), and investigate their relationship to Nearest Neighbor classifiers. We show that OHM classifiers provide a novel framework in which to train Nearest Neighbor type classifiers by minimizing empirical error based loss functions. Wemore » use the framework to investigate a new cost sensitive loss function that allows us to train a Nearest Neighbor type classifier for low false alarm rate applications. We report results on both synthetic data and real-world image data.« less

Improved analytical methods for microarray-based genome-composition analysis

PubMed Central

Kim, Charles C; Joyce, Elizabeth A; Chan, Kaman; Falkow, Stanley

2002-01-01

Background Whereas genome sequencing has given us high-resolution pictures of many different species of bacteria, microarrays provide a means of obtaining information on genome composition for many strains of a given species. Genome-composition analysis using microarrays, or 'genomotyping', can be used to categorize genes into 'present' and 'divergent' categories based on the level of hybridization signal. This typically involves selecting a signal value that is used as a cutoff to discriminate present (high signal) and divergent (low signal) genes. Current methodology uses empirical determination of cutoffs for classification into these categories, but this methodology is subject to several problems that can result in the misclassification of many genes. Results We describe a method that depends on the shape of the signal-ratio distribution and does not require empirical determination of a cutoff. Moreover, the cutoff is determined on an array-to-array basis, accounting for variation in strain composition and hybridization quality. The algorithm also provides an estimate of the probability that any given gene is present, which provides a measure of confidence in the categorical assignments. Conclusions Many genes previously classified as present using static methods are in fact divergent on the basis of microarray signal; this is corrected by our algorithm. We have reassigned hundreds of genes from previous genomotyping studies of Helicobacter pylori and Campylobacter jejuni strains, and expect that the algorithm should be widely applicable to genomotyping data. PMID:12429064

Self-Cohering Airborne Distributed Array

DTIC Science & Technology

1988-06-01

F19628-84- C -0080 ft. ADDRESS (City, State, and ZIP Code) 10. SOURCE OF FUNDING NUMBERS PROGRAM PROJECT JTASK JWORK UNIT Hanscom APE MA 01731-5000...algorithms under consideration (including the newly developed algorithms). The algorithms are classified both according to the type c -f processing and...4.1 RADIO CAMERA DATA FORMAT AND PROCEDURES (FROM C -23) The range trace delivered by each antenna element is stonred as a rc’w of coimplex number-s

Machine learning classifier using abnormal brain network topological metrics in major depressive disorder.

PubMed

Guo, Hao; Cao, Xiaohua; Liu, Zhifen; Li, Haifang; Chen, Junjie; Zhang, Kerang

2012-12-05

Resting state functional brain networks have been widely studied in brain disease research. However, it is currently unclear whether abnormal resting state functional brain network metrics can be used with machine learning for the classification of brain diseases. Resting state functional brain networks were constructed for 28 healthy controls and 38 major depressive disorder patients by thresholding partial correlation matrices of 90 regions. Three nodal metrics were calculated using graph theory-based approaches. Nonparametric permutation tests were then used for group comparisons of topological metrics, which were used as classified features in six different algorithms. We used statistical significance as the threshold for selecting features and measured the accuracies of six classifiers with different number of features. A sensitivity analysis method was used to evaluate the importance of different features. The result indicated that some of the regions exhibited significantly abnormal nodal centralities, including the limbic system, basal ganglia, medial temporal, and prefrontal regions. Support vector machine with radial basis kernel function algorithm and neural network algorithm exhibited the highest average accuracy (79.27 and 78.22%, respectively) with 28 features (P<0.05). Correlation analysis between feature importance and the statistical significance of metrics was investigated, and the results revealed a strong positive correlation between them. Overall, the current study demonstrated that major depressive disorder is associated with abnormal functional brain network topological metrics and statistically significant nodal metrics can be successfully used for feature selection in classification algorithms.

Evaluation of machine learning algorithms for prediction of regions of high Reynolds averaged Navier Stokes uncertainty

DOE PAGES

Ling, Julia; Templeton, Jeremy Alan

2015-08-04

Reynolds Averaged Navier Stokes (RANS) models are widely used in industry to predict fluid flows, despite their acknowledged deficiencies. Not only do RANS models often produce inaccurate flow predictions, but there are very limited diagnostics available to assess RANS accuracy for a given flow configuration. If experimental or higher fidelity simulation results are not available for RANS validation, there is no reliable method to evaluate RANS accuracy. This paper explores the potential of utilizing machine learning algorithms to identify regions of high RANS uncertainty. Three different machine learning algorithms were evaluated: support vector machines, Adaboost decision trees, and random forests.more » The algorithms were trained on a database of canonical flow configurations for which validated direct numerical simulation or large eddy simulation results were available, and were used to classify RANS results on a point-by-point basis as having either high or low uncertainty, based on the breakdown of specific RANS modeling assumptions. Classifiers were developed for three different basic RANS eddy viscosity model assumptions: the isotropy of the eddy viscosity, the linearity of the Boussinesq hypothesis, and the non-negativity of the eddy viscosity. It is shown that these classifiers are able to generalize to flows substantially different from those on which they were trained. As a result, feature selection techniques, model evaluation, and extrapolation detection are discussed in the context of turbulence modeling applications.« less

Classifier ensemble based on feature selection and diversity measures for predicting the affinity of A(2B) adenosine receptor antagonists.

PubMed

Bonet, Isis; Franco-Montero, Pedro; Rivero, Virginia; Teijeira, Marta; Borges, Fernanda; Uriarte, Eugenio; Morales Helguera, Aliuska

2013-12-23

A(2B) adenosine receptor antagonists may be beneficial in treating diseases like asthma, diabetes, diabetic retinopathy, and certain cancers. This has stimulated research for the development of potent ligands for this subtype, based on quantitative structure-affinity relationships. In this work, a new ensemble machine learning algorithm is proposed for classification and prediction of the ligand-binding affinity of A(2B) adenosine receptor antagonists. This algorithm is based on the training of different classifier models with multiple training sets (composed of the same compounds but represented by diverse features). The k-nearest neighbor, decision trees, neural networks, and support vector machines were used as single classifiers. To select the base classifiers for combining into the ensemble, several diversity measures were employed. The final multiclassifier prediction results were computed from the output obtained by using a combination of selected base classifiers output, by utilizing different mathematical functions including the following: majority vote, maximum and average probability. In this work, 10-fold cross- and external validation were used. The strategy led to the following results: i) the single classifiers, together with previous features selections, resulted in good overall accuracy, ii) a comparison between single classifiers, and their combinations in the multiclassifier model, showed that using our ensemble gave a better performance than the single classifier model, and iii) our multiclassifier model performed better than the most widely used multiclassifier models in the literature. The results and statistical analysis demonstrated the supremacy of our multiclassifier approach for predicting the affinity of A(2B) adenosine receptor antagonists, and it can be used to develop other QSAR models.

Poor concordance among nine immunohistochemistry classifiers of cell-of-origin for Diffuse Large B-cell Lymphoma: implications for therapeutic strategies

PubMed Central

Coutinho, Rita; Clear, Andrew James; Owen, Andrew; Wilson, Andrew; Matthews, Janet; Lee, Abigail; Alvarez, Rute; da Silva, Maria Gomes; Cabeçadas, José; Calaminici, Maria; Gribben, John G.

2014-01-01

Purpose The opportunity to improve therapeutic choices on the basis of molecular features of the tumour cells is on the horizon in Diffuse Large B-cell Lymphoma (DLBCL). Agents such as bortezomib exhibit selective activity against the poor outcome activated B-cell type DLBCL. In order for targeted therapies to succeed in this disease, robust strategies that segregate patients into molecular groups with high reliability are needed. While molecular studies are considered gold standard, several immunohistochemistry (IHC) algorithms have been published that claim to be able to stratify patients according to their cell-of-origin and to be relevant for patient outcome. However results are poorly reproducible by independent groups. Experimental design We investigated nine IHC algorithms for molecular classification in a dataset of DLBCL diagnostic biopsies, incorporating immunostaining for CD10, BCL6, BCL2, MUM1, FOXP1, GCET1 and LMO2. IHC profiles were assessed and agreed among three expert observers. A consensus matrix based on all scoring combinations and the number of subjects for each combination allowed to assess reliability. The survival impact of individual markers and classifiers was evaluated using Kaplan-Meier curves and the log-rank test. Results The concordance in patient’s classification across the different algorithms was low. Only 4% the tumors have been classified as GCB and 21% as ABC/non-GCB by all methods. None of the algorithms provided prognostic information in the R-CHOP treated cohort. Conclusion Further work is required to standardize IHC algorithms for DLBCL cell-of-origin classification for these to be considered reliable alternatives to molecular-based methods to be used for clinical decisions. PMID:24122791

Poor concordance among nine immunohistochemistry classifiers of cell-of-origin for diffuse large B-cell lymphoma: implications for therapeutic strategies.

PubMed

Coutinho, Rita; Clear, Andrew James; Owen, Andrew; Wilson, Andrew; Matthews, Janet; Lee, Abigail; Alvarez, Rute; Gomes da Silva, Maria; Cabeçadas, José; Calaminici, Maria; Gribben, John G

2013-12-15

The opportunity to improve therapeutic choices on the basis of molecular features of the tumor cells is on the horizon in diffuse large B-cell lymphoma (DLBCL). Agents such as bortezomib exhibit selective activity against the poor outcome activated B-cell type (ABC) DLBCL. In order for targeted therapies to succeed in this disease, robust strategies that segregate patients into molecular groups with high reliability are needed. Although molecular studies are considered gold standard, several immunohistochemistry (IHC) algorithms have been published that claim to be able to stratify patients according to their cell-of-origin and to be relevant for patient outcome. However, results are poorly reproducible by independent groups. We investigated nine IHC algorithms for molecular classification in a dataset of DLBCL diagnostic biopsies, incorporating immunostaining for CD10, BCL6, BCL2, MUM1, FOXP1, GCET1, and LMO2. IHC profiles were assessed and agreed among three expert observers. A consensus matrix based on all scoring combinations and the number of subjects for each combination allowed us to assess reliability. The survival impact of individual markers and classifiers was evaluated using Kaplan-Meier curves and the log-rank test. The concordance in patient's classification across the different algorithms was low. Only 4% of the tumors have been classified as germinal center B-cell type (GCB) and 21% as ABC/non-GCB by all methods. None of the algorithms provided prognostic information in the R-CHOP (rituximab plus cyclophosphamide-adriamycin-vincristine-prednisone)-treated cohort. Further work is required to standardize IHC algorithms for DLBCL cell-of-origin classification for these to be considered reliable alternatives to molecular-based methods to be used for clinical decisions. ©2013 AACR.

Activity recognition using a single accelerometer placed at the wrist or ankle.

PubMed

Mannini, Andrea; Intille, Stephen S; Rosenberger, Mary; Sabatini, Angelo M; Haskell, William

2013-11-01

Large physical activity surveillance projects such as the UK Biobank and NHANES are using wrist-worn accelerometer-based activity monitors that collect raw data. The goal is to increase wear time by asking subjects to wear the monitors on the wrist instead of the hip, and then to use information in the raw signal to improve activity type and intensity estimation. The purposes of this work was to obtain an algorithm to process wrist and ankle raw data and to classify behavior into four broad activity classes: ambulation, cycling, sedentary, and other activities. Participants (N = 33) wearing accelerometers on the wrist and ankle performed 26 daily activities. The accelerometer data were collected, cleaned, and preprocessed to extract features that characterize 2-, 4-, and 12.8-s data windows. Feature vectors encoding information about frequency and intensity of motion extracted from analysis of the raw signal were used with a support vector machine classifier to identify a subject's activity. Results were compared with categories classified by a human observer. Algorithms were validated using a leave-one-subject-out strategy. The computational complexity of each processing step was also evaluated. With 12.8-s windows, the proposed strategy showed high classification accuracies for ankle data (95.0%) that decreased to 84.7% for wrist data. Shorter (4 s) windows only minimally decreased performances of the algorithm on the wrist to 84.2%. A classification algorithm using 13 features shows good classification into the four classes given the complexity of the activities in the original data set. The algorithm is computationally efficient and could be implemented in real time on mobile devices with only 4-s latency.

Self-reported transient ischemic attack and stroke symptoms: methods and baseline prevalence. The ARIC Study, 1987-1989.

PubMed

Toole, J F; Lefkowitz, D S; Chambless, L E; Wijnberg, L; Paton, C C; Heiss, G

1996-11-01

As part of the Atherosclerosis Risk in Communities (ARIC) Study assessment of the etiology and sequelae of atherosclerosis, a standardized questionnaire on transient ischemic attack (TIA) and nonfatal stroke and a computerized diagnostic algorithm simulating clinical reasoning were developed and tested at the four ARIC field centers: Forsyth County, North Carolina; Minneapolis, Minnesota; Jackson, Mississippi; and Washington County, Maryland. The diagnostic algorithm used participant responses to a series of questions about six neurologic trigger symptoms to identify symptoms of TIA or stroke and their vascular distribution. Among 12,205 ARIO participants reporting their lifetime occurrence of one or more symptoms probably due to cerebrovascular causes, nearly half (47%) reported the sudden onset of at least one symptom sometime prior to their ARIC examination. Of those with at least one symptom, only 12.9% were classified by the computer algorithm as having symptoms of TIA or stroke. Dizziness/loss of balance was the most frequently reported symptom (36%); 1.2% of these persons were classified by the algorithm as having a TIA/stroke event. Positive symptoms of speech dysfunction were classified most often (77.%) as being symptoms of TIA or stroke. Symptoms suggesting TIA were reported more frequently than symptoms suggesting stroke by both sexes. TIA or stroke-like phenomena were more frequent (p < 0.001) in females (7%) than in males (5%) and increased with age in both sexes (p = 0.13 for females; p = 0.02 for males). In Forsyth County, TIA and stroke symptoms were greater in African Americans than in Caucasians (p = 0.05, controlling for sex). The association of algorithmically defined symptoms of TIA or stroke with traditional cerebrovascular risk factors is the subject of a companion paper.

Hybrid three-dimensional and support vector machine approach for automatic vehicle tracking and classification using a single camera

NASA Astrophysics Data System (ADS)

Kachach, Redouane; Cañas, José María

2016-05-01

Using video in traffic monitoring is one of the most active research domains in the computer vision community. TrafficMonitor, a system that employs a hybrid approach for automatic vehicle tracking and classification on highways using a simple stationary calibrated camera, is presented. The proposed system consists of three modules: vehicle detection, vehicle tracking, and vehicle classification. Moving vehicles are detected by an enhanced Gaussian mixture model background estimation algorithm. The design includes a technique to resolve the occlusion problem by using a combination of two-dimensional proximity tracking algorithm and the Kanade-Lucas-Tomasi feature tracking algorithm. The last module classifies the shapes identified into five vehicle categories: motorcycle, car, van, bus, and truck by using three-dimensional templates and an algorithm based on histogram of oriented gradients and the support vector machine classifier. Several experiments have been performed using both real and simulated traffic in order to validate the system. The experiments were conducted on GRAM-RTM dataset and a proper real video dataset which is made publicly available as part of this work.

Optical Detection of Degraded Therapeutic Proteins.

PubMed

Herrington, William F; Singh, Gajendra P; Wu, Di; Barone, Paul W; Hancock, William; Ram, Rajeev J

2018-03-23

The quality of therapeutic proteins such as hormones, subunit and conjugate vaccines, and antibodies is critical to the safety and efficacy of modern medicine. Identifying malformed proteins at the point-of-care can prevent adverse immune reactions in patients; this is of special concern when there is an insecure supply chain resulting in the delivery of degraded, or even counterfeit, drug product. Identification of degraded protein, for example human growth hormone, is demonstrated by applying automated anomaly detection algorithms. Detection of the degraded protein differs from previous applications of machine-learning and classification to spectral analysis: only example spectra of genuine, high-quality drug products are used to construct the classifier. The algorithm is tested on Raman spectra acquired on protein dilutions typical of formulated drug product and at sample volumes of 25 µL, below the typical overfill (waste) volumes present in vials of injectable drug product. The algorithm is demonstrated to correctly classify anomalous recombinant human growth hormone (rhGH) with 92% sensitivity and 98% specificity even when the algorithm has only previously encountered high-quality drug product.

Comparison of the algorithms classifying the ABC and GCB subtypes in diffuse large B-cell lymphoma.

PubMed

Boltežar, Lučka; Prevodnik, Veronika Kloboves; Perme, Maja Pohar; Gašljević, Gorana; Novaković, Barbara Jezeršek

2018-05-01

Different immunohistochemical algorithms for the classification of the activated B-cell (ABC) and germinal center B-cell (GCB) subtypes of diffuse large B-cell lymphoma (DLBCL) are applied in different laboratories. In the present study, 127 patients with DLCBL were investigated, all treated with rituximab and cyclophosphamide, hydroxydaunorubicin, oncovin and prednisone (CHOP) or CHOP-like regimens between April 2004 and December 2010. Multi-tumor tissue microarrays were prepared and were tested according to 4 algorithms: Hans; modified Hans; Choi; and modified Choi. For 39 patients, the flow cytometric quantification of CD19 and CD20 antigen expression was performed and the level of expression presented as molecules of equivalent soluble fluorochrome units. The Choi algorithm was demonstrated to be prognostic for OS and classified patients into the GCB subgroup with an HR of 0.91. No difference in the expression of the CD19 antigen between the ABC and GCB groups was observed, but the ABC subtype exhibited a decreased expression of the CD20 antigen compared with the GCB subtype.

Uncertainty analysis of wavelet-based feature extraction for isotope identification on NaI gamma-ray spectra

DOE PAGES

Stinnett, Jacob; Sullivan, Clair J.; Xiong, Hao

2017-03-02

Low-resolution isotope identifiers are widely deployed for nuclear security purposes, but these detectors currently demonstrate problems in making correct identifications in many typical usage scenarios. While there are many hardware alternatives and improvements that can be made, performance on existing low resolution isotope identifiers should be able to be improved by developing new identification algorithms. We have developed a wavelet-based peak extraction algorithm and an implementation of a Bayesian classifier for automated peak-based identification. The peak extraction algorithm has been extended to compute uncertainties in the peak area calculations. To build empirical joint probability distributions of the peak areas andmore » uncertainties, a large set of spectra were simulated in MCNP6 and processed with the wavelet-based feature extraction algorithm. Kernel density estimation was then used to create a new component of the likelihood function in the Bayesian classifier. Furthermore, identification performance is demonstrated on a variety of real low-resolution spectra, including Category I quantities of special nuclear material.« less

A compressed sensing method with analytical results for lidar feature classification

NASA Astrophysics Data System (ADS)

Allen, Josef D.; Yuan, Jiangbo; Liu, Xiuwen; Rahmes, Mark

2011-04-01

We present an innovative way to autonomously classify LiDAR points into bare earth, building, vegetation, and other categories. One desirable product of LiDAR data is the automatic classification of the points in the scene. Our algorithm automatically classifies scene points using Compressed Sensing Methods via Orthogonal Matching Pursuit algorithms utilizing a generalized K-Means clustering algorithm to extract buildings and foliage from a Digital Surface Models (DSM). This technology reduces manual editing while being cost effective for large scale automated global scene modeling. Quantitative analyses are provided using Receiver Operating Characteristics (ROC) curves to show Probability of Detection and False Alarm of buildings vs. vegetation classification. Histograms are shown with sample size metrics. Our inpainting algorithms then fill the voids where buildings and vegetation were removed, utilizing Computational Fluid Dynamics (CFD) techniques and Partial Differential Equations (PDE) to create an accurate Digital Terrain Model (DTM) [6]. Inpainting preserves building height contour consistency and edge sharpness of identified inpainted regions. Qualitative results illustrate other benefits such as Terrain Inpainting's unique ability to minimize or eliminate undesirable terrain data artifacts.

A clustering algorithm for sample data based on environmental pollution characteristics

NASA Astrophysics Data System (ADS)

Chen, Mei; Wang, Pengfei; Chen, Qiang; Wu, Jiadong; Chen, Xiaoyun

2015-04-01

Environmental pollution has become an issue of serious international concern in recent years. Among the receptor-oriented pollution models, CMB, PMF, UNMIX, and PCA are widely used as source apportionment models. To improve the accuracy of source apportionment and classify the sample data for these models, this study proposes an easy-to-use, high-dimensional EPC algorithm that not only organizes all of the sample data into different groups according to the similarities in pollution characteristics such as pollution sources and concentrations but also simultaneously detects outliers. The main clustering process consists of selecting the first unlabelled point as the cluster centre, then assigning each data point in the sample dataset to its most similar cluster centre according to both the user-defined threshold and the value of similarity function in each iteration, and finally modifying the clusters using a method similar to k-Means. The validity and accuracy of the algorithm are tested using both real and synthetic datasets, which makes the EPC algorithm practical and effective for appropriately classifying sample data for source apportionment models and helpful for better understanding and interpreting the sources of pollution.

Robust Feature Selection Technique using Rank Aggregation.

PubMed

Sarkar, Chandrima; Cooley, Sarah; Srivastava, Jaideep

2014-01-01

Although feature selection is a well-developed research area, there is an ongoing need to develop methods to make classifiers more efficient. One important challenge is the lack of a universal feature selection technique which produces similar outcomes with all types of classifiers. This is because all feature selection techniques have individual statistical biases while classifiers exploit different statistical properties of data for evaluation. In numerous situations this can put researchers into dilemma as to which feature selection method and a classifiers to choose from a vast range of choices. In this paper, we propose a technique that aggregates the consensus properties of various feature selection methods to develop a more optimal solution. The ensemble nature of our technique makes it more robust across various classifiers. In other words, it is stable towards achieving similar and ideally higher classification accuracy across a wide variety of classifiers. We quantify this concept of robustness with a measure known as the Robustness Index (RI). We perform an extensive empirical evaluation of our technique on eight data sets with different dimensions including Arrythmia, Lung Cancer, Madelon, mfeat-fourier, internet-ads, Leukemia-3c and Embryonal Tumor and a real world data set namely Acute Myeloid Leukemia (AML). We demonstrate not only that our algorithm is more robust, but also that compared to other techniques our algorithm improves the classification accuracy by approximately 3-4% (in data set with less than 500 features) and by more than 5% (in data set with more than 500 features), across a wide range of classifiers.

Effective Sequential Classifier Training for SVM-Based Multitemporal Remote Sensing Image Classification

NASA Astrophysics Data System (ADS)

Guo, Yiqing; Jia, Xiuping; Paull, David

2018-06-01

The explosive availability of remote sensing images has challenged supervised classification algorithms such as Support Vector Machines (SVM), as training samples tend to be highly limited due to the expensive and laborious task of ground truthing. The temporal correlation and spectral similarity between multitemporal images have opened up an opportunity to alleviate this problem. In this study, a SVM-based Sequential Classifier Training (SCT-SVM) approach is proposed for multitemporal remote sensing image classification. The approach leverages the classifiers of previous images to reduce the required number of training samples for the classifier training of an incoming image. For each incoming image, a rough classifier is firstly predicted based on the temporal trend of a set of previous classifiers. The predicted classifier is then fine-tuned into a more accurate position with current training samples. This approach can be applied progressively to sequential image data, with only a small number of training samples being required from each image. Experiments were conducted with Sentinel-2A multitemporal data over an agricultural area in Australia. Results showed that the proposed SCT-SVM achieved better classification accuracies compared with two state-of-the-art model transfer algorithms. When training data are insufficient, the overall classification accuracy of the incoming image was improved from 76.18% to 94.02% with the proposed SCT-SVM, compared with those obtained without the assistance from previous images. These results demonstrate that the leverage of a priori information from previous images can provide advantageous assistance for later images in multitemporal image classification.

Classification of patients by severity grades during triage in the emergency department using data mining methods.

PubMed

Zmiri, Dror; Shahar, Yuval; Taieb-Maimon, Meirav

2012-04-01

To test the feasibility of classifying emergency department patients into severity grades using data mining methods. Emergency department records of 402 patients were classified into five severity grades by two expert physicians. The Naïve Bayes and C4.5 algorithms were applied to produce classifiers from patient data into severity grades. The classifiers' results over several subsets of the data were compared with the physicians' assessments, with a random classifier, and with a classifier that selects the maximal-prevalence class. Positive predictive value, multiple-class extensions of sensitivity and specificity combinations, and entropy change. The mean accuracy of the data mining classifiers was 52.94 ± 5.89%, significantly better (P < 0.05) than the mean accuracy of a random classifier (34.60 ± 2.40%). The entropy of the input data sets was reduced through classification by a mean of 10.1%. Allowing for classification deviations of one severity grade led to mean accuracy of 85.42 ± 1.42%. The classifiers' accuracy in that case was similar to the physicians' consensus rate. Learning from consensus records led to better performance. Reducing the number of severity grades improved results in certain cases. The performance of the Naïve Bayes and C4.5 algorithms was similar; in unbalanced data sets, Naïve Bayes performed better. It is possible to produce a computerized classification model for the severity grade of triage patients, using data mining methods. Learning from patient records regarding which there is a consensus of several physicians is preferable to learning from each physician's patients. Either Naïve Bayes or C4.5 can be used; Naïve Bayes is preferable for unbalanced data sets. An ambiguity in the intermediate severity grades seems to hamper both the physicians' agreement and the classifiers' accuracy. © 2010 Blackwell Publishing Ltd.

Data integration modeling applied to drill hole planning through semi-supervised learning: A case study from the Dalli Cu-Au porphyry deposit in the central Iran

NASA Astrophysics Data System (ADS)

Fatehi, Moslem; Asadi, Hooshang H.

2017-04-01

In this study, the application of a transductive support vector machine (TSVM), an innovative semi-supervised learning algorithm, has been proposed for mapping the potential drill targets at a detailed exploration stage. The semi-supervised learning method is a hybrid of supervised and unsupervised learning approach that simultaneously uses both training and non-training data to design a classifier. By using the TSVM algorithm, exploration layers at the Dalli porphyry Cu-Au deposit in the central Iran were integrated to locate the boundary of the Cu-Au mineralization for further drilling. By applying this algorithm on the non-training (unlabeled) and limited training (labeled) Dalli exploration data, the study area was classified in two domains of Cu-Au ore and waste. Then, the results were validated by the earlier block models created, using the available borehole and trench data. In addition to TSVM, the support vector machine (SVM) algorithm was also implemented on the study area for comparison. Thirty percent of the labeled exploration data was used to evaluate the performance of these two algorithms. The results revealed 87 percent correct recognition accuracy for the TSVM algorithm and 82 percent for the SVM algorithm. The deepest inclined borehole, recently drilled in the western part of the Dalli deposit, indicated that the boundary of Cu-Au mineralization, as identified by the TSVM algorithm, was only 15 m off from the actual boundary intersected by this borehole. According to the results of the TSVM algorithm, six new boreholes were suggested for further drilling at the Dalli deposit. This study showed that the TSVM algorithm could be a useful tool for enhancing the mineralization zones and consequently, ensuring a more accurate drill hole planning.

A comparison of graph- and kernel-based -omics data integration algorithms for classifying complex traits.

PubMed

Yan, Kang K; Zhao, Hongyu; Pang, Herbert

2017-12-06

High-throughput sequencing data are widely collected and analyzed in the study of complex diseases in quest of improving human health. Well-studied algorithms mostly deal with single data source, and cannot fully utilize the potential of these multi-omics data sources. In order to provide a holistic understanding of human health and diseases, it is necessary to integrate multiple data sources. Several algorithms have been proposed so far, however, a comprehensive comparison of data integration algorithms for classification of binary traits is currently lacking. In this paper, we focus on two common classes of integration algorithms, graph-based that depict relationships with subjects denoted by nodes and relationships denoted by edges, and kernel-based that can generate a classifier in feature space. Our paper provides a comprehensive comparison of their performance in terms of various measurements of classification accuracy and computation time. Seven different integration algorithms, including graph-based semi-supervised learning, graph sharpening integration, composite association network, Bayesian network, semi-definite programming-support vector machine (SDP-SVM), relevance vector machine (RVM) and Ada-boost relevance vector machine are compared and evaluated with hypertension and two cancer data sets in our study. In general, kernel-based algorithms create more complex models and require longer computation time, but they tend to perform better than graph-based algorithms. The performance of graph-based algorithms has the advantage of being faster computationally. The empirical results demonstrate that composite association network, relevance vector machine, and Ada-boost RVM are the better performers. We provide recommendations on how to choose an appropriate algorithm for integrating data from multiple sources.

Classification of voting algorithms for N-version software

NASA Astrophysics Data System (ADS)

Tsarev, R. Yu; Durmuş, M. S.; Üstoglu, I.; Morozov, V. A.

2018-05-01

A voting algorithm in N-version software is a crucial component that evaluates the execution of each of the N versions and determines the correct result. Obviously, the result of the voting algorithm determines the outcome of the N-version software in general. Thus, the choice of the voting algorithm is a vital issue. A lot of voting algorithms were already developed and they may be selected for implementation based on the specifics of the analysis of input data. However, the voting algorithms applied in N-version software are not classified. This article presents an overview of classic and recent voting algorithms used in N-version software and the authors' classification of the voting algorithms. Moreover, the steps of the voting algorithms are presented and the distinctive features of the voting algorithms in Nversion software are defined.

Matching incomplete time series with dynamic time warping: an algorithm and an application to post-stroke rehabilitation.

PubMed

Tormene, Paolo; Giorgino, Toni; Quaglini, Silvana; Stefanelli, Mario

2009-01-01

The purpose of this study was to assess the performance of a real-time ("open-end") version of the dynamic time warping (DTW) algorithm for the recognition of motor exercises. Given a possibly incomplete input stream of data and a reference time series, the open-end DTW algorithm computes both the size of the prefix of reference which is best matched by the input, and the dissimilarity between the matched portions. The algorithm was used to provide real-time feedback to neurological patients undergoing motor rehabilitation. We acquired a dataset of multivariate time series from a sensorized long-sleeve shirt which contains 29 strain sensors distributed on the upper limb. Seven typical rehabilitation exercises were recorded in several variations, both correctly and incorrectly executed, and at various speeds, totaling a data set of 840 time series. Nearest-neighbour classifiers were built according to the outputs of open-end DTW alignments and their global counterparts on exercise pairs. The classifiers were also tested on well-known public datasets from heterogeneous domains. Nonparametric tests show that (1) on full time series the two algorithms achieve the same classification accuracy (p-value =0.32); (2) on partial time series, classifiers based on open-end DTW have a far higher accuracy (kappa=0.898 versus kappa=0.447;p<10(-5)); and (3) the prediction of the matched fraction follows closely the ground truth (root mean square <10%). The results hold for the motor rehabilitation and the other datasets tested, as well. The open-end variant of the DTW algorithm is suitable for the classification of truncated quantitative time series, even in the presence of noise. Early recognition and accurate class prediction can be achieved, provided that enough variance is available over the time span of the reference. Therefore, the proposed technique expands the use of DTW to a wider range of applications, such as real-time biofeedback systems.

Systems Biological Approach of Molecular Descriptors Connectivity: Optimal Descriptors for Oral Bioavailability Prediction

PubMed Central

Ahmed, Shiek S. S. J.; Ramakrishnan, V.

2012-01-01

Background Poor oral bioavailability is an important parameter accounting for the failure of the drug candidates. Approximately, 50% of developing drugs fail because of unfavorable oral bioavailability. In silico prediction of oral bioavailability (%F) based on physiochemical properties are highly needed. Although many computational models have been developed to predict oral bioavailability, their accuracy remains low with a significant number of false positives. In this study, we present an oral bioavailability model based on systems biological approach, using a machine learning algorithm coupled with an optimal discriminative set of physiochemical properties. Results The models were developed based on computationally derived 247 physicochemical descriptors from 2279 molecules, among which 969, 605 and 705 molecules were corresponds to oral bioavailability, intestinal absorption (HIA) and caco-2 permeability data set, respectively. The partial least squares discriminate analysis showed 49 descriptors of HIA and 50 descriptors of caco-2 are the major contributing descriptors in classifying into groups. Of these descriptors, 47 descriptors were commonly associated to HIA and caco-2, which suggests to play a vital role in classifying oral bioavailability. To determine the best machine learning algorithm, 21 classifiers were compared using a bioavailability data set of 969 molecules with 47 descriptors. Each molecule in the data set was represented by a set of 47 physiochemical properties with the functional relevance labeled as (+bioavailability/−bioavailability) to indicate good-bioavailability/poor-bioavailability molecules. The best-performing algorithm was the logistic algorithm. The correlation based feature selection (CFS) algorithm was implemented, which confirms that these 47 descriptors are the fundamental descriptors for oral bioavailability prediction. Conclusion The logistic algorithm with 47 selected descriptors correctly predicted the oral bioavailability, with a predictive accuracy of more than 71%. Overall, the method captures the fundamental molecular descriptors, that can be used as an entity to facilitate prediction of oral bioavailability. PMID:22815781

Systems biological approach of molecular descriptors connectivity: optimal descriptors for oral bioavailability prediction.

PubMed

Ahmed, Shiek S S J; Ramakrishnan, V

2012-01-01

Poor oral bioavailability is an important parameter accounting for the failure of the drug candidates. Approximately, 50% of developing drugs fail because of unfavorable oral bioavailability. In silico prediction of oral bioavailability (%F) based on physiochemical properties are highly needed. Although many computational models have been developed to predict oral bioavailability, their accuracy remains low with a significant number of false positives. In this study, we present an oral bioavailability model based on systems biological approach, using a machine learning algorithm coupled with an optimal discriminative set of physiochemical properties. The models were developed based on computationally derived 247 physicochemical descriptors from 2279 molecules, among which 969, 605 and 705 molecules were corresponds to oral bioavailability, intestinal absorption (HIA) and caco-2 permeability data set, respectively. The partial least squares discriminate analysis showed 49 descriptors of HIA and 50 descriptors of caco-2 are the major contributing descriptors in classifying into groups. Of these descriptors, 47 descriptors were commonly associated to HIA and caco-2, which suggests to play a vital role in classifying oral bioavailability. To determine the best machine learning algorithm, 21 classifiers were compared using a bioavailability data set of 969 molecules with 47 descriptors. Each molecule in the data set was represented by a set of 47 physiochemical properties with the functional relevance labeled as (+bioavailability/-bioavailability) to indicate good-bioavailability/poor-bioavailability molecules. The best-performing algorithm was the logistic algorithm. The correlation based feature selection (CFS) algorithm was implemented, which confirms that these 47 descriptors are the fundamental descriptors for oral bioavailability prediction. The logistic algorithm with 47 selected descriptors correctly predicted the oral bioavailability, with a predictive accuracy of more than 71%. Overall, the method captures the fundamental molecular descriptors, that can be used as an entity to facilitate prediction of oral bioavailability.

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

PubMed

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

2008-10-01

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

A fuzzy classifier system for process control

NASA Technical Reports Server (NTRS)

Karr, C. L.; Phillips, J. C.

1994-01-01

A fuzzy classifier system that discovers rules for controlling a mathematical model of a pH titration system was developed by researchers at the U.S. Bureau of Mines (USBM). Fuzzy classifier systems successfully combine the strengths of learning classifier systems and fuzzy logic controllers. Learning classifier systems resemble familiar production rule-based systems, but they represent their IF-THEN rules by strings of characters rather than in the traditional linguistic terms. Fuzzy logic is a tool that allows for the incorporation of abstract concepts into rule based-systems, thereby allowing the rules to resemble the familiar 'rules-of-thumb' commonly used by humans when solving difficult process control and reasoning problems. Like learning classifier systems, fuzzy classifier systems employ a genetic algorithm to explore and sample new rules for manipulating the problem environment. Like fuzzy logic controllers, fuzzy classifier systems encapsulate knowledge in the form of production rules. The results presented in this paper demonstrate the ability of fuzzy classifier systems to generate a fuzzy logic-based process control system.

Phase retrieval based wavefront sensing experimental implementation and wavefront sensing accuracy calibration

NASA Astrophysics Data System (ADS)

Mao, Heng; Wang, Xiao; Zhao, Dazun

2009-05-01

As a wavefront sensing (WFS) tool, Baseline algorithm, which is classified as the iterative-transform algorithm of phase retrieval, estimates the phase distribution at pupil from some known PSFs at defocus planes. By using multiple phase diversities and appropriate phase unwrapping methods, this algorithm can accomplish reliable unique solution and high dynamic phase measurement. In the paper, a Baseline algorithm based wavefront sensing experiment with modification of phase unwrapping has been implemented, and corresponding Graphical User Interfaces (GUI) software has also been given. The adaptability and repeatability of Baseline algorithm have been validated in experiments. Moreover, referring to the ZYGO interferometric results, the WFS accuracy of this algorithm has been exactly calibrated.

A native Bayesian classifier based routing protocol for VANETS

NASA Astrophysics Data System (ADS)

Bao, Zhenshan; Zhou, Keqin; Zhang, Wenbo; Gong, Xiaolei

2016-12-01

Geographic routing protocols are one of the most hot research areas in VANET (Vehicular Ad-hoc Network). However, there are few routing protocols can take both the transmission efficient and the usage of ratio into account. As we have noticed, different messages in VANET may ask different quality of service. So we raised a Native Bayesian Classifier based routing protocol (Naive Bayesian Classifier-Greedy, NBC-Greedy), which can classify and transmit different messages by its emergency degree. As a result, we can balance the transmission efficient and the usage of ratio with this protocol. Based on Matlab simulation, we can draw a conclusion that NBC-Greedy is more efficient and stable than LR-Greedy and GPSR.

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.

Preprocessing and meta-classification for brain-computer interfaces.

PubMed

Hammon, Paul S; de Sa, Virginia R

2007-03-01

A brain-computer interface (BCI) is a system which allows direct translation of brain states into actions, bypassing the usual muscular pathways. A BCI system works by extracting user brain signals, applying machine learning algorithms to classify the user's brain state, and performing a computer-controlled action. Our goal is to improve brain state classification. Perhaps the most obvious way to improve classification performance is the selection of an advanced learning algorithm. However, it is now well known in the BCI community that careful selection of preprocessing steps is crucial to the success of any classification scheme. Furthermore, recent work indicates that combining the output of multiple classifiers (meta-classification) leads to improved classification rates relative to single classifiers (Dornhege et al., 2004). In this paper, we develop an automated approach which systematically analyzes the relative contributions of different preprocessing and meta-classification approaches. We apply this procedure to three data sets drawn from BCI Competition 2003 (Blankertz et al., 2004) and BCI Competition III (Blankertz et al., 2006), each of which exhibit very different characteristics. Our final classification results compare favorably with those from past BCI competitions. Additionally, we analyze the relative contributions of individual preprocessing and meta-classification choices and discuss which types of BCI data benefit most from specific algorithms.

Document-Level Classification of CT Pulmonary Angiography Reports based on an Extension of the ConText Algorithm

PubMed Central

Chapman, Brian E.; Lee, Sean; Kang, Hyunseok Peter; Chapman, Wendy W.

2011-01-01

In this paper we describe an application called peFinder for document-level classification of CT pulmonary angiography reports. peFinder is based on a generalized version of the ConText algorithm, a simple text processing algorithm for identifying features in clinical report documents. peFinder was used to answer questions about the disease state (pulmonary emboli present or absent), the certainty state of the diagnosis (uncertainty present or absent), the temporal state of an identified pulmonary embolus (acute or chronic), and the technical quality state of the exam (diagnostic or not diagnostic). Gold standard answers for each question were determined from the consensus classifications of three human annotators. peFinder results were compared to naive Bayes’ classifiers using unigrams and bigrams. The sensitivities (and positive predictive values) for peFinder were 0.98(0.83), 0.86(0.96), 0.94(0.93), and 0.60(0.90) for disease state, quality state, certainty state, and temporal state respectively, compared to 0.68(0.77), 0.67(0.87), 0.62(0.82), and 0.04(0.25) for the naive Bayes’ classifier using unigrams, and 0.75(0.79), 0.52(0.69), 0.59(0.84), and 0.04(0.25) for the naive Bayes’ classifier using bigrams. PMID:21459155

A three-parameter model for classifying anurans into four genera based on advertisement calls.

PubMed

Gingras, Bruno; Fitch, William Tecumseh

2013-01-01

The vocalizations of anurans are innate in structure and may therefore contain indicators of phylogenetic history. Thus, advertisement calls of species which are more closely related phylogenetically are predicted to be more similar than those of distant species. This hypothesis was evaluated by comparing several widely used machine-learning algorithms. Recordings of advertisement calls from 142 species belonging to four genera were analyzed. A logistic regression model, using mean values for dominant frequency, coefficient of variation of root-mean square energy, and spectral flux, correctly classified advertisement calls with regard to genus with an accuracy above 70%. Similar accuracy rates were obtained using these parameters with a support vector machine model, a K-nearest neighbor algorithm, and a multivariate Gaussian distribution classifier, whereas a Gaussian mixture model performed slightly worse. In contrast, models based on mel-frequency cepstral coefficients did not fare as well. Comparable accuracy levels were obtained on out-of-sample recordings from 52 of the 142 original species. The results suggest that a combination of low-level acoustic attributes is sufficient to discriminate efficiently between the vocalizations of these four genera, thus supporting the initial premise and validating the use of high-throughput algorithms on animal vocalizations to evaluate phylogenetic hypotheses.

Combining classifiers using their receiver operating characteristics and maximum likelihood estimation.

PubMed

Haker, Steven; Wells, William M; Warfield, Simon K; Talos, Ion-Florin; Bhagwat, Jui G; Goldberg-Zimring, Daniel; Mian, Asim; Ohno-Machado, Lucila; Zou, Kelly H

2005-01-01

In any medical domain, it is common to have more than one test (classifier) to diagnose a disease. In image analysis, for example, there is often more than one reader or more than one algorithm applied to a certain data set. Combining of classifiers is often helpful, but determining the way in which classifiers should be combined is not trivial. Standard strategies are based on learning classifier combination functions from data. We describe a simple strategy to combine results from classifiers that have not been applied to a common data set, and therefore can not undergo this type of joint training. The strategy, which assumes conditional independence of classifiers, is based on the calculation of a combined Receiver Operating Characteristic (ROC) curve, using maximum likelihood analysis to determine a combination rule for each ROC operating point. We offer some insights into the use of ROC analysis in the field of medical imaging.

Combining Classifiers Using Their Receiver Operating Characteristics and Maximum Likelihood Estimation*

PubMed Central

Haker, Steven; Wells, William M.; Warfield, Simon K.; Talos, Ion-Florin; Bhagwat, Jui G.; Goldberg-Zimring, Daniel; Mian, Asim; Ohno-Machado, Lucila; Zou, Kelly H.

2010-01-01

In any medical domain, it is common to have more than one test (classifier) to diagnose a disease. In image analysis, for example, there is often more than one reader or more than one algorithm applied to a certain data set. Combining of classifiers is often helpful, but determining the way in which classifiers should be combined is not trivial. Standard strategies are based on learning classifier combination functions from data. We describe a simple strategy to combine results from classifiers that have not been applied to a common data set, and therefore can not undergo this type of joint training. The strategy, which assumes conditional independence of classifiers, is based on the calculation of a combined Receiver Operating Characteristic (ROC) curve, using maximum likelihood analysis to determine a combination rule for each ROC operating point. We offer some insights into the use of ROC analysis in the field of medical imaging. PMID:16685884

Comparison of the MPP with other supercomputers for LANDSAT data processing

NASA Technical Reports Server (NTRS)

Ozga, Martin

1987-01-01

The massively parallel processor is compared to the CRAY X-MP and the CYBER-205 for LANDSAT data processing. The maximum likelihood classification algorithm is the basis for comparison since this algorithm is simple to implement and vectorizes very well. The algorithm was implemented on all three machines and tested by classifying the same full scene of LANDSAT multispectral scan data. Timings are compared as well as features of the machines and available software.

Determination of colonoscopy indication from administrative claims data.

PubMed

Ko, Cynthia W; Dominitz, Jason A; Neradilek, Moni; Polissar, Nayak; Green, Pam; Kreuter, William; Baldwin, Laura-Mae

2014-04-01

Colonoscopy outcomes, such as polyp detection or complication rates, may differ by procedure indication. To develop methods to classify colonoscopy indications from administrative data, facilitating study of colonoscopy quality and outcomes. We linked 14,844 colonoscopy reports from the Clinical Outcomes Research Initiative, a national repository of endoscopic reports, to the corresponding Medicare Carrier and Outpatient File claims. Colonoscopy indication was determined from the procedure reports. We developed algorithms using classification and regression trees and linear discriminant analysis (LDA) to classify colonoscopy indication. Predictor variables included ICD-9CM and CPT/HCPCS codes present on the colonoscopy claim or in the 12 months prior, patient demographics, and site of colonoscopy service. Algorithms were developed on a training set of 7515 procedures, then validated using a test set of 7329 procedures. Sensitivity was lowest for identifying average-risk screening colonoscopies, varying between 55% and 86% for the different algorithms, but specificity for this indication was consistently over 95%. Sensitivity for diagnostic colonoscopy varied between 77% and 89%, with specificity between 55% and 87%. Algorithms with classification and regression trees with 7 variables or LDA with 10 variables had similar overall accuracy, and generally lower accuracy than the algorithm using LDA with 30 variables. Algorithms using Medicare claims data have moderate sensitivity and specificity for colonoscopy indication, and will be useful for studying colonoscopy quality in this population. Further validation may be needed before use in alternative populations.

Detection of algorithmic trading

NASA Astrophysics Data System (ADS)

Bogoev, Dimitar; Karam, Arzé

2017-10-01

We develop a new approach to reflect the behavior of algorithmic traders. Specifically, we provide an analytical and tractable way to infer patterns of quote volatility and price momentum consistent with different types of strategies employed by algorithmic traders, and we propose two ratios to quantify these patterns. Quote volatility ratio is based on the rate of oscillation of the best ask and best bid quotes over an extremely short period of time; whereas price momentum ratio is based on identifying patterns of rapid upward or downward movement in prices. The two ratios are evaluated across several asset classes. We further run a two-stage Artificial Neural Network experiment on the quote volatility ratio; the first stage is used to detect the quote volatility patterns resulting from algorithmic activity, while the second is used to validate the quality of signal detection provided by our measure.

System and method for resolving gamma-ray spectra

DOEpatents

Gentile, Charles A.; Perry, Jason; Langish, Stephen W.; Silber, Kenneth; Davis, William M.; Mastrovito, Dana

2010-05-04

A system for identifying radionuclide emissions is described. The system includes at least one processor for processing output signals from a radionuclide detecting device, at least one training algorithm run by the at least one processor for analyzing data derived from at least one set of known sample data from the output signals, at least one classification algorithm derived from the training algorithm for classifying unknown sample data, wherein the at least one training algorithm analyzes the at least one sample data set to derive at least one rule used by said classification algorithm for identifying at least one radionuclide emission detected by the detecting device.

Detection of chewing from piezoelectric film sensor signals using ensemble classifiers.

PubMed

Farooq, Muhammad; Sazonov, Edward

2016-08-01

Selection and use of pattern recognition algorithms is application dependent. In this work, we explored the use of several ensembles of weak classifiers to classify signals captured from a wearable sensor system to detect food intake based on chewing. Three sensor signals (Piezoelectric sensor, accelerometer, and hand to mouth gesture) were collected from 12 subjects in free-living conditions for 24 hrs. Sensor signals were divided into 10 seconds epochs and for each epoch combination of time and frequency domain features were computed. In this work, we present a comparison of three different ensemble techniques: boosting (AdaBoost), bootstrap aggregation (bagging) and stacking, each trained with 3 different weak classifiers (Decision Trees, Linear Discriminant Analysis (LDA) and Logistic Regression). Type of feature normalization used can also impact the classification results. For each ensemble method, three feature normalization techniques: (no-normalization, z-score normalization, and minmax normalization) were tested. A 12 fold cross-validation scheme was used to evaluate the performance of each model where the performance was evaluated in terms of precision, recall, and accuracy. Best results achieved here show an improvement of about 4% over our previous algorithms.

Development and Testing of Data Mining Algorithms for Earth Observation

NASA Technical Reports Server (NTRS)

Glymour, Clark

2005-01-01

The new algorithms developed under this project included a principled procedure for classification of objects, events or circumstances according to a target variable when a very large number of potential predictor variables is available but the number of cases that can be used for training a classifier is relatively small. These "high dimensional" problems require finding a minimal set of variables -called the Markov Blanket-- sufficient for predicting the value of the target variable. An algorithm, the Markov Blanket Fan Search, was developed, implemented and tested on both simulated and real data in conjunction with a graphical model classifier, which was also implemented. Another algorithm developed and implemented in TETRAD IV for time series elaborated on work by C. Granger and N. Swanson, which in turn exploited some of our earlier work. The algorithms in question learn a linear time series model from data. Given such a time series, the simultaneous residual covariances, after factoring out time dependencies, may provide information about causal processes that occur more rapidly than the time series representation allow, so called simultaneous or contemporaneous causal processes. Working with A. Monetta, a graduate student from Italy, we produced the correct statistics for estimating the contemporaneous causal structure from time series data using the TETRAD IV suite of algorithms. Two economists, David Bessler and Kevin Hoover, have independently published applications using TETRAD style algorithms to the same purpose. These implementations and algorithmic developments were separately used in two kinds of studies of climate data: Short time series of geographically proximate climate variables predicting agricultural effects in California, and longer duration climate measurements of temperature teleconnections.

Results of the 2016 International Skin Imaging Collaboration International Symposium on Biomedical Imaging challenge: Comparison of the accuracy of computer algorithms to dermatologists for the diagnosis of melanoma from dermoscopic images.

PubMed

Marchetti, Michael A; Codella, Noel C F; Dusza, Stephen W; Gutman, David A; Helba, Brian; Kalloo, Aadi; Mishra, Nabin; Carrera, Cristina; Celebi, M Emre; DeFazio, Jennifer L; Jaimes, Natalia; Marghoob, Ashfaq A; Quigley, Elizabeth; Scope, Alon; Yélamos, Oriol; Halpern, Allan C

2018-02-01

Computer vision may aid in melanoma detection. We sought to compare melanoma diagnostic accuracy of computer algorithms to dermatologists using dermoscopic images. We conducted a cross-sectional study using 100 randomly selected dermoscopic images (50 melanomas, 44 nevi, and 6 lentigines) from an international computer vision melanoma challenge dataset (n = 379), along with individual algorithm results from 25 teams. We used 5 methods (nonlearned and machine learning) to combine individual automated predictions into "fusion" algorithms. In a companion study, 8 dermatologists classified the lesions in the 100 images as either benign or malignant. The average sensitivity and specificity of dermatologists in classification was 82% and 59%. At 82% sensitivity, dermatologist specificity was similar to the top challenge algorithm (59% vs. 62%, P = .68) but lower than the best-performing fusion algorithm (59% vs. 76%, P = .02). Receiver operating characteristic area of the top fusion algorithm was greater than the mean receiver operating characteristic area of dermatologists (0.86 vs. 0.71, P = .001). The dataset lacked the full spectrum of skin lesions encountered in clinical practice, particularly banal lesions. Readers and algorithms were not provided clinical data (eg, age or lesion history/symptoms). Results obtained using our study design cannot be extrapolated to clinical practice. Deep learning computer vision systems classified melanoma dermoscopy images with accuracy that exceeded some but not all dermatologists. Copyright © 2017 American Academy of Dermatology, Inc. Published by Elsevier Inc. All rights reserved.

Emerging from the database shadows: characterizing undocumented immigrants in a large cohort of HIV-infected persons.

PubMed

Ross, Jonathan; Hanna, David B; Felsen, Uriel R; Cunningham, Chinazo O; Patel, Viraj V

2017-12-01

Little is known about how HIV affects undocumented immigrants despite social and structural factors that may place them at risk of poor HIV outcomes. Our understanding of the clinical epidemiology of HIV-infected undocumented immigrants is limited by the challenges of determining undocumented immigration status in large data sets. We developed an algorithm to predict undocumented status using social security number (SSN) and insurance data. We retrospectively applied this algorithm to a cohort of HIV-infected adults receiving care at a large urban healthcare system who attended at least one HIV-related outpatient visit from 1997 to 2013, classifying patients as "screened undocumented" or "documented". We then reviewed the medical records of screened undocumented patients, classifying those whose records contained evidence of undocumented status as "undocumented per medical chart" (charted undocumented). Bivariate measures of association were used to identify demographic and clinical characteristics associated with undocumented immigrant status. Of 7593 patients, 205 (2.7%) were classified as undocumented by the algorithm. Compared to documented patients, undocumented patients were younger at entry to care (mean 38.5 years vs. 40.6 years, p < 0.05), less likely to be female (33.2% vs. 43.1%, p < 0.01), less likely to report injection drug use as their primary HIV risk factor (3.4% vs. 18.0%, p < 0.001), and had lower median CD4 count at entry to care (288 vs. 339 cells/mm 3 , p < 0.01). After medical record review, we re-classified 104 patients (50.7%) as charted undocumented. Demographic and clinical characteristics of charted undocumented did not differ substantially from screened undocumented. Our algorithm allowed us to identify and clinically characterize undocumented immigrants within an HIV-infected population, though it overestimated the prevalence of patients who were undocumented.

Artificial intelligence techniques applied to the development of a decision–support system for diagnosing celiac disease

PubMed Central

Tenório, Josceli Maria; Hummel, Anderson Diniz; Cohrs, Frederico Molina; Sdepanian, Vera Lucia; Pisa, Ivan Torres; de Fátima Marin, Heimar

2013-01-01

Background Celiac disease (CD) is a difficult-to-diagnose condition because of its multiple clinical presentations and symptoms shared with other diseases. Gold-standard diagnostic confirmation of suspected CD is achieved by biopsying the small intestine. Objective To develop a clinical decision–support system (CDSS) integrated with an automated classifier to recognize CD cases, by selecting from experimental models developed using intelligence artificial techniques. Methods A web-based system was designed for constructing a retrospective database that included 178 clinical cases for training. Tests were run on 270 automated classifiers available in Weka 3.6.1 using five artificial intelligence techniques, namely decision trees, Bayesian inference, k-nearest neighbor algorithm, support vector machines and artificial neural networks. The parameters evaluated were accuracy, sensitivity, specificity and area under the ROC curve (AUC). AUC was used as a criterion for selecting the CDSS algorithm. A testing database was constructed including 38 clinical CD cases for CDSS evaluation. The diagnoses suggested by CDSS were compared with those made by physicians during patient consultations. Results The most accurate method during the training phase was the averaged one-dependence estimator (AODE) algorithm (a Bayesian classifier), which showed accuracy 80.0%, sensitivity 0.78, specificity 0.80 and AUC 0.84. This classifier was integrated into the web-based decision–support system. The gold-standard validation of CDSS achieved accuracy of 84.2% and k = 0.68 (p < 0.0001) with good agreement. The same accuracy was achieved in the comparison between the physician’s diagnostic impression and the gold standard k = 0. 64 (p < 0.0001). There was moderate agreement between the physician’s diagnostic impression and CDSS k = 0.46 (p = 0.0008). Conclusions The study results suggest that CDSS could be used to help in diagnosing CD, since the algorithm tested achieved excellent accuracy in differentiating possible positive from negative CD diagnoses. This study may contribute towards developing of a computer-assisted environment to support CD diagnosis. PMID:21917512

Comparison Of Semi-Automatic And Automatic Slick Detection Algorithms For Jiyeh Power Station Oil Spill, Lebanon

NASA Astrophysics Data System (ADS)

Osmanoglu, B.; Ozkan, C.; Sunar, F.

2013-10-01

After air strikes on July 14 and 15, 2006 the Jiyeh Power Station started leaking oil into the eastern Mediterranean Sea. The power station is located about 30 km south of Beirut and the slick covered about 170 km of coastline threatening the neighboring countries Turkey and Cyprus. Due to the ongoing conflict between Israel and Lebanon, cleaning efforts could not start immediately resulting in 12 000 to 15 000 tons of fuel oil leaking into the sea. In this paper we compare results from automatic and semi-automatic slick detection algorithms. The automatic detection method combines the probabilities calculated for each pixel from each image to obtain a joint probability, minimizing the adverse effects of atmosphere on oil spill detection. The method can readily utilize X-, C- and L-band data where available. Furthermore wind and wave speed observations can be used for a more accurate analysis. For this study, we utilize Envisat ASAR ScanSAR data. A probability map is generated based on the radar backscatter, effect of wind and dampening value. The semi-automatic algorithm is based on supervised classification. As a classifier, Artificial Neural Network Multilayer Perceptron (ANN MLP) classifier is used since it is more flexible and efficient than conventional maximum likelihood classifier for multisource and multi-temporal data. The learning algorithm for ANN MLP is chosen as the Levenberg-Marquardt (LM). Training and test data for supervised classification are composed from the textural information created from SAR images. This approach is semiautomatic because tuning the parameters of classifier and composing training data need a human interaction. We point out the similarities and differences between the two methods and their results as well as underlining their advantages and disadvantages. Due to the lack of ground truth data, we compare obtained results to each other, as well as other published oil slick area assessments.

Artificial intelligence techniques applied to the development of a decision-support system for diagnosing celiac disease.

PubMed

Tenório, Josceli Maria; Hummel, Anderson Diniz; Cohrs, Frederico Molina; Sdepanian, Vera Lucia; Pisa, Ivan Torres; de Fátima Marin, Heimar

2011-11-01

Celiac disease (CD) is a difficult-to-diagnose condition because of its multiple clinical presentations and symptoms shared with other diseases. Gold-standard diagnostic confirmation of suspected CD is achieved by biopsying the small intestine. To develop a clinical decision-support system (CDSS) integrated with an automated classifier to recognize CD cases, by selecting from experimental models developed using intelligence artificial techniques. A web-based system was designed for constructing a retrospective database that included 178 clinical cases for training. Tests were run on 270 automated classifiers available in Weka 3.6.1 using five artificial intelligence techniques, namely decision trees, Bayesian inference, k-nearest neighbor algorithm, support vector machines and artificial neural networks. The parameters evaluated were accuracy, sensitivity, specificity and area under the ROC curve (AUC). AUC was used as a criterion for selecting the CDSS algorithm. A testing database was constructed including 38 clinical CD cases for CDSS evaluation. The diagnoses suggested by CDSS were compared with those made by physicians during patient consultations. The most accurate method during the training phase was the averaged one-dependence estimator (AODE) algorithm (a Bayesian classifier), which showed accuracy 80.0%, sensitivity 0.78, specificity 0.80 and AUC 0.84. This classifier was integrated into the web-based decision-support system. The gold-standard validation of CDSS achieved accuracy of 84.2% and k=0.68 (p<0.0001) with good agreement. The same accuracy was achieved in the comparison between the physician's diagnostic impression and the gold standard k=0. 64 (p<0.0001). There was moderate agreement between the physician's diagnostic impression and CDSS k=0.46 (p=0.0008). The study results suggest that CDSS could be used to help in diagnosing CD, since the algorithm tested achieved excellent accuracy in differentiating possible positive from negative CD diagnoses. This study may contribute towards developing of a computer-assisted environment to support CD diagnosis. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

Development and Validation of Various Phenotyping Algorithms for Diabetes Mellitus Using Data from Electronic Health Records.

PubMed

Esteban, Santiago; Rodríguez Tablado, Manuel; Peper, Francisco; Mahumud, Yamila S; Ricci, Ricardo I; Kopitowski, Karin; Terrasa, Sergio

2017-01-01

Precision medicine requires extremely large samples. Electronic health records (EHR) are thought to be a cost-effective source of data for that purpose. Phenotyping algorithms help reduce classification errors, making EHR a more reliable source of information for research. Four algorithm development strategies for classifying patients according to their diabetes status (diabetics; non-diabetics; inconclusive) were tested (one codes-only algorithm; one boolean algorithm, four statistical learning algorithms and six stacked generalization meta-learners). The best performing algorithms within each strategy were tested on the validation set. The stacked generalization algorithm yielded the highest Kappa coefficient value in the validation set (0.95 95% CI 0.91, 0.98). The implementation of these algorithms allows for the exploitation of data from thousands of patients accurately, greatly reducing the costs of constructing retrospective cohorts for research.

A Ternary Brain-Computer Interface Based on Single-Trial Readiness Potentials of Self-initiated Fine Movements: A Diversified Classification Scheme

PubMed Central

Abou Zeid, Elias; Rezazadeh Sereshkeh, Alborz; Schultz, Benjamin; Chau, Tom

2017-01-01

In recent years, the readiness potential (RP), a type of pre-movement neural activity, has been investigated for asynchronous electroencephalogram (EEG)-based brain-computer interfaces (BCIs). Since the RP is attenuated for involuntary movements, a BCI driven by RP alone could facilitate intentional control amid a plethora of unintentional movements. Previous studies have mainly attempted binary single-trial classification of RP. An RP-based BCI with three or more states would expand the options for functional control. Here, we propose a ternary BCI based on single-trial RPs. This BCI classifies amongst an idle state, a left hand and a right hand self-initiated fine movement. A pipeline of spatio-temporal filtering with per participant parameter optimization was used for feature extraction. The ternary classification was decomposed into binary classifications using a decision-directed acyclic graph (DDAG). For each class pair in the DDAG structure, an ordered diversified classifier system (ODCS-DDAG) was used to select the best among various classification algorithms or to combine the results of different classification algorithms. Using EEG data from 14 participants performing self-initiated left or right key presses, punctuated with rest periods, we compared the performance of ODCS-DDAG to a ternary classifier and four popular multiclass decomposition methods using only a single classification algorithm. ODCS-DDAG had the highest performance (0.769 Cohen's Kappa score) and was significantly better than the ternary classifier and two of the four multiclass decomposition methods. Our work supports further study of RP-based BCI for intuitive asynchronous environmental control or augmentative communication. PMID:28596725

Detection of fruit-fly infestation in olives using X-ray imaging: Algorithm development and prospects

USDA-ARS?s Scientific Manuscript database

An algorithm using a Bayesian classifier was developed to automatically detect olive fruit fly infestations in x-ray images of olives. The data set consisted of 249 olives with various degrees of infestation and 161 non-infested olives. Each olive was x-rayed on film and digital images were acquired...

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.

Self-adaptive MOEA feature selection for classification of bankruptcy prediction data.

PubMed

Gaspar-Cunha, A; Recio, G; Costa, L; Estébanez, C

2014-01-01

Bankruptcy prediction is a vast area of finance and accounting whose importance lies in the relevance for creditors and investors in evaluating the likelihood of getting into bankrupt. As companies become complex, they develop sophisticated schemes to hide their real situation. In turn, making an estimation of the credit risks associated with counterparts or predicting bankruptcy becomes harder. Evolutionary algorithms have shown to be an excellent tool to deal with complex problems in finances and economics where a large number of irrelevant features are involved. This paper provides a methodology for feature selection in classification of bankruptcy data sets using an evolutionary multiobjective approach that simultaneously minimise the number of features and maximise the classifier quality measure (e.g., accuracy). The proposed methodology makes use of self-adaptation by applying the feature selection algorithm while simultaneously optimising the parameters of the classifier used. The methodology was applied to four different sets of data. The obtained results showed the utility of using the self-adaptation of the classifier.

Genetic programming based ensemble system for microarray data classification.

PubMed

Liu, Kun-Hong; Tong, Muchenxuan; Xie, Shu-Tong; Yee Ng, Vincent To

2015-01-01

Recently, more and more machine learning techniques have been applied to microarray data analysis. The aim of this study is to propose a genetic programming (GP) based new ensemble system (named GPES), which can be used to effectively classify different types of cancers. Decision trees are deployed as base classifiers in this ensemble framework with three operators: Min, Max, and Average. Each individual of the GP is an ensemble system, and they become more and more accurate in the evolutionary process. The feature selection technique and balanced subsampling technique are applied to increase the diversity in each ensemble system. The final ensemble committee is selected by a forward search algorithm, which is shown to be capable of fitting data automatically. The performance of GPES is evaluated using five binary class and six multiclass microarray datasets, and results show that the algorithm can achieve better results in most cases compared with some other ensemble systems. By using elaborate base classifiers or applying other sampling techniques, the performance of GPES may be further improved.

Genetic Programming Based Ensemble System for Microarray Data Classification

PubMed Central

Liu, Kun-Hong; Tong, Muchenxuan; Xie, Shu-Tong; Yee Ng, Vincent To

2015-01-01

Recently, more and more machine learning techniques have been applied to microarray data analysis. The aim of this study is to propose a genetic programming (GP) based new ensemble system (named GPES), which can be used to effectively classify different types of cancers. Decision trees are deployed as base classifiers in this ensemble framework with three operators: Min, Max, and Average. Each individual of the GP is an ensemble system, and they become more and more accurate in the evolutionary process. The feature selection technique and balanced subsampling technique are applied to increase the diversity in each ensemble system. The final ensemble committee is selected by a forward search algorithm, which is shown to be capable of fitting data automatically. The performance of GPES is evaluated using five binary class and six multiclass microarray datasets, and results show that the algorithm can achieve better results in most cases compared with some other ensemble systems. By using elaborate base classifiers or applying other sampling techniques, the performance of GPES may be further improved. PMID:25810748

Approach to explosive hazard detection using sensor fusion and multiple kernel learning with downward-looking GPR and EMI sensor data

NASA Astrophysics Data System (ADS)

Pinar, Anthony; Masarik, Matthew; Havens, Timothy C.; Burns, Joseph; Thelen, Brian; Becker, John

2015-05-01

This paper explores the effectiveness of an anomaly detection algorithm for downward-looking ground penetrating radar (GPR) and electromagnetic inductance (EMI) data. Threat detection with GPR is challenged by high responses to non-target/clutter objects, leading to a large number of false alarms (FAs), and since the responses of target and clutter signatures are so similar, classifier design is not trivial. We suggest a method based on a Run Packing (RP) algorithm to fuse GPR and EMI data into a composite confidence map to improve detection as measured by the area-under-ROC (NAUC) metric. We examine the value of a multiple kernel learning (MKL) support vector machine (SVM) classifier using image features such as histogram of oriented gradients (HOG), local binary patterns (LBP), and local statistics. Experimental results on government furnished data show that use of our proposed fusion and classification methods improves the NAUC when compared with the results from individual sensors and a single kernel SVM classifier.

Optimizing classification performance in an object-based very-high-resolution land use-land cover urban application

NASA Astrophysics Data System (ADS)

Georganos, Stefanos; Grippa, Tais; Vanhuysse, Sabine; Lennert, Moritz; Shimoni, Michal; Wolff, Eléonore

2017-10-01

This study evaluates the impact of three Feature Selection (FS) algorithms in an Object Based Image Analysis (OBIA) framework for Very-High-Resolution (VHR) Land Use-Land Cover (LULC) classification. The three selected FS algorithms, Correlation Based Selection (CFS), Mean Decrease in Accuracy (MDA) and Random Forest (RF) based Recursive Feature Elimination (RFE), were tested on Support Vector Machine (SVM), K-Nearest Neighbor, and Random Forest (RF) classifiers. The results demonstrate that the accuracy of SVM and KNN classifiers are the most sensitive to FS. The RF appeared to be more robust to high dimensionality, although a significant increase in accuracy was found by using the RFE method. In terms of classification accuracy, SVM performed the best using FS, followed by RF and KNN. Finally, only a small number of features is needed to achieve the highest performance using each classifier. This study emphasizes the benefits of rigorous FS for maximizing performance, as well as for minimizing model complexity and interpretation.

Adaptive classifier for steel strip surface defects

NASA Astrophysics Data System (ADS)

Jiang, Mingming; Li, Guangyao; Xie, Li; Xiao, Mang; Yi, Li

2017-01-01

Surface defects detection system has been receiving increased attention as its precision, speed and less cost. One of the most challenges is reacting to accuracy deterioration with time as aged equipment and changed processes. These variables will make a tiny change to the real world model but a big impact on the classification result. In this paper, we propose a new adaptive classifier with a Bayes kernel (BYEC) which update the model with small sample to it adaptive for accuracy deterioration. Firstly, abundant features were introduced to cover lots of information about the defects. Secondly, we constructed a series of SVMs with the random subspace of the features. Then, a Bayes classifier was trained as an evolutionary kernel to fuse the results from base SVMs. Finally, we proposed the method to update the Bayes evolutionary kernel. The proposed algorithm is experimentally compared with different algorithms, experimental results demonstrate that the proposed method can be updated with small sample and fit the changed model well. Robustness, low requirement for samples and adaptive is presented in the experiment.

Apply lightweight recognition algorithms in optical music recognition

NASA Astrophysics Data System (ADS)

Pham, Viet-Khoi; Nguyen, Hai-Dang; Nguyen-Khac, Tung-Anh; Tran, Minh-Triet

2015-02-01

The problems of digitalization and transformation of musical scores into machine-readable format are necessary to be solved since they help people to enjoy music, to learn music, to conserve music sheets, and even to assist music composers. However, the results of existing methods still require improvements for higher accuracy. Therefore, the authors propose lightweight algorithms for Optical Music Recognition to help people to recognize and automatically play musical scores. In our proposal, after removing staff lines and extracting symbols, each music symbol is represented as a grid of identical M ∗ N cells, and the features are extracted and classified with multiple lightweight SVM classifiers. Through experiments, the authors find that the size of 10 ∗ 12 cells yields the highest precision value. Experimental results on the dataset consisting of 4929 music symbols taken from 18 modern music sheets in the Synthetic Score Database show that our proposed method is able to classify printed musical scores with accuracy up to 99.56%.

Self-Adaptive MOEA Feature Selection for Classification of Bankruptcy Prediction Data

PubMed Central

Gaspar-Cunha, A.; Recio, G.; Costa, L.; Estébanez, C.

2014-01-01

Bankruptcy prediction is a vast area of finance and accounting whose importance lies in the relevance for creditors and investors in evaluating the likelihood of getting into bankrupt. As companies become complex, they develop sophisticated schemes to hide their real situation. In turn, making an estimation of the credit risks associated with counterparts or predicting bankruptcy becomes harder. Evolutionary algorithms have shown to be an excellent tool to deal with complex problems in finances and economics where a large number of irrelevant features are involved. This paper provides a methodology for feature selection in classification of bankruptcy data sets using an evolutionary multiobjective approach that simultaneously minimise the number of features and maximise the classifier quality measure (e.g., accuracy). The proposed methodology makes use of self-adaptation by applying the feature selection algorithm while simultaneously optimising the parameters of the classifier used. The methodology was applied to four different sets of data. The obtained results showed the utility of using the self-adaptation of the classifier. PMID:24707201

A Hybrid Classification System for Heart Disease Diagnosis Based on the RFRS Method.

PubMed

Liu, Xiao; Wang, Xiaoli; Su, Qiang; Zhang, Mo; Zhu, Yanhong; Wang, Qiugen; Wang, Qian

2017-01-01

Heart disease is one of the most common diseases in the world. The objective of this study is to aid the diagnosis of heart disease using a hybrid classification system based on the ReliefF and Rough Set (RFRS) method. The proposed system contains two subsystems: the RFRS feature selection system and a classification system with an ensemble classifier. The first system includes three stages: (i) data discretization, (ii) feature extraction using the ReliefF algorithm, and (iii) feature reduction using the heuristic Rough Set reduction algorithm that we developed. In the second system, an ensemble classifier is proposed based on the C4.5 classifier. The Statlog (Heart) dataset, obtained from the UCI database, was used for experiments. A maximum classification accuracy of 92.59% was achieved according to a jackknife cross-validation scheme. The results demonstrate that the performance of the proposed system is superior to the performances of previously reported classification techniques.

Tests of a Semi-Analytical Case 1 and Gelbstoff Case 2 SeaWiFS Algorithm with a Global Data Set

NASA Technical Reports Server (NTRS)

Carder, Kendall L.; Hawes, Steve K.; Lee, Zhongping

1997-01-01

A semi-analytical algorithm was tested with a total of 733 points of either unpackaged or packaged-pigment data, with corresponding algorithm parameters for each data type. The 'unpackaged' type consisted of data sets that were generally consistent with the Case 1 CZCS algorithm and other well calibrated data sets. The 'packaged' type consisted of data sets apparently containing somewhat more packaged pigments, requiring modification of the absorption parameters of the model consistent with the CalCOFI study area. This resulted in two equally divided data sets. A more thorough scrutiny of these and other data sets using a semianalytical model requires improved knowledge of the phytoplankton and gelbstoff of the specific environment studied. Since the semi-analytical algorithm is dependent upon 4 spectral channels including the 412 nm channel, while most other algorithms are not, a means of testing data sets for consistency was sought. A numerical filter was developed to classify data sets into the above classes. The filter uses reflectance ratios, which can be determined from space. The sensitivity of such numerical filters to measurement resulting from atmospheric correction and sensor noise errors requires further study. The semi-analytical algorithm performed superbly on each of the data sets after classification, resulting in RMS1 errors of 0.107 and 0.121, respectively, for the unpackaged and packaged data-set classes, with little bias and slopes near 1.0. In combination, the RMS1 performance was 0.114. While these numbers appear rather sterling, one must bear in mind what mis-classification does to the results. Using an average or compromise parameterization on the modified global data set yielded an RMS1 error of 0.171, while using the unpackaged parameterization on the global evaluation data set yielded an RMS1 error of 0.284. So, without classification, the algorithm performs better globally using the average parameters than it does using the unpackaged parameters. Finally, the effects of even more extreme pigment packaging must be examined in order to improve algorithm performance at high latitudes. Note, however, that the North Sea and Mississippi River plume studies contributed data to the packaged and unpackaged classess, respectively, with little effect on algorithm performance. This suggests that gelbstoff-rich Case 2 waters do not seriously degrade performance of the semi-analytical algorithm.

Validation of accelerometer wear and nonwear time classification algorithm.

PubMed

Choi, Leena; Liu, Zhouwen; Matthews, Charles E; Buchowski, Maciej S

2011-02-01

the use of movement monitors (accelerometers) for measuring physical activity (PA) in intervention and population-based studies is becoming a standard methodology for the objective measurement of sedentary and active behaviors and for the validation of subjective PA self-reports. A vital step in PA measurement is the classification of daily time into accelerometer wear and nonwear intervals using its recordings (counts) and an accelerometer-specific algorithm. the purpose of this study was to validate and improve a commonly used algorithm for classifying accelerometer wear and nonwear time intervals using objective movement data obtained in the whole-room indirect calorimeter. we conducted a validation study of a wear or nonwear automatic algorithm using data obtained from 49 adults and 76 youth wearing accelerometers during a strictly monitored 24-h stay in a room calorimeter. The accelerometer wear and nonwear time classified by the algorithm was compared with actual wearing time. Potential improvements to the algorithm were examined using the minimum classification error as an optimization target. the recommended elements in the new algorithm are as follows: 1) zero-count threshold during a nonwear time interval, 2) 90-min time window for consecutive zero or nonzero counts, and 3) allowance of 2-min interval of nonzero counts with the upstream or downstream 30-min consecutive zero-count window for detection of artifactual movements. Compared with the true wearing status, improvements to the algorithm decreased nonwear time misclassification during the waking and the 24-h periods (all P values < 0.001). the accelerometer wear or nonwear time algorithm improvements may lead to more accurate estimation of time spent in sedentary and active behaviors.

Differentially Private Empirical Risk Minimization

PubMed Central

Chaudhuri, Kamalika; Monteleoni, Claire; Sarwate, Anand D.

2011-01-01

Privacy-preserving machine learning algorithms are crucial for the increasingly common setting in which personal data, such as medical or financial records, are analyzed. We provide general techniques to produce privacy-preserving approximations of classifiers learned via (regularized) empirical risk minimization (ERM). These algorithms are private under the ε-differential privacy definition due to Dwork et al. (2006). First we apply the output perturbation ideas of Dwork et al. (2006), to ERM classification. Then we propose a new method, objective perturbation, for privacy-preserving machine learning algorithm design. This method entails perturbing the objective function before optimizing over classifiers. If the loss and regularizer satisfy certain convexity and differentiability criteria, we prove theoretical results showing that our algorithms preserve privacy, and provide generalization bounds for linear and nonlinear kernels. We further present a privacy-preserving technique for tuning the parameters in general machine learning algorithms, thereby providing end-to-end privacy guarantees for the training process. We apply these results to produce privacy-preserving analogues of regularized logistic regression and support vector machines. We obtain encouraging results from evaluating their performance on real demographic and benchmark data sets. Our results show that both theoretically and empirically, objective perturbation is superior to the previous state-of-the-art, output perturbation, in managing the inherent tradeoff between privacy and learning performance. PMID:21892342

Real Time Intelligent Target Detection and Analysis with Machine Vision

NASA Technical Reports Server (NTRS)

Howard, Ayanna; Padgett, Curtis; Brown, Kenneth

2000-01-01

We present an algorithm for detecting a specified set of targets for an Automatic Target Recognition (ATR) application. ATR involves processing images for detecting, classifying, and tracking targets embedded in a background scene. We address the problem of discriminating between targets and nontarget objects in a scene by evaluating 40x40 image blocks belonging to an image. Each image block is first projected onto a set of templates specifically designed to separate images of targets embedded in a typical background scene from those background images without targets. These filters are found using directed principal component analysis which maximally separates the two groups. The projected images are then clustered into one of n classes based on a minimum distance to a set of n cluster prototypes. These cluster prototypes have previously been identified using a modified clustering algorithm based on prior sensed data. Each projected image pattern is then fed into the associated cluster's trained neural network for classification. A detailed description of our algorithm will be given in this paper. We outline our methodology for designing the templates, describe our modified clustering algorithm, and provide details on the neural network classifiers. Evaluation of the overall algorithm demonstrates that our detection rates approach 96% with a false positive rate of less than 0.03%.

Algorithms for the detection of chewing behavior in dietary monitoring applications

NASA Astrophysics Data System (ADS)

Schmalz, Mark S.; Helal, Abdelsalam; Mendez-Vasquez, Andres

2009-08-01

The detection of food consumption is key to the implementation of successful behavior modification in support of dietary monitoring and therapy, for example, during the course of controlling obesity, diabetes, or cardiovascular disease. Since the vast majority of humans consume food via mastication (chewing), we have designed an algorithm that automatically detects chewing behaviors in surveillance video of a person eating. Our algorithm first detects the mouth region, then computes the spatiotemporal frequency spectrum of a small perioral region (including the mouth). Spectral data are analyzed to determine the presence of periodic motion that characterizes chewing. A classifier is then applied to discriminate different types of chewing behaviors. Our algorithm was tested on seven volunteers, whose behaviors included chewing with mouth open, chewing with mouth closed, talking, static face presentation (control case), and moving face presentation. Early test results show that the chewing behaviors induce a temporal frequency peak at 0.5Hz to 2.5Hz, which is readily detected using a distance-based classifier. Computational cost is analyzed for implementation on embedded processing nodes, for example, in a healthcare sensor network. Complexity analysis emphasizes the relationship between the work and space estimates of the algorithm, and its estimated error. It is shown that chewing detection is possible within a computationally efficient, accurate, and subject-independent framework.

A Novel Hybrid Classification Model of Genetic Algorithms, Modified k-Nearest Neighbor and Developed Backpropagation Neural Network

PubMed Central

Salari, Nader; Shohaimi, Shamarina; Najafi, Farid; Nallappan, Meenakshii; Karishnarajah, Isthrinayagy

2014-01-01

Among numerous artificial intelligence approaches, k-Nearest Neighbor algorithms, genetic algorithms, and artificial neural networks are considered as the most common and effective methods in classification problems in numerous studies. In the present study, the results of the implementation of a novel hybrid feature selection-classification model using the above mentioned methods are presented. The purpose is benefitting from the synergies obtained from combining these technologies for the development of classification models. Such a combination creates an opportunity to invest in the strength of each algorithm, and is an approach to make up for their deficiencies. To develop proposed model, with the aim of obtaining the best array of features, first, feature ranking techniques such as the Fisher's discriminant ratio and class separability criteria were used to prioritize features. Second, the obtained results that included arrays of the top-ranked features were used as the initial population of a genetic algorithm to produce optimum arrays of features. Third, using a modified k-Nearest Neighbor method as well as an improved method of backpropagation neural networks, the classification process was advanced based on optimum arrays of the features selected by genetic algorithms. The performance of the proposed model was compared with thirteen well-known classification models based on seven datasets. Furthermore, the statistical analysis was performed using the Friedman test followed by post-hoc tests. The experimental findings indicated that the novel proposed hybrid model resulted in significantly better classification performance compared with all 13 classification methods. Finally, the performance results of the proposed model was benchmarked against the best ones reported as the state-of-the-art classifiers in terms of classification accuracy for the same data sets. The substantial findings of the comprehensive comparative study revealed that performance of the proposed model in terms of classification accuracy is desirable, promising, and competitive to the existing state-of-the-art classification models. PMID:25419659

On Evaluating Brain Tissue Classifiers without a Ground Truth

PubMed Central

Martin-Fernandez, Marcos; Ungar, Lida; Nakamura, Motoaki; Koo, Min-Seong; McCarley, Robert W.; Shenton, Martha E.

2009-01-01

In this paper, we present a set of techniques for the evaluation of brain tissue classifiers on a large data set of MR images of the head. Due to the difficulty of establishing a gold standard for this type of data, we focus our attention on methods which do not require a ground truth, but instead rely on a common agreement principle. Three different techniques are presented: the Williams’ index, a measure of common agreement; STAPLE, an Expectation Maximization algorithm which simultaneously estimates performance parameters and constructs an estimated reference standard; and Multidimensional Scaling, a visualization technique to explore similarity data. We apply these different evaluation methodologies to a set eleven different segmentation algorithms on forty MR images. We then validate our evaluation pipeline by building a ground truth based on human expert tracings. The evaluations with and without a ground truth are compared. Our findings show that comparing classifiers without a gold standard can provide a lot of interesting information. In particular, outliers can be easily detected, strongly consistent or highly variable techniques can be readily discriminated, and the overall similarity between different techniques can be assessed. On the other hand, we also find that some information present in the expert segmentations is not captured by the automatic classifiers, suggesting that common agreement alone may not be sufficient for a precise performance evaluation of brain tissue classifiers. PMID:17532646

Handling Imbalanced Data Sets in Multistage Classification

NASA Astrophysics Data System (ADS)

López, M.

Multistage classification is a logical approach, based on a divide-and-conquer solution, for dealing with problems with a high number of classes. The classification problem is divided into several sequential steps, each one associated to a single classifier that works with subgroups of the original classes. In each level, the current set of classes is split into smaller subgroups of classes until they (the subgroups) are composed of only one class. The resulting chain of classifiers can be represented as a tree, which (1) simplifies the classification process by using fewer categories in each classifier and (2) makes it possible to combine several algorithms or use different attributes in each stage. Most of the classification algorithms can be biased in the sense of selecting the most populated class in overlapping areas of the input space. This can degrade a multistage classifier performance if the training set sample frequencies do not reflect the real prevalence in the population. Several techniques such as applying prior probabilities, assigning weights to the classes, or replicating instances have been developed to overcome this handicap. Most of them are designed for two-class (accept-reject) problems. In this article, we evaluate several of these techniques as applied to multistage classification and analyze how they can be useful for astronomy. We compare the results obtained by classifying a data set based on Hipparcos with and without these methods.

A hybrid MLP-CNN classifier for very fine resolution remotely sensed image classification

NASA Astrophysics Data System (ADS)

Zhang, Ce; Pan, Xin; Li, Huapeng; Gardiner, Andy; Sargent, Isabel; Hare, Jonathon; Atkinson, Peter M.

2018-06-01

The contextual-based convolutional neural network (CNN) with deep architecture and pixel-based multilayer perceptron (MLP) with shallow structure are well-recognized neural network algorithms, representing the state-of-the-art deep learning method and the classical non-parametric machine learning approach, respectively. The two algorithms, which have very different behaviours, were integrated in a concise and effective way using a rule-based decision fusion approach for the classification of very fine spatial resolution (VFSR) remotely sensed imagery. The decision fusion rules, designed primarily based on the classification confidence of the CNN, reflect the generally complementary patterns of the individual classifiers. In consequence, the proposed ensemble classifier MLP-CNN harvests the complementary results acquired from the CNN based on deep spatial feature representation and from the MLP based on spectral discrimination. Meanwhile, limitations of the CNN due to the adoption of convolutional filters such as the uncertainty in object boundary partition and loss of useful fine spatial resolution detail were compensated. The effectiveness of the ensemble MLP-CNN classifier was tested in both urban and rural areas using aerial photography together with an additional satellite sensor dataset. The MLP-CNN classifier achieved promising performance, consistently outperforming the pixel-based MLP, spectral and textural-based MLP, and the contextual-based CNN in terms of classification accuracy. This research paves the way to effectively address the complicated problem of VFSR image classification.

Classifier utility modeling and analysis of hypersonic inlet start/unstart considering training data costs

NASA Astrophysics Data System (ADS)

Chang, Juntao; Hu, Qinghua; Yu, Daren; Bao, Wen

2011-11-01

Start/unstart detection is one of the most important issues of hypersonic inlets and is also the foundation of protection control of scramjet. The inlet start/unstart detection can be attributed to a standard pattern classification problem, and the training sample costs have to be considered for the classifier modeling as the CFD numerical simulations and wind tunnel experiments of hypersonic inlets both cost time and money. To solve this problem, the CFD simulation of inlet is studied at first step, and the simulation results could provide the training data for pattern classification of hypersonic inlet start/unstart. Then the classifier modeling technology and maximum classifier utility theories are introduced to analyze the effect of training data cost on classifier utility. In conclusion, it is useful to introduce support vector machine algorithms to acquire the classifier model of hypersonic inlet start/unstart, and the minimum total cost of hypersonic inlet start/unstart classifier can be obtained by the maximum classifier utility theories.

An algorithm to improve diagnostic accuracy in diabetes in computerised problem orientated medical records (POMR) compared with an established algorithm developed in episode orientated records (EOMR).

PubMed

de Lusignan, Simon; Liaw, Siaw-Teng; Dedman, Daniel; Khunti, Kamlesh; Sadek, Khaled; Jones, Simon

2015-06-05

An algorithm that detects errors in diagnosis, classification or coding of diabetes in primary care computerised medial record (CMR) systems is currently available. However, this was developed on CMR systems that are episode orientated medical records (EOMR); and do not force the user to always code a problem or link data to an existing one. More strictly problem orientated medical record (POMR) systems mandate recording a problem and linking consultation data to them. To compare the rates of detection of diagnostic accuracy using an algorithm developed in EOMR with a new POMR specific algorithm. We used data from The Health Improvement Network (THIN) database (N = 2,466,364) to identify a population of 100,513 (4.08%) patients considered likely to have diabetes. We recalibrated algorithms designed to classify cases of diabetes to take account of that POMR enforced coding consistency in the computerised medical record systems [In Practice Systems (InPS) Vision] that contribute data to THIN. We explored the different proportions of people classified as having type 1 diabetes mellitus (T1DM) or type 2 diabetes mellitus (T2DM) and with diabetes unclassifiable as either T1DM or T2DM. We compared proportions using chi-square tests and used Tukey's test to compare the characteristics of the people in each group. The prevalence of T1DM using the original EOMR algorithm was 0.38% (9,264/2,466,364), and for T2DM 3.22% (79,417/2,466,364). The prevalence using the new POMR algorithm was 0.31% (7,750/2,466,364) T1DM and 3.65% (89,990/2,466,364) T2DM. The EOMR algorithms also left more people unclassified 11,439 (12%), as to their type of diabetes compared with 2,380 (2.4%), for the new algorithm. Those people who were only classified by the EOMR system differed in terms of older age, and apparently better glycaemic control, despite not being prescribed medication for their diabetes (p < 0.005). Increasing the degree of problem orientation of the medical record system can improve the accuracy of recording of diagnoses and, therefore, the accuracy of using routinely collected data from CMRs to determine the prevalence of diabetes mellitus; data processing strategies should reflect the degree of problem orientation.

Automatic detection of osteoporosis based on hybrid genetic swarm fuzzy classifier approaches

PubMed Central

Kavitha, Muthu Subash; Ganesh Kumar, Pugalendhi; Park, Soon-Yong; Huh, Kyung-Hoe; Heo, Min-Suk; Kurita, Takio; Asano, Akira; An, Seo-Yong

2016-01-01

Objectives: This study proposed a new automated screening system based on a hybrid genetic swarm fuzzy (GSF) classifier using digital dental panoramic radiographs to diagnose females with a low bone mineral density (BMD) or osteoporosis. Methods: The geometrical attributes of both the mandibular cortical bone and trabecular bone were acquired using previously developed software. Designing an automated system for osteoporosis screening involved partitioning of the input attributes to generate an initial membership function (MF) and a rule set (RS), classification using a fuzzy inference system and optimization of the generated MF and RS using the genetic swarm algorithm. Fivefold cross-validation (5-FCV) was used to estimate the classification accuracy of the hybrid GSF classifier. The performance of the hybrid GSF classifier has been further compared with that of individual genetic algorithm and particle swarm optimization fuzzy classifiers. Results: Proposed hybrid GSF classifier in identifying low BMD or osteoporosis at the lumbar spine and femoral neck BMD was evaluated. The sensitivity, specificity and accuracy of the hybrid GSF with optimized MF and RS in identifying females with a low BMD were 95.3%, 94.7% and 96.01%, respectively, at the lumbar spine and 99.1%, 98.4% and 98.9%, respectively, at the femoral neck BMD. The diagnostic performance of the proposed system with femoral neck BMD was 0.986 with a confidence interval of 0.942–0.998. The highest mean accuracy using 5-FCV was 97.9% with femoral neck BMD. Conclusions: The combination of high accuracy along with its interpretation ability makes this proposed automatic system using hybrid GSF classifier capable of identifying a large proportion of undetected low BMD or osteoporosis at its early stage. PMID:27186991

Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks.

PubMed

Chai, Rifai; Ling, Sai Ho; San, Phyo Phyo; Naik, Ganesh R; Nguyen, Tuan N; Tran, Yvonne; Craig, Ashley; Nguyen, Hung T

2017-01-01

This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively.

Improving EEG-Based Driver Fatigue Classification Using Sparse-Deep Belief Networks

PubMed Central

Chai, Rifai; Ling, Sai Ho; San, Phyo Phyo; Naik, Ganesh R.; Nguyen, Tuan N.; Tran, Yvonne; Craig, Ashley; Nguyen, Hung T.

2017-01-01

This paper presents an improvement of classification performance for electroencephalography (EEG)-based driver fatigue classification between fatigue and alert states with the data collected from 43 participants. The system employs autoregressive (AR) modeling as the features extraction algorithm, and sparse-deep belief networks (sparse-DBN) as the classification algorithm. Compared to other classifiers, sparse-DBN is a semi supervised learning method which combines unsupervised learning for modeling features in the pre-training layer and supervised learning for classification in the following layer. The sparsity in sparse-DBN is achieved with a regularization term that penalizes a deviation of the expected activation of hidden units from a fixed low-level prevents the network from overfitting and is able to learn low-level structures as well as high-level structures. For comparison, the artificial neural networks (ANN), Bayesian neural networks (BNN), and original deep belief networks (DBN) classifiers are used. The classification results show that using AR feature extractor and DBN classifiers, the classification performance achieves an improved classification performance with a of sensitivity of 90.8%, a specificity of 90.4%, an accuracy of 90.6%, and an area under the receiver operating curve (AUROC) of 0.94 compared to ANN (sensitivity at 80.8%, specificity at 77.8%, accuracy at 79.3% with AUC-ROC of 0.83) and BNN classifiers (sensitivity at 84.3%, specificity at 83%, accuracy at 83.6% with AUROC of 0.87). Using the sparse-DBN classifier, the classification performance improved further with sensitivity of 93.9%, a specificity of 92.3%, and an accuracy of 93.1% with AUROC of 0.96. Overall, the sparse-DBN classifier improved accuracy by 13.8, 9.5, and 2.5% over ANN, BNN, and DBN classifiers, respectively. PMID:28326009

Behavioral Modeling for Mental Health using Machine Learning Algorithms.

PubMed

Srividya, M; Mohanavalli, S; Bhalaji, N

2018-04-03

Mental health is an indicator of emotional, psychological and social well-being of an individual. It determines how an individual thinks, feels and handle situations. Positive mental health helps one to work productively and realize their full potential. Mental health is important at every stage of life, from childhood and adolescence through adulthood. Many factors contribute to mental health problems which lead to mental illness like stress, social anxiety, depression, obsessive compulsive disorder, drug addiction, and personality disorders. It is becoming increasingly important to determine the onset of the mental illness to maintain proper life balance. The nature of machine learning algorithms and Artificial Intelligence (AI) can be fully harnessed for predicting the onset of mental illness. Such applications when implemented in real time will benefit the society by serving as a monitoring tool for individuals with deviant behavior. This research work proposes to apply various machine learning algorithms such as support vector machines, decision trees, naïve bayes classifier, K-nearest neighbor classifier and logistic regression to identify state of mental health in a target group. The responses obtained from the target group for the designed questionnaire were first subject to unsupervised learning techniques. The labels obtained as a result of clustering were validated by computing the Mean Opinion Score. These cluster labels were then used to build classifiers to predict the mental health of an individual. Population from various groups like high school students, college students and working professionals were considered as target groups. The research presents an analysis of applying the aforementioned machine learning algorithms on the target groups and also suggests directions for future work.

Evaluation of supervised machine-learning algorithms to distinguish between inflammatory bowel disease and alimentary lymphoma in cats.

PubMed

Awaysheh, Abdullah; Wilcke, Jeffrey; Elvinger, François; Rees, Loren; Fan, Weiguo; Zimmerman, Kurt L

2016-11-01

Inflammatory bowel disease (IBD) and alimentary lymphoma (ALA) are common gastrointestinal diseases in cats. The very similar clinical signs and histopathologic features of these diseases make the distinction between them diagnostically challenging. We tested the use of supervised machine-learning algorithms to differentiate between the 2 diseases using data generated from noninvasive diagnostic tests. Three prediction models were developed using 3 machine-learning algorithms: naive Bayes, decision trees, and artificial neural networks. The models were trained and tested on data from complete blood count (CBC) and serum chemistry (SC) results for the following 3 groups of client-owned cats: normal, inflammatory bowel disease (IBD), or alimentary lymphoma (ALA). Naive Bayes and artificial neural networks achieved higher classification accuracy (sensitivities of 70.8% and 69.2%, respectively) than the decision tree algorithm (63%, p < 0.0001). The areas under the receiver-operating characteristic curve for classifying cases into the 3 categories was 83% by naive Bayes, 79% by decision tree, and 82% by artificial neural networks. Prediction models using machine learning provided a method for distinguishing between ALA-IBD, ALA-normal, and IBD-normal. The naive Bayes and artificial neural networks classifiers used 10 and 4 of the CBC and SC variables, respectively, to outperform the C4.5 decision tree, which used 5 CBC and SC variables in classifying cats into the 3 classes. These models can provide another noninvasive diagnostic tool to assist clinicians with differentiating between IBD and ALA, and between diseased and nondiseased cats. © 2016 The Author(s).

Equilibrium Sampling in Biomolecular Simulation

PubMed Central

2015-01-01

Equilibrium sampling of biomolecules remains an unmet challenge after more than 30 years of atomistic simulation. Efforts to enhance sampling capability, which are reviewed here, range from the development of new algorithms to parallelization to novel uses of hardware. Special focus is placed on classifying algorithms — most of which are underpinned by a few key ideas — in order to understand their fundamental strengths and limitations. Although algorithms have proliferated, progress resulting from novel hardware use appears to be more clear-cut than from algorithms alone, partly due to the lack of widely used sampling measures. PMID:21370970

Research of information classification and strategy intelligence extract algorithm based on military strategy hall

NASA Astrophysics Data System (ADS)

Chen, Lei; Li, Dehua; Yang, Jie

2007-12-01

Constructing virtual international strategy environment needs many kinds of information, such as economy, politic, military, diploma, culture, science, etc. So it is very important to build an information auto-extract, classification, recombination and analysis management system with high efficiency as the foundation and component of military strategy hall. This paper firstly use improved Boost algorithm to classify obtained initial information, then use a strategy intelligence extract algorithm to extract strategy intelligence from initial information to help strategist to analysis information.

Traffic sign recognition by color segmentation and neural network

NASA Astrophysics Data System (ADS)

Surinwarangkoon, Thongchai; Nitsuwat, Supot; Moore, Elvin J.

2011-12-01

An algorithm is proposed for traffic sign detection and identification based on color filtering, color segmentation and neural networks. Traffic signs in Thailand are classified by color into four types: namely, prohibitory signs (red or blue), general warning signs (yellow) and construction area warning signs (amber). A color filtering method is first used to detect traffic signs and classify them by type. Then color segmentation methods adapted for each color type are used to extract inner features, e.g., arrows, bars etc. Finally, neural networks trained to recognize signs in each color type are used to identify any given traffic sign. Experiments show that the algorithm can improve the accuracy of traffic sign detection and recognition for the traffic signs used in Thailand.

An improved K-means clustering method for cDNA microarray image segmentation.

PubMed

Wang, T N; Li, T J; Shao, G F; Wu, S X

2015-07-14

Microarray technology is a powerful tool for human genetic research and other biomedical applications. Numerous improvements to the standard K-means algorithm have been carried out to complete the image segmentation step. However, most of the previous studies classify the image into two clusters. In this paper, we propose a novel K-means algorithm, which first classifies the image into three clusters, and then one of the three clusters is divided as the background region and the other two clusters, as the foreground region. The proposed method was evaluated on six different data sets. The analyses of accuracy, efficiency, expression values, special gene spots, and noise images demonstrate the effectiveness of our method in improving the segmentation quality.

Neural CMOS-integrated circuit and its application to data classification.

PubMed

Göknar, Izzet Cem; Yildiz, Merih; Minaei, Shahram; Deniz, Engin

2012-05-01

Implementation and new applications of a tunable complementary metal-oxide-semiconductor-integrated circuit (CMOS-IC) of a recently proposed classifier core-cell (CC) are presented and tested with two different datasets. With two algorithms-one based on Fisher's linear discriminant analysis and the other based on perceptron learning, used to obtain CCs' tunable parameters-the Haberman and Iris datasets are classified. The parameters so obtained are used for hard-classification of datasets with a neural network structured circuit. Classification performance and coefficient calculation times for both algorithms are given. The CC has 6-ns response time and 1.8-mW power consumption. The fabrication parameters used for the IC are taken from CMOS AMS 0.35-μm technology.

Determination of water depth with high-resolution satellite imagery over variable bottom types

USGS Publications Warehouse

Stumpf, Richard P.; Holderied, Kristine; Sinclair, Mark

2003-01-01

A standard algorithm for determining depth in clear water from passive sensors exists; but it requires tuning of five parameters and does not retrieve depths where the bottom has an extremely low albedo. To address these issues, we developed an empirical solution using a ratio of reflectances that has only two tunable parameters and can be applied to low-albedo features. The two algorithms--the standard linear transform and the new ratio transform--were compared through analysis of IKONOS satellite imagery against lidar bathymetry. The coefficients for the ratio algorithm were tuned manually to a few depths from a nautical chart, yet performed as well as the linear algorithm tuned using multiple linear regression against the lidar. Both algorithms compensate for variable bottom type and albedo (sand, pavement, algae, coral) and retrieve bathymetry in water depths of less than 10-15 m. However, the linear transform does not distinguish depths >15 m and is more subject to variability across the studied atolls. The ratio transform can, in clear water, retrieve depths in >25 m of water and shows greater stability between different areas. It also performs slightly better in scattering turbidity than the linear transform. The ratio algorithm is somewhat noisier and cannot always adequately resolve fine morphology (structures smaller than 4-5 pixels) in water depths >15-20 m. In general, the ratio transform is more robust than the linear transform.

A Proposed Methodology to Classify Frontier Capital Markets

DTIC Science & Technology

2011-07-31

but because it is the surest route to our common good.” -Inaugural Speech by President Barack Obama, Jan 2009 This project involves basic...machine learning. The algorithm consists of a unique binary classifier mechanism that combines three methods: k-Nearest Neighbors ( kNN ), ensemble...Through kNN Ensemble Classification Techniques E. Capital Market Classification Based on Capital Flows and Trading Architecture F. Horizontal

A Proposed Methodology to Classify Frontier Capital Markets

DTIC Science & Technology

2011-07-31

out of charity, but because it is the surest route to our common good.” -Inaugural Speech by President Barack Obama, Jan 2009 This project...identification, and machine learning. The algorithm consists of a unique binary classifier mechanism that combines three methods: k-Nearest Neighbors ( kNN ...Support Through kNN Ensemble Classification Techniques E. Capital Market Classification Based on Capital Flows and Trading Architecture F

A hybrid approach to select features and classify diseases based on medical data

NASA Astrophysics Data System (ADS)

AbdelLatif, Hisham; Luo, Jiawei

2018-03-01

Feature selection is popular problem in the classification of diseases in clinical medicine. Here, we developing a hybrid methodology to classify diseases, based on three medical datasets, Arrhythmia, Breast cancer, and Hepatitis datasets. This methodology called k-means ANOVA Support Vector Machine (K-ANOVA-SVM) uses K-means cluster with ANOVA statistical to preprocessing data and selection the significant features, and Support Vector Machines in the classification process. To compare and evaluate the performance, we choice three classification algorithms, decision tree Naïve Bayes, Support Vector Machines and applied the medical datasets direct to these algorithms. Our methodology was a much better classification accuracy is given of 98% in Arrhythmia datasets, 92% in Breast cancer datasets and 88% in Hepatitis datasets, Compare to use the medical data directly with decision tree Naïve Bayes, and Support Vector Machines. Also, the ROC curve and precision with (K-ANOVA-SVM) Achieved best results than other algorithms

Classification of heavy metal ions present in multi-frequency multi-electrode potable water data using evolutionary algorithm

NASA Astrophysics Data System (ADS)

Karkra, Rashmi; Kumar, Prashant; Bansod, Baban K. S.; Bagchi, Sudeshna; Sharma, Pooja; Krishna, C. Rama

2017-11-01

Access to potable water for the common people is one of the most challenging tasks in the present era. Contamination of drinking water has become a serious problem due to various anthropogenic and geogenic events. The paper demonstrates the application of evolutionary algorithms, viz., particle swan optimization and genetic algorithm to 24 water samples containing eight different heavy metal ions (Cd, Cu, Co, Pb, Zn, Ar, Cr and Ni) for the optimal estimation of electrode and frequency to classify the heavy metal ions. The work has been carried out on multi-variate data, viz., single electrode multi-frequency, single frequency multi-electrode and multi-frequency multi-electrode water samples. The electrodes used are platinum, gold, silver nanoparticles and glassy carbon electrodes. Various hazardous metal ions present in the water samples have been optimally classified and validated by the application of Davis Bouldin index. Such studies are useful in the segregation of hazardous heavy metal ions found in water resources, thereby quantifying the degree of water quality.

Support Vector Machines Trained with Evolutionary Algorithms Employing Kernel Adatron for Large Scale Classification of Protein Structures.

PubMed

Arana-Daniel, Nancy; Gallegos, Alberto A; López-Franco, Carlos; Alanís, Alma Y; Morales, Jacob; López-Franco, Adriana

2016-01-01

With the increasing power of computers, the amount of data that can be processed in small periods of time has grown exponentially, as has the importance of classifying large-scale data efficiently. Support vector machines have shown good results classifying large amounts of high-dimensional data, such as data generated by protein structure prediction, spam recognition, medical diagnosis, optical character recognition and text classification, etc. Most state of the art approaches for large-scale learning use traditional optimization methods, such as quadratic programming or gradient descent, which makes the use of evolutionary algorithms for training support vector machines an area to be explored. The present paper proposes an approach that is simple to implement based on evolutionary algorithms and Kernel-Adatron for solving large-scale classification problems, focusing on protein structure prediction. The functional properties of proteins depend upon their three-dimensional structures. Knowing the structures of proteins is crucial for biology and can lead to improvements in areas such as medicine, agriculture and biofuels.

Fuzzy support vector machine: an efficient rule-based classification technique for microarrays.

PubMed

Hajiloo, Mohsen; Rabiee, Hamid R; Anooshahpour, Mahdi

2013-01-01

The abundance of gene expression microarray data has led to the development of machine learning algorithms applicable for tackling disease diagnosis, disease prognosis, and treatment selection problems. However, these algorithms often produce classifiers with weaknesses in terms of accuracy, robustness, and interpretability. This paper introduces fuzzy support vector machine which is a learning algorithm based on combination of fuzzy classifiers and kernel machines for microarray classification. Experimental results on public leukemia, prostate, and colon cancer datasets show that fuzzy support vector machine applied in combination with filter or wrapper feature selection methods develops a robust model with higher accuracy than the conventional microarray classification models such as support vector machine, artificial neural network, decision trees, k nearest neighbors, and diagonal linear discriminant analysis. Furthermore, the interpretable rule-base inferred from fuzzy support vector machine helps extracting biological knowledge from microarray data. Fuzzy support vector machine as a new classification model with high generalization power, robustness, and good interpretability seems to be a promising tool for gene expression microarray classification.

CAVIAR: CLASSIFICATION VIA AGGREGATED REGRESSION AND ITS APPLICATION IN CLASSIFYING OASIS BRAIN DATABASE

PubMed Central

Chen, Ting; Rangarajan, Anand; Vemuri, Baba C.

2010-01-01

This paper presents a novel classification via aggregated regression algorithm – dubbed CAVIAR – and its application to the OASIS MRI brain image database. The CAVIAR algorithm simultaneously combines a set of weak learners based on the assumption that the weight combination for the final strong hypothesis in CAVIAR depends on both the weak learners and the training data. A regularization scheme using the nearest neighbor method is imposed in the testing stage to avoid overfitting. A closed form solution to the cost function is derived for this algorithm. We use a novel feature – the histogram of the deformation field between the MRI brain scan and the atlas which captures the structural changes in the scan with respect to the atlas brain – and this allows us to automatically discriminate between various classes within OASIS [1] using CAVIAR. We empirically show that CAVIAR significantly increases the performance of the weak classifiers by showcasing the performance of our technique on OASIS. PMID:21151847

CAVIAR: CLASSIFICATION VIA AGGREGATED REGRESSION AND ITS APPLICATION IN CLASSIFYING OASIS BRAIN DATABASE.

PubMed

Chen, Ting; Rangarajan, Anand; Vemuri, Baba C

2010-04-14

This paper presents a novel classification via aggregated regression algorithm - dubbed CAVIAR - and its application to the OASIS MRI brain image database. The CAVIAR algorithm simultaneously combines a set of weak learners based on the assumption that the weight combination for the final strong hypothesis in CAVIAR depends on both the weak learners and the training data. A regularization scheme using the nearest neighbor method is imposed in the testing stage to avoid overfitting. A closed form solution to the cost function is derived for this algorithm. We use a novel feature - the histogram of the deformation field between the MRI brain scan and the atlas which captures the structural changes in the scan with respect to the atlas brain - and this allows us to automatically discriminate between various classes within OASIS [1] using CAVIAR. We empirically show that CAVIAR significantly increases the performance of the weak classifiers by showcasing the performance of our technique on OASIS.

Composition-based classification of short metagenomic sequences elucidates the landscapes of taxonomic and functional enrichment of microorganisms

PubMed Central

Liu, Jiemeng; Wang, Haifeng; Yang, Hongxing; Zhang, Yizhe; Wang, Jinfeng; Zhao, Fangqing; Qi, Ji

2013-01-01

Compared with traditional algorithms for long metagenomic sequence classification, characterizing microorganisms’ taxonomic and functional abundance based on tens of millions of very short reads are much more challenging. We describe an efficient composition and phylogeny-based algorithm [Metagenome Composition Vector (MetaCV)] to classify very short metagenomic reads (75–100 bp) into specific taxonomic and functional groups. We applied MetaCV to the Meta-HIT data (371-Gb 75-bp reads of 109 human gut metagenomes), and this single-read-based, instead of assembly-based, classification has a high resolution to characterize the composition and structure of human gut microbiota, especially for low abundance species. Most strikingly, it only took MetaCV 10 days to do all the computation work on a server with five 24-core nodes. To our knowledge, MetaCV, benefited from the strategy of composition comparison, is the first algorithm that can classify millions of very short reads within affordable time. PMID:22941634

Feasibility and validity of using WHO adolescent job aid algorithms by health workers for reproductive morbidities among adolescent girls in rural North India.

PubMed

Archana, Siddaiah; Nongkrynh, B; Anand, K; Pandav, C S

2015-09-21

High prevalence of reproductive morbidities is seen among adolescents in India. Health workers play an important role in providing health services in the community, including the adolescent reproductive health services. A study was done to assess the feasibility of training female health workers (FHWs) in the classification and management of selected adolescent girls' reproductive health problems according to modified WHO algorithms. The study was conducted between Jan-Sept 2011 in Northern India. Thirteen FHWs were trained regarding adolescent girls' reproductive health as per WHO Adolescent Job-Aid booklet. A pre and post-test assessment of the knowledge of the FHWs was carried out. All FHWs were given five modified WHO algorithms to classify and manage common reproductive morbidities among adolescent girls. All the FHWs applied the algorithms on at least ten adolescent girls at their respective sub-centres. Simultaneously, a medical doctor independently applied the same algorithms in all girls. Classification of the condition was followed by relevant management and advice provided in the algorithm. Focus group discussion with the FHWs was carried out to receive their feedback. After training the median score of the FHWs increased from 19.2 to 25.2 (p - 0.0071). Out of 144 girls examined by the FHWs 108 were classified as true positives and 30 as true negatives and agreement as measured by kappa was 0.7 (0.5-0.9). Sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were 94.3% (88.2-97.4), 78.9% (63.6-88.9), 92.5% (86.0-96.2), and 83.3% (68.1-92.1) respectively. A consistent and significant difference between pre and post training knowledge scores of the FHWs were observed and hence it was possible to use the modified Job Aid algorithms with ease. Limitation of this study was the munber of FHWs trained was small. Issues such as time management during routine work, timing of training, overhead cost of training etc were not taken into account. Training was successful in increasing the knowledge of the FHWs about adolescent girls' reproductive health issues. The FHWs were able to satisfactorily classify the common adolescent girls' problems using the modified WHO algorithms.

Indications for spine surgery: validation of an administrative coding algorithm to classify degenerative diagnoses

PubMed Central

Lurie, Jon D.; Tosteson, Anna N.A.; Deyo, Richard A.; Tosteson, Tor; Weinstein, James; Mirza, Sohail K.

2014-01-01

Study Design Retrospective analysis of Medicare claims linked to a multi-center clinical trial. Objective The Spine Patient Outcomes Research Trial (SPORT) provided a unique opportunity to examine the validity of a claims-based algorithm for grouping patients by surgical indication. SPORT enrolled patients for lumbar disc herniation, spinal stenosis, and degenerative spondylolisthesis. We compared the surgical indication derived from Medicare claims to that provided by SPORT surgeons, the “gold standard”. Summary of Background Data Administrative data are frequently used to report procedure rates, surgical safety outcomes, and costs in the management of spinal surgery. However, the accuracy of using diagnosis codes to classify patients by surgical indication has not been examined. Methods Medicare claims were link to beneficiaries enrolled in SPORT. The sensitivity and specificity of three claims-based approaches to group patients based on surgical indications were examined: 1) using the first listed diagnosis; 2) using all diagnoses independently; and 3) using a diagnosis hierarchy based on the support for fusion surgery. Results Medicare claims were obtained from 376 SPORT participants, including 21 with disc herniation, 183 with spinal stenosis, and 172 with degenerative spondylolisthesis. The hierarchical coding algorithm was the most accurate approach for classifying patients by surgical indication, with sensitivities of 76.2%, 88.1%, and 84.3% for disc herniation, spinal stenosis, and degenerative spondylolisthesis cohorts, respectively. The specificity was 98.3% for disc herniation, 83.2% for spinal stenosis, and 90.7% for degenerative spondylolisthesis. Misclassifications were primarily due to codes attributing more complex pathology to the case. Conclusion Standardized approaches for using claims data to accurately group patients by surgical indications has widespread interest. We found that a hierarchical coding approach correctly classified over 90% of spine patients into their respective SPORT cohorts. Therefore, claims data appears to be a reasonably valid approach to classifying patients by surgical indication. PMID:24525995

Evaluation of accelerometer based multi-sensor versus single-sensor activity recognition systems.

PubMed

Gao, Lei; Bourke, A K; Nelson, John

2014-06-01

Physical activity has a positive impact on people's well-being and it had been shown to decrease the occurrence of chronic diseases in the older adult population. To date, a substantial amount of research studies exist, which focus on activity recognition using inertial sensors. Many of these studies adopt a single sensor approach and focus on proposing novel features combined with complex classifiers to improve the overall recognition accuracy. In addition, the implementation of the advanced feature extraction algorithms and the complex classifiers exceed the computing ability of most current wearable sensor platforms. This paper proposes a method to adopt multiple sensors on distributed body locations to overcome this problem. The objective of the proposed system is to achieve higher recognition accuracy with "light-weight" signal processing algorithms, which run on a distributed computing based sensor system comprised of computationally efficient nodes. For analysing and evaluating the multi-sensor system, eight subjects were recruited to perform eight normal scripted activities in different life scenarios, each repeated three times. Thus a total of 192 activities were recorded resulting in 864 separate annotated activity states. The methods for designing such a multi-sensor system required consideration of the following: signal pre-processing algorithms, sampling rate, feature selection and classifier selection. Each has been investigated and the most appropriate approach is selected to achieve a trade-off between recognition accuracy and computing execution time. A comparison of six different systems, which employ single or multiple sensors, is presented. The experimental results illustrate that the proposed multi-sensor system can achieve an overall recognition accuracy of 96.4% by adopting the mean and variance features, using the Decision Tree classifier. The results demonstrate that elaborate classifiers and feature sets are not required to achieve high recognition accuracies on a multi-sensor system. Copyright © 2014 IPEM. Published by Elsevier Ltd. All rights reserved.

Soy sauce classification by geographic region and fermentation based on artificial neural network and genetic algorithm.

PubMed

Xu, Libin; Li, Yang; Xu, Ning; Hu, Yong; Wang, Chao; He, Jianjun; Cao, Yueze; Chen, Shigui; Li, Dongsheng

2014-12-24

This work demonstrated the possibility of using artificial neural networks to classify soy sauce from China. The aroma profiles of different soy sauce samples were differentiated using headspace solid-phase microextraction. The soy sauce samples were analyzed by gas chromatography-mass spectrometry, and 22 and 15 volatile aroma compounds were selected for sensitivity analysis to classify the samples by fermentation and geographic region, respectively. The 15 selected samples can be classified by fermentation and geographic region with a prediction success rate of 100%. Furans and phenols represented the variables with the greatest contribution in classifying soy sauce samples by fermentation and geographic region, respectively.

Construction of Pancreatic Cancer Classifier Based on SVM Optimized by Improved FOA

PubMed Central

Ma, Xiaoqi

2015-01-01

A novel method is proposed to establish the pancreatic cancer classifier. Firstly, the concept of quantum and fruit fly optimal algorithm (FOA) are introduced, respectively. Then FOA is improved by quantum coding and quantum operation, and a new smell concentration determination function is defined. Finally, the improved FOA is used to optimize the parameters of support vector machine (SVM) and the classifier is established by optimized SVM. In order to verify the effectiveness of the proposed method, SVM and other classification methods have been chosen as the comparing methods. The experimental results show that the proposed method can improve the classifier performance and cost less time. PMID:26543867

The influence of negative training set size on machine learning-based virtual screening.

PubMed

Kurczab, Rafał; Smusz, Sabina; Bojarski, Andrzej J

2014-01-01

The paper presents a thorough analysis of the influence of the number of negative training examples on the performance of machine learning methods. The impact of this rather neglected aspect of machine learning methods application was examined for sets containing a fixed number of positive and a varying number of negative examples randomly selected from the ZINC database. An increase in the ratio of positive to negative training instances was found to greatly influence most of the investigated evaluating parameters of ML methods in simulated virtual screening experiments. In a majority of cases, substantial increases in precision and MCC were observed in conjunction with some decreases in hit recall. The analysis of dynamics of those variations let us recommend an optimal composition of training data. The study was performed on several protein targets, 5 machine learning algorithms (SMO, Naïve Bayes, Ibk, J48 and Random Forest) and 2 types of molecular fingerprints (MACCS and CDK FP). The most effective classification was provided by the combination of CDK FP with SMO or Random Forest algorithms. The Naïve Bayes models appeared to be hardly sensitive to changes in the number of negative instances in the training set. In conclusion, the ratio of positive to negative training instances should be taken into account during the preparation of machine learning experiments, as it might significantly influence the performance of particular classifier. What is more, the optimization of negative training set size can be applied as a boosting-like approach in machine learning-based virtual screening.

The influence of negative training set size on machine learning-based virtual screening

PubMed Central

2014-01-01

Background The paper presents a thorough analysis of the influence of the number of negative training examples on the performance of machine learning methods. Results The impact of this rather neglected aspect of machine learning methods application was examined for sets containing a fixed number of positive and a varying number of negative examples randomly selected from the ZINC database. An increase in the ratio of positive to negative training instances was found to greatly influence most of the investigated evaluating parameters of ML methods in simulated virtual screening experiments. In a majority of cases, substantial increases in precision and MCC were observed in conjunction with some decreases in hit recall. The analysis of dynamics of those variations let us recommend an optimal composition of training data. The study was performed on several protein targets, 5 machine learning algorithms (SMO, Naïve Bayes, Ibk, J48 and Random Forest) and 2 types of molecular fingerprints (MACCS and CDK FP). The most effective classification was provided by the combination of CDK FP with SMO or Random Forest algorithms. The Naïve Bayes models appeared to be hardly sensitive to changes in the number of negative instances in the training set. Conclusions In conclusion, the ratio of positive to negative training instances should be taken into account during the preparation of machine learning experiments, as it might significantly influence the performance of particular classifier. What is more, the optimization of negative training set size can be applied as a boosting-like approach in machine learning-based virtual screening. PMID:24976867

Applying a new unequally weighted feature fusion method to improve CAD performance of classifying breast lesions

NASA Astrophysics Data System (ADS)

Zargari Khuzani, Abolfazl; Danala, Gopichandh; Heidari, Morteza; Du, Yue; Mashhadi, Najmeh; Qiu, Yuchen; Zheng, Bin

2018-02-01

Higher recall rates are a major challenge in mammography screening. Thus, developing computer-aided diagnosis (CAD) scheme to classify between malignant and benign breast lesions can play an important role to improve efficacy of mammography screening. Objective of this study is to develop and test a unique image feature fusion framework to improve performance in classifying suspicious mass-like breast lesions depicting on mammograms. The image dataset consists of 302 suspicious masses detected on both craniocaudal and mediolateral-oblique view images. Amongst them, 151 were malignant and 151 were benign. The study consists of following 3 image processing and feature analysis steps. First, an adaptive region growing segmentation algorithm was used to automatically segment mass regions. Second, a set of 70 image features related to spatial and frequency characteristics of mass regions were initially computed. Third, a generalized linear regression model (GLM) based machine learning classifier combined with a bat optimization algorithm was used to optimally fuse the selected image features based on predefined assessment performance index. An area under ROC curve (AUC) with was used as a performance assessment index. Applying CAD scheme to the testing dataset, AUC was 0.75+/-0.04, which was significantly higher than using a single best feature (AUC=0.69+/-0.05) or the classifier with equally weighted features (AUC=0.73+/-0.05). This study demonstrated that comparing to the conventional equal-weighted approach, using an unequal-weighted feature fusion approach had potential to significantly improve accuracy in classifying between malignant and benign breast masses.

Quasi-Supervised Scoring of Human Sleep in Polysomnograms Using Augmented Input Variables

PubMed Central

Yaghouby, Farid; Sunderam, Sridhar

2015-01-01

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18 to 79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models—specifically Gaussian mixtures and hidden Markov models—are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's K statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations. PMID:25679475

Quasi-supervised scoring of human sleep in polysomnograms using augmented input variables.

PubMed

Yaghouby, Farid; Sunderam, Sridhar

2015-04-01

The limitations of manual sleep scoring make computerized methods highly desirable. Scoring errors can arise from human rater uncertainty or inter-rater variability. Sleep scoring algorithms either come as supervised classifiers that need scored samples of each state to be trained, or as unsupervised classifiers that use heuristics or structural clues in unscored data to define states. We propose a quasi-supervised classifier that models observations in an unsupervised manner but mimics a human rater wherever training scores are available. EEG, EMG, and EOG features were extracted in 30s epochs from human-scored polysomnograms recorded from 42 healthy human subjects (18-79 years) and archived in an anonymized, publicly accessible database. Hypnograms were modified so that: 1. Some states are scored but not others; 2. Samples of all states are scored but not for transitional epochs; and 3. Two raters with 67% agreement are simulated. A framework for quasi-supervised classification was devised in which unsupervised statistical models-specifically Gaussian mixtures and hidden Markov models--are estimated from unlabeled training data, but the training samples are augmented with variables whose values depend on available scores. Classifiers were fitted to signal features incorporating partial scores, and used to predict scores for complete recordings. Performance was assessed using Cohen's Κ statistic. The quasi-supervised classifier performed significantly better than an unsupervised model and sometimes as well as a completely supervised model despite receiving only partial scores. The quasi-supervised algorithm addresses the need for classifiers that mimic scoring patterns of human raters while compensating for their limitations. Copyright © 2015 Elsevier Ltd. All rights reserved.

An improved method of early diagnosis of smoking-induced respiratory changes using machine learning algorithms.

PubMed

Amaral, Jorge L M; Lopes, Agnaldo J; Jansen, José M; Faria, Alvaro C D; Melo, Pedro L

2013-12-01

The purpose of this study was to develop an automatic classifier to increase the accuracy of the forced oscillation technique (FOT) for diagnosing early respiratory abnormalities in smoking patients. The data consisted of FOT parameters obtained from 56 volunteers, 28 healthy and 28 smokers with low tobacco consumption. Many supervised learning techniques were investigated, including logistic linear classifiers, k nearest neighbor (KNN), neural networks and support vector machines (SVM). To evaluate performance, the ROC curve of the most accurate parameter was established as baseline. To determine the best input features and classifier parameters, we used genetic algorithms and a 10-fold cross-validation using the average area under the ROC curve (AUC). In the first experiment, the original FOT parameters were used as input. We observed a significant improvement in accuracy (KNN=0.89 and SVM=0.87) compared with the baseline (0.77). The second experiment performed a feature selection on the original FOT parameters. This selection did not cause any significant improvement in accuracy, but it was useful in identifying more adequate FOT parameters. In the third experiment, we performed a feature selection on the cross products of the FOT parameters. This selection resulted in a further increase in AUC (KNN=SVM=0.91), which allows for high diagnostic accuracy. In conclusion, machine learning classifiers can help identify early smoking-induced respiratory alterations. The use of FOT cross products and the search for the best features and classifier parameters can markedly improve the performance of machine learning classifiers. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

Summary of Research 1997, Department of Mathematics.

DTIC Science & Technology

1999-01-01

problems. This capabil- ity is especially important at the present time when technology in general, and information operations in particular, are changing...compression algorithms, especially the Radiant TIN algorithm and its use on tactical imagery. SUMMARY: Several aspects of this problem were...points are not always the same, especially when bifurcation occurs. The equilibrium sets of control systems and their bifurcations are classified based