Detection and recognition of simple spatial forms

NASA Technical Reports Server (NTRS)

Watson, A. B.

1983-01-01

A model of human visual sensitivity to spatial patterns is constructed. The model predicts the visibility and discriminability of arbitrary two-dimensional monochrome images. The image is analyzed by a large array of linear feature sensors, which differ in spatial frequency, phase, orientation, and position in the visual field. All sensors have one octave frequency bandwidths, and increase in size linearly with eccentricity. Sensor responses are processed by an ideal Bayesian classifier, subject to uncertainty. The performance of the model is compared to that of the human observer in detecting and discriminating some simple images.

Using color histograms and SPA-LDA to classify bacteria.

PubMed

de Almeida, Valber Elias; da Costa, Gean Bezerra; de Sousa Fernandes, David Douglas; Gonçalves Dias Diniz, Paulo Henrique; Brandão, Deysiane; de Medeiros, Ana Claudia Dantas; Véras, Germano

2014-09-01

In this work, a new approach is proposed to verify the differentiating characteristics of five bacteria (Escherichia coli, Enterococcus faecalis, Streptococcus salivarius, Streptococcus oralis, and Staphylococcus aureus) by using digital images obtained with a simple webcam and variable selection by the Successive Projections Algorithm associated with Linear Discriminant Analysis (SPA-LDA). In this sense, color histograms in the red-green-blue (RGB), hue-saturation-value (HSV), and grayscale channels and their combinations were used as input data, and statistically evaluated by using different multivariate classifiers (Soft Independent Modeling by Class Analogy (SIMCA), Principal Component Analysis-Linear Discriminant Analysis (PCA-LDA), Partial Least Squares Discriminant Analysis (PLS-DA) and Successive Projections Algorithm-Linear Discriminant Analysis (SPA-LDA)). The bacteria strains were cultivated in a nutritive blood agar base layer for 24 h by following the Brazilian Pharmacopoeia, maintaining the status of cell growth and the nature of nutrient solutions under the same conditions. The best result in classification was obtained by using RGB and SPA-LDA, which reached 94 and 100 % of classification accuracy in the training and test sets, respectively. This result is extremely positive from the viewpoint of routine clinical analyses, because it avoids bacterial identification based on phenotypic identification of the causative organism using Gram staining, culture, and biochemical proofs. Therefore, the proposed method presents inherent advantages, promoting a simpler, faster, and low-cost alternative for bacterial identification.

Gender classification of running subjects using full-body kinematics

NASA Astrophysics Data System (ADS)

Williams, Christina M.; Flora, Jeffrey B.; Iftekharuddin, Khan M.

2016-05-01

This paper proposes novel automated gender classification of subjects while engaged in running activity. The machine learning techniques include preprocessing steps using principal component analysis followed by classification with linear discriminant analysis, and nonlinear support vector machines, and decision-stump with AdaBoost. The dataset consists of 49 subjects (25 males, 24 females, 2 trials each) all equipped with approximately 80 retroreflective markers. The trials are reflective of the subject's entire body moving unrestrained through a capture volume at a self-selected running speed, thus producing highly realistic data. The classification accuracy using leave-one-out cross validation for the 49 subjects is improved from 66.33% using linear discriminant analysis to 86.74% using the nonlinear support vector machine. Results are further improved to 87.76% by means of implementing a nonlinear decision stump with AdaBoost classifier. The experimental findings suggest that the linear classification approaches are inadequate in classifying gender for a large dataset with subjects running in a moderately uninhibited environment.

Discriminative Bayesian Dictionary Learning for Classification.

PubMed

Akhtar, Naveed; Shafait, Faisal; Mian, Ajmal

2016-12-01

We propose a Bayesian approach to learn discriminative dictionaries for sparse representation of data. The proposed approach infers probability distributions over the atoms of a discriminative dictionary using a finite approximation of Beta Process. It also computes sets of Bernoulli distributions that associate class labels to the learned dictionary atoms. This association signifies the selection probabilities of the dictionary atoms in the expansion of class-specific data. Furthermore, the non-parametric character of the proposed approach allows it to infer the correct size of the dictionary. We exploit the aforementioned Bernoulli distributions in separately learning a linear classifier. The classifier uses the same hierarchical Bayesian model as the dictionary, which we present along the analytical inference solution for Gibbs sampling. For classification, a test instance is first sparsely encoded over the learned dictionary and the codes are fed to the classifier. We performed experiments for face and action recognition; and object and scene-category classification using five public datasets and compared the results with state-of-the-art discriminative sparse representation approaches. Experiments show that the proposed Bayesian approach consistently outperforms the existing approaches.

MIDAS: Regionally linear multivariate discriminative statistical mapping.

PubMed

Varol, Erdem; Sotiras, Aristeidis; Davatzikos, Christos

2018-07-01

Statistical parametric maps formed via voxel-wise mass-univariate tests, such as the general linear model, are commonly used to test hypotheses about regionally specific effects in neuroimaging cross-sectional studies where each subject is represented by a single image. Despite being informative, these techniques remain limited as they ignore multivariate relationships in the data. Most importantly, the commonly employed local Gaussian smoothing, which is important for accounting for registration errors and making the data follow Gaussian distributions, is usually chosen in an ad hoc fashion. Thus, it is often suboptimal for the task of detecting group differences and correlations with non-imaging variables. Information mapping techniques, such as searchlight, which use pattern classifiers to exploit multivariate information and obtain more powerful statistical maps, have become increasingly popular in recent years. However, existing methods may lead to important interpretation errors in practice (i.e., misidentifying a cluster as informative, or failing to detect truly informative voxels), while often being computationally expensive. To address these issues, we introduce a novel efficient multivariate statistical framework for cross-sectional studies, termed MIDAS, seeking highly sensitive and specific voxel-wise brain maps, while leveraging the power of regional discriminant analysis. In MIDAS, locally linear discriminative learning is applied to estimate the pattern that best discriminates between two groups, or predicts a variable of interest. This pattern is equivalent to local filtering by an optimal kernel whose coefficients are the weights of the linear discriminant. By composing information from all neighborhoods that contain a given voxel, MIDAS produces a statistic that collectively reflects the contribution of the voxel to the regional classifiers as well as the discriminative power of the classifiers. Critically, MIDAS efficiently assesses the statistical significance of the derived statistic by analytically approximating its null distribution without the need for computationally expensive permutation tests. The proposed framework was extensively validated using simulated atrophy in structural magnetic resonance imaging (MRI) and further tested using data from a task-based functional MRI study as well as a structural MRI study of cognitive performance. The performance of the proposed framework was evaluated against standard voxel-wise general linear models and other information mapping methods. The experimental results showed that MIDAS achieves relatively higher sensitivity and specificity in detecting group differences. Together, our results demonstrate the potential of the proposed approach to efficiently map effects of interest in both structural and functional data. Copyright © 2018. Published by Elsevier Inc.

Classifying depression patients and normal subjects using machine learning techniques and nonlinear features from EEG signal.

PubMed

Hosseinifard, Behshad; Moradi, Mohammad Hassan; Rostami, Reza

2013-03-01

Diagnosing depression in the early curable stages is very important and may even save the life of a patient. In this paper, we study nonlinear analysis of EEG signal for discriminating depression patients and normal controls. Forty-five unmedicated depressed patients and 45 normal subjects were participated in this study. Power of four EEG bands and four nonlinear features including detrended fluctuation analysis (DFA), higuchi fractal, correlation dimension and lyapunov exponent were extracted from EEG signal. For discriminating the two groups, k-nearest neighbor, linear discriminant analysis and logistic regression as the classifiers are then used. Highest classification accuracy of 83.3% is obtained by correlation dimension and LR classifier among other nonlinear features. For further improvement, all nonlinear features are combined and applied to classifiers. A classification accuracy of 90% is achieved by all nonlinear features and LR classifier. In all experiments, genetic algorithm is employed to select the most important features. The proposed technique is compared and contrasted with the other reported methods and it is demonstrated that by combining nonlinear features, the performance is enhanced. This study shows that nonlinear analysis of EEG can be a useful method for discriminating depressed patients and normal subjects. It is suggested that this analysis may be a complementary tool to help psychiatrists for diagnosing depressed patients. Copyright © 2012 Elsevier Ireland Ltd. All rights reserved.

Structured Kernel Dictionary Learning with Correlation Constraint for Object Recognition.

PubMed

Wang, Zhengjue; Wang, Yinghua; Liu, Hongwei; Zhang, Hao

2017-06-21

In this paper, we propose a new discriminative non-linear dictionary learning approach, called correlation constrained structured kernel KSVD, for object recognition. The objective function for dictionary learning contains a reconstructive term and a discriminative term. In the reconstructive term, signals are implicitly non-linearly mapped into a space, where a structured kernel dictionary, each sub-dictionary of which lies in the span of the mapped signals from the corresponding class, is established. In the discriminative term, by analyzing the classification mechanism, the correlation constraint is proposed in kernel form, constraining the correlations between different discriminative codes, and restricting the coefficient vectors to be transformed into a feature space, where the features are highly correlated inner-class and nearly independent between-classes. The objective function is optimized by the proposed structured kernel KSVD. During the classification stage, the specific form of the discriminative feature is needless to be known, while the inner product of the discriminative feature with kernel matrix embedded is available, and is suitable for a linear SVM classifier. Experimental results demonstrate that the proposed approach outperforms many state-of-the-art dictionary learning approaches for face, scene and synthetic aperture radar (SAR) vehicle target recognition.

Optical Coherence Tomography Machine Learning Classifiers for Glaucoma Detection: A Preliminary Study

PubMed Central

Burgansky-Eliash, Zvia; Wollstein, Gadi; Chu, Tianjiao; Ramsey, Joseph D.; Glymour, Clark; Noecker, Robert J.; Ishikawa, Hiroshi; Schuman, Joel S.

2007-01-01

Purpose Machine-learning classifiers are trained computerized systems with the ability to detect the relationship between multiple input parameters and a diagnosis. The present study investigated whether the use of machine-learning classifiers improves optical coherence tomography (OCT) glaucoma detection. Methods Forty-seven patients with glaucoma (47 eyes) and 42 healthy subjects (42 eyes) were included in this cross-sectional study. Of the glaucoma patients, 27 had early disease (visual field mean deviation [MD] ≥ −6 dB) and 20 had advanced glaucoma (MD < −6 dB). Machine-learning classifiers were trained to discriminate between glaucomatous and healthy eyes using parameters derived from OCT output. The classifiers were trained with all 38 parameters as well as with only 8 parameters that correlated best with the visual field MD. Five classifiers were tested: linear discriminant analysis, support vector machine, recursive partitioning and regression tree, generalized linear model, and generalized additive model. For the last two classifiers, a backward feature selection was used to find the minimal number of parameters that resulted in the best and most simple prediction. The cross-validated receiver operating characteristic (ROC) curve and accuracies were calculated. Results The largest area under the ROC curve (AROC) for glaucoma detection was achieved with the support vector machine using eight parameters (0.981). The sensitivity at 80% and 95% specificity was 97.9% and 92.5%, respectively. This classifier also performed best when judged by cross-validated accuracy (0.966). The best classification between early glaucoma and advanced glaucoma was obtained with the generalized additive model using only three parameters (AROC = 0.854). Conclusions Automated machine classifiers of OCT data might be useful for enhancing the utility of this technology for detecting glaucomatous abnormality. PMID:16249492

Automated segmentation of retinal blood vessels and identification of proliferative diabetic retinopathy

NASA Astrophysics Data System (ADS)

Jelinek, Herbert F.; Cree, Michael J.; Leandro, Jorge J. G.; Soares, João V. B.; Cesar, Roberto M.; Luckie, A.

2007-05-01

Proliferative diabetic retinopathy can lead to blindness. However, early recognition allows appropriate, timely intervention. Fluorescein-labeled retinal blood vessels of 27 digital images were automatically segmented using the Gabor wavelet transform and classified using traditional features such as area, perimeter, and an additional five morphological features based on the derivatives-of-Gaussian wavelet-derived data. Discriminant analysis indicated that traditional features do not detect early proliferative retinopathy. The best single feature for discrimination was the wavelet curvature with an area under the curve (AUC) of 0.76. Linear discriminant analysis with a selection of six features achieved an AUC of 0.90 (0.73-0.97, 95% confidence interval). The wavelet method was able to segment retinal blood vessels and classify the images according to the presence or absence of proliferative retinopathy.

Fluorescent polymer sensor array for detection and discrimination of explosives in water.

PubMed

Woodka, Marc D; Schnee, Vincent P; Polcha, Michael P

2010-12-01

A fluorescent polymer sensor array (FPSA) was made from commercially available fluorescent polymers coated onto glass beads and was tested to assess the ability of the array to discriminate between different analytes in aqueous solution. The array was challenged with exposures to 17 different analytes, including the explosives trinitrotoluene (TNT), tetryl, and RDX, various explosive-related compounds (ERCs), and nonexplosive electron-withdrawing compounds (EWCs). The array exhibited a natural selectivity toward EWCs, while the non-electron-withdrawing explosive 1,3,5-trinitroperhydro-1,3,5-triazine (RDX) produced no response. Response signatures were visualized by principal component analysis (PCA), and classified by linear discriminant analysis (LDA). RDX produced the same response signature as the sampled blanks and was classified accordingly. The array exhibited excellent discrimination toward all other compounds, with the exception of the isomers of nitrotoluene and aminodinitrotoluene. Of particular note was the ability of the array to discriminate between the three isomers of dinitrobenzene. The natural selectivity of the FPSA toward EWCs, plus the ability of the FPSA to discriminate between different EWCs, could be used to design a sensor with a low false alarm rate and an excellent ability to discriminate between explosives and explosive-related compounds.

A multiple maximum scatter difference discriminant criterion for facial feature extraction.

PubMed

Song, Fengxi; Zhang, David; Mei, Dayong; Guo, Zhongwei

2007-12-01

Maximum scatter difference (MSD) discriminant criterion was a recently presented binary discriminant criterion for pattern classification that utilizes the generalized scatter difference rather than the generalized Rayleigh quotient as a class separability measure, thereby avoiding the singularity problem when addressing small-sample-size problems. MSD classifiers based on this criterion have been quite effective on face-recognition tasks, but as they are binary classifiers, they are not as efficient on large-scale classification tasks. To address the problem, this paper generalizes the classification-oriented binary criterion to its multiple counterpart--multiple MSD (MMSD) discriminant criterion for facial feature extraction. The MMSD feature-extraction method, which is based on this novel discriminant criterion, is a new subspace-based feature-extraction method. Unlike most other subspace-based feature-extraction methods, the MMSD computes its discriminant vectors from both the range of the between-class scatter matrix and the null space of the within-class scatter matrix. The MMSD is theoretically elegant and easy to calculate. Extensive experimental studies conducted on the benchmark database, FERET, show that the MMSD out-performs state-of-the-art facial feature-extraction methods such as null space method, direct linear discriminant analysis (LDA), eigenface, Fisherface, and complete LDA.

Hierarchical ensemble of global and local classifiers for face recognition.

PubMed

Su, Yu; Shan, Shiguang; Chen, Xilin; Gao, Wen

2009-08-01

In the literature of psychophysics and neurophysiology, many studies have shown that both global and local features are crucial for face representation and recognition. This paper proposes a novel face recognition method which exploits both global and local discriminative features. In this method, global features are extracted from the whole face images by keeping the low-frequency coefficients of Fourier transform, which we believe encodes the holistic facial information, such as facial contour. For local feature extraction, Gabor wavelets are exploited considering their biological relevance. After that, Fisher's linear discriminant (FLD) is separately applied to the global Fourier features and each local patch of Gabor features. Thus, multiple FLD classifiers are obtained, each embodying different facial evidences for face recognition. Finally, all these classifiers are combined to form a hierarchical ensemble classifier. We evaluate the proposed method using two large-scale face databases: FERET and FRGC version 2.0. Experiments show that the results of our method are impressively better than the best known results with the same evaluation protocol.

Structural vibration-based damage classification of delaminated smart composite laminates

NASA Astrophysics Data System (ADS)

Khan, Asif; Kim, Heung Soo; Sohn, Jung Woo

2018-03-01

Separation along the interfaces of layers (delamination) is a principal mode of failure in laminated composites and its detection is of prime importance for structural integrity of composite materials. In this work, structural vibration response is employed to detect and classify delaminations in piezo-bonded laminated composites. Improved layerwise theory and finite element method are adopted to develop the electromechanically coupled governing equation of a smart composite laminate with and without delaminations. Transient responses of the healthy and damaged structures are obtained through a surface bonded piezoelectric sensor by solving the governing equation in the time domain. Wavelet packet transform (WPT) and linear discriminant analysis (LDA) are employed to extract discriminative features from the structural vibration response of the healthy and delaminated structures. Dendrogram-based support vector machine (DSVM) is used to classify the discriminative features. The confusion matrix of the classification algorithm provided physically consistent results.

Nonparametric, Coupled ,Bayesian ,Dictionary ,and Classifier Learning for Hyperspectral Classification.

PubMed

Akhtar, Naveed; Mian, Ajmal

2017-10-03

We present a principled approach to learn a discriminative dictionary along a linear classifier for hyperspectral classification. Our approach places Gaussian Process priors over the dictionary to account for the relative smoothness of the natural spectra, whereas the classifier parameters are sampled from multivariate Gaussians. We employ two Beta-Bernoulli processes to jointly infer the dictionary and the classifier. These processes are coupled under the same sets of Bernoulli distributions. In our approach, these distributions signify the frequency of the dictionary atom usage in representing class-specific training spectra, which also makes the dictionary discriminative. Due to the coupling between the dictionary and the classifier, the popularity of the atoms for representing different classes gets encoded into the classifier. This helps in predicting the class labels of test spectra that are first represented over the dictionary by solving a simultaneous sparse optimization problem. The labels of the spectra are predicted by feeding the resulting representations to the classifier. Our approach exploits the nonparametric Bayesian framework to automatically infer the dictionary size--the key parameter in discriminative dictionary learning. Moreover, it also has the desirable property of adaptively learning the association between the dictionary atoms and the class labels by itself. We use Gibbs sampling to infer the posterior probability distributions over the dictionary and the classifier under the proposed model, for which, we derive analytical expressions. To establish the effectiveness of our approach, we test it on benchmark hyperspectral images. The classification performance is compared with the state-of-the-art dictionary learning-based classification methods.

Discriminative illumination: per-pixel classification of raw materials based on optimal projections of spectral BRDF.

PubMed

Liu, Chao; Gu, Jinwei

2014-01-01

Classifying raw, unpainted materials--metal, plastic, ceramic, fabric, and so on--is an important yet challenging task for computer vision. Previous works measure subsets of surface spectral reflectance as features for classification. However, acquiring the full spectral reflectance is time consuming and error-prone. In this paper, we propose to use coded illumination to directly measure discriminative features for material classification. Optimal illumination patterns--which we call "discriminative illumination"--are learned from training samples, after projecting to which the spectral reflectance of different materials are maximally separated. This projection is automatically realized by the integration of incident light for surface reflection. While a single discriminative illumination is capable of linear, two-class classification, we show that multiple discriminative illuminations can be used for nonlinear and multiclass classification. We also show theoretically that the proposed method has higher signal-to-noise ratio than previous methods due to light multiplexing. Finally, we construct an LED-based multispectral dome and use the discriminative illumination method for classifying a variety of raw materials, including metal (aluminum, alloy, steel, stainless steel, brass, and copper), plastic, ceramic, fabric, and wood. Experimental results demonstrate its effectiveness.

Variations in the Intragene Methylation Profiles Hallmark Induced Pluripotency

PubMed Central

Druzhkov, Pavel; Zolotykh, Nikolay; Meyerov, Iosif; Alsaedi, Ahmed; Shutova, Maria; Ivanchenko, Mikhail; Zaikin, Alexey

2015-01-01

We demonstrate the potential of differentiating embryonic and induced pluripotent stem cells by the regularized linear and decision tree machine learning classification algorithms, based on a number of intragene methylation measures. The resulting average accuracy of classification has been proven to be above 95%, which overcomes the earlier achievements. We propose a constructive and transparent method of feature selection based on classifier accuracy. Enrichment analysis reveals statistically meaningful presence of stemness group and cancer discriminating genes among the selected best classifying features. These findings stimulate the further research on the functional consequences of these differences in methylation patterns. The presented approach can be broadly used to discriminate the cells of different phenotype or in different state by their methylation profiles, identify groups of genes constituting multifeature classifiers, and assess enrichment of these groups by the sets of genes with a functionality of interest. PMID:26618180

Predictive models reduce talent development costs in female gymnastics.

PubMed

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

2017-04-01

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

Combining features from ERP components in single-trial EEG for discriminating four-category visual objects.

PubMed

Wang, Changming; Xiong, Shi; Hu, Xiaoping; Yao, Li; Zhang, Jiacai

2012-10-01

Categorization of images containing visual objects can be successfully recognized using single-trial electroencephalograph (EEG) measured when subjects view images. Previous studies have shown that task-related information contained in event-related potential (ERP) components could discriminate two or three categories of object images. In this study, we investigated whether four categories of objects (human faces, buildings, cats and cars) could be mutually discriminated using single-trial EEG data. Here, the EEG waveforms acquired while subjects were viewing four categories of object images were segmented into several ERP components (P1, N1, P2a and P2b), and then Fisher linear discriminant analysis (Fisher-LDA) was used to classify EEG features extracted from ERP components. Firstly, we compared the classification results using features from single ERP components, and identified that the N1 component achieved the highest classification accuracies. Secondly, we discriminated four categories of objects using combining features from multiple ERP components, and showed that combination of ERP components improved four-category classification accuracies by utilizing the complementarity of discriminative information in ERP components. These findings confirmed that four categories of object images could be discriminated with single-trial EEG and could direct us to select effective EEG features for classifying visual objects.

Life satisfaction and trauma in clinical and non-clinical children living in a war-torn environment: A discriminant analysis.

PubMed

Veronese, Guido; Pepe, Alessandro

2017-07-01

The aim of this work was to discriminate between healthy children and children at risk of developing mental impairments by evaluating the impact on contextual and individual factors of a context characterized by war. We tested the hypothesis that a linear discriminant function composed of trauma, life satisfaction, and affect balance has the power to classify the children as community or clinical referred. Membership of the clinical-referred group was associated with poorer life satisfaction and higher levels of trauma. Community-referred profiles were associated with lesser trauma. Perceived life satisfaction regarding family and school was the main contributor to the discriminant function.

A Prototype SSVEP Based Real Time BCI Gaming System

PubMed Central

Martišius, Ignas

2016-01-01

Although brain-computer interface technology is mainly designed with disabled people in mind, it can also be beneficial to healthy subjects, for example, in gaming or virtual reality systems. In this paper we discuss the typical architecture, paradigms, requirements, and limitations of electroencephalogram-based gaming systems. We have developed a prototype three-class brain-computer interface system, based on the steady state visually evoked potentials paradigm and the Emotiv EPOC headset. An online target shooting game, implemented in the OpenViBE environment, has been used for user feedback. The system utilizes wave atom transform for feature extraction, achieving an average accuracy of 78.2% using linear discriminant analysis classifier, 79.3% using support vector machine classifier with a linear kernel, and 80.5% using a support vector machine classifier with a radial basis function kernel. PMID:27051414

A Prototype SSVEP Based Real Time BCI Gaming System.

PubMed

Martišius, Ignas; Damaševičius, Robertas

2016-01-01

Although brain-computer interface technology is mainly designed with disabled people in mind, it can also be beneficial to healthy subjects, for example, in gaming or virtual reality systems. In this paper we discuss the typical architecture, paradigms, requirements, and limitations of electroencephalogram-based gaming systems. We have developed a prototype three-class brain-computer interface system, based on the steady state visually evoked potentials paradigm and the Emotiv EPOC headset. An online target shooting game, implemented in the OpenViBE environment, has been used for user feedback. The system utilizes wave atom transform for feature extraction, achieving an average accuracy of 78.2% using linear discriminant analysis classifier, 79.3% using support vector machine classifier with a linear kernel, and 80.5% using a support vector machine classifier with a radial basis function kernel.

Realistic Subsurface Anomaly Discrimination Using Electromagnetic Induction and an SVM Classifier

DTIC Science & Technology

2010-01-01

proposed by Pasion and Oldenburg [25]: Q(t) = kt−βe−γt. (10) Various combinations of these fitting parameters can be used as inputs to classifier... Pasion -Oldenburg parameters k, β, and γ for each anomaly by a direct nonlinear least-squares fit of (10) and by linear (pseudo)inversion of its...combinations of the Pasion -Oldenburg parameters. Com- bining k and γ yields results similar to those of k and R, as Figure 7 and Table 2 show. Figure 8 and

Spatial-temporal discriminant analysis for ERP-based brain-computer interface.

PubMed

Zhang, Yu; Zhou, Guoxu; Zhao, Qibin; Jin, Jing; Wang, Xingyu; Cichocki, Andrzej

2013-03-01

Linear discriminant analysis (LDA) has been widely adopted to classify event-related potential (ERP) in brain-computer interface (BCI). Good classification performance of the ERP-based BCI usually requires sufficient data recordings for effective training of the LDA classifier, and hence a long system calibration time which however may depress the system practicability and cause the users resistance to the BCI system. In this study, we introduce a spatial-temporal discriminant analysis (STDA) to ERP classification. As a multiway extension of the LDA, the STDA method tries to maximize the discriminant information between target and nontarget classes through finding two projection matrices from spatial and temporal dimensions collaboratively, which reduces effectively the feature dimensionality in the discriminant analysis, and hence decreases significantly the number of required training samples. The proposed STDA method was validated with dataset II of the BCI Competition III and dataset recorded from our own experiments, and compared to the state-of-the-art algorithms for ERP classification. Online experiments were additionally implemented for the validation. The superior classification performance in using few training samples shows that the STDA is effective to reduce the system calibration time and improve the classification accuracy, thereby enhancing the practicability of ERP-based BCI.

Predictor of increase in caregiver burden for disabled elderly at home.

PubMed

Okamoto, Kazushi; Harasawa, Yuko

2009-01-01

In order to classify the caregivers at high risk of increase in their burden early, linear discriminant analysis was performed to obtain an effective discriminant model for differentiation of the presence or absence of increase in caregiver burden. The data obtained by self-administered questionnaire from 193 caregivers of frail elderly from January to February of 2005 were used. The discriminant analysis yielded a statistically significant function explaining 35.0% (Rc=0.59; d.f.=6; p=0.0001). The configuration indicated that the psychological predictors of change in caregiver burden with much perceived stress (1.47), high caregiver burden at baseline (1.28), emotional control (0.75), effort to achieve (-0.28), symptomatic depression (0.20) and "ikigai" (purpose in life) (0.18) made statistically significant contributions to the differentiation between no increase and increase in caregiver burden. The discriminant function showed a sensitivity of 86% and specificity of 81%, and successfully classified 83% of the caregivers. The function at baseline is a simple and useful method for screening of an increase in caregiver burden among caregivers for the frail elderly at home.

Joint recognition and discrimination in nonlinear feature space

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1997-09-01

A new general method for linear and nonlinear feature extraction is presented. It is novel since it provides both representation and discrimination while most other methods are concerned with only one of these issues. We call this approach the maximum representation and discrimination feature (MRDF) method and show that the Bayes classifier and the Karhunen- Loeve transform are special cases of it. We refer to our nonlinear feature extraction technique as nonlinear eigen- feature extraction. It is new since it has a closed-form solution and produces nonlinear decision surfaces with higher rank than do iterative methods. Results on synthetic databases are shown and compared with results from standard Fukunaga- Koontz transform and Fisher discriminant function methods. The method is also applied to an automated product inspection problem (discrimination) and to the classification and pose estimation of two similar objects (representation and discrimination).

Discriminative analysis of early Alzheimer's disease based on two intrinsically anti-correlated networks with resting-state fMRI.

PubMed

Wang, Kun; Jiang, Tianzi; Liang, Meng; Wang, Liang; Tian, Lixia; Zhang, Xinqing; Li, Kuncheng; Liu, Zhening

2006-01-01

In this work, we proposed a discriminative model of Alzheimer's disease (AD) on the basis of multivariate pattern classification and functional magnetic resonance imaging (fMRI). This model used the correlation/anti-correlation coefficients of two intrinsically anti-correlated networks in resting brains, which have been suggested by two recent studies, as the feature of classification. Pseudo-Fisher Linear Discriminative Analysis (pFLDA) was then performed on the feature space and a linear classifier was generated. Using leave-one-out (LOO) cross validation, our results showed a correct classification rate of 83%. We also compared the proposed model with another one based on the whole brain functional connectivity. Our proposed model outperformed the other one significantly, and this implied that the two intrinsically anti-correlated networks may be a more susceptible part of the whole brain network in the early stage of AD.

Comparison of discriminant analysis methods: Application to occupational exposure to particulate matter

NASA Astrophysics Data System (ADS)

Ramos, M. Rosário; Carolino, E.; Viegas, Carla; Viegas, Sandra

2016-06-01

Health effects associated with occupational exposure to particulate matter have been studied by several authors. In this study were selected six industries of five different areas: Cork company 1, Cork company 2, poultry, slaughterhouse for cattle, riding arena and production of animal feed. The measurements tool was a portable device for direct reading. This tool provides information on the particle number concentration for six different diameters, namely 0.3 µm, 0.5 µm, 1 µm, 2.5 µm, 5 µm and 10 µm. The focus on these features is because they might be more closely related with adverse health effects. The aim is to identify the particles that better discriminate the industries, with the ultimate goal of classifying industries regarding potential negative effects on workers' health. Several methods of discriminant analysis were applied to data of occupational exposure to particulate matter and compared with respect to classification accuracy. The selected methods were linear discriminant analyses (LDA); linear quadratic discriminant analysis (QDA), robust linear discriminant analysis with selected estimators (MLE (Maximum Likelihood Estimators), MVE (Minimum Volume Elipsoid), "t", MCD (Minimum Covariance Determinant), MCD-A, MCD-B), multinomial logistic regression and artificial neural networks (ANN). The predictive accuracy of the methods was accessed through a simulation study. ANN yielded the highest rate of classification accuracy in the data set under study. Results indicate that the particle number concentration of diameter size 0.5 µm is the parameter that better discriminates industries.

Brownian motion curve-based textural classification and its application in cancer diagnosis.

PubMed

Mookiah, Muthu Rama Krishnan; Shah, Pratik; Chakraborty, Chandan; Ray, Ajoy K

2011-06-01

To develop an automated diagnostic methodology based on textural features of the oral mucosal epithelium to discriminate normal and oral submucous fibrosis (OSF). A total of 83 normal and 29 OSF images from histopathologic sections of the oral mucosa are considered. The proposed diagnostic mechanism consists of two parts: feature extraction using Brownian motion curve (BMC) and design ofa suitable classifier. The discrimination ability of the features has been substantiated by statistical tests. An error back-propagation neural network (BPNN) is used to classify OSF vs. normal. In development of an automated oral cancer diagnostic module, BMC has played an important role in characterizing textural features of the oral images. Fisher's linear discriminant analysis yields 100% sensitivity and 85% specificity, whereas BPNN leads to 92.31% sensitivity and 100% specificity, respectively. In addition to intensity and morphology-based features, textural features are also very important, especially in histopathologic diagnosis of oral cancer. In view of this, a set of textural features are extracted using the BMC for the diagnosis of OSF. Finally, a textural classifier is designed using BPNN, which leads to a diagnostic performance with 96.43% accuracy. (Anal Quant

Personality and affect characteristics of outpatients with depression.

PubMed

Petrocelli, J V; Glaser, B A; Calhoun, G B; Campbell, L F

2001-08-01

This investigation was designed to examine the relationship between depression severity and personality disorders measured by the Millon Clinical Multiaxial Inventory-II (Millon, 1987) and affectivity measured by the Positive Affectivity/Negative Affectivity Schedule (Watson, Clark, & Tellegen, 1988). Discriminant analyses were employed to identify the personality and affective dimensions that maximally discriminate between 4 different levels of depressive severity. Differences between the 4 levels of depressive severity are suggestive of unique patterns of personality characteristics. Discriminant analysis showed that 74.8% of the cases were correctly classified by a single linear discriminant function, and that 61% of the variance in depression severity was accounted for by selected personality and affect variables. Results extend current conceptualizations of comorbidity and are discussed with respect to depression severity.

Discriminative analysis of non-linear brain connectivity for leukoaraiosis with resting-state fMRI

NASA Astrophysics Data System (ADS)

Lai, Youzhi; Xu, Lele; Yao, Li; Wu, Xia

2015-03-01

Leukoaraiosis (LA) describes diffuse white matter abnormalities on CT or MR brain scans, often seen in the normal elderly and in association with vascular risk factors such as hypertension, or in the context of cognitive impairment. The mechanism of cognitive dysfunction is still unclear. The recent clinical studies have revealed that the severity of LA was not corresponding to the cognitive level, and functional connectivity analysis is an appropriate method to detect the relation between LA and cognitive decline. However, existing functional connectivity analyses of LA have been mostly limited to linear associations. In this investigation, a novel measure utilizing the extended maximal information coefficient (eMIC) was applied to construct non-linear functional connectivity in 44 LA subjects (9 dementia, 25 mild cognitive impairment (MCI) and 10 cognitively normal (CN)). The strength of non-linear functional connections for the first 1% of discriminative power increased in MCI compared with CN and dementia, which was opposed to its linear counterpart. Further functional network analysis revealed that the changes of the non-linear and linear connectivity have similar but not completely the same spatial distribution in human brain. In the multivariate pattern analysis with multiple classifiers, the non-linear functional connectivity mostly identified dementia, MCI and CN from LA with a relatively higher accuracy rate than the linear measure. Our findings revealed the non-linear functional connectivity provided useful discriminative power in classification of LA, and the spatial distributed changes between the non-linear and linear measure may indicate the underlying mechanism of cognitive dysfunction in LA.

Single-cultivar extra virgin olive oil classification using a potentiometric electronic tongue.

PubMed

Dias, Luís G; Fernandes, Andreia; Veloso, Ana C A; Machado, Adélio A S C; Pereira, José A; Peres, António M

2014-10-01

Label authentication of monovarietal extra virgin olive oils is of great importance. A novel approach based on a potentiometric electronic tongue is proposed to classify oils obtained from single olive cultivars (Portuguese cvs. Cobrançosa, Madural, Verdeal Transmontana; Spanish cvs. Arbequina, Hojiblanca, Picual). A meta-heuristic simulated annealing algorithm was applied to select the most informative sets of sensors to establish predictive linear discriminant models. Olive oils were correctly classified according to olive cultivar (sensitivities greater than 97%) and each Spanish olive oil was satisfactorily discriminated from the Portuguese ones with the exception of cv. Arbequina (sensitivities from 61% to 98%). Also, the discriminant ability was related to the polar compounds contents of olive oils and so, indirectly, with organoleptic properties like bitterness, astringency or pungency. Therefore the proposed E-tongue can be foreseen as a useful auxiliary tool for trained sensory panels for the classification of monovarietal extra virgin olive oils. Copyright © 2014 Elsevier Ltd. All rights reserved.

Identifying Plant Part Composition of Forest Logging Residue Using Infrared Spectral Data and Linear Discriminant Analysis

PubMed Central

Acquah, Gifty E.; Via, Brian K.; Billor, Nedret; Fasina, Oladiran O.; Eckhardt, Lori G.

2016-01-01

As new markets, technologies and economies evolve in the low carbon bioeconomy, forest logging residue, a largely untapped renewable resource will play a vital role. The feedstock can however be variable depending on plant species and plant part component. This heterogeneity can influence the physical, chemical and thermochemical properties of the material, and thus the final yield and quality of products. Although it is challenging to control compositional variability of a batch of feedstock, it is feasible to monitor this heterogeneity and make the necessary changes in process parameters. Such a system will be a first step towards optimization, quality assurance and cost-effectiveness of processes in the emerging biofuel/chemical industry. The objective of this study was therefore to qualitatively classify forest logging residue made up of different plant parts using both near infrared spectroscopy (NIRS) and Fourier transform infrared spectroscopy (FTIRS) together with linear discriminant analysis (LDA). Forest logging residue harvested from several Pinus taeda (loblolly pine) plantations in Alabama, USA, were classified into three plant part components: clean wood, wood and bark and slash (i.e., limbs and foliage). Five-fold cross-validated linear discriminant functions had classification accuracies of over 96% for both NIRS and FTIRS based models. An extra factor/principal component (PC) was however needed to achieve this in FTIRS modeling. Analysis of factor loadings of both NIR and FTIR spectra showed that, the statistically different amount of cellulose in the three plant part components of logging residue contributed to their initial separation. This study demonstrated that NIR or FTIR spectroscopy coupled with PCA and LDA has the potential to be used as a high throughput tool in classifying the plant part makeup of a batch of forest logging residue feedstock. Thus, NIR/FTIR could be employed as a tool to rapidly probe/monitor the variability of forest biomass so that the appropriate online adjustments to parameters can be made in time to ensure process optimization and product quality. PMID:27618901

Development of a universal water signature for the LANDSAT-3 Multispectral Scanner, part 1

NASA Technical Reports Server (NTRS)

Schlosser, E. H.

1980-01-01

A generalized four channel hyperplane to discriminate water from nonwater was developed using LANDSAT-3 multispectral scaner (MSS) scenes and matching same/next day color infrared aerial photography. The MSS scenes varied in sun elevation angle from 40 to 58 deg. The 28 matching air photo frames contained over 1400 water bodies larger than one surface acre. A preliminary water discriminant, was used to screen the data and eliminate from further consideration all pixels distant from water in MSS spectral space. A linear discriminant was iteratively fitted to the labelled pixels. This discriminant correctly classified 98.7% of the water pixels and 98.6% of the nonwater pixels. The discriminant detected 91.3% of the 414 water bodies over 10 acres in surface area, and misclassified as water 36 groups of contiguous nonwater pixels.

Nonlinear Statistical Estimation with Numerical Maximum Likelihood

DTIC Science & Technology

1974-10-01

probably most directly attributable to the speed, precision and compactness of the linear programming algorithm exercised ; the mutual primal-dual...discriminant analysis is to classify the individual as a member of T# or IT, 1 2 according to the relative...Introduction to the Dissertation 1 Introduction to Statistical Estimation Theory 3 Choice of Estimator.. .Density Functions 12 Choice of Estimator

Novel methods of time-resolved fluorescence data analysis for in-vivo tissue characterization: application to atherosclerosis.

PubMed

Jo, J A; Fang, Q; Papaioannou, T; Qiao, J H; Fishbein, M C; Dorafshar, A; Reil, T; Baker, D; Freischlag, J; Marcu, L

2004-01-01

This study investigates the ability of new analytical methods of time-resolved laser-induced fluorescence spectroscopy (TR-LIFS) data to characterize tissue in-vivo, such as the composition of atherosclerotic vulnerable plaques. A total of 73 TR-LIFS measurements were taken in-vivo from the aorta of 8 rabbits, and subsequently analyzed using the Laguerre deconvolution technique. The investigated spots were classified as normal aorta, thin or thick lesions, and lesions rich in either collagen or macrophages/foam-cells. Different linear and nonlinear classification algorithms (linear discriminant analysis, stepwise linear discriminant analysis, principal component analysis, and feedforward neural networks) were developed using spectral and TR features (ratios of intensity values and Laguerre expansion coefficients, respectively). Normal intima and thin lesions were discriminated from thick lesions (sensitivity >90%, specificity 100%) using only spectral features. However, both spectral and time-resolved features were necessary to discriminate thick lesions rich in collagen from thick lesions rich in foam cells (sensitivity >85%, specificity >93%), and thin lesions rich in foam cells from normal aorta and thin lesions rich in collagen (sensitivity >85%, specificity >94%). Based on these findings, we believe that TR-LIFS information derived from the Laguerre expansion coefficients can provide a valuable additional dimension for in-vivo tissue characterization.

Classification of speech dysfluencies using LPC based parameterization techniques.

PubMed

Hariharan, M; Chee, Lim Sin; Ai, Ooi Chia; Yaacob, Sazali

2012-06-01

The goal of this paper is to discuss and compare three feature extraction methods: Linear Predictive Coefficients (LPC), Linear Prediction Cepstral Coefficients (LPCC) and Weighted Linear Prediction Cepstral Coefficients (WLPCC) for recognizing the stuttered events. Speech samples from the University College London Archive of Stuttered Speech (UCLASS) were used for our analysis. The stuttered events were identified through manual segmentation and were used for feature extraction. Two simple classifiers namely, k-nearest neighbour (kNN) and Linear Discriminant Analysis (LDA) were employed for speech dysfluencies classification. Conventional validation method was used for testing the reliability of the classifier results. The study on the effect of different frame length, percentage of overlapping, value of ã in a first order pre-emphasizer and different order p were discussed. The speech dysfluencies classification accuracy was found to be improved by applying statistical normalization before feature extraction. The experimental investigation elucidated LPC, LPCC and WLPCC features can be used for identifying the stuttered events and WLPCC features slightly outperforms LPCC features and LPC features.

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

PubMed

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

2014-01-01

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

A novel Bayesian framework for discriminative feature extraction in Brain-Computer Interfaces.

PubMed

Suk, Heung-Il; Lee, Seong-Whan

2013-02-01

As there has been a paradigm shift in the learning load from a human subject to a computer, machine learning has been considered as a useful tool for Brain-Computer Interfaces (BCIs). In this paper, we propose a novel Bayesian framework for discriminative feature extraction for motor imagery classification in an EEG-based BCI in which the class-discriminative frequency bands and the corresponding spatial filters are optimized by means of the probabilistic and information-theoretic approaches. In our framework, the problem of simultaneous spatiospectral filter optimization is formulated as the estimation of an unknown posterior probability density function (pdf) that represents the probability that a single-trial EEG of predefined mental tasks can be discriminated in a state. In order to estimate the posterior pdf, we propose a particle-based approximation method by extending a factored-sampling technique with a diffusion process. An information-theoretic observation model is also devised to measure discriminative power of features between classes. From the viewpoint of classifier design, the proposed method naturally allows us to construct a spectrally weighted label decision rule by linearly combining the outputs from multiple classifiers. We demonstrate the feasibility and effectiveness of the proposed method by analyzing the results and its success on three public databases.

Chemometric brand differentiation of commercial spices using direct analysis in real time mass spectrometry.

PubMed

Pavlovich, Matthew J; Dunn, Emily E; Hall, Adam B

2016-05-15

Commercial spices represent an emerging class of fuels for improvised explosives. Being able to classify such spices not only by type but also by brand would represent an important step in developing methods to analytically investigate these explosive compositions. Therefore, a combined ambient mass spectrometric/chemometric approach was developed to quickly and accurately classify commercial spices by brand. Direct analysis in real time mass spectrometry (DART-MS) was used to generate mass spectra for samples of black pepper, cayenne pepper, and turmeric, along with four different brands of cinnamon, all dissolved in methanol. Unsupervised learning techniques showed that the cinnamon samples clustered according to brand. Then, we used supervised machine learning algorithms to build chemometric models with a known training set and classified the brands of an unknown testing set of cinnamon samples. Ten independent runs of five-fold cross-validation showed that the training set error for the best-performing models (i.e., the linear discriminant and neural network models) was lower than 2%. The false-positive percentages for these models were 3% or lower, and the false-negative percentages were lower than 10%. In particular, the linear discriminant model perfectly classified the testing set with 0% error. Repeated iterations of training and testing gave similar results, demonstrating the reproducibility of these models. Chemometric models were able to classify the DART mass spectra of commercial cinnamon samples according to brand, with high specificity and low classification error. This method could easily be generalized to other classes of spices, and it could be applied to authenticating questioned commercial samples of spices or to examining evidence from improvised explosives. Copyright © 2016 John Wiley & Sons, Ltd.

Comparative study on fast classification of brick samples by combination of principal component analysis and linear discriminant analysis using stand-off and table-top laser-induced breakdown spectroscopy

NASA Astrophysics Data System (ADS)

Vítková, Gabriela; Prokeš, Lubomír; Novotný, Karel; Pořízka, Pavel; Novotný, Jan; Všianský, Dalibor; Čelko, Ladislav; Kaiser, Jozef

2014-11-01

Focusing on historical aspect, during archeological excavation or restoration works of buildings or different structures built from bricks it is important to determine, preferably in-situ and in real-time, the locality of bricks origin. Fast classification of bricks on the base of Laser-Induced Breakdown Spectroscopy (LIBS) spectra is possible using multivariate statistical methods. Combination of principal component analysis (PCA) and linear discriminant analysis (LDA) was applied in this case. LIBS was used to classify altogether the 29 brick samples from 7 different localities. Realizing comparative study using two different LIBS setups - stand-off and table-top it is shown that stand-off LIBS has a big potential for archeological in-field measurements.

Effect of separate sampling on classification accuracy.

PubMed

Shahrokh Esfahani, Mohammad; Dougherty, Edward R

2014-01-15

Measurements are commonly taken from two phenotypes to build a classifier, where the number of data points from each class is predetermined, not random. In this 'separate sampling' scenario, the data cannot be used to estimate the class prior probabilities. Moreover, predetermined class sizes can severely degrade classifier performance, even for large samples. We employ simulations using both synthetic and real data to show the detrimental effect of separate sampling on a variety of classification rules. We establish propositions related to the effect on the expected classifier error owing to a sampling ratio different from the population class ratio. From these we derive a sample-based minimax sampling ratio and provide an algorithm for approximating it from the data. We also extend to arbitrary distributions the classical population-based Anderson linear discriminant analysis minimax sampling ratio derived from the discriminant form of the Bayes classifier. All the codes for synthetic data and real data examples are written in MATLAB. A function called mmratio, whose output is an approximation of the minimax sampling ratio of a given dataset, is also written in MATLAB. All the codes are available at: http://gsp.tamu.edu/Publications/supplementary/shahrokh13b.

Single-Trial Classification of Multi-User P300-Based Brain-Computer Interface Using Riemannian Geometry.

PubMed

Korczowski, L; Congedo, M; Jutten, C

2015-08-01

The classification of electroencephalographic (EEG) data recorded from multiple users simultaneously is an important challenge in the field of Brain-Computer Interface (BCI). In this paper we compare different approaches for classification of single-trials Event-Related Potential (ERP) on two subjects playing a collaborative BCI game. The minimum distance to mean (MDM) classifier in a Riemannian framework is extended to use the diversity of the inter-subjects spatio-temporal statistics (MDM-hyper) or to merge multiple classifiers (MDM-multi). We show that both these classifiers outperform significantly the mean performance of the two users and analogous classifiers based on the step-wise linear discriminant analysis. More importantly, the MDM-multi outperforms the performance of the best player within the pair.

Application of the laguerre deconvolution method for time-resolved fluorescence spectroscopy to the characterization of atherosclerotic plaques.

PubMed

Jo, J A; Fang, Q; Papaioannou, T; Qiao, J H; Fishbein, M C; Beseth, B; Dorafshar, A H; Reil, T; Baker, D; Freischlag, J; Marcu, L

2005-01-01

This study investigates the ability of time-resolved laser-induced fluorescence spectroscopy (TR-LIFS) to detect inflammation in atherosclerotic lesion, a key feature of plaque vulnerability. A total of 348 TR-LIFS measurements were taken from carotid plaques of 30 patients, and subsequently analyzed using the Laguerre deconvolution technique. The investigated spots were classified as Early, Fibrotic/Calcified or Inflamed lesions. A stepwise linear discriminant analysis algorithm was developed using spectral and TR features (normalized intensity values and Laguerre expansion coefficients at discrete emission wavelengths, respectively). Features from only three emission wavelengths (390, 450 and 500 nm) were used in the classifier. The Inflamed lesions were discriminated with sensitivity > 80% and specificity > 90 %, when the Laguerre expansion coefficients were included in the feature space. These results indicate that TR-LIFS information derived from the Laguerre expansion coefficients at few selected emission wavelengths can discriminate inflammation in atherosclerotic plaques. We believe that TR-LIFS derived Laguerre expansion coefficients can provide a valuable additional dimension for the detection of vulnerable plaques.

Discrimination of premalignant lesions and cancer tissues from normal gastric tissues using Raman spectroscopy

NASA Astrophysics Data System (ADS)

Luo, Shuwen; Chen, Changshui; Mao, Hua; Jin, Shaoqin

2013-06-01

The feasibility of early detection of gastric cancer using near-infrared (NIR) Raman spectroscopy (RS) by distinguishing premalignant lesions (adenomatous polyp, n=27) and cancer tissues (adenocarcinoma, n=33) from normal gastric tissues (n=45) is evaluated. Significant differences in Raman spectra are observed among the normal, adenomatous polyp, and adenocarcinoma gastric tissues at 936, 1003, 1032, 1174, 1208, 1323, 1335, 1450, and 1655 cm-1. Diverse statistical methods are employed to develop effective diagnostic algorithms for classifying the Raman spectra of different types of ex vivo gastric tissues, including principal component analysis (PCA), linear discriminant analysis (LDA), and naive Bayesian classifier (NBC) techniques. Compared with PCA-LDA algorithms, PCA-NBC techniques together with leave-one-out, cross-validation method provide better discriminative results of normal, adenomatous polyp, and adenocarcinoma gastric tissues, resulting in superior sensitivities of 96.3%, 96.9%, and 96.9%, and specificities of 93%, 100%, and 95.2%, respectively. Therefore, NIR RS associated with multivariate statistical algorithms has the potential for early diagnosis of gastric premalignant lesions and cancer tissues in molecular level.

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

PubMed

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

2005-04-15

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

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

NASA Astrophysics Data System (ADS)

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

2017-11-01

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

A comprehensive simulation study on classification of RNA-Seq data.

PubMed

Zararsız, Gökmen; Goksuluk, Dincer; Korkmaz, Selcuk; Eldem, Vahap; Zararsiz, Gozde Erturk; Duru, Izzet Parug; Ozturk, Ahmet

2017-01-01

RNA sequencing (RNA-Seq) is a powerful technique for the gene-expression profiling of organisms that uses the capabilities of next-generation sequencing technologies. Developing gene-expression-based classification algorithms is an emerging powerful method for diagnosis, disease classification and monitoring at molecular level, as well as providing potential markers of diseases. Most of the statistical methods proposed for the classification of gene-expression data are either based on a continuous scale (eg. microarray data) or require a normal distribution assumption. Hence, these methods cannot be directly applied to RNA-Seq data since they violate both data structure and distributional assumptions. However, it is possible to apply these algorithms with appropriate modifications to RNA-Seq data. One way is to develop count-based classifiers, such as Poisson linear discriminant analysis and negative binomial linear discriminant analysis. Another way is to bring the data closer to microarrays and apply microarray-based classifiers. In this study, we compared several classifiers including PLDA with and without power transformation, NBLDA, single SVM, bagging SVM (bagSVM), classification and regression trees (CART), and random forests (RF). We also examined the effect of several parameters such as overdispersion, sample size, number of genes, number of classes, differential-expression rate, and the transformation method on model performances. A comprehensive simulation study is conducted and the results are compared with the results of two miRNA and two mRNA experimental datasets. The results revealed that increasing the sample size, differential-expression rate and decreasing the dispersion parameter and number of groups lead to an increase in classification accuracy. Similar with differential-expression studies, the classification of RNA-Seq data requires careful attention when handling data overdispersion. We conclude that, as a count-based classifier, the power transformed PLDA and, as a microarray-based classifier, vst or rlog transformed RF and SVM classifiers may be a good choice for classification. An R/BIOCONDUCTOR package, MLSeq, is freely available at https://www.bioconductor.org/packages/release/bioc/html/MLSeq.html.

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

PubMed

Chen, Shizhi; Yang, Xiaodong; Tian, Yingli

2015-09-01

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

Towards exaggerated emphysema stereotypes

NASA Astrophysics Data System (ADS)

Chen, C.; Sørensen, L.; Lauze, F.; Igel, C.; Loog, M.; Feragen, A.; de Bruijne, M.; Nielsen, M.

2012-03-01

Classification is widely used in the context of medical image analysis and in order to illustrate the mechanism of a classifier, we introduce the notion of an exaggerated image stereotype based on training data and trained classifier. The stereotype of some image class of interest should emphasize/exaggerate the characteristic patterns in an image class and visualize the information the employed classifier relies on. This is useful for gaining insight into the classification and serves for comparison with the biological models of disease. In this work, we build exaggerated image stereotypes by optimizing an objective function which consists of a discriminative term based on the classification accuracy, and a generative term based on the class distributions. A gradient descent method based on iterated conditional modes (ICM) is employed for optimization. We use this idea with Fisher's linear discriminant rule and assume a multivariate normal distribution for samples within a class. The proposed framework is applied to computed tomography (CT) images of lung tissue with emphysema. The synthesized stereotypes illustrate the exaggerated patterns of lung tissue with emphysema, which is underpinned by three different quantitative evaluation methods.

Application of Linear Discriminant Analysis in Dimensionality Reduction for Hand Motion Classification

NASA Astrophysics Data System (ADS)

Phinyomark, A.; Hu, H.; Phukpattaranont, P.; Limsakul, C.

2012-01-01

The classification of upper-limb movements based on surface electromyography (EMG) signals is an important issue in the control of assistive devices and rehabilitation systems. Increasing the number of EMG channels and features in order to increase the number of control commands can yield a high dimensional feature vector. To cope with the accuracy and computation problems associated with high dimensionality, it is commonplace to apply a processing step that transforms the data to a space of significantly lower dimensions with only a limited loss of useful information. Linear discriminant analysis (LDA) has been successfully applied as an EMG feature projection method. Recently, a number of extended LDA-based algorithms have been proposed, which are more competitive in terms of both classification accuracy and computational costs/times with classical LDA. This paper presents the findings of a comparative study of classical LDA and five extended LDA methods. From a quantitative comparison based on seven multi-feature sets, three extended LDA-based algorithms, consisting of uncorrelated LDA, orthogonal LDA and orthogonal fuzzy neighborhood discriminant analysis, produce better class separability when compared with a baseline system (without feature projection), principle component analysis (PCA), and classical LDA. Based on a 7-dimension time domain and time-scale feature vectors, these methods achieved respectively 95.2% and 93.2% classification accuracy by using a linear discriminant classifier.

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.

Analysis of longitudinal diffusion-weighted images in healthy and pathological aging: An ADNI study.

PubMed

Kruggel, Frithjof; Masaki, Fumitaro; Solodkin, Ana

2017-02-15

The widely used framework of voxel-based morphometry for analyzing neuroimages is extended here to model longitudinal imaging data by exchanging the linear model with a linear mixed-effects model. The new approach is employed for analyzing a large longitudinal sample of 756 diffusion-weighted images acquired in 177 subjects of the Alzheimer's Disease Neuroimaging initiative (ADNI). While sample- and group-level results from both approaches are equivalent, the mixed-effect model yields information at the single subject level. Interestingly, the neurobiological relevance of the relevant parameter at the individual level describes specific differences associated with aging. In addition, our approach highlights white matter areas that reliably discriminate between patients with Alzheimer's disease and healthy controls with a predictive power of 0.99 and include the hippocampal alveus, the para-hippocampal white matter, the white matter of the posterior cingulate, and optic tracts. In this context, notably the classifier includes a sub-population of patients with minimal cognitive impairment into the pathological domain. Our classifier offers promising features for an accessible biomarker that predicts the risk of conversion to Alzheimer's disease. Data used in preparation of this article were obtained from the Alzheimer's Disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu). As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at: http://adni.loni.usc.edu/wp-content/uploads/how to apply/ADNI Acknowledgement List.pdf. Significance statement This study assesses neuro-degenerative processes in the brain's white matter as revealed by diffusion-weighted imaging, in order to discriminate healthy from pathological aging in a large sample of elderly subjects. The analysis of time-series examinations in a linear mixed effects model allowed the discrimination of population-based aging processes from individual determinants. We demonstrate that a simple classifier based on white matter imaging data is able to predict the conversion to Alzheimer's disease with a high predictive power. Copyright © 2017 Elsevier B.V. All rights reserved.

Parametric Time-Frequency Analysis and Its Applications in Music Classification

NASA Astrophysics Data System (ADS)

Shen, Ying; Li, Xiaoli; Ma, Ngok-Wah; Krishnan, Sridhar

2010-12-01

Analysis of nonstationary signals, such as music signals, is a challenging task. The purpose of this study is to explore an efficient and powerful technique to analyze and classify music signals in higher frequency range (44.1 kHz). The pursuit methods are good tools for this purpose, but they aimed at representing the signals rather than classifying them as in Y. Paragakin et al., 2009. Among the pursuit methods, matching pursuit (MP), an adaptive true nonstationary time-frequency signal analysis tool, is applied for music classification. First, MP decomposes the sample signals into time-frequency functions or atoms. Atom parameters are then analyzed and manipulated, and discriminant features are extracted from atom parameters. Besides the parameters obtained using MP, an additional feature, central energy, is also derived. Linear discriminant analysis and the leave-one-out method are used to evaluate the classification accuracy rate for different feature sets. The study is one of the very few works that analyze atoms statistically and extract discriminant features directly from the parameters. From our experiments, it is evident that the MP algorithm with the Gabor dictionary decomposes nonstationary signals, such as music signals, into atoms in which the parameters contain strong discriminant information sufficient for accurate and efficient signal classifications.

Thyroid nodule classification using ultrasound elastography via linear discriminant analysis.

PubMed

Luo, Si; Kim, Eung-Hun; Dighe, Manjiri; Kim, Yongmin

2011-05-01

The non-surgical diagnosis of thyroid nodules is currently made via a fine needle aspiration (FNA) biopsy. It is estimated that somewhere between 250,000 and 300,000 thyroid FNA biopsies are performed in the United States annually. However, a large percentage (approximately 70%) of these biopsies turn out to be benign. Since the aggressive FNA management of thyroid nodules is costly, quantitative risk assessment and stratification of a nodule's malignancy is of value in triage and more appropriate healthcare resources utilization. In this paper, we introduce a new method for classifying the thyroid nodules based on the ultrasound (US) elastography features. Unlike approaches to assess the stiffness of a thyroid nodule by visually inspecting the pseudo-color pattern in the strain image, we use a classification algorithm to stratify the nodule by using the power spectrum of strain rate waveform extracted from the US elastography image sequence. Pulsation from the carotid artery was used to compress the thyroid nodules. Ultrasound data previously acquired from 98 thyroid nodules were used in this retrospective study to evaluate our classification algorithm. A classifier was developed based on the linear discriminant analysis (LDA) and used to differentiate the thyroid nodules into two types: (I) no FNA (observation-only) and (II) FNA. Using our method, 62 nodules were classified as type I, all of which were benign, while 36 nodules were classified as Type-II, 16 malignant and 20 benign, resulting in a sensitivity of 100% and specificity of 75.6% in detecting malignant thyroid nodules. This indicates that our triage method based on US elastography has the potential to substantially reduce the number of FNA biopsies (63.3%) by detecting benign nodules and managing them via follow-up observations rather than an FNA biopsy. Published by Elsevier B.V.

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/.

Prediction of Potential Hit Song and Musical Genre Using Artificial Neural Networks

NASA Astrophysics Data System (ADS)

Monterola, Christopher; Abundo, Cheryl; Tugaff, Jeric; Venturina, Lorcel Ericka

Accurately quantifying the goodness of music based on the seemingly subjective taste of the public is a multi-million industry. Recording companies can make sound decisions on which songs or artists to prioritize if accurate forecasting is achieved. We extract 56 single-valued musical features (e.g. pitch and tempo) from 380 Original Pilipino Music (OPM) songs (190 are hit songs) released from 2004 to 2006. Based on an effect size criterion which measures a variable's discriminating power, the 20 highest ranked features are fed to a classifier tasked to predict hit songs. We show that regardless of musical genre, a trained feed-forward neural network (NN) can predict potential hit songs with an average accuracy of ΦNN = 81%. The accuracy is about +20% higher than those of standard classifiers such as linear discriminant analysis (LDA, ΦLDA = 61%) and classification and regression trees (CART, ΦCART = 57%). Both LDA and CART are above the proportional chance criterion (PCC, ΦPCC = 50%) but are slightly below the suggested acceptable classifier requirement of 1.25*ΦPCC = 63%. Utilizing a similar procedure, we demonstrate that different genres (ballad, alternative rock or rock) of OPM songs can be automatically classified with near perfect accuracy using LDA or NN but only around 77% using CART.

Combining various types of classifiers and features extracted from magnetic resonance imaging data in schizophrenia recognition.

PubMed

Janousova, Eva; Schwarz, Daniel; Kasparek, Tomas

2015-06-30

We investigated a combination of three classification algorithms, namely the modified maximum uncertainty linear discriminant analysis (mMLDA), the centroid method, and the average linkage, with three types of features extracted from three-dimensional T1-weighted magnetic resonance (MR) brain images, specifically MR intensities, grey matter densities, and local deformations for distinguishing 49 first episode schizophrenia male patients from 49 healthy male subjects. The feature sets were reduced using intersubject principal component analysis before classification. By combining the classifiers, we were able to obtain slightly improved results when compared with single classifiers. The best classification performance (81.6% accuracy, 75.5% sensitivity, and 87.8% specificity) was significantly better than classification by chance. We also showed that classifiers based on features calculated using more computation-intensive image preprocessing perform better; mMLDA with classification boundary calculated as weighted mean discriminative scores of the groups had improved sensitivity but similar accuracy compared to the original MLDA; reducing a number of eigenvectors during data reduction did not always lead to higher classification accuracy, since noise as well as the signal important for classification were removed. Our findings provide important information for schizophrenia research and may improve accuracy of computer-aided diagnostics of neuropsychiatric diseases. Copyright © 2015 Elsevier Ireland Ltd. All rights reserved.

Accurate discrimination of Alzheimer's disease from other dementia and/or normal subjects using SPECT specific volume analysis

NASA Astrophysics Data System (ADS)

Iyatomi, Hitoshi; Hashimoto, Jun; Yoshii, Fumuhito; Kazama, Toshiki; Kawada, Shuichi; Imai, Yutaka

2014-03-01

Discrimination between Alzheimer's disease and other dementia is clinically significant, however it is often difficult. In this study, we developed classification models among Alzheimer's disease (AD), other dementia (OD) and/or normal subjects (NC) using patient factors and indices obtained by brain perfusion SPECT. SPECT is commonly used to assess cerebral blood flow (CBF) and allows the evaluation of the severity of hypoperfusion by introducing statistical parametric mapping (SPM). We investigated a total of 150 cases (50 cases each for AD, OD, and NC) from Tokai University Hospital, Japan. In each case, we obtained a total of 127 candidate parameters from: (A) 2 patient factors (age and sex), (B) 12 CBF parameters and 113 SPM parameters including (C) 3 from specific volume analysis (SVA), and (D) 110 from voxel-based analysis stereotactic extraction estimation (vbSEE). We built linear classifiers with a statistical stepwise feature selection and evaluated the performance with the leave-one-out cross validation strategy. Our classifiers achieved very high classification performances with reasonable number of selected parameters. In the most significant discrimination in clinical, namely those of AD from OD, our classifier achieved both sensitivity (SE) and specificity (SP) of 96%. In a similar way, our classifiers achieved a SE of 90% and a SP of 98% in AD from NC, as well as a SE of 88% and a SP of 86% in AD from OD and NC cases. Introducing SPM indices such as SVA and vbSEE, classification performances improved around 7-15%. We confirmed that these SPM factors are quite important for diagnosing Alzheimer's disease.

Automated discrimination of dementia spectrum disorders using extreme learning machine and structural T1 MRI features.

PubMed

Jongin Kim; Boreom Lee

2017-07-01

The classification of neuroimaging data for the diagnosis of Alzheimer's Disease (AD) is one of the main research goals of the neuroscience and clinical fields. In this study, we performed extreme learning machine (ELM) classifier to discriminate the AD, mild cognitive impairment (MCI) from normal control (NC). We compared the performance of ELM with that of a linear kernel support vector machine (SVM) for 718 structural MRI images from Alzheimer's Disease Neuroimaging Initiative (ADNI) database. The data consisted of normal control, MCI converter (MCI-C), MCI non-converter (MCI-NC), and AD. We employed SVM-based recursive feature elimination (RFE-SVM) algorithm to find the optimal subset of features. In this study, we found that the RFE-SVM feature selection approach in combination with ELM shows the superior classification accuracy to that of linear kernel SVM for structural T1 MRI data.

Development of a universal water signature for the LANDSAT-3 Multispectral Scanner, part 2 of 2

NASA Technical Reports Server (NTRS)

Schlosser, E. H.

1980-01-01

A generalized four-channel hyperplane to discriminate water from non-water was developed using LANDSAT-3 multispectral scanner (MSS) scences and matching same/next-day color infrared aerial photography. The MSS scenes over upstate New York, eastern Washington, Montana and Louisiana taken between May and October 1978 varied in Sun elevation angle from 40 to 58 degrees. The 28 matching air photo frames selected for analysis contained over 1400 water bodies larger than one surface acre. A preliminary water discriminant was used to screen the data and eliminate from further consideration all pixels distant from water in MSS spectral space. Approximately 1300 pixels, half of them non-edge water pixels and half non-water pixels spectrally close to water, were labelled. A linear discriminant was iteratively fitted to the labelled pixels, giving more weight to those pixels that were difficult to discriminate. This discriminant correctly classified 98.7 percent of the water pixels and 98.6 percent of the non-water pixels.

Margin-maximizing feature elimination methods for linear and nonlinear kernel-based discriminant functions.

PubMed

Aksu, Yaman; Miller, David J; Kesidis, George; Yang, Qing X

2010-05-01

Feature selection for classification in high-dimensional spaces can improve generalization, reduce classifier complexity, and identify important, discriminating feature "markers." For support vector machine (SVM) classification, a widely used technique is recursive feature elimination (RFE). We demonstrate that RFE is not consistent with margin maximization, central to the SVM learning approach. We thus propose explicit margin-based feature elimination (MFE) for SVMs and demonstrate both improved margin and improved generalization, compared with RFE. Moreover, for the case of a nonlinear kernel, we show that RFE assumes that the squared weight vector 2-norm is strictly decreasing as features are eliminated. We demonstrate this is not true for the Gaussian kernel and, consequently, RFE may give poor results in this case. MFE for nonlinear kernels gives better margin and generalization. We also present an extension which achieves further margin gains, by optimizing only two degrees of freedom--the hyperplane's intercept and its squared 2-norm--with the weight vector orientation fixed. We finally introduce an extension that allows margin slackness. We compare against several alternatives, including RFE and a linear programming method that embeds feature selection within the classifier design. On high-dimensional gene microarray data sets, University of California at Irvine (UCI) repository data sets, and Alzheimer's disease brain image data, MFE methods give promising results.

Recognition of aspect-dependent three-dimensional objects by an echolocating Atlantic bottlenose dolphin.

PubMed

Helweg, D A; Roitblat, H L; Nachtigall, P E; Hautus, M J

1996-01-01

We examined the ability of a bottlenose dolphin (Tursiops truncatus) to recognize aspect-dependent objects using echolocation. An aspect-dependent object such as a cube produces acoustically different echoes at different angles relative to the echolocation signal. The dolphin recognized the objects even though the objects were free to rotate and sway. A linear discriminant analysis and nearest centroid classifier could classify the objects using average amplitude, center frequency, and bandwidth of object echoes. The results show that dolphins can use varying acoustic properties to recognize constant objects and suggest that aspect-independent representations may be formed by combining information gleaned from multiple echoes.

Auditory evoked potentials in patients with major depressive disorder measured by Emotiv system.

PubMed

Wang, Dongcui; Mo, Fongming; Zhang, Yangde; Yang, Chao; Liu, Jun; Chen, Zhencheng; Zhao, Jinfeng

2015-01-01

In a previous study (unpublished), Emotiv headset was validated for capturing event-related potentials (ERPs) from normal subjects. In the present follow-up study, the signal quality of Emotiv headset was tested by the accuracy rate of discriminating Major Depressive Disorder (MDD) patients from the normal subjects. ERPs of 22 MDD patients and 15 normal subjects were induced by an auditory oddball task and the amplitude of N1, N2 and P3 of ERP components were specifically analyzed. The features of ERPs were statistically investigated. It is found that Emotiv headset is capable of discriminating the abnormal N1, N2 and P3 components in MDD patients. Relief-F algorithm was applied to all features for feature selection. The selected features were then input to a linear discriminant analysis (LDA) classifier with leave-one-out cross-validation to characterize the ERP features of MDD. 127 possible combinations out of the selected 7 ERP features were classified using LDA. The best classification accuracy was achieved to be 89.66%. These results suggest that MDD patients are identifiable from normal subjects by ERPs measured by Emotiv headset.

Discriminating the Mineralogical Composition in Drill Cuttings Based on Absorption Spectra in the Terahertz Range.

PubMed

Miao, Xinyang; Li, Hao; Bao, Rima; Feng, Chengjing; Wu, Hang; Zhan, Honglei; Li, Yizhang; Zhao, Kun

2017-02-01

Understanding the geological units of a reservoir is essential to the development and management of the resource. In this paper, drill cuttings from several depths from an oilfield were studied using terahertz time domain spectroscopy (THz-TDS). Cluster analysis (CA) and principal component analysis (PCA) were employed to classify and analyze the cuttings. The cuttings were clearly classified based on CA and PCA methods, and the results were in agreement with the lithology. Moreover, calcite and dolomite have stronger absorption of a THz pulse than any other minerals, based on an analysis of the PC1 scores. Quantitative analyses of minor minerals were also realized by building a series of linear and non-linear models between contents and PC2 scores. The results prove THz technology to be a promising means for determining reservoir lithology as well as other properties, which will be a significant supplementary method in oil fields.

Computer aided diagnosis system for Alzheimer disease using brain diffusion tensor imaging features selected by Pearson's correlation.

PubMed

Graña, M; Termenon, M; Savio, A; Gonzalez-Pinto, A; Echeveste, J; Pérez, J M; Besga, A

2011-09-20

The aim of this paper is to obtain discriminant features from two scalar measures of Diffusion Tensor Imaging (DTI) data, Fractional Anisotropy (FA) and Mean Diffusivity (MD), and to train and test classifiers able to discriminate Alzheimer's Disease (AD) patients from controls on the basis of features extracted from the FA or MD volumes. In this study, support vector machine (SVM) classifier was trained and tested on FA and MD data. Feature selection is done computing the Pearson's correlation between FA or MD values at voxel site across subjects and the indicative variable specifying the subject class. Voxel sites with high absolute correlation are selected for feature extraction. Results are obtained over an on-going study in Hospital de Santiago Apostol collecting anatomical T1-weighted MRI volumes and DTI data from healthy control subjects and AD patients. FA features and a linear SVM classifier achieve perfect accuracy, sensitivity and specificity in several cross-validation studies, supporting the usefulness of DTI-derived features as an image-marker for AD and to the feasibility of building Computer Aided Diagnosis systems for AD based on them. Copyright © 2011 Elsevier Ireland Ltd. All rights reserved.

Hormonally active agents in the environment and children's behavior: assessing effects on children's gender-dimorphic outcomes.

PubMed

Sandberg, David E; Vena, John E; Weiner, John; Beehler, Gregory P; Swanson, Mya; Meyer-Bahlburg, Heino F L

2003-03-01

Early sex hormone exposure contributes to gender-dimorphic behavioral development in mammals, including humans. Environmental toxicants concentrated in contaminated sport fish can interfere with the actions of sex steroids. This study developed an outcome variable by combining gender-dimorphic behaviors that differentiates boys and girls. Offspring of participants in the New York State Angler Cohort Study (NYSACS) were targeted in a parent-report postal survey. Instruments were selected based on findings of gender differences in the general population. A linear discriminant function model incorporating three gender behavior scales correctly classified the sex of 97.7% of children (252 boys and 234 girls) from a random NYSACS sample. The discriminant function was cross-validated by correctly classifying the sex of 98.4% of children (457 boys and 425 girls) from the remaining NYSACS cases and 97.6% of children (154 boys and 142 girls) from an independent school sample. Within-sex stepwise multiple regression analyses revealed that masculine behavior increased among boys with age and with the number of years of maternal sport fish consumption. In girls, older age and previous live-born siblings were associated with more masculine behavior, whereas feminine behavior increased with the duration of breast feeding. These associations were replicated in an independent sample. A linear discriminant function effectively transformed the binary classification of sex (male-female) to a bipolar continuum of gender (masculinity-femininity). Findings from this study are consistent with the hypothesis that environmental contaminants contribute to shifts in gender-role behavior. Future investigations will need to account for competing explanations of this effect.

Multi-class ERP-based BCI data analysis using a discriminant space self-organizing map.

PubMed

Onishi, Akinari; Natsume, Kiyohisa

2014-01-01

Emotional or non-emotional image stimulus is recently applied to event-related potential (ERP) based brain computer interfaces (BCI). Though the classification performance is over 80% in a single trial, a discrimination between those ERPs has not been considered. In this research we tried to clarify the discriminability of four-class ERP-based BCI target data elicited by desk, seal, spider images and letter intensifications. A conventional self organizing map (SOM) and newly proposed discriminant space SOM (ds-SOM) were applied, then the discriminabilites were visualized. We also classify all pairs of those ERPs by stepwise linear discriminant analysis (SWLDA) and verify the visualization of discriminabilities. As a result, the ds-SOM showed understandable visualization of the data with a shorter computational time than the traditional SOM. We also confirmed the clear boundary between the letter cluster and the other clusters. The result was coherent with the classification performances by SWLDA. The method might be helpful not only for developing a new BCI paradigm, but also for the big data analysis.

Novel nonlinear knowledge-based mean force potentials based on machine learning.

PubMed

Dong, Qiwen; Zhou, Shuigeng

2011-01-01

The prediction of 3D structures of proteins from amino acid sequences is one of the most challenging problems in molecular biology. An essential task for solving this problem with coarse-grained models is to deduce effective interaction potentials. The development and evaluation of new energy functions is critical to accurately modeling the properties of biological macromolecules. Knowledge-based mean force potentials are derived from statistical analysis of proteins of known structures. Current knowledge-based potentials are almost in the form of weighted linear sum of interaction pairs. In this study, a class of novel nonlinear knowledge-based mean force potentials is presented. The potential parameters are obtained by nonlinear classifiers, instead of relative frequencies of interaction pairs against a reference state or linear classifiers. The support vector machine is used to derive the potential parameters on data sets that contain both native structures and decoy structures. Five knowledge-based mean force Boltzmann-based or linear potentials are introduced and their corresponding nonlinear potentials are implemented. They are the DIH potential (single-body residue-level Boltzmann-based potential), the DFIRE-SCM potential (two-body residue-level Boltzmann-based potential), the FS potential (two-body atom-level Boltzmann-based potential), the HR potential (two-body residue-level linear potential), and the T32S3 potential (two-body atom-level linear potential). Experiments are performed on well-established decoy sets, including the LKF data set, the CASP7 data set, and the Decoys “R”Us data set. The evaluation metrics include the energy Z score and the ability of each potential to discriminate native structures from a set of decoy structures. Experimental results show that all nonlinear potentials significantly outperform the corresponding Boltzmann-based or linear potentials, and the proposed discriminative framework is effective in developing knowledge-based mean force potentials. The nonlinear potentials can be widely used for ab initio protein structure prediction, model quality assessment, protein docking, and other challenging problems in computational biology.

The Emotion Recognition System Based on Autoregressive Model and Sequential Forward Feature Selection of Electroencephalogram Signals

PubMed Central

Hatamikia, Sepideh; Maghooli, Keivan; Nasrabadi, Ali Motie

2014-01-01

Electroencephalogram (EEG) is one of the useful biological signals to distinguish different brain diseases and mental states. In recent years, detecting different emotional states from biological signals has been merged more attention by researchers and several feature extraction methods and classifiers are suggested to recognize emotions from EEG signals. In this research, we introduce an emotion recognition system using autoregressive (AR) model, sequential forward feature selection (SFS) and K-nearest neighbor (KNN) classifier using EEG signals during emotional audio-visual inductions. The main purpose of this paper is to investigate the performance of AR features in the classification of emotional states. To achieve this goal, a distinguished AR method (Burg's method) based on Levinson-Durbin's recursive algorithm is used and AR coefficients are extracted as feature vectors. In the next step, two different feature selection methods based on SFS algorithm and Davies–Bouldin index are used in order to decrease the complexity of computing and redundancy of features; then, three different classifiers include KNN, quadratic discriminant analysis and linear discriminant analysis are used to discriminate two and three different classes of valence and arousal levels. The proposed method is evaluated with EEG signals of available database for emotion analysis using physiological signals, which are recorded from 32 participants during 40 1 min audio visual inductions. According to the results, AR features are efficient to recognize emotional states from EEG signals, and KNN performs better than two other classifiers in discriminating of both two and three valence/arousal classes. The results also show that SFS method improves accuracies by almost 10-15% as compared to Davies–Bouldin based feature selection. The best accuracies are %72.33 and %74.20 for two classes of valence and arousal and %61.10 and %65.16 for three classes, respectively. PMID:25298928

Discriminative Learning of Receptive Fields from Responses to Non-Gaussian Stimulus Ensembles

PubMed Central

Meyer, Arne F.; Diepenbrock, Jan-Philipp; Happel, Max F. K.; Ohl, Frank W.; Anemüller, Jörn

2014-01-01

Analysis of sensory neurons' processing characteristics requires simultaneous measurement of presented stimuli and concurrent spike responses. The functional transformation from high-dimensional stimulus space to the binary space of spike and non-spike responses is commonly described with linear-nonlinear models, whose linear filter component describes the neuron's receptive field. From a machine learning perspective, this corresponds to the binary classification problem of discriminating spike-eliciting from non-spike-eliciting stimulus examples. The classification-based receptive field (CbRF) estimation method proposed here adapts a linear large-margin classifier to optimally predict experimental stimulus-response data and subsequently interprets learned classifier weights as the neuron's receptive field filter. Computational learning theory provides a theoretical framework for learning from data and guarantees optimality in the sense that the risk of erroneously assigning a spike-eliciting stimulus example to the non-spike class (and vice versa) is minimized. Efficacy of the CbRF method is validated with simulations and for auditory spectro-temporal receptive field (STRF) estimation from experimental recordings in the auditory midbrain of Mongolian gerbils. Acoustic stimulation is performed with frequency-modulated tone complexes that mimic properties of natural stimuli, specifically non-Gaussian amplitude distribution and higher-order correlations. Results demonstrate that the proposed approach successfully identifies correct underlying STRFs, even in cases where second-order methods based on the spike-triggered average (STA) do not. Applied to small data samples, the method is shown to converge on smaller amounts of experimental recordings and with lower estimation variance than the generalized linear model and recent information theoretic methods. Thus, CbRF estimation may prove useful for investigation of neuronal processes in response to natural stimuli and in settings where rapid adaptation is induced by experimental design. PMID:24699631

Discriminative learning of receptive fields from responses to non-Gaussian stimulus ensembles.

PubMed

Meyer, Arne F; Diepenbrock, Jan-Philipp; Happel, Max F K; Ohl, Frank W; Anemüller, Jörn

2014-01-01

Analysis of sensory neurons' processing characteristics requires simultaneous measurement of presented stimuli and concurrent spike responses. The functional transformation from high-dimensional stimulus space to the binary space of spike and non-spike responses is commonly described with linear-nonlinear models, whose linear filter component describes the neuron's receptive field. From a machine learning perspective, this corresponds to the binary classification problem of discriminating spike-eliciting from non-spike-eliciting stimulus examples. The classification-based receptive field (CbRF) estimation method proposed here adapts a linear large-margin classifier to optimally predict experimental stimulus-response data and subsequently interprets learned classifier weights as the neuron's receptive field filter. Computational learning theory provides a theoretical framework for learning from data and guarantees optimality in the sense that the risk of erroneously assigning a spike-eliciting stimulus example to the non-spike class (and vice versa) is minimized. Efficacy of the CbRF method is validated with simulations and for auditory spectro-temporal receptive field (STRF) estimation from experimental recordings in the auditory midbrain of Mongolian gerbils. Acoustic stimulation is performed with frequency-modulated tone complexes that mimic properties of natural stimuli, specifically non-Gaussian amplitude distribution and higher-order correlations. Results demonstrate that the proposed approach successfully identifies correct underlying STRFs, even in cases where second-order methods based on the spike-triggered average (STA) do not. Applied to small data samples, the method is shown to converge on smaller amounts of experimental recordings and with lower estimation variance than the generalized linear model and recent information theoretic methods. Thus, CbRF estimation may prove useful for investigation of neuronal processes in response to natural stimuli and in settings where rapid adaptation is induced by experimental design.

Brain tumor image segmentation using kernel dictionary learning.

PubMed

Jeon Lee; Seung-Jun Kim; Rong Chen; Herskovits, Edward H

2015-08-01

Automated brain tumor image segmentation with high accuracy and reproducibility holds a big potential to enhance the current clinical practice. Dictionary learning (DL) techniques have been applied successfully to various image processing tasks recently. In this work, kernel extensions of the DL approach are adopted. Both reconstructive and discriminative versions of the kernel DL technique are considered, which can efficiently incorporate multi-modal nonlinear feature mappings based on the kernel trick. Our novel discriminative kernel DL formulation allows joint learning of a task-driven kernel-based dictionary and a linear classifier using a K-SVD-type algorithm. The proposed approaches were tested using real brain magnetic resonance (MR) images of patients with high-grade glioma. The obtained preliminary performances are competitive with the state of the art. The discriminative kernel DL approach is seen to reduce computational burden without much sacrifice in performance.

Incremental Structured Dictionary Learning for Video Sensor-Based Object Tracking

PubMed Central

Xue, Ming; Yang, Hua; Zheng, Shibao; Zhou, Yi; Yu, Zhenghua

2014-01-01

To tackle robust object tracking for video sensor-based applications, an online discriminative algorithm based on incremental discriminative structured dictionary learning (IDSDL-VT) is presented. In our framework, a discriminative dictionary combining both positive, negative and trivial patches is designed to sparsely represent the overlapped target patches. Then, a local update (LU) strategy is proposed for sparse coefficient learning. To formulate the training and classification process, a multiple linear classifier group based on a K-combined voting (KCV) function is proposed. As the dictionary evolves, the models are also trained to timely adapt the target appearance variation. Qualitative and quantitative evaluations on challenging image sequences compared with state-of-the-art algorithms demonstrate that the proposed tracking algorithm achieves a more favorable performance. We also illustrate its relay application in visual sensor networks. PMID:24549252

Overlapped Partitioning for Ensemble Classifiers of P300-Based Brain-Computer Interfaces

PubMed Central

Onishi, Akinari; Natsume, Kiyohisa

2014-01-01

A P300-based brain-computer interface (BCI) enables a wide range of people to control devices that improve their quality of life. Ensemble classifiers with naive partitioning were recently applied to the P300-based BCI and these classification performances were assessed. However, they were usually trained on a large amount of training data (e.g., 15300). In this study, we evaluated ensemble linear discriminant analysis (LDA) classifiers with a newly proposed overlapped partitioning method using 900 training data. In addition, the classification performances of the ensemble classifier with naive partitioning and a single LDA classifier were compared. One of three conditions for dimension reduction was applied: the stepwise method, principal component analysis (PCA), or none. The results show that an ensemble stepwise LDA (SWLDA) classifier with overlapped partitioning achieved a better performance than the commonly used single SWLDA classifier and an ensemble SWLDA classifier with naive partitioning. This result implies that the performance of the SWLDA is improved by overlapped partitioning and the ensemble classifier with overlapped partitioning requires less training data than that with naive partitioning. This study contributes towards reducing the required amount of training data and achieving better classification performance. PMID:24695550

Overlapped partitioning for ensemble classifiers of P300-based brain-computer interfaces.

PubMed

Onishi, Akinari; Natsume, Kiyohisa

2014-01-01

A P300-based brain-computer interface (BCI) enables a wide range of people to control devices that improve their quality of life. Ensemble classifiers with naive partitioning were recently applied to the P300-based BCI and these classification performances were assessed. However, they were usually trained on a large amount of training data (e.g., 15300). In this study, we evaluated ensemble linear discriminant analysis (LDA) classifiers with a newly proposed overlapped partitioning method using 900 training data. In addition, the classification performances of the ensemble classifier with naive partitioning and a single LDA classifier were compared. One of three conditions for dimension reduction was applied: the stepwise method, principal component analysis (PCA), or none. The results show that an ensemble stepwise LDA (SWLDA) classifier with overlapped partitioning achieved a better performance than the commonly used single SWLDA classifier and an ensemble SWLDA classifier with naive partitioning. This result implies that the performance of the SWLDA is improved by overlapped partitioning and the ensemble classifier with overlapped partitioning requires less training data than that with naive partitioning. This study contributes towards reducing the required amount of training data and achieving better classification performance.

Three-dimensional passive sensing photon counting for object classification

NASA Astrophysics Data System (ADS)

Yeom, Seokwon; Javidi, Bahram; Watson, Edward

2007-04-01

In this keynote address, we address three-dimensional (3D) distortion-tolerant object recognition using photon-counting integral imaging (II). A photon-counting linear discriminant analysis (LDA) is discussed for classification of photon-limited images. We develop a compact distortion-tolerant recognition system based on the multiple-perspective imaging of II. Experimental and simulation results have shown that a low level of photons is sufficient to classify out-of-plane rotated objects.

Ranking of predictor variables based on effect size criterion provides an accurate means of automatically classifying opinion column articles

NASA Astrophysics Data System (ADS)

Legara, Erika Fille; Monterola, Christopher; Abundo, Cheryl

2011-01-01

We demonstrate an accurate procedure based on linear discriminant analysis that allows automatic authorship classification of opinion column articles. First, we extract the following stylometric features of 157 column articles from four authors: statistics on high frequency words, number of words per sentence, and number of sentences per paragraph. Then, by systematically ranking these features based on an effect size criterion, we show that we can achieve an average classification accuracy of 93% for the test set. In comparison, frequency size based ranking has an average accuracy of 80%. The highest possible average classification accuracy of our data merely relying on chance is ∼31%. By carrying out sensitivity analysis, we show that the effect size criterion is superior than frequency ranking because there exist low frequency words that significantly contribute to successful author discrimination. Consistent results are seen when the procedure is applied in classifying the undisputed Federalist papers of Alexander Hamilton and James Madison. To the best of our knowledge, the work is the first attempt in classifying opinion column articles, that by virtue of being shorter in length (as compared to novels or short stories), are more prone to over-fitting issues. The near perfect classification for the longer papers supports this claim. Our results provide an important insight on authorship attribution that has been overlooked in previous studies: that ranking discriminant variables based on word frequency counts is not necessarily an optimal procedure.

Workplace discrimination and alcohol consumption: findings from the San Francisco Muni Health and Safety Study.

PubMed

Yen, I H; Ragland, D R; Greiner, B A; Fisher, J M

1999-01-01

There is evidence of an association between occupational stress and alcohol consumption. This study investigates the association between workplace racial discrimination and alcohol consumption in a sample of urban transit operators. During 1993-1995, after undergoing a medical exam, 1,542 transit operators completed an interview. Depending on the outcome, we used logistic or linear regression models to examine the cross-sectional relationship between discrimination experience and alcohol consumption. Operators who reported discrimination in at least one situation, out of a possible four, were more likely to have had negative life consequences as a result of drinking (adjusted OR = 1.97; 95% CI, 1.20-3.83) and were more likely to be classified as having an alcohol disorder (OR = 1.56 [0.96-2.54]), compared to those who reported no instances of workplace discrimination. Results adjusted simultaneously for age, sex, race/ethnicity, education, income, marital status, and seniority. There was no association between workplace discrimination and heavy drinking or drinks per month. Cross-sectional data from a sample of urban transit operators indicates an association between workplace racial discrimination and some measures of alcohol consumption.

Classification of functional near-infrared spectroscopy signals corresponding to the right- and left-wrist motor imagery for development of a brain-computer interface.

PubMed

Naseer, Noman; Hong, Keum-Shik

2013-10-11

This paper presents a study on functional near-infrared spectroscopy (fNIRS) indicating that the hemodynamic responses of the right- and left-wrist motor imageries have distinct patterns that can be classified using a linear classifier for the purpose of developing a brain-computer interface (BCI). Ten healthy participants were instructed to imagine kinesthetically the right- or left-wrist flexion indicated on a computer screen. Signals from the right and left primary motor cortices were acquired simultaneously using a multi-channel continuous-wave fNIRS system. Using two distinct features (the mean and the slope of change in the oxygenated hemoglobin concentration), the linear discriminant analysis classifier was used to classify the right- and left-wrist motor imageries resulting in average classification accuracies of 73.35% and 83.0%, respectively, during the 10s task period. Moreover, when the analysis time was confined to the 2-7s span within the overall 10s task period, the average classification accuracies were improved to 77.56% and 87.28%, respectively. These results demonstrate the feasibility of an fNIRS-based BCI and the enhanced performance of the classifier by removing the initial 2s span and/or the time span after the peak value. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

A Novel Design of 4-Class BCI Using Two Binary Classifiers and Parallel Mental Tasks

PubMed Central

Geng, Tao; Gan, John Q.; Dyson, Matthew; Tsui, Chun SL; Sepulveda, Francisco

2008-01-01

A novel 4-class single-trial brain computer interface (BCI) based on two (rather than four or more) binary linear discriminant analysis (LDA) classifiers is proposed, which is called a “parallel BCI.” Unlike other BCIs where mental tasks are executed and classified in a serial way one after another, the parallel BCI uses properly designed parallel mental tasks that are executed on both sides of the subject body simultaneously, which is the main novelty of the BCI paradigm used in our experiments. Each of the two binary classifiers only classifies the mental tasks executed on one side of the subject body, and the results of the two binary classifiers are combined to give the result of the 4-class BCI. Data was recorded in experiments with both real movement and motor imagery in 3 able-bodied subjects. Artifacts were not detected or removed. Offline analysis has shown that, in some subjects, the parallel BCI can generate a higher accuracy than a conventional 4-class BCI, although both of them have used the same feature selection and classification algorithms. PMID:18584040

Classification of Multiple Chinese Liquors by Means of a QCM-based E-Nose and MDS-SVM Classifier.

PubMed

Li, Qiang; Gu, Yu; Jia, Jing

2017-01-30

Chinese liquors are internationally well-known fermentative alcoholic beverages. They have unique flavors attributable to the use of various bacteria and fungi, raw materials, and production processes. Developing a novel, rapid, and reliable method to identify multiple Chinese liquors is of positive significance. This paper presents a pattern recognition system for classifying ten brands of Chinese liquors based on multidimensional scaling (MDS) and support vector machine (SVM) algorithms in a quartz crystal microbalance (QCM)-based electronic nose (e-nose) we designed. We evaluated the comprehensive performance of the MDS-SVM classifier that predicted all ten brands of Chinese liquors individually. The prediction accuracy (98.3%) showed superior performance of the MDS-SVM classifier over the back-propagation artificial neural network (BP-ANN) classifier (93.3%) and moving average-linear discriminant analysis (MA-LDA) classifier (87.6%). The MDS-SVM classifier has reasonable reliability, good fitting and prediction (generalization) performance in classification of the Chinese liquors. Taking both application of the e-nose and validation of the MDS-SVM classifier into account, we have thus created a useful method for the classification of multiple Chinese liquors.

Automatic sleep staging using empirical mode decomposition, discrete wavelet transform, time-domain, and nonlinear dynamics features of heart rate variability signals.

PubMed

Ebrahimi, Farideh; Setarehdan, Seyed-Kamaledin; Ayala-Moyeda, Jose; Nazeran, Homer

2013-10-01

The conventional method for sleep staging is to analyze polysomnograms (PSGs) recorded in a sleep lab. The electroencephalogram (EEG) is one of the most important signals in PSGs but recording and analysis of this signal presents a number of technical challenges, especially at home. Instead, electrocardiograms (ECGs) are much easier to record and may offer an attractive alternative for home sleep monitoring. The heart rate variability (HRV) signal proves suitable for automatic sleep staging. Thirty PSGs from the Sleep Heart Health Study (SHHS) database were used. Three feature sets were extracted from 5- and 0.5-min HRV segments: time-domain features, nonlinear-dynamics features and time-frequency features. The latter was achieved by using empirical mode decomposition (EMD) and discrete wavelet transform (DWT) methods. Normalized energies in important frequency bands of HRV signals were computed using time-frequency methods. ANOVA and t-test were used for statistical evaluations. Automatic sleep staging was based on HRV signal features. The ANOVA followed by a post hoc Bonferroni was used for individual feature assessment. Most features were beneficial for sleep staging. A t-test was used to compare the means of extracted features in 5- and 0.5-min HRV segments. The results showed that the extracted features means were statistically similar for a small number of features. A separability measure showed that time-frequency features, especially EMD features, had larger separation than others. There was not a sizable difference in separability of linear features between 5- and 0.5-min HRV segments but separability of nonlinear features, especially EMD features, decreased in 0.5-min HRV segments. HRV signal features were classified by linear discriminant (LD) and quadratic discriminant (QD) methods. Classification results based on features from 5-min segments surpassed those obtained from 0.5-min segments. The best result was obtained from features using 5-min HRV segments classified by the LD classifier. A combination of linear/nonlinear features from HRV signals is effective in automatic sleep staging. Moreover, time-frequency features are more informative than others. In addition, a separability measure and classification results showed that HRV signal features, especially nonlinear features, extracted from 5-min segments are more discriminative than those from 0.5-min segments in automatic sleep staging. Copyright © 2013 Elsevier Ireland Ltd. All rights reserved.

Label consistent K-SVD: learning a discriminative dictionary for recognition.

PubMed

Jiang, Zhuolin; Lin, Zhe; Davis, Larry S

2013-11-01

A label consistent K-SVD (LC-KSVD) algorithm to learn a discriminative dictionary for sparse coding is presented. In addition to using class labels of training data, we also associate label information with each dictionary item (columns of the dictionary matrix) to enforce discriminability in sparse codes during the dictionary learning process. More specifically, we introduce a new label consistency constraint called "discriminative sparse-code error" and combine it with the reconstruction error and the classification error to form a unified objective function. The optimal solution is efficiently obtained using the K-SVD algorithm. Our algorithm learns a single overcomplete dictionary and an optimal linear classifier jointly. The incremental dictionary learning algorithm is presented for the situation of limited memory resources. It yields dictionaries so that feature points with the same class labels have similar sparse codes. Experimental results demonstrate that our algorithm outperforms many recently proposed sparse-coding techniques for face, action, scene, and object category recognition under the same learning conditions.

Detection of cervical lesions by multivariate analysis of diffuse reflectance spectra: a clinical study.

PubMed

Prabitha, Vasumathi Gopala; Suchetha, Sambasivan; Jayanthi, Jayaraj Lalitha; Baiju, Kamalasanan Vijayakumary; Rema, Prabhakaran; Anuraj, Koyippurath; Mathews, Anita; Sebastian, Paul; Subhash, Narayanan

2016-01-01

Diffuse reflectance (DR) spectroscopy is a non-invasive, real-time, and cost-effective tool for early detection of malignant changes in squamous epithelial tissues. The present study aims to evaluate the diagnostic power of diffuse reflectance spectroscopy for non-invasive discrimination of cervical lesions in vivo. A clinical trial was carried out on 48 sites in 34 patients by recording DR spectra using a point-monitoring device with white light illumination. The acquired data were analyzed and classified using multivariate statistical analysis based on principal component analysis (PCA) and linear discriminant analysis (LDA). Diagnostic accuracies were validated using random number generators. The receiver operating characteristic (ROC) curves were plotted for evaluating the discriminating power of the proposed statistical technique. An algorithm was developed and used to classify non-diseased (normal) from diseased sites (abnormal) with a sensitivity of 72 % and specificity of 87 %. While low-grade squamous intraepithelial lesion (LSIL) could be discriminated from normal with a sensitivity of 56 % and specificity of 80 %, and high-grade squamous intraepithelial lesion (HSIL) from normal with a sensitivity of 89 % and specificity of 97 %, LSIL could be discriminated from HSIL with 100 % sensitivity and specificity. The areas under the ROC curves were 0.993 (95 % confidence interval (CI) 0.0 to 1) and 1 (95 % CI 1) for the discrimination of HSIL from normal and HSIL from LSIL, respectively. The results of the study show that DR spectroscopy could be used along with multivariate analytical techniques as a non-invasive technique to monitor cervical disease status in real time.

Near-infrared Raman spectroscopy for estimating biochemical changes associated with different pathological conditions of cervix

NASA Astrophysics Data System (ADS)

Daniel, Amuthachelvi; Prakasarao, Aruna; Ganesan, Singaravelu

2018-02-01

The molecular level changes associated with oncogenesis precede the morphological changes in cells and tissues. Hence molecular level diagnosis would promote early diagnosis of the disease. Raman spectroscopy is capable of providing specific spectral signature of various biomolecules present in the cells and tissues under various pathological conditions. The aim of this work is to develop a non-linear multi-class statistical methodology for discrimination of normal, neoplastic and malignant cells/tissues. The tissues were classified as normal, pre-malignant and malignant by employing Principal Component Analysis followed by Artificial Neural Network (PC-ANN). The overall accuracy achieved was 99%. Further, to get an insight into the quantitative biochemical composition of the normal, neoplastic and malignant tissues, a linear combination of the major biochemicals by non-negative least squares technique was fit to the measured Raman spectra of the tissues. This technique confirms the changes in the major biomolecules such as lipids, nucleic acids, actin, glycogen and collagen associated with the different pathological conditions. To study the efficacy of this technique in comparison with histopathology, we have utilized Principal Component followed by Linear Discriminant Analysis (PC-LDA) to discriminate the well differentiated, moderately differentiated and poorly differentiated squamous cell carcinoma with an accuracy of 94.0%. And the results demonstrated that Raman spectroscopy has the potential to complement the good old technique of histopathology.

Automated aural classification used for inter-species discrimination of cetaceans.

PubMed

Binder, Carolyn M; Hines, Paul C

2014-04-01

Passive acoustic methods are in widespread use to detect and classify cetacean species; however, passive acoustic systems often suffer from large false detection rates resulting from numerous transient sources. To reduce the acoustic analyst workload, automatic recognition methods may be implemented in a two-stage process. First, a general automatic detector is implemented that produces many detections to ensure cetacean presence is noted. Then an automatic classifier is used to significantly reduce the number of false detections and classify the cetacean species. This process requires development of a robust classifier capable of performing inter-species classification. Because human analysts can aurally discriminate species, an automated aural classifier that uses perceptual signal features was tested on a cetacean data set. The classifier successfully discriminated between four species of cetaceans-bowhead, humpback, North Atlantic right, and sperm whales-with 85% accuracy. It also performed well (100% accuracy) for discriminating sperm whale clicks from right whale gunshots. An accuracy of 92% and area under the receiver operating characteristic curve of 0.97 were obtained for the relatively challenging bowhead and humpback recognition case. These results demonstrated that the perceptual features employed by the aural classifier provided powerful discrimination cues for inter-species classification of cetaceans.

Fully optimized discrimination of physiological responses to auditory stimuli

PubMed Central

Kruglikov, Stepan Y; Chari, Sharmila; Rapp, Paul E; Weinstein, Steven L; Given, Barbara K; Schiff, Steven J

2008-01-01

The use of multivariate measurements to characterize brain activity (electrical, magnetic, optical) is widespread. The most common approaches to reduce the complexity of such observations include principal and independent component analyses (PCA and ICA), which are not well suited for discrimination tasks. We addressed two questions: first, how do the neurophysiological responses to elongated phonemes relate to tone and phoneme responses in normal children, and, second, how discriminable are these responses. We employed fully optimized linear discrimination analysis to maximally separate the multi-electrode responses to tones and phonemes, and classified the response to elongated phonemes. We find that discrimination between tones and phonemes is dependent upon responses from associative regions of the brain apparently distinct from the primary sensory cortices typically emphasized by PCA or ICA, and that the neuronal correlates corresponding to elongated phonemes are highly variable in normal children (about half respond with neural correlates of tones and half as phonemes). Our approach is made feasible by the increase in computational power of ordinary personal computers and has significant advantages for a wide range of neuronal imaging modalities. PMID:18430975

Discriminant analysis of resting-state functional connectivity patterns on the Grassmann manifold

NASA Astrophysics Data System (ADS)

Fan, Yong; Liu, Yong; Jiang, Tianzi; Liu, Zhening; Hao, Yihui; Liu, Haihong

2010-03-01

The functional networks, extracted from fMRI images using independent component analysis, have been demonstrated informative for distinguishing brain states of cognitive functions and neurological diseases. In this paper, we propose a novel algorithm for discriminant analysis of functional networks encoded by spatial independent components. The functional networks of each individual are used as bases for a linear subspace, referred to as a functional connectivity pattern, which facilitates a comprehensive characterization of temporal signals of fMRI data. The functional connectivity patterns of different individuals are analyzed on the Grassmann manifold by adopting a principal angle based subspace distance. In conjunction with a support vector machine classifier, a forward component selection technique is proposed to select independent components for constructing the most discriminative functional connectivity pattern. The discriminant analysis method has been applied to an fMRI based schizophrenia study with 31 schizophrenia patients and 31 healthy individuals. The experimental results demonstrate that the proposed method not only achieves a promising classification performance for distinguishing schizophrenia patients from healthy controls, but also identifies discriminative functional networks that are informative for schizophrenia diagnosis.

Screening analysis of biodiesel feedstock using UV-vis, NIR and synchronous fluorescence spectrometries and the successive projections algorithm.

PubMed

Insausti, Matías; Gomes, Adriano A; Cruz, Fernanda V; Pistonesi, Marcelo F; Araujo, Mario C U; Galvão, Roberto K H; Pereira, Claudete F; Band, Beatriz S F

2012-08-15

This paper investigates the use of UV-vis, near infrared (NIR) and synchronous fluorescence (SF) spectrometries coupled with multivariate classification methods to discriminate biodiesel samples with respect to the base oil employed in their production. More specifically, the present work extends previous studies by investigating the discrimination of corn-based biodiesel from two other biodiesel types (sunflower and soybean). Two classification methods are compared, namely full-spectrum SIMCA (soft independent modelling of class analogies) and SPA-LDA (linear discriminant analysis with variables selected by the successive projections algorithm). Regardless of the spectrometric technique employed, full-spectrum SIMCA did not provide an appropriate discrimination of the three biodiesel types. In contrast, all samples were correctly classified on the basis of a reduced number of wavelengths selected by SPA-LDA. It can be concluded that UV-vis, NIR and SF spectrometries can be successfully employed to discriminate corn-based biodiesel from the two other biodiesel types, but wavelength selection by SPA-LDA is key to the proper separation of the classes. Copyright © 2012 Elsevier B.V. All rights reserved.

Documenting Differences between Early Stone Age Flake Production Systems: An Experimental Model and Archaeological Verification.

PubMed

Presnyakova, Darya; Archer, Will; Braun, David R; Flear, Wesley

2015-01-01

This study investigates morphological differences between flakes produced via "core and flake" technologies and those resulting from bifacial shaping strategies. We investigate systematic variation between two technological groups of flakes using experimentally produced assemblages, and then apply the experimental model to the Cutting 10 Mid -Pleistocene archaeological collection from Elandsfontein, South Africa. We argue that a specific set of independent variables--and their interactions--including external platform angle, platform depth, measures of thickness variance and flake curvature should distinguish between these two technological groups. The role of these variables in technological group separation was further investigated using the Generalized Linear Model as well as Linear Discriminant Analysis. The Discriminant model was used to classify archaeological flakes from the Cutting 10 locality in terms of their probability of association, within either experimentally developed technological group. The results indicate that the selected independent variables play a central role in separating core and flake from bifacial technologies. Thickness evenness and curvature had the greatest effect sizes in both the Generalized Linear and Discriminant models. Interestingly the interaction between thickness evenness and platform depth was significant and played an important role in influencing technological group membership. The identified interaction emphasizes the complexity in attempting to distinguish flake production strategies based on flake morphological attributes. The results of the discriminant function analysis demonstrate that the majority of flakes at the Cutting 10 locality were not associated with the production of the numerous Large Cutting Tools found at the site, which corresponds with previous suggestions regarding technological behaviors reflected in this assemblage.

Documenting Differences between Early Stone Age Flake Production Systems: An Experimental Model and Archaeological Verification

PubMed Central

Presnyakova, Darya; Archer, Will; Braun, David R.; Flear, Wesley

2015-01-01

This study investigates morphological differences between flakes produced via “core and flake” technologies and those resulting from bifacial shaping strategies. We investigate systematic variation between two technological groups of flakes using experimentally produced assemblages, and then apply the experimental model to the Cutting 10 Mid -Pleistocene archaeological collection from Elandsfontein, South Africa. We argue that a specific set of independent variables—and their interactions—including external platform angle, platform depth, measures of thickness variance and flake curvature should distinguish between these two technological groups. The role of these variables in technological group separation was further investigated using the Generalized Linear Model as well as Linear Discriminant Analysis. The Discriminant model was used to classify archaeological flakes from the Cutting 10 locality in terms of their probability of association, within either experimentally developed technological group. The results indicate that the selected independent variables play a central role in separating core and flake from bifacial technologies. Thickness evenness and curvature had the greatest effect sizes in both the Generalized Linear and Discriminant models. Interestingly the interaction between thickness evenness and platform depth was significant and played an important role in influencing technological group membership. The identified interaction emphasizes the complexity in attempting to distinguish flake production strategies based on flake morphological attributes. The results of the discriminant function analysis demonstrate that the majority of flakes at the Cutting 10 locality were not associated with the production of the numerous Large Cutting Tools found at the site, which corresponds with previous suggestions regarding technological behaviors reflected in this assemblage. PMID:26111251

Typification of cider brandy on the basis of cider used in its manufacture.

PubMed

Rodríguez Madrera, Roberto; Mangas Alonso, Juan J

2005-04-20

A study of typification of cider brandies on the basis of the origin of the raw material used in their manufacture was conducted using chemometric techniques (principal component analysis, linear discriminant analysis, and Bayesian analysis) together with their composition in volatile compounds, as analyzed by gas chromatography with flame ionization to detect the major volatiles and by mass spectrometric to detect the minor ones. Significant principal components computed by a double cross-validation procedure allowed the structure of the database to be visualized as a function of the raw material, that is, cider made from fresh apple juice versus cider made from apple juice concentrate. Feasible and robust discriminant rules were computed and validated by a cross-validation procedure that allowed the authors to classify fresh and concentrate cider brandies, obtaining classification hits of >92%. The most discriminating variables for typifying cider brandies according to their raw material were 1-butanol and ethyl hexanoate.

Liquid contrabands classification based on energy dispersive X-ray diffraction and hybrid discriminant analysis

NASA Astrophysics Data System (ADS)

YangDai, Tianyi; Zhang, Li

2016-02-01

Energy dispersive X-ray diffraction (EDXRD) combined with hybrid discriminant analysis (HDA) has been utilized for classifying the liquid materials for the first time. The XRD spectra of 37 kinds of liquid contrabands and daily supplies were obtained using an EDXRD test bed facility. The unique spectra of different samples reveal XRD's capability to distinguish liquid contrabands from daily supplies. In order to create a system to detect liquid contrabands, the diffraction spectra were subjected to HDA which is the combination of principal components analysis (PCA) and linear discriminant analysis (LDA). Experiments based on the leave-one-out method demonstrate that HDA is a practical method with higher classification accuracy and lower noise sensitivity than the other methods in this application. The study shows the great capability and potential of the combination of XRD and HDA for liquid contrabands classification.

Trace element analysis of rough diamond by LA-ICP-MS: a case of source discrimination?

PubMed

Dalpé, Claude; Hudon, Pierre; Ballantyne, David J; Williams, Darrell; Marcotte, Denis

2010-11-01

Current profiling of rough diamond source is performed using different physical and/or morphological techniques that require strong knowledge and experience in the field. More recently, chemical impurities have been used to discriminate diamond source and with the advance of laser ablation-inductively coupled plasma-mass spectrometry (LA-ICP-MS) empirical profiling of rough diamonds is possible to some extent. In this study, we present a LA-ICP-MS methodology that we developed for analyzing ultra-trace element impurities in rough diamond for origin determination ("profiling"). Diamonds from two sources were analyzed by LA-ICP-MS and were statistically classified by accepted methods. For the two diamond populations analyzed in this study, binomial logistic regression produced a better overall correct classification than linear discriminant analysis. The results suggest that an anticipated matrix match reference material would improve the robustness of our methodology for forensic applications. © 2010 American Academy of Forensic Sciences.

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.

EEG-based emergency braking intention prediction for brain-controlled driving considering one electrode falling-off.

PubMed

Huikang Wang; Luzheng Bi; Teng Teng

2017-07-01

This paper proposes a novel method of electroencephalography (EEG)-based driver emergency braking intention detection system for brain-controlled driving considering one electrode falling-off. First, whether one electrode falls off is discriminated based on EEG potentials. Then, the missing signals are estimated by using the signals collected from other channels based on multivariate linear regression. Finally, a linear decoder is applied to classify driver intentions. Experimental results show that the falling-off discrimination accuracy is 99.63% on average and the correlation coefficient and root mean squared error (RMSE) between the estimated and experimental data are 0.90 and 11.43 μV, respectively, on average. Given one electrode falls off, the system accuracy of the proposed intention prediction method is significantly higher than that of the original method (95.12% VS 79.11%) and is close to that (95.95%) of the original system under normal situations (i. e., no electrode falling-off).

Application of linear discriminant analysis and Attenuated Total Reflectance Fourier Transform Infrared microspectroscopy for diagnosis of colon cancer.

PubMed

Khanmohammadi, Mohammadreza; Bagheri Garmarudi, Amir; Samani, Simin; Ghasemi, Keyvan; Ashuri, Ahmad

2011-06-01

Attenuated Total Reflectance Fourier Transform Infrared (ATR-FTIR) microspectroscopy was applied for detection of colon cancer according to the spectral features of colon tissues. Supervised classification models can be trained to identify the tissue type based on the spectroscopic fingerprint. A total of 78 colon tissues were used in spectroscopy studies. Major spectral differences were observed in 1,740-900 cm(-1) spectral region. Several chemometric methods such as analysis of variance (ANOVA), cluster analysis (CA) and linear discriminate analysis (LDA) were applied for classification of IR spectra. Utilizing the chemometric techniques, clear and reproducible differences were observed between the spectra of normal and cancer cases, suggesting that infrared microspectroscopy in conjunction with spectral data processing would be useful for diagnostic classification. Using LDA technique, the spectra were classified into cancer and normal tissue classes with an accuracy of 95.8%. The sensitivity and specificity was 100 and 93.1%, respectively.

Evaluation of linear classifiers on articles containing pharmacokinetic evidence of drug-drug interactions.

PubMed

Kolchinsky, A; Lourenço, A; Li, L; Rocha, L M

2013-01-01

Drug-drug interaction (DDI) is a major cause of morbidity and mortality. DDI research includes the study of different aspects of drug interactions, from in vitro pharmacology, which deals with drug interaction mechanisms, to pharmaco-epidemiology, which investigates the effects of DDI on drug efficacy and adverse drug reactions. Biomedical literature mining can aid both kinds of approaches by extracting relevant DDI signals from either the published literature or large clinical databases. However, though drug interaction is an ideal area for translational research, the inclusion of literature mining methodologies in DDI workflows is still very preliminary. One area that can benefit from literature mining is the automatic identification of a large number of potential DDIs, whose pharmacological mechanisms and clinical significance can then be studied via in vitro pharmacology and in populo pharmaco-epidemiology. We implemented a set of classifiers for identifying published articles relevant to experimental pharmacokinetic DDI evidence. These documents are important for identifying causal mechanisms behind putative drug-drug interactions, an important step in the extraction of large numbers of potential DDIs. We evaluate performance of several linear classifiers on PubMed abstracts, under different feature transformation and dimensionality reduction methods. In addition, we investigate the performance benefits of including various publicly-available named entity recognition features, as well as a set of internally-developed pharmacokinetic dictionaries. We found that several classifiers performed well in distinguishing relevant and irrelevant abstracts. We found that the combination of unigram and bigram textual features gave better performance than unigram features alone, and also that normalization transforms that adjusted for feature frequency and document length improved classification. For some classifiers, such as linear discriminant analysis (LDA), proper dimensionality reduction had a large impact on performance. Finally, the inclusion of NER features and dictionaries was found not to help classification.

EEG-based mild depressive detection using feature selection methods and classifiers.

PubMed

Li, Xiaowei; Hu, Bin; Sun, Shuting; Cai, Hanshu

2016-11-01

Depression has become a major health burden worldwide, and effectively detection of such disorder is a great challenge which requires latest technological tool, such as Electroencephalography (EEG). This EEG-based research seeks to find prominent frequency band and brain regions that are most related to mild depression, as well as an optimal combination of classification algorithms and feature selection methods which can be used in future mild depression detection. An experiment based on facial expression viewing task (Emo_block and Neu_block) was conducted, and EEG data of 37 university students were collected using a 128 channel HydroCel Geodesic Sensor Net (HCGSN). For discriminating mild depressive patients and normal controls, BayesNet (BN), Support Vector Machine (SVM), Logistic Regression (LR), k-nearest neighbor (KNN) and RandomForest (RF) classifiers were used. And BestFirst (BF), GreedyStepwise (GSW), GeneticSearch (GS), LinearForwordSelection (LFS) and RankSearch (RS) based on Correlation Features Selection (CFS) were applied for linear and non-linear EEG features selection. Independent Samples T-test with Bonferroni correction was used to find the significantly discriminant electrodes and features. Data mining results indicate that optimal performance is achieved using a combination of feature selection method GSW based on CFS and classifier KNN for beta frequency band. Accuracies achieved 92.00% and 98.00%, and AUC achieved 0.957 and 0.997, for Emo_block and Neu_block beta band data respectively. T-test results validate the effectiveness of selected features by search method GSW. Simplified EEG system with only FP1, FP2, F3, O2, T3 electrodes was also explored with linear features, which yielded accuracies of 91.70% and 96.00%, AUC of 0.952 and 0.972, for Emo_block and Neu_block respectively. Classification results obtained by GSW + KNN are encouraging and better than previously published results. In the spatial distribution of features, we find that left parietotemporal lobe in beta EEG frequency band has greater effect on mild depression detection. And fewer EEG channels (FP1, FP2, F3, O2 and T3) combined with linear features may be good candidates for usage in portable systems for mild depression detection. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

Discrimination among populations of sockeye salmon fry with Fourier analysis of otolith banding patterns formed during incubation

USGS Publications Warehouse

Finn, James E.; Burger, Carl V.; Holland-Bartels, Leslie E.

1997-01-01

We used otolith banding patterns formed during incubation to discriminate among hatchery- and wild-incubated fry of sockeye salmon Oncorhynchus nerka from Tustumena Lake, Alaska. Fourier analysis of otolith luminance profiles was used to describe banding patterns: the amplitudes of individual Fourier harmonics were discriminant variables. Correct classification of otoliths to either hatchery or wild origin was 83.1% (cross-validation) and 72.7% (test data) with the use of quadratic discriminant function analysts on 10 Fourier amplitudes. Overall classification rates among the six test groups (one hatchery and five wild groups) were 46.5% (cross-validation) and 39.3% (test data) with the use of linear discriminant function analysis on 16 Fourier amplitudes. Although classification rates for wild-incubated fry from any one site never exceeded 67% (cross-validation) or 60% (test data), location-specific information was evident for all groups because the probability of classifying an individual to its true incubation location was significantly greater than chance. Results indicate phenotypic differences in otolith microstructure among incubation sites separated by less than 10 km. Analysis of otolith luminance profiles is a potentially useful technique for discriminating among and between various populations of hatchery and wild fish.

Gas chimney detection based on improving the performance of combined multilayer perceptron and support vector classifier

NASA Astrophysics Data System (ADS)

Hashemi, H.; Tax, D. M. J.; Duin, R. P. W.; Javaherian, A.; de Groot, P.

2008-11-01

Seismic object detection is a relatively new field in which 3-D bodies are visualized and spatial relationships between objects of different origins are studied in order to extract geologic information. In this paper, we propose a method for finding an optimal classifier with the help of a statistical feature ranking technique and combining different classifiers. The method, which has general applicability, is demonstrated here on a gas chimney detection problem. First, we evaluate a set of input seismic attributes extracted at locations labeled by a human expert using regularized discriminant analysis (RDA). In order to find the RDA score for each seismic attribute, forward and backward search strategies are used. Subsequently, two non-linear classifiers: multilayer perceptron (MLP) and support vector classifier (SVC) are run on the ranked seismic attributes. Finally, to capitalize on the intrinsic differences between both classifiers, the MLP and SVC results are combined using logical rules of maximum, minimum and mean. The proposed method optimizes the ranked feature space size and yields the lowest classification error in the final combined result. We will show that the logical minimum reveals gas chimneys that exhibit both the softness of MLP and the resolution of SVC classifiers.

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

PubMed

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

2016-01-01

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

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

PubMed Central

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

2016-01-01

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

Comparison of the Predictive Accuracy of DNA Array-Based Multigene Classifiers across cDNA Arrays and Affymetrix GeneChips

PubMed Central

Stec, James; Wang, Jing; Coombes, Kevin; Ayers, Mark; Hoersch, Sebastian; Gold, David L.; Ross, Jeffrey S; Hess, Kenneth R.; Tirrell, Stephen; Linette, Gerald; Hortobagyi, Gabriel N.; Symmans, W. Fraser; Pusztai, Lajos

2005-01-01

We examined how well differentially expressed genes and multigene outcome classifiers retain their class-discriminating values when tested on data generated by different transcriptional profiling platforms. RNA from 33 stage I-III breast cancers was hybridized to both Affymetrix GeneChip and Millennium Pharmaceuticals cDNA arrays. Only 30% of all corresponding gene expression measurements on the two platforms had Pearson correlation coefficient r ≥ 0.7 when UniGene was used to match probes. There was substantial variation in correlation between different Affymetrix probe sets matched to the same cDNA probe. When cDNA and Affymetrix probes were matched by basic local alignment tool (BLAST) sequence identity, the correlation increased substantially. We identified 182 genes in the Affymetrix and 45 in the cDNA data (including 17 common genes) that accurately separated 91% of cases in supervised hierarchical clustering in each data set. Cross-platform testing of these informative genes resulted in lower clustering accuracy of 45 and 79%, respectively. Several sets of accurate five-gene classifiers were developed on each platform using linear discriminant analysis. The best 100 classifiers showed average misclassification error rate of 2% on the original data that rose to 19.5% when tested on data from the other platform. Random five-gene classifiers showed misclassification error rate of 33%. We conclude that multigene predictors optimized for one platform lose accuracy when applied to data from another platform due to missing genes and sequence differences in probes that result in differing measurements for the same gene. PMID:16049308

Classification of Self-Driven Mental Tasks from Whole-Brain Activity Patterns

PubMed Central

Nawa, Norberto Eiji; Ando, Hiroshi

2014-01-01

During wakefulness, a constant and continuous stream of complex stimuli and self-driven thoughts permeate the human mind. Here, eleven participants were asked to count down numbers and remember negative or positive autobiographical episodes of their personal lives, for 32 seconds at a time, during which they could freely engage in the execution of those tasks. We then examined the possibility of determining from a single whole-brain functional magnetic resonance imaging scan which one of the two mental tasks each participant was performing at a given point in time. Linear support-vector machines were used to build within-participant classifiers and across-participants classifiers. The within-participant classifiers could correctly discriminate scans with an average accuracy as high as 82%, when using data from all individual voxels in the brain. These results demonstrate that it is possible to accurately classify self-driven mental tasks from whole-brain activity patterns recorded in a time interval as short as 2 seconds. PMID:24824899

Joint deconvolution and classification with applications to passive acoustic underwater multipath.

PubMed

Anderson, Hyrum S; Gupta, Maya R

2008-11-01

This paper addresses the problem of classifying signals that have been corrupted by noise and unknown linear time-invariant (LTI) filtering such as multipath, given labeled uncorrupted training signals. A maximum a posteriori approach to the deconvolution and classification is considered, which produces estimates of the desired signal, the unknown channel, and the class label. For cases in which only a class label is needed, the classification accuracy can be improved by not committing to an estimate of the channel or signal. A variant of the quadratic discriminant analysis (QDA) classifier is proposed that probabilistically accounts for the unknown LTI filtering, and which avoids deconvolution. The proposed QDA classifier can work either directly on the signal or on features whose transformation by LTI filtering can be analyzed; as an example a classifier for subband-power features is derived. Results on simulated data and real Bowhead whale vocalizations show that jointly considering deconvolution with classification can dramatically improve classification performance over traditional methods over a range of signal-to-noise ratios.

The effect of combining two echo times in automatic brain tumor classification by MRS.

PubMed

García-Gómez, Juan M; Tortajada, Salvador; Vidal, César; Julià-Sapé, Margarida; Luts, Jan; Moreno-Torres, Angel; Van Huffel, Sabine; Arús, Carles; Robles, Montserrat

2008-11-01

(1)H MRS is becoming an accurate, non-invasive technique for initial examination of brain masses. We investigated if the combination of single-voxel (1)H MRS at 1.5 T at two different (TEs), short TE (PRESS or STEAM, 20-32 ms) and long TE (PRESS, 135-136 ms), improves the classification of brain tumors over using only one echo TE. A clinically validated dataset of 50 low-grade meningiomas, 105 aggressive tumors (glioblastoma and metastasis), and 30 low-grade glial tumors (astrocytomas grade II, oligodendrogliomas and oligoastrocytomas) was used to fit predictive models based on the combination of features from short-TEs and long-TE spectra. A new approach that combines the two consecutively was used to produce a single data vector from which relevant features of the two TE spectra could be extracted by means of three algorithms: stepwise, reliefF, and principal components analysis. Least squares support vector machines and linear discriminant analysis were applied to fit the pairwise and multiclass classifiers, respectively. Significant differences in performance were found when short-TE, long-TE or both spectra combined were used as input. In our dataset, to discriminate meningiomas, the combination of the two TE acquisitions produced optimal performance. To discriminate aggressive tumors from low-grade glial tumours, the use of short-TE acquisition alone was preferable. The classifier development strategy used here lends itself to automated learning and test performance processes, which may be of use for future web-based multicentric classifier development studies. Copyright (c) 2008 John Wiley & Sons, Ltd.

Discrimination between Alzheimer's Disease and Late Onset Bipolar Disorder Using Multivariate Analysis.

PubMed

Besga, Ariadna; Gonzalez, Itxaso; Echeburua, Enrique; Savio, Alexandre; Ayerdi, Borja; Chyzhyk, Darya; Madrigal, Jose L M; Leza, Juan C; Graña, Manuel; Gonzalez-Pinto, Ana Maria

2015-01-01

Late onset bipolar disorder (LOBD) is often difficult to distinguish from degenerative dementias, such as Alzheimer disease (AD), due to comorbidities and common cognitive symptoms. Moreover, LOBD prevalence in the elder population is not negligible and it is increasing. Both pathologies share pathophysiological neuroinflammation features. Improvements in differential diagnosis of LOBD and AD will help to select the best personalized treatment. The aim of this study is to assess the relative significance of clinical observations, neuropsychological tests, and specific blood plasma biomarkers (inflammatory and neurotrophic), separately and combined, in the differential diagnosis of LOBD versus AD. It was carried out evaluating the accuracy achieved by classification-based computer-aided diagnosis (CAD) systems based on these variables. A sample of healthy controls (HC) (n = 26), AD patients (n = 37), and LOBD patients (n = 32) was recruited at the Alava University Hospital. Clinical observations, neuropsychological tests, and plasma biomarkers were measured at recruitment time. We applied multivariate machine learning classification methods to discriminate subjects from HC, AD, and LOBD populations in the study. We analyzed, for each classification contrast, feature sets combining clinical observations, neuropsychological measures, and biological markers, including inflammation biomarkers. Furthermore, we analyzed reduced feature sets containing variables with significative differences determined by a Welch's t-test. Furthermore, a battery of classifier architectures were applied, encompassing linear and non-linear Support Vector Machines (SVM), Random Forests (RF), Classification and regression trees (CART), and their performance was evaluated in a leave-one-out (LOO) cross-validation scheme. Post hoc analysis of Gini index in CART classifiers provided a measure of each variable importance. Welch's t-test found one biomarker (Malondialdehyde) with significative differences (p < 0.001) in LOBD vs. AD contrast. Classification results with the best features are as follows: discrimination of HC vs. AD patients reaches accuracy 97.21% and AUC 98.17%. Discrimination of LOBD vs. AD patients reaches accuracy 90.26% and AUC 89.57%. Discrimination of HC vs LOBD patients achieves accuracy 95.76% and AUC 88.46%. It is feasible to build CAD systems for differential diagnosis of LOBD and AD on the basis of a reduced set of clinical variables. Clinical observations provide the greatest discrimination. Neuropsychological tests are improved by the addition of biomarkers, and both contribute significantly to improve the overall predictive performance.

Decoding grating orientation from microelectrode array recordings in monkey cortical area V4.

PubMed

Manyakov, Nikolay V; Van Hulle, Marc M

2010-04-01

We propose an invasive brain-machine interface (BMI) that decodes the orientation of a visual grating from spike train recordings made with a 96 microelectrodes array chronically implanted into the prelunate gyrus (area V4) of a rhesus monkey. The orientation is decoded irrespective of the grating's spatial frequency. Since pyramidal cells are less prominent in visual areas, compared to (pre)motor areas, the recordings contain spikes with smaller amplitudes, compared to the noise level. Hence, rather than performing spike decoding, feature selection algorithms are applied to extract the required information for the decoder. Two types of feature selection procedures are compared, filter and wrapper. The wrapper is combined with a linear discriminant analysis classifier, and the filter is followed by a radial-basis function support vector machine classifier. In addition, since we have a multiclass classification problen, different methods for combining pairwise classifiers are compared.

Ambiguity domain-based identification of altered gait pattern in ALS disorder

NASA Astrophysics Data System (ADS)

Sugavaneswaran, L.; Umapathy, K.; Krishnan, S.

2012-08-01

The onset of a neurological disorder, such as amyotrophic lateral sclerosis (ALS), is so subtle that the symptoms are often overlooked, thereby ruling out the option of early detection of the abnormality. In the case of ALS, over 75% of the affected individuals often experience awkwardness when using their limbs, which alters their gait, i.e. stride and swing intervals. The aim of this work is to suitably represent the non-stationary characteristics of gait (fluctuations in stride and swing intervals) in order to facilitate discrimination between normal and ALS subjects. We define a simple-yet-representative feature vector space by exploiting the ambiguity domain (AD) to achieve efficient classification between healthy and pathological gait stride interval. The stride-to-stride fluctuations and the swing intervals of 16 healthy control and 13 ALS-affected subjects were analyzed. Three features that are representative of the gait signal characteristics were extracted from the AD-space and are fed to linear discriminant analysis and neural network classifiers, respectively. Overall, maximum accuracies of 89.2% (LDA) and 100% (NN) were obtained in classifying the ALS gait.

A bench-top hyperspectral imaging system to classify beef from Nellore cattle based on tenderness

NASA Astrophysics Data System (ADS)

Nubiato, Keni Eduardo Zanoni; Mazon, Madeline Rezende; Antonelo, Daniel Silva; Calkins, Chris R.; Naganathan, Govindarajan Konda; Subbiah, Jeyamkondan; da Luz e Silva, Saulo

2018-03-01

The aim of this study was to evaluate the accuracy of classification of Nellore beef aged for 0, 7, 14, or 21 days and classification based on tenderness and aging period using a bench-top hyperspectral imaging system. A hyperspectral imaging system (λ = 928-2524 nm) was used to collect hyperspectral images of the Longissimus thoracis et lumborum (aging n = 376 and tenderness n = 345) of Nellore cattle. The image processing steps included selection of region of interest, extraction of spectra, and indentification and evalution of selected wavelengths for classification. Six linear discriminant models were developed to classify samples based on tenderness and aging period. The model using the first derivative of partial absorbance spectra (give wavelength range spectra) was able to classify steaks based on the tenderness with an overall accuracy of 89.8%. The model using the first derivative of full absorbance spectra was able to classify steaks based on aging period with an overall accuracy of 84.8%. The results demonstrate that the HIS may be a viable technology for classifying beef based on tenderness and aging period.

Improving EMG based classification of basic hand movements using EMD.

PubMed

Sapsanis, Christos; Georgoulas, George; Tzes, Anthony; Lymberopoulos, Dimitrios

2013-01-01

This paper presents a pattern recognition approach for the identification of basic hand movements using surface electromyographic (EMG) data. The EMG signal is decomposed using Empirical Mode Decomposition (EMD) into Intrinsic Mode Functions (IMFs) and subsequently a feature extraction stage takes place. Various combinations of feature subsets are tested using a simple linear classifier for the detection task. Our results suggest that the use of EMD can increase the discrimination ability of the conventional feature sets extracted from the raw EMG signal.

Optical diagnosis of cervical cancer by higher order spectra and boosting

NASA Astrophysics Data System (ADS)

Pratiher, Sawon; Mukhopadhyay, Sabyasachi; Barman, Ritwik; Pratiher, Souvik; Pradhan, Asima; Ghosh, Nirmalya; Panigrahi, Prasanta K.

2017-03-01

In this contribution, we report the application of higher order statistical moments using decision tree and ensemble based learning methodology for the development of diagnostic algorithms for optical diagnosis of cancer. The classification results were compared to those obtained with an independent feature extractors like linear discriminant analysis (LDA). The performance and efficacy of these methodology using higher order statistics as a classifier using boosting has higher specificity and sensitivity while being much faster as compared to other time-frequency domain based methods.

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.

Dynamic Dimensionality Selection for Bayesian Classifier Ensembles

DTIC Science & Technology

2015-03-19

learning of weights in an otherwise generatively learned naive Bayes classifier. WANBIA-C is very cometitive to Logistic Regression but much more...classifier, Generative learning, Discriminative learning, Naïve Bayes, Feature selection, Logistic regression , higher order attribute independence 16...discriminative learning of weights in an otherwise generatively learned naive Bayes classifier. WANBIA-C is very cometitive to Logistic Regression but

Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI

NASA Astrophysics Data System (ADS)

Niaf, Emilie; Rouvière, Olivier; Mège-Lechevallier, Florence; Bratan, Flavie; Lartizien, Carole

2012-06-01

This study evaluated a computer-assisted diagnosis (CADx) system for determining a likelihood measure of prostate cancer presence in the peripheral zone (PZ) based on multiparametric magnetic resonance (MR) imaging, including T2-weighted, diffusion-weighted and dynamic contrast-enhanced MRI at 1.5 T. Based on a feature set derived from grey-level images, including first-order statistics, Haralick features, gradient features, semi-quantitative and quantitative (pharmacokinetic modelling) dynamic parameters, four kinds of classifiers were trained and compared : nonlinear support vector machine (SVM), linear discriminant analysis, k-nearest neighbours and naïve Bayes classifiers. A set of feature selection methods based on t-test, mutual information and minimum-redundancy-maximum-relevancy criteria were also compared. The aim was to discriminate between the relevant features as well as to create an efficient classifier using these features. The diagnostic performances of these different CADx schemes were evaluated based on a receiver operating characteristic (ROC) curve analysis. The evaluation database consisted of 30 sets of multiparametric MR images acquired from radical prostatectomy patients. Using histologic sections as the gold standard, both cancer and nonmalignant (but suspicious) tissues were annotated in consensus on all MR images by two radiologists, a histopathologist and a researcher. Benign tissue regions of interest (ROIs) were also delineated in the remaining prostate PZ. This resulted in a series of 42 cancer ROIs, 49 benign but suspicious ROIs and 124 nonsuspicious benign ROIs. From the outputs of all evaluated feature selection methods on the test bench, a restrictive set of about 15 highly informative features coming from all MR sequences was discriminated, thus confirming the validity of the multiparametric approach. Quantitative evaluation of the diagnostic performance yielded a maximal area under the ROC curve (AUC) of 0.89 (0.81-0.94) for the discrimination of the malignant versus nonmalignant tissues and 0.82 (0.73-0.90) for the discrimination of the malignant versus suspicious tissues when combining the t-test feature selection approach with a SVM classifier. A preliminary comparison showed that the optimal CADx scheme mimicked, in terms of AUC, the human experts in differentiating malignant from suspicious tissues, thus demonstrating its potential for assisting cancer identification in the PZ.

Discrimination-Aware Classifiers for Student Performance Prediction

ERIC Educational Resources Information Center

Luo, Ling; Koprinska, Irena; Liu, Wei

2015-01-01

In this paper we consider discrimination-aware classification of educational data. Mining and using rules that distinguish groups of students based on sensitive attributes such as gender and nationality may lead to discrimination. It is desirable to keep the sensitive attributes during the training of a classifier to avoid information loss but…

Interpretability of Multivariate Brain Maps in Linear Brain Decoding: Definition, and Heuristic Quantification in Multivariate Analysis of MEG Time-Locked Effects.

PubMed

Kia, Seyed Mostafa; Vega Pons, Sandro; Weisz, Nathan; Passerini, Andrea

2016-01-01

Brain decoding is a popular multivariate approach for hypothesis testing in neuroimaging. Linear classifiers are widely employed in the brain decoding paradigm to discriminate among experimental conditions. Then, the derived linear weights are visualized in the form of multivariate brain maps to further study spatio-temporal patterns of underlying neural activities. It is well known that the brain maps derived from weights of linear classifiers are hard to interpret because of high correlations between predictors, low signal to noise ratios, and the high dimensionality of neuroimaging data. Therefore, improving the interpretability of brain decoding approaches is of primary interest in many neuroimaging studies. Despite extensive studies of this type, at present, there is no formal definition for interpretability of multivariate brain maps. As a consequence, there is no quantitative measure for evaluating the interpretability of different brain decoding methods. In this paper, first, we present a theoretical definition of interpretability in brain decoding; we show that the interpretability of multivariate brain maps can be decomposed into their reproducibility and representativeness. Second, as an application of the proposed definition, we exemplify a heuristic for approximating the interpretability in multivariate analysis of evoked magnetoencephalography (MEG) responses. Third, we propose to combine the approximated interpretability and the generalization performance of the brain decoding into a new multi-objective criterion for model selection. Our results, for the simulated and real MEG data, show that optimizing the hyper-parameters of the regularized linear classifier based on the proposed criterion results in more informative multivariate brain maps. More importantly, the presented definition provides the theoretical background for quantitative evaluation of interpretability, and hence, facilitates the development of more effective brain decoding algorithms in the future.

Interpretability of Multivariate Brain Maps in Linear Brain Decoding: Definition, and Heuristic Quantification in Multivariate Analysis of MEG Time-Locked Effects

PubMed Central

Kia, Seyed Mostafa; Vega Pons, Sandro; Weisz, Nathan; Passerini, Andrea

2017-01-01

Brain decoding is a popular multivariate approach for hypothesis testing in neuroimaging. Linear classifiers are widely employed in the brain decoding paradigm to discriminate among experimental conditions. Then, the derived linear weights are visualized in the form of multivariate brain maps to further study spatio-temporal patterns of underlying neural activities. It is well known that the brain maps derived from weights of linear classifiers are hard to interpret because of high correlations between predictors, low signal to noise ratios, and the high dimensionality of neuroimaging data. Therefore, improving the interpretability of brain decoding approaches is of primary interest in many neuroimaging studies. Despite extensive studies of this type, at present, there is no formal definition for interpretability of multivariate brain maps. As a consequence, there is no quantitative measure for evaluating the interpretability of different brain decoding methods. In this paper, first, we present a theoretical definition of interpretability in brain decoding; we show that the interpretability of multivariate brain maps can be decomposed into their reproducibility and representativeness. Second, as an application of the proposed definition, we exemplify a heuristic for approximating the interpretability in multivariate analysis of evoked magnetoencephalography (MEG) responses. Third, we propose to combine the approximated interpretability and the generalization performance of the brain decoding into a new multi-objective criterion for model selection. Our results, for the simulated and real MEG data, show that optimizing the hyper-parameters of the regularized linear classifier based on the proposed criterion results in more informative multivariate brain maps. More importantly, the presented definition provides the theoretical background for quantitative evaluation of interpretability, and hence, facilitates the development of more effective brain decoding algorithms in the future. PMID:28167896

Discrimination of Man-Made Events and Tectonic Earthquakes in Utah Using Data Recorded at Local Distances

NASA Astrophysics Data System (ADS)

Tibi, R.; Young, C. J.; Koper, K. D.; Pankow, K. L.

2017-12-01

Seismic event discrimination methods exploit the differing characteristics—in terms of amplitude and/or frequency content—of the generated seismic phases among the event types to be classified. Most of the commonly used seismic discrimination methods are designed for regional data recorded at distances of about 200 to 2000 km. Relatively little attention has focused on discriminants for local distances (< 200 km), the range at which the smallest events are recorded. Short-period fundamental mode Rayleigh waves (Rg) are commonly observed on seismograms of man-made seismic events, and shallow, naturally occurring tectonic earthquakes recorded at local distances. We leverage the well-known notion that Rg amplitude decreases dramatically with increasing event depth to propose a new depth discriminant based on Rg-to-Sg spectral amplitude ratios. The approach is successfully used to discriminate shallow events from deeper tectonic earthquakes in the Utah region recorded at local distances (< 150 km) by the University of Utah Seismographic Stations (UUSS) regional seismic network. Using Mood's median test, we obtained probabilities of nearly zero that the median Rg-to-Sg spectral amplitude ratios are the same between shallow events on one side (including both shallow tectonic earthquakes and man-made events), and deeper earthquakes on the other side, suggesting that there is a statistically significant difference in the estimated Rg-to-Sg ratios between the two populations. We also observed consistent disparities between the different types of shallow events (e.g., explosions vs. mining-induced events), implying that it may be possible to separate the sub-populations that make up this group. This suggests that using local distance Rg-to-Sg spectral amplitude ratios one can not only discriminate shallow from deeper events, but may also be able to discriminate different populations of shallow events. We also experimented with Pg-to-Sg amplitude ratios in multi-frequency linear discriminant functions to classify man-made events and tectonic earthquakes in Utah. Initial results are very promising, showing probabilities of misclassification of only 2.4-14.3%.

Application of texture analysis method for classification of benign and malignant thyroid nodules in ultrasound images.

PubMed

Abbasian Ardakani, Ali; Gharbali, Akbar; Mohammadi, Afshin

2015-01-01

The aim of this study was to evaluate computer aided diagnosis (CAD) system with texture analysis (TA) to improve radiologists' accuracy in identification of thyroid nodules as malignant or benign. A total of 70 cases (26 benign and 44 malignant) were analyzed in this study. We extracted up to 270 statistical texture features as a descriptor for each selected region of interests (ROIs) in three normalization schemes (default, 3s and 1%-99%). Then features by the lowest probability of classification error and average correlation coefficients (POE+ACC), and Fisher coefficient (Fisher) eliminated to 10 best and most effective features. These features were analyzed under standard and nonstandard states. For TA of the thyroid nodules, Principle Component Analysis (PCA), Linear Discriminant Analysis (LDA) and Non-Linear Discriminant Analysis (NDA) were applied. First Nearest-Neighbour (1-NN) classifier was performed for the features resulting from PCA and LDA. NDA features were classified by artificial neural network (A-NN). Receiver operating characteristic (ROC) curve analysis was used for examining the performance of TA methods. The best results were driven in 1-99% normalization with features extracted by POE+ACC algorithm and analyzed by NDA with the area under the ROC curve ( Az) of 0.9722 which correspond to sensitivity of 94.45%, specificity of 100%, and accuracy of 97.14%. Our results indicate that TA is a reliable method, can provide useful information help radiologist in detection and classification of benign and malignant thyroid nodules.

Unsupervised learning of discriminative edge measures for vehicle matching between nonoverlapping cameras.

PubMed

Shan, Ying; Sawhney, Harpreet S; Kumar, Rakesh

2008-04-01

This paper proposes a novel unsupervised algorithm learning discriminative features in the context of matching road vehicles between two non-overlapping cameras. The matching problem is formulated as a same-different classification problem, which aims to compute the probability of vehicle images from two distinct cameras being from the same vehicle or different vehicle(s). We employ a novel measurement vector that consists of three independent edge-based measures and their associated robust measures computed from a pair of aligned vehicle edge maps. The weight of each measure is determined by an unsupervised learning algorithm that optimally separates the same-different classes in the combined measurement space. This is achieved with a weak classification algorithm that automatically collects representative samples from same-different classes, followed by a more discriminative classifier based on Fisher' s Linear Discriminants and Gibbs Sampling. The robustness of the match measures and the use of unsupervised discriminant analysis in the classification ensures that the proposed method performs consistently in the presence of missing/false features, temporally and spatially changing illumination conditions, and systematic misalignment caused by different camera configurations. Extensive experiments based on real data of over 200 vehicles at different times of day demonstrate promising results.

Differentiation of Chinese rice wines from different wineries based on mineral elemental fingerprinting.

PubMed

Shen, Fei; Wu, Jian; Ying, Yibin; Li, Bobin; Jiang, Tao

2013-12-15

Discrimination of Chinese rice wines from three well-known wineries ("Guyuelongshan", "Kuaijishan", and "Pagoda") in China has been carried out according to mineral element contents in this study. Nineteen macro and trace mineral elements (Na, Mg, Al, K, Ca, Mn, Fe, Cu, Zn, V, Cr, Co, Ni, As, Se, Mo, Cd, Ba and Pb) were determined by inductively coupled plasma mass spectrometry (ICP-MS) in 117 samples. Then the experimental data were subjected to analysis of variance (ANOVA) and principal component analysis (PCA) to reveal significant differences and potential patterns between samples. Stepwise linear discriminant analysis (LDA) and partial least square discriminant analysis (PLS-DA) were applied to develop classification models and achieved correct classified rates of 100% and 97.4% for the prediction sample set, respectively. The discrimination could be attributed to different raw materials (mainly water) and elaboration processes employed. The results indicate that the element compositions combined with multivariate analysis can be used as fingerprinting techniques to protect prestigious wineries and enable the authenticity of Chinese rice wine. Copyright © 2013 Elsevier Ltd. All rights reserved.

Geographical origin discrimination of lentils (Lens culinaris Medik.) using 1H NMR fingerprinting and multivariate statistical analyses.

PubMed

Longobardi, Francesco; Innamorato, Valentina; Di Gioia, Annalisa; Ventrella, Andrea; Lippolis, Vincenzo; Logrieco, Antonio F; Catucci, Lucia; Agostiano, Angela

2017-12-15

Lentil samples coming from two different countries, i.e. Italy and Canada, were analysed using untargeted 1 H NMR fingerprinting in combination with chemometrics in order to build models able to classify them according to their geographical origin. For such aim, Soft Independent Modelling of Class Analogy (SIMCA), k-Nearest Neighbor (k-NN), Principal Component Analysis followed by Linear Discriminant Analysis (PCA-LDA) and Partial Least Squares-Discriminant Analysis (PLS-DA) were applied to the NMR data and the results were compared. The best combination of average recognition (100%) and cross-validation prediction abilities (96.7%) was obtained for the PCA-LDA. All the statistical models were validated both by using a test set and by carrying out a Monte Carlo Cross Validation: the obtained performances were found to be satisfying for all the models, with prediction abilities higher than 95% demonstrating the suitability of the developed methods. Finally, the metabolites that mostly contributed to the lentil discrimination were indicated. Copyright © 2017 Elsevier Ltd. All rights reserved.

Deep and Structured Robust Information Theoretic Learning for Image Analysis.

PubMed

Deng, Yue; Bao, Feng; Deng, Xuesong; Wang, Ruiping; Kong, Youyong; Dai, Qionghai

2016-07-07

This paper presents a robust information theoretic (RIT) model to reduce the uncertainties, i.e. missing and noisy labels, in general discriminative data representation tasks. The fundamental pursuit of our model is to simultaneously learn a transformation function and a discriminative classifier that maximize the mutual information of data and their labels in the latent space. In this general paradigm, we respectively discuss three types of the RIT implementations with linear subspace embedding, deep transformation and structured sparse learning. In practice, the RIT and deep RIT are exploited to solve the image categorization task whose performances will be verified on various benchmark datasets. The structured sparse RIT is further applied to a medical image analysis task for brain MRI segmentation that allows group-level feature selections on the brain tissues.

Quantitation of twelve metals in tequila and mezcal spirits as authenticity parameters.

PubMed

Ceballos-Magańa, Silvia Guillermina; Jurado, José Marcos; Martín, María Jesús; Pablos, Fernando

2009-02-25

In this paper the differentiation of silver, gold, aged and extra-aged tequila and mezcal has been carried out according to their metal content. Aluminum, barium, calcium, copper, iron, magnesium, manganese, potassium, sodium, strontium, zinc, and sulfur were determined by inductively coupled plasma optical emission spectrometry. The concentrations found for each element in the samples were used as chemical descriptors for characterization purposes. Principal component analysis, linear discriminant analysis and artificial neural networks were applied to differentiate types of tequila and mezcal. Using probabilistic neural networks 100% of success in the classification was obtained for silver, gold, extra-aged tequila and mezcal. In the case of aged tequila 90% of samples were successfully classified. Sodium, potassium, calcium, sulfur, magnesium, iron, strontium, copper and zinc were the most discriminant elements.

Cortical activity patterns predict robust speech discrimination ability in noise

PubMed Central

Shetake, Jai A.; Wolf, Jordan T.; Cheung, Ryan J.; Engineer, Crystal T.; Ram, Satyananda K.; Kilgard, Michael P.

2012-01-01

The neural mechanisms that support speech discrimination in noisy conditions are poorly understood. In quiet conditions, spike timing information appears to be used in the discrimination of speech sounds. In this study, we evaluated the hypothesis that spike timing is also used to distinguish between speech sounds in noisy conditions that significantly degrade neural responses to speech sounds. We tested speech sound discrimination in rats and recorded primary auditory cortex (A1) responses to speech sounds in background noise of different intensities and spectral compositions. Our behavioral results indicate that rats, like humans, are able to accurately discriminate consonant sounds even in the presence of background noise that is as loud as the speech signal. Our neural recordings confirm that speech sounds evoke degraded but detectable responses in noise. Finally, we developed a novel neural classifier that mimics behavioral discrimination. The classifier discriminates between speech sounds by comparing the A1 spatiotemporal activity patterns evoked on single trials with the average spatiotemporal patterns evoked by known sounds. Unlike classifiers in most previous studies, this classifier is not provided with the stimulus onset time. Neural activity analyzed with the use of relative spike timing was well correlated with behavioral speech discrimination in quiet and in noise. Spike timing information integrated over longer intervals was required to accurately predict rat behavioral speech discrimination in noisy conditions. The similarity of neural and behavioral discrimination of speech in noise suggests that humans and rats may employ similar brain mechanisms to solve this problem. PMID:22098331

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.

Performance and strategy comparisons of human listeners and logistic regression in discriminating underwater targets.

PubMed

Yang, Lixue; Chen, Kean

2015-11-01

To improve the design of underwater target recognition systems based on auditory perception, this study compared human listeners with automatic classifiers. Performances measures and strategies in three discrimination experiments, including discriminations between man-made and natural targets, between ships and submarines, and among three types of ships, were used. In the experiments, the subjects were asked to assign a score to each sound based on how confident they were about the category to which it belonged, and logistic regression, which represents linear discriminative models, also completed three similar tasks by utilizing many auditory features. The results indicated that the performances of logistic regression improved as the ratio between inter- and intra-class differences became larger, whereas the performances of the human subjects were limited by their unfamiliarity with the targets. Logistic regression performed better than the human subjects in all tasks but the discrimination between man-made and natural targets, and the strategies employed by excellent human subjects were similar to that of logistic regression. Logistic regression and several human subjects demonstrated similar performances when discriminating man-made and natural targets, but in this case, their strategies were not similar. An appropriate fusion of their strategies led to further improvement in recognition accuracy.

Highly sensitive molecular diagnosis of prostate cancer using surplus material washed off from biopsy needles

PubMed Central

Bermudo, R; Abia, D; Mozos, A; García-Cruz, E; Alcaraz, A; Ortiz, Á R; Thomson, T M; Fernández, P L

2011-01-01

Introduction: Currently, final diagnosis of prostate cancer (PCa) is based on histopathological analysis of needle biopsies, but this process often bears uncertainties due to small sample size, tumour focality and pathologist's subjective assessment. Methods: Prostate cancer diagnostic signatures were generated by applying linear discriminant analysis to microarray and real-time RT–PCR (qRT–PCR) data from normal and tumoural prostate tissue samples. Additionally, after removal of biopsy tissues, material washed off from transrectal biopsy needles was used for molecular profiling and discriminant analysis. Results: Linear discriminant analysis applied to microarray data for a set of 318 genes differentially expressed between non-tumoural and tumoural prostate samples produced 26 gene signatures, which classified the 84 samples used with 100% accuracy. To identify signatures potentially useful for the diagnosis of prostate biopsies, surplus material washed off from routine biopsy needles from 53 patients was used to generate qRT–PCR data for a subset of 11 genes. This analysis identified a six-gene signature that correctly assigned the biopsies as benign or tumoural in 92.6% of the cases, with 88.8% sensitivity and 96.1% specificity. Conclusion: Surplus material from prostate needle biopsies can be used for minimal-size gene signature analysis for sensitive and accurate discrimination between non-tumoural and tumoural prostates, without interference with current diagnostic procedures. This approach could be a useful adjunct to current procedures in PCa diagnosis. PMID:22009027

Classification of cardiovascular tissues using LBP based descriptors and a cascade SVM.

PubMed

Mazo, Claudia; Alegre, Enrique; Trujillo, Maria

2017-08-01

Histological images have characteristics, such as texture, shape, colour and spatial structure, that permit the differentiation of each fundamental tissue and organ. Texture is one of the most discriminative features. The automatic classification of tissues and organs based on histology images is an open problem, due to the lack of automatic solutions when treating tissues without pathologies. In this paper, we demonstrate that it is possible to automatically classify cardiovascular tissues using texture information and Support Vector Machines (SVM). Additionally, we realised that it is feasible to recognise several cardiovascular organs following the same process. The texture of histological images was described using Local Binary Patterns (LBP), LBP Rotation Invariant (LBPri), Haralick features and different concatenations between them, representing in this way its content. Using a SVM with linear kernel, we selected the more appropriate descriptor that, for this problem, was a concatenation of LBP and LBPri. Due to the small number of the images available, we could not follow an approach based on deep learning, but we selected the classifier who yielded the higher performance by comparing SVM with Random Forest and Linear Discriminant Analysis. Once SVM was selected as the classifier with a higher area under the curve that represents both higher recall and precision, we tuned it evaluating different kernels, finding that a linear SVM allowed us to accurately separate four classes of tissues: (i) cardiac muscle of the heart, (ii) smooth muscle of the muscular artery, (iii) loose connective tissue, and (iv) smooth muscle of the large vein and the elastic artery. The experimental validation was conducted using 3000 blocks of 100 × 100 sized pixels, with 600 blocks per class and the classification was assessed using a 10-fold cross-validation. using LBP as the descriptor, concatenated with LBPri and a SVM with linear kernel, the main four classes of tissues were recognised with an AUC higher than 0.98. A polynomial kernel was then used to separate the elastic artery and vein, yielding an AUC in both cases superior to 0.98. Following the proposed approach, it is possible to separate with very high precision (AUC greater than 0.98) the fundamental tissues of the cardiovascular system along with some organs, such as the heart, arteries and veins. Copyright © 2017 Elsevier B.V. All rights reserved.

Unambiguous discrimination between linearly dependent equidistant states with multiple copies

NASA Astrophysics Data System (ADS)

Zhang, Wen-Hai; Ren, Gang

2018-07-01

Linearly independent quantum states can be unambiguously discriminated, but linearly dependent ones cannot. For linearly dependent quantum states, however, if C copies of the single states are available, then they may form linearly independent states, and can be unambiguously discriminated. We consider unambiguous discrimination among N = D + 1 linearly dependent states given that C copies are available and that the single copies span a D-dimensional space with equal inner products. The maximum unambiguous discrimination probability is derived for all C with equal a priori probabilities. For this classification of the linearly dependent equidistant states, our result shows that if C is even then adding a further copy fails to increase the maximum discrimination probability.

Comparative evaluation of support vector machine classification for computer aided detection of breast masses in mammography

NASA Astrophysics Data System (ADS)

Lesniak, J. M.; Hupse, R.; Blanc, R.; Karssemeijer, N.; Székely, G.

2012-08-01

False positive (FP) marks represent an obstacle for effective use of computer-aided detection (CADe) of breast masses in mammography. Typically, the problem can be approached either by developing more discriminative features or by employing different classifier designs. In this paper, the usage of support vector machine (SVM) classification for FP reduction in CADe is investigated, presenting a systematic quantitative evaluation against neural networks, k-nearest neighbor classification, linear discriminant analysis and random forests. A large database of 2516 film mammography examinations and 73 input features was used to train the classifiers and evaluate for their performance on correctly diagnosed exams as well as false negatives. Further, classifier robustness was investigated using varying training data and feature sets as input. The evaluation was based on the mean exam sensitivity in 0.05-1 FPs on normals on the free-response receiver operating characteristic curve (FROC), incorporated into a tenfold cross validation framework. It was found that SVM classification using a Gaussian kernel offered significantly increased detection performance (P = 0.0002) compared to the reference methods. Varying training data and input features, SVMs showed improved exploitation of large feature sets. It is concluded that with the SVM-based CADe a significant reduction of FPs is possible outperforming other state-of-the-art approaches for breast mass CADe.

A Pulsed Thermographic Imaging System for Detection and Identification of Cotton Foreign Matter

PubMed Central

Kuzy, Jesse; Li, Changying

2017-01-01

Detection of foreign matter in cleaned cotton is instrumental to accurately grading cotton quality, which in turn impacts the marketability of the cotton. Current grading systems return estimates of the amount of foreign matter present, but provide no information about the identity of the contaminants. This paper explores the use of pulsed thermographic analysis to detect and identify cotton foreign matter. The design and implementation of a pulsed thermographic analysis system is described. A sample set of 240 foreign matter and cotton lint samples were collected. Hand-crafted waveform features and frequency-domain features were extracted and analyzed for statistical significance. Classification was performed on these features using linear discriminant analysis and support vector machines. Using waveform features and support vector machine classifiers, detection of cotton foreign matter was performed with 99.17% accuracy. Using frequency-domain features and linear discriminant analysis, identification was performed with 90.00% accuracy. These results demonstrate that pulsed thermographic imaging analysis produces data which is of significant utility for the detection and identification of cotton foreign matter. PMID:28273848

Enzyme class identification in cleaning products by hydrolysis followed by derivatization with o-phthaldialdehyde, HPLC and linear discriminant analysis.

PubMed

Beneito-Cambra, M; Bernabé-Zafón, V; Herrero-Martínez, J M; Simó-Alfonso, E F; Ramis-Ramos, G

2009-07-15

The enzymes present in raw materials of the cleaning industry (enzyme industrial concentrates) and in household cleaners were isolated by precipitation with acetone and hydrolyzed with HCl. The resulting amino acids were derivatized with o-phthaldialdehyde, and the derivatives were separated by HPLC. The peaks of 14 amino acids were observed using a C18 column and a multi-segmented gradient of acetonitrile-water in the presence of a 5 mM citric/citrate buffer of pH 6.5. Using either normalized peak areas (divided by the sum of the peak areas of the chromatogram) or ratios of pairs of peak areas as predictor variables, linear discriminant analysis models, capable of predicting the enzyme class, including proteases, lipases, amylases and cellulases, were constructed. For this purpose, both enzyme industrial concentrates and detergent bases spiked with them were included in the training set. In all cases, the enzymes of the evaluation set, including industrial concentrates, spiked detergent bases and commercial cleaners were correctly classified with assignment probabilities higher than 99%.

Authentication of animal origin of heparin and low molecular weight heparin including ovine, porcine and bovine species using 1D NMR spectroscopy and chemometric tools.

PubMed

Monakhova, Yulia B; Diehl, Bernd W K; Fareed, Jawed

2018-02-05

High resolution (600MHz) nuclear magnetic resonance (NMR) spectroscopy is used to distinguish heparin and low-molecular weight heparins (LMWHs) produced from porcine, bovine and ovine mucosal tissues as well as their blends. For multivariate analysis several statistical methods such as principal component analysis (PCA), factor discriminant analysis (FDA), partial least squares - discriminant analysis (PLS-DA), linear discriminant analysis (LDA) were utilized for the modeling of NMR data of more than 100 authentic samples. Heparin and LMWH samples from the independent test set (n=15) were 100% correctly classified according to its animal origin. Moreover, by using 1 H NMR coupled with chemometrics and several batches of bovine heparins from two producers were differentiated. Thus, NMR spectroscopy combined with chemometrics is an efficient tool for simultaneous identification of animal origin and process based manufacturing difference in heparin products. Copyright © 2017 Elsevier B.V. All rights reserved.

Chemometric classification of apple juices according to variety and geographical origin based on polyphenolic profiles.

PubMed

Guo, Jing; Yue, Tianli; Yuan, Yahong; Wang, Yutang

2013-07-17

To characterize and classify apple juices according to apple variety and geographical origin on the basis of their polyphenol composition, the polyphenolic profiles of 58 apple juice samples belonging to 5 apple varieties and from 6 regions in Shaanxi province of China were assessed. Fifty-one of the samples were from protected designation of origin (PDO) districts. Polyphenols were determined by high-performance liquid chromatography coupled to photodiode array detection (HPLC-PDA) and to a Q Exactive quadrupole-Orbitrap mass spectrometer. Chemometric techniques including principal component analysis (PCA) and stepwise linear discriminant analysis (SLDA) were carried out on polyphenolic profiles of the samples to develop discrimination models. SLDA achieved satisfactory discriminations of apple juices according to variety and geographical origin, providing respectively 98.3 and 91.2% success rate in terms of prediction ability. This result demonstrated that polyphenols could served as characteristic indices to verify the variety and geographical origin of apple juices.

Vowel Imagery Decoding toward Silent Speech BCI Using Extreme Learning Machine with Electroencephalogram

PubMed Central

Kim, Jongin; Park, Hyeong-jun

2016-01-01

The purpose of this study is to classify EEG data on imagined speech in a single trial. We recorded EEG data while five subjects imagined different vowels, /a/, /e/, /i/, /o/, and /u/. We divided each single trial dataset into thirty segments and extracted features (mean, variance, standard deviation, and skewness) from all segments. To reduce the dimension of the feature vector, we applied a feature selection algorithm based on the sparse regression model. These features were classified using a support vector machine with a radial basis function kernel, an extreme learning machine, and two variants of an extreme learning machine with different kernels. Because each single trial consisted of thirty segments, our algorithm decided the label of the single trial by selecting the most frequent output among the outputs of the thirty segments. As a result, we observed that the extreme learning machine and its variants achieved better classification rates than the support vector machine with a radial basis function kernel and linear discrimination analysis. Thus, our results suggested that EEG responses to imagined speech could be successfully classified in a single trial using an extreme learning machine with a radial basis function and linear kernel. This study with classification of imagined speech might contribute to the development of silent speech BCI systems. PMID:28097128

Multiple directed graph large-class multi-spectral processor

NASA Technical Reports Server (NTRS)

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

1988-01-01

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

Automatic Cataract Hardness Classification Ex Vivo by Ultrasound Techniques.

PubMed

Caixinha, Miguel; Santos, Mário; Santos, Jaime

2016-04-01

To demonstrate the feasibility of a new methodology for cataract hardness characterization and automatic classification using ultrasound techniques, different cataract degrees were induced in 210 porcine lenses. A 25-MHz ultrasound transducer was used to obtain acoustical parameters (velocity and attenuation) and backscattering signals. B-Scan and parametric Nakagami images were constructed. Ninety-seven parameters were extracted and subjected to a Principal Component Analysis. Bayes, K-Nearest-Neighbours, Fisher Linear Discriminant and Support Vector Machine (SVM) classifiers were used to automatically classify the different cataract severities. Statistically significant increases with cataract formation were found for velocity, attenuation, mean brightness intensity of the B-Scan images and mean Nakagami m parameter (p < 0.01). The four classifiers showed a good performance for healthy versus cataractous lenses (F-measure ≥ 92.68%), while for initial versus severe cataracts the SVM classifier showed the higher performance (90.62%). The results showed that ultrasound techniques can be used for non-invasive cataract hardness characterization and automatic classification. Copyright © 2016 World Federation for Ultrasound in Medicine & Biology. Published by Elsevier Inc. All rights reserved.

Automatic classification of artifactual ICA-components for artifact removal in EEG signals.

PubMed

Winkler, Irene; Haufe, Stefan; Tangermann, Michael

2011-08-02

Artifacts contained in EEG recordings hamper both, the visual interpretation by experts as well as the algorithmic processing and analysis (e.g. for Brain-Computer Interfaces (BCI) or for Mental State Monitoring). While hand-optimized selection of source components derived from Independent Component Analysis (ICA) to clean EEG data is widespread, the field could greatly profit from automated solutions based on Machine Learning methods. Existing ICA-based removal strategies depend on explicit recordings of an individual's artifacts or have not been shown to reliably identify muscle artifacts. We propose an automatic method for the classification of general artifactual source components. They are estimated by TDSEP, an ICA method that takes temporal correlations into account. The linear classifier is based on an optimized feature subset determined by a Linear Programming Machine (LPM). The subset is composed of features from the frequency-, the spatial- and temporal domain. A subject independent classifier was trained on 640 TDSEP components (reaction time (RT) study, n = 12) that were hand labeled by experts as artifactual or brain sources and tested on 1080 new components of RT data of the same study. Generalization was tested on new data from two studies (auditory Event Related Potential (ERP) paradigm, n = 18; motor imagery BCI paradigm, n = 80) that used data with different channel setups and from new subjects. Based on six features only, the optimized linear classifier performed on level with the inter-expert disagreement (<10% Mean Squared Error (MSE)) on the RT data. On data of the auditory ERP study, the same pre-calculated classifier generalized well and achieved 15% MSE. On data of the motor imagery paradigm, we demonstrate that the discriminant information used for BCI is preserved when removing up to 60% of the most artifactual source components. We propose a universal and efficient classifier of ICA components for the subject independent removal of artifacts from EEG data. Based on linear methods, it is applicable for different electrode placements and supports the introspection of results. Trained on expert ratings of large data sets, it is not restricted to the detection of eye- and muscle artifacts. Its performance and generalization ability is demonstrated on data of different EEG studies.

Towards a hemodynamic BCI using transcranial Doppler without user-specific training data

NASA Astrophysics Data System (ADS)

Aleem, Idris; Chau, Tom

2013-02-01

Transcranial Doppler (TCD) was recently introduced as a new brain-computer interface (BCI) modality for detecting task-induced hemispheric lateralization. To date, single-trial discrimination between a lateralized mental activity and a rest state has been demonstrated with long (45 s) activation time periods. However, the possibility of detecting successive activations in a user-independent framework (i.e. without training data from the user) remains an open question. Objective. The objective of this research was to assess TCD-based detection of lateralized mental activity with a user-independent classifier. In so doing, we also investigated the accuracy of detecting successive lateralizations. Approach. TCD data from 18 participants were collected during verbal fluency, mental rotation tasks and baseline counting tasks. Linear discriminant analysis and a set of four time-domain features were used to classify successive left and right brain activations. Main results. In a user-independent framework, accuracies up to 74.6 ± 12.6% were achieved using training data from a single participant, and lateralization task durations of 18 s. Significance. Subject-independent, algorithmic classification of TCD signals corresponding to successive brain lateralization may be a feasible paradigm for TCD-BCI design.

High-speed potato grading and quality inspection based on a color vision system

NASA Astrophysics Data System (ADS)

Noordam, Jacco C.; Otten, Gerwoud W.; Timmermans, Toine J. M.; van Zwol, Bauke H.

2000-03-01

A high-speed machine vision system for the quality inspection and grading of potatoes has been developed. The vision system grades potatoes on size, shape and external defects such as greening, mechanical damages, rhizoctonia, silver scab, common scab, cracks and growth cracks. A 3-CCD line-scan camera inspects the potatoes in flight as they pass under the camera. The use of mirrors to obtain a 360-degree view of the potato and the lack of product holders guarantee a full view of the potato. To achieve the required capacity of 12 tons/hour, 11 SHARC Digital Signal Processors perform the image processing and classification tasks. The total capacity of the system is about 50 potatoes/sec. The color segmentation procedure uses Linear Discriminant Analysis (LDA) in combination with a Mahalanobis distance classifier to classify the pixels. The procedure for the detection of misshapen potatoes uses a Fourier based shape classification technique. Features such as area, eccentricity and central moments are used to discriminate between similar colored defects. Experiments with red and yellow skin-colored potatoes have shown that the system is robust and consistent in its classification.

Classifying Failing States

DTIC Science & Technology

2007-03-01

state failure, and Discriminant Analysis to classify states as Stable, Borderline, or Failing based on these indicators. Furthermore, each...nation’s discriminant function scores are used to determine their degree of instability. The methodology is applied to 200 countries for which open source...and go for a long walk. Finally, to my wonderful wife, who now knows more about Discriminant Analysis than any Legal Assistant on the planet, thank

Segmentation of thalamus from MR images via task-driven dictionary learning

NASA Astrophysics Data System (ADS)

Liu, Luoluo; Glaister, Jeffrey; Sun, Xiaoxia; Carass, Aaron; Tran, Trac D.; Prince, Jerry L.

2016-03-01

Automatic thalamus segmentation is useful to track changes in thalamic volume over time. In this work, we introduce a task-driven dictionary learning framework to find the optimal dictionary given a set of eleven features obtained from T1-weighted MRI and diffusion tensor imaging. In this dictionary learning framework, a linear classifier is designed concurrently to classify voxels as belonging to the thalamus or non-thalamus class. Morphological post-processing is applied to produce the final thalamus segmentation. Due to the uneven size of the training data samples for the non-thalamus and thalamus classes, a non-uniform sampling scheme is pro- posed to train the classifier to better discriminate between the two classes around the boundary of the thalamus. Experiments are conducted on data collected from 22 subjects with manually delineated ground truth. The experimental results are promising in terms of improvements in the Dice coefficient of the thalamus segmentation overstate-of-the-art atlas-based thalamus segmentation algorithms.

Classifying Facial Actions

PubMed Central

Donato, Gianluca; Bartlett, Marian Stewart; Hager, Joseph C.; Ekman, Paul; Sejnowski, Terrence J.

2010-01-01

The Facial Action Coding System (FACS) [23] is an objective method for quantifying facial movement in terms of component actions. This system is widely used in behavioral investigations of emotion, cognitive processes, and social interaction. The coding is presently performed by highly trained human experts. This paper explores and compares techniques for automatically recognizing facial actions in sequences of images. These techniques include analysis of facial motion through estimation of optical flow; holistic spatial analysis, such as principal component analysis, independent component analysis, local feature analysis, and linear discriminant analysis; and methods based on the outputs of local filters, such as Gabor wavelet representations and local principal components. Performance of these systems is compared to naive and expert human subjects. Best performances were obtained using the Gabor wavelet representation and the independent component representation, both of which achieved 96 percent accuracy for classifying 12 facial actions of the upper and lower face. The results provide converging evidence for the importance of using local filters, high spatial frequencies, and statistical independence for classifying facial actions. PMID:21188284

Segmentation of Thalamus from MR images via Task-Driven Dictionary Learning.

PubMed

Liu, Luoluo; Glaister, Jeffrey; Sun, Xiaoxia; Carass, Aaron; Tran, Trac D; Prince, Jerry L

2016-02-27

Automatic thalamus segmentation is useful to track changes in thalamic volume over time. In this work, we introduce a task-driven dictionary learning framework to find the optimal dictionary given a set of eleven features obtained from T1-weighted MRI and diffusion tensor imaging. In this dictionary learning framework, a linear classifier is designed concurrently to classify voxels as belonging to the thalamus or non-thalamus class. Morphological post-processing is applied to produce the final thalamus segmentation. Due to the uneven size of the training data samples for the non-thalamus and thalamus classes, a non-uniform sampling scheme is proposed to train the classifier to better discriminate between the two classes around the boundary of the thalamus. Experiments are conducted on data collected from 22 subjects with manually delineated ground truth. The experimental results are promising in terms of improvements in the Dice coefficient of the thalamus segmentation over state-of-the-art atlas-based thalamus segmentation algorithms.

Automated processing of the single-lead electrocardiogram for the detection of obstructive sleep apnoea.

PubMed

de Chazal, Philip; Heneghan, Conor; Sheridan, Elaine; Reilly, Richard; Nolan, Philip; O'Malley, Mark

2003-06-01

A method for the automatic processing of the electrocardiogram (ECG) for the detection of obstructive apnoea is presented. The method screens nighttime single-lead ECG recordings for the presence of major sleep apnoea and provides a minute-by-minute analysis of disordered breathing. A large independently validated database of 70 ECG recordings acquired from normal subjects and subjects with obstructive and mixed sleep apnoea, each of approximately eight hours in duration, was used throughout the study. Thirty-five of these recordings were used for training and 35 retained for independent testing. A wide variety of features based on heartbeat intervals and an ECG-derived respiratory signal were considered. Classifiers based on linear and quadratic discriminants were compared. Feature selection and regularization of classifier parameters were used to optimize classifier performance. Results show that the normal recordings could be separated from the apnoea recordings with a 100% success rate and a minute-by-minute classification accuracy of over 90% is achievable.

Classification of vegetation types in military region

NASA Astrophysics Data System (ADS)

Gonçalves, Miguel; Silva, Jose Silvestre; Bioucas-Dias, Jose

2015-10-01

In decision-making process regarding planning and execution of military operations, the terrain is a determining factor. Aerial photographs are a source of vital information for the success of an operation in hostile region, namely when the cartographic information behind enemy lines is scarce or non-existent. The objective of present work is the development of a tool capable of processing aerial photos. The methodology implemented starts with feature extraction, followed by the application of an automatic selector of features. The next step, using the k-fold cross validation technique, estimates the input parameters for the following classifiers: Sparse Multinomial Logist Regression (SMLR), K Nearest Neighbor (KNN), Linear Classifier using Principal Component Expansion on the Joint Data (PCLDC) and Multi-Class Support Vector Machine (MSVM). These classifiers were used in two different studies with distinct objectives: discrimination of vegetation's density and identification of vegetation's main components. It was found that the best classifier on the first approach is the Sparse Logistic Multinomial Regression (SMLR). On the second approach, the implemented methodology applied to high resolution images showed that the better performance was achieved by KNN classifier and PCLDC. Comparing the two approaches there is a multiscale issue, in which for different resolutions, the best solution to the problem requires different classifiers and the extraction of different features.

Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics

PubMed Central

Belo, David; Gamboa, Hugo

2017-01-01

The paper presents results of machine learning approach accuracy applied analysis of cardiac activity. The study evaluates the diagnostics possibilities of the arterial hypertension by means of the short-term heart rate variability signals. Two groups were studied: 30 relatively healthy volunteers and 40 patients suffering from the arterial hypertension of II-III degree. The following machine learning approaches were studied: linear and quadratic discriminant analysis, k-nearest neighbors, support vector machine with radial basis, decision trees, and naive Bayes classifier. Moreover, in the study, different methods of feature extraction are analyzed: statistical, spectral, wavelet, and multifractal. All in all, 53 features were investigated. Investigation results show that discriminant analysis achieves the highest classification accuracy. The suggested approach of noncorrelated feature set search achieved higher results than data set based on the principal components. PMID:28831239

Authentication of the botanical origin of honey by near-infrared spectroscopy.

PubMed

Ruoff, Kaspar; Luginbühl, Werner; Bogdanov, Stefan; Bosset, Jacques Olivier; Estermann, Barbara; Ziolko, Thomas; Amado, Renato

2006-09-06

Fourier transform near-infrared spectroscopy (FT-NIR) was evaluated for the authentication of eight unifloral and polyfloral honey types (n = 364 samples) previously classified using traditional methods such as chemical, pollen, and sensory analysis. Chemometric evaluation of the spectra was carried out by applying principal component analysis and linear discriminant analysis. The corresponding error rates were calculated according to Bayes' theorem. NIR spectroscopy enabled a reliable discrimination of acacia, chestnut, and fir honeydew honey from the other unifloral and polyfloral honey types studied. The error rates ranged from <0.1 to 6.3% depending on the honey type. NIR proved also to be useful for the classification of blossom and honeydew honeys. The results demonstrate that near-infrared spectrometry is a valuable, rapid, and nondestructive tool for the authentication of the above-mentioned honeys, but not for all varieties studied.

A boosted optimal linear learner for retinal vessel segmentation

NASA Astrophysics Data System (ADS)

Poletti, E.; Grisan, E.

2014-03-01

Ocular fundus images provide important information about retinal degeneration, which may be related to acute pathologies or to early signs of systemic diseases. An automatic and quantitative assessment of vessel morphological features, such as diameters and tortuosity, can improve clinical diagnosis and evaluation of retinopathy. At variance with available methods, we propose a data-driven approach, in which the system learns a set of optimal discriminative convolution kernels (linear learner). The set is progressively built based on an ADA-boost sample weighting scheme, providing seamless integration between linear learner estimation and classification. In order to capture the vessel appearance changes at different scales, the kernels are estimated on a pyramidal decomposition of the training samples. The set is employed as a rotating bank of matched filters, whose response is used by the boosted linear classifier to provide a classification of each image pixel into the two classes of interest (vessel/background). We tested the approach fundus images available from the DRIVE dataset. We show that the segmentation performance yields an accuracy of 0.94.

Cortical sensorimotor alterations classify clinical phenotype and putative genotype of spasmodic dysphonia.

PubMed

Battistella, G; Fuertinger, S; Fleysher, L; Ozelius, L J; Simonyan, K

2016-10-01

Spasmodic dysphonia (SD), or laryngeal dystonia, is a task-specific isolated focal dystonia of unknown causes and pathophysiology. Although functional and structural abnormalities have been described in this disorder, the influence of its different clinical phenotypes and genotypes remains scant, making it difficult to explain SD pathophysiology and to identify potential biomarkers. We used a combination of independent component analysis and linear discriminant analysis of resting-state functional magnetic resonance imaging data to investigate brain organization in different SD phenotypes (abductor versus adductor type) and putative genotypes (familial versus sporadic cases) and to characterize neural markers for genotype/phenotype categorization. We found abnormal functional connectivity within sensorimotor and frontoparietal networks in patients with SD compared with healthy individuals as well as phenotype- and genotype-distinct alterations of these networks, involving primary somatosensory, premotor and parietal cortices. The linear discriminant analysis achieved 71% accuracy classifying SD and healthy individuals using connectivity measures in the left inferior parietal and sensorimotor cortices. When categorizing between different forms of SD, the combination of measures from the left inferior parietal, premotor and right sensorimotor cortices achieved 81% discriminatory power between familial and sporadic SD cases, whereas the combination of measures from the right superior parietal, primary somatosensory and premotor cortices led to 71% accuracy in the classification of adductor and abductor SD forms. Our findings present the first effort to identify and categorize isolated focal dystonia based on its brain functional connectivity profile, which may have a potential impact on the future development of biomarkers for this rare disorder. © 2016 EAN.

Cortical sensorimotor alterations classify clinical phenotype and putative genotype of spasmodic dysphonia

PubMed Central

Battistella, Giovanni; Fuertinger, Stefan; Fleysher, Lazar; Ozelius, Laurie J.; Simonyan, Kristina

2017-01-01

Background Spasmodic dysphonia (SD), or laryngeal dystonia, is a task-specific isolated focal dystonia of unknown causes and pathophysiology. Although functional and structural abnormalities have been described in this disorder, the influence of its different clinical phenotypes and genotypes remains scant, making it difficult to explain SD pathophysiology and to identify potential biomarkers. Methods We used a combination of independent component analysis and linear discriminant analysis of resting-state functional MRI data to investigate brain organization in different SD phenotypes (abductor vs. adductor type) and putative genotypes (familial vs. sporadic cases) and to characterize neural markers for genotype/phenotype categorization. Results We found abnormal functional connectivity within sensorimotor and frontoparietal networks in SD patients compared to healthy individuals as well as phenotype- and genotype-distinct alterations of these networks, involving primary somatosensory, premotor and parietal cortices. The linear discriminant analysis achieved 71% accuracy classifying SD and healthy individuals using connectivity measures in the left inferior parietal and sensorimotor cortex. When categorizing between different forms of SD, the combination of measures from left inferior parietal, premotor and right sensorimotor cortices achieved 81% discriminatory power between familial and sporadic SD cases, whereas the combination of measures from the right superior parietal, primary somatosensory and premotor cortices led to 71% accuracy in the classification of adductor and abductor SD forms. Conclusions Our findings present the first effort to identify and categorize isolated focal dystonia based on its brain functional connectivity profile, which may have a potential impact on the future development of biomarkers for this rare disorder. PMID:27346568

MORFOMETRYKA—A NEW WAY OF ESTABLISHING MORPHOLOGICAL CLASSIFICATION OF GALAXIES

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

Ferrari, F.; Carvalho, R. R. de; Trevisan, M., E-mail: fabricio@ferrari.pro.br

We present an extended morphometric system to automatically classify galaxies from astronomical images. The new system includes the original and modified versions of the CASGM coefficients (Concentration C{sub 1}, Asymmetry A{sub 3}, and Smoothness S{sub 3}), and the new parameters entropy, H, and spirality σ{sub ψ}. The new parameters A{sub 3}, S{sub 3}, and H are better to discriminate galaxy classes than A{sub 1}, S{sub 1}, and G, respectively. The new parameter σ{sub ψ} captures the amount of non-radial pattern on the image and is almost linearly dependent on T-type. Using a sample of spiral and elliptical galaxies from themore » Galaxy Zoo project as a training set, we employed the Linear Discriminant Analysis (LDA) technique to classify EFIGI (Baillard et al. 4458 galaxies), Nair and Abraham (14,123 galaxies), and SDSS Legacy (779,235 galaxies) samples. The cross-validation test shows that we can achieve an accuracy of more than 90% with our classification scheme. Therefore, we are able to define a plane in the morphometric parameter space that separates the elliptical and spiral classes with a mismatch between classes smaller than 10%. We use the distance to this plane as a morphometric index (M{sub i}) and we show that it follows the human based T-type index very closely. We calculate morphometric index M{sub i} for ∼780k galaxies from SDSS Legacy Survey–DR7. We discuss how M{sub i} correlates with stellar population parameters obtained using the spectra available from SDSS–DR7.« less

Common spatial pattern combined with kernel linear discriminate and generalized radial basis function for motor imagery-based brain computer interface applications

NASA Astrophysics Data System (ADS)

Hekmatmanesh, Amin; Jamaloo, Fatemeh; Wu, Huapeng; Handroos, Heikki; Kilpeläinen, Asko

2018-04-01

Brain Computer Interface (BCI) can be a challenge for developing of robotic, prosthesis and human-controlled systems. This work focuses on the implementation of a common spatial pattern (CSP) base algorithm to detect event related desynchronization patterns. Utilizing famous previous work in this area, features are extracted by filter bank with common spatial pattern (FBCSP) method, and then weighted by a sensitive learning vector quantization (SLVQ) algorithm. In the current work, application of the radial basis function (RBF) as a mapping kernel of linear discriminant analysis (KLDA) method on the weighted features, allows the transfer of data into a higher dimension for more discriminated data scattering by RBF kernel. Afterwards, support vector machine (SVM) with generalized radial basis function (GRBF) kernel is employed to improve the efficiency and robustness of the classification. Averagely, 89.60% accuracy and 74.19% robustness are achieved. BCI Competition III, Iva data set is used to evaluate the algorithm for detecting right hand and foot imagery movement patterns. Results show that combination of KLDA with SVM-GRBF classifier makes 8.9% and 14.19% improvements in accuracy and robustness, respectively. For all the subjects, it is concluded that mapping the CSP features into a higher dimension by RBF and utilization GRBF as a kernel of SVM, improve the accuracy and reliability of the proposed method.

Fast mental states decoding in mixed reality.

PubMed

De Massari, Daniele; Pacheco, Daniel; Malekshahi, Rahim; Betella, Alberto; Verschure, Paul F M J; Birbaumer, Niels; Caria, Andrea

2014-01-01

The combination of Brain-Computer Interface (BCI) technology, allowing online monitoring and decoding of brain activity, with virtual and mixed reality (MR) systems may help to shape and guide implicit and explicit learning using ecological scenarios. Real-time information of ongoing brain states acquired through BCI might be exploited for controlling data presentation in virtual environments. Brain states discrimination during mixed reality experience is thus critical for adapting specific data features to contingent brain activity. In this study we recorded electroencephalographic (EEG) data while participants experienced MR scenarios implemented through the eXperience Induction Machine (XIM). The XIM is a novel framework modeling the integration of a sensing system that evaluates and measures physiological and psychological states with a number of actuators and effectors that coherently reacts to the user's actions. We then assessed continuous EEG-based discrimination of spatial navigation, reading and calculation performed in MR, using linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Dynamic single trial classification showed high accuracy of LDA and SVM classifiers in detecting multiple brain states as well as in differentiating between high and low mental workload, using a 5 s time-window shifting every 200 ms. Our results indicate overall better performance of LDA with respect to SVM and suggest applicability of our approach in a BCI-controlled MR scenario. Ultimately, successful prediction of brain states might be used to drive adaptation of data representation in order to boost information processing in MR.

Fast mental states decoding in mixed reality

PubMed Central

De Massari, Daniele; Pacheco, Daniel; Malekshahi, Rahim; Betella, Alberto; Verschure, Paul F. M. J.; Birbaumer, Niels; Caria, Andrea

2014-01-01

The combination of Brain-Computer Interface (BCI) technology, allowing online monitoring and decoding of brain activity, with virtual and mixed reality (MR) systems may help to shape and guide implicit and explicit learning using ecological scenarios. Real-time information of ongoing brain states acquired through BCI might be exploited for controlling data presentation in virtual environments. Brain states discrimination during mixed reality experience is thus critical for adapting specific data features to contingent brain activity. In this study we recorded electroencephalographic (EEG) data while participants experienced MR scenarios implemented through the eXperience Induction Machine (XIM). The XIM is a novel framework modeling the integration of a sensing system that evaluates and measures physiological and psychological states with a number of actuators and effectors that coherently reacts to the user's actions. We then assessed continuous EEG-based discrimination of spatial navigation, reading and calculation performed in MR, using linear discriminant analysis (LDA) and support vector machine (SVM) classifiers. Dynamic single trial classification showed high accuracy of LDA and SVM classifiers in detecting multiple brain states as well as in differentiating between high and low mental workload, using a 5 s time-window shifting every 200 ms. Our results indicate overall better performance of LDA with respect to SVM and suggest applicability of our approach in a BCI-controlled MR scenario. Ultimately, successful prediction of brain states might be used to drive adaptation of data representation in order to boost information processing in MR. PMID:25505878

Detection of inter-patient left and right bundle branch block heartbeats in ECG using ensemble classifiers

PubMed Central

2014-01-01

Background Left bundle branch block (LBBB) and right bundle branch block (RBBB) not only mask electrocardiogram (ECG) changes that reflect diseases but also indicate important underlying pathology. The timely detection of LBBB and RBBB is critical in the treatment of cardiac diseases. Inter-patient heartbeat classification is based on independent training and testing sets to construct and evaluate a heartbeat classification system. Therefore, a heartbeat classification system with a high performance evaluation possesses a strong predictive capability for unknown data. The aim of this study was to propose a method for inter-patient classification of heartbeats to accurately detect LBBB and RBBB from the normal beat (NORM). Methods This study proposed a heartbeat classification method through a combination of three different types of classifiers: a minimum distance classifier constructed between NORM and LBBB; a weighted linear discriminant classifier between NORM and RBBB based on Bayesian decision making using posterior probabilities; and a linear support vector machine (SVM) between LBBB and RBBB. Each classifier was used with matching features to obtain better classification performance. The final types of the test heartbeats were determined using a majority voting strategy through the combination of class labels from the three classifiers. The optimal parameters for the classifiers were selected using cross-validation on the training set. The effects of different lead configurations on the classification results were assessed, and the performance of these three classifiers was compared for the detection of each pair of heartbeat types. Results The study results showed that a two-lead configuration exhibited better classification results compared with a single-lead configuration. The construction of a classifier with good performance between each pair of heartbeat types significantly improved the heartbeat classification performance. The results showed a sensitivity of 91.4% and a positive predictive value of 37.3% for LBBB and a sensitivity of 92.8% and a positive predictive value of 88.8% for RBBB. Conclusions A multi-classifier ensemble method was proposed based on inter-patient data and demonstrated a satisfactory classification performance. This approach has the potential for application in clinical practice to distinguish LBBB and RBBB from NORM of unknown patients. PMID:24903422

Detection of inter-patient left and right bundle branch block heartbeats in ECG using ensemble classifiers.

PubMed

Huang, Huifang; Liu, Jie; Zhu, Qiang; Wang, Ruiping; Hu, Guangshu

2014-06-05

Left bundle branch block (LBBB) and right bundle branch block (RBBB) not only mask electrocardiogram (ECG) changes that reflect diseases but also indicate important underlying pathology. The timely detection of LBBB and RBBB is critical in the treatment of cardiac diseases. Inter-patient heartbeat classification is based on independent training and testing sets to construct and evaluate a heartbeat classification system. Therefore, a heartbeat classification system with a high performance evaluation possesses a strong predictive capability for unknown data. The aim of this study was to propose a method for inter-patient classification of heartbeats to accurately detect LBBB and RBBB from the normal beat (NORM). This study proposed a heartbeat classification method through a combination of three different types of classifiers: a minimum distance classifier constructed between NORM and LBBB; a weighted linear discriminant classifier between NORM and RBBB based on Bayesian decision making using posterior probabilities; and a linear support vector machine (SVM) between LBBB and RBBB. Each classifier was used with matching features to obtain better classification performance. The final types of the test heartbeats were determined using a majority voting strategy through the combination of class labels from the three classifiers. The optimal parameters for the classifiers were selected using cross-validation on the training set. The effects of different lead configurations on the classification results were assessed, and the performance of these three classifiers was compared for the detection of each pair of heartbeat types. The study results showed that a two-lead configuration exhibited better classification results compared with a single-lead configuration. The construction of a classifier with good performance between each pair of heartbeat types significantly improved the heartbeat classification performance. The results showed a sensitivity of 91.4% and a positive predictive value of 37.3% for LBBB and a sensitivity of 92.8% and a positive predictive value of 88.8% for RBBB. A multi-classifier ensemble method was proposed based on inter-patient data and demonstrated a satisfactory classification performance. This approach has the potential for application in clinical practice to distinguish LBBB and RBBB from NORM of unknown patients.

Vineland-II adaptive behavior profile of children with attention-deficit/hyperactivity disorder or specific learning disorders.

PubMed

Balboni, Giulia; Incognito, Oriana; Belacchi, Carmen; Bonichini, Sabrina; Cubelli, Roberto

2017-02-01

The evaluation of adaptive behavior is informative in children with attention-deficit/hyperactivity disorder (ADHD) or specific learning disorders (SLD). However, the few investigations available have focused only on the gross level of domains of adaptive behavior. To investigate which item subsets of the Vineland-II can discriminate children with ADHD or SLD from peers with typical development. Student's t-tests, ROC analysis, logistic regression, and linear discriminant function analysis were used to compare 24 children with ADHD, 61 elementary students with SLD, and controls matched on age, sex, school level attended, and both parents' education level. Several item subsets that address not only ADHD core symptoms, but also understanding in social context and development of interpersonal relationships, allowed discrimination of children with ADHD from controls. The combination of four item subsets (Listening and attending, Expressing complex ideas, Social communication, and Following instructions) classified children with ADHD with both sensitivity and specificity of 87.5%. Only Reading skills, Writing skills, and Time and dates discriminated children with SLD from controls. Evaluation of Vineland-II scores at the level of item content categories is a useful procedure for an efficient clinical description. Copyright © 2016 Elsevier Ltd. All rights reserved.

Sparse network-based models for patient classification using fMRI

PubMed Central

Rosa, Maria J.; Portugal, Liana; Hahn, Tim; Fallgatter, Andreas J.; Garrido, Marta I.; Shawe-Taylor, John; Mourao-Miranda, Janaina

2015-01-01

Pattern recognition applied to whole-brain neuroimaging data, such as functional Magnetic Resonance Imaging (fMRI), has proved successful at discriminating psychiatric patients from healthy participants. However, predictive patterns obtained from whole-brain voxel-based features are difficult to interpret in terms of the underlying neurobiology. Many psychiatric disorders, such as depression and schizophrenia, are thought to be brain connectivity disorders. Therefore, pattern recognition based on network models might provide deeper insights and potentially more powerful predictions than whole-brain voxel-based approaches. Here, we build a novel sparse network-based discriminative modeling framework, based on Gaussian graphical models and L1-norm regularized linear Support Vector Machines (SVM). In addition, the proposed framework is optimized in terms of both predictive power and reproducibility/stability of the patterns. Our approach aims to provide better pattern interpretation than voxel-based whole-brain approaches by yielding stable brain connectivity patterns that underlie discriminative changes in brain function between the groups. We illustrate our technique by classifying patients with major depressive disorder (MDD) and healthy participants, in two (event- and block-related) fMRI datasets acquired while participants performed a gender discrimination and emotional task, respectively, during the visualization of emotional valent faces. PMID:25463459

Determination of patellofemoral pain sub-groups and development of a method for predicting treatment outcome using running gait kinematics.

PubMed

Watari, Ricky; Kobsar, Dylan; Phinyomark, Angkoon; Osis, Sean; Ferber, Reed

2016-10-01

Not all patients with patellofemoral pain exhibit successful outcomes following exercise therapy. Thus, the ability to identify patellofemoral pain subgroups related to treatment response is important for the development of optimal therapeutic strategies to improve rehabilitation outcomes. The purpose of this study was to use baseline running gait kinematic and clinical outcome variables to classify patellofemoral pain patients on treatment response retrospectively. Forty-one individuals with patellofemoral pain that underwent a 6-week exercise intervention program were sub-grouped as treatment Responders (n=28) and Non-responders (n=13) based on self-reported measures of pain and function. Baseline three-dimensional running kinematics, and self-reported measures underwent a linear discriminant analysis of the principal components of the variables to retrospectively classify participants based on treatment response. The significance of the discriminant function was verified with a Wilk's lambda test (α=0.05). The model selected 2 gait principal components and had a 78.1% classification accuracy. Overall, Non-responders exhibited greater ankle dorsiflexion, knee abduction and hip flexion during the swing phase and greater ankle inversion during the stance phase, compared to Responders. This is the first study to investigate an objective method to use baseline kinematic and self-report outcome variables to classify on patellofemoral pain treatment outcome. This study represents a significant first step towards a method to help clinicians make evidence-informed decisions regarding optimal treatment strategies for patients with patellofemoral pain. Copyright © 2016 Elsevier Ltd. All rights reserved.

Multispectral imaging burn wound tissue classification system: a comparison of test accuracies between several common machine learning algorithms

NASA Astrophysics Data System (ADS)

Squiers, John J.; Li, Weizhi; King, Darlene R.; Mo, Weirong; Zhang, Xu; Lu, Yang; Sellke, Eric W.; Fan, Wensheng; DiMaio, J. Michael; Thatcher, Jeffrey E.

2016-03-01

The clinical judgment of expert burn surgeons is currently the standard on which diagnostic and therapeutic decisionmaking regarding burn injuries is based. Multispectral imaging (MSI) has the potential to increase the accuracy of burn depth assessment and the intraoperative identification of viable wound bed during surgical debridement of burn injuries. A highly accurate classification model must be developed using machine-learning techniques in order to translate MSI data into clinically-relevant information. An animal burn model was developed to build an MSI training database and to study the burn tissue classification ability of several models trained via common machine-learning algorithms. The algorithms tested, from least to most complex, were: K-nearest neighbors (KNN), decision tree (DT), linear discriminant analysis (LDA), weighted linear discriminant analysis (W-LDA), quadratic discriminant analysis (QDA), ensemble linear discriminant analysis (EN-LDA), ensemble K-nearest neighbors (EN-KNN), and ensemble decision tree (EN-DT). After the ground-truth database of six tissue types (healthy skin, wound bed, blood, hyperemia, partial injury, full injury) was generated by histopathological analysis, we used 10-fold cross validation to compare the algorithms' performances based on their accuracies in classifying data against the ground truth, and each algorithm was tested 100 times. The mean test accuracy of the algorithms were KNN 68.3%, DT 61.5%, LDA 70.5%, W-LDA 68.1%, QDA 68.9%, EN-LDA 56.8%, EN-KNN 49.7%, and EN-DT 36.5%. LDA had the highest test accuracy, reflecting the bias-variance tradeoff over the range of complexities inherent to the algorithms tested. Several algorithms were able to match the current standard in burn tissue classification, the clinical judgment of expert burn surgeons. These results will guide further development of an MSI burn tissue classification system. Given that there are few surgeons and facilities specializing in burn care, this technology may improve the standard of burn care for patients without access to specialized facilities.

Pattern classification approach to characterizing solitary pulmonary nodules imaged on high-resolution computed tomography

NASA Astrophysics Data System (ADS)

McNitt-Gray, Michael F.; Hart, Eric M.; Goldin, Jonathan G.; Yao, Chih-Wei; Aberle, Denise R.

1996-04-01

The purpose of our study was to characterize solitary pulmonary nodules (SPN) as benign or malignant based on pattern classification techniques using size, shape, density and texture features extracted from HRCT images. HRCT images of patients with a SPN are acquired, routed through a PACS and displayed on a thoracic radiology workstation. Using the original data, the SPN is semiautomatically contoured using a nodule/background threshold. The contour is used to calculate size and several shape parameters, including compactness and bending energy. Pixels within the interior of the contour are used to calculate several features including: (1) nodule density-related features, such as representative Hounsfield number and moment of inertia, and (2) texture measures based on the spatial gray level dependence matrix and fractal dimension. The true diagnosis of the SPN is established by histology from biopsy or, in the case of some benign nodules, extended follow-up. Multi-dimensional analyses of the features are then performed to determine which features can discriminate between benign and malignant nodules. When a sufficient number of cases are obtained two pattern classifiers, a linear discriminator and a neural network, are trained and tested using a select subset of features. Preliminary data from nine (9) nodule cases have been obtained and several features extracted. While the representative CT number is a reasonably good indicator, it is an inconclusive predictor of SPN diagnosis when considered by itself. Separation between benign and malignant nodules improves when other features, such as the distribution of density as measured by moment of inertia, are included in the analysis. Software has been developed and preliminary results have been obtained which show that individual features may not be sufficient to discriminate between benign and malignant nodules. However, combinations of these features may be able to discriminate between these two classes. With additional cases and more features, we will be able to perform a feature selection procedure and ultimately to train and test pattern classifiers in this discrimination task.

A Biomimetic Sensor for the Classification of Honeys of Different Floral Origin and the Detection of Adulteration

PubMed Central

Zakaria, Ammar; Shakaff, Ali Yeon Md; Masnan, Maz Jamilah; Ahmad, Mohd Noor; Adom, Abdul Hamid; Jaafar, Mahmad Nor; Ghani, Supri A.; Abdullah, Abu Hassan; Aziz, Abdul Hallis Abdul; Kamarudin, Latifah Munirah; Subari, Norazian; Fikri, Nazifah Ahmad

2011-01-01

The major compounds in honey are carbohydrates such as monosaccharides and disaccharides. The same compounds are found in cane-sugar concentrates. Unfortunately when sugar concentrate is added to honey, laboratory assessments are found to be ineffective in detecting this adulteration. Unlike tracing heavy metals in honey, sugar adulterated honey is much trickier and harder to detect, and traditionally it has been very challenging to come up with a suitable method to prove the presence of adulterants in honey products. This paper proposes a combination of array sensing and multi-modality sensor fusion that can effectively discriminate the samples not only based on the compounds present in the sample but also mimic the way humans perceive flavours and aromas. Conversely, analytical instruments are based on chemical separations which may alter the properties of the volatiles or flavours of a particular honey. The present work is focused on classifying 18 samples of different honeys, sugar syrups and adulterated samples using data fusion of electronic nose (e-nose) and electronic tongue (e-tongue) measurements. Each group of samples was evaluated separately by the e-nose and e-tongue. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were able to separately discriminate monofloral honey from sugar syrup, and polyfloral honey from sugar and adulterated samples using the e-nose and e-tongue. The e-nose was observed to give better separation compared to e-tongue assessment, particularly when LDA was applied. However, when all samples were combined in one classification analysis, neither PCA nor LDA were able to discriminate between honeys of different floral origins, sugar syrup and adulterated samples. By applying a sensor fusion technique, the classification for the 18 different samples was improved. Significant improvement was observed using PCA, while LDA not only improved the discrimination but also gave better classification. An improvement in performance was also observed using a Probabilistic Neural Network classifier when the e-nose and e-tongue data were fused. PMID:22164046

A biomimetic sensor for the classification of honeys of different floral origin and the detection of adulteration.

PubMed

Zakaria, Ammar; Shakaff, Ali Yeon Md; Masnan, Maz Jamilah; Ahmad, Mohd Noor; Adom, Abdul Hamid; Jaafar, Mahmad Nor; Ghani, Supri A; Abdullah, Abu Hassan; Aziz, Abdul Hallis Abdul; Kamarudin, Latifah Munirah; Subari, Norazian; Fikri, Nazifah Ahmad

2011-01-01

The major compounds in honey are carbohydrates such as monosaccharides and disaccharides. The same compounds are found in cane-sugar concentrates. Unfortunately when sugar concentrate is added to honey, laboratory assessments are found to be ineffective in detecting this adulteration. Unlike tracing heavy metals in honey, sugar adulterated honey is much trickier and harder to detect, and traditionally it has been very challenging to come up with a suitable method to prove the presence of adulterants in honey products. This paper proposes a combination of array sensing and multi-modality sensor fusion that can effectively discriminate the samples not only based on the compounds present in the sample but also mimic the way humans perceive flavours and aromas. Conversely, analytical instruments are based on chemical separations which may alter the properties of the volatiles or flavours of a particular honey. The present work is focused on classifying 18 samples of different honeys, sugar syrups and adulterated samples using data fusion of electronic nose (e-nose) and electronic tongue (e-tongue) measurements. Each group of samples was evaluated separately by the e-nose and e-tongue. Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were able to separately discriminate monofloral honey from sugar syrup, and polyfloral honey from sugar and adulterated samples using the e-nose and e-tongue. The e-nose was observed to give better separation compared to e-tongue assessment, particularly when LDA was applied. However, when all samples were combined in one classification analysis, neither PCA nor LDA were able to discriminate between honeys of different floral origins, sugar syrup and adulterated samples. By applying a sensor fusion technique, the classification for the 18 different samples was improved. Significant improvement was observed using PCA, while LDA not only improved the discrimination but also gave better classification. An improvement in performance was also observed using a Probabilistic Neural Network classifier when the e-nose and e-tongue data were fused.

Default mode network connectivity distinguishes chemotherapy-treated breast cancer survivors from controls

PubMed Central

Kesler, Shelli R.; Wefel, Jeffrey S.; Hosseini, S. M. Hadi; Cheung, Maria; Watson, Christa L.; Hoeft, Fumiko

2013-01-01

Breast cancer (BC) chemotherapy is associated with cognitive changes including persistent deficits in some individuals. We tested the accuracy of default mode network (DMN) resting state functional connectivity patterns in discriminating chemotherapy treated (C+) from non–chemotherapy (C−) treated BC survivors and healthy controls (HC). We also examined the relationship between DMN connectivity patterns and cognitive function. Multivariate pattern analysis was used to classify 30 C+, 27 C−, and 24 HC, which showed significant accuracy for discriminating C+ from C− (91.23%, P < 0.0001) and C+ from HC (90.74%, P < 0.0001). The C− group did not differ significantly from HC (47.06%, P = 0.60). Lower subjective memory function was correlated (P < 0.002) with greater hyperplane distance (distance from the linear decision function that optimally separates the groups). Disrupted DMN connectivity may help explain long-term cognitive difficulties following BC chemotherapy. PMID:23798392

Robotic wheelchair commanded by SSVEP, motor imagery and word generation.

PubMed

Bastos, Teodiano F; Muller, Sandra M T; Benevides, Alessandro B; Sarcinelli-Filho, Mario

2011-01-01

This work presents a robotic wheelchair that can be commanded by a Brain Computer Interface (BCI) through Steady-State Visual Evoked Potential (SSVEP), Motor Imagery and Word Generation. When using SSVEP, a statistical test is used to extract the evoked response and a decision tree is used to discriminate the stimulus frequency, allowing volunteers to online operate the BCI, with hit rates varying from 60% to 100%, and guide a robotic wheelchair through an indoor environment. When using motor imagery and word generation, three mental task are used: imagination of left or right hand, and imagination of generation of words starting with the same random letter. Linear Discriminant Analysis is used to recognize the mental tasks, and the feature extraction uses Power Spectral Density. The choice of EEG channel and frequency uses the Kullback-Leibler symmetric divergence and a reclassification model is proposed to stabilize the classifier.

Improved Classification of Orthosiphon stamineus by Data Fusion of Electronic Nose and Tongue Sensors

PubMed Central

Zakaria, Ammar; Shakaff, Ali Yeon Md.; Adom, Abdul Hamid; Ahmad, Mohd Noor; Masnan, Maz Jamilah; Aziz, Abdul Hallis Abdul; Fikri, Nazifah Ahmad; Abdullah, Abu Hassan; Kamarudin, Latifah Munirah

2010-01-01

An improved classification of Orthosiphon stamineus using a data fusion technique is presented. Five different commercial sources along with freshly prepared samples were discriminated using an electronic nose (e-nose) and an electronic tongue (e-tongue). Samples from the different commercial brands were evaluated by the e-tongue and then followed by the e-nose. Applying Principal Component Analysis (PCA) separately on the respective e-tongue and e-nose data, only five distinct groups were projected. However, by employing a low level data fusion technique, six distinct groupings were achieved. Hence, this technique can enhance the ability of PCA to analyze the complex samples of Orthosiphon stamineus. Linear Discriminant Analysis (LDA) was then used to further validate and classify the samples. It was found that the LDA performance was also improved when the responses from the e-nose and e-tongue were fused together. PMID:22163381

Improved classification of Orthosiphon stamineus by data fusion of electronic nose and tongue sensors.

PubMed

Zakaria, Ammar; Shakaff, Ali Yeon Md; Adom, Abdul Hamid; Ahmad, Mohd Noor; Masnan, Maz Jamilah; Aziz, Abdul Hallis Abdul; Fikri, Nazifah Ahmad; Abdullah, Abu Hassan; Kamarudin, Latifah Munirah

2010-01-01

An improved classification of Orthosiphon stamineus using a data fusion technique is presented. Five different commercial sources along with freshly prepared samples were discriminated using an electronic nose (e-nose) and an electronic tongue (e-tongue). Samples from the different commercial brands were evaluated by the e-tongue and then followed by the e-nose. Applying Principal Component Analysis (PCA) separately on the respective e-tongue and e-nose data, only five distinct groups were projected. However, by employing a low level data fusion technique, six distinct groupings were achieved. Hence, this technique can enhance the ability of PCA to analyze the complex samples of Orthosiphon stamineus. Linear Discriminant Analysis (LDA) was then used to further validate and classify the samples. It was found that the LDA performance was also improved when the responses from the e-nose and e-tongue were fused together.

Classification of adulterated honeys by multivariate analysis.

PubMed

Amiry, Saber; Esmaiili, Mohsen; Alizadeh, Mohammad

2017-06-01

In this research, honey samples were adulterated with date syrup (DS) and invert sugar syrup (IS) at three concentrations (7%, 15% and 30%). 102 adulterated samples were prepared in six batches with 17 replications for each batch. For each sample, 32 parameters including color indices, rheological, physical, and chemical parameters were determined. To classify the samples, based on type and concentrations of adulterant, a multivariate analysis was applied using principal component analysis (PCA) followed by a linear discriminant analysis (LDA). Then, 21 principal components (PCs) were selected in five sets. Approximately two-thirds were identified correctly using color indices (62.75%) or rheological properties (67.65%). A power discrimination was obtained using physical properties (97.06%), and the best separations were achieved using two sets of chemical properties (set 1: lactone, diastase activity, sucrose - 100%) (set 2: free acidity, HMF, ash - 95%). Copyright © 2016 Elsevier Ltd. All rights reserved.

Rapid classification of enzymes in cleaning products by hydrolysis, mass spectrometry and linear discriminant analysis.

PubMed

Beneito-Cambra, Miriam; Herrero-Martínez, José Manuel; Simó-Alfonso, Ernesto F; Ramis-Ramos, Guillermo

2008-11-01

A method for the rapid classification of proteases, lipases, amylases and cellulases used as enhancers in cleaning products, based on precipitation with acetone, hydrolysis with HCl, dilution of the hydrolysates with ethanol, and direct infusion into the electrospray ion source of an ion-trap mass spectrometer, has been developed. The abundances of the ([M+H]+ ions of the amino acids, from the hydrolysates of both the enzyme industrial concentrates and the detergent bases spiked with them, were used to construct linear discriminant analysis models, capable of distinguishing between the enzyme classes. For this purpose, the variables were normalized as follows: (A) the ion abundance of each amino acid was divided by the sum of the ion abundances of all the amino acids in the corresponding mass spectrum; (B) the ratios of pairs of ion abundances were obtained by dividing the ion abundance of each amino acid by each one of the ion abundances of the other 17 amino acids in the corresponding mass spectrum. Using normalization procedure B, excellent class-resolution between proteases, lipases, amylases and cellulases was achieved. In all cases, enzymes in industrial concentrates and manufactured cleaning products were correctly classified with >98% assignment probability.

Multivariate analysis of the geochemistry and mineralogy of soils along two continental-scale transects in North America

USGS Publications Warehouse

Drew, L.J.; Grunsky, E.C.; Sutphin, D.M.; Woodruff, L.G.

2010-01-01

Soils collected in 2004 along two North American continental-scale transects were subjected to geochemical and mineralogical analyses. In previous interpretations of these analyses, data were expressed in weight percent and parts per million, and thus were subject to the effect of the constant-sum phenomenon. In a new approach to the data, this effect was removed by using centered log-ratio transformations to 'open' the mineralogical and geochemical arrays. Multivariate analyses, including principal component and linear discriminant analyses, of the centered log-ratio data reveal the effects of soil-forming processes, including soil parent material, weathering, and soil age, at the continental-scale of the data arrays that were not readily apparent in the more conventionally presented data. Linear discriminant analysis of the data arrays indicates that the majority of the soil samples collected along the transects can be more successfully classified with Level 1 ecological regional-scale classification by the soil geochemistry than soil mineralogy. A primary objective of this study is to discover and describe, in a parsimonious way, geochemical processes that are both independent and inter-dependent and manifested through compositional data including estimates of the elements and corresponding mineralogy. ?? 2010.

Target discrimination method for SAR images based on semisupervised co-training

NASA Astrophysics Data System (ADS)

Wang, Yan; Du, Lan; Dai, Hui

2018-01-01

Synthetic aperture radar (SAR) target discrimination is usually performed in a supervised manner. However, supervised methods for SAR target discrimination may need lots of labeled training samples, whose acquirement is costly, time consuming, and sometimes impossible. This paper proposes an SAR target discrimination method based on semisupervised co-training, which utilizes a limited number of labeled samples and an abundant number of unlabeled samples. First, Lincoln features, widely used in SAR target discrimination, are extracted from the training samples and partitioned into two sets according to their physical meanings. Second, two support vector machine classifiers are iteratively co-trained with the extracted two feature sets based on the co-training algorithm. Finally, the trained classifiers are exploited to classify the test data. The experimental results on real SAR images data not only validate the effectiveness of the proposed method compared with the traditional supervised methods, but also demonstrate the superiority of co-training over self-training, which only uses one feature set.

BagMOOV: A novel ensemble for heart disease prediction bootstrap aggregation with multi-objective optimized voting.

PubMed

Bashir, Saba; Qamar, Usman; Khan, Farhan Hassan

2015-06-01

Conventional clinical decision support systems are based on individual classifiers or simple combination of these classifiers which tend to show moderate performance. This research paper presents a novel classifier ensemble framework based on enhanced bagging approach with multi-objective weighted voting scheme for prediction and analysis of heart disease. The proposed model overcomes the limitations of conventional performance by utilizing an ensemble of five heterogeneous classifiers: Naïve Bayes, linear regression, quadratic discriminant analysis, instance based learner and support vector machines. Five different datasets are used for experimentation, evaluation and validation. The datasets are obtained from publicly available data repositories. Effectiveness of the proposed ensemble is investigated by comparison of results with several classifiers. Prediction results of the proposed ensemble model are assessed by ten fold cross validation and ANOVA statistics. The experimental evaluation shows that the proposed framework deals with all type of attributes and achieved high diagnosis accuracy of 84.16 %, 93.29 % sensitivity, 96.70 % specificity, and 82.15 % f-measure. The f-ratio higher than f-critical and p value less than 0.05 for 95 % confidence interval indicate that the results are extremely statistically significant for most of the datasets.

Application of texture analysis method for mammogram density classification

NASA Astrophysics Data System (ADS)

Nithya, R.; Santhi, B.

2017-07-01

Mammographic density is considered a major risk factor for developing breast cancer. This paper proposes an automated approach to classify breast tissue types in digital mammogram. The main objective of the proposed Computer-Aided Diagnosis (CAD) system is to investigate various feature extraction methods and classifiers to improve the diagnostic accuracy in mammogram density classification. Texture analysis methods are used to extract the features from the mammogram. Texture features are extracted by using histogram, Gray Level Co-Occurrence Matrix (GLCM), Gray Level Run Length Matrix (GLRLM), Gray Level Difference Matrix (GLDM), Local Binary Pattern (LBP), Entropy, Discrete Wavelet Transform (DWT), Wavelet Packet Transform (WPT), Gabor transform and trace transform. These extracted features are selected using Analysis of Variance (ANOVA). The features selected by ANOVA are fed into the classifiers to characterize the mammogram into two-class (fatty/dense) and three-class (fatty/glandular/dense) breast density classification. This work has been carried out by using the mini-Mammographic Image Analysis Society (MIAS) database. Five classifiers are employed namely, Artificial Neural Network (ANN), Linear Discriminant Analysis (LDA), Naive Bayes (NB), K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). Experimental results show that ANN provides better performance than LDA, NB, KNN and SVM classifiers. The proposed methodology has achieved 97.5% accuracy for three-class and 99.37% for two-class density classification.

Age and gender estimation using Region-SIFT and multi-layered SVM

NASA Astrophysics Data System (ADS)

Kim, Hyunduk; Lee, Sang-Heon; Sohn, Myoung-Kyu; Hwang, Byunghun

2018-04-01

In this paper, we propose an age and gender estimation framework using the region-SIFT feature and multi-layered SVM classifier. The suggested framework entails three processes. The first step is landmark based face alignment. The second step is the feature extraction step. In this step, we introduce the region-SIFT feature extraction method based on facial landmarks. First, we define sub-regions of the face. We then extract SIFT features from each sub-region. In order to reduce the dimensions of features we employ a Principal Component Analysis (PCA) and a Linear Discriminant Analysis (LDA). Finally, we classify age and gender using a multi-layered Support Vector Machines (SVM) for efficient classification. Rather than performing gender estimation and age estimation independently, the use of the multi-layered SVM can improve the classification rate by constructing a classifier that estimate the age according to gender. Moreover, we collect a dataset of face images, called by DGIST_C, from the internet. A performance evaluation of proposed method was performed with the FERET database, CACD database, and DGIST_C database. The experimental results demonstrate that the proposed approach classifies age and performs gender estimation very efficiently and accurately.

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

NASA Astrophysics Data System (ADS)

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

2012-03-01

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

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.

High Stimulus-Related Information in Barrel Cortex Inhibitory Interneurons

PubMed Central

Reyes-Puerta, Vicente; Kim, Suam; Sun, Jyh-Jang; Imbrosci, Barbara; Kilb, Werner; Luhmann, Heiko J.

2015-01-01

The manner in which populations of inhibitory (INH) and excitatory (EXC) neocortical neurons collectively encode stimulus-related information is a fundamental, yet still unresolved question. Here we address this question by simultaneously recording with large-scale multi-electrode arrays (of up to 128 channels) the activity of cell ensembles (of up to 74 neurons) distributed along all layers of 3–4 neighboring cortical columns in the anesthetized adult rat somatosensory barrel cortex in vivo. Using two different whisker stimulus modalities (location and frequency) we show that individual INH neurons – classified as such according to their distinct extracellular spike waveforms – discriminate better between restricted sets of stimuli (≤6 stimulus classes) than EXC neurons in granular and infra-granular layers. We also demonstrate that ensembles of INH cells jointly provide as much information about such stimuli as comparable ensembles containing the ~20% most informative EXC neurons, however presenting less information redundancy – a result which was consistent when applying both theoretical information measurements and linear discriminant analysis classifiers. These results suggest that a consortium of INH neurons dominates the information conveyed to the neocortical network, thereby efficiently processing incoming sensory activity. This conclusion extends our view on the role of the inhibitory system to orchestrate cortical activity. PMID:26098109

Analysis of physiological signals for recognition of boredom, pain, and surprise emotions.

PubMed

Jang, Eun-Hye; Park, Byoung-Jun; Park, Mi-Sook; Kim, Sang-Hyeob; Sohn, Jin-Hun

2015-06-18

The aim of the study was to examine the differences of boredom, pain, and surprise. In addition to that, it was conducted to propose approaches for emotion recognition based on physiological signals. Three emotions, boredom, pain, and surprise, are induced through the presentation of emotional stimuli and electrocardiography (ECG), electrodermal activity (EDA), skin temperature (SKT), and photoplethysmography (PPG) as physiological signals are measured to collect a dataset from 217 participants when experiencing the emotions. Twenty-seven physiological features are extracted from the signals to classify the three emotions. The discriminant function analysis (DFA) as a statistical method, and five machine learning algorithms (linear discriminant analysis (LDA), classification and regression trees (CART), self-organizing map (SOM), Naïve Bayes algorithm, and support vector machine (SVM)) are used for classifying the emotions. The result shows that the difference of physiological responses among emotions is significant in heart rate (HR), skin conductance level (SCL), skin conductance response (SCR), mean skin temperature (meanSKT), blood volume pulse (BVP), and pulse transit time (PTT), and the highest recognition accuracy of 84.7% is obtained by using DFA. This study demonstrates the differences of boredom, pain, and surprise and the best emotion recognizer for the classification of the three emotions by using physiological signals.

Computing symmetrical strength of N-grams: a two pass filtering approach in automatic classification of text documents.

PubMed

Agnihotri, Deepak; Verma, Kesari; Tripathi, Priyanka

2016-01-01

The contiguous sequences of the terms (N-grams) in the documents are symmetrically distributed among different classes. The symmetrical distribution of the N-Grams raises uncertainty in the belongings of the N-Grams towards the class. In this paper, we focused on the selection of most discriminating N-Grams by reducing the effects of symmetrical distribution. In this context, a new text feature selection method named as the symmetrical strength of the N-Grams (SSNG) is proposed using a two pass filtering based feature selection (TPF) approach. Initially, in the first pass of the TPF, the SSNG method chooses various informative N-Grams from the entire extracted N-Grams of the corpus. Subsequently, in the second pass the well-known Chi Square (χ(2)) method is being used to select few most informative N-Grams. Further, to classify the documents the two standard classifiers Multinomial Naive Bayes and Linear Support Vector Machine have been applied on the ten standard text data sets. In most of the datasets, the experimental results state the performance and success rate of SSNG method using TPF approach is superior to the state-of-the-art methods viz. Mutual Information, Information Gain, Odds Ratio, Discriminating Feature Selection and χ(2).

High wavenumber Raman spectroscopy in the characterization of urinary metabolites of normal subjects, oral premalignant and malignant patients

NASA Astrophysics Data System (ADS)

Brindha, Elumalai; Rajasekaran, Ramu; Aruna, Prakasarao; Koteeswaran, Dornadula; Ganesan, Singaravelu

2017-01-01

Urine has emerged as one of the diagnostically potential bio fluids, as it has many metabolites. As the concentration and the physiochemical properties of the urinary metabolites may vary under pathological transformation, Raman spectroscopic characterization of urine has been exploited as a significant tool in identifying several diseased conditions, including cancers. In the present study, an attempt was made to study the high wavenumber (HWVN) Raman spectroscopic characterization of urine samples of normal subjects, oral premalignant and malignant patients. It is concluded that the urinary metabolites flavoproteins, tryptophan and phenylalanine are responsible for the observed spectral variations between the normal and abnormal groups. Principal component analysis-based linear discriminant analysis was carried out to verify the diagnostic potentiality of the present technique. The discriminant analysis performed across normal and oral premalignant subjects classifies 95.6% of the original and 94.9% of the cross-validated grouped cases correctly. In the second analysis performed across normal and oral malignant groups, the accuracy of the original and cross-validated grouped cases was 96.4% and 92.1% respectively. Similarly, the third analysis performed across three groups, normal, oral premalignant and malignant groups, classifies 93.3% and 91.2% of the original and cross-validated grouped cases correctly.

Assignment of Colletotrichum coccodes isolates into vegetative compatibility groups using infrared spectroscopy: a step towards practical application.

PubMed

Salman, A; Shufan, E; Lapidot, I; Tsror, L; Moreh, R; Mordechai, S; Huleihel, M

2015-05-07

Colletotrichum coccodes (C. coccodes) is a pathogenic fungus that causes anthracnose on tomatoes and black dot disease in potatoes. It is considered as a seed tuber and soil-borne pathogen that is difficult to control. C. coccodes isolates are classified into Vegetative Compatibility Groups (VCGs). Early classification of isolates into VCGs is of great importance for a better understanding of the epidemiology of the disease and improving its control. Moreover, the differentiation among these isolates and the assignment of newly-discovered isolates enable control of the disease at its early stages. Distinguishing between isolates using microbiological or genetic methods is time-consuming and not readily available. Our results show that it is possible to assign the isolates into their VCGs and to classify them at the isolate level with a high success rate using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA).

Objective Measurement of Erythema in Psoriasis using Digital Color Photography with Color Calibration

PubMed Central

Raina, Abhay; Hennessy, Ricky; Rains, Michael; Allred, James; Hirshburg, Jason M; Diven, Dayna; Markey, Mia K.

2016-01-01

Background Traditional metrics for evaluating the severity of psoriasis are subjective, which complicates efforts to measure effective treatments in clinical trials. Methods We collected images of psoriasis plaques and calibrated the coloration of the images according to an included color card. Features were extracted from the images and used to train a linear discriminant analysis classifier with cross-validation to automatically classify the degree of erythema. The results were tested against numerical scores obtained by a panel of dermatologists using a standard rating system. Results Quantitative measures of erythema based on the digital color images showed good agreement with subjective assessment of erythema severity (κ = 0.4203). The color calibration process improved the agreement from κ = 0.2364 to κ = 0.4203. Conclusions We propose a method for the objective measurement of the psoriasis severity parameter of erythema and show that the calibration process improved the results. PMID:26517973

Classifying Degraded Modern Polymeric Museum Artefacts by Their Smell.

PubMed

Curran, Katherine; Underhill, Mark; Grau-Bové, Josep; Fearn, Tom; Gibson, Lorraine T; Strlič, Matija

2018-02-05

The use of VOC analysis to diagnose degradation in modern polymeric museum artefacts is reported. Volatile organic compound (VOC) analysis is a successful method for diagnosing medical conditions but to date has found little application in museums. Modern polymers are increasingly found in museum collections but pose serious conservation difficulties owing to unstable and widely varying formulations. Solid-phase microextraction gas chromatography/mass spectrometry and linear discriminant analysis were used to classify samples according to the length of time they had been artificially degraded. Accuracies in classification of 50-83 % were obtained after validation with separate test sets. The method was applied to three artefacts from collections at Tate to detect evidence of degradation. This approach could be used for any material in heritage collections and more widely in the field of polymer degradation. © 2018 The Authors. Published by Wiley-VCH Verlag GmbH & Co. KGaA.

An approach to predict Sudden Cardiac Death (SCD) using time domain and bispectrum features from HRV signal.

PubMed

Houshyarifar, Vahid; Chehel Amirani, Mehdi

2016-08-12

In this paper we present a method to predict Sudden Cardiac Arrest (SCA) with higher order spectral (HOS) and linear (Time) features extracted from heart rate variability (HRV) signal. Predicting the occurrence of SCA is important in order to avoid the probability of Sudden Cardiac Death (SCD). This work is a challenge to predict five minutes before SCA onset. The method consists of four steps: pre-processing, feature extraction, feature reduction, and classification. In the first step, the QRS complexes are detected from the electrocardiogram (ECG) signal and then the HRV signal is extracted. In second step, bispectrum features of HRV signal and time-domain features are obtained. Six features are extracted from bispectrum and two features from time-domain. In the next step, these features are reduced to one feature by the linear discriminant analysis (LDA) technique. Finally, KNN and support vector machine-based classifiers are used to classify the HRV signals. We used two database named, MIT/BIH Sudden Cardiac Death (SCD) Database and Physiobank Normal Sinus Rhythm (NSR). In this work we achieved prediction of SCD occurrence for six minutes before the SCA with the accuracy over 91%.

Classification of molecular structure images by using ANN, RF, LBP, HOG, and size reduction methods for early stomach cancer detection

NASA Astrophysics Data System (ADS)

Aytaç Korkmaz, Sevcan; Binol, Hamidullah

2018-03-01

Patients who die from stomach cancer are still present. Early diagnosis is crucial in reducing the mortality rate of cancer patients. Therefore, computer aided methods have been developed for early detection in this article. Stomach cancer images were obtained from Fırat University Medical Faculty Pathology Department. The Local Binary Patterns (LBP) and Histogram of Oriented Gradients (HOG) features of these images are calculated. At the same time, Sammon mapping, Stochastic Neighbor Embedding (SNE), Isomap, Classical multidimensional scaling (MDS), Local Linear Embedding (LLE), Linear Discriminant Analysis (LDA), t-Distributed Stochastic Neighbor Embedding (t-SNE), and Laplacian Eigenmaps methods are used for dimensional the reduction of the features. The high dimension of these features has been reduced to lower dimensions using dimensional reduction methods. Artificial neural networks (ANN) and Random Forest (RF) classifiers were used to classify stomach cancer images with these new lower feature sizes. New medical systems have developed to measure the effects of these dimensions by obtaining features in different dimensional with dimensional reduction methods. When all the methods developed are compared, it has been found that the best accuracy results are obtained with LBP_MDS_ANN and LBP_LLE_ANN methods.

Full-motion video analysis for improved gender classification

NASA Astrophysics Data System (ADS)

Flora, Jeffrey B.; Lochtefeld, Darrell F.; Iftekharuddin, Khan M.

2014-06-01

The ability of computer systems to perform gender classification using the dynamic motion of the human subject has important applications in medicine, human factors, and human-computer interface systems. Previous works in motion analysis have used data from sensors (including gyroscopes, accelerometers, and force plates), radar signatures, and video. However, full-motion video, motion capture, range data provides a higher resolution time and spatial dataset for the analysis of dynamic motion. Works using motion capture data have been limited by small datasets in a controlled environment. In this paper, we explore machine learning techniques to a new dataset that has a larger number of subjects. Additionally, these subjects move unrestricted through a capture volume, representing a more realistic, less controlled environment. We conclude that existing linear classification methods are insufficient for the gender classification for larger dataset captured in relatively uncontrolled environment. A method based on a nonlinear support vector machine classifier is proposed to obtain gender classification for the larger dataset. In experimental testing with a dataset consisting of 98 trials (49 subjects, 2 trials per subject), classification rates using leave-one-out cross-validation are improved from 73% using linear discriminant analysis to 88% using the nonlinear support vector machine classifier.

A Machine Learning and Cross-Validation Approach for the Discrimination of Vegetation Physiognomic Types Using Satellite Based Multispectral and Multitemporal Data.

PubMed

Sharma, Ram C; Hara, Keitarou; Hirayama, Hidetake

2017-01-01

This paper presents the performance and evaluation of a number of machine learning classifiers for the discrimination between the vegetation physiognomic classes using the satellite based time-series of the surface reflectance data. Discrimination of six vegetation physiognomic classes, Evergreen Coniferous Forest, Evergreen Broadleaf Forest, Deciduous Coniferous Forest, Deciduous Broadleaf Forest, Shrubs, and Herbs, was dealt with in the research. Rich-feature data were prepared from time-series of the satellite data for the discrimination and cross-validation of the vegetation physiognomic types using machine learning approach. A set of machine learning experiments comprised of a number of supervised classifiers with different model parameters was conducted to assess how the discrimination of vegetation physiognomic classes varies with classifiers, input features, and ground truth data size. The performance of each experiment was evaluated by using the 10-fold cross-validation method. Experiment using the Random Forests classifier provided highest overall accuracy (0.81) and kappa coefficient (0.78). However, accuracy metrics did not vary much with experiments. Accuracy metrics were found to be very sensitive to input features and size of ground truth data. The results obtained in the research are expected to be useful for improving the vegetation physiognomic mapping in Japan.

Automatic Classification of Artifactual ICA-Components for Artifact Removal in EEG Signals

PubMed Central

2011-01-01

Background Artifacts contained in EEG recordings hamper both, the visual interpretation by experts as well as the algorithmic processing and analysis (e.g. for Brain-Computer Interfaces (BCI) or for Mental State Monitoring). While hand-optimized selection of source components derived from Independent Component Analysis (ICA) to clean EEG data is widespread, the field could greatly profit from automated solutions based on Machine Learning methods. Existing ICA-based removal strategies depend on explicit recordings of an individual's artifacts or have not been shown to reliably identify muscle artifacts. Methods We propose an automatic method for the classification of general artifactual source components. They are estimated by TDSEP, an ICA method that takes temporal correlations into account. The linear classifier is based on an optimized feature subset determined by a Linear Programming Machine (LPM). The subset is composed of features from the frequency-, the spatial- and temporal domain. A subject independent classifier was trained on 640 TDSEP components (reaction time (RT) study, n = 12) that were hand labeled by experts as artifactual or brain sources and tested on 1080 new components of RT data of the same study. Generalization was tested on new data from two studies (auditory Event Related Potential (ERP) paradigm, n = 18; motor imagery BCI paradigm, n = 80) that used data with different channel setups and from new subjects. Results Based on six features only, the optimized linear classifier performed on level with the inter-expert disagreement (<10% Mean Squared Error (MSE)) on the RT data. On data of the auditory ERP study, the same pre-calculated classifier generalized well and achieved 15% MSE. On data of the motor imagery paradigm, we demonstrate that the discriminant information used for BCI is preserved when removing up to 60% of the most artifactual source components. Conclusions We propose a universal and efficient classifier of ICA components for the subject independent removal of artifacts from EEG data. Based on linear methods, it is applicable for different electrode placements and supports the introspection of results. Trained on expert ratings of large data sets, it is not restricted to the detection of eye- and muscle artifacts. Its performance and generalization ability is demonstrated on data of different EEG studies. PMID:21810266

Geometry-based ensembles: toward a structural characterization of the classification boundary.

PubMed

Pujol, Oriol; Masip, David

2009-06-01

This paper introduces a novel binary discriminative learning technique based on the approximation of the nonlinear decision boundary by a piecewise linear smooth additive model. The decision border is geometrically defined by means of the characterizing boundary points-points that belong to the optimal boundary under a certain notion of robustness. Based on these points, a set of locally robust linear classifiers is defined and assembled by means of a Tikhonov regularized optimization procedure in an additive model to create a final lambda-smooth decision rule. As a result, a very simple and robust classifier with a strong geometrical meaning and nonlinear behavior is obtained. The simplicity of the method allows its extension to cope with some of today's machine learning challenges, such as online learning, large-scale learning or parallelization, with linear computational complexity. We validate our approach on the UCI database, comparing with several state-of-the-art classification techniques. Finally, we apply our technique in online and large-scale scenarios and in six real-life computer vision and pattern recognition problems: gender recognition based on face images, intravascular ultrasound tissue classification, speed traffic sign detection, Chagas' disease myocardial damage severity detection, old musical scores clef classification, and action recognition using 3D accelerometer data from a wearable device. The results are promising and this paper opens a line of research that deserves further attention.

Temporal lobe epilepsy: quantitative MR volumetry in detection of hippocampal atrophy.

PubMed

Farid, Nikdokht; Girard, Holly M; Kemmotsu, Nobuko; Smith, Michael E; Magda, Sebastian W; Lim, Wei Y; Lee, Roland R; McDonald, Carrie R

2012-08-01

To determine the ability of fully automated volumetric magnetic resonance (MR) imaging to depict hippocampal atrophy (HA) and to help correctly lateralize the seizure focus in patients with temporal lobe epilepsy (TLE). This study was conducted with institutional review board approval and in compliance with HIPAA regulations. Volumetric MR imaging data were analyzed for 34 patients with TLE and 116 control subjects. Structural volumes were calculated by using U.S. Food and Drug Administration-cleared software for automated quantitative MR imaging analysis (NeuroQuant). Results of quantitative MR imaging were compared with visual detection of atrophy, and, when available, with histologic specimens. Receiver operating characteristic analyses were performed to determine the optimal sensitivity and specificity of quantitative MR imaging for detecting HA and asymmetry. A linear classifier with cross validation was used to estimate the ability of quantitative MR imaging to help lateralize the seizure focus. Quantitative MR imaging-derived hippocampal asymmetries discriminated patients with TLE from control subjects with high sensitivity (86.7%-89.5%) and specificity (92.2%-94.1%). When a linear classifier was used to discriminate left versus right TLE, hippocampal asymmetry achieved 94% classification accuracy. Volumetric asymmetries of other subcortical structures did not improve classification. Compared with invasive video electroencephalographic recordings, lateralization accuracy was 88% with quantitative MR imaging and 85% with visual inspection of volumetric MR imaging studies but only 76% with visual inspection of clinical MR imaging studies. Quantitative MR imaging can depict the presence and laterality of HA in TLE with accuracy rates that may exceed those achieved with visual inspection of clinical MR imaging studies. Thus, quantitative MR imaging may enhance standard visual analysis, providing a useful and viable means for translating volumetric analysis into clinical practice.

Discrimination of raw and processed Dipsacus asperoides by near infrared spectroscopy combined with least squares-support vector machine and random forests

NASA Astrophysics Data System (ADS)

Xin, Ni; Gu, Xiao-Feng; Wu, Hao; Hu, Yu-Zhu; Yang, Zhong-Lin

2012-04-01

Most herbal medicines could be processed to fulfill the different requirements of therapy. The purpose of this study was to discriminate between raw and processed Dipsacus asperoides, a common traditional Chinese medicine, based on their near infrared (NIR) spectra. Least squares-support vector machine (LS-SVM) and random forests (RF) were employed for full-spectrum classification. Three types of kernels, including linear kernel, polynomial kernel and radial basis function kernel (RBF), were checked for optimization of LS-SVM model. For comparison, a linear discriminant analysis (LDA) model was performed for classification, and the successive projections algorithm (SPA) was executed prior to building an LDA model to choose an appropriate subset of wavelengths. The three methods were applied to a dataset containing 40 raw herbs and 40 corresponding processed herbs. We ran 50 runs of 10-fold cross validation to evaluate the model's efficiency. The performance of the LS-SVM with RBF kernel (RBF LS-SVM) was better than the other two kernels. The RF, RBF LS-SVM and SPA-LDA successfully classified all test samples. The mean error rates for the 50 runs of 10-fold cross validation were 1.35% for RBF LS-SVM, 2.87% for RF, and 2.50% for SPA-LDA. The best classification results were obtained by using LS-SVM with RBF kernel, while RF was fast in the training and making predictions.

Color model and method for video fire flame and smoke detection using Fisher linear discriminant

NASA Astrophysics Data System (ADS)

Wei, Yuan; Jie, Li; Jun, Fang; Yongming, Zhang

2013-02-01

Video fire detection is playing an increasingly important role in our life. But recent research is often based on a traditional RGB color model used to analyze the flame, which may be not the optimal color space for fire recognition. It is worse when we research smoke simply using gray images instead of color ones. We clarify the importance of color information for fire detection. We present a fire discriminant color (FDC) model for flame or smoke recognition based on color images. The FDC models aim to unify fire color image representation and fire recognition task into one framework. With the definition of between-class scatter matrices and within-class scatter matrices of Fisher linear discriminant, the proposed models seek to obtain one color-space-transform matrix and a discriminate projection basis vector by maximizing the ratio of these two scatter matrices. First, an iterative basic algorithm is designed to get one-component color space transformed from RGB. Then, a general algorithm is extended to generate three-component color space for further improvement. Moreover, we propose a method for video fire detection based on the models using the kNN classifier. To evaluate the recognition performance, we create a database including flame, smoke, and nonfire images for training and testing. The test experiments show that the proposed model achieves a flame verification rate receiver operating characteristic (ROC I) of 97.5% at a false alarm rate (FAR) of 1.06% and a smoke verification rate (ROC II) of 91.5% at a FAR of 1.2%, and lots of fire video experiments demonstrate that our method reaches a high accuracy for fire recognition.

Unsupervised Wishart Classfication of Wetlands in Newfoundland, Canada Using Polsar Data Based on Fisher Linear Discriminant Analysis

NASA Astrophysics Data System (ADS)

Mohammadimanesh, F.; Salehi, B.; Mahdianpari, M.; Homayouni, S.

2016-06-01

Polarimetric Synthetic Aperture Radar (PolSAR) imagery is a complex multi-dimensional dataset, which is an important source of information for various natural resources and environmental classification and monitoring applications. PolSAR imagery produces valuable information by observing scattering mechanisms from different natural and man-made objects. Land cover mapping using PolSAR data classification is one of the most important applications of SAR remote sensing earth observations, which have gained increasing attention in the recent years. However, one of the most challenging aspects of classification is selecting features with maximum discrimination capability. To address this challenge, a statistical approach based on the Fisher Linear Discriminant Analysis (FLDA) and the incorporation of physical interpretation of PolSAR data into classification is proposed in this paper. After pre-processing of PolSAR data, including the speckle reduction, the H/α classification is used in order to classify the basic scattering mechanisms. Then, a new method for feature weighting, based on the fusion of FLDA and physical interpretation, is implemented. This method proves to increase the classification accuracy as well as increasing between-class discrimination in the final Wishart classification. The proposed method was applied to a full polarimetric C-band RADARSAT-2 data set from Avalon area, Newfoundland and Labrador, Canada. This imagery has been acquired in June 2015, and covers various types of wetlands including bogs, fens, marshes and shallow water. The results were compared with the standard Wishart classification, and an improvement of about 20% was achieved in the overall accuracy. This method provides an opportunity for operational wetland classification in northern latitude with high accuracy using only SAR polarimetric data.

Pulse shape discrimination and classification methods for continuous depth of interaction encoding PET detectors.

PubMed

Roncali, Emilie; Phipps, Jennifer E; Marcu, Laura; Cherry, Simon R

2012-10-21

In previous work we demonstrated the potential of positron emission tomography (PET) detectors with depth-of-interaction (DOI) encoding capability based on phosphor-coated crystals. A DOI resolution of 8 mm full-width at half-maximum was obtained for 20 mm long scintillator crystals using a delayed charge integration linear regression method (DCI-LR). Phosphor-coated crystals modify the pulse shape to allow continuous DOI information determination, but the relationship between pulse shape and DOI is complex. We are therefore interested in developing a sensitive and robust method to estimate the DOI. Here, linear discriminant analysis (LDA) was implemented to classify the events based on information extracted from the pulse shape. Pulses were acquired with 2×2×20 mm(3) phosphor-coated crystals at five irradiation depths and characterized by their DCI values or Laguerre coefficients. These coefficients were obtained by expanding the pulses on a Laguerre basis set and constituted a unique signature for each pulse. The DOI of individual events was predicted using LDA based on Laguerre coefficients (Laguerre-LDA) or DCI values (DCI-LDA) as discriminant features. Predicted DOIs were compared to true irradiation depths. Laguerre-LDA showed higher sensitivity and accuracy than DCI-LDA and DCI-LR and was also more robust to predict the DOI of pulses with higher statistical noise due to low light levels (interaction depths further from the photodetector face). This indicates that Laguerre-LDA may be more suitable to DOI estimation in smaller crystals where lower collected light levels are expected. This novel approach is promising for calculating DOI using pulse shape discrimination in single-ended readout depth-encoding PET detectors.

Pulse Shape Discrimination and Classification Methods for Continuous Depth of Interaction Encoding PET Detectors

PubMed Central

Roncali, Emilie; Phipps, Jennifer E.; Marcu, Laura; Cherry, Simon R.

2012-01-01

In previous work we demonstrated the potential of positron emission tomography (PET) detectors with depth-of-interaction (DOI) encoding capability based on phosphor-coated crystals. A DOI resolution of 8 mm full-width at half-maximum was obtained for 20 mm long scintillator crystals using a delayed charge integration linear regression method (DCI-LR). Phosphor-coated crystals modify the pulse shape to allow continuous DOI information determination, but the relationship between pulse shape and DOI is complex. We are therefore interested in developing a sensitive and robust method to estimate the DOI. Here, linear discriminant analysis (LDA) was implemented to classify the events based on information extracted from the pulse shape. Pulses were acquired with 2 × 2 × 20 mm3 phosphor-coated crystals at five irradiation depths and characterized by their DCI values or Laguerre coefficients. These coefficients were obtained by expanding the pulses on a Laguerre basis set and constituted a unique signature for each pulse. The DOI of individual events was predicted using LDA based on Laguerre coefficients (Laguerre-LDA) or DCI values (DCI-LDA) as discriminant features. Predicted DOIs were compared to true irradiation depths. Laguerre-LDA showed higher sensitivity and accuracy than DCI-LDA and DCI-LR and was also more robust to predict the DOI of pulses with higher statistical noise due to low light levels (interaction depths further from the photodetector face). This indicates that Laguerre-LDA may be more suitable to DOI estimation in smaller crystals where lower collected light levels are expected. This novel approach is promising for calculating DOI using pulse shape discrimination in single-ended readout depth-encoding PET detectors. PMID:23010690

sEMG-based joint force control for an upper-limb power-assist exoskeleton robot.

PubMed

Li, Zhijun; Wang, Baocheng; Sun, Fuchun; Yang, Chenguang; Xie, Qing; Zhang, Weidong

2014-05-01

This paper investigates two surface electromyogram (sEMG)-based control strategies developed for a power-assist exoskeleton arm. Different from most of the existing position control approaches, this paper develops force control methods to make the exoskeleton robot behave like humans in order to provide better assistance. The exoskeleton robot is directly attached to a user's body and activated by the sEMG signals of the user's muscles, which reflect the user's motion intention. In the first proposed control method, the forces of agonist and antagonist muscles pair are estimated, and their difference is used to produce the torque of the corresponding joints. In the second method, linear discriminant analysis-based classifiers are introduced as the indicator of the motion type of the joints. Then, the classifier's outputs together with the estimated force of corresponding active muscle determine the torque control signals. Different from the conventional approaches, one classifier is assigned to each joint, which decreases the training time and largely simplifies the recognition process. Finally, the extensive experiments are conducted to illustrate the effectiveness of the proposed approaches.

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

NASA Astrophysics Data System (ADS)

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

2010-01-01

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

Pattern Recognition Approaches for Breast Cancer DCE-MRI Classification: A Systematic Review.

PubMed

Fusco, Roberta; Sansone, Mario; Filice, Salvatore; Carone, Guglielmo; Amato, Daniela Maria; Sansone, Carlo; Petrillo, Antonella

2016-01-01

We performed a systematic review of several pattern analysis approaches for classifying breast lesions using dynamic, morphological, and textural features in dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). Several machine learning approaches, namely artificial neural networks (ANN), support vector machines (SVM), linear discriminant analysis (LDA), tree-based classifiers (TC), and Bayesian classifiers (BC), and features used for classification are described. The findings of a systematic review of 26 studies are presented. The sensitivity and specificity are respectively 91 and 83 % for ANN, 85 and 82 % for SVM, 96 and 85 % for LDA, 92 and 87 % for TC, and 82 and 85 % for BC. The sensitivity and specificity are respectively 82 and 74 % for dynamic features, 93 and 60 % for morphological features, 88 and 81 % for textural features, 95 and 86 % for a combination of dynamic and morphological features, and 88 and 84 % for a combination of dynamic, morphological, and other features. LDA and TC have the best performance. A combination of dynamic and morphological features gives the best performance.

A mechatronics platform to study prosthetic hand control using EMG signals.

PubMed

Geethanjali, P

2016-09-01

In this paper, a low-cost mechatronics platform for the design and development of robotic hands as well as a surface electromyogram (EMG) pattern recognition system is proposed. This paper also explores various EMG classification techniques using a low-cost electronics system in prosthetic hand applications. The proposed platform involves the development of a four channel EMG signal acquisition system; pattern recognition of acquired EMG signals; and development of a digital controller for a robotic hand. Four-channel surface EMG signals, acquired from ten healthy subjects for six different movements of the hand, were used to analyse pattern recognition in prosthetic hand control. Various time domain features were extracted and grouped into five ensembles to compare the influence of features in feature-selective classifiers (SLR) with widely considered non-feature-selective classifiers, such as neural networks (NN), linear discriminant analysis (LDA) and support vector machines (SVM) applied with different kernels. The results divulged that the average classification accuracy of the SVM, with a linear kernel function, outperforms other classifiers with feature ensembles, Hudgin's feature set and auto regression (AR) coefficients. However, the slight improvement in classification accuracy of SVM incurs more processing time and memory space in the low-level controller. The Kruskal-Wallis (KW) test also shows that there is no significant difference in the classification performance of SLR with Hudgin's feature set to that of SVM with Hudgin's features along with AR coefficients. In addition, the KW test shows that SLR was found to be better in respect to computation time and memory space, which is vital in a low-level controller. Similar to SVM, with a linear kernel function, other non-feature selective LDA and NN classifiers also show a slight improvement in performance using twice the features but with the drawback of increased memory space requirement and time. This prototype facilitated the study of various issues of pattern recognition and identified an efficient classifier, along with a feature ensemble, in the implementation of EMG controlled prosthetic hands in a laboratory setting at low-cost. This platform may help to motivate and facilitate prosthetic hand research in developing countries.

Toward improving fine needle aspiration cytology by applying Raman microspectroscopy

NASA Astrophysics Data System (ADS)

Becker-Putsche, Melanie; Bocklitz, Thomas; Clement, Joachim; Rösch, Petra; Popp, Jürgen

2013-04-01

Medical diagnosis of biopsies performed by fine needle aspiration has to be very reliable. Therefore, pathologists/cytologists need additional biochemical information on single cancer cells for an accurate diagnosis. Accordingly, we applied three different classification models for discriminating various features of six breast cancer cell lines by analyzing Raman microspectroscopic data. The statistical evaluations are implemented by linear discriminant analysis (LDA) and support vector machines (SVM). For the first model, a total of 61,580 Raman spectra from 110 single cells are discriminated at the cell-line level with an accuracy of 99.52% using an SVM. The LDA classification based on Raman data achieved an accuracy of 94.04% by discriminating cell lines by their origin (solid tumor versus pleural effusion). In the third model, Raman cell spectra are classified by their cancer subtypes. LDA results show an accuracy of 97.45% and specificities of 97.78%, 99.11%, and 98.97% for the subtypes basal-like, HER2+/ER-, and luminal, respectively. These subtypes are confirmed by gene expression patterns, which are important prognostic features in diagnosis. This work shows the applicability of Raman spectroscopy and statistical data handling in analyzing cancer-relevant biochemical information for advanced medical diagnosis on the single-cell level.

Robust Visual Tracking via Online Discriminative and Low-Rank Dictionary Learning.

PubMed

Zhou, Tao; Liu, Fanghui; Bhaskar, Harish; Yang, Jie

2017-09-12

In this paper, we propose a novel and robust tracking framework based on online discriminative and low-rank dictionary learning. The primary aim of this paper is to obtain compact and low-rank dictionaries that can provide good discriminative representations of both target and background. We accomplish this by exploiting the recovery ability of low-rank matrices. That is if we assume that the data from the same class are linearly correlated, then the corresponding basis vectors learned from the training set of each class shall render the dictionary to become approximately low-rank. The proposed dictionary learning technique incorporates a reconstruction error that improves the reliability of classification. Also, a multiconstraint objective function is designed to enable active learning of a discriminative and robust dictionary. Further, an optimal solution is obtained by iteratively computing the dictionary, coefficients, and by simultaneously learning the classifier parameters. Finally, a simple yet effective likelihood function is implemented to estimate the optimal state of the target during tracking. Moreover, to make the dictionary adaptive to the variations of the target and background during tracking, an online update criterion is employed while learning the new dictionary. Experimental results on a publicly available benchmark dataset have demonstrated that the proposed tracking algorithm performs better than other state-of-the-art trackers.

Detecting single-trial EEG evoked potential using a wavelet domain linear mixed model: application to error potentials classification.

PubMed

Spinnato, J; Roubaud, M-C; Burle, B; Torrésani, B

2015-06-01

The main goal of this work is to develop a model for multisensor signals, such as magnetoencephalography or electroencephalography (EEG) signals that account for inter-trial variability, suitable for corresponding binary classification problems. An important constraint is that the model be simple enough to handle small size and unbalanced datasets, as often encountered in BCI-type experiments. The method involves the linear mixed effects statistical model, wavelet transform, and spatial filtering, and aims at the characterization of localized discriminant features in multisensor signals. After discrete wavelet transform and spatial filtering, a projection onto the relevant wavelet and spatial channels subspaces is used for dimension reduction. The projected signals are then decomposed as the sum of a signal of interest (i.e., discriminant) and background noise, using a very simple Gaussian linear mixed model. Thanks to the simplicity of the model, the corresponding parameter estimation problem is simplified. Robust estimates of class-covariance matrices are obtained from small sample sizes and an effective Bayes plug-in classifier is derived. The approach is applied to the detection of error potentials in multichannel EEG data in a very unbalanced situation (detection of rare events). Classification results prove the relevance of the proposed approach in such a context. The combination of the linear mixed model, wavelet transform and spatial filtering for EEG classification is, to the best of our knowledge, an original approach, which is proven to be effective. This paper improves upon earlier results on similar problems, and the three main ingredients all play an important role.

GBM heterogeneity characterization by radiomic analysis of phenotype anatomical planes

NASA Astrophysics Data System (ADS)

Chaddad, Ahmad; Desrosiers, Christian; Toews, Matthew

2016-03-01

Glioblastoma multiforme (GBM) is the most common malignant primary tumor of the central nervous system, characterized among other traits by rapid metastatis. Three tissue phenotypes closely associated with GBMs, namely, necrosis (N), contrast enhancement (CE), and edema/invasion (E), exhibit characteristic patterns of texture heterogeneity in magnetic resonance images (MRI). In this study, we propose a novel model to characterize GBM tissue phenotypes using gray level co-occurrence matrices (GLCM) in three anatomical planes. The GLCM encodes local image patches in terms of informative, orientation-invariant texture descriptors, which are used here to sub-classify GBM tissue phenotypes. Experiments demonstrate the model on MRI data of 41 GBM patients, obtained from the cancer genome atlas (TCGA). Intensity-based automatic image registration is applied to align corresponding pairs of fixed T1˗weighted (T1˗WI) post-contrast and fluid attenuated inversion recovery (FLAIR) images. GBM tissue regions are then segmented using the 3D Slicer tool. Texture features are computed from 12 quantifier functions operating on GLCM descriptors, that are generated from MRI intensities within segmented GBM tissue regions. Various classifier models are used to evaluate the effectiveness of texture features for discriminating between GBM phenotypes. Results based on T1-WI scans showed a phenotype classification accuracy of over 88.14%, a sensitivity of 85.37% and a specificity of 96.1%, using the linear discriminant analysis (LDA) classifier. This model has the potential to provide important characteristics of tumors, which can be used for the sub-classification of GBM phenotypes.

Molecular activity prediction by means of supervised subspace projection based ensembles of classifiers.

PubMed

Cerruela García, G; García-Pedrajas, N; Luque Ruiz, I; Gómez-Nieto, M Á

2018-03-01

This paper proposes a method for molecular activity prediction in QSAR studies using ensembles of classifiers constructed by means of two supervised subspace projection methods, namely nonparametric discriminant analysis (NDA) and hybrid discriminant analysis (HDA). We studied the performance of the proposed ensembles compared to classical ensemble methods using four molecular datasets and eight different models for the representation of the molecular structure. Using several measures and statistical tests for classifier comparison, we observe that our proposal improves the classification results with respect to classical ensemble methods. Therefore, we show that ensembles constructed using supervised subspace projections offer an effective way of creating classifiers in cheminformatics.

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.

Discrimination among spawning aggregations of lake herring from Lake Superior using whole-body morphometric characters

USGS Publications Warehouse

Hoff, Michael H.

2004-01-01

The lake herring (Coregonus artedi) was one of the most commercially and ecologically valuable Lake Superior fishes, but declined in the second half of the 20th century as the result of overharvest of putatively discrete stocks. No tools were previously available that described lake herring stock structure and accurately classified lake herring to their spawning stocks. The accuracy of discriminating among spawning aggregations was evaluated using whole-body morphometrics based on a truss network. Lake herring were collected from 11 spawning aggregations in Lake Superior and two inland Wisconsin lakes to evaluate morphometrics as a stock discrimination tool. Discriminant function analysis correctly classified 53% of all fish from all spawning aggregations, and fish from all but one aggregation were classified at greater rates than were possible by chance. Discriminant analysis also correctly classified 66% of fish to nearest neighbor groups, which were groups that accounted for the possibility of mixing among the aggregations. Stepwise discriminant analysis showed that posterior body length and depth measurements were among the best discriminators of spawning aggregations. These findings support other evidence that discrete stocks of lake herring exist in Lake Superior, and fishery managers should consider all but one of the spawning aggregations as discrete stocks. Abundance, annual harvest, total annual mortality rate, and exploitation data should be collected from each stock, and surplus production of each stock should be estimated. Prudent management of stock surplus production and exploitation rates will aid in restoration of stocks and will prevent a repeat of the stock collapses that occurred in the middle of the 20th century, when the species was nearly extirpated from the lake.

Event Recognition for Contactless Activity Monitoring Using Phase-Modulated Continuous Wave Radar.

PubMed

Forouzanfar, Mohamad; Mabrouk, Mohamed; Rajan, Sreeraman; Bolic, Miodrag; Dajani, Hilmi R; Groza, Voicu Z

2017-02-01

The use of remote sensing technologies such as radar is gaining popularity as a technique for contactless detection of physiological signals and analysis of human motion. This paper presents a methodology for classifying different events in a collection of phase modulated continuous wave radar returns. The primary application of interest is to monitor inmates where the presence of human vital signs amidst different, interferences needs to be identified. A comprehensive set of features is derived through time and frequency domain analyses of the radar returns. The Bhattacharyya distance is used to preselect the features with highest class separability as the possible candidate features for use in the classification process. The uncorrelated linear discriminant analysis is performed to decorrelate, denoise, and reduce the dimension of the candidate feature set. Linear and quadratic Bayesian classifiers are designed to distinguish breathing, different human motions, and nonhuman motions. The performance of these classifiers is evaluated on a pilot dataset of radar returns that contained different events including breathing, stopped breathing, simple human motions, and movement of fan and water. Our proposed pattern classification system achieved accuracies of up to 93% in stationary subject detection, 90% in stop-breathing detection, and 86% in interference detection. Our proposed radar pattern recognition system was able to accurately distinguish the predefined events amidst interferences. Besides inmate monitoring and suicide attempt detection, this paper can be extended to other radar applications such as home-based monitoring of elderly people, apnea detection, and home occupancy detection.

Detecting natural occlusion boundaries using local cues

PubMed Central

DiMattina, Christopher; Fox, Sean A.; Lewicki, Michael S.

2012-01-01

Occlusion boundaries and junctions provide important cues for inferring three-dimensional scene organization from two-dimensional images. Although several investigators in machine vision have developed algorithms for detecting occlusions and other edges in natural images, relatively few psychophysics or neurophysiology studies have investigated what features are used by the visual system to detect natural occlusions. In this study, we addressed this question using a psychophysical experiment where subjects discriminated image patches containing occlusions from patches containing surfaces. Image patches were drawn from a novel occlusion database containing labeled occlusion boundaries and textured surfaces in a variety of natural scenes. Consistent with related previous work, we found that relatively large image patches were needed to attain reliable performance, suggesting that human subjects integrate complex information over a large spatial region to detect natural occlusions. By defining machine observers using a set of previously studied features measured from natural occlusions and surfaces, we demonstrate that simple features defined at the spatial scale of the image patch are insufficient to account for human performance in the task. To define machine observers using a more biologically plausible multiscale feature set, we trained standard linear and neural network classifiers on the rectified outputs of a Gabor filter bank applied to the image patches. We found that simple linear classifiers could not match human performance, while a neural network classifier combining filter information across location and spatial scale compared well. These results demonstrate the importance of combining a variety of cues defined at multiple spatial scales for detecting natural occlusions. PMID:23255731

Deformable segmentation of 3D MR prostate images via distributed discriminative dictionary and ensemble learning

PubMed Central

Guo, Yanrong; Gao, Yaozong; Shao, Yeqin; Price, True; Oto, Aytekin; Shen, Dinggang

2014-01-01

Purpose: Automatic prostate segmentation from MR images is an important task in various clinical applications such as prostate cancer staging and MR-guided radiotherapy planning. However, the large appearance and shape variations of the prostate in MR images make the segmentation problem difficult to solve. Traditional Active Shape/Appearance Model (ASM/AAM) has limited accuracy on this problem, since its basic assumption, i.e., both shape and appearance of the targeted organ follow Gaussian distributions, is invalid in prostate MR images. To this end, the authors propose a sparse dictionary learning method to model the image appearance in a nonparametric fashion and further integrate the appearance model into a deformable segmentation framework for prostate MR segmentation. Methods: To drive the deformable model for prostate segmentation, the authors propose nonparametric appearance and shape models. The nonparametric appearance model is based on a novel dictionary learning method, namely distributed discriminative dictionary (DDD) learning, which is able to capture fine distinctions in image appearance. To increase the differential power of traditional dictionary-based classification methods, the authors' DDD learning approach takes three strategies. First, two dictionaries for prostate and nonprostate tissues are built, respectively, using the discriminative features obtained from minimum redundancy maximum relevance feature selection. Second, linear discriminant analysis is employed as a linear classifier to boost the optimal separation between prostate and nonprostate tissues, based on the representation residuals from sparse representation. Third, to enhance the robustness of the authors' classification method, multiple local dictionaries are learned for local regions along the prostate boundary (each with small appearance variations), instead of learning one global classifier for the entire prostate. These discriminative dictionaries are located on different patches of the prostate surface and trained to adaptively capture the appearance in different prostate zones, thus achieving better local tissue differentiation. For each local region, multiple classifiers are trained based on the randomly selected samples and finally assembled by a specific fusion method. In addition to this nonparametric appearance model, a prostate shape model is learned from the shape statistics using a novel approach, sparse shape composition, which can model nonGaussian distributions of shape variation and regularize the 3D mesh deformation by constraining it within the observed shape subspace. Results: The proposed method has been evaluated on two datasets consisting of T2-weighted MR prostate images. For the first (internal) dataset, the classification effectiveness of the authors' improved dictionary learning has been validated by comparing it with three other variants of traditional dictionary learning methods. The experimental results show that the authors' method yields a Dice Ratio of 89.1% compared to the manual segmentation, which is more accurate than the three state-of-the-art MR prostate segmentation methods under comparison. For the second dataset, the MICCAI 2012 challenge dataset, the authors' proposed method yields a Dice Ratio of 87.4%, which also achieves better segmentation accuracy than other methods under comparison. Conclusions: A new magnetic resonance image prostate segmentation method is proposed based on the combination of deformable model and dictionary learning methods, which achieves more accurate segmentation performance on prostate T2 MR images. PMID:24989402

Deformable segmentation of 3D MR prostate images via distributed discriminative dictionary and ensemble learning.

PubMed

Guo, Yanrong; Gao, Yaozong; Shao, Yeqin; Price, True; Oto, Aytekin; Shen, Dinggang

2014-07-01

Automatic prostate segmentation from MR images is an important task in various clinical applications such as prostate cancer staging and MR-guided radiotherapy planning. However, the large appearance and shape variations of the prostate in MR images make the segmentation problem difficult to solve. Traditional Active Shape/Appearance Model (ASM/AAM) has limited accuracy on this problem, since its basic assumption, i.e., both shape and appearance of the targeted organ follow Gaussian distributions, is invalid in prostate MR images. To this end, the authors propose a sparse dictionary learning method to model the image appearance in a nonparametric fashion and further integrate the appearance model into a deformable segmentation framework for prostate MR segmentation. To drive the deformable model for prostate segmentation, the authors propose nonparametric appearance and shape models. The nonparametric appearance model is based on a novel dictionary learning method, namely distributed discriminative dictionary (DDD) learning, which is able to capture fine distinctions in image appearance. To increase the differential power of traditional dictionary-based classification methods, the authors' DDD learning approach takes three strategies. First, two dictionaries for prostate and nonprostate tissues are built, respectively, using the discriminative features obtained from minimum redundancy maximum relevance feature selection. Second, linear discriminant analysis is employed as a linear classifier to boost the optimal separation between prostate and nonprostate tissues, based on the representation residuals from sparse representation. Third, to enhance the robustness of the authors' classification method, multiple local dictionaries are learned for local regions along the prostate boundary (each with small appearance variations), instead of learning one global classifier for the entire prostate. These discriminative dictionaries are located on different patches of the prostate surface and trained to adaptively capture the appearance in different prostate zones, thus achieving better local tissue differentiation. For each local region, multiple classifiers are trained based on the randomly selected samples and finally assembled by a specific fusion method. In addition to this nonparametric appearance model, a prostate shape model is learned from the shape statistics using a novel approach, sparse shape composition, which can model nonGaussian distributions of shape variation and regularize the 3D mesh deformation by constraining it within the observed shape subspace. The proposed method has been evaluated on two datasets consisting of T2-weighted MR prostate images. For the first (internal) dataset, the classification effectiveness of the authors' improved dictionary learning has been validated by comparing it with three other variants of traditional dictionary learning methods. The experimental results show that the authors' method yields a Dice Ratio of 89.1% compared to the manual segmentation, which is more accurate than the three state-of-the-art MR prostate segmentation methods under comparison. For the second dataset, the MICCAI 2012 challenge dataset, the authors' proposed method yields a Dice Ratio of 87.4%, which also achieves better segmentation accuracy than other methods under comparison. A new magnetic resonance image prostate segmentation method is proposed based on the combination of deformable model and dictionary learning methods, which achieves more accurate segmentation performance on prostate T2 MR images.

Perception of olive oils sensory defects using a potentiometric taste device.

PubMed

Veloso, Ana C A; Silva, Lucas M; Rodrigues, Nuno; Rebello, Ligia P G; Dias, Luís G; Pereira, José A; Peres, António M

2018-01-01

The capability of perceiving olive oils sensory defects and intensities plays a key role on olive oils quality grade classification since olive oils can only be classified as extra-virgin if no defect can be perceived by a human trained sensory panel. Otherwise, olive oils may be classified as virgin or lampante depending on the median intensity of the defect predominantly perceived and on the physicochemical levels. However, sensory analysis is time-consuming and requires an official sensory panel, which can only evaluate a low number of samples per day. In this work, the potential use of an electronic tongue as a taste sensor device to identify the defect predominantly perceived in olive oils was evaluated. The potentiometric profiles recorded showed that intra- and inter-day signal drifts could be neglected (i.e., relative standard deviations lower than 25%), being not statistically significant the effect of the analysis day on the overall recorded E-tongue sensor fingerprints (P-value = 0.5715, for multivariate analysis of variance using Pillai's trace test), which significantly differ according to the olive oils' sensory defect (P-value = 0.0084, for multivariate analysis of variance using Pillai's trace test). Thus, a linear discriminant model based on 19 potentiometric signal sensors, selected by the simulated annealing algorithm, could be established to correctly predict the olive oil main sensory defect (fusty, rancid, wet-wood or winey-vinegary) with average sensitivity of 75 ± 3% and specificity of 73 ± 4% (repeated K-fold cross-validation variant: 4 folds×10 repeats). Similarly, a linear discriminant model, based on 24 selected sensors, correctly classified 92 ± 3% of the olive oils as virgin or lampante, being an average specificity of 93 ± 3% achieved. The overall satisfactory predictive performances strengthen the feasibility of the developed taste sensor device as a complementary methodology for olive oils' defects analysis and subsequent quality grade classification. Furthermore, the capability of identifying the type of sensory defect of an olive oil may allow establishing helpful insights regarding bad practices of olives or olive oils production, harvesting, transport and storage. Copyright © 2017 Elsevier B.V. All rights reserved.

Development of a noninvasive system for monitoring dairy cattle sleep.

PubMed

Klefot, J M; Murphy, J L; Donohue, K D; O'Hara, B F; Lhamon, M E; Bewley, J M

2016-10-01

Limited research has been conducted to assess sleep in production livestock primarily because of limitations with monitoring capabilities. Consequently, biological understanding of production circumstances and facility options that affect sleep is limited. The objective of this study was to assess if data collected from a proof-of-concept, noninvasive 3-axis accelerometer device are correlated with sleep and wake-like behaviors in dairy cattle. Four Holstein dairy cows housed at the University of Kentucky Coldstream Dairy in September 2013 were visually observed for 2 consecutive 24-h periods. The accelerometer device was attached to a harness positioned on the right side of each cow's neck. Times of classified behaviors of wake (standing, head up, alert, eyes open) or sleep-like behaviors (lying, still, head resting on ground, eyes closed) were recorded continuously by 2 observers who each watched 2 cows at a time. The radial signal was extracted from 3 different axes of the accelerometer to obtain a motion signal independent of direction of movement. Radial signal features were examined for maximizing the performance of detecting sleep-like behaviors using a Fisher's linear discriminant analysis classifier. The study included 652min of high-activity wake behaviors and 107min of sleep-like behavior among 4 cows. Results from a bootstrapping analysis showed an agreement between human observation and the linear discriminant analysis classifier, with an accuracy of 93.7±0.7% for wake behavior and 92.2±0.8% for sleep-like behavior (±95% confidence interval).This prototype shows promise in measuring sleep-like behaviors. Improvements to both hardware and software should allow more accurate determinations of subtle head movements and respiratory movements that will further improve the assessment of these sleep-like behaviors, including estimates of deep, light, and rapid eye movement sleep. These future studies will require simultaneous electroencephalography and electromyography measures and perhaps additional measures of arousal thresholds to validate this system for measuring true sleep. Copyright © 2016 American Dairy Science Association. Published by Elsevier Inc. All rights reserved.

Discrimination of stroke-related mild cognitive impairment and vascular dementia using EEG signal analysis.

PubMed

Al-Qazzaz, Noor Kamal; Ali, Sawal Hamid Bin Mohd; Ahmad, Siti Anom; Islam, Mohd Shabiul; Escudero, Javier

2018-01-01

Stroke survivors are more prone to developing cognitive impairment and dementia. Dementia detection is a challenge for supporting personalized healthcare. This study analyzes the electroencephalogram (EEG) background activity of 5 vascular dementia (VaD) patients, 15 stroke-related patients with mild cognitive impairment (MCI), and 15 control healthy subjects during a working memory (WM) task. The objective of this study is twofold. First, it aims to enhance the discrimination of VaD, stroke-related MCI patients, and control subjects using fuzzy neighborhood preserving analysis with QR-decomposition (FNPAQR); second, it aims to extract and investigate the spectral features that characterize the post-stroke dementia patients compared to the control subjects. Nineteen channels were recorded and analyzed using the independent component analysis and wavelet analysis (ICA-WT) denoising technique. Using ANOVA, linear spectral power including relative powers (RP) and power ratio were calculated to test whether the EEG dominant frequencies were slowed down in VaD and stroke-related MCI patients. Non-linear features including permutation entropy (PerEn) and fractal dimension (FD) were used to test the degree of irregularity and complexity, which was significantly lower in patients with VaD and stroke-related MCI than that in control subjects (ANOVA; p ˂ 0.05). This study is the first to use fuzzy neighborhood preserving analysis with QR-decomposition (FNPAQR) dimensionality reduction technique with EEG background activity of dementia patients. The impairment of post-stroke patients was detected using support vector machine (SVM) and k-nearest neighbors (kNN) classifiers. A comparative study has been performed to check the effectiveness of using FNPAQR dimensionality reduction technique with the SVM and kNN classifiers. FNPAQR with SVM and kNN obtained 91.48 and 89.63% accuracy, respectively, whereas without using the FNPAQR exhibited 70 and 67.78% accuracy for SVM and kNN, respectively, in classifying VaD, stroke-related MCI, and control patients, respectively. Therefore, EEG could be a reliable index for inspecting concise markers that are sensitive to VaD and stroke-related MCI patients compared to control healthy subjects.

Predicting hepatotoxicity using ToxCast in vitro bioactivity and ...

EPA Pesticide Factsheets

Background: The U.S. EPA ToxCastTM program is screening thousands of environmental chemicals for bioactivity using hundreds of high-throughput in vitro assays to build predictive models of toxicity. We represented chemicals based on bioactivity and chemical structure descriptors then used supervised machine learning to predict their hepatotoxic effects.Results: A set of 677 chemicals were represented by 711 in vitro bioactivity descriptors (from ToxCast assays), 4,376 chemical structure descriptors (from QikProp, OpenBabel, PADEL, and PubChem), and three hepatotoxicity categories (from animal studies). Hepatotoxicants were defined by rat liver histopathology observed after chronic chemical testing and grouped into hypertrophy (161), injury (101) and proliferative lesions (99). Classifiers were built using six machine learning algorithms: linear discriminant analysis (LDA), Naïve Bayes (NB), support vector classification (SVM), classification and regression trees (CART), k-nearest neighbors (KNN) and an ensemble of classifiers (ENSMB). Classifiers of hepatotoxicity were built using chemical structure, ToxCast bioactivity, and a hybrid representation. Predictive performance was evaluated using 10-fold cross-validation testing and in-loop, filter-based, feature subset selection. Hybrid classifiers had the best balanced accuracy for predicting hypertrophy (0.78±0.08), injury (0.73±0.10) and proliferative lesions (0.72±0.09). Though chemical and bioactivity class

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

PubMed Central

Hatch, Kenneth D.

2012-01-01

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

Evaluation of Oil-Palm Fungal Disease Infestation with Canopy Hyperspectral Reflectance Data

PubMed Central

Lelong, Camille C. D.; Roger, Jean-Michel; Brégand, Simon; Dubertret, Fabrice; Lanore, Mathieu; Sitorus, Nurul A.; Raharjo, Doni A.; Caliman, Jean-Pierre

2010-01-01

Fungal disease detection in perennial crops is a major issue in estate management and production. However, nowadays such diagnostics are long and difficult when only made from visual symptom observation, and very expensive and damaging when based on root or stem tissue chemical analysis. As an alternative, we propose in this study to evaluate the potential of hyperspectral reflectance data to help detecting the disease efficiently without destruction of tissues. This study focuses on the calibration of a statistical model of discrimination between several stages of Ganoderma attack on oil palm trees, based on field hyperspectral measurements at tree scale. Field protocol and measurements are first described. Then, combinations of pre-processing, partial least square regression and linear discriminant analysis are tested on about hundred samples to prove the efficiency of canopy reflectance in providing information about the plant sanitary status. A robust algorithm is thus derived, allowing classifying oil-palm in a 4-level typology, based on disease severity from healthy to critically sick stages, with a global performance close to 94%. Moreover, this model discriminates sick from healthy trees with a confidence level of almost 98%. Applications and further improvements of this experiment are finally discussed. PMID:22315565

Botanical discrimination of Greek unifloral honeys with physico-chemical and chemometric analyses.

PubMed

Karabagias, Ioannis K; Badeka, Anastasia V; Kontakos, Stavros; Karabournioti, Sofia; Kontominas, Michael G

2014-12-15

The aim of the present study was to investigate the possibility of characterisation and classification of Greek unifloral honeys (pine, thyme, fir and orange blossom) according to botanical origin using volatile compounds, conventional physico-chemical parameters and chemometric analyses (MANOVA and Linear Discriminant Analysis). For this purpose, 119 honey samples were collected during the harvesting period 2011 from 14 different regions in Greece known to produce unifloral honey of good quality. Physico-chemical analysis included the identification and semi quantification of fifty five volatile compounds performed by Headspace Solid Phase Microextraction coupled to gas chromatography/mass spectroscopy and the determination of conventional quality parameters such as pH, free, lactonic, total acidity, electrical conductivity, moisture, ash, lactonic/free acidity ratio and colour parameters L, a, b. Results showed that using 40 diverse variables (30 volatile compounds of different classes and 10 physico-chemical parameters) the honey samples were satisfactorily classified according to botanical origin using volatile compounds (84.0% correct prediction), physicochemical parameters (97.5% correct prediction), and the combination of both (95.8% correct prediction) indicating that multi element analysis comprises a powerful tool for honey discrimination purposes. Copyright © 2014 Elsevier Ltd. All rights reserved.

Detection of high-risk atherosclerotic lesions by time-resolved fluorescence spectroscopy based on the Laguerre deconvolution technique

NASA Astrophysics Data System (ADS)

Jo, J. A.; Fang, Q.; Papaioannou, T.; Qiao, J. H.; Fishbein, M. C.; Beseth, B.; Dorafshar, A. H.; Reil, T.; Baker, D.; Freischlag, J.; Marcu, L.

2006-02-01

This study introduces new methods of time-resolved laser-induced fluorescence spectroscopy (TR-LIFS) data analysis for tissue characterization. These analytical methods were applied for the detection of atherosclerotic vulnerable plaques. Upon pulsed nitrogen laser (337 nm, 1 ns) excitation, TR-LIFS measurements were obtained from carotid atherosclerotic plaque specimens (57 endarteroctomy patients) at 492 distinct areas. The emission was both spectrally- (360-600 nm range at 5 nm interval) and temporally- (0.3 ns resolution) resolved using a prototype clinically compatible fiber-optic catheter TR-LIFS apparatus. The TR-LIFS measurements were subsequently analyzed using a standard multiexponential deconvolution and a recently introduced Laguerre deconvolution technique. Based on their histopathology, the lesions were classified as early (thin intima), fibrotic (collagen-rich intima), and high-risk (thin cap over necrotic core and/or inflamed intima). Stepwise linear discriminant analysis (SLDA) was applied for lesion classification. Normalized spectral intensity values and Laguerre expansion coefficients (LEC) at discrete emission wavelengths (390, 450, 500 and 550 nm) were used as features for classification. The Laguerre based SLDA classifier provided discrimination of high-risk lesions with high sensitivity (SE>81%) and specificity (SP>95%). Based on these findings, we believe that TR-LIFS information derived from the Laguerre expansion coefficients can provide a valuable additional dimension for the diagnosis of high-risk vulnerable atherosclerotic plaques.

Spectral Mining for Discriminating Blood Origins in the Presence of Substrate Interference via Attenuated Total Reflection Fourier Transform Infrared Spectroscopy: Postmortem or Antemortem Blood?

PubMed

Takamura, Ayari; Watanabe, Ken; Akutsu, Tomoko; Ikegaya, Hiroshi; Ozawa, Takeaki

2017-09-19

Often in criminal investigations, discrimination of types of body fluid evidence is crucially important to ascertain how a crime was committed. Compared to current methods using biochemical techniques, vibrational spectroscopic approaches can provide versatile applicability to identify various body fluid types without sample invasion. However, their applicability is limited to pure body fluid samples because important signals from body fluids incorporated in a substrate are affected strongly by interference from substrate signals. Herein, we describe a novel approach to recover body fluid signals that are embedded in strong substrate interferences using attenuated total reflection Fourier transform infrared (ATR FT-IR) spectroscopy and an innovative multivariate spectral processing. This technique supported detection of covert features of body fluid signals, and then identified origins of body fluid stains on substrates. We discriminated between ATR FT-IR spectra of postmortem blood (PB) and those of antemortem blood (AB) by creating a multivariate statistics model. From ATR FT-IR spectra of PB and AB stains on interfering substrates (polyester, cotton, and denim), blood-originated signals were extracted by a weighted linear regression approach we developed originally using principal components of both blood and substrate spectra. The blood-originated signals were finally classified by the discriminant model, demonstrating high discriminant accuracy. The present method can identify body fluid evidence independently of the substrate type, which is expected to promote the application of vibrational spectroscopic techniques in forensic body fluid analysis.

Nonlinear features for classification and pose estimation of machined parts from single views

NASA Astrophysics Data System (ADS)

Talukder, Ashit; Casasent, David P.

1998-10-01

A new nonlinear feature extraction method is presented for classification and pose estimation of objects from single views. The feature extraction method is called the maximum representation and discrimination feature (MRDF) method. The nonlinear MRDF transformations to use are obtained in closed form, and offer significant advantages compared to nonlinear neural network implementations. The features extracted are useful for both object discrimination (classification) and object representation (pose estimation). We consider MRDFs on image data, provide a new 2-stage nonlinear MRDF solution, and show it specializes to well-known linear and nonlinear image processing transforms under certain conditions. We show the use of MRDF in estimating the class and pose of images of rendered solid CAD models of machine parts from single views using a feature-space trajectory neural network classifier. We show new results with better classification and pose estimation accuracy than are achieved by standard principal component analysis and Fukunaga-Koontz feature extraction methods.

Design of Clinical Support Systems Using Integrated Genetic Algorithm and Support Vector Machine

NASA Astrophysics Data System (ADS)

Chen, Yung-Fu; Huang, Yung-Fa; Jiang, Xiaoyi; Hsu, Yuan-Nian; Lin, Hsuan-Hung

Clinical decision support system (CDSS) provides knowledge and specific information for clinicians to enhance diagnostic efficiency and improving healthcare quality. An appropriate CDSS can highly elevate patient safety, improve healthcare quality, and increase cost-effectiveness. Support vector machine (SVM) is believed to be superior to traditional statistical and neural network classifiers. However, it is critical to determine suitable combination of SVM parameters regarding classification performance. Genetic algorithm (GA) can find optimal solution within an acceptable time, and is faster than greedy algorithm with exhaustive searching strategy. By taking the advantage of GA in quickly selecting the salient features and adjusting SVM parameters, a method using integrated GA and SVM (IGS), which is different from the traditional method with GA used for feature selection and SVM for classification, was used to design CDSSs for prediction of successful ventilation weaning, diagnosis of patients with severe obstructive sleep apnea, and discrimination of different cell types form Pap smear. The results show that IGS is better than methods using SVM alone or linear discriminator.

Authentication of the botanical and geographical origin of honey by mid-infrared spectroscopy.

PubMed

Ruoff, Kaspar; Luginbühl, Werner; Künzli, Raphael; Iglesias, María Teresa; Bogdanov, Stefan; Bosset, Jacques Olivier; von der Ohe, Katharina; von der Ohe, Werner; Amado, Renato

2006-09-06

The potential of Fourier transform mid-infrared spectroscopy (FT-MIR) using an attenuated total reflectance (ATR) cell was evaluated for the authentication of 11 unifloral (acacia, alpine rose, chestnut, dandelion, heather, lime, rape, fir honeydew, metcalfa honeydew, oak honeydew) and polyfloral honey types (n = 411 samples) previously classified with traditional methods such as chemical, pollen, and sensory analysis. Chemometric evaluation of the spectra was carried out by applying principal component analysis and linear discriminant analysis, the error rates of the discriminant models being calculated by using Bayes' theorem. The error rates ranged from <0.1% (polyfloral and heather honeys as well as honeydew honeys from metcalfa, oak, and fir) to 8.3% (alpine rose honey) in both jackknife classification and validation, depending on the honey type considered. This study indicates that ATR-MIR spectroscopy is a valuable tool for the authentication of the botanical origin and quality control and may also be useful for the determination of the geographical origin of honey.

Discriminating plant species across California's diverse ecosystems using airborne VSWIR and TIR imagery

NASA Astrophysics Data System (ADS)

Meerdink, S.; Roberts, D. A.; Roth, K. L.

2015-12-01

Accurate knowledge of the spatial distribution of plant species is required for many research and management agendas that track ecosystem health. Because of this, there is continuous development of research focused on remotely-sensed species classifications for many diverse ecosystems. While plant species have been mapped using airborne imaging spectroscopy, the geographic extent has been limited due to data availability and spectrally similar species continue to be difficult to separate. The proposed Hyperspectral Infrared Imager (HyspIRI) space-borne mission, which includes a visible near infrared/shortwave infrared (VSWIR) imaging spectrometer and thermal infrared (TIR) multi-spectral imager, would present an opportunity to improve species discrimination over a much broader scale. Here we evaluate: 1) the capability of VSWIR and/or TIR spectra to discriminate plant species; 2) the accuracy of species classifications within an ecosystem; and 3) the potential for discriminating among species across a range of ecosystems. Simulated HyspIRI imagery was acquired in spring/summer of 2013 spanning from Santa Barbara to Bakersfield, CA with the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) and the MODIS/ASTER Airborne Simulator (MASTER) instruments. Three spectral libraries were created from these images: AVIRIS (224 bands from 0.4 - 2.5 µm), MASTER (8 bands from 7.5 - 12 µm), and AVIRIS + MASTER. We used canonical discriminant analysis (CDA) as a dimension reduction technique and then classified plant species using linear discriminant analysis (LDA). Our results show the inclusion of TIR spectra improved species discrimination, but only for plant species with emissivities departing from that of a gray body. Ecosystems with species that have high spectral contrast had higher classification accuracies. Mapping plant species across all ecosystems resulted in a classification with lower accuracies than a single ecosystem due to the complex nature of incorporating more plant species.

Differentiation of cumin seeds using a metal-oxide based gas sensor array in tandem with chemometric tools.

PubMed

Ghasemi-Varnamkhasti, Mahdi; Amiri, Zahra Safari; Tohidi, Mojtaba; Dowlati, Majid; Mohtasebi, Seyed Saeid; Silva, Adenilton C; Fernandes, David D S; Araujo, Mário C U

2018-01-01

Cumin is a plant of the Apiaceae family (umbelliferae) which has been used since ancient times as a medicinal plant and as a spice. The difference in the percentage of aromatic compounds in cumin obtained from different locations has led to differentiation of some species of cumin from other species. The quality and price of cumin vary according to the specie and may be an incentive for the adulteration of high value samples with low quality cultivars. An electronic nose simulates the human olfactory sense by using an array of sensors to distinguish complex smells. This makes it an alternative for the identification and classification of cumin species. The data, however, may have a complex structure, difficult to interpret. Given this, chemometric tools can be used to manipulate data with two-dimensional structure (sensor responses in time) obtained by using electronic nose sensors. In this study, an electronic nose based on eight metal oxide semiconductor sensors (MOS) and 2D-LDA (two-dimensional linear discriminant analysis), U-PLS-DA (Partial least square discriminant analysis applied to the unfolded data) and PARAFAC-LDA (Parallel factor analysis with linear discriminant analysis) algorithms were used in order to identify and classify different varieties of both cultivated and wild black caraway and cumin. The proposed methodology presented a correct classification rate of 87.1% for PARAFAC-LDA and 100% for 2D-LDA and U-PLS-DA, indicating a promising strategy for the classification different varieties of cumin, caraway and other seeds. Copyright © 2017 Elsevier B.V. All rights reserved.

Predicting groundwater redox status on a regional scale using linear discriminant analysis.

PubMed

Close, M E; Abraham, P; Humphries, B; Lilburne, L; Cuthill, T; Wilson, S

2016-08-01

Reducing conditions are necessary for denitrification, thus the groundwater redox status can be used to identify subsurface zones where potentially significant nitrate reduction can occur. Groundwater chemistry in two contrasting regions of New Zealand was classified with respect to redox status and related to mappable factors, such as geology, topography and soil characteristics using discriminant analysis. Redox assignment was carried out for water sampled from 568 and 2223 wells in the Waikato and Canterbury regions, respectively. For the Waikato region 64% of wells sampled indicated oxic conditions in the water; 18% indicated reduced conditions and 18% had attributes indicating both reducing and oxic conditions termed "mixed". In Canterbury 84% of wells indicated oxic conditions; 10% were mixed; and only 5% indicated reduced conditions. The analysis was performed over three different well depths, <25m, 25 to 100 and >100m. For both regions, the percentage of oxidised groundwater decreased with increasing well depth. Linear discriminant analysis was used to develop models to differentiate between the three redox states. Models were derived for each depth and region using 67% of the data, and then subsequently validated on the remaining 33%. The average agreement between predicted and measured redox status was 63% and 70% for the Waikato and Canterbury regions, respectively. The models were incorporated into GIS and the prediction of redox status was extended over the whole region, excluding mountainous land. This knowledge improves spatial prediction of reduced groundwater zones, and therefore, when combined with groundwater flow paths, improves estimates of denitrification. Copyright © 2016 Elsevier B.V. All rights reserved.

Characterization of Italian honeys (Marche Region) on the basis of their mineral content and some typical quality parameters

PubMed Central

Conti, Marcelo Enrique; Stripeikis, Jorge; Campanella, Luigi; Cucina, Domenico; Tudino, Mabel Beatriz

2007-01-01

Background The characterization of three types of Marche (Italy) honeys (Acacia, Multifloral, Honeydew) was carried out on the basis of the their quality parameters (pH, sugar content, humidity) and mineral content (Na, K, Ca, Mg, Cu, Fe, and Mn). Pattern recognition methods such as principal components analysis (PCA) and linear discriminant analysis (LDA) were performed in order to classify honey samples whose botanical origins were different, and identify the most discriminant parameters. Lastly, using ANOVA and correlations for all parameters, significant differences between diverse types of honey were examined. Results Most of the samples' water content showed good maturity (98%) whilst pH values were in the range 3.50 – 4.21 confirming the good quality of the honeys analysed. Potassium was quantitatively the most relevant mineral (mean = 643 ppm), accounting for 79% of the total mineral content. The Ca, Na and Mg contents account for 14, 3 and 3% of the total mineral content respectively, while other minerals (Cu, Mn, Fe) were present at very low levels. PCA explained 75% or more of the variance with the first two PC variables. The variables with higher discrimination power according to the multivariate statistical procedure were Mg and pH. On the other hand, all samples of acacia and honeydew, and more than 90% of samples of multifloral type have been correctly classified using the LDA. ANOVA shows significant differences between diverse floral origins for all variables except sugar, moisture and Fe. Conclusion In general, the analytical results obtained for the Marche honeys indicate the products' high quality. The determination of physicochemical parameters and mineral content in combination with modern statistical techniques can be a useful tool for honey classification. PMID:17880749

Development of a tree classifier for discrimination of surface mine activity from Landsat digital data

NASA Technical Reports Server (NTRS)

Solomon, J. L.; Miller, W. F.; Quattrochi, D. A.

1979-01-01

In a cooperative project with the Geological Survey of Alabama, the Mississippi State Remote Sensing Applications Program has developed a single purpose, decision-tree classifier using band-ratioing techniques to discriminate various stages of surface mining activity. The tree classifier has four levels and employs only two channels in classification at each level. An accurate computation of the amount of disturbed land resulting from the mining activity can be made as a product of the classification output. The utilization of Landsat data provides a cost-efficient, rapid, and accurate means of monitoring surface mining activities.

Exploration of computational methods for classification of movement intention during human voluntary movement from single trial EEG.

PubMed

Bai, Ou; Lin, Peter; Vorbach, Sherry; Li, Jiang; Furlani, Steve; Hallett, Mark

2007-12-01

To explore effective combinations of computational methods for the prediction of movement intention preceding the production of self-paced right and left hand movements from single trial scalp electroencephalogram (EEG). Twelve naïve subjects performed self-paced movements consisting of three key strokes with either hand. EEG was recorded from 128 channels. The exploration was performed offline on single trial EEG data. We proposed that a successful computational procedure for classification would consist of spatial filtering, temporal filtering, feature selection, and pattern classification. A systematic investigation was performed with combinations of spatial filtering using principal component analysis (PCA), independent component analysis (ICA), common spatial patterns analysis (CSP), and surface Laplacian derivation (SLD); temporal filtering using power spectral density estimation (PSD) and discrete wavelet transform (DWT); pattern classification using linear Mahalanobis distance classifier (LMD), quadratic Mahalanobis distance classifier (QMD), Bayesian classifier (BSC), multi-layer perceptron neural network (MLP), probabilistic neural network (PNN), and support vector machine (SVM). A robust multivariate feature selection strategy using a genetic algorithm was employed. The combinations of spatial filtering using ICA and SLD, temporal filtering using PSD and DWT, and classification methods using LMD, QMD, BSC and SVM provided higher performance than those of other combinations. Utilizing one of the better combinations of ICA, PSD and SVM, the discrimination accuracy was as high as 75%. Further feature analysis showed that beta band EEG activity of the channels over right sensorimotor cortex was most appropriate for discrimination of right and left hand movement intention. Effective combinations of computational methods provide possible classification of human movement intention from single trial EEG. Such a method could be the basis for a potential brain-computer interface based on human natural movement, which might reduce the requirement of long-term training. Effective combinations of computational methods can classify human movement intention from single trial EEG with reasonable accuracy.

Information theoretic partitioning and confidence based weight assignment for multi-classifier decision level fusion in hyperspectral target recognition applications

NASA Astrophysics Data System (ADS)

Prasad, S.; Bruce, L. M.

2007-04-01

There is a growing interest in using multiple sources for automatic target recognition (ATR) applications. One approach is to take multiple, independent observations of a phenomenon and perform a feature level or a decision level fusion for ATR. This paper proposes a method to utilize these types of multi-source fusion techniques to exploit hyperspectral data when only a small number of training pixels are available. Conventional hyperspectral image based ATR techniques project the high dimensional reflectance signature onto a lower dimensional subspace using techniques such as Principal Components Analysis (PCA), Fisher's linear discriminant analysis (LDA), subspace LDA and stepwise LDA. While some of these techniques attempt to solve the curse of dimensionality, or small sample size problem, these are not necessarily optimal projections. In this paper, we present a divide and conquer approach to address the small sample size problem. The hyperspectral space is partitioned into contiguous subspaces such that the discriminative information within each subspace is maximized, and the statistical dependence between subspaces is minimized. We then treat each subspace as a separate source in a multi-source multi-classifier setup and test various decision fusion schemes to determine their efficacy. Unlike previous approaches which use correlation between variables for band grouping, we study the efficacy of higher order statistical information (using average mutual information) for a bottom up band grouping. We also propose a confidence measure based decision fusion technique, where the weights associated with various classifiers are based on their confidence in recognizing the training data. To this end, training accuracies of all classifiers are used for weight assignment in the fusion process of test pixels. The proposed methods are tested using hyperspectral data with known ground truth, such that the efficacy can be quantitatively measured in terms of target recognition accuracies.

Determining quality of caviar from Caspian Sea based on Raman spectroscopy and using artificial neural networks.

PubMed

Mohamadi Monavar, H; Afseth, N K; Lozano, J; Alimardani, R; Omid, M; Wold, J P

2013-07-15

The purpose of this study was to evaluate the feasibility of Raman spectroscopy for predicting purity of caviars. The 93 wild caviar samples of three different types, namely; Beluga, Asetra and Sevruga were analysed by Raman spectroscopy in the range 1995 cm(-1) to 545 cm(-1). Also, 60 samples from combinations of every two types were examined. The chemical origin of the samples was identified by reference measurements on pure samples. Linear chemometric methods like Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) were used for data visualisation and classification which permitted clear distinction between different caviars. Non-linear methods like Artificial Neural Networks (ANN) were used to classify caviar samples. Two different networks were tested in the classification: Probabilistic Neural Network with Radial-Basis Function (PNN) and Multilayer Feed Forward Networks with Back Propagation (BP-NN). In both cases, scores of principal components (PCs) were chosen as input nodes for the input layer in PC-ANN models in order to reduce the redundancy of data and time of training. Leave One Out (LOO) cross validation was applied in order to check the performance of the networks. Results of PCA indicated that, features like type and purity can be used to discriminate different caviar samples. These findings were also supported by LDA with efficiency between 83.77% and 100%. These results were confirmed with the results obtained by developed PC-ANN models, able to classify pure caviar samples with 93.55% and 71.00% accuracy in BP network and PNN, respectively. In comparison, LDA, PNN and BP-NN models for predicting caviar types have 90.3%, 73.1% and 91.4% accuracy. Partial least squares regression (PLSR) models were built under cross validation and tested with different independent data sets, yielding determination coefficients (R(2)) of 0.86, 0.83, 0.92 and 0.91 with root mean square error (RMSE) of validation of 0.32, 0.11, 0.03 and 0.09 for fatty acids of 16.0, 20.5, 22.6 and fat, respectively. Crown Copyright © 2013. Published by Elsevier B.V. All rights reserved.

A comparison of different chemometrics approaches for the robust classification of electronic nose data.

PubMed

Gromski, Piotr S; Correa, Elon; Vaughan, Andrew A; Wedge, David C; Turner, Michael L; Goodacre, Royston

2014-11-01

Accurate detection of certain chemical vapours is important, as these may be diagnostic for the presence of weapons, drugs of misuse or disease. In order to achieve this, chemical sensors could be deployed remotely. However, the readout from such sensors is a multivariate pattern, and this needs to be interpreted robustly using powerful supervised learning methods. Therefore, in this study, we compared the classification accuracy of four pattern recognition algorithms which include linear discriminant analysis (LDA), partial least squares-discriminant analysis (PLS-DA), random forests (RF) and support vector machines (SVM) which employed four different kernels. For this purpose, we have used electronic nose (e-nose) sensor data (Wedge et al., Sensors Actuators B Chem 143:365-372, 2009). In order to allow direct comparison between our four different algorithms, we employed two model validation procedures based on either 10-fold cross-validation or bootstrapping. The results show that LDA (91.56% accuracy) and SVM with a polynomial kernel (91.66% accuracy) were very effective at analysing these e-nose data. These two models gave superior prediction accuracy, sensitivity and specificity in comparison to the other techniques employed. With respect to the e-nose sensor data studied here, our findings recommend that SVM with a polynomial kernel should be favoured as a classification method over the other statistical models that we assessed. SVM with non-linear kernels have the advantage that they can be used for classifying non-linear as well as linear mapping from analytical data space to multi-group classifications and would thus be a suitable algorithm for the analysis of most e-nose sensor data.

Discrimination of soft tissues using laser-induced breakdown spectroscopy in combination with k nearest neighbors (kNN) and support vector machine (SVM) classifiers

NASA Astrophysics Data System (ADS)

Li, Xiaohui; Yang, Sibo; Fan, Rongwei; Yu, Xin; Chen, Deying

2018-06-01

In this paper, discrimination of soft tissues using laser-induced breakdown spectroscopy (LIBS) in combination with multivariate statistical methods is presented. Fresh pork fat, skin, ham, loin and tenderloin muscle tissues are manually cut into slices and ablated using a 1064 nm pulsed Nd:YAG laser. Discrimination analyses between fat, skin and muscle tissues, and further between highly similar ham, loin and tenderloin muscle tissues, are performed based on the LIBS spectra in combination with multivariate statistical methods, including principal component analysis (PCA), k nearest neighbors (kNN) classification, and support vector machine (SVM) classification. Performances of the discrimination models, including accuracy, sensitivity and specificity, are evaluated using 10-fold cross validation. The classification models are optimized to achieve best discrimination performances. The fat, skin and muscle tissues can be definitely discriminated using both kNN and SVM classifiers, with accuracy of over 99.83%, sensitivity of over 0.995 and specificity of over 0.998. The highly similar ham, loin and tenderloin muscle tissues can also be discriminated with acceptable performances. The best performances are achieved with SVM classifier using Gaussian kernel function, with accuracy of 76.84%, sensitivity of over 0.742 and specificity of over 0.869. The results show that the LIBS technique assisted with multivariate statistical methods could be a powerful tool for online discrimination of soft tissues, even for tissues of high similarity, such as muscles from different parts of the animal body. This technique could be used for discrimination of tissues suffering minor clinical changes, thus may advance the diagnosis of early lesions and abnormalities.

Automated detection of radioisotopes from an aircraft platform by pattern recognition analysis of gamma-ray spectra.

PubMed

Dess, Brian W; Cardarelli, John; Thomas, Mark J; Stapleton, Jeff; Kroutil, Robert T; Miller, David; Curry, Timothy; Small, Gary W

2018-03-08

A generalized methodology was developed for automating the detection of radioisotopes from gamma-ray spectra collected from an aircraft platform using sodium-iodide detectors. Employing data provided by the U.S Environmental Protection Agency Airborne Spectral Photometric Environmental Collection Technology (ASPECT) program, multivariate classification models based on nonparametric linear discriminant analysis were developed for application to spectra that were preprocessed through a combination of altitude-based scaling and digital filtering. Training sets of spectra for use in building classification models were assembled from a combination of background spectra collected in the field and synthesized spectra obtained by superimposing laboratory-collected spectra of target radioisotopes onto field backgrounds. This approach eliminated the need for field experimentation with radioactive sources for use in building classification models. Through a bi-Gaussian modeling procedure, the discriminant scores that served as the outputs from the classification models were related to associated confidence levels. This provided an easily interpreted result regarding the presence or absence of the signature of a specific radioisotope in each collected spectrum. Through the use of this approach, classifiers were built for cesium-137 ( 137 Cs) and cobalt-60 ( 60 Co), two radioisotopes that are of interest in airborne radiological monitoring applications. The optimized classifiers were tested with field data collected from a set of six geographically diverse sites, three of which contained either 137 Cs, 60 Co, or both. When the optimized classification models were applied, the overall percentages of correct classifications for spectra collected at these sites were 99.9 and 97.9% for the 60 Co and 137 Cs classifiers, respectively. Copyright © 2018 Elsevier Ltd. All rights reserved.

NIR spectroscopy as a tool for discriminating between lichens exposed to air pollution.

PubMed

Casale, Monica; Bagnasco, Lucia; Giordani, Paolo; Mariotti, Mauro Giorgio; Malaspina, Paola

2015-09-01

Lichens are used as biomonitors of air pollution because they are extremely sensitive to the presence of substances that alter atmospheric composition. Fifty-one thalli of two different varieties of Pseudevernia furfuracea (var. furfuracea and var. ceratea) were collected far from local sources of air pollution. Twenty-six of these thalli were then exposed to the air for one month in the industrial port of Genoa, which has high levels of environmental pollution. The possibility of using Near-infrared spectroscopy (NIRS) for generating a 'fingerprint' of lichens was investigated. Chemometric methods were successfully applied to discriminate between samples from polluted and non-polluted areas. In particular, Principal Component Analysis (PCA) was applied as a multivariate display method on the NIR spectra to visualise the data structure. This showed that the difference between samples of different varieties was not significant in comparison to the difference between samples exposed to different levels of environmental pollution. Then Linear Discriminant Analysis (LDA) was carried out to discriminate between lichens based on their exposure to pollutants. The distinction between control samples (not exposed) and samples exposed to the air in the industrial port of Genoa was evaluated. On average, 95.2% of samples were correctly classified, 93.0% of total internal prediction (5 cross-validation groups) and 100.0% of external prediction (on the test set) was achieved. Copyright © 2015 Elsevier Ltd. All rights reserved.

Classification of Hand Grasp Kinetics and Types Using Movement-Related Cortical Potentials and EEG Rhythms.

PubMed

Jochumsen, Mads; Rovsing, Cecilie; Rovsing, Helene; Niazi, Imran Khan; Dremstrup, Kim; Kamavuako, Ernest Nlandu

2017-01-01

Detection of single-trial movement intentions from EEG is paramount for brain-computer interfacing in neurorehabilitation. These movement intentions contain task-related information and if this is decoded, the neurorehabilitation could potentially be optimized. The aim of this study was to classify single-trial movement intentions associated with two levels of force and speed and three different grasp types using EEG rhythms and components of the movement-related cortical potential (MRCP) as features. The feature importance was used to estimate encoding of discriminative information. Two data sets were used. 29 healthy subjects executed and imagined different hand movements, while EEG was recorded over the contralateral sensorimotor cortex. The following features were extracted: delta, theta, mu/alpha, beta, and gamma rhythms, readiness potential, negative slope, and motor potential of the MRCP. Sequential forward selection was performed, and classification was performed using linear discriminant analysis and support vector machines. Limited classification accuracies were obtained from the EEG rhythms and MRCP-components: 0.48 ± 0.05 (grasp types), 0.41 ± 0.07 (kinetic profiles, motor execution), and 0.39 ± 0.08 (kinetic profiles, motor imagination). Delta activity contributed the most but all features provided discriminative information. These findings suggest that information from the entire EEG spectrum is needed to discriminate between task-related parameters from single-trial movement intentions.

Characterization of Chinese rice wine taste attributes using liquid chromatographic analysis, sensory evaluation, and an electronic tongue.

PubMed

Yu, HaiYan; Zhao, Jie; Li, Fenghua; Tian, Huaixiang; Ma, Xia

2015-08-01

To evaluate the taste characteristics of Chinese rice wine, wine samples sourced from different vintage years were analyzed using liquid chromatographic analysis, sensory evaluation, and an electronic tongue. Six organic acids and seventeen amino acids were measured using high performance liquid chromatography (HPLC). Five monosaccharides were measured using anion-exchange chromatography. The global taste attributes were analyzed using an electronic tongue (E-tongue). The correlations between the 28 taste-active compounds and the sensory attributes, and the correlations between the E-tongue response and the sensory attributes were established via partial least square discriminant analysis (PLSDA). E-tongue response data combined with linear discriminant analysis (LDA) were used to discriminate the Chinese rice wine samples sourced from different vintage years. Sensory evaluation indicated significant differences in the Chinese rice wine samples sourced from 2003, 2005, 2008, and 2010 vintage years in the sensory attributes of harmony and mellow. The PLSDA model for the taste-active compounds and the sensory attributes showed that proline, fucose, arabinose, lactic acid, glutamic acid, arginine, isoleucine, valine, threonine, and lysine had an influence on the taste characteristic of Chinese rice wine. The Chinese rice wine samples were all correctly classified using the E-tongue and LDA. The electronic tongue was an effective tool for rapid discrimination of Chinese rice wine. Copyright © 2015 Elsevier B.V. All rights reserved.

Robust infrared target tracking using discriminative and generative approaches

NASA Astrophysics Data System (ADS)

Asha, C. S.; Narasimhadhan, A. V.

2017-09-01

The process of designing an efficient tracker for thermal infrared imagery is one of the most challenging tasks in computer vision. Although a lot of advancement has been achieved in RGB videos over the decades, textureless and colorless properties of objects in thermal imagery pose hard constraints in the design of an efficient tracker. Tracking of an object using a single feature or a technique often fails to achieve greater accuracy. Here, we propose an effective method to track an object in infrared imagery based on a combination of discriminative and generative approaches. The discriminative technique makes use of two complementary methods such as kernelized correlation filter with spatial feature and AdaBoost classifier with pixel intesity features to operate in parallel. After obtaining optimized locations through discriminative approaches, the generative technique is applied to determine the best target location using a linear search method. Unlike the baseline algorithms, the proposed method estimates the scale of the target by Lucas-Kanade homography estimation. To evaluate the proposed method, extensive experiments are conducted on 17 challenging infrared image sequences obtained from LTIR dataset and a significant improvement of mean distance precision and mean overlap precision is accomplished as compared with the existing trackers. Further, a quantitative and qualitative assessment of the proposed approach with the state-of-the-art trackers is illustrated to clearly demonstrate an overall increase in performance.

Diffuse reflectance spectroscopy as a tool for real-time tissue assessment during colorectal cancer surgery

NASA Astrophysics Data System (ADS)

Baltussen, Elisabeth J. M.; Snaebjornsson, Petur; de Koning, Susan G. Brouwer; Sterenborg, Henricus J. C. M.; Aalbers, Arend G. J.; Kok, Niels; Beets, Geerard L.; Hendriks, Benno H. W.; Kuhlmann, Koert F. D.; Ruers, Theo J. M.

2017-10-01

Colorectal surgery is the standard treatment for patients with colorectal cancer. To overcome two of the main challenges, the circumferential resection margin and postoperative complications, real-time tissue assessment could be of great benefit during surgery. In this ex vivo study, diffuse reflectance spectroscopy (DRS) was used to differentiate tumor tissue from healthy surrounding tissues in patients with colorectal neoplasia. DRS spectra were obtained from tumor tissue, healthy colon, or rectal wall and fat tissue, for every patient. Data were randomly divided into training (80%) and test (20%) sets. After spectral band selection, the spectra were classified using a quadratic classifier and a linear support vector machine. Of the 38 included patients, 36 had colorectal cancer and 2 had an adenoma. When the classifiers were applied to the test set, colorectal cancer could be discriminated from healthy tissue with an overall accuracy of 0.95 (±0.03). This study demonstrates the possibility to separate colorectal cancer from healthy surrounding tissue by applying DRS. High classification accuracies were obtained both in homogeneous and inhomogeneous tissues. This is a fundamental step toward the development of a tool for real-time in vivo tissue assessment during colorectal surgery.

Acoustic basis for recognition of aspect-dependent three-dimensional targets by an echolocating bottlenose dolphin.

PubMed

Helweg, D A; Au, W W; Roitblat, H L; Nachtigall, P E

1996-04-01

The relationships between acoustic features of target echoes and the cognitive representations of the target formed by an echolocating dolphin will influence the ease with which the dolphin can recognize a target. A blindfolded Atlantic bottlenose dolphin (Tursiops truncatus) learned to match aspect-dependent three-dimensional targets (such as a cube) at haphazard orientations, although with some difficulty. This task may have been difficult because aspect-dependent targets produce different echoes at different orientations, which required the dolphin to have some capability for object constancy across changes in echo characteristics. Significant target-related differences in echo amplitude, rms bandwidth, and distributions of interhighlight intervals were observed among echoes collected when the dolphin was performing the task. Targets could be classified using a combination of energy flux density and rms bandwidth by a linear discriminant analysis and a nearest centroid classifier. Neither statistical model could classify targets without amplitude information, but the highest accuracy required spectral information as well. This suggests that the dolphin recognized the targets using a multidimensional representation containing amplitude and spectral information and that dolphins can form stable representations of targets regardless of orientation based on varying sensory properties.

Image Statistics and the Representation of Material Properties in the Visual Cortex

PubMed Central

Baumgartner, Elisabeth; Gegenfurtner, Karl R.

2016-01-01

We explored perceived material properties (roughness, texturedness, and hardness) with a novel approach that compares perception, image statistics and brain activation, as measured with fMRI. We initially asked participants to rate 84 material images with respect to the above mentioned properties, and then scanned 15 of the participants with fMRI while they viewed the material images. The images were analyzed with a set of image statistics capturing their spatial frequency and texture properties. Linear classifiers were then applied to the image statistics as well as the voxel patterns of visually responsive voxels and early visual areas to discriminate between images with high and low perceptual ratings. Roughness and texturedness could be classified above chance level based on image statistics. Roughness and texturedness could also be classified based on the brain activation patterns in visual cortex, whereas hardness could not. Importantly, the agreement in classification based on image statistics and brain activation was also above chance level. Our results show that information about visual material properties is to a large degree contained in low-level image statistics, and that these image statistics are also partially reflected in brain activity patterns induced by the perception of material images. PMID:27582714

Image Statistics and the Representation of Material Properties in the Visual Cortex.

PubMed

Baumgartner, Elisabeth; Gegenfurtner, Karl R

2016-01-01

We explored perceived material properties (roughness, texturedness, and hardness) with a novel approach that compares perception, image statistics and brain activation, as measured with fMRI. We initially asked participants to rate 84 material images with respect to the above mentioned properties, and then scanned 15 of the participants with fMRI while they viewed the material images. The images were analyzed with a set of image statistics capturing their spatial frequency and texture properties. Linear classifiers were then applied to the image statistics as well as the voxel patterns of visually responsive voxels and early visual areas to discriminate between images with high and low perceptual ratings. Roughness and texturedness could be classified above chance level based on image statistics. Roughness and texturedness could also be classified based on the brain activation patterns in visual cortex, whereas hardness could not. Importantly, the agreement in classification based on image statistics and brain activation was also above chance level. Our results show that information about visual material properties is to a large degree contained in low-level image statistics, and that these image statistics are also partially reflected in brain activity patterns induced by the perception of material images.

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

PubMed

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

2016-04-01

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

Mild Depression Detection of College Students: an EEG-Based Solution with Free Viewing Tasks.

PubMed

Li, Xiaowei; Hu, Bin; Shen, Ji; Xu, Tingting; Retcliffe, Martyn

2015-12-01

Depression is a common mental disorder with growing prevalence; however current diagnoses of depression face the problem of patient denial, clinical experience and subjective biases from self-report. By using a combination of linear and nonlinear EEG features in our research, we aim to develop a more accurate and objective approach to depression detection that supports the process of diagnosis and assists the monitoring of risk factors. By classifying EEG features during free viewing task, an accuracy of 99.1%, which is the highest to our knowledge by far, was achieved using kNN classifier to discriminate depressed and non-depressed subjects. Furthermore, through correlation analysis, comparisons of performance on each electrode were discussed on the availability of single channel EEG recording depression detection system. Combined with wearable EEG collecting devices, our method offers the possibility of cost effective wearable ubiquitous system for doctors to monitor their patients with depression, and for normal people to understand their mental states in time.

Objective measurement of erythema in psoriasis using digital color photography with color calibration.

PubMed

Raina, A; Hennessy, R; Rains, M; Allred, J; Hirshburg, J M; Diven, D G; Markey, M K

2016-08-01

Traditional metrics for evaluating the severity of psoriasis are subjective, which complicates efforts to measure effective treatments in clinical trials. We collected images of psoriasis plaques and calibrated the coloration of the images according to an included color card. Features were extracted from the images and used to train a linear discriminant analysis classifier with cross-validation to automatically classify the degree of erythema. The results were tested against numerical scores obtained by a panel of dermatologists using a standard rating system. Quantitative measures of erythema based on the digital color images showed good agreement with subjective assessment of erythema severity (κ = 0.4203). The color calibration process improved the agreement from κ = 0.2364 to κ = 0.4203. We propose a method for the objective measurement of the psoriasis severity parameter of erythema and show that the calibration process improved the results. © 2015 John Wiley & Sons A/S. Published by John Wiley & Sons Ltd.

Classification of pumpkin seed oils according to their species and genetic variety by attenuated total reflection Fourier-transform infrared spectroscopy.

PubMed

Saucedo-Hernández, Yanelis; Lerma-García, María Jesús; Herrero-Martínez, José Manuel; Ramis-Ramos, Guillermo; Jorge-Rodríguez, Elisa; Simí-Alfonso, Ernesto F

2011-04-27

Attenuated total reflection Fourier-transform infrared spectroscopy (ATR-FTIR), followed by multivariate treatment of the spectral data, was used to classify seed oils of the genus Cucurbita (pumpkins) according to their species as C. maxima, C. pepo, and C. moschata. Also, C. moschata seed oils were classified according to their genetic variety as RG, Inivit C-88, and Inivit C-2000. Up to 23 wavelength regions were selected on the spectra, each region corresponding to a peak or shoulder. The normalized absorbance peak areas within these regions were used as predictors. Using linear discriminant analysis (LDA), an excellent resolution among all categories concerning both Cucurbita species and C. moschata varieties was achieved. The proposed method was straightforward and quick and can be easily implemented. Quality control of pumpkin seed oils is important because Cucurbita species and genetic variety are both related to the pharmaceutical properties of the oils.

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.

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

PubMed

Wang, Jinjia; Liu, Yuan

2015-04-01

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

Discriminative and predictive validity of the scoliosis research society-22 questionnaire in management and curve-severity subgroups of adolescents with idiopathic scoliosis.

PubMed

Parent, Eric C; Hill, Doug; Mahood, Jim; Moreau, Marc; Raso, Jim; Lou, Edmond

2009-10-15

Prospective cross-sectional measurement study. To determine the ability of the Scoliosis Research Society (SRS)-22 questionnaire to discriminate among management and scoliosis severity subgroups and to correlate with internal and external measures of curve severity. In earlier studies of the SRS-22 discriminative ability, age was not a controlled factor. The ability of the SRS-22 to predict curve severity has not been thoroughly examined. The SRS-22 was completed by 227 females with adolescent idiopathic scoliosis. Using Analysis of covariance analyses controlling for age, the SRS-22 scores were compared among management subgroups (observation, brace, presurgery, and postsurgery) and curve-severity subgroups (in nonoperated subjects: Cobb angles of <30 degrees, 30 degrees -50 degrees, and >50 degrees). A stepwise discriminant analysis was used to identify the SRS-22 domains most discriminative for curve-severity categories. Correlation between SRS-22 scores and radiographic or surface topography measurements was used to determine the predictive ability of the questionnaire. Pain was better for subjects treated with braces than for those planning surgery. Self-image was better for subjects under observation or postsurgery than for those planning surgery. Satisfaction was better for the brace and postsurgery subgroups than for the observation or presurgery subgroups. Statistically significant mean differences between subgroups were all larger than 0.5, which is within the range of minimal clinically important differences recommended for each of the 5-point SRS-22 domain scoring scales. Pain and mental health were worse for those with Cobb angles of >50 degrees than with Cobb angles of 30 degrees to 50 degrees. Self-image and total scores were worse for those with Cobb angles of >50 degrees than both other subgroups. Using discriminant analysis, self-image was the only SRS-22 domain score selected to classify subjects within curve severity subgroups. The percentage of patients accurately classified was 54% when trying to classify within 3 curve severity subgroups. The percentage of patients accurately classified was 73% when classifying simply as those with curves larger or smaller than 50 degrees . Pain, self-image, and satisfaction scores could discriminate among management subgroups, but function, mental health and total scores could not. The total score and all domain scores except satisfaction discriminated among curve-severity subgroups. Using discriminant analysis, self-image was the only domain retained in a model predicting curve-severity categories.

[Feature extraction for breast cancer data based on geometric algebra theory and feature selection using differential evolution].

PubMed

Li, Jing; Hong, Wenxue

2014-12-01

The feature extraction and feature selection are the important issues in pattern recognition. Based on the geometric algebra representation of vector, a new feature extraction method using blade coefficient of geometric algebra was proposed in this study. At the same time, an improved differential evolution (DE) feature selection method was proposed to solve the elevated high dimension issue. The simple linear discriminant analysis was used as the classifier. The result of the 10-fold cross-validation (10 CV) classification of public breast cancer biomedical dataset was more than 96% and proved superior to that of the original features and traditional feature extraction method.

Evaluation of Classifier Performance for Multiclass Phenotype Discrimination in Untargeted Metabolomics.

PubMed

Trainor, Patrick J; DeFilippis, Andrew P; Rai, Shesh N

2017-06-21

Statistical classification is a critical component of utilizing metabolomics data for examining the molecular determinants of phenotypes. Despite this, a comprehensive and rigorous evaluation of the accuracy of classification techniques for phenotype discrimination given metabolomics data has not been conducted. We conducted such an evaluation using both simulated and real metabolomics datasets, comparing Partial Least Squares-Discriminant Analysis (PLS-DA), Sparse PLS-DA, Random Forests, Support Vector Machines (SVM), Artificial Neural Network, k -Nearest Neighbors ( k -NN), and Naïve Bayes classification techniques for discrimination. We evaluated the techniques on simulated data generated to mimic global untargeted metabolomics data by incorporating realistic block-wise correlation and partial correlation structures for mimicking the correlations and metabolite clustering generated by biological processes. Over the simulation studies, covariance structures, means, and effect sizes were stochastically varied to provide consistent estimates of classifier performance over a wide range of possible scenarios. The effects of the presence of non-normal error distributions, the introduction of biological and technical outliers, unbalanced phenotype allocation, missing values due to abundances below a limit of detection, and the effect of prior-significance filtering (dimension reduction) were evaluated via simulation. In each simulation, classifier parameters, such as the number of hidden nodes in a Neural Network, were optimized by cross-validation to minimize the probability of detecting spurious results due to poorly tuned classifiers. Classifier performance was then evaluated using real metabolomics datasets of varying sample medium, sample size, and experimental design. We report that in the most realistic simulation studies that incorporated non-normal error distributions, unbalanced phenotype allocation, outliers, missing values, and dimension reduction, classifier performance (least to greatest error) was ranked as follows: SVM, Random Forest, Naïve Bayes, sPLS-DA, Neural Networks, PLS-DA and k -NN classifiers. When non-normal error distributions were introduced, the performance of PLS-DA and k -NN classifiers deteriorated further relative to the remaining techniques. Over the real datasets, a trend of better performance of SVM and Random Forest classifier performance was observed.

Classification of brain tumours using short echo time 1H MR spectra

NASA Astrophysics Data System (ADS)

Devos, A.; Lukas, L.; Suykens, J. A. K.; Vanhamme, L.; Tate, A. R.; Howe, F. A.; Majós, C.; Moreno-Torres, A.; van der Graaf, M.; Arús, C.; Van Huffel, S.

2004-09-01

The purpose was to objectively compare the application of several techniques and the use of several input features for brain tumour classification using Magnetic Resonance Spectroscopy (MRS). Short echo time 1H MRS signals from patients with glioblastomas ( n = 87), meningiomas ( n = 57), metastases ( n = 39), and astrocytomas grade II ( n = 22) were provided by six centres in the European Union funded INTERPRET project. Linear discriminant analysis, least squares support vector machines (LS-SVM) with a linear kernel and LS-SVM with radial basis function kernel were applied and evaluated over 100 stratified random splittings of the dataset into training and test sets. The area under the receiver operating characteristic curve (AUC) was used to measure the performance of binary classifiers, while the percentage of correct classifications was used to evaluate the multiclass classifiers. The influence of several factors on the classification performance has been tested: L2- vs. water normalization, magnitude vs. real spectra and baseline correction. The effect of input feature reduction was also investigated by using only the selected frequency regions containing the most discriminatory information, and peak integrated values. Using L2-normalized complete spectra the automated binary classifiers reached a mean test AUC of more than 0.95, except for glioblastomas vs. metastases. Similar results were obtained for all classification techniques and input features except for water normalized spectra, where classification performance was lower. This indicates that data acquisition and processing can be simplified for classification purposes, excluding the need for separate water signal acquisition, baseline correction or phasing.

A neural network approach to cloud classification

NASA Technical Reports Server (NTRS)

Lee, Jonathan; Weger, Ronald C.; Sengupta, Sailes K.; Welch, Ronald M.

1990-01-01

It is shown that, using high-spatial-resolution data, very high cloud classification accuracies can be obtained with a neural network approach. A texture-based neural network classifier using only single-channel visible Landsat MSS imagery achieves an overall cloud identification accuracy of 93 percent. Cirrus can be distinguished from boundary layer cloudiness with an accuracy of 96 percent, without the use of an infrared channel. Stratocumulus is retrieved with an accuracy of 92 percent, cumulus at 90 percent. The use of the neural network does not improve cirrus classification accuracy. Rather, its main effect is in the improved separation between stratocumulus and cumulus cloudiness. While most cloud classification algorithms rely on linear parametric schemes, the present study is based on a nonlinear, nonparametric four-layer neural network approach. A three-layer neural network architecture, the nonparametric K-nearest neighbor approach, and the linear stepwise discriminant analysis procedure are compared. A significant finding is that significantly higher accuracies are attained with the nonparametric approaches using only 20 percent of the database as training data, compared to 67 percent of the database in the linear approach.

Improving predictions of protein-protein interfaces by combining amino acid-specific classifiers based on structural and physicochemical descriptors with their weighted neighbor averages.

PubMed

de Moraes, Fábio R; Neshich, Izabella A P; Mazoni, Ivan; Yano, Inácio H; Pereira, José G C; Salim, José A; Jardine, José G; Neshich, Goran

2014-01-01

Protein-protein interactions are involved in nearly all regulatory processes in the cell and are considered one of the most important issues in molecular biology and pharmaceutical sciences but are still not fully understood. Structural and computational biology contributed greatly to the elucidation of the mechanism of protein interactions. In this paper, we present a collection of the physicochemical and structural characteristics that distinguish interface-forming residues (IFR) from free surface residues (FSR). We formulated a linear discriminative analysis (LDA) classifier to assess whether chosen descriptors from the BlueStar STING database (http://www.cbi.cnptia.embrapa.br/SMS/) are suitable for such a task. Receiver operating characteristic (ROC) analysis indicates that the particular physicochemical and structural descriptors used for building the linear classifier perform much better than a random classifier and in fact, successfully outperform some of the previously published procedures, whose performance indicators were recently compared by other research groups. The results presented here show that the selected set of descriptors can be utilized to predict IFRs, even when homologue proteins are missing (particularly important for orphan proteins where no homologue is available for comparative analysis/indication) or, when certain conformational changes accompany interface formation. The development of amino acid type specific classifiers is shown to increase IFR classification performance. Also, we found that the addition of an amino acid conservation attribute did not improve the classification prediction. This result indicates that the increase in predictive power associated with amino acid conservation is exhausted by adequate use of an extensive list of independent physicochemical and structural parameters that, by themselves, fully describe the nano-environment at protein-protein interfaces. The IFR classifier developed in this study is now integrated into the BlueStar STING suite of programs. Consequently, the prediction of protein-protein interfaces for all proteins available in the PDB is possible through STING_interfaces module, accessible at the following website: (http://www.cbi.cnptia.embrapa.br/SMS/predictions/index.html).

Improving Predictions of Protein-Protein Interfaces by Combining Amino Acid-Specific Classifiers Based on Structural and Physicochemical Descriptors with Their Weighted Neighbor Averages

PubMed Central

de Moraes, Fábio R.; Neshich, Izabella A. P.; Mazoni, Ivan; Yano, Inácio H.; Pereira, José G. C.; Salim, José A.; Jardine, José G.; Neshich, Goran

2014-01-01

Protein-protein interactions are involved in nearly all regulatory processes in the cell and are considered one of the most important issues in molecular biology and pharmaceutical sciences but are still not fully understood. Structural and computational biology contributed greatly to the elucidation of the mechanism of protein interactions. In this paper, we present a collection of the physicochemical and structural characteristics that distinguish interface-forming residues (IFR) from free surface residues (FSR). We formulated a linear discriminative analysis (LDA) classifier to assess whether chosen descriptors from the BlueStar STING database (http://www.cbi.cnptia.embrapa.br/SMS/) are suitable for such a task. Receiver operating characteristic (ROC) analysis indicates that the particular physicochemical and structural descriptors used for building the linear classifier perform much better than a random classifier and in fact, successfully outperform some of the previously published procedures, whose performance indicators were recently compared by other research groups. The results presented here show that the selected set of descriptors can be utilized to predict IFRs, even when homologue proteins are missing (particularly important for orphan proteins where no homologue is available for comparative analysis/indication) or, when certain conformational changes accompany interface formation. The development of amino acid type specific classifiers is shown to increase IFR classification performance. Also, we found that the addition of an amino acid conservation attribute did not improve the classification prediction. This result indicates that the increase in predictive power associated with amino acid conservation is exhausted by adequate use of an extensive list of independent physicochemical and structural parameters that, by themselves, fully describe the nano-environment at protein-protein interfaces. The IFR classifier developed in this study is now integrated into the BlueStar STING suite of programs. Consequently, the prediction of protein-protein interfaces for all proteins available in the PDB is possible through STING_interfaces module, accessible at the following website: (http://www.cbi.cnptia.embrapa.br/SMS/predictions/index.html). PMID:24489849

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.

Orthogonal sparse linear discriminant analysis

NASA Astrophysics Data System (ADS)

Liu, Zhonghua; Liu, Gang; Pu, Jiexin; Wang, Xiaohong; Wang, Haijun

2018-03-01

Linear discriminant analysis (LDA) is a linear feature extraction approach, and it has received much attention. On the basis of LDA, researchers have done a lot of research work on it, and many variant versions of LDA were proposed. However, the inherent problem of LDA cannot be solved very well by the variant methods. The major disadvantages of the classical LDA are as follows. First, it is sensitive to outliers and noises. Second, only the global discriminant structure is preserved, while the local discriminant information is ignored. In this paper, we present a new orthogonal sparse linear discriminant analysis (OSLDA) algorithm. The k nearest neighbour graph is first constructed to preserve the locality discriminant information of sample points. Then, L2,1-norm constraint on the projection matrix is used to act as loss function, which can make the proposed method robust to outliers in data points. Extensive experiments have been performed on several standard public image databases, and the experiment results demonstrate the performance of the proposed OSLDA algorithm.

[Frequency and variables associated with perceived devaluation-discrimination in victims of the armed conflict in Colombia].

PubMed

Campo-Arias, Adalberto; Ospino, Anyelly C; Sanabria, Adriana R; Guerra, Valeria M; Caamaño, Beatriz H; Herazo, Edwin

2017-11-21

There is no information on frequency of perceived devaluation-discrimination in victims of the armed conflict in Colombia. The aim of this study was thus to determine the frequency of perceived devaluation-discrimination and associated variables among victims of the armed conflict in municipalities in the Department of Magdalena, Colombia. A cross-sectional study was conducted among victims enrolled in the Program for Psychosocial Care and Comprehensive Healthcare for Victims. Depressive symptoms were quantified with four dichotomous items (three or more were classified as high level of depressive symptoms), and perceived devaluation-discrimination was quantified with six dichotomous items (two or more were classified as high perceived devaluation-discrimination). A total of 943 adults participated (M = 47.9; SD = 14.2); 67.4%, women; 109 (11.6%) reported high level of depressive symptoms and 217 (23%) showed high perceived devaluation-discrimination. High perceived devaluation-discrimination was associated with high level of depressive symptoms (OR = 6.47; 95%CI: 4.23-9.88). In conclusion, one-fourth of the victims of the armed conflict in Magdalena reported high perceived devaluation-discrimination, which was significantly associated with high level of depressive symptoms.

A Gaussian mixture model based adaptive classifier for fNIRS brain-computer interfaces and its testing via simulation

NASA Astrophysics Data System (ADS)

Li, Zheng; Jiang, Yi-han; Duan, Lian; Zhu, Chao-zhe

2017-08-01

Objective. Functional near infra-red spectroscopy (fNIRS) is a promising brain imaging technology for brain-computer interfaces (BCI). Future clinical uses of fNIRS will likely require operation over long time spans, during which neural activation patterns may change. However, current decoders for fNIRS signals are not designed to handle changing activation patterns. The objective of this study is to test via simulations a new adaptive decoder for fNIRS signals, the Gaussian mixture model adaptive classifier (GMMAC). Approach. GMMAC can simultaneously classify and track activation pattern changes without the need for ground-truth labels. This adaptive classifier uses computationally efficient variational Bayesian inference to label new data points and update mixture model parameters, using the previous model parameters as priors. We test GMMAC in simulations in which neural activation patterns change over time and compare to static decoders and unsupervised adaptive linear discriminant analysis classifiers. Main results. Our simulation experiments show GMMAC can accurately decode under time-varying activation patterns: shifts of activation region, expansions of activation region, and combined contractions and shifts of activation region. Furthermore, the experiments show the proposed method can track the changing shape of the activation region. Compared to prior work, GMMAC performed significantly better than the other unsupervised adaptive classifiers on a difficult activation pattern change simulation: 99% versus  <54% in two-choice classification accuracy. Significance. We believe GMMAC will be useful for clinical fNIRS-based brain-computer interfaces, including neurofeedback training systems, where operation over long time spans is required.

Deformable segmentation of 3D MR prostate images via distributed discriminative dictionary and ensemble learning

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

Guo, Yanrong; Shao, Yeqin; Gao, Yaozong

Purpose: Automatic prostate segmentation from MR images is an important task in various clinical applications such as prostate cancer staging and MR-guided radiotherapy planning. However, the large appearance and shape variations of the prostate in MR images make the segmentation problem difficult to solve. Traditional Active Shape/Appearance Model (ASM/AAM) has limited accuracy on this problem, since its basic assumption, i.e., both shape and appearance of the targeted organ follow Gaussian distributions, is invalid in prostate MR images. To this end, the authors propose a sparse dictionary learning method to model the image appearance in a nonparametric fashion and further integratemore » the appearance model into a deformable segmentation framework for prostate MR segmentation. Methods: To drive the deformable model for prostate segmentation, the authors propose nonparametric appearance and shape models. The nonparametric appearance model is based on a novel dictionary learning method, namely distributed discriminative dictionary (DDD) learning, which is able to capture fine distinctions in image appearance. To increase the differential power of traditional dictionary-based classification methods, the authors' DDD learning approach takes three strategies. First, two dictionaries for prostate and nonprostate tissues are built, respectively, using the discriminative features obtained from minimum redundancy maximum relevance feature selection. Second, linear discriminant analysis is employed as a linear classifier to boost the optimal separation between prostate and nonprostate tissues, based on the representation residuals from sparse representation. Third, to enhance the robustness of the authors' classification method, multiple local dictionaries are learned for local regions along the prostate boundary (each with small appearance variations), instead of learning one global classifier for the entire prostate. These discriminative dictionaries are located on different patches of the prostate surface and trained to adaptively capture the appearance in different prostate zones, thus achieving better local tissue differentiation. For each local region, multiple classifiers are trained based on the randomly selected samples and finally assembled by a specific fusion method. In addition to this nonparametric appearance model, a prostate shape model is learned from the shape statistics using a novel approach, sparse shape composition, which can model nonGaussian distributions of shape variation and regularize the 3D mesh deformation by constraining it within the observed shape subspace. Results: The proposed method has been evaluated on two datasets consisting of T2-weighted MR prostate images. For the first (internal) dataset, the classification effectiveness of the authors' improved dictionary learning has been validated by comparing it with three other variants of traditional dictionary learning methods. The experimental results show that the authors' method yields a Dice Ratio of 89.1% compared to the manual segmentation, which is more accurate than the three state-of-the-art MR prostate segmentation methods under comparison. For the second dataset, the MICCAI 2012 challenge dataset, the authors' proposed method yields a Dice Ratio of 87.4%, which also achieves better segmentation accuracy than other methods under comparison. Conclusions: A new magnetic resonance image prostate segmentation method is proposed based on the combination of deformable model and dictionary learning methods, which achieves more accurate segmentation performance on prostate T2 MR images.« less

Evaluation of extreme learning machine for classification of individual and combined finger movements using electromyography on amputees and non-amputees.

PubMed

Anam, Khairul; Al-Jumaily, Adel

2017-01-01

The success of myoelectric pattern recognition (M-PR) mostly relies on the features extracted and classifier employed. This paper proposes and evaluates a fast classifier, extreme learning machine (ELM), to classify individual and combined finger movements on amputees and non-amputees. ELM is a single hidden layer feed-forward network (SLFN) that avoids iterative learning by determining input weights randomly and output weights analytically. Therefore, it can accelerate the training time of SLFNs. In addition to the classifier evaluation, this paper evaluates various feature combinations to improve the performance of M-PR and investigate some feature projections to improve the class separability of the features. Different from other studies on the implementation of ELM in the myoelectric controller, this paper presents a complete and thorough investigation of various types of ELMs including the node-based and kernel-based ELM. Furthermore, this paper provides comparisons of ELMs and other well-known classifiers such as linear discriminant analysis (LDA), k-nearest neighbour (kNN), support vector machine (SVM) and least-square SVM (LS-SVM). The experimental results show the most accurate ELM classifier is radial basis function ELM (RBF-ELM). The comparison of RBF-ELM and other well-known classifiers shows that RBF-ELM is as accurate as SVM and LS-SVM but faster than the SVM family; it is superior to LDA and kNN. The experimental results also indicate that the accuracy gap of the M-PR on the amputees and non-amputees is not too much with the accuracy of 98.55% on amputees and 99.5% on the non-amputees using six electromyography (EMG) channels. Copyright © 2016 Elsevier Ltd. All rights reserved.

Local connected fractal dimension analysis in gill of fish experimentally exposed to toxicants.

PubMed

Manera, Maurizio; Giari, Luisa; De Pasquale, Joseph A; Sayyaf Dezfuli, Bahram

2016-06-01

An operator-neutral method was implemented to objectively assess European seabass, Dicentrarchus labrax (Linnaeus, 1758) gill pathology after experimental exposure to cadmium (Cd) and terbuthylazine (TBA) for 24 and 48h. An algorithm-derived local connected fractal dimension (LCFD) frequency measure was used in this comparative analysis. Canonical variates (CVA) and linear discriminant analysis (LDA) were used to evaluate the discrimination power of the method among exposure classes (unexposed, Cd exposed, TBA exposed). Misclassification, sensitivity and specificity, both with original and cross-validated cases, were determined. LCFDs frequencies enhanced the differences among classes which were visually selected after their means, respective variances and the differences between Cd and TBA exposed means, with respect to unexposed mean, were analyzed by scatter plots. Selected frequencies were then scanned by means of LDA, stepwise analysis, and Mahalanobis distance to detect the most discriminative frequencies out of ten originally selected. Discrimination resulted in 91.7% of cross-validated cases correctly classified (22 out of 24 total cases), with sensitivity and specificity, respectively, of 95.5% (1 false negative with respect to 21 really positive cases) and 75% (1 false positive with respect to 3 really negative cases). CVA with convex hull polygons ensured prompt, visually intuitive discrimination among exposure classes and graphically supported the false positive case. The combined use of semithin sections, which enhanced the visual evaluation of the overall lamellar structure; of LCFD analysis, which objectively detected local variation in complexity, without the possible bias connected to human personnel; and of CVA/LDA, could be an objective, sensitive and specific approach to study fish gill lamellar pathology. Furthermore this approach enabled discrimination with sufficient confidence between exposure classes or pathological states and avoided misdiagnosis. Copyright © 2016 Elsevier B.V. All rights reserved.

Temporal Lobe Epilepsy: Quantitative MR Volumetry in Detection of Hippocampal Atrophy

PubMed Central

Farid, Nikdokht; Girard, Holly M.; Kemmotsu, Nobuko; Smith, Michael E.; Magda, Sebastian W.; Lim, Wei Y.; Lee, Roland R.

2012-01-01

Purpose: To determine the ability of fully automated volumetric magnetic resonance (MR) imaging to depict hippocampal atrophy (HA) and to help correctly lateralize the seizure focus in patients with temporal lobe epilepsy (TLE). Materials and Methods: This study was conducted with institutional review board approval and in compliance with HIPAA regulations. Volumetric MR imaging data were analyzed for 34 patients with TLE and 116 control subjects. Structural volumes were calculated by using U.S. Food and Drug Administration–cleared software for automated quantitative MR imaging analysis (NeuroQuant). Results of quantitative MR imaging were compared with visual detection of atrophy, and, when available, with histologic specimens. Receiver operating characteristic analyses were performed to determine the optimal sensitivity and specificity of quantitative MR imaging for detecting HA and asymmetry. A linear classifier with cross validation was used to estimate the ability of quantitative MR imaging to help lateralize the seizure focus. Results: Quantitative MR imaging–derived hippocampal asymmetries discriminated patients with TLE from control subjects with high sensitivity (86.7%–89.5%) and specificity (92.2%–94.1%). When a linear classifier was used to discriminate left versus right TLE, hippocampal asymmetry achieved 94% classification accuracy. Volumetric asymmetries of other subcortical structures did not improve classification. Compared with invasive video electroencephalographic recordings, lateralization accuracy was 88% with quantitative MR imaging and 85% with visual inspection of volumetric MR imaging studies but only 76% with visual inspection of clinical MR imaging studies. Conclusion: Quantitative MR imaging can depict the presence and laterality of HA in TLE with accuracy rates that may exceed those achieved with visual inspection of clinical MR imaging studies. Thus, quantitative MR imaging may enhance standard visual analysis, providing a useful and viable means for translating volumetric analysis into clinical practice. © RSNA, 2012 Supplemental material: http://radiology.rsna.org/lookup/suppl/doi:10.1148/radiol.12112638/-/DC1 PMID:22723496

Combination of dynamic Bayesian network classifiers for the recognition of degraded characters

NASA Astrophysics Data System (ADS)

Likforman-Sulem, Laurence; Sigelle, Marc

2009-01-01

We investigate in this paper the combination of DBN (Dynamic Bayesian Network) classifiers, either independent or coupled, for the recognition of degraded characters. The independent classifiers are a vertical HMM and a horizontal HMM whose observable outputs are the image columns and the image rows respectively. The coupled classifiers, presented in a previous study, associate the vertical and horizontal observation streams into single DBNs. The scores of the independent and coupled classifiers are then combined linearly at the decision level. We compare the different classifiers -independent, coupled or linearly combined- on two tasks: the recognition of artificially degraded handwritten digits and the recognition of real degraded old printed characters. Our results show that coupled DBNs perform better on degraded characters than the linear combination of independent HMM scores. Our results also show that the best classifier is obtained by linearly combining the scores of the best coupled DBN and the best independent HMM.

A Predictive Model to Identify Patients With Fecal Incontinence Based on High-Definition Anorectal Manometry.

PubMed

Zifan, Ali; Ledgerwood-Lee, Melissa; Mittal, Ravinder K

2016-12-01

Three-dimensional high-definition anorectal manometry (3D-HDAM) is used to assess anal sphincter function; it determines profiles of regional pressure distribution along the length and circumference of the anal canal. There is no consensus, however, on the best way to analyze data from 3D-HDAM to distinguish healthy individuals from persons with sphincter dysfunction. We developed a computer analysis system to analyze 3D-HDAM data and to aid in the diagnosis and assessment of patients with fecal incontinence (FI). In a prospective study, we performed 3D-HDAM analysis of 24 asymptomatic healthy subjects (control subjects; all women; mean age, 39 ± 10 years) and 24 patients with symptoms of FI (all women; mean age, 58 ± 13 years). Patients completed a standardized questionnaire (FI severity index) to score the severity of FI symptoms. We developed and evaluated a robust prediction model to distinguish patients with FI from control subjects using linear discriminant, quadratic discriminant, and logistic regression analyses. In addition to collecting pressure information from the HDAM data, we assessed regional features based on shape characteristics and the anal sphincter pressure symmetry index. The combination of pressure values, anal sphincter area, and reflective symmetry values was identified in patients with FI versus control subjects with an area under the curve value of 1.0. In logistic regression analyses using different predictors, the model identified patients with FI with an area under the curve value of 0.96 (interquartile range, 0.22). In discriminant analysis, results were classified with a minimum error of 0.02, calculated using 10-fold cross-validation; different combinations of predictors produced median classification errors of 0.16 in linear discriminant analysis (interquartile range, 0.25) and 0.08 in quadratic discriminant analysis (interquartile range, 0.25). We developed and validated a novel prediction model to analyze 3D-HDAM data. This system can accurately distinguish patients with FI from control subjects. Copyright © 2016 AGA Institute. Published by Elsevier Inc. All rights reserved.

Epileptic Seizure Prediction Using Diffusion Distance and Bayesian Linear Discriminate Analysis on Intracranial EEG.

PubMed

Yuan, Shasha; Zhou, Weidong; Chen, Liyan

2018-02-01

Epilepsy is a chronic neurological disorder characterized by sudden and apparently unpredictable seizures. A system capable of forecasting the occurrence of seizures is crucial and could open new therapeutic possibilities for human health. This paper addresses an algorithm for seizure prediction using a novel feature - diffusion distance (DD) in intracranial Electroencephalograph (iEEG) recordings. Wavelet decomposition is conducted on segmented electroencephalograph (EEG) epochs and subband signals at scales 3, 4 and 5 are utilized to extract the diffusion distance. The features of all channels composing a feature vector are then fed into a Bayesian Linear Discriminant Analysis (BLDA) classifier. Finally, postprocessing procedure is applied to reduce false prediction alarms. The prediction method is evaluated on the public intracranial EEG dataset, which consists of 577.67[Formula: see text]h of intracranial EEG recordings from 21 patients with 87 seizures. We achieved a sensitivity of 85.11% for a seizure occurrence period of 30[Formula: see text]min and a sensitivity of 93.62% for a seizure occurrence period of 50[Formula: see text]min, both with the seizure prediction horizon of 10[Formula: see text]s. Our false prediction rate was 0.08/h. The proposed method yields a high sensitivity as well as a low false prediction rate, which demonstrates its potential for real-time prediction of seizures.

Discriminating the reaction types of plant type III polyketide synthases

PubMed Central

Shimizu, Yugo; Ogata, Hiroyuki; Goto, Susumu

2017-01-01

Abstract Motivation: Functional prediction of paralogs is challenging in bioinformatics because of rapid functional diversification after gene duplication events combined with parallel acquisitions of similar functions by different paralogs. Plant type III polyketide synthases (PKSs), producing various secondary metabolites, represent a paralogous family that has undergone gene duplication and functional alteration. Currently, there is no computational method available for the functional prediction of type III PKSs. Results: We developed a plant type III PKS reaction predictor, pPAP, based on the recently proposed classification of type III PKSs. pPAP combines two kinds of similarity measures: one calculated by profile hidden Markov models (pHMMs) built from functionally and structurally important partial sequence regions, and the other based on mutual information between residue positions. pPAP targets PKSs acting on ring-type starter substrates, and classifies their functions into four reaction types. The pHMM approach discriminated two reaction types with high accuracy (97.5%, 39/40), but its accuracy decreased when discriminating three reaction types (87.8%, 43/49). When combined with a correlation-based approach, all 49 PKSs were correctly discriminated, and pPAP was still highly accurate (91.4%, 64/70) even after adding other reaction types. These results suggest pPAP, which is based on linear discriminant analyses of similarity measures, is effective for plant type III PKS function prediction. Availability and Implementation: pPAP is freely available at ftp://ftp.genome.jp/pub/tools/ppap/ Contact: goto@kuicr.kyoto-u.ac.jp Supplementary information: Supplementary data are available at Bioinformatics online. PMID:28334262

Discrimination of irradiated MOX fuel from UOX fuel by multivariate statistical analysis of simulated activities of gamma-emitting isotopes

NASA Astrophysics Data System (ADS)

Åberg Lindell, M.; Andersson, P.; Grape, S.; Hellesen, C.; Håkansson, A.; Thulin, M.

2018-03-01

This paper investigates how concentrations of certain fission products and their related gamma-ray emissions can be used to discriminate between uranium oxide (UOX) and mixed oxide (MOX) type fuel. Discrimination of irradiated MOX fuel from irradiated UOX fuel is important in nuclear facilities and for transport of nuclear fuel, for purposes of both criticality safety and nuclear safeguards. Although facility operators keep records on the identity and properties of each fuel, tools for nuclear safeguards inspectors that enable independent verification of the fuel are critical in the recovery of continuity of knowledge, should it be lost. A discrimination methodology for classification of UOX and MOX fuel, based on passive gamma-ray spectroscopy data and multivariate analysis methods, is presented. Nuclear fuels and their gamma-ray emissions were simulated in the Monte Carlo code Serpent, and the resulting data was used as input to train seven different multivariate classification techniques. The trained classifiers were subsequently implemented and evaluated with respect to their capabilities to correctly predict the classes of unknown fuel items. The best results concerning successful discrimination of UOX and MOX-fuel were acquired when using non-linear classification techniques, such as the k nearest neighbors method and the Gaussian kernel support vector machine. For fuel with cooling times up to 20 years, when it is considered that gamma-rays from the isotope 134Cs can still be efficiently measured, success rates of 100% were obtained. A sensitivity analysis indicated that these methods were also robust.

Estimating a Logistic Discrimination Functions When One of the Training Samples Is Subject to Misclassification: A Maximum Likelihood Approach.

PubMed

Nagelkerke, Nico; Fidler, Vaclav

2015-01-01

The problem of discrimination and classification is central to much of epidemiology. Here we consider the estimation of a logistic regression/discrimination function from training samples, when one of the training samples is subject to misclassification or mislabeling, e.g. diseased individuals are incorrectly classified/labeled as healthy controls. We show that this leads to zero-inflated binomial model with a defective logistic regression or discrimination function, whose parameters can be estimated using standard statistical methods such as maximum likelihood. These parameters can be used to estimate the probability of true group membership among those, possibly erroneously, classified as controls. Two examples are analyzed and discussed. A simulation study explores properties of the maximum likelihood parameter estimates and the estimates of the number of mislabeled observations.

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

PubMed

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

2014-05-01

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

Blessing of dimensionality: mathematical foundations of the statistical physics of data.

PubMed

Gorban, A N; Tyukin, I Y

2018-04-28

The concentrations of measure phenomena were discovered as the mathematical background to statistical mechanics at the end of the nineteenth/beginning of the twentieth century and have been explored in mathematics ever since. At the beginning of the twenty-first century, it became clear that the proper utilization of these phenomena in machine learning might transform the curse of dimensionality into the blessing of dimensionality This paper summarizes recently discovered phenomena of measure concentration which drastically simplify some machine learning problems in high dimension, and allow us to correct legacy artificial intelligence systems. The classical concentration of measure theorems state that i.i.d. random points are concentrated in a thin layer near a surface (a sphere or equators of a sphere, an average or median-level set of energy or another Lipschitz function, etc.). The new stochastic separation theorems describe the thin structure of these thin layers: the random points are not only concentrated in a thin layer but are all linearly separable from the rest of the set, even for exponentially large random sets. The linear functionals for separation of points can be selected in the form of the linear Fisher's discriminant. All artificial intelligence systems make errors. Non-destructive correction requires separation of the situations (samples) with errors from the samples corresponding to correct behaviour by a simple and robust classifier. The stochastic separation theorems provide us with such classifiers and determine a non-iterative (one-shot) procedure for their construction.This article is part of the theme issue 'Hilbert's sixth problem'. © 2018 The Author(s).

Blessing of dimensionality: mathematical foundations of the statistical physics of data

NASA Astrophysics Data System (ADS)

Gorban, A. N.; Tyukin, I. Y.

2018-04-01

The concentrations of measure phenomena were discovered as the mathematical background to statistical mechanics at the end of the nineteenth/beginning of the twentieth century and have been explored in mathematics ever since. At the beginning of the twenty-first century, it became clear that the proper utilization of these phenomena in machine learning might transform the curse of dimensionality into the blessing of dimensionality. This paper summarizes recently discovered phenomena of measure concentration which drastically simplify some machine learning problems in high dimension, and allow us to correct legacy artificial intelligence systems. The classical concentration of measure theorems state that i.i.d. random points are concentrated in a thin layer near a surface (a sphere or equators of a sphere, an average or median-level set of energy or another Lipschitz function, etc.). The new stochastic separation theorems describe the thin structure of these thin layers: the random points are not only concentrated in a thin layer but are all linearly separable from the rest of the set, even for exponentially large random sets. The linear functionals for separation of points can be selected in the form of the linear Fisher's discriminant. All artificial intelligence systems make errors. Non-destructive correction requires separation of the situations (samples) with errors from the samples corresponding to correct behaviour by a simple and robust classifier. The stochastic separation theorems provide us with such classifiers and determine a non-iterative (one-shot) procedure for their construction. This article is part of the theme issue `Hilbert's sixth problem'.

Diagnosis of meningioma by time-resolved fluorescence spectroscopy.

PubMed

Butte, Pramod V; Pikul, Brian K; Hever, Aviv; Yong, William H; Black, Keith L; Marcu, Laura

2005-01-01

We investigate the use of time-resolved laser-induced fluorescence spectroscopy (TR-LIFS) as an adjunctive tool for the intraoperative rapid evaluation of tumor specimens and delineation of tumor from surrounding normal tissue. Tissue autofluorescence is induced with a pulsed nitrogen laser (337 nm, 1.2 ns) and the intensity decay profiles are recorded in the 370 to 500 nm spectral range with a fast digitizer (0.2 ns resolution). Experiments are conducted on excised specimens (meningioma, dura mater, cerebral cortex) from 26 patients (97 sites). Spectral intensities and time-dependent parameters derived from the time-resolved spectra of each site are used for tissue characterization. A linear discriminant analysis algorithm is used for tissue classification. Our results reveal that meningioma is characterized by unique fluorescence characteristics that enable discrimination of tumor from normal tissue with high sensitivity (>89%) and specificity (100%). The accuracy of classification is found to increase (92.8% cases in the training set and 91.8% in the cross-validated set correctly classified) when parameters from both the spectral and the time domain are used for discrimination. Our findings establish the feasibility of using TR-LIFS as a tool for the identification of meningiomas and enables further development of real-time diagnostic tools for analyzing surgical tissue specimens of meningioma or other brain tumors.

Diagnosis of meningioma by time-resolved fluorescence spectroscopy

PubMed Central

Butte, Pramod V.; Pikul, Brian K.; Hever, Aviv; Yong, William H.; Black, Keith L.; Marcu, Laura

2010-01-01

We investigate the use of time-resolved laser-induced fluorescence spectroscopy (TR-LIFS) as an adjunctive tool for the intraoperative rapid evaluation of tumor specimens and delineation of tumor from surrounding normal tissue. Tissue autofluorescence is induced with a pulsed nitrogen laser (337 nm, 1.2 ns) and the intensity decay profiles are recorded in the 370 to 500 nm spectral range with a fast digitizer (0.2 ns resolution). Experiments are conducted on excised specimens (meningioma, dura mater, cerebral cortex) from 26 patients (97 sites). Spectral intensities and time-dependent parameters derived from the time-resolved spectra of each site are used for tissue characterization. A linear discriminant analysis algorithm is used for tissue classification. Our results reveal that meningioma is characterized by unique fluorescence characteristics that enable discrimination of tumor from normal tissue with high sensitivity (>89%) and specificity (100%). The accuracy of classification is found to increase (92.8% cases in the training set and 91.8% in the cross-validated set correctly classified) when parameters from both the spectral and the time domain are used for discrimination. Our findings establish the feasibility of using TR-LIFS as a tool for the identification of meningiomas and enables further development of real-time diagnostic tools for analyzing surgical tissue specimens of meningioma or other brain tumors. PMID:16409091

Prestimulus alpha power predicts fidelity of sensory encoding in perceptual decision making.

PubMed

Lou, Bin; Li, Yun; Philiastides, Marios G; Sajda, Paul

2014-02-15

Pre-stimulus α power has been shown to correlate with the behavioral accuracy of perceptual decisions. In most cases, these correlations have been observed by comparing α power for different behavioral outcomes (e.g. correct vs incorrect trials). In this paper we investigate such covariation within the context of behaviorally-latent fluctuations in task-relevant post-stimulus neural activity. Specially we consider variations of pre-stimulus α power with post-stimulus EEG components in a two alternative forced choice visual discrimination task. EEG components, discriminative of stimulus class, are identified using a linear multivariate classifier and only the variability of the components for correct trials (regardless of stimulus class, and for nominally identical stimuli) are correlated with the corresponding pre-stimulus α power. We find a significant relationship between the mean and variance of the pre-stimulus α power and the variation of the trial-to-trial magnitude of an early post-stimulus EEG component. This relationship is not seen for a later EEG component that is also discriminative of stimulus class and which has been previously linked to the quality of evidence driving the decision process. Our results suggest that early perceptual representations, rather than temporally later neural correlates of the perceptual decision, are modulated by pre-stimulus state. © 2013 Elsevier Inc. All rights reserved.

Prestimulus alpha power predicts fidelity of sensory encoding in perceptual decision making

PubMed Central

Lou, Bin; Li, Yun; Philiastides, Marios G.; Sajda, Paul

2013-01-01

Pre-stimulus α power has been shown to correlate with the behavioral accuracy of perceptual decisions. In most cases, these correlations have been observed by comparing α power for different behavioral outcomes (e.g. correct vs incorrect trials). In this paper we investigate such covariation within the context of behaviorally-latent fluctuations in task-relevant post-stimulus neural activity. Specially we consider variations of pre-stimulus α power with post-stimulus EEG components in a two alternative forced choice visual discrimination task. EEG components, discriminative of stimulus class, are identified using a linear multivariate classifier and only the variability of the components for correct trials (regardless of stimulus class, and for nominally identical stimuli) are correlated with the corresponding pre-stimulus α power. We find a significant relationship between the mean and variance of the pre-stimulus α power and the variation of the trial-to-trial magnitude of an early post-stimulus EEG component. This relationship is not seen for a later EEG component that is also discriminative of stimulus class and which has been previously linked to the quality of evidence driving the decision process. Our results suggest that early perceptual representations, rather than temporally later neural correlates of the perceptual decision, are modulated by pre-stimulus state. PMID:24185020

A Comparative Study of Land Cover Classification by Using Multispectral and Texture Data

PubMed Central

Qadri, Salman; Khan, Dost Muhammad; Ahmad, Farooq; Qadri, Syed Furqan; Babar, Masroor Ellahi; Shahid, Muhammad; Ul-Rehman, Muzammil; Razzaq, Abdul; Shah Muhammad, Syed; Fahad, Muhammad; Ahmad, Sarfraz; Pervez, Muhammad Tariq; Naveed, Nasir; Aslam, Naeem; Jamil, Mutiullah; Rehmani, Ejaz Ahmad; Ahmad, Nazir; Akhtar Khan, Naeem

2016-01-01

The main objective of this study is to find out the importance of machine vision approach for the classification of five types of land cover data such as bare land, desert rangeland, green pasture, fertile cultivated land, and Sutlej river land. A novel spectra-statistical framework is designed to classify the subjective land cover data types accurately. Multispectral data of these land covers were acquired by using a handheld device named multispectral radiometer in the form of five spectral bands (blue, green, red, near infrared, and shortwave infrared) while texture data were acquired with a digital camera by the transformation of acquired images into 229 texture features for each image. The most discriminant 30 features of each image were obtained by integrating the three statistical features selection techniques such as Fisher, Probability of Error plus Average Correlation, and Mutual Information (F + PA + MI). Selected texture data clustering was verified by nonlinear discriminant analysis while linear discriminant analysis approach was applied for multispectral data. For classification, the texture and multispectral data were deployed to artificial neural network (ANN: n-class). By implementing a cross validation method (80-20), we received an accuracy of 91.332% for texture data and 96.40% for multispectral data, respectively. PMID:27376088

Online Learning for Classification of Alzheimer Disease based on Cortical Thickness and Hippocampal Shape Analysis.

PubMed

Lee, Ga-Young; Kim, Jeonghun; Kim, Ju Han; Kim, Kiwoong; Seong, Joon-Kyung

2014-01-01

Mobile healthcare applications are becoming a growing trend. Also, the prevalence of dementia in modern society is showing a steady growing trend. Among degenerative brain diseases that cause dementia, Alzheimer disease (AD) is the most common. The purpose of this study was to identify AD patients using magnetic resonance imaging in the mobile environment. We propose an incremental classification for mobile healthcare systems. Our classification method is based on incremental learning for AD diagnosis and AD prediction using the cortical thickness data and hippocampus shape. We constructed a classifier based on principal component analysis and linear discriminant analysis. We performed initial learning and mobile subject classification. Initial learning is the group learning part in our server. Our smartphone agent implements the mobile classification and shows various results. With use of cortical thickness data analysis alone, the discrimination accuracy was 87.33% (sensitivity 96.49% and specificity 64.33%). When cortical thickness data and hippocampal shape were analyzed together, the achieved accuracy was 87.52% (sensitivity 96.79% and specificity 63.24%). In this paper, we presented a classification method based on online learning for AD diagnosis by employing both cortical thickness data and hippocampal shape analysis data. Our method was implemented on smartphone devices and discriminated AD patients for normal group.

A computerized method for automated identification of erect posteroanterior and supine anteroposterior chest radiographs

NASA Astrophysics Data System (ADS)

Kao, E.-Fong; Lin, Wei-Chen; Hsu, Jui-Sheng; Chou, Ming-Chung; Jaw, Twei-Shiun; Liu, Gin-Chung

2011-12-01

A computerized scheme was developed for automated identification of erect posteroanterior (PA) and supine anteroposterior (AP) chest radiographs. The method was based on three features, the tilt angle of the scapula superior border, the tilt angle of the clavicle and the extent of radiolucence in lung fields, to identify the view of a chest radiograph. The three indices Ascapula, Aclavicle and Clung were determined from a chest image for the three features. Linear discriminant analysis was used to classify PA and AP chest images based on the three indices. The performance of the method was evaluated by receiver operating characteristic analysis. The proposed method was evaluated using a database of 600 PA and 600 AP chest radiographs. The discriminant performances Az of Ascapula, Aclavicle and Clung were 0.878 ± 0.010, 0.683 ± 0.015 and 0.962 ± 0.006, respectively. The combination of the three indices obtained an Az value of 0.979 ± 0.004. The results indicate that the combination of the three indices could yield high discriminant performance. The proposed method could provide radiologists with information about the view of chest radiographs for interpretation or could be used as a preprocessing step for analyzing chest images.

Feature extraction with deep neural networks by a generalized discriminant analysis.

PubMed

Stuhlsatz, André; Lippel, Jens; Zielke, Thomas

2012-04-01

We present an approach to feature extraction that is a generalization of the classical linear discriminant analysis (LDA) on the basis of deep neural networks (DNNs). As for LDA, discriminative features generated from independent Gaussian class conditionals are assumed. This modeling has the advantages that the intrinsic dimensionality of the feature space is bounded by the number of classes and that the optimal discriminant function is linear. Unfortunately, linear transformations are insufficient to extract optimal discriminative features from arbitrarily distributed raw measurements. The generalized discriminant analysis (GerDA) proposed in this paper uses nonlinear transformations that are learnt by DNNs in a semisupervised fashion. We show that the feature extraction based on our approach displays excellent performance on real-world recognition and detection tasks, such as handwritten digit recognition and face detection. In a series of experiments, we evaluate GerDA features with respect to dimensionality reduction, visualization, classification, and detection. Moreover, we show that GerDA DNNs can preprocess truly high-dimensional input data to low-dimensional representations that facilitate accurate predictions even if simple linear predictors or measures of similarity are used.

Analysis of Optimal Sequential State Discrimination for Linearly Independent Pure Quantum States.

PubMed

Namkung, Min; Kwon, Younghun

2018-04-25

Recently, J. A. Bergou et al. proposed sequential state discrimination as a new quantum state discrimination scheme. In the scheme, by the successful sequential discrimination of a qubit state, receivers Bob and Charlie can share the information of the qubit prepared by a sender Alice. A merit of the scheme is that a quantum channel is established between Bob and Charlie, but a classical communication is not allowed. In this report, we present a method for extending the original sequential state discrimination of two qubit states to a scheme of N linearly independent pure quantum states. Specifically, we obtain the conditions for the sequential state discrimination of N = 3 pure quantum states. We can analytically provide conditions when there is a special symmetry among N = 3 linearly independent pure quantum states. Additionally, we show that the scenario proposed in this study can be applied to quantum key distribution. Furthermore, we show that the sequential state discrimination of three qutrit states performs better than the strategy of probabilistic quantum cloning.

Impact of gluconic fermentation of strawberry using acetic acid bacteria on amino acids and biogenic amines profile.

PubMed

Ordóñez, J L; Sainz, F; Callejón, R M; Troncoso, A M; Torija, M J; García-Parrilla, M C

2015-07-01

This paper studies the amino acid profile of beverages obtained through the fermentation of strawberry purée by a surface culture using three strains belonging to different acetic acid bacteria species (one of Gluconobacter japonicus, one of Gluconobacter oxydans and one of Acetobacter malorum). An HPLC-UV method involving diethyl ethoxymethylenemalonate (DEEMM) was adapted and validated. From the entire set of 21 amino acids, multiple linear regressions showed that glutamine, alanine, arginine, tryptophan, GABA and proline were significantly related to the fermentation process. Furthermore, linear discriminant analysis classified 100% of the samples correctly in accordance with the microorganism involved. G. japonicus consumed glucose most quickly and achieved the greatest decrease in amino acid concentration. None of the 8 biogenic amines were detected in the final products, which could serve as a safety guarantee for these strawberry gluconic fermentation beverages, in this regard. Copyright © 2015 Elsevier Ltd. All rights reserved.

Kmeans-ICA based automatic method for ocular artifacts removal in a motorimagery classification.

PubMed

Bou Assi, Elie; Rihana, Sandy; Sawan, Mohamad

2014-01-01

Electroencephalogram (EEG) recordings aroused as inputs of a motor imagery based BCI system. Eye blinks contaminate the spectral frequency of the EEG signals. Independent Component Analysis (ICA) has been already proved for removing these artifacts whose frequency band overlap with the EEG of interest. However, already ICA developed methods, use a reference lead such as the ElectroOculoGram (EOG) to identify the ocular artifact components. In this study, artifactual components were identified using an adaptive thresholding by means of Kmeans clustering. The denoised EEG signals have been fed into a feature extraction algorithm extracting the band power, the coherence and the phase locking value and inserted into a linear discriminant analysis classifier for a motor imagery classification.

A control system for a powered prosthesis using positional and myoelectric inputs from the shoulder complex.

PubMed

Losier, Y; Englehart, K; Hudgins, B

2007-01-01

The integration of multiple input sources within a control strategy for powered upper limb prostheses could provide smoother, more intuitive multi-joint reaching movements based on the user's intended motion. The work presented in this paper presents the results of using myoelectric signals (MES) of the shoulder area in combination with the position of the shoulder as input sources to multiple linear discriminant analysis classifiers. Such an approach may provide users with control signals capable of controlling three degrees of freedom (DOF). This work is another important step in the development of hybrid systems that will enable simultaneous control of multiple degrees of freedom used for reaching tasks in a prosthetic limb.

Decoding emotional valence from electroencephalographic rhythmic activity.

PubMed

Celikkanat, Hande; Moriya, Hiroki; Ogawa, Takeshi; Kauppi, Jukka-Pekka; Kawanabe, Motoaki; Hyvarinen, Aapo

2017-07-01

We attempt to decode emotional valence from electroencephalographic rhythmic activity in a naturalistic setting. We employ a data-driven method developed in a previous study, Spectral Linear Discriminant Analysis, to discover the relationships between the classification task and independent neuronal sources, optimally utilizing multiple frequency bands. A detailed investigation of the classifier provides insight into the neuronal sources related with emotional valence, and the individual differences of the subjects in processing emotions. Our findings show: (1) sources whose locations are similar across subjects are consistently involved in emotional responses, with the involvement of parietal sources being especially significant, and (2) even though the locations of the involved neuronal sources are consistent, subjects can display highly varying degrees of valence-related EEG activity in the sources.

Harmonic wavelet packet transform for on-line system health diagnosis

NASA Astrophysics Data System (ADS)

Yan, Ruqiang; Gao, Robert X.

2004-07-01

This paper presents a new approach to on-line health diagnosis of mechanical systems, based on the wavelet packet transform. Specifically, signals acquired from vibration sensors are decomposed into sub-bands by means of the discrete harmonic wavelet packet transform (DHWPT). Based on the Fisher linear discriminant criterion, features in the selected sub-bands are then used as inputs to three classifiers (Nearest Neighbor rule-based and two Neural Network-based), for system health condition assessment. Experimental results have confirmed that, comparing to the conventional approach where statistical parameters from raw signals are used, the presented approach enabled higher signal-to-noise ratio for more effective and intelligent use of the sensory information, thus leading to more accurate system health diagnosis.

Recurrence quantification analysis and support vector machines for golf handicap and low back pain EMG classification.

PubMed

Silva, Luís; Vaz, João Rocha; Castro, Maria António; Serranho, Pedro; Cabri, Jan; Pezarat-Correia, Pedro

2015-08-01

The quantification of non-linear characteristics of electromyography (EMG) must contain information allowing to discriminate neuromuscular strategies during dynamic skills. There are a lack of studies about muscle coordination under motor constrains during dynamic contractions. In golf, both handicap (Hc) and low back pain (LBP) are the main factors associated with the occurrence of injuries. The aim of this study was to analyze the accuracy of support vector machines SVM on EMG-based classification to discriminate Hc (low and high handicap) and LBP (with and without LPB) in the main phases of golf swing. For this purpose recurrence quantification analysis (RQA) features of the trunk and the lower limb muscles were used to feed a SVM classifier. Recurrence rate (RR) and the ratio between determinism (DET) and RR showed a high discriminant power. The Hc accuracy for the swing, backswing, and downswing were 94.4±2.7%, 97.1±2.3%, and 95.3±2.6%, respectively. For LBP, the accuracy was 96.9±3.8% for the swing, and 99.7±0.4% in the backswing. External oblique (EO), biceps femoris (BF), semitendinosus (ST) and rectus femoris (RF) showed high accuracy depending on the laterality within the phase. RQA features and SVM showed a high muscle discriminant capacity within swing phases by Hc and by LBP. Low back pain golfers showed different neuromuscular coordination strategies when compared with asymptomatic. Copyright © 2015 Elsevier Ltd. All rights reserved.

Realistic Subsurface Anomaly Discrimination Using Electromagnetic Induction and an SVM Classifier

NASA Astrophysics Data System (ADS)

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

2010-12-01

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

Ethnicity identification from face images

NASA Astrophysics Data System (ADS)

Lu, Xiaoguang; Jain, Anil K.

2004-08-01

Human facial images provide the demographic information, such as ethnicity and gender. Conversely, ethnicity and gender also play an important role in face-related applications. Image-based ethnicity identification problem is addressed in a machine learning framework. The Linear Discriminant Analysis (LDA) based scheme is presented for the two-class (Asian vs. non-Asian) ethnicity classification task. Multiscale analysis is applied to the input facial images. An ensemble framework, which integrates the LDA analysis for the input face images at different scales, is proposed to further improve the classification performance. The product rule is used as the combination strategy in the ensemble. Experimental results based on a face database containing 263 subjects (2,630 face images, with equal balance between the two classes) are promising, indicating that LDA and the proposed ensemble framework have sufficient discriminative power for the ethnicity classification problem. The normalized ethnicity classification scores can be helpful in the facial identity recognition. Useful as a "soft" biometric, face matching scores can be updated based on the output of ethnicity classification module. In other words, ethnicity classifier does not have to be perfect to be useful in practice.

Discriminant analysis for fast multiclass data classification through regularized kernel function approximation.

PubMed

Ghorai, Santanu; Mukherjee, Anirban; Dutta, Pranab K

2010-06-01

In this brief we have proposed the multiclass data classification by computationally inexpensive discriminant analysis through vector-valued regularized kernel function approximation (VVRKFA). VVRKFA being an extension of fast regularized kernel function approximation (FRKFA), provides the vector-valued response at single step. The VVRKFA finds a linear operator and a bias vector by using a reduced kernel that maps a pattern from feature space into the low dimensional label space. The classification of patterns is carried out in this low dimensional label subspace. A test pattern is classified depending on its proximity to class centroids. The effectiveness of the proposed method is experimentally verified and compared with multiclass support vector machine (SVM) on several benchmark data sets as well as on gene microarray data for multi-category cancer classification. The results indicate the significant improvement in both training and testing time compared to that of multiclass SVM with comparable testing accuracy principally in large data sets. Experiments in this brief also serve as comparison of performance of VVRKFA with stratified random sampling and sub-sampling.

Discrimination thresholds of normal and anomalous trichromats: Model of senescent changes in ocular media density on the Cambridge Colour Test

PubMed Central

Shinomori, Keizo; Panorgias, Athanasios; Werner, John S.

2017-01-01

Age-related changes in chromatic discrimination along dichromatic confusion lines were measured with the Cambridge Colour Test (CCT). One hundred and sixty-two individuals (16 to 88 years old) with normal Rayleigh matches were the major focus of this paper. An additional 32 anomalous trichromats classified by their Rayleigh matches were also tested. All subjects were screened to rule out abnormalities of the anterior and posterior segments. Thresholds on all three chromatic vectors measured with the CCT showed age-related increases. Protan and deutan vector thresholds increased linearly with age while the tritan vector threshold was described with a bilinear model. Analysis and modeling demonstrated that the nominal vectors of the CCT are shifted by senescent changes in ocular media density, and a method for correcting the CCT vectors is demonstrated. A correction for these shifts indicates that classification among individuals of different ages is unaffected. New vector thresholds for elderly observers and for all age groups are suggested based on calculated tolerance limits. PMID:26974943

Nonnegative constraint analysis of key fluorophores within human breast cancer using native fluorescence spectroscopy excited by selective wavelength of 300 nm

NASA Astrophysics Data System (ADS)

Pu, Yang; Sordillo, Laura A.; Alfano, Robert R.

2015-03-01

Native fluorescence spectroscopy offers an important role in cancer discrimination. It is widely acknowledged that the emission spectrum of tissue is a superposition of spectra of various salient fluorophores. In this study, the native fluorescence spectra of human cancerous and normal breast tissues excited by selected wavelength of 300 nm are used to investigate the key building block fluorophores: tryptophan and reduced nicotinamide adenine dinucleotide (NADH). The basis spectra of these key fluorophores' contribution to the tissue emission spectra are obtained by nonnegative constraint analysis. The emission spectra of human cancerous and normal tissue samples are projected onto the fluorophore spectral subspace. Since previous studies indicate that tryptophan and NADH are key fluorophores related with tumor evolution, it is essential to obtain their information from tissue fluorescence but discard the redundancy. To evaluate the efficacy of for cancer detection, linear discriminant analysis (LDA) classifier is used to evaluate the sensitivity, and specificity. This research demonstrates that the native fluorescence spectroscopy measurements are effective to detect changes of fluorophores' compositions in tissues due to the development of cancer.

Quantifying heterogeneity of lesion uptake in dynamic contrast enhanced MRI for breast cancer diagnosis

NASA Astrophysics Data System (ADS)

Karahaliou, A.; Vassiou, K.; Skiadopoulos, S.; Kanavou, T.; Yiakoumelos, A.; Costaridou, L.

2009-07-01

The current study investigates whether texture features extracted from lesion kinetics feature maps can be used for breast cancer diagnosis. Fifty five women with 57 breast lesions (27 benign, 30 malignant) were subjected to dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) on 1.5T system. A linear-slope model was fitted pixel-wise to a representative lesion slice time series and fitted parameters were used to create three kinetic maps (wash out, time to peak enhancement and peak enhancement). 28 grey level co-occurrence matrices features were extracted from each lesion kinetic map. The ability of texture features per map in discriminating malignant from benign lesions was investigated using a Probabilistic Neural Network classifier. Additional classification was performed by combining classification outputs of most discriminating feature subsets from the three maps, via majority voting. The combined scheme outperformed classification based on individual maps achieving area under Receiver Operating Characteristics curve 0.960±0.029. Results suggest that heterogeneity of breast lesion kinetics, as quantified by texture analysis, may contribute to computer assisted tissue characterization in DCE-MRI.

Face-selective regions differ in their ability to classify facial expressions

PubMed Central

Zhang, Hui; Japee, Shruti; Nolan, Rachel; Chu, Carlton; Liu, Ning; Ungerleider, Leslie G

2016-01-01

Recognition of facial expressions is crucial for effective social interactions. Yet, the extent to which the various face-selective regions in the human brain classify different facial expressions remains unclear. We used functional magnetic resonance imaging (fMRI) and support vector machine pattern classification analysis to determine how well face-selective brain regions are able to decode different categories of facial expression. Subjects participated in a slow event-related fMRI experiment in which they were shown 32 face pictures, portraying four different expressions: neutral, fearful, angry, and happy and belonging to eight different identities. Our results showed that only the amygdala and the posterior superior temporal sulcus (STS) were able to accurately discriminate between these expressions, albeit in different ways: The amygdala discriminated fearful faces from non-fearful faces, whereas STS discriminated neutral from emotional (fearful, angry and happy) faces. In contrast to these findings on the classification of emotional expression, only the fusiform face area (FFA) and anterior inferior temporal cortex (aIT) could discriminate among the various facial identities. Further, the amygdala and STS were better than FFA and aIT at classifying expression, while FFA and aIT were better than the amygdala and STS at classifying identity. Taken together, our findings indicate that the decoding of facial emotion and facial identity occurs in different neural substrates: the amygdala and STS for the former and FFA and aIT for the latter. PMID:26826513

Face-selective regions differ in their ability to classify facial expressions.

PubMed

Zhang, Hui; Japee, Shruti; Nolan, Rachel; Chu, Carlton; Liu, Ning; Ungerleider, Leslie G

2016-04-15

Recognition of facial expressions is crucial for effective social interactions. Yet, the extent to which the various face-selective regions in the human brain classify different facial expressions remains unclear. We used functional magnetic resonance imaging (fMRI) and support vector machine pattern classification analysis to determine how well face-selective brain regions are able to decode different categories of facial expression. Subjects participated in a slow event-related fMRI experiment in which they were shown 32 face pictures, portraying four different expressions: neutral, fearful, angry, and happy and belonging to eight different identities. Our results showed that only the amygdala and the posterior superior temporal sulcus (STS) were able to accurately discriminate between these expressions, albeit in different ways: the amygdala discriminated fearful faces from non-fearful faces, whereas STS discriminated neutral from emotional (fearful, angry and happy) faces. In contrast to these findings on the classification of emotional expression, only the fusiform face area (FFA) and anterior inferior temporal cortex (aIT) could discriminate among the various facial identities. Further, the amygdala and STS were better than FFA and aIT at classifying expression, while FFA and aIT were better than the amygdala and STS at classifying identity. Taken together, our findings indicate that the decoding of facial emotion and facial identity occurs in different neural substrates: the amygdala and STS for the former and FFA and aIT for the latter. Published by Elsevier Inc.

Sex determination from the femur in Portuguese populations with classical and machine-learning classifiers.

PubMed

Curate, F; Umbelino, C; Perinha, A; Nogueira, C; Silva, A M; Cunha, E

2017-11-01

The assessment of sex is of paramount importance in the establishment of the biological profile of a skeletal individual. Femoral relevance for sex estimation is indisputable, particularly when other exceedingly dimorphic skeletal regions are missing. As such, this study intended to generate population-specific osteometric models for the estimation of sex with the femur and to compare the accuracy of the models obtained through classical and machine-learning classifiers. A set of 15 standard femoral measurements was acquired in a training sample (100 females; 100 males) from the Coimbra Identified Skeletal Collection (University of Coimbra, Portugal) and models for sex classification were produced with logistic regression (LR), linear discriminant analysis (LDA), support vector machines (SVM), and reduce error pruning trees (REPTree). Under cross-validation, univariable sectioning points generated with REPTree correctly estimated sex in 60.0-87.5% of cases (systematic error ranging from 0.0 to 37.0%), while multivariable models correctly classified sex in 84.0-92.5% of cases (bias from 0.0 to 7.0%). All models were assessed in a holdout sample (24 females; 34 males) from the 21st Century Identified Skeletal Collection (University of Coimbra, Portugal), with an allocation accuracy ranging from 56.9 to 86.2% (bias from 4.4 to 67.0%) in the univariable models, and from 84.5 to 89.7% (bias from 3.7 to 23.3%) in the multivariable models. This study makes available a detailed description of sexual dimorphism in femoral linear dimensions in two Portuguese identified skeletal samples, emphasizing the relevance of the femur for the estimation of sex in skeletal remains in diverse conditions of completeness and preservation. Copyright © 2017 Elsevier Ltd and Faculty of Forensic and Legal Medicine. All rights reserved.

Visual modifications on the P300 speller BCI paradigm

NASA Astrophysics Data System (ADS)

Salvaris, M.; Sepulveda, F.

2009-08-01

The best known P300 speller brain-computer interface (BCI) paradigm is the Farwell and Donchin paradigm. In this paper, various changes to the visual aspects of this protocol are explored as well as their effects on classification. Changes to the dimensions of the symbols, the distance between the symbols and the colours used were tested. The purpose of the present work was not to achieve the highest possible accuracy results, but to ascertain whether these simple modifications to the visual protocol will provide classification differences between them and what these differences will be. Eight subjects were used, with each subject carrying out a total of six different experiments. In each experiment, the user spelt a total of 39 characters. Two types of classifiers were trained and tested to determine whether the results were classifier dependant. These were a support vector machine (SVM) with a radial basis function (RBF) kernel and Fisher's linear discriminant (FLD). The single-trial classification results and multiple-trial classification results were recorded and compared. Although no visual protocol was the best for all subjects, the best performances, across both classifiers, were obtained with the white background (WB) visual protocol. The worst performance was obtained with the small symbol size (SSS) visual protocol.

Authenticity assessment of banknotes using portable near infrared spectrometer and chemometrics.

PubMed

da Silva Oliveira, Vanessa; Honorato, Ricardo Saldanha; Honorato, Fernanda Araújo; Pereira, Claudete Fernandes

2018-05-01

Spectra recorded using a portable near infrared (NIR) spectrometer, Soft Independent Modeling of Class Analogy (SIMCA) and Linear Discriminant Analysis (LDA) associated to Successive Projections Algorithm (SPA) models were applied to identify counterfeit and authentic Brazilian Real (R$20, R$50 and R$100) banknotes, enabling a simple field analysis. NIR spectra (950-1650nm) were recorded from seven different areas of the banknotes (two with fluorescent ink, one over watermark, three with intaglio printing process and one over the serial numbers with typography printing). SIMCA and SPA-LDA models were built using 1st derivative preprocessed spectral data from one of the intaglio areas. For the SIMCA models, all authentic (300) banknotes were correctly classified and the counterfeits (227) were not classified. For the two classes SPA-LDA models (authentic and counterfeit currencies), all the test samples were correctly classified into their respective class. The number of selected variables by SPA varied from two to nineteen for R$20, R$50 and R$100 currencies. These results show that the use of the portable near-infrared with SIMCA or SPA-LDA models can be a completely effective, fast, and non-destructive way to identify authenticity of banknotes as well as permitting field analysis. Copyright © 2018 Elsevier B.V. All rights reserved.

Face recognition system using multiple face model of hybrid Fourier feature under uncontrolled illumination variation.

PubMed

Hwang, Wonjun; Wang, Haitao; Kim, Hyunwoo; Kee, Seok-Cheol; Kim, Junmo

2011-04-01

The authors present a robust face recognition system for large-scale data sets taken under uncontrolled illumination variations. The proposed face recognition system consists of a novel illumination-insensitive preprocessing method, a hybrid Fourier-based facial feature extraction, and a score fusion scheme. First, in the preprocessing stage, a face image is transformed into an illumination-insensitive image, called an "integral normalized gradient image," by normalizing and integrating the smoothed gradients of a facial image. Then, for feature extraction of complementary classifiers, multiple face models based upon hybrid Fourier features are applied. The hybrid Fourier features are extracted from different Fourier domains in different frequency bandwidths, and then each feature is individually classified by linear discriminant analysis. In addition, multiple face models are generated by plural normalized face images that have different eye distances. Finally, to combine scores from multiple complementary classifiers, a log likelihood ratio-based score fusion scheme is applied. The proposed system using the face recognition grand challenge (FRGC) experimental protocols is evaluated; FRGC is a large available data set. Experimental results on the FRGC version 2.0 data sets have shown that the proposed method shows an average of 81.49% verification rate on 2-D face images under various environmental variations such as illumination changes, expression changes, and time elapses.

Global detection approach for clustered microcalcifications in mammograms using a deep learning network.

PubMed

Wang, Juan; Nishikawa, Robert M; Yang, Yongyi

2017-04-01

In computerized detection of clustered microcalcifications (MCs) from mammograms, the traditional approach is to apply a pattern detector to locate the presence of individual MCs, which are subsequently grouped into clusters. Such an approach is often susceptible to the occurrence of false positives (FPs) caused by local image patterns that resemble MCs. We investigate the feasibility of a direct detection approach to determining whether an image region contains clustered MCs or not. Toward this goal, we develop a deep convolutional neural network (CNN) as the classifier model to which the input consists of a large image window ([Formula: see text] in size). The multiple layers in the CNN classifier are trained to automatically extract image features relevant to MCs at different spatial scales. In the experiments, we demonstrated this approach on a dataset consisting of both screen-film mammograms and full-field digital mammograms. We evaluated the detection performance both on classifying image regions of clustered MCs using a receiver operating characteristic (ROC) analysis and on detecting clustered MCs from full mammograms by a free-response receiver operating characteristic analysis. For comparison, we also considered a recently developed MC detector with FP suppression. In classifying image regions of clustered MCs, the CNN classifier achieved 0.971 in the area under the ROC curve, compared to 0.944 for the MC detector. In detecting clustered MCs from full mammograms, at 90% sensitivity, the CNN classifier obtained an FP rate of 0.69 clusters/image, compared to 1.17 clusters/image by the MC detector. These results indicate that using global image features can be more effective in discriminating clustered MCs from FPs caused by various sources, such as linear structures, thereby providing a more accurate detection of clustered MCs on mammograms.

Predicting variations of perceptual performance across individuals from neural activity using pattern classifiers.

PubMed

Das, Koel; Giesbrecht, Barry; Eckstein, Miguel P

2010-07-15

Within the past decade computational approaches adopted from the field of machine learning have provided neuroscientists with powerful new tools for analyzing neural data. For instance, previous studies have applied pattern classification algorithms to electroencephalography data to predict the category of presented visual stimuli, human observer decision choices and task difficulty. Here, we quantitatively compare the ability of pattern classifiers and three ERP metrics (peak amplitude, mean amplitude, and onset latency of the face-selective N170) to predict variations across individuals' behavioral performance in a difficult perceptual task identifying images of faces and cars embedded in noise. We investigate three different pattern classifiers (Classwise Principal Component Analysis, CPCA; Linear Discriminant Analysis, LDA; and Support Vector Machine, SVM), five training methods differing in the selection of training data sets and three analyses procedures for the ERP measures. We show that all three pattern classifier algorithms surpass traditional ERP measurements in their ability to predict individual differences in performance. Although the differences across pattern classifiers were not large, the CPCA method with training data sets restricted to EEG activity for trials in which observers expressed high confidence about their decisions performed the highest at predicting perceptual performance of observers. We also show that the neural activity predicting the performance across individuals was distributed through time starting at 120ms, and unlike the face-selective ERP response, sustained for more than 400ms after stimulus presentation, indicating that both early and late components contain information correlated with observers' behavioral performance. Together, our results further demonstrate the potential of pattern classifiers compared to more traditional ERP techniques as an analysis tool for modeling spatiotemporal dynamics of the human brain and relating neural activity to behavior. Copyright 2010 Elsevier Inc. All rights reserved.

Real-data comparison of data mining methods in prediction of diabetes in iran.

PubMed

Tapak, Lily; Mahjub, Hossein; Hamidi, Omid; Poorolajal, Jalal

2013-09-01

Diabetes is one of the most common non-communicable diseases in developing countries. Early screening and diagnosis play an important role in effective prevention strategies. This study compared two traditional classification methods (logistic regression and Fisher linear discriminant analysis) and four machine-learning classifiers (neural networks, support vector machines, fuzzy c-mean, and random forests) to classify persons with and without diabetes. The data set used in this study included 6,500 subjects from the Iranian national non-communicable diseases risk factors surveillance obtained through a cross-sectional survey. The obtained sample was based on cluster sampling of the Iran population which was conducted in 2005-2009 to assess the prevalence of major non-communicable disease risk factors. Ten risk factors that are commonly associated with diabetes were selected to compare the performance of six classifiers in terms of sensitivity, specificity, total accuracy, and area under the receiver operating characteristic (ROC) curve criteria. Support vector machines showed the highest total accuracy (0.986) as well as area under the ROC (0.979). Also, this method showed high specificity (1.000) and sensitivity (0.820). All other methods produced total accuracy of more than 85%, but for all methods, the sensitivity values were very low (less than 0.350). The results of this study indicate that, in terms of sensitivity, specificity, and overall classification accuracy, the support vector machine model ranks first among all the classifiers tested in the prediction of diabetes. Therefore, this approach is a promising classifier for predicting diabetes, and it should be further investigated for the prediction of other diseases.

Molecular Signature for Lymphatic Invasion Associated with Survival of Epithelial Ovarian Cancer.

PubMed

Paik, E Sun; Choi, Hyun Jin; Kim, Tae-Joong; Lee, Jeong-Won; Kim, Byoung-Gie; Bae, Duk-Soo; Choi, Chel Hun

2018-04-01

We aimed to develop molecular classifier that can predict lymphatic invasion and their clinical significance in epithelial ovarian cancer (EOC) patients. We analyzed gene expression (mRNA, methylated DNA) in data from The Cancer Genome Atlas. To identify molecular signatures for lymphatic invasion, we found differentially expressed genes. The performance of classifier was validated by receiver operating characteristics analysis, logistic regression, linear discriminant analysis (LDA), and support vector machine (SVM). We assessed prognostic role of classifier using random survival forest (RSF) model and pathway deregulation score (PDS). For external validation,we analyzed microarray data from 26 EOC samples of Samsung Medical Center and curatedOvarianData database. We identified 21 mRNAs, and seven methylated DNAs from primary EOC tissues that predicted lymphatic invasion and created prognostic models. The classifier predicted lymphatic invasion well, which was validated by logistic regression, LDA, and SVM algorithm (C-index of 0.90, 0.71, and 0.74 for mRNA and C-index of 0.64, 0.68, and 0.69 for DNA methylation). Using RSF model, incorporating molecular data with clinical variables improved prediction of progression-free survival compared with using only clinical variables (p < 0.001 and p=0.008). Similarly, PDS enabled us to classify patients into high-risk and low-risk group, which resulted in survival difference in mRNA profiles (log-rank p-value=0.011). In external validation, gene signature was well correlated with prediction of lymphatic invasion and patients' survival. Molecular signature model predicting lymphatic invasion was well performed and also associated with survival of EOC patients.

29 CFR 1625.8 - Bona fide seniority systems.

Code of Federal Regulations, 2011 CFR

2011-07-01

... Regulations Relating to Labor (Continued) EQUAL EMPLOYMENT OPPORTUNITY COMMISSION AGE DISCRIMINATION IN... equitable allocation of available employment opportunities and prerogatives among younger and older workers... systems which segregate, classify, or otherwise discriminate against individuals on the basis of race...

29 CFR 1625.8 - Bona fide seniority systems.

Code of Federal Regulations, 2014 CFR

2014-07-01

... Regulations Relating to Labor (Continued) EQUAL EMPLOYMENT OPPORTUNITY COMMISSION AGE DISCRIMINATION IN... equitable allocation of available employment opportunities and prerogatives among younger and older workers... systems which segregate, classify, or otherwise discriminate against individuals on the basis of race...

29 CFR 1625.8 - Bona fide seniority systems.

Code of Federal Regulations, 2012 CFR

2012-07-01

... Regulations Relating to Labor (Continued) EQUAL EMPLOYMENT OPPORTUNITY COMMISSION AGE DISCRIMINATION IN... equitable allocation of available employment opportunities and prerogatives among younger and older workers... systems which segregate, classify, or otherwise discriminate against individuals on the basis of race...

29 CFR 1625.8 - Bona fide seniority systems.

Code of Federal Regulations, 2010 CFR

2010-07-01

... Regulations Relating to Labor (Continued) EQUAL EMPLOYMENT OPPORTUNITY COMMISSION AGE DISCRIMINATION IN... equitable allocation of available employment opportunities and prerogatives among younger and older workers... systems which segregate, classify, or otherwise discriminate against individuals on the basis of race...

29 CFR 1625.8 - Bona fide seniority systems.

Code of Federal Regulations, 2013 CFR

2013-07-01

... Regulations Relating to Labor (Continued) EQUAL EMPLOYMENT OPPORTUNITY COMMISSION AGE DISCRIMINATION IN... equitable allocation of available employment opportunities and prerogatives among younger and older workers... systems which segregate, classify, or otherwise discriminate against individuals on the basis of race...

Angular velocity discrimination

NASA Technical Reports Server (NTRS)

Kaiser, Mary K.

1990-01-01

Three experiments designed to investigate the ability of naive observers to discriminate rotational velocities of two simultaneously viewed objects are described. Rotations are constrained to occur about the x and y axes, resulting in linear two-dimensional image trajectories. The results indicate that observers can discriminate angular velocities with a competence near that for linear velocities. However, perceived angular rate is influenced by structural aspects of the stimuli.

Bias and Stability of Single Variable Classifiers for Feature Ranking and Selection

PubMed Central

Fakhraei, Shobeir; Soltanian-Zadeh, Hamid; Fotouhi, Farshad

2014-01-01

Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices. PMID:25177107

Bias and Stability of Single Variable Classifiers for Feature Ranking and Selection.

PubMed

Fakhraei, Shobeir; Soltanian-Zadeh, Hamid; Fotouhi, Farshad

2014-11-01

Feature rankings are often used for supervised dimension reduction especially when discriminating power of each feature is of interest, dimensionality of dataset is extremely high, or computational power is limited to perform more complicated methods. In practice, it is recommended to start dimension reduction via simple methods such as feature rankings before applying more complex approaches. Single Variable Classifier (SVC) ranking is a feature ranking based on the predictive performance of a classifier built using only a single feature. While benefiting from capabilities of classifiers, this ranking method is not as computationally intensive as wrappers. In this paper, we report the results of an extensive study on the bias and stability of such feature ranking method. We study whether the classifiers influence the SVC rankings or the discriminative power of features themselves has a dominant impact on the final rankings. We show the common intuition of using the same classifier for feature ranking and final classification does not always result in the best prediction performance. We then study if heterogeneous classifiers ensemble approaches provide more unbiased rankings and if they improve final classification performance. Furthermore, we calculate an empirical prediction performance loss for using the same classifier in SVC feature ranking and final classification from the optimal choices.

Luminance sticker based facial expression recognition using discrete wavelet transform for physically disabled persons.

PubMed

Nagarajan, R; Hariharan, M; Satiyan, M

2012-08-01

Developing tools to assist physically disabled and immobilized people through facial expression is a challenging area of research and has attracted many researchers recently. In this paper, luminance stickers based facial expression recognition is proposed. Recognition of facial expression is carried out by employing Discrete Wavelet Transform (DWT) as a feature extraction method. Different wavelet families with their different orders (db1 to db20, Coif1 to Coif 5 and Sym2 to Sym8) are utilized to investigate their performance in recognizing facial expression and to evaluate their computational time. Standard deviation is computed for the coefficients of first level of wavelet decomposition for every order of wavelet family. This standard deviation is used to form a set of feature vectors for classification. In this study, conventional validation and cross validation are performed to evaluate the efficiency of the suggested feature vectors. Three different classifiers namely Artificial Neural Network (ANN), k-Nearest Neighborhood (kNN) and Linear Discriminant Analysis (LDA) are used to classify a set of eight facial expressions. The experimental results demonstrate that the proposed method gives very promising classification accuracies.

Decoding magnetoencephalographic rhythmic activity using spectrospatial information.

PubMed

Kauppi, Jukka-Pekka; Parkkonen, Lauri; Hari, Riitta; Hyvärinen, Aapo

2013-12-01

We propose a new data-driven decoding method called Spectral Linear Discriminant Analysis (Spectral LDA) for the analysis of magnetoencephalography (MEG). The method allows investigation of changes in rhythmic neural activity as a result of different stimuli and tasks. The introduced classification model only assumes that each "brain state" can be characterized as a combination of neural sources, each of which shows rhythmic activity at one or several frequency bands. Furthermore, the model allows the oscillation frequencies to be different for each such state. We present decoding results from 9 subjects in a four-category classification problem defined by an experiment involving randomly alternating epochs of auditory, visual and tactile stimuli interspersed with rest periods. The performance of Spectral LDA was very competitive compared with four alternative classifiers based on different assumptions concerning the organization of rhythmic brain activity. In addition, the spectral and spatial patterns extracted automatically on the basis of trained classifiers showed that Spectral LDA offers a novel and interesting way of analyzing spectrospatial oscillatory neural activity across the brain. All the presented classification methods and visualization tools are freely available as a Matlab toolbox. © 2013.

[Study on application of SVM in prediction of coronary heart disease].

PubMed

Zhu, Yue; Wu, Jianghua; Fang, Ying

2013-12-01

Base on the data of blood pressure, plasma lipid, Glu and UA by physical test, Support Vector Machine (SVM) was applied to identify coronary heart disease (CHD) in patients and non-CHD individuals in south China population for guide of further prevention and treatment of the disease. Firstly, the SVM classifier was built using radial basis kernel function, liner kernel function and polynomial kernel function, respectively. Secondly, the SVM penalty factor C and kernel parameter sigma were optimized by particle swarm optimization (PSO) and then employed to diagnose and predict the CHD. By comparison with those from artificial neural network with the back propagation (BP) model, linear discriminant analysis, logistic regression method and non-optimized SVM, the overall results of our calculation demonstrated that the classification performance of optimized RBF-SVM model could be superior to other classifier algorithm with higher accuracy rate, sensitivity and specificity, which were 94.51%, 92.31% and 96.67%, respectively. So, it is well concluded that SVM could be used as a valid method for assisting diagnosis of CHD.

Distinguishing centrarchid genera by use of lateral line scales

USGS Publications Warehouse

Roberts, N.M.; Rabeni, C.F.; Stanovick, J.S.

2007-01-01

Predator-prey relations involving fishes are often evaluated using scales remaining in gut contents or feces. While several reliable keys help identify North American freshwater fish scales to the family level, none attempt to separate the family Centrarchidae to the genus level. Centrarchidae is of particular concern in the midwestern United States because it contains several popular sport fishes, such as smallmouth bass Micropterus dolomieu, largemouth bass M. salmoides, and rock bass Ambloplites rupestris, as well as less-sought-after species of sunfishes Lepomis spp. and crappies Pomoxis spp. Differentiating sport fish from non-sport fish has important management implications. Morphological characteristics of lateral line scales (n = 1,581) from known centrarchid fishes were analyzed. The variability of measurements within and between genera was examined to select variables that were the most useful in further classifying unknown centrarchid scales. A linear discriminant analysis model was developed using 10 variables. Based on this model, 84.4% of Ambloplites scales, 81.2% of Lepomis scales, and 86.6% of Micropterus scales were classified correctly using a jackknife procedure. ?? Copyright by the American Fisheries Society 2007.

A Locomotion Intent Prediction System Based on Multi-Sensor Fusion

PubMed Central

Chen, Baojun; Zheng, Enhao; Wang, Qining

2014-01-01

Locomotion intent prediction is essential for the control of powered lower-limb prostheses to realize smooth locomotion transitions. In this research, we develop a multi-sensor fusion based locomotion intent prediction system, which can recognize current locomotion mode and detect locomotion transitions in advance. Seven able-bodied subjects were recruited for this research. Signals from two foot pressure insoles and three inertial measurement units (one on the thigh, one on the shank and the other on the foot) are measured. A two-level recognition strategy is used for the recognition with linear discriminate classifier. Six kinds of locomotion modes and ten kinds of locomotion transitions are tested in this study. Recognition accuracy during steady locomotion periods (i.e., no locomotion transitions) is 99.71% ± 0.05% for seven able-bodied subjects. During locomotion transition periods, all the transitions are correctly detected and most of them can be detected before transiting to new locomotion modes. No significant deterioration in recognition performance is observed in the following five hours after the system is trained, and small number of experiment trials are required to train reliable classifiers. PMID:25014097

A locomotion intent prediction system based on multi-sensor fusion.

PubMed

Chen, Baojun; Zheng, Enhao; Wang, Qining

2014-07-10

Locomotion intent prediction is essential for the control of powered lower-limb prostheses to realize smooth locomotion transitions. In this research, we develop a multi-sensor fusion based locomotion intent prediction system, which can recognize current locomotion mode and detect locomotion transitions in advance. Seven able-bodied subjects were recruited for this research. Signals from two foot pressure insoles and three inertial measurement units (one on the thigh, one on the shank and the other on the foot) are measured. A two-level recognition strategy is used for the recognition with linear discriminate classifier. Six kinds of locomotion modes and ten kinds of locomotion transitions are tested in this study. Recognition accuracy during steady locomotion periods (i.e., no locomotion transitions) is 99.71% ± 0.05% for seven able-bodied subjects. During locomotion transition periods, all the transitions are correctly detected and most of them can be detected before transiting to new locomotion modes. No significant deterioration in recognition performance is observed in the following five hours after the system is trained, and small number of experiment trials are required to train reliable classifiers.

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.

Force Trends and Pulsatility for Catheter Contact Identification in Intracardiac Electrograms during Arrhythmia Ablation.

PubMed

Rivas-Lalaleo, David; Muñoz-Romero, Sergio; Huerta, Mónica; Erazo-Rodas, Mayra; Sánchez-Muñoz, Juan José; Rojo-Álvarez, José Luis; García-Alberola, Arcadi

2018-05-02

The intracardiac electrical activation maps are commonly used as a guide in the ablation of cardiac arrhythmias. The use of catheters with force sensors has been proposed in order to know if the electrode is in contact with the tissue during the registration of intracardiac electrograms (EGM). Although threshold criteria on force signals are often used to determine the catheter contact, this may be a limited criterion due to the complexity of the heart dynamics and cardiac vorticity. The present paper is devoted to determining the criteria and force signal profiles that guarantee the contact of the electrode with the tissue. In this study, we analyzed 1391 force signals and their associated EGM recorded during 2 and 8 s, respectively, in 17 patients (82 ± 60 points per patient). We aimed to establish a contact pattern by first visually examining and classifying the signals, according to their likely-contact joint profile and following the suggestions from experts in the doubtful cases. First, we used Principal Component Analysis to scrutinize the force signal dynamics by analyzing the main eigen-directions, first globally and then grouped according to the certainty of their tissue-catheter contact. Second, we used two different linear classifiers (Fisher discriminant and support vector machines) to identify the most relevant components of the previous signal models. We obtained three main types of eigenvectors, namely, pulsatile relevant, non-pulsatile relevant, and irrelevant components. The classifiers reached a moderate to sufficient discrimination capacity (areas under the curve between 0.84 and 0.95 depending on the contact certainty and on the classifier), which allowed us to analyze the relevant properties in the force signals. We conclude that the catheter-tissue contact profiles in force recordings are complex and do not depend only on the signal intensity being above a threshold at a single time instant, but also on time pulsatility and trends. These findings pave the way towards a subsystem which can be included in current intracardiac navigation systems assisted by force contact sensors, and it can provide the clinician with an estimate of the reliability on the tissue-catheter contact in the point-by-point EGM acquisition procedure.

Force Trends and Pulsatility for Catheter Contact Identification in Intracardiac Electrograms during Arrhythmia Ablation

PubMed Central

Muñoz-Romero, Sergio; Erazo-Rodas, Mayra; Sánchez-Muñoz, Juan José; García-Alberola, Arcadi

2018-01-01

The intracardiac electrical activation maps are commonly used as a guide in the ablation of cardiac arrhythmias. The use of catheters with force sensors has been proposed in order to know if the electrode is in contact with the tissue during the registration of intracardiac electrograms (EGM). Although threshold criteria on force signals are often used to determine the catheter contact, this may be a limited criterion due to the complexity of the heart dynamics and cardiac vorticity. The present paper is devoted to determining the criteria and force signal profiles that guarantee the contact of the electrode with the tissue. In this study, we analyzed 1391 force signals and their associated EGM recorded during 2 and 8 s, respectively, in 17 patients (82 ± 60 points per patient). We aimed to establish a contact pattern by first visually examining and classifying the signals, according to their likely-contact joint profile and following the suggestions from experts in the doubtful cases. First, we used Principal Component Analysis to scrutinize the force signal dynamics by analyzing the main eigen-directions, first globally and then grouped according to the certainty of their tissue-catheter contact. Second, we used two different linear classifiers (Fisher discriminant and support vector machines) to identify the most relevant components of the previous signal models. We obtained three main types of eigenvectors, namely, pulsatile relevant, non-pulsatile relevant, and irrelevant components. The classifiers reached a moderate to sufficient discrimination capacity (areas under the curve between 0.84 and 0.95 depending on the contact certainty and on the classifier), which allowed us to analyze the relevant properties in the force signals. We conclude that the catheter-tissue contact profiles in force recordings are complex and do not depend only on the signal intensity being above a threshold at a single time instant, but also on time pulsatility and trends. These findings pave the way towards a subsystem which can be included in current intracardiac navigation systems assisted by force contact sensors, and it can provide the clinician with an estimate of the reliability on the tissue-catheter contact in the point-by-point EGM acquisition procedure. PMID:29724033

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

PubMed

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

2014-11-01

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

Automatic staging of bladder cancer on CT urography

NASA Astrophysics Data System (ADS)

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

2016-03-01

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

Neural network classification of sweet potato embryos

NASA Astrophysics Data System (ADS)

Molto, Enrique; Harrell, Roy C.

1993-05-01

Somatic embryogenesis is a process that allows for the in vitro propagation of thousands of plants in sub-liter size vessels and has been successfully applied to many significant species. The heterogeneity of maturity and quality of embryos produced with this technique requires sorting to obtain a uniform product. An automated harvester is being developed at the University of Florida to sort embryos in vitro at different stages of maturation in a suspension culture. The system utilizes machine vision to characterize embryo morphology and a fluidic based separation device to isolate embryos associated with a pre-defined, targeted morphology. Two different backpropagation neural networks (BNN) were used to classify embryos based on information extracted from the vision system. One network utilized geometric features such as embryo area, length, and symmetry as inputs. The alternative network utilized polar coordinates of an embryo's perimeter with respect to its centroid as inputs. The performances of both techniques were compared with each other and with an embryo classification method based on linear discriminant analysis (LDA). Similar results were obtained with all three techniques. Classification efficiency was improved by reducing the dimension of the feature vector trough a forward stepwise analysis by LDA. In order to enhance the purity of the sample selected as harvestable, a reject to classify option was introduced in the model and analyzed. The best classifier performances (76% overall correct classifications, 75% harvestable objects properly classified, homogeneity improvement ratio 1.5) were obtained using 8 features in a BNN.

Prognostic Classifier Based on Genome-Wide DNA Methylation Profiling in Well-Differentiated Thyroid Tumors.

PubMed

Bisarro Dos Reis, Mariana; Barros-Filho, Mateus Camargo; Marchi, Fábio Albuquerque; Beltrami, Caroline Moraes; Kuasne, Hellen; Pinto, Clóvis Antônio Lopes; Ambatipudi, Srikant; Herceg, Zdenko; Kowalski, Luiz Paulo; Rogatto, Silvia Regina

2017-11-01

Even though the majority of well-differentiated thyroid carcinoma (WDTC) is indolent, a number of cases display an aggressive behavior. Cumulative evidence suggests that the deregulation of DNA methylation has the potential to point out molecular markers associated with worse prognosis. To identify a prognostic epigenetic signature in thyroid cancer. Genome-wide DNA methylation assays (450k platform, Illumina) were performed in a cohort of 50 nonneoplastic thyroid tissues (NTs), 17 benign thyroid lesions (BTLs), and 74 thyroid carcinomas (60 papillary, 8 follicular, 2 Hürthle cell, 1 poorly differentiated, and 3 anaplastic). A prognostic classifier for WDTC was developed via diagonal linear discriminant analysis. The results were compared with The Cancer Genome Atlas (TCGA) database. A specific epigenetic profile was detected according to each histological subtype. BTLs and follicular carcinomas showed a greater number of methylated CpG in comparison with NTs, whereas hypomethylation was predominant in papillary and undifferentiated carcinomas. A prognostic classifier based on 21 DNA methylation probes was able to predict poor outcome in patients with WDTC (sensitivity 63%, specificity 92% for internal data; sensitivity 64%, specificity 88% for TCGA data). High-risk score based on the classifier was considered an independent factor of poor outcome (Cox regression, P < 0.001). The methylation profile of thyroid lesions exhibited a specific signature according to the histological subtype. A meaningful algorithm composed of 21 probes was capable of predicting the recurrence in WDTC. Copyright © 2017 Endocrine Society

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

PubMed

Misimi, E; Erikson, U; Skavhaug, A

2008-06-01

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

Accurate Diabetes Risk Stratification Using Machine Learning: Role of Missing Value and Outliers.

PubMed

Maniruzzaman, Md; Rahman, Md Jahanur; Al-MehediHasan, Md; Suri, Harman S; Abedin, Md Menhazul; El-Baz, Ayman; Suri, Jasjit S

2018-04-10

Diabetes mellitus is a group of metabolic diseases in which blood sugar levels are too high. About 8.8% of the world was diabetic in 2017. It is projected that this will reach nearly 10% by 2045. The major challenge is that when machine learning-based classifiers are applied to such data sets for risk stratification, leads to lower performance. Thus, our objective is to develop an optimized and robust machine learning (ML) system under the assumption that missing values or outliers if replaced by a median configuration will yield higher risk stratification accuracy. This ML-based risk stratification is designed, optimized and evaluated, where: (i) the features are extracted and optimized from the six feature selection techniques (random forest, logistic regression, mutual information, principal component analysis, analysis of variance, and Fisher discriminant ratio) and combined with ten different types of classifiers (linear discriminant analysis, quadratic discriminant analysis, naïve Bayes, Gaussian process classification, support vector machine, artificial neural network, Adaboost, logistic regression, decision tree, and random forest) under the hypothesis that both missing values and outliers when replaced by computed medians will improve the risk stratification accuracy. Pima Indian diabetic dataset (768 patients: 268 diabetic and 500 controls) was used. Our results demonstrate that on replacing the missing values and outliers by group median and median values, respectively and further using the combination of random forest feature selection and random forest classification technique yields an accuracy, sensitivity, specificity, positive predictive value, negative predictive value and area under the curve as: 92.26%, 95.96%, 79.72%, 91.14%, 91.20%, and 0.93, respectively. This is an improvement of 10% over previously developed techniques published in literature. The system was validated for its stability and reliability. RF-based model showed the best performance when outliers are replaced by median values.

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

PubMed

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

2018-05-29

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

Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning.

PubMed

Wang, Jinhua; Yang, Xi; Cai, Hongmin; Tan, Wanchang; Jin, Cangzheng; Li, Li

2016-06-07

Microcalcification is an effective indicator of early breast cancer. To improve the diagnostic accuracy of microcalcifications, this study evaluates the performance of deep learning-based models on large datasets for its discrimination. A semi-automated segmentation method was used to characterize all microcalcifications. A discrimination classifier model was constructed to assess the accuracies of microcalcifications and breast masses, either in isolation or combination, for classifying breast lesions. Performances were compared to benchmark models. Our deep learning model achieved a discriminative accuracy of 87.3% if microcalcifications were characterized alone, compared to 85.8% with a support vector machine. The accuracies were 61.3% for both methods with masses alone and improved to 89.7% and 85.8% after the combined analysis with microcalcifications. Image segmentation with our deep learning model yielded 15, 26 and 41 features for the three scenarios, respectively. Overall, deep learning based on large datasets was superior to standard methods for the discrimination of microcalcifications. Accuracy was increased by adopting a combinatorial approach to detect microcalcifications and masses simultaneously. This may have clinical value for early detection and treatment of breast cancer.

Discrimination of Breast Cancer with Microcalcifications on Mammography by Deep Learning

PubMed Central

Wang, Jinhua; Yang, Xi; Cai, Hongmin; Tan, Wanchang; Jin, Cangzheng; Li, Li

2016-01-01

Microcalcification is an effective indicator of early breast cancer. To improve the diagnostic accuracy of microcalcifications, this study evaluates the performance of deep learning-based models on large datasets for its discrimination. A semi-automated segmentation method was used to characterize all microcalcifications. A discrimination classifier model was constructed to assess the accuracies of microcalcifications and breast masses, either in isolation or combination, for classifying breast lesions. Performances were compared to benchmark models. Our deep learning model achieved a discriminative accuracy of 87.3% if microcalcifications were characterized alone, compared to 85.8% with a support vector machine. The accuracies were 61.3% for both methods with masses alone and improved to 89.7% and 85.8% after the combined analysis with microcalcifications. Image segmentation with our deep learning model yielded 15, 26 and 41 features for the three scenarios, respectively. Overall, deep learning based on large datasets was superior to standard methods for the discrimination of microcalcifications. Accuracy was increased by adopting a combinatorial approach to detect microcalcifications and masses simultaneously. This may have clinical value for early detection and treatment of breast cancer. PMID:27273294

A Label Propagation Approach for Detecting Buried Objects in Handheld GPR Data

DTIC Science & Technology

2016-04-17

regions of interest that correspond to locations with anomalous signatures. Second, a classifier (or an ensemble of classifiers ) is used to assign a...investigated for almost two decades and several classifiers have been developed. Most of these methods are based on the supervised learning paradigm where...labeled target and clutter signatures are needed to train a classifier to discriminate between the two classes. Typically, large and diverse labeled

Decision Making Configurations: An Alternative to the Centralization/Decentralization Conceptualization.

ERIC Educational Resources Information Center

Cullen, John B.; Perrewe, Pamela L.

1981-01-01

Used factors identified in the literature as predictors of centralization/decentralization as potential discriminating variables among several decision making configurations in university affiliated professional schools. The model developed from multiple discriminant analysis had reasonable success in classifying correctly only the decentralized…

Aggression against Women by Men: Sexual and Spousal Assault.

ERIC Educational Resources Information Center

Dewhurst, Ann Marie; And Others

1992-01-01

Compared 19 sexual offenders, 22 batterers, 10 violent community comparison subjects, and 21 community comparison subjects on demographic, personality, and attitudinal variables. Discriminating variables correctly classified 75 percent of participants. Hostility toward women and depression were two best discriminating variables, suggesting that…

Classifying next-generation sequencing data using a zero-inflated Poisson model.

PubMed

Zhou, Yan; Wan, Xiang; Zhang, Baoxue; Tong, Tiejun

2018-04-15

With the development of high-throughput techniques, RNA-sequencing (RNA-seq) is becoming increasingly popular as an alternative for gene expression analysis, such as RNAs profiling and classification. Identifying which type of diseases a new patient belongs to with RNA-seq data has been recognized as a vital problem in medical research. As RNA-seq data are discrete, statistical methods developed for classifying microarray data cannot be readily applied for RNA-seq data classification. Witten proposed a Poisson linear discriminant analysis (PLDA) to classify the RNA-seq data in 2011. Note, however, that the count datasets are frequently characterized by excess zeros in real RNA-seq or microRNA sequence data (i.e. when the sequence depth is not enough or small RNAs with the length of 18-30 nucleotides). Therefore, it is desired to develop a new model to analyze RNA-seq data with an excess of zeros. In this paper, we propose a Zero-Inflated Poisson Logistic Discriminant Analysis (ZIPLDA) for RNA-seq data with an excess of zeros. The new method assumes that the data are from a mixture of two distributions: one is a point mass at zero, and the other follows a Poisson distribution. We then consider a logistic relation between the probability of observing zeros and the mean of the genes and the sequencing depth in the model. Simulation studies show that the proposed method performs better than, or at least as well as, the existing methods in a wide range of settings. Two real datasets including a breast cancer RNA-seq dataset and a microRNA-seq dataset are also analyzed, and they coincide with the simulation results that our proposed method outperforms the existing competitors. The software is available at http://www.math.hkbu.edu.hk/∼tongt. xwan@comp.hkbu.edu.hk or tongt@hkbu.edu.hk. Supplementary data are available at Bioinformatics online.

Automated classification of immunostaining patterns in breast tissue from the human protein atlas.

PubMed

Swamidoss, Issac Niwas; Kårsnäs, Andreas; Uhlmann, Virginie; Ponnusamy, Palanisamy; Kampf, Caroline; Simonsson, Martin; Wählby, Carolina; Strand, Robin

2013-01-01

The Human Protein Atlas (HPA) is an effort to map the location of all human proteins (http://www.proteinatlas.org/). It contains a large number of histological images of sections from human tissue. Tissue micro arrays (TMA) are imaged by a slide scanning microscope, and each image represents a thin slice of a tissue core with a dark brown antibody specific stain and a blue counter stain. When generating antibodies for protein profiling of the human proteome, an important step in the quality control is to compare staining patterns of different antibodies directed towards the same protein. This comparison is an ultimate control that the antibody recognizes the right protein. In this paper, we propose and evaluate different approaches for classifying sub-cellular antibody staining patterns in breast tissue samples. The proposed methods include the computation of various features including gray level co-occurrence matrix (GLCM) features, complex wavelet co-occurrence matrix (CWCM) features, and weighted neighbor distance using compound hierarchy of algorithms representing morphology (WND-CHARM)-inspired features. The extracted features are used into two different multivariate classifiers (support vector machine (SVM) and linear discriminant analysis (LDA) classifier). Before extracting features, we use color deconvolution to separate different tissue components, such as the brownly stained positive regions and the blue cellular regions, in the immuno-stained TMA images of breast tissue. We present classification results based on combinations of feature measurements. The proposed complex wavelet features and the WND-CHARM features have accuracy similar to that of a human expert. Both human experts and the proposed automated methods have difficulties discriminating between nuclear and cytoplasmic staining patterns. This is to a large extent due to mixed staining of nucleus and cytoplasm. Methods for quantification of staining patterns in histopathology have many applications, ranging from antibody quality control to tumor grading.

Multivariate Classification of Major Depressive Disorder Using the Effective Connectivity and Functional Connectivity

PubMed Central

Geng, Xiangfei; Xu, Junhai; Liu, Baolin; Shi, Yonggang

2018-01-01

Major depressive disorder (MDD) is a mental disorder characterized by at least 2 weeks of low mood, which is present across most situations. Diagnosis of MDD using rest-state functional magnetic resonance imaging (fMRI) data faces many challenges due to the high dimensionality, small samples, noisy and individual variability. To our best knowledge, no studies aim at classification with effective connectivity and functional connectivity measures between MDD patients and healthy controls. In this study, we performed a data-driving classification analysis using the whole brain connectivity measures which included the functional connectivity from two brain templates and effective connectivity measures created by the default mode network (DMN), dorsal attention network (DAN), frontal-parietal network (FPN), and silence network (SN). Effective connectivity measures were extracted using spectral Dynamic Causal Modeling (spDCM) and transformed into a vectorial feature space. Linear Support Vector Machine (linear SVM), non-linear SVM, k-Nearest Neighbor (KNN), and Logistic Regression (LR) were used as the classifiers to identify the differences between MDD patients and healthy controls. Our results showed that the highest accuracy achieved 91.67% (p < 0.0001) when using 19 effective connections and 89.36% when using 6,650 functional connections. The functional connections with high discriminative power were mainly located within or across the whole brain resting-state networks while the discriminative effective connections located in several specific regions, such as posterior cingulate cortex (PCC), ventromedial prefrontal cortex (vmPFC), dorsal cingulate cortex (dACC), and inferior parietal lobes (IPL). To further compare the discriminative power of functional connections and effective connections, a classification analysis only using the functional connections from those four networks was conducted and the highest accuracy achieved 78.33% (p < 0.0001). Our study demonstrated that the effective connectivity measures might play a more important role than functional connectivity in exploring the alterations between patients and health controls and afford a better mechanistic interpretability. Moreover, our results showed a diagnostic potential of the effective connectivity for the diagnosis of MDD patients with high accuracies allowing for earlier prevention or intervention. PMID:29515348

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

PubMed Central

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

2016-01-01

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

Protein linear indices of the 'macromolecular pseudograph alpha-carbon atom adjacency matrix' in bioinformatics. Part 1: prediction of protein stability effects of a complete set of alanine substitutions in Arc repressor.

PubMed

Marrero-Ponce, Yovani; Medina-Marrero, Ricardo; Castillo-Garit, Juan A; Romero-Zaldivar, Vicente; Torrens, Francisco; Castro, Eduardo A

2005-04-15

A novel approach to bio-macromolecular design from a linear algebra point of view is introduced. A protein's total (whole protein) and local (one or more amino acid) linear indices are a new set of bio-macromolecular descriptors of relevance to protein QSAR/QSPR studies. These amino-acid level biochemical descriptors are based on the calculation of linear maps on Rn[f k(xmi):Rn-->Rn] in canonical basis. These bio-macromolecular indices are calculated from the kth power of the macromolecular pseudograph alpha-carbon atom adjacency matrix. Total linear indices are linear functional on Rn. That is, the kth total linear indices are linear maps from Rn to the scalar R[f k(xm):Rn-->R]. Thus, the kth total linear indices are calculated by summing the amino-acid linear indices of all amino acids in the protein molecule. A study of the protein stability effects for a complete set of alanine substitutions in the Arc repressor illustrates this approach. A quantitative model that discriminates near wild-type stability alanine mutants from the reduced-stability ones in a training series was obtained. This model permitted the correct classification of 97.56% (40/41) and 91.67% (11/12) of proteins in the training and test set, respectively. It shows a high Matthews correlation coefficient (MCC=0.952) for the training set and an MCC=0.837 for the external prediction set. Additionally, canonical regression analysis corroborated the statistical quality of the classification model (Rcanc=0.824). This analysis was also used to compute biological stability canonical scores for each Arc alanine mutant. On the other hand, the linear piecewise regression model compared favorably with respect to the linear regression one on predicting the melting temperature (tm) of the Arc alanine mutants. The linear model explains almost 81% of the variance of the experimental tm (R=0.90 and s=4.29) and the LOO press statistics evidenced its predictive ability (q2=0.72 and scv=4.79). Moreover, the TOMOCOMD-CAMPS method produced a linear piecewise regression (R=0.97) between protein backbone descriptors and tm values for alanine mutants of the Arc repressor. A break-point value of 51.87 degrees C characterized two mutant clusters and coincided perfectly with the experimental scale. For this reason, we can use the linear discriminant analysis and piecewise models in combination to classify and predict the stability of the mutant Arc homodimers. These models also permitted the interpretation of the driving forces of such folding process, indicating that topologic/topographic protein backbone interactions control the stability profile of wild-type Arc and its alanine mutants.

Cluster-based exposure variation analysis

PubMed Central

2013-01-01

Background Static posture, repetitive movements and lack of physical variation are known risk factors for work-related musculoskeletal disorders, and thus needs to be properly assessed in occupational studies. The aims of this study were (i) to investigate the effectiveness of a conventional exposure variation analysis (EVA) in discriminating exposure time lines and (ii) to compare it with a new cluster-based method for analysis of exposure variation. Methods For this purpose, we simulated a repeated cyclic exposure varying within each cycle between “low” and “high” exposure levels in a “near” or “far” range, and with “low” or “high” velocities (exposure change rates). The duration of each cycle was also manipulated by selecting a “small” or “large” standard deviation of the cycle time. Theses parameters reflected three dimensions of exposure variation, i.e. range, frequency and temporal similarity. Each simulation trace included two realizations of 100 concatenated cycles with either low (ρ = 0.1), medium (ρ = 0.5) or high (ρ = 0.9) correlation between the realizations. These traces were analyzed by conventional EVA, and a novel cluster-based EVA (C-EVA). Principal component analysis (PCA) was applied on the marginal distributions of 1) the EVA of each of the realizations (univariate approach), 2) a combination of the EVA of both realizations (multivariate approach) and 3) C-EVA. The least number of principal components describing more than 90% of variability in each case was selected and the projection of marginal distributions along the selected principal component was calculated. A linear classifier was then applied to these projections to discriminate between the simulated exposure patterns, and the accuracy of classified realizations was determined. Results C-EVA classified exposures more correctly than univariate and multivariate EVA approaches; classification accuracy was 49%, 47% and 52% for EVA (univariate and multivariate), and C-EVA, respectively (p < 0.001). All three methods performed poorly in discriminating exposure patterns differing with respect to the variability in cycle time duration. Conclusion While C-EVA had a higher accuracy than conventional EVA, both failed to detect differences in temporal similarity. The data-driven optimality of data reduction and the capability of handling multiple exposure time lines in a single analysis are the advantages of the C-EVA. PMID:23557439

Discriminant forest classification method and system

DOEpatents

Chen, Barry Y.; Hanley, William G.; Lemmond, Tracy D.; Hiller, Lawrence J.; Knapp, David A.; Mugge, Marshall J.

2012-11-06

A hybrid machine learning methodology and system for classification that combines classical random forest (RF) methodology with discriminant analysis (DA) techniques to provide enhanced classification capability. A DA technique which uses feature measurements of an object to predict its class membership, such as linear discriminant analysis (LDA) or Andersen-Bahadur linear discriminant technique (AB), is used to split the data at each node in each of its classification trees to train and grow the trees and the forest. When training is finished, a set of n DA-based decision trees of a discriminant forest is produced for use in predicting the classification of new samples of unknown class.

Accuracy of Acoustic Analysis Measurements in the Evaluation of Patients With Different Laryngeal Diagnoses.

PubMed

Lopes, Leonardo Wanderley; Batista Simões, Layssa; Delfino da Silva, Jocélio; da Silva Evangelista, Deyverson; da Nóbrega E Ugulino, Ana Celiane; Oliveira Costa Silva, Priscila; Jefferson Dias Vieira, Vinícius

2017-05-01

This study aims to investigate the accuracy of acoustic measures in discriminating between patients with different laryngeal diagnoses. The study design is descriptive, cross-sectional, and retrospective. A total of 279 female patients participated in the research. Acoustic measures of the mean and standard deviation (SD) values of the fundamental frequency (F 0 ), jitter, shimmer, and glottal to noise excitation (GNE) were extracted from the emission of the vowel /ε/. Isolated acoustic measures do not demonstrate adequate performance in discriminating patients with and without laryngeal alteration. The combination of GNE, SD of the F 0 , jitter, and shimmer improved the ability to classify patients with and without laryngeal alteration. In isolation, the SD of the F 0 , shimmer, and GNE presented acceptable performance in discriminating individuals with different laryngeal diagnoses. The combination of acoustic measurements caused discrete improvement in performance of the classifier to discriminate healthy larynx vs vocal polyp (SD of the F 0 , shimmer, and GNE), healthy larynx vs unilateral vocal fold paralysis (SD of the F 0 and jitter), healthy larynx vs vocal nodules (SD of the F 0 and jitter), healthy larynx vs sulcus vocalis (SD of the F 0 and shimmer), and healthy larynx vs voice disorder due to gastroesophageal reflux (F 0 mean, jitter, and shimmer). Isolated acoustic measures do not demonstrate adequate performance in discriminating patients with and without laryngeal alteration, although they present acceptable performance in classifying different laryngeal diagnoses. Combined acoustic measures present an acceptable capacity to discriminate between the presence and the absence of laryngeal alteration and to differentiate several laryngeal diagnoses. Copyright © 2017 The Voice Foundation. Published by Elsevier Inc. All rights reserved.

Characterizing Computer Access Using a One-Channel EEG Wireless Sensor

PubMed Central

Guerrero-Cubero, Jaime; Gómez-González, Isabel M.; Merino-Monge, Manuel; Silva-Silva, Juan I.

2017-01-01

This work studies the feasibility of using mental attention to access a computer. Brain activity was measured with an electrode placed at the Fp1 position and the reference on the left ear; seven normally developed people and three subjects with cerebral palsy (CP) took part in the experimentation. They were asked to keep their attention high and low for as long as possible during several trials. We recorded attention levels and power bands conveyed by the sensor, but only the first was used for feedback purposes. All of the information was statistically analyzed to find the most significant parameters and a classifier based on linear discriminant analysis (LDA) was also set up. In addition, 60% of the participants were potential users of this technology with an accuracy of over 70%. Including power bands in the classifier did not improve the accuracy in discriminating between the two attentional states. For most people, the best results were obtained by using only the attention indicator in classification. Tiredness was higher in the group with disabilities (2.7 in a scale of 3) than in the other (1.5 in the same scale); and modulating the attention to access a communication board requires that it does not contain many pictograms (between 4 and 7) on screen and has a scanning period of a relatively high tscan≈ 10 s. The information transfer rate (ITR) is similar to the one obtained by other brain computer interfaces (BCI), like those based on sensorimotor rhythms (SMR) or slow cortical potentials (SCP), and makes it suitable as an eye-gaze independent BCI. PMID:28661425

Structures of the recurrence plot of heart rate variability signal as a tool for predicting the onset of paroxysmal atrial fibrillation.

PubMed

Mohebbi, Maryam; Ghassemian, Hassan; Asl, Babak Mohammadzadeh

2011-05-01

This paper aims to propose an effective paroxysmal atrial fibrillation (PAF) predictor which is based on the analysis of the heart rate variability (HRV) signal. Predicting the onset of PAF, based on non-invasive techniques, is clinically important and can be invaluable in order to avoid useless therapeutic interventions and to minimize the risks for the patients. This method consists of four steps: Preprocessing, feature extraction, feature reduction, and classification. In the first step, the QRS complexes are detected from the electrocardiogram (ECG) signal and then the HRV signal is extracted. In the next step, the recurrence plot (RP) of HRV signal is obtained and six features are extracted to characterize the basic patterns of the RP. These features consist of length of longest diagonal segments, average length of the diagonal lines, entropy, trapping time, length of longest vertical line, and recurrence trend. In the third step, these features are reduced to three features by the linear discriminant analysis (LDA) technique. Using LDA not only reduces the number of the input features, but also increases the classification accuracy by selecting the most discriminating features. Finally, a support vector machine-based classifier is used to classify the HRV signals. The performance of the proposed method in prediction of PAF episodes was evaluated using the Atrial Fibrillation Prediction Database which consists of both 30-minutes ECG recordings end just prior to the onset of PAF and segments at least 45 min distant from any PAF events. The obtained sensitivity, specificity, and positive predictivity were 96.55%, 100%, and 100%, respectively.

Disrupted white matter connectivity underlying developmental dyslexia: A machine learning approach.

PubMed

Cui, Zaixu; Xia, Zhichao; Su, Mengmeng; Shu, Hua; Gong, Gaolang

2016-04-01

Developmental dyslexia has been hypothesized to result from multiple causes and exhibit multiple manifestations, implying a distributed multidimensional effect on human brain. The disruption of specific white-matter (WM) tracts/regions has been observed in dyslexic children. However, it remains unknown if developmental dyslexia affects the human brain WM in a multidimensional manner. Being a natural tool for evaluating this hypothesis, the multivariate machine learning approach was applied in this study to compare 28 school-aged dyslexic children with 33 age-matched controls. Structural magnetic resonance imaging (MRI) and diffusion tensor imaging were acquired to extract five multitype WM features at a regional level: white matter volume, fractional anisotropy, mean diffusivity, axial diffusivity, and radial diffusivity. A linear support vector machine (LSVM) classifier achieved an accuracy of 83.61% using these MRI features to distinguish dyslexic children from controls. Notably, the most discriminative features that contributed to the classification were primarily associated with WM regions within the putative reading network/system (e.g., the superior longitudinal fasciculus, inferior fronto-occipital fasciculus, thalamocortical projections, and corpus callosum), the limbic system (e.g., the cingulum and fornix), and the motor system (e.g., the cerebellar peduncle, corona radiata, and corticospinal tract). These results were well replicated using a logistic regression classifier. These findings provided direct evidence supporting a multidimensional effect of developmental dyslexia on WM connectivity of human brain, and highlighted the involvement of WM tracts/regions beyond the well-recognized reading system in dyslexia. Finally, the discriminating results demonstrated a potential of WM neuroimaging features as imaging markers for identifying dyslexic individuals. © 2016 Wiley Periodicals, Inc.

Characterizing Computer Access Using a One-Channel EEG Wireless Sensor.

PubMed

Molina-Cantero, Alberto J; Guerrero-Cubero, Jaime; Gómez-González, Isabel M; Merino-Monge, Manuel; Silva-Silva, Juan I

2017-06-29

This work studies the feasibility of using mental attention to access a computer. Brain activity was measured with an electrode placed at the Fp1 position and the reference on the left ear; seven normally developed people and three subjects with cerebral palsy (CP) took part in the experimentation. They were asked to keep their attention high and low for as long as possible during several trials. We recorded attention levels and power bands conveyed by the sensor, but only the first was used for feedback purposes. All of the information was statistically analyzed to find the most significant parameters and a classifier based on linear discriminant analysis (LDA) was also set up. In addition, 60% of the participants were potential users of this technology with an accuracy of over 70%. Including power bands in the classifier did not improve the accuracy in discriminating between the two attentional states. For most people, the best results were obtained by using only the attention indicator in classification. Tiredness was higher in the group with disabilities (2.7 in a scale of 3) than in the other (1.5 in the same scale); and modulating the attention to access a communication board requires that it does not contain many pictograms (between 4 and 7) on screen and has a scanning period of a relatively high t s c a n ≈ 10 s. The information transfer rate (ITR) is similar to the one obtained by other brain computer interfaces (BCI), like those based on sensorimotor rhythms (SMR) or slow cortical potentials (SCP), and makes it suitable as an eye-gaze independent BCI.

Diagnosis of human prostate carcinoma cancer stem cells enriched from DU145 cell lines changes with microscopic texture analysis in radiation and hyperthermia treatment using run-length matrix.

PubMed

Abbasian Ardakani, Ali; Rajaee, Jila; Khoei, Samideh

2017-11-01

Hyperthermia and radiation have the ability to induce structural and morphological changes on both macroscopic and microscopic level. Normal and damage cells have a different texture but may be perceived by human eye, as having the same texture. To explore the potential of texture analysis based on run-length matrix, a total of 32 sphere images for each group and treatment regime were used in this study. Cells were subjected to the treatment with different doses of 6 MeV electron radiation (0 2, 4 and 6 Gy), hyperthermia (at 43° C in 0, 30, 60 and 90 min) and radiation + hyperthermia (at 43 °C in 30 min with 2, 4 and 6 Gy dose), respectively. Twenty run-length matrix (RLM) features were extracted as descriptors for each selected region of interest for texture analysis. Linear discriminant analysis was employed to transform raw data to lower-dimensional spaces and increase discriminative power. The features were classified by the first nearest neighbor classifier. RLM features represented the best performance with sensitivity, specificity, accuracy, positive predictive value (PPV) and negative predictive value (NPV) of 100% between 0 and 6 Gy radiation, 0 and 6 Gy radiation + hyperthermia, 0 and 90 min and 30 and 90 min hyperthermia groups. The area under receiver operating characteristic curve was 1 for these groups. RLM features have a high potential to characterize cell changes during different treatment regimes.

Linear Discriminant Analysis on a Spreadsheet.

ERIC Educational Resources Information Center

Busbey, Arthur Bresnahan III

1989-01-01

Described is a software package, "Trapeze," within which a routine called LinDis can be used. Discussed are teaching methods, the linear discriminant model and equations, the LinDis worksheet, and an example. The set up for this routine is included. (CW)

Discrimination of Clover and Citrus Honeys from Egypt According to Floral Type Using Easily Assessable Physicochemical Parameters and Discriminant Analysis: An External Validation of the Chemometric Approach.

PubMed

Karabagias, Ioannis K; Karabournioti, Sofia

2018-05-03

Twenty-two honey samples, namely clover and citrus honeys, were collected from the greater Cairo area during the harvesting year 2014⁻2015. The main purpose of the present study was to characterize the aforementioned honey types and to investigate whether the use of easily assessable physicochemical parameters, including color attributes in combination with chemometrics, could differentiate honey floral origin. Parameters taken into account were: pH, electrical conductivity, ash, free acidity, lactonic acidity, total acidity, moisture content, total sugars (degrees Brix-°Bx), total dissolved solids and their ratio to total acidity, salinity, CIELAB color parameters, along with browning index values. Results showed that all honey samples analyzed met the European quality standards set for honey and had variations in the aforementioned physicochemical parameters depending on floral origin. Application of linear discriminant analysis showed that eight physicochemical parameters, including color, could classify Egyptian honeys according to floral origin ( p < 0.05). Correct classification rate was 95.5% using the original method and 90.9% using the cross validation method. The discriminatory ability of the developed model was further validated using unknown honey samples. The overall correct classification rate was not affected. Specific physicochemical parameter analysis in combination with chemometrics has the potential to enhance the differences in floral honeys produced in a given geographical zone.

Discrimination of Clover and Citrus Honeys from Egypt According to Floral Type Using Easily Assessable Physicochemical Parameters and Discriminant Analysis: An External Validation of the Chemometric Approach

PubMed Central

Karabournioti, Sofia

2018-01-01

Twenty-two honey samples, namely clover and citrus honeys, were collected from the greater Cairo area during the harvesting year 2014–2015. The main purpose of the present study was to characterize the aforementioned honey types and to investigate whether the use of easily assessable physicochemical parameters, including color attributes in combination with chemometrics, could differentiate honey floral origin. Parameters taken into account were: pH, electrical conductivity, ash, free acidity, lactonic acidity, total acidity, moisture content, total sugars (degrees Brix-°Bx), total dissolved solids and their ratio to total acidity, salinity, CIELAB color parameters, along with browning index values. Results showed that all honey samples analyzed met the European quality standards set for honey and had variations in the aforementioned physicochemical parameters depending on floral origin. Application of linear discriminant analysis showed that eight physicochemical parameters, including color, could classify Egyptian honeys according to floral origin (p < 0.05). Correct classification rate was 95.5% using the original method and 90.9% using the cross validation method. The discriminatory ability of the developed model was further validated using unknown honey samples. The overall correct classification rate was not affected. Specific physicochemical parameter analysis in combination with chemometrics has the potential to enhance the differences in floral honeys produced in a given geographical zone. PMID:29751543

Smoke detection

DOEpatents

Warmack, Robert J. Bruce; Wolf, Dennis A.; Frank, Steven Shane

2016-09-06

Various apparatus and methods for smoke detection are disclosed. In one embodiment, a method of training a classifier for a smoke detector comprises inputting sensor data from a plurality of tests into a processor. The sensor data is processed to generate derived signal data corresponding to the test data for respective tests. The derived signal data is assigned into categories comprising at least one fire group and at least one non-fire group. Linear discriminant analysis (LDA) training is performed by the processor. The derived signal data and the assigned categories for the derived signal data are inputs to the LDA training. The output of the LDA training is stored in a computer readable medium, such as in a smoke detector that uses LDA to determine, based on the training, whether present conditions indicate the existence of a fire.

Smoke detection

DOEpatents

Warmack, Robert J. Bruce; Wolf, Dennis A.; Frank, Steven Shane

2015-10-27

Various apparatus and methods for smoke detection are disclosed. In one embodiment, a method of training a classifier for a smoke detector comprises inputting sensor data from a plurality of tests into a processor. The sensor data is processed to generate derived signal data corresponding to the test data for respective tests. The derived signal data is assigned into categories comprising at least one fire group and at least one non-fire group. Linear discriminant analysis (LDA) training is performed by the processor. The derived signal data and the assigned categories for the derived signal data are inputs to the LDA training. The output of the LDA training is stored in a computer readable medium, such as in a smoke detector that uses LDA to determine, based on the training, whether present conditions indicate the existence of a fire.

Supervised learning with decision margins in pools of spiking neurons.

PubMed

Le Mouel, Charlotte; Harris, Kenneth D; Yger, Pierre

2014-10-01

Learning to categorise sensory inputs by generalising from a few examples whose category is precisely known is a crucial step for the brain to produce appropriate behavioural responses. At the neuronal level, this may be performed by adaptation of synaptic weights under the influence of a training signal, in order to group spiking patterns impinging on the neuron. Here we describe a framework that allows spiking neurons to perform such "supervised learning", using principles similar to the Support Vector Machine, a well-established and robust classifier. Using a hinge-loss error function, we show that requesting a margin similar to that of the SVM improves performance on linearly non-separable problems. Moreover, we show that using pools of neurons to discriminate categories can also increase the performance by sharing the load among neurons.

Integrated Sensing Processor, Phase 2

DTIC Science & Technology

2005-12-01

performance analysis for several baseline classifiers including neural nets, linear classifiers, and kNN classifiers. Use of CCDR as a preprocessing step...below the level of the benchmark non-linear classifier for this problem ( kNN ). Furthermore, the CCDR preconditioned kNN achieved a 10% improvement over...the benchmark kNN without CCDR. Finally, we found an important connection between intrinsic dimension estimation via entropic graphs and the optimal

Statistical classification techniques for engineering and climatic data samples

NASA Technical Reports Server (NTRS)

Temple, E. C.; Shipman, J. R.

1981-01-01

Fisher's sample linear discriminant function is modified through an appropriate alteration of the common sample variance-covariance matrix. The alteration consists of adding nonnegative values to the eigenvalues of the sample variance covariance matrix. The desired results of this modification is to increase the number of correct classifications by the new linear discriminant function over Fisher's function. This study is limited to the two-group discriminant problem.

Comparison of Classifiers for Decoding Sensory and Cognitive Information from Prefrontal Neuronal Populations

PubMed Central

Astrand, Elaine; Enel, Pierre; Ibos, Guilhem; Dominey, Peter Ford; Baraduc, Pierre; Ben Hamed, Suliann

2014-01-01

Decoding neuronal information is important in neuroscience, both as a basic means to understand how neuronal activity is related to cerebral function and as a processing stage in driving neuroprosthetic effectors. Here, we compare the readout performance of six commonly used classifiers at decoding two different variables encoded by the spiking activity of the non-human primate frontal eye fields (FEF): the spatial position of a visual cue, and the instructed orientation of the animal's attention. While the first variable is exogenously driven by the environment, the second variable corresponds to the interpretation of the instruction conveyed by the cue; it is endogenously driven and corresponds to the output of internal cognitive operations performed on the visual attributes of the cue. These two variables were decoded using either a regularized optimal linear estimator in its explicit formulation, an optimal linear artificial neural network estimator, a non-linear artificial neural network estimator, a non-linear naïve Bayesian estimator, a non-linear Reservoir recurrent network classifier or a non-linear Support Vector Machine classifier. Our results suggest that endogenous information such as the orientation of attention can be decoded from the FEF with the same accuracy as exogenous visual information. All classifiers did not behave equally in the face of population size and heterogeneity, the available training and testing trials, the subject's behavior and the temporal structure of the variable of interest. In most situations, the regularized optimal linear estimator and the non-linear Support Vector Machine classifiers outperformed the other tested decoders. PMID:24466019

The use of wavelength dispersive X-ray fluorescence in the identification of the elemental composition of vanilla samples and the determination of the geographic origin by discriminant function analysis.

PubMed

Hondrogiannis, Ellen; Rotta, Kathryn; Zapf, Charles M

2013-03-01

Sixteen elements found in 37 vanilla samples from Madagascar, Uganda, India, Indonesia (all Vanilla planifolia species), and Papa New Guinea (Vanilla tahitensis species) were measured by wavelength dispersive X-ray fluorescence (WDXRF) spectroscopy for the purpose of determining the elemental concentrations to discriminate among the origins. Pellets were prepared of the samples and elemental concentrations were calculated based on calibration curves created using 4 Natl. Inst. of Standards and Technology (NIST) standards. Discriminant analysis was used to successfully classify the vanilla samples by their species and their geographical region. Our method allows for higher throughput in the rapid screening of vanilla samples in less time than analytical methods currently available. Wavelength dispersive X-ray fluorescence spectroscopy and discriminant function analysis were used to classify vanilla from different origins resulting in a model that could potentially serve to rapidly validate these samples before purchasing from a producer. © 2013 Institute of Food Technologists®

Linear discriminant analysis with misallocation in training samples

NASA Technical Reports Server (NTRS)

Chhikara, R. (Principal Investigator); Mckeon, J.

1982-01-01

Linear discriminant analysis for a two-class case is studied in the presence of misallocation in training samples. A general appraoch to modeling of mislocation is formulated, and the mean vectors and covariance matrices of the mixture distributions are derived. The asymptotic distribution of the discriminant boundary is obtained and the asymptotic first two moments of the two types of error rate given. Certain numerical results for the error rates are presented by considering the random and two non-random misallocation models. It is shown that when the allocation procedure for training samples is objectively formulated, the effect of misallocation on the error rates of the Bayes linear discriminant rule can almost be eliminated. If, however, this is not possible, the use of Fisher rule may be preferred over the Bayes rule.

Toward Automated Cochlear Implant Fitting Procedures Based on Event-Related Potentials.

PubMed

Finke, Mareike; Billinger, Martin; Büchner, Andreas

Cochlear implants (CIs) restore hearing to the profoundly deaf by direct electrical stimulation of the auditory nerve. To provide an optimal electrical stimulation pattern the CI must be individually fitted to each CI user. To date, CI fitting is primarily based on subjective feedback from the user. However, not all CI users are able to provide such feedback, for example, small children. This study explores the possibility of using the electroencephalogram (EEG) to objectively determine if CI users are able to hear differences in tones presented to them, which has potential applications in CI fitting or closed loop systems. Deviant and standard stimuli were presented to 12 CI users in an active auditory oddball paradigm. The EEG was recorded in two sessions and classification of the EEG data was performed with shrinkage linear discriminant analysis. Also, the impact of CI artifact removal on classification performance and the possibility to reuse a trained classifier in future sessions were evaluated. Overall, classification performance was above chance level for all participants although performance varied considerably between participants. Also, artifacts were successfully removed from the EEG without impairing classification performance. Finally, reuse of the classifier causes only a small loss in classification performance. Our data provide first evidence that EEG can be automatically classified on single-trial basis in CI users. Despite the slightly poorer classification performance over sessions, classifier and CI artifact correction appear stable over successive sessions. Thus, classifier and artifact correction weights can be reused without repeating the set-up procedure in every session, which makes the technique easier applicable. With our present data, we can show successful classification of event-related cortical potential patterns in CI users. In the future, this has the potential to objectify and automate parts of CI fitting procedures.

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].

Improving the analysis of near-spectroscopy data with multivariate classification of hemodynamic patterns: a theoretical formulation and validation.

PubMed

Gemignani, Jessica; Middell, Eike; Barbour, Randall L; Graber, Harry L; Blankertz, Benjamin

2018-04-04

The statistical analysis of functional near infrared spectroscopy (fNIRS) data based on the general linear model (GLM) is often made difficult by serial correlations, high inter-subject variability of the hemodynamic response, and the presence of motion artifacts. In this work we propose to extract information on the pattern of hemodynamic activations without using any a priori model for the data, by classifying the channels as 'active' or 'not active' with a multivariate classifier based on linear discriminant analysis (LDA). This work is developed in two steps. First we compared the performance of the two analyses, using a synthetic approach in which simulated hemodynamic activations were combined with either simulated or real resting-state fNIRS data. This procedure allowed for exact quantification of the classification accuracies of GLM and LDA. In the case of real resting-state data, the correlations between classification accuracy and demographic characteristics were investigated by means of a Linear Mixed Model. In the second step, to further characterize the reliability of the newly proposed analysis method, we conducted an experiment in which participants had to perform a simple motor task and data were analyzed with the LDA-based classifier as well as with the standard GLM analysis. The results of the simulation study show that the LDA-based method achieves higher classification accuracies than the GLM analysis, and that the LDA results are more uniform across different subjects and, in contrast to the accuracies achieved by the GLM analysis, have no significant correlations with any of the demographic characteristics. Findings from the real-data experiment are consistent with the results of the real-plus-simulation study, in that the GLM-analysis results show greater inter-subject variability than do the corresponding LDA results. The results obtained suggest that the outcome of GLM analysis is highly vulnerable to violations of theoretical assumptions, and that therefore a data-driven approach such as that provided by the proposed LDA-based method is to be favored.

Raman Spectroscopy and Chemometrics for Identification and Strain Discrimination of the Wine Spoilage Yeasts Saccharomyces cerevisiae, Zygosaccharomyces bailii, and Brettanomyces bruxellensis

PubMed Central

Thornton, Mark A.; Thornton, Roy J.

2013-01-01

The yeasts Zygosaccharomyces bailii, Dekkera bruxellensis (anamorph, Brettanomyces bruxellensis), and Saccharomyces cerevisiae are the major spoilage agents of finished wine. A novel method using Raman spectroscopy in combination with a chemometric classification tool has been developed for the identification of these yeast species and for strain discrimination of these yeasts. Raman spectra were collected for six strains of each of the yeasts Z. bailii, B. bruxellensis, and S. cerevisiae. The yeasts were classified with high sensitivity at the species level: 93.8% for Z. bailii, 92.3% for B. bruxellensis, and 98.6% for S. cerevisiae. Furthermore, we have demonstrated that it is possible to discriminate between strains of these species. These yeasts were classified at the strain level with an overall accuracy of 81.8%. PMID:23913433

Raman spectroscopy and chemometrics for identification and strain discrimination of the wine spoilage yeasts Saccharomyces cerevisiae, Zygosaccharomyces bailii, and Brettanomyces bruxellensis.

PubMed

Rodriguez, Susan B; Thornton, Mark A; Thornton, Roy J

2013-10-01

The yeasts Zygosaccharomyces bailii, Dekkera bruxellensis (anamorph, Brettanomyces bruxellensis), and Saccharomyces cerevisiae are the major spoilage agents of finished wine. A novel method using Raman spectroscopy in combination with a chemometric classification tool has been developed for the identification of these yeast species and for strain discrimination of these yeasts. Raman spectra were collected for six strains of each of the yeasts Z. bailii, B. bruxellensis, and S. cerevisiae. The yeasts were classified with high sensitivity at the species level: 93.8% for Z. bailii, 92.3% for B. bruxellensis, and 98.6% for S. cerevisiae. Furthermore, we have demonstrated that it is possible to discriminate between strains of these species. These yeasts were classified at the strain level with an overall accuracy of 81.8%.

Enhancement of plant metabolite fingerprinting by machine learning.

PubMed

Scott, Ian M; Vermeer, Cornelia P; Liakata, Maria; Corol, Delia I; Ward, Jane L; Lin, Wanchang; Johnson, Helen E; Whitehead, Lynne; Kular, Baldeep; Baker, John M; Walsh, Sean; Dave, Anuja; Larson, Tony R; Graham, Ian A; Wang, Trevor L; King, Ross D; Draper, John; Beale, Michael H

2010-08-01

Metabolite fingerprinting of Arabidopsis (Arabidopsis thaliana) mutants with known or predicted metabolic lesions was performed by (1)H-nuclear magnetic resonance, Fourier transform infrared, and flow injection electrospray-mass spectrometry. Fingerprinting enabled processing of five times more plants than conventional chromatographic profiling and was competitive for discriminating mutants, other than those affected in only low-abundance metabolites. Despite their rapidity and complexity, fingerprints yielded metabolomic insights (e.g. that effects of single lesions were usually not confined to individual pathways). Among fingerprint techniques, (1)H-nuclear magnetic resonance discriminated the most mutant phenotypes from the wild type and Fourier transform infrared discriminated the fewest. To maximize information from fingerprints, data analysis was crucial. One-third of distinctive phenotypes might have been overlooked had data models been confined to principal component analysis score plots. Among several methods tested, machine learning (ML) algorithms, namely support vector machine or random forest (RF) classifiers, were unsurpassed for phenotype discrimination. Support vector machines were often the best performing classifiers, but RFs yielded some particularly informative measures. First, RFs estimated margins between mutant phenotypes, whose relations could then be visualized by Sammon mapping or hierarchical clustering. Second, RFs provided importance scores for the features within fingerprints that discriminated mutants. These scores correlated with analysis of variance F values (as did Kruskal-Wallis tests, true- and false-positive measures, mutual information, and the Relief feature selection algorithm). ML classifiers, as models trained on one data set to predict another, were ideal for focused metabolomic queries, such as the distinctiveness and consistency of mutant phenotypes. Accessible software for use of ML in plant physiology is highlighted.

Scintillation decay time and pulse shape discrimination in oxygenated and deoxygenated solutions of linear alkylbenzene for the SNO+ experiment

NASA Astrophysics Data System (ADS)

O'Keeffe, H. M.; O'Sullivan, E.; Chen, M. C.

2011-06-01

The SNO+ liquid scintillator experiment is under construction in the SNOLAB facility in Canada. The success of this experiment relies upon accurate characterization of the liquid scintillator, linear alkylbenzene (LAB). In this paper, scintillation decay times for alpha and electron excitations in LAB with 2 g/L PPO are presented for both oxygenated and deoxygenated solutions. While deoxygenation is expected to improve pulse shape discrimination in liquid scintillators, it is not commonly demonstrated in the literature. This paper shows that for linear alkylbenzene, deoxygenation improves discrimination between electron and alpha excitations in the scintillator.

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

PubMed

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

2016-08-01

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

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.

Prediction of in vivo hepatotoxicity effects using in vitro ...

EPA Pesticide Factsheets

High-throughput in vitro transcriptomics data support molecular understanding of chemical-induced toxicity. Here, we evaluated the utility of such data to predict liver toxicity. First, in vitro gene expression data for 93 genes was generated following exposure of metabolically competent HepaRG cells to 1060 environmental chemicals from the US EPA ToxCast library. The empirical relationship between these data and rat chronic liver endpoints from animal studies in the Toxicity Reference Database (ToxRefDB) was then evaluated using machine learning techniques. Chemicals were classified as positive (242) or negative (135) based on observed hepatic histopathologic effects, and divided into three categories: hypertrophy (183), injury (112) and proliferative lesions (101). Hepatotoxicants were classified on the basis of the bioactivity of 93 genes (descriptors) using six machine learning algorithms: linear discriminant analysis, naïve Bayes, support vector classification, classification and regression trees, k-nearest neighbors, and an ensemble of classifiers. Classification performance was evaluated using 10-fold cross-validation testing, and in-loop, filter-based, feature subset selection. The best balanced accuracy for prediction of hypertrophy, injury and proliferative lesions were 0.81 ± 0.07, 0.79 ± 0.08 and 0.77 ± 0.09, respectively. Gene specific perturbation of xenobiotic metabolism enzymes (CYP7A1/2E1/4A11/1A1/4A22) and transporters (ABCG2, ABCB11, SLC22

SU-F-303-05: DCE-MRI Before and During Treatment for Prediction of Concurrent Chemotherapy and Radiation Therapy Response in Head and Neck Cancer

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

Liu, Y; Diwanji, T; Zhang, B

2015-06-15

Purpose: To determine the ability of pharmacokinetic parameters derived from dynamic contrast-enhanced MRI (DCE- MRI) acquired before and during concurrent chemotherapy and radiation therapy to predict clinical response in patients with head and neck cancer. Methods: Eleven patients underwent a DCE-MRI scan at three time points: 1–2 weeks before treatment, 4–5 weeks after treatment initiation, and 3–4 months after treatment completion. Post-processing of MRI data included correction to reduce motion artifacts. The arterial input function was obtained by measuring the dynamic tracer concentration in the jugular veins. The volume transfer constant (Ktrans), extracellular extravascular volume fraction (ve), rate constant (Kep;more » Kep = Ktrans/ve), and plasma volume fraction (vp) were computed for primary tumors and cervical nodal masses. Patients were categorized into two groups based on response to therapy at 3–4 months: responders (no evidence of disease) and partial responders (regression of disease). Responses of the primary tumor and nodes were evaluated separately. A linear classifier and receiver operating characteristic curve analyses were used to determine the best model for discrimination of responders from partial responders. Results: When the above pharmacokinetic parameters of the primary tumor measured before and during treatment were incorporated into the linear classifier, a discriminative accuracy of 88.9%, with sensitivity =100% and specificity = 66.7%, was observed between responders (n=6) and partial responders (n=3) for the primary tumor with the corresponding accuracy = 44.4%, sensitivity = 66.7%, and specificity of 0% for nodal masses. When only pre-treatment parameters were used, the accuracy decreased to 66.7%, with sensitivity = 66.7% and specificity = 66.7% for the primary tumor and decreased to 33.3%, sensitivity of 50%, and specificity of 0% for nodal masses. Conclusion: Higher accuracy, sensitivity, and specificity were obtained using DCE-MRI-derived pharmacokinetic parameters acquired before and during treatment as compared with those derived from the pre-treatment time-point, exclusively.« less

Use of Nintendo Wii Balance Board for posturographic analysis of Multiple Sclerosis patients with minimal balance impairment.

PubMed

Severini, Giacomo; Straudi, Sofia; Pavarelli, Claudia; Da Roit, Marco; Martinuzzi, Carlotta; Di Marco Pizzongolo, Laura; Basaglia, Nino

2017-03-11

The Wii Balance Board (WBB) has been proposed as an inexpensive alternative to laboratory-grade Force Plates (FP) for the instrumented assessment of balance. Previous studies have reported a good validity and reliability of the WBB for estimating the path length of the Center of Pressure. Here we extend this analysis to 18 balance related features extracted from healthy subjects (HS) and individuals affected by Multiple Sclerosis (MS) with minimal balance impairment. Eighteen MS patients with minimal balance impairment (Berg Balance Scale 53.3 ± 3.1) and 18 age-matched HS were recruited in this study. All subjects underwent instrumented balance tests on the FP and WBB consisting of quiet standing with the eyes open and closed. Linear correlation analysis and Bland-Altman plots were used to assess relations between path lengths estimated using the WBB and the FP. 18 features were extracted from the instrumented balance tests. Statistical analysis was used to assess significant differences between the features estimated using the WBB and the FP and between HS and MS. The Spearman correlation coefficient was used to evaluate the validity and the Intraclass Correlation Coefficient was used to assess the reliability of WBB measures with respect to the FP. Classifiers based on Support Vector Machines trained on the FP and WBB features were used to assess the ability of both devices to discriminate between HS and MS. We found a significant linear relation between the path lengths calculated from the WBB and the FP indicating an overestimation of these parameters in the WBB. We observed significant differences in the path lengths between FP and WBB in most conditions. However, significant differences were not found for the majority of the other features. We observed the same significant differences between the HS and MS populations across the two measurement systems. Validity and reliability were moderate-to-high for all the analyzed features. Both the FP and WBB trained classifier showed similar classification performance (>80%) when discriminating between HS and MS. Our results support the observation that the WBB, although not suitable for obtaining absolute measures, could be successfully used in comparative analysis of different populations.

Using recorded sound spectra profile as input data for real-time short-term urban road-traffic-flow estimation.

PubMed

Torija, Antonio J; Ruiz, Diego P

2012-10-01

Road traffic has a heavy impact on the urban sound environment, constituting the main source of noise and widely dominating its spectral composition. In this context, our research investigates the use of recorded sound spectra as input data for the development of real-time short-term road traffic flow estimation models. For this, a series of models based on the use of Multilayer Perceptron Neural Networks, multiple linear regression, and the Fisher linear discriminant were implemented to estimate road traffic flow as well as to classify it according to the composition of heavy vehicles and motorcycles/mopeds. In view of the results, the use of the 50-400 Hz and 1-2.5 kHz frequency ranges as input variables in multilayer perceptron-based models successfully estimated urban road traffic flow with an average percentage of explained variance equal to 86%, while the classification of the urban road traffic flow gave an average success rate of 96.1%. Copyright © 2012 Elsevier B.V. All rights reserved.

Supralinear and Supramodal Integration of Visual and Tactile Signals in Rats: Psychophysics and Neuronal Mechanisms.

PubMed

Nikbakht, Nader; Tafreshiha, Azadeh; Zoccolan, Davide; Diamond, Mathew E

2018-02-07

To better understand how object recognition can be triggered independently of the sensory channel through which information is acquired, we devised a task in which rats judged the orientation of a raised, black and white grating. They learned to recognize two categories of orientation: 0° ± 45° ("horizontal") and 90° ± 45° ("vertical"). Each trial required a visual (V), a tactile (T), or a visual-tactile (VT) discrimination; VT performance was better than that predicted by optimal linear combination of V and T signals, indicating synergy between sensory channels. We examined posterior parietal cortex (PPC) and uncovered key neuronal correlates of the behavioral findings: PPC carried both graded information about object orientation and categorical information about the rat's upcoming choice; single neurons exhibited identical responses under the three modality conditions. Finally, a linear classifier of neuronal population firing replicated the behavioral findings. Taken together, these findings suggest that PPC is involved in the supramodal processing of shape. Copyright © 2018 The Authors. Published by Elsevier Inc. All rights reserved.

Particle Swarm Optimization Based Feature Enhancement and Feature Selection for Improved Emotion Recognition in Speech and Glottal Signals

PubMed Central

Muthusamy, Hariharan; Polat, Kemal; Yaacob, Sazali

2015-01-01

In the recent years, many research works have been published using speech related features for speech emotion recognition, however, recent studies show that there is a strong correlation between emotional states and glottal features. In this work, Mel-frequency cepstralcoefficients (MFCCs), linear predictive cepstral coefficients (LPCCs), perceptual linear predictive (PLP) features, gammatone filter outputs, timbral texture features, stationary wavelet transform based timbral texture features and relative wavelet packet energy and entropy features were extracted from the emotional speech (ES) signals and its glottal waveforms(GW). Particle swarm optimization based clustering (PSOC) and wrapper based particle swarm optimization (WPSO) were proposed to enhance the discerning ability of the features and to select the discriminating features respectively. Three different emotional speech databases were utilized to gauge the proposed method. Extreme learning machine (ELM) was employed to classify the different types of emotions. Different experiments were conducted and the results show that the proposed method significantly improves the speech emotion recognition performance compared to previous works published in the literature. PMID:25799141

Local kernel nonparametric discriminant analysis for adaptive extraction of complex structures

NASA Astrophysics Data System (ADS)

Li, Quanbao; Wei, Fajie; Zhou, Shenghan

2017-05-01

The linear discriminant analysis (LDA) is one of popular means for linear feature extraction. It usually performs well when the global data structure is consistent with the local data structure. Other frequently-used approaches of feature extraction usually require linear, independence, or large sample condition. However, in real world applications, these assumptions are not always satisfied or cannot be tested. In this paper, we introduce an adaptive method, local kernel nonparametric discriminant analysis (LKNDA), which integrates conventional discriminant analysis with nonparametric statistics. LKNDA is adept in identifying both complex nonlinear structures and the ad hoc rule. Six simulation cases demonstrate that LKNDA have both parametric and nonparametric algorithm advantages and higher classification accuracy. Quartic unilateral kernel function may provide better robustness of prediction than other functions. LKNDA gives an alternative solution for discriminant cases of complex nonlinear feature extraction or unknown feature extraction. At last, the application of LKNDA in the complex feature extraction of financial market activities is proposed.

Principal Component Clustering Approach to Teaching Quality Discriminant Analysis

ERIC Educational Resources Information Center

Xian, Sidong; Xia, Haibo; Yin, Yubo; Zhai, Zhansheng; Shang, Yan

2016-01-01

Teaching quality is the lifeline of the higher education. Many universities have made some effective achievement about evaluating the teaching quality. In this paper, we establish the Students' evaluation of teaching (SET) discriminant analysis model and algorithm based on principal component clustering analysis. Additionally, we classify the SET…

Fat discrimination: A phenotype with potential implications for studying fat intake behaviors and obesity

PubMed Central

Liang, Lisa C.H.; Sakimura, Johannah; May, Daniel; Breen, Cameron; Driggin, Elissa; Tepper, Beverly J.; Chung, Wendy K.; Keller, Kathleen L.

2013-01-01

Variations in fat preference and intake across humans are poorly understood in part because of difficulties in studying this behavior. The objective of this study was to develop a simple procedure to assess fat discrimination, the ability to accurately perceive differences in the fat content of foods, and assess the associations between this phenotype and fat ingestive behaviors and adiposity. African-American adults (n=317) were tested for fat discrimination using 7 forced choice same/different tests with Italian salad dressings that ranged in fat-by-weight content from 5–55%. Performance on this procedure was determined by tallying the number of trials in which a participant correctly identified the pair of samples as “same” or “different” across all test pairs (ranging from 1–7). Individuals who received the lowest scores on this task (≤3 out of 7 correct) were classified as fat non-discriminators (n=33) and those who received the highest scores (7 out of 7 correct) were classified as fat discriminators (n=59). These 2 groups were compared for the primary outcome variables: reported food intake, preferences, and adiposity. After adjusting for BMI, sex, age, and dietary restraint and disinhibition, fat non-discriminators reported greater consumption of both added fats and reduced fat foods (p<0.05 for both). Fat non-discriminators also had greater abdominal adiposity compared to fat discriminators (p<0.05). Test-retest scores performed in a subset of participants (n=40) showed moderate reliability of the fat discrimination test (rho=0.53;p<0.01). If these results are replicated, fat discrimination may serve as clinical research tool to identify participants who are at risk for obesity and other chronic diseases due to increased fat intake. PMID:21925524

Fat discrimination: a phenotype with potential implications for studying fat intake behaviors and obesity.

PubMed

Liang, Lisa C H; Sakimura, Johannah; May, Daniel; Breen, Cameron; Driggin, Elissa; Tepper, Beverly J; Chung, Wendy K; Keller, Kathleen L

2012-01-18

Variations in fat preference and intake across humans are poorly understood in part because of difficulties in studying this behavior. The objective of this study was to develop a simple procedure to assess fat discrimination, the ability to accurately perceive differences in the fat content of foods, and assess the associations between this phenotype and fat ingestive behaviors and adiposity. African-American adults (n=317) were tested for fat discrimination using 7 forced choice same/different tests with Italian salad dressings that ranged in fat-by-weight content from 5 to 55%. Performance on this procedure was determined by tallying the number of trials in which a participant correctly identified the pair of samples as "same" or "different" across all test pairs (ranging from 1 to 7). Individuals who received the lowest scores on this task (≤3 out of 7 correct) were classified as fat non-discriminators (n=33) and those who received the highest scores (7 out of 7 correct) were classified as fat discriminators (n=59). These 2 groups were compared for the primary outcome variables: reported food intake, preferences, and adiposity. After adjusting for BMI, sex, age, and dietary restraint and disinhibition, fat non-discriminators reported greater consumption of both added fats and reduced fat foods (p<0.05 for both). Fat non-discriminators also had greater abdominal adiposity compared to fat discriminators (p<0.05). Test-retest scores performed in a subset of participants (n=40) showed moderate reliability of the fat discrimination test (rho=0.53; p<0.01). If these results are replicated, fat discrimination may serve as clinical research tool to identify participants who are at risk for obesity and other chronic diseases due to increased fat intake. Copyright © 2011 Elsevier Inc. All rights reserved.

Shape classification of wear particles by image boundary analysis using machine learning algorithms

NASA Astrophysics Data System (ADS)

Yuan, Wei; Chin, K. S.; Hua, Meng; Dong, Guangneng; Wang, Chunhui

2016-05-01

The shape features of wear particles generated from wear track usually contain plenty of information about the wear states of a machinery operational condition. Techniques to quickly identify types of wear particles quickly to respond to the machine operation and prolong the machine's life appear to be lacking and are yet to be established. To bridge rapid off-line feature recognition with on-line wear mode identification, this paper presents a new radial concave deviation (RCD) method that mainly involves the use of the particle boundary signal to analyze wear particle features. Signal output from the RCDs subsequently facilitates the determination of several other feature parameters, typically relevant to the shape and size of the wear particle. Debris feature and type are identified through the use of various classification methods, such as linear discriminant analysis, quadratic discriminant analysis, naïve Bayesian method, and classification and regression tree method (CART). The average errors of the training and test via ten-fold cross validation suggest CART is a highly suitable approach for classifying and analyzing particle features. Furthermore, the results of the wear debris analysis enable the maintenance team to diagnose faults appropriately.

Differentiation of tea varieties using UV-Vis spectra and pattern recognition techniques

NASA Astrophysics Data System (ADS)

Palacios-Morillo, Ana; Alcázar, Ángela.; de Pablos, Fernando; Jurado, José Marcos

2013-02-01

Tea, one of the most consumed beverages all over the world, is of great importance in the economies of a number of countries. Several methods have been developed to classify tea varieties or origins based in pattern recognition techniques applied to chemical data, such as metal profile, amino acids, catechins and volatile compounds. Some of these analytical methods become tedious and expensive to be applied in routine works. The use of UV-Vis spectral data as discriminant variables, highly influenced by the chemical composition, can be an alternative to these methods. UV-Vis spectra of methanol-water extracts of tea have been obtained in the interval 250-800 nm. Absorbances have been used as input variables. Principal component analysis was used to reduce the number of variables and several pattern recognition methods, such as linear discriminant analysis, support vector machines and artificial neural networks, have been applied in order to differentiate the most common tea varieties. A successful classification model was built by combining principal component analysis and multilayer perceptron artificial neural networks, allowing the differentiation between tea varieties. This rapid and simple methodology can be applied to solve classification problems in food industry saving economic resources.

Authentication of the botanical and geographical origin of honey by front-face fluorescence spectroscopy.

PubMed

Ruoff, Kaspar; Luginbühl, Werner; Künzli, Raphael; Bogdanov, Stefan; Bosset, Jacques Olivier; von der Ohe, Katharina; von der Ohe, Werner; Amado, Renato

2006-09-06

Front-face fluorescence spectroscopy, directly applied on honey samples, was used for the authentication of 11 unifloral and polyfloral honey types (n = 371 samples) previously classified using traditional methods such as chemical, pollen, and sensory analysis. Excitation spectra (220-400 nm) were recorded with the emission measured at 420 nm. In addition, emission spectra were recorded between 290 and 500 nm (excitation at 270 nm) as well as between 330 and 550 nm (excitation at 310 nm). A total of four different spectral data sets were considered for data analysis. Chemometric evaluation of the spectra included principal component analysis and linear discriminant analysis; the error rates of the discriminant models were calculated by using Bayes' theorem. They ranged from <0.1% (polyfloral and chestnut honeys) to 9.9% (fir honeydew honey) by using single spectral data sets and from <0.1% (metcalfa honeydew, polyfloral, and chestnut honeys) to 7.5% (lime honey) by combining two data sets. This study indicates that front-face fluorescence spectroscopy is a promising technique for the authentication of the botanical origin of honey and may also be useful for the determination of the geographical origin within the same unifloral honey type.

Modelling spatio-temporal heterogeneities in groundwater quality in Ghana: a multivariate chemometric approach.

PubMed

Armah, Frederick Ato; Paintsil, Arnold; Yawson, David Oscar; Adu, Michael Osei; Odoi, Justice O

2017-08-01

Chemometric techniques were applied to evaluate the spatial and temporal heterogeneities in groundwater quality data for approximately 740 goldmining and agriculture-intensive locations in Ghana. The strongest linear and monotonic relationships occurred between Mn and Fe. Sixty-nine per cent of total variance in the dataset was explained by four variance factors: physicochemical properties, bacteriological quality, natural geologic attributes and anthropogenic factors (artisanal goldmining). There was evidence of significant differences in means of all trace metals and physicochemical parameters (p < 0.001) between goldmining and non-goldmining locations. Arsenic and turbidity produced very high value F's demonstrating that 'physical properties and chalcophilic elements' was the function that most discriminated between non-goldmining and goldmining locations. Variations in Escherichia coli and total coliforms were observed between the dry and wet seasons. The overall predictive accuracy of the discriminant function showed that non-goldmining locations were classified with slightly better accuracy (89%) than goldmining areas (69.6%). There were significant differences between the underlying distributions of Cd, Mn and Pb in the wet and dry seasons. This study emphasizes the practicality of chemometrics in the assessment and elucidation of complex water quality datasets to promote effective management of groundwater resources for sustaining human health.

Driving behavior recognition using EEG data from a simulated car-following experiment.

PubMed

Yang, Liu; Ma, Rui; Zhang, H Michael; Guan, Wei; Jiang, Shixiong

2018-07-01

Driving behavior recognition is the foundation of driver assistance systems, with potential applications in automated driving systems. Most prevailing studies have used subjective questionnaire data and objective driving data to classify driving behaviors, while few studies have used physiological signals such as electroencephalography (EEG) to gather data. To bridge this gap, this paper proposes a two-layer learning method for driving behavior recognition using EEG data. A simulated car-following driving experiment was designed and conducted to simultaneously collect data on the driving behaviors and EEG data of drivers. The proposed learning method consists of two layers. In Layer I, two-dimensional driving behavior features representing driving style and stability were selected and extracted from raw driving behavior data using K-means and support vector machine recursive feature elimination. Five groups of driving behaviors were classified based on these two-dimensional driving behavior features. In Layer II, the classification results from Layer I were utilized as inputs to generate a k-Nearest-Neighbor classifier identifying driving behavior groups using EEG data. Using independent component analysis, a fast Fourier transformation, and linear discriminant analysis sequentially, the raw EEG signals were processed to extract two core EEG features. Classifier performance was enhanced using the adaptive synthetic sampling approach. A leave-one-subject-out cross validation was conducted. The results showed that the average classification accuracy for all tested traffic states was 69.5% and the highest accuracy reached 83.5%, suggesting a significant correlation between EEG patterns and car-following behavior. Copyright © 2017 Elsevier Ltd. All rights reserved.

Multi-feature classifiers for burst detection in single EEG channels from preterm infants

NASA Astrophysics Data System (ADS)

Navarro, X.; Porée, F.; Kuchenbuch, M.; Chavez, M.; Beuchée, Alain; Carrault, G.

2017-08-01

Objective. The study of electroencephalographic (EEG) bursts in preterm infants provides valuable information about maturation or prognostication after perinatal asphyxia. Over the last two decades, a number of works proposed algorithms to automatically detect EEG bursts in preterm infants, but they were designed for populations under 35 weeks of post menstrual age (PMA). However, as the brain activity evolves rapidly during postnatal life, these solutions might be under-performing with increasing PMA. In this work we focused on preterm infants reaching term ages (PMA  ⩾36 weeks) using multi-feature classification on a single EEG channel. Approach. Five EEG burst detectors relying on different machine learning approaches were compared: logistic regression (LR), linear discriminant analysis (LDA), k-nearest neighbors (kNN), support vector machines (SVM) and thresholding (Th). Classifiers were trained by visually labeled EEG recordings from 14 very preterm infants (born after 28 weeks of gestation) with 36-41 weeks PMA. Main results. The most performing classifiers reached about 95% accuracy (kNN, SVM and LR) whereas Th obtained 84%. Compared to human-automatic agreements, LR provided the highest scores (Cohen’s kappa  =  0.71) using only three EEG features. Applying this classifier in an unlabeled database of 21 infants  ⩾36 weeks PMA, we found that long EEG bursts and short inter-burst periods are characteristic of infants with the highest PMA and weights. Significance. In view of these results, LR-based burst detection could be a suitable tool to study maturation in monitoring or portable devices using a single EEG channel.

Machine Learning-based Texture Analysis of Contrast-enhanced MR Imaging to Differentiate between Glioblastoma and Primary Central Nervous System Lymphoma.

PubMed

Kunimatsu, Akira; Kunimatsu, Natsuko; Yasaka, Koichiro; Akai, Hiroyuki; Kamiya, Kouhei; Watadani, Takeyuki; Mori, Harushi; Abe, Osamu

2018-05-16

Although advanced MRI techniques are increasingly available, imaging differentiation between glioblastoma and primary central nervous system lymphoma (PCNSL) is sometimes confusing. We aimed to evaluate the performance of image classification by support vector machine, a method of traditional machine learning, using texture features computed from contrast-enhanced T 1 -weighted images. This retrospective study on preoperative brain tumor MRI included 76 consecutives, initially treated patients with glioblastoma (n = 55) or PCNSL (n = 21) from one institution, consisting of independent training group (n = 60: 44 glioblastomas and 16 PCNSLs) and test group (n = 16: 11 glioblastomas and 5 PCNSLs) sequentially separated by time periods. A total set of 67 texture features was computed on routine contrast-enhanced T 1 -weighted images of the training group, and the top four most discriminating features were selected as input variables to train support vector machine classifiers. These features were then evaluated on the test group with subsequent image classification. The area under the receiver operating characteristic curves on the training data was calculated at 0.99 (95% confidence interval [CI]: 0.96-1.00) for the classifier with a Gaussian kernel and 0.87 (95% CI: 0.77-0.95) for the classifier with a linear kernel. On the test data, both of the classifiers showed prediction accuracy of 75% (12/16) of the test images. Although further improvement is needed, our preliminary results suggest that machine learning-based image classification may provide complementary diagnostic information on routine brain MRI.

Combining functional and structural tests improves the diagnostic accuracy of relevance vector machine classifiers

PubMed Central

Racette, Lyne; Chiou, Christine Y.; Hao, Jiucang; Bowd, Christopher; Goldbaum, Michael H.; Zangwill, Linda M.; Lee, Te-Won; Weinreb, Robert N.; Sample, Pamela A.

2009-01-01

Purpose To investigate whether combining optic disc topography and short-wavelength automated perimetry (SWAP) data improves the diagnostic accuracy of relevance vector machine (RVM) classifiers for detecting glaucomatous eyes compared to using each test alone. Methods One eye of 144 glaucoma patients and 68 healthy controls from the Diagnostic Innovations in Glaucoma Study were included. RVM were trained and tested with cross-validation on optimized (backward elimination) SWAP features (thresholds plus age; pattern deviation (PD); total deviation (TD)) and on Heidelberg Retina Tomograph II (HRT) optic disc topography features, independently and in combination. RVM performance was also compared to two HRT linear discriminant functions (LDF) and to SWAP mean deviation (MD) and pattern standard deviation (PSD). Classifier performance was measured by the area under the receiver operating characteristic curves (AUROCs) generated for each feature set and by the sensitivities at set specificities of 75%, 90% and 96%. Results RVM trained on combined HRT and SWAP thresholds plus age had significantly higher AUROC (0.93) than RVM trained on HRT (0.88) and SWAP (0.76) alone. AUROCs for the SWAP global indices (MD: 0.68; PSD: 0.72) offered no advantage over SWAP thresholds plus age, while the LDF AUROCs were significantly lower than RVM trained on the combined SWAP and HRT feature set and on HRT alone feature set. Conclusions Training RVM on combined optimized HRT and SWAP data improved diagnostic accuracy compared to training on SWAP and HRT parameters alone. Future research may identify other combinations of tests and classifiers that can also improve diagnostic accuracy. PMID:19528827

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

Third-Degree Price Discrimination Revisited

ERIC Educational Resources Information Center

Kwon, Youngsun

2006-01-01

The author derives the probability that price discrimination improves social welfare, using a simple model of third-degree price discrimination assuming two independent linear demands. The probability that price discrimination raises social welfare increases as the preferences or incomes of consumer groups become more heterogeneous. He derives the…

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.

Identification of rheumatoid arthritis and osteoarthritis patients by transcriptome-based rule set generation

PubMed Central

2014-01-01

Introduction Discrimination of rheumatoid arthritis (RA) patients from patients with other inflammatory or degenerative joint diseases or healthy individuals purely on the basis of genes differentially expressed in high-throughput data has proven very difficult. Thus, the present study sought to achieve such discrimination by employing a novel unbiased approach using rule-based classifiers. Methods Three multi-center genome-wide transcriptomic data sets (Affymetrix HG-U133 A/B) from a total of 79 individuals, including 20 healthy controls (control group - CG), as well as 26 osteoarthritis (OA) and 33 RA patients, were used to infer rule-based classifiers to discriminate the disease groups. The rules were ranked with respect to Kiendl’s statistical relevance index, and the resulting rule set was optimized by pruning. The rule sets were inferred separately from data of one of three centers and applied to the two remaining centers for validation. All rules from the optimized rule sets of all centers were used to analyze their biological relevance applying the software Pathway Studio. Results The optimized rule sets for the three centers contained a total of 29, 20, and 8 rules (including 10, 8, and 4 rules for ‘RA’), respectively. The mean sensitivity for the prediction of RA based on six center-to-center tests was 96% (range 90% to 100%), that for OA 86% (range 40% to 100%). The mean specificity for RA prediction was 94% (range 80% to 100%), that for OA 96% (range 83.3% to 100%). The average overall accuracy of the three different rule-based classifiers was 91% (range 80% to 100%). Unbiased analyses by Pathway Studio of the gene sets obtained by discrimination of RA from OA and CG with rule-based classifiers resulted in the identification of the pathogenetically and/or therapeutically relevant interferon-gamma and GM-CSF pathways. Conclusion First-time application of rule-based classifiers for the discrimination of RA resulted in high performance, with means for all assessment parameters close to or higher than 90%. In addition, this unbiased, new approach resulted in the identification not only of pathways known to be critical to RA, but also of novel molecules such as serine/threonine kinase 10. PMID:24690414

Special event discrimination analysis: The TEXAR blind test and identification of the August 16, 1997 Kara Sea event. Final report, 13 September 1995--31 January 1998

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

Baumgardt, D.

1998-03-31

The International Monitoring System (IMS) for the Comprehensive Test Ban Treaty (CTBT) faces the serious challenge of being able to accurately and reliably identify seismic events in any region of the world. Extensive research has been performed in recent years on developing discrimination techniques which appear to classify seismic events into broad categories of source types, such as nuclear explosion, earthquake, and mine blast. This report examines in detail the problem of effectiveness of regional discrimination procedures in the application of waveform discriminants to Special Event identification and the issue of discriminant transportability.

Classification of narcotics in solid mixtures using principal component analysis and Raman spectroscopy.

PubMed

Ryder, Alan G

2002-03-01

Eighty-five solid samples consisting of illegal narcotics diluted with several different materials were analyzed by near-infrared (785 nm excitation) Raman spectroscopy. Principal Component Analysis (PCA) was employed to classify the samples according to narcotic type. The best sample discrimination was obtained by using the first derivative of the Raman spectra. Furthermore, restricting the spectral variables for PCA to 2 or 3% of the original spectral data according to the most intense peaks in the Raman spectrum of the pure narcotic resulted in a rapid discrimination method for classifying samples according to narcotic type. This method allows for the easy discrimination between cocaine, heroin, and MDMA mixtures even when the Raman spectra are complex or very similar. This approach of restricting the spectral variables also decreases the computational time by a factor of 30 (compared to the complete spectrum), making the methodology attractive for rapid automatic classification and identification of suspect materials.

Study of a Vocal Feature Selection Method and Vocal Properties for Discriminating Four Constitution Types

PubMed Central

Kim, Keun Ho; Ku, Boncho; Kang, Namsik; Kim, Young-Su; Jang, Jun-Su; Kim, Jong Yeol

2012-01-01

The voice has been used to classify the four constitution types, and to recognize a subject's health condition by extracting meaningful physical quantities, in traditional Korean medicine. In this paper, we propose a method of selecting the reliable variables from various voice features, such as frequency derivative features, frequency band ratios, and intensity, from vowels and a sentence. Further, we suggest a process to extract independent variables by eliminating explanatory variables and reducing their correlation and remove outlying data to enable reliable discriminant analysis. Moreover, the suitable division of data for analysis, according to the gender and age of subjects, is discussed. Finally, the vocal features are applied to a discriminant analysis to classify each constitution type. This method of voice classification can be widely used in the u-Healthcare system of personalized medicine and for improving diagnostic accuracy. PMID:22529874

A ROC-based feature selection method for computer-aided detection and diagnosis

NASA Astrophysics Data System (ADS)

Wang, Songyuan; Zhang, Guopeng; Liao, Qimei; Zhang, Junying; Jiao, Chun; Lu, Hongbing

2014-03-01

Image-based computer-aided detection and diagnosis (CAD) has been a very active research topic aiming to assist physicians to detect lesions and distinguish them from benign to malignant. However, the datasets fed into a classifier usually suffer from small number of samples, as well as significantly less samples available in one class (have a disease) than the other, resulting in the classifier's suboptimal performance. How to identifying the most characterizing features of the observed data for lesion detection is critical to improve the sensitivity and minimize false positives of a CAD system. In this study, we propose a novel feature selection method mR-FAST that combines the minimal-redundancymaximal relevance (mRMR) framework with a selection metric FAST (feature assessment by sliding thresholds) based on the area under a ROC curve (AUC) generated on optimal simple linear discriminants. With three feature datasets extracted from CAD systems for colon polyps and bladder cancer, we show that the space of candidate features selected by mR-FAST is more characterizing for lesion detection with higher AUC, enabling to find a compact subset of superior features at low cost.

Detection of myasthenia gravis using electrooculography signals.

PubMed

Liang, T; Boulos, M I; Murray, B J; Krishnan, S; Katzberg, H; Umapathy, K

2016-08-01

Myasthenia gravis (MG) is an autoimmune neuromuscular disorder resulting from skeletal muscle weakness and fatigue. An early common symptom is fatigable weakness of the extrinsic ocular muscles; if symptoms remain confined to the ocular muscles after a few years, this is classified as ocular myasthenia gravis (OMG). Diagnosis of MG when there are mild, isolated ocular symptoms can be difficult, and currently available diagnostic techniques are insensitive, non-specific or technically cumbersome. In addition, there are no accurate biomarkers to follow severity of ocular dysfunction in MG over time. Single-fiber electromyography (SFEMG) and repetitive nerve stimulation (RNS) offers a way of detecting and measuring ocular muscle dysfunction in MG, however, challenges of these methods include a poor signal to noise ratio in quantifying eye muscle weakness especially in mild cases. This paper presents one of the attempts to use the electric potentials from the eyes or electrooculography (EOG) signals but obtained from three different forms of sleep testing to differentiate MG patients from age- and gender-matched controls. We analyzed 8 MG patients and 8 control patients and demonstrated a difference in the average eye movements detected between the groups. A classification accuracy as high as 68.8% was achieved using a linear discriminant analysis based classifier.

Classification of plum spirit drinks by synchronous fluorescence spectroscopy.

PubMed

Sádecká, J; Jakubíková, M; Májek, P; Kleinová, A

2016-04-01

Synchronous fluorescence spectroscopy was used in combination with principal component analysis (PCA) and linear discriminant analysis (LDA) for the differentiation of plum spirits according to their geographical origin. A total of 14 Czech, 12 Hungarian and 18 Slovak plum spirit samples were used. The samples were divided in two categories: colorless (22 samples) and colored (22 samples). Synchronous fluorescence spectra (SFS) obtained at a wavelength difference of 60 nm provided the best results. Considering the PCA-LDA applied to the SFS of all samples, Czech, Hungarian and Slovak colorless samples were properly classified in both the calibration and prediction sets. 100% of correct classification was also obtained for Czech and Hungarian colored samples. However, one group of Slovak colored samples was classified as belonging to the Hungarian group in the calibration set. Thus, the total correct classifications obtained were 94% and 100% for the calibration and prediction steps, respectively. The results were compared with those obtained using near-infrared (NIR) spectroscopy. Applying PCA-LDA to NIR spectra (5500-6000 cm(-1)), the total correct classifications were 91% and 92% for the calibration and prediction steps, respectively, which were slightly lower than those obtained using SFS. Copyright © 2015 Elsevier Ltd. All rights reserved.

Characterization and noninvasive diagnosis of bladder cancer with serum surface enhanced Raman spectroscopy and genetic algorithms

NASA Astrophysics Data System (ADS)

Li, Shaoxin; Li, Linfang; Zeng, Qiuyao; Zhang, Yanjiao; Guo, Zhouyi; Liu, Zhiming; Jin, Mei; Su, Chengkang; Lin, Lin; Xu, Junfa; Liu, Songhao

2015-05-01

This study aims to characterize and classify serum surface-enhanced Raman spectroscopy (SERS) spectra between bladder cancer patients and normal volunteers by genetic algorithms (GAs) combined with linear discriminate analysis (LDA). Two group serum SERS spectra excited with nanoparticles are collected from healthy volunteers (n = 36) and bladder cancer patients (n = 55). Six diagnostic Raman bands in the regions of 481-486, 682-687, 1018-1034, 1313-1323, 1450-1459 and 1582-1587 cm-1 related to proteins, nucleic acids and lipids are picked out with the GAs and LDA. By the diagnostic models built with the identified six Raman bands, the improved diagnostic sensitivity of 90.9% and specificity of 100% were acquired for classifying bladder cancer patients from normal serum SERS spectra. The results are superior to the sensitivity of 74.6% and specificity of 97.2% obtained with principal component analysis by the same serum SERS spectra dataset. Receiver operating characteristic (ROC) curves further confirmed the efficiency of diagnostic algorithm based on GA-LDA technique. This exploratory work demonstrates that the serum SERS associated with GA-LDA technique has enormous potential to characterize and non-invasively detect bladder cancer through peripheral blood.

Extracting features from protein sequences to improve deep extreme learning machine for protein fold recognition.

PubMed

Ibrahim, Wisam; Abadeh, Mohammad Saniee

2017-05-21

Protein fold recognition is an important problem in bioinformatics to predict three-dimensional structure of a protein. One of the most challenging tasks in protein fold recognition problem is the extraction of efficient features from the amino-acid sequences to obtain better classifiers. In this paper, we have proposed six descriptors to extract features from protein sequences. These descriptors are applied in the first stage of a three-stage framework PCA-DELM-LDA to extract feature vectors from the amino-acid sequences. Principal Component Analysis PCA has been implemented to reduce the number of extracted features. The extracted feature vectors have been used with original features to improve the performance of the Deep Extreme Learning Machine DELM in the second stage. Four new features have been extracted from the second stage and used in the third stage by Linear Discriminant Analysis LDA to classify the instances into 27 folds. The proposed framework is implemented on the independent and combined feature sets in SCOP datasets. The experimental results show that extracted feature vectors in the first stage could improve the performance of DELM in extracting new useful features in second stage. Copyright © 2017 Elsevier Ltd. All rights reserved.

Characterization of French and Spanish dry-cured hams: influence of the volatiles from the muscles and the subcutaneous fat quantified by SPME-GC.

PubMed

Sánchez-Peña, Carolina M; Luna, Guadalupe; García-González, Diego L; Aparicio, Ramón

2005-04-01

The influence of the volatile compounds on the characterization of Spanish and French dry-cured hams was studied. Thirty volatiles were quantified in each one of four locations (biceps femoris, semimembranosus and semitendinosus muscles and subcutaneous fat) of 29 dry-cured hams by solid-phase microextraction gas-chromatography (SPME-GC). The Brown-Forsythe univariate test allowed determination of the volatiles that individually could characterize (p<0.05) the samples by their geographical origin (France, Spain) and breed type (Iberian, white). Stepwise linear discriminant procedure, under very strict conditions (F-to-Enter for a F-distribution>0.95), then selected the most remarkable volatile compounds. Four compounds from the subcutaneous fat (methyl benzene and octanol) and the semitendinosus muscle (2-butanone and 2-octanone) allowed 100% correct classifications by geographic origin. On the other hand, only two compounds from the subcutaneous fat (octanol) and the biceps femoris muscle (3-methyl 1-butanol) correctly classified all the samples by the breed type. The ability of these variables to classify the samples was checked by the unsupervised procedure of principal components.

Pathological speech signal analysis and classification using empirical mode decomposition.

PubMed

Kaleem, Muhammad; Ghoraani, Behnaz; Guergachi, Aziz; Krishnan, Sridhar

2013-07-01

Automated classification of normal and pathological speech signals can provide an objective and accurate mechanism for pathological speech diagnosis, and is an active area of research. A large part of this research is based on analysis of acoustic measures extracted from sustained vowels. However, sustained vowels do not reflect real-world attributes of voice as effectively as continuous speech, which can take into account important attributes of speech such as rapid voice onset and termination, changes in voice frequency and amplitude, and sudden discontinuities in speech. This paper presents a methodology based on empirical mode decomposition (EMD) for classification of continuous normal and pathological speech signals obtained from a well-known database. EMD is used to decompose randomly chosen portions of speech signals into intrinsic mode functions, which are then analyzed to extract meaningful temporal and spectral features, including true instantaneous features which can capture discriminative information in signals hidden at local time-scales. A total of six features are extracted, and a linear classifier is used with the feature vector to classify continuous speech portions obtained from a database consisting of 51 normal and 161 pathological speakers. A classification accuracy of 95.7 % is obtained, thus demonstrating the effectiveness of the methodology.

Computer-Vision-Assisted Palm Rehabilitation With Supervised Learning.

PubMed

Vamsikrishna, K M; Dogra, Debi Prosad; Desarkar, Maunendra Sankar

2016-05-01

Physical rehabilitation supported by the computer-assisted-interface is gaining popularity among health-care fraternity. In this paper, we have proposed a computer-vision-assisted contactless methodology to facilitate palm and finger rehabilitation. Leap motion controller has been interfaced with a computing device to record parameters describing 3-D movements of the palm of a user undergoing rehabilitation. We have proposed an interface using Unity3D development platform. Our interface is capable of analyzing intermediate steps of rehabilitation without the help of an expert, and it can provide online feedback to the user. Isolated gestures are classified using linear discriminant analysis (DA) and support vector machines (SVM). Finally, a set of discrete hidden Markov models (HMM) have been used to classify gesture sequence performed during rehabilitation. Experimental validation using a large number of samples collected from healthy volunteers reveals that DA and SVM perform similarly while applied on isolated gesture recognition. We have compared the results of HMM-based sequence classification with CRF-based techniques. Our results confirm that both HMM and CRF perform quite similarly when tested on gesture sequences. The proposed system can be used for home-based palm or finger rehabilitation in the absence of experts.

Transcutaneous in vivo Raman spectroscopic studies in a mouse model: evaluation of changes in the breast associated with pregnancy and lactation

NASA Astrophysics Data System (ADS)

Bhattacharjee, Tanmoy; Maru, Girish; Ingle, Arvind; Krishna, C. Murali

2013-04-01

Raman spectroscopy (RS) has been extensively explored as an alternative diagnostic tool for breast cancer. This can be attributed to its sensitivity to malignancy-associated biochemical changes. However, biochemical changes due to nonmalignant conditions like benign lesions, inflammatory diseases, aging, menstrual cycle, pregnancy, and lactation may act as confounding factors in diagnosis of breast cancer. Therefore, in this study, the efficacy of RS to classify pregnancy and lactation-associated changes as well as its effect on breast tumor diagnosis was evaluated. Since such studies are difficult in human subjects, a mouse model was used. Spectra were recorded transcutaneously from the breast region of six Swiss bare mice postmating, during pregnancy, and during lactation. Data were analyzed using multivariate statistical tool Principal Component-Linear Discriminant Analysis. Results suggest that RS can differentiate breasts of pregnant/lactating mice from those of normal mice, the classification efficiencies being 100%, 60%, and 88% for normal, pregnant, and lactating mice, respectively. Frank breast tumors could be classified with 97.5% efficiency, suggesting that these physiological changes do not affect the ability of RS to detect breast tumors.

A hybrid sensing approach for pure and adulterated honey classification.

PubMed

Subari, Norazian; Mohamad Saleh, Junita; Md Shakaff, Ali Yeon; Zakaria, Ammar

2012-10-17

This paper presents a comparison between data from single modality and fusion methods to classify Tualang honey as pure or adulterated using Linear Discriminant Analysis (LDA) and Principal Component Analysis (PCA) statistical classification approaches. Ten different brands of certified pure Tualang honey were obtained throughout peninsular Malaysia and Sumatera, Indonesia. Various concentrations of two types of sugar solution (beet and cane sugar) were used in this investigation to create honey samples of 20%, 40%, 60% and 80% adulteration concentrations. Honey data extracted from an electronic nose (e-nose) and Fourier Transform Infrared Spectroscopy (FTIR) were gathered, analyzed and compared based on fusion methods. Visual observation of classification plots revealed that the PCA approach able to distinct pure and adulterated honey samples better than the LDA technique. Overall, the validated classification results based on FTIR data (88.0%) gave higher classification accuracy than e-nose data (76.5%) using the LDA technique. Honey classification based on normalized low-level and intermediate-level FTIR and e-nose fusion data scored classification accuracies of 92.2% and 88.7%, respectively using the Stepwise LDA method. The results suggested that pure and adulterated honey samples were better classified using FTIR and e-nose fusion data than single modality data.

Fault diagnosis for analog circuits utilizing time-frequency features and improved VVRKFA

NASA Astrophysics Data System (ADS)

He, Wei; He, Yigang; Luo, Qiwu; Zhang, Chaolong

2018-04-01

This paper proposes a novel scheme for analog circuit fault diagnosis utilizing features extracted from the time-frequency representations of signals and an improved vector-valued regularized kernel function approximation (VVRKFA). First, the cross-wavelet transform is employed to yield the energy-phase distribution of the fault signals over the time and frequency domain. Since the distribution is high-dimensional, a supervised dimensionality reduction technique—the bilateral 2D linear discriminant analysis—is applied to build a concise feature set from the distributions. Finally, VVRKFA is utilized to locate the fault. In order to improve the classification performance, the quantum-behaved particle swarm optimization technique is employed to gradually tune the learning parameter of the VVRKFA classifier. The experimental results for the analog circuit faults classification have demonstrated that the proposed diagnosis scheme has an advantage over other approaches.

Joint source based analysis of multiple brain structures in studying major depressive disorder

NASA Astrophysics Data System (ADS)

Ramezani, Mahdi; Rasoulian, Abtin; Hollenstein, Tom; Harkness, Kate; Johnsrude, Ingrid; Abolmaesumi, Purang

2014-03-01

We propose a joint Source-Based Analysis (jSBA) framework to identify brain structural variations in patients with Major Depressive Disorder (MDD). In this framework, features representing position, orientation and size (i.e. pose), shape, and local tissue composition are extracted. Subsequently, simultaneous analysis of these features within a joint analysis method is performed to generate the basis sources that show signi cant di erences between subjects with MDD and those in healthy control. Moreover, in a cross-validation leave- one-out experiment, we use a Fisher Linear Discriminant (FLD) classi er to identify individuals within the MDD group. Results show that we can classify the MDD subjects with an accuracy of 76% solely based on the information gathered from the joint analysis of pose, shape, and tissue composition in multiple brain structures.

Hybrid Feature Extraction-based Approach for Facial Parts Representation and Recognition

NASA Astrophysics Data System (ADS)

Rouabhia, C.; Tebbikh, H.

2008-06-01

Face recognition is a specialized image processing which has attracted a considerable attention in computer vision. In this article, we develop a new facial recognition system from video sequences images dedicated to person identification whose face is partly occulted. This system is based on a hybrid image feature extraction technique called ACPDL2D (Rouabhia et al. 2007), it combines two-dimensional principal component analysis and two-dimensional linear discriminant analysis with neural network. We performed the feature extraction task on the eyes and the nose images separately then a Multi-Layers Perceptron classifier is used. Compared to the whole face, the results of simulation are in favor of the facial parts in terms of memory capacity and recognition (99.41% for the eyes part, 98.16% for the nose part and 97.25 % for the whole face).

Classification of burst and suppression in the neonatal electroencephalogram

NASA Astrophysics Data System (ADS)

Löfhede, J.; Löfgren, N.; Thordstein, M.; Flisberg, A.; Kjellmer, I.; Lindecrantz, K.

2008-12-01

Fisher's linear discriminant (FLD), a feed-forward artificial neural network (ANN) and a support vector machine (SVM) were compared with respect to their ability to distinguish bursts from suppressions in electroencephalograms (EEG) displaying a burst-suppression pattern. Five features extracted from the EEG were used as inputs. The study was based on EEG signals from six full-term infants who had suffered from perinatal asphyxia, and the methods have been trained with reference data classified by an experienced electroencephalographer. The results are summarized as the area under the curve (AUC), derived from receiver operating characteristic (ROC) curves for the three methods. Based on this, the SVM performs slightly better than the others. Testing the three methods with combinations of increasing numbers of the five features shows that the SVM handles the increasing amount of information better than the other methods.

Estimating the mutual information of an EEG-based Brain-Computer Interface.

PubMed

Schlögl, A; Neuper, C; Pfurtscheller, G

2002-01-01

An EEG-based Brain-Computer Interface (BCI) could be used as an additional communication channel between human thoughts and the environment. The efficacy of such a BCI depends mainly on the transmitted information rate. Shannon's communication theory was used to quantify the information rate of BCI data. For this purpose, experimental EEG data from four BCI experiments was analyzed off-line. Subjects imaginated left and right hand movements during EEG recording from the sensorimotor area. Adaptive autoregressive (AAR) parameters were used as features of single trial EEG and classified with linear discriminant analysis. The intra-trial variation as well as the inter-trial variability, the signal-to-noise ratio, the entropy of information, and the information rate were estimated. The entropy difference was used as a measure of the separability of two classes of EEG patterns.

[Electroencephalogram Feature Selection Based on Correlation Coefficient Analysis].

PubMed

Zhou, Jinzhi; Tang, Xiaofang

2015-08-01

In order to improve the accuracy of classification with small amount of motor imagery training data on the development of brain-computer interface (BCD systems, we proposed an analyzing method to automatically select the characteristic parameters based on correlation coefficient analysis. Throughout the five sample data of dataset IV a from 2005 BCI Competition, we utilized short-time Fourier transform (STFT) and correlation coefficient calculation to reduce the number of primitive electroencephalogram dimension, then introduced feature extraction based on common spatial pattern (CSP) and classified by linear discriminant analysis (LDA). Simulation results showed that the average rate of classification accuracy could be improved by using correlation coefficient feature selection method than those without using this algorithm. Comparing with support vector machine (SVM) optimization features algorithm, the correlation coefficient analysis can lead better selection parameters to improve the accuracy of classification.

Magnetoencephalogram blind source separation and component selection procedure to improve the diagnosis of Alzheimer's disease patients.

PubMed

Escudero, Javier; Hornero, Roberto; Abásolo, Daniel; Fernández, Alberto; Poza, Jesús

2007-01-01

The aim of this study was to improve the diagnosis of Alzheimer's disease (AD) patients applying a blind source separation (BSS) and component selection procedure to their magnetoencephalogram (MEG) recordings. MEGs from 18 AD patients and 18 control subjects were decomposed with the algorithm for multiple unknown signals extraction. MEG channels and components were characterized by their mean frequency, spectral entropy, approximate entropy, and Lempel-Ziv complexity. Using Student's t-test, the components which accounted for the most significant differences between groups were selected. Then, these relevant components were used to partially reconstruct the MEG channels. By means of a linear discriminant analysis, we found that the BSS-preprocessed MEGs classified the subjects with an accuracy of 80.6%, whereas 72.2% accuracy was obtained without the BSS and component selection procedure.

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

Warmack, Robert J. Bruce; Wolf, Dennis A.; Frank, Steven Shane

Various apparatus and methods for smoke detection are disclosed. In one embodiment, a method of training a classifier for a smoke detector comprises inputting sensor data from a plurality of tests into a processor. The sensor data is processed to generate derived signal data corresponding to the test data for respective tests. The derived signal data is assigned into categories comprising at least one fire group and at least one non-fire group. Linear discriminant analysis (LDA) training is performed by the processor. The derived signal data and the assigned categories for the derived signal data are inputs to the LDAmore » training. The output of the LDA training is stored in a computer readable medium, such as in a smoke detector that uses LDA to determine, based on the training, whether present conditions indicate the existence of a fire.« less

Comparing success levels of different neural network structures in extracting discriminative information from the response patterns of a temperature-modulated resistive gas sensor

NASA Astrophysics Data System (ADS)

Hosseini-Golgoo, S. M.; Bozorgi, H.; Saberkari, A.

2015-06-01

Performances of three neural networks, consisting of a multi-layer perceptron, a radial basis function, and a neuro-fuzzy network with local linear model tree training algorithm, in modeling and extracting discriminative features from the response patterns of a temperature-modulated resistive gas sensor are quantitatively compared. For response pattern recording, a voltage staircase containing five steps each with a 20 s plateau is applied to the micro-heater of the sensor, when 12 different target gases, each at 11 concentration levels, are present. In each test, the hidden layer neuron weights are taken as the discriminatory feature vector of the target gas. These vectors are then mapped to a 3D feature space using linear discriminant analysis. The discriminative information content of the feature vectors are determined by the calculation of the Fisher’s discriminant ratio, affording quantitative comparison among the success rates achieved by the different neural network structures. The results demonstrate a superior discrimination ratio for features extracted from local linear neuro-fuzzy and radial-basis-function networks with recognition rates of 96.27% and 90.74%, respectively.

Resonance Raman Spectroscopy of human brain metastasis of lung cancer analyzed by blind source separation

NASA Astrophysics Data System (ADS)

Zhou, Yan; Liu, Cheng-Hui; Pu, Yang; Cheng, Gangge; Yu, Xinguang; Zhou, Lixin; Lin, Dongmei; Zhu, Ke; Alfano, Robert R.

2017-02-01

Resonance Raman (RR) spectroscopy offers a novel Optical Biopsy method in cancer discrimination by a means of enhancement in Raman scattering. It is widely acknowledged that the RR spectrum of tissue is a superposition of spectra of various key building block molecules. In this study, the Resonance Raman (RR) spectra of human metastasis of lung cancerous and normal brain tissues excited by a visible selected wavelength at 532 nm are used to explore spectral changes caused by the tumor evolution. The potential application of RR spectra human brain metastasis of lung cancer was investigated by Blind Source Separation such as Principal Component Analysis (PCA). PCA is a statistical procedure that uses an orthogonal transformation to convert a set of observations of possibly correlated variables into a set of values of linearly uncorrelated variables called principal components (PCs). The results show significant RR spectra difference between human metastasis of lung cancerous and normal brain tissues analyzed by PCA. To evaluate the efficacy of for cancer detection, a linear discriminant analysis (LDA) classifier is utilized to calculate the sensitivity, and specificity and the receiver operating characteristic (ROC) curves are used to evaluate the performance of this criterion. Excellent sensitivity of 0.97, specificity (close to 1.00) and the Area Under ROC Curve (AUC) of 0.99 values are achieved under best optimal circumstance. This research demonstrates that RR spectroscopy is effective for detecting changes of tissues due to the development of brain metastasis of lung cancer. RR spectroscopy analyzed by blind source separation may have potential to be a new armamentarium.

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.

Detection of radiation-induced brain necrosis in live rats using label-free time-resolved fluorescence spectroscopy (TRFS) (Conference Presentation)

NASA Astrophysics Data System (ADS)

Hartl, Brad A.; Ma, Htet S. W.; Sridharan, Shamira; Hansen, Katherine; Klich, Melanie; Perks, Julian; Kent, Michael; Kim, Kyoungmi; Fragoso, Ruben; Marcu, Laura

2017-02-01

Differentiating radiation-induced necrosis from recurrent tumor in the brain remains a significant challenge to the neurosurgeon. Clinical imaging modalities are not able to reliably discriminate the two tissue types, making biopsy location selection and surgical management difficult. Label-free fluorescence lifetime techniques have previously been shown to be able to delineate human brain tumor from healthy tissues. Thus, fluorescence lifetime techniques represent a potential means to discriminate the two tissues in real-time during surgery. This study aims to characterize the endogenous fluorescence lifetime signatures from radiation induced brain necrosis in a tumor-free rat model. Fischer rats received a single fraction of 60 Gy of radiation to the right hemisphere using a linear accelerator. Animals underwent a terminal live surgery after gross necrosis had developed, as verified with MRI. During surgery, healthy and necrotic brain tissue was measured with a fiber optic needle connected to a multispectral fluorescence lifetime system. Measurements of the necrotic tissue showed a 48% decrease in intensity and 20% increase in lifetimes relative to healthy tissue. Using a support vector machine classifier and leave-one-out validation technique, the necrotic tissue was correctly classified with 94% sensitivity and 97% specificity. Spectral contribution analysis also confirmed that the primary source of fluorescence contrast lies within the redox and bound-unbound population shifts of nicotinamide adenine dinucleotide. A clinical trial is presently underway to measure these tissue types in humans. These results show for the first time that radiation-induced necrotic tissue in the brain contains significantly different metabolic signatures that are detectable with label-free fluorescence lifetime techniques.

Identifying Neural Patterns of Functional Dyspepsia Using Multivariate Pattern Analysis: A Resting-State fMRI Study

PubMed Central

Liu, Peng; Qin, Wei; Wang, Jingjing; Zeng, Fang; Zhou, Guangyu; Wen, Haixia; von Deneen, Karen M.; Liang, Fanrong; Gong, Qiyong; Tian, Jie

2013-01-01

Background Previous imaging studies on functional dyspepsia (FD) have focused on abnormal brain functions during special tasks, while few studies concentrated on the resting-state abnormalities of FD patients, which might be potentially valuable to provide us with direct information about the neural basis of FD. The main purpose of the current study was thereby to characterize the distinct patterns of resting-state function between FD patients and healthy controls (HCs). Methodology/Principal Findings Thirty FD patients and thirty HCs were enrolled and experienced 5-mintue resting-state scanning. Based on the support vector machine (SVM), we applied multivariate pattern analysis (MVPA) to investigate the differences of resting-state function mapped by regional homogeneity (ReHo). A classifier was designed by using the principal component analysis and the linear SVM. Permutation test was then employed to identify the significant contribution to the final discrimination. The results displayed that the mean classifier accuracy was 86.67%, and highly discriminative brain regions mainly included the prefrontal cortex (PFC), orbitofrontal cortex (OFC), supplementary motor area (SMA), temporal pole (TP), insula, anterior/middle cingulate cortex (ACC/MCC), thalamus, hippocampus (HIPP)/parahippocamus (ParaHIPP) and cerebellum. Correlation analysis revealed significant correlations between ReHo values in certain regions of interest (ROI) and the FD symptom severity and/or duration, including the positive correlations between the dmPFC, pACC and the symptom severity; whereas, the positive correlations between the MCC, OFC, insula, TP and FD duration. Conclusions These findings indicated that significantly distinct patterns existed between FD patients and HCs during the resting-state, which could expand our understanding of the neural basis of FD. Meanwhile, our results possibly showed potential feasibility of functional magnetic resonance imaging diagnostic assay for FD. PMID:23874543

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

NASA Astrophysics Data System (ADS)

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

2016-12-01

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

Structures of the Recurrence Plot of Heart Rate Variability Signal as a Tool for Predicting the Onset of Paroxysmal Atrial Fibrillation

PubMed Central

Mohebbi, Maryam; Ghassemian, Hassan; Asl, Babak Mohammadzadeh

2011-01-01

This paper aims to propose an effective paroxysmal atrial fibrillation (PAF) predictor which is based on the analysis of the heart rate variability (HRV) signal. Predicting the onset of PAF, based on non-invasive techniques, is clinically important and can be invaluable in order to avoid useless therapeutic interventions and to minimize the risks for the patients. This method consists of four steps: Preprocessing, feature extraction, feature reduction, and classification. In the first step, the QRS complexes are detected from the electrocardiogram (ECG) signal and then the HRV signal is extracted. In the next step, the recurrence plot (RP) of HRV signal is obtained and six features are extracted to characterize the basic patterns of the RP. These features consist of length of longest diagonal segments, average length of the diagonal lines, entropy, trapping time, length of longest vertical line, and recurrence trend. In the third step, these features are reduced to three features by the linear discriminant analysis (LDA) technique. Using LDA not only reduces the number of the input features, but also increases the classification accuracy by selecting the most discriminating features. Finally, a support vector machine-based classifier is used to classify the HRV signals. The performance of the proposed method in prediction of PAF episodes was evaluated using the Atrial Fibrillation Prediction Database which consists of both 30-minutes ECG recordings end just prior to the onset of PAF and segments at least 45 min distant from any PAF events. The obtained sensitivity, specificity, and positive predictivity were 96.55%, 100%, and 100%, respectively. PMID:22606666

Detection of Aspens Using High Resolution Aerial Laser Scanning Data and Digital Aerial Images

PubMed Central

Säynäjoki, Raita; Packalén, Petteri; Maltamo, Matti; Vehmas, Mikko; Eerikäinen, Kalle

2008-01-01

The aim was to use high resolution Aerial Laser Scanning (ALS) data and aerial images to detect European aspen (Populus tremula L.) from among other deciduous trees. The field data consisted of 14 sample plots of 30 m × 30 m size located in the Koli National Park in the North Karelia, Eastern Finland. A Canopy Height Model (CHM) was interpolated from the ALS data with a pulse density of 3.86/m2, low-pass filtered using Height-Based Filtering (HBF) and binarized to create the mask needed to separate the ground pixels from the canopy pixels within individual areas. Watershed segmentation was applied to the low-pass filtered CHM in order to create preliminary canopy segments, from which the non-canopy elements were extracted to obtain the final canopy segmentation, i.e. the ground mask was analysed against the canopy mask. A manual classification of aerial images was employed to separate the canopy segments of deciduous trees from those of coniferous trees. Finally, linear discriminant analysis was applied to the correctly classified canopy segments of deciduous trees to classify them into segments belonging to aspen and those belonging to other deciduous trees. The independent variables used in the classification were obtained from the first pulse ALS point data. The accuracy of discrimination between aspen and other deciduous trees was 78.6%. The independent variables in the classification function were the proportion of vegetation hits, the standard deviation of in pulse heights, accumulated intensity at the 90th percentile and the proportion of laser points reflected at the 60th height percentile. The accuracy of classification corresponded to the validation results of earlier ALS-based studies on the classification of individual deciduous trees to tree species. PMID:27873799

Identification of wheat varieties with a parallel-plate capacitance sensor using fisher linear discriminant analysis

USDA-ARS?s Scientific Manuscript database

Fisher’s linear discriminant (FLD) models for wheat variety classification were developed and validated. The inputs to the FLD models were the capacitance (C), impedance (Z), and phase angle ('), measured at two frequencies. Classification of wheat varieties was obtained as output of the FLD mod...

Robust linear discriminant analysis with distance based estimators

NASA Astrophysics Data System (ADS)

Lim, Yai-Fung; Yahaya, Sharipah Soaad Syed; Ali, Hazlina

2017-11-01

Linear discriminant analysis (LDA) is one of the supervised classification techniques concerning relationship between a categorical variable and a set of continuous variables. The main objective of LDA is to create a function to distinguish between populations and allocating future observations to previously defined populations. Under the assumptions of normality and homoscedasticity, the LDA yields optimal linear discriminant rule (LDR) between two or more groups. However, the optimality of LDA highly relies on the sample mean and pooled sample covariance matrix which are known to be sensitive to outliers. To alleviate these conflicts, a new robust LDA using distance based estimators known as minimum variance vector (MVV) has been proposed in this study. The MVV estimators were used to substitute the classical sample mean and classical sample covariance to form a robust linear discriminant rule (RLDR). Simulation and real data study were conducted to examine on the performance of the proposed RLDR measured in terms of misclassification error rates. The computational result showed that the proposed RLDR is better than the classical LDR and was comparable with the existing robust LDR.

Enhancement of Plant Metabolite Fingerprinting by Machine Learning1[W

PubMed Central

Scott, Ian M.; Vermeer, Cornelia P.; Liakata, Maria; Corol, Delia I.; Ward, Jane L.; Lin, Wanchang; Johnson, Helen E.; Whitehead, Lynne; Kular, Baldeep; Baker, John M.; Walsh, Sean; Dave, Anuja; Larson, Tony R.; Graham, Ian A.; Wang, Trevor L.; King, Ross D.; Draper, John; Beale, Michael H.

2010-01-01

Metabolite fingerprinting of Arabidopsis (Arabidopsis thaliana) mutants with known or predicted metabolic lesions was performed by 1H-nuclear magnetic resonance, Fourier transform infrared, and flow injection electrospray-mass spectrometry. Fingerprinting enabled processing of five times more plants than conventional chromatographic profiling and was competitive for discriminating mutants, other than those affected in only low-abundance metabolites. Despite their rapidity and complexity, fingerprints yielded metabolomic insights (e.g. that effects of single lesions were usually not confined to individual pathways). Among fingerprint techniques, 1H-nuclear magnetic resonance discriminated the most mutant phenotypes from the wild type and Fourier transform infrared discriminated the fewest. To maximize information from fingerprints, data analysis was crucial. One-third of distinctive phenotypes might have been overlooked had data models been confined to principal component analysis score plots. Among several methods tested, machine learning (ML) algorithms, namely support vector machine or random forest (RF) classifiers, were unsurpassed for phenotype discrimination. Support vector machines were often the best performing classifiers, but RFs yielded some particularly informative measures. First, RFs estimated margins between mutant phenotypes, whose relations could then be visualized by Sammon mapping or hierarchical clustering. Second, RFs provided importance scores for the features within fingerprints that discriminated mutants. These scores correlated with analysis of variance F values (as did Kruskal-Wallis tests, true- and false-positive measures, mutual information, and the Relief feature selection algorithm). ML classifiers, as models trained on one data set to predict another, were ideal for focused metabolomic queries, such as the distinctiveness and consistency of mutant phenotypes. Accessible software for use of ML in plant physiology is highlighted. PMID:20566707

Gas Sensors Characterization and Multilayer Perceptron (MLP) Hardware Implementation for Gas Identification Using a Field Programmable Gate Array (FPGA)

PubMed Central

Benrekia, Fayçal; Attari, Mokhtar; Bouhedda, Mounir

2013-01-01

This paper develops a primitive gas recognition system for discriminating between industrial gas species. The system under investigation consists of an array of eight micro-hotplate-based SnO2 thin film gas sensors with different selectivity patterns. The output signals are processed through a signal conditioning and analyzing system. These signals feed a decision-making classifier, which is obtained via a Field Programmable Gate Array (FPGA) with Very High-Speed Integrated Circuit Hardware Description Language. The classifier relies on a multilayer neural network based on a back propagation algorithm with one hidden layer of four neurons and eight neurons at the input and five neurons at the output. The neural network designed after implementation consists of twenty thousand gates. The achieved experimental results seem to show the effectiveness of the proposed classifier, which can discriminate between five industrial gases. PMID:23529119

Rapid discrimination of bergamot essential oil by paper spray mass spectrometry and chemometric analysis.

PubMed

Taverna, Domenico; Di Donna, Leonardo; Mazzotti, Fabio; Tagarelli, Antonio; Napoli, Anna; Furia, Emilia; Sindona, Giovanni

2016-09-01

A novel approach for the rapid discrimination of bergamot essential oil from other citrus fruits oils is presented. The method was developed using paper spray mass spectrometry (PS-MS) allowing for a rapid molecular profiling coupled with a statistic tool for a precise and reliable discrimination between the bergamot complex matrix and other similar matrices, commonly used for its reconstitution. Ambient mass spectrometry possesses the ability to record mass spectra of ordinary samples, in their native environment, without sample preparation or pre-separation by creating ions outside the instrument. The present study reports a PS-MS method for the determination of oxygen heterocyclic compounds such as furocoumarins, psoralens and flavonoids present in the non-volatile fraction of citrus fruits essential oils followed by chemometric analysis. The volatile fraction of Bergamot is one of the most known and fashionable natural products, which found applications in flavoring industry as ingredient in beverages and flavored foodstuff. The development of the presented method employed bergamot, sweet orange, orange, cedar, grapefruit and mandarin essential oils. PS-MS measurements were carried out in full scan mode for a total run time of 2 min. The capability of PS-MS profiling to act as marker for the classification of bergamot essential oils was evaluated by using multivariate statistical analysis. Two pattern recognition techniques, linear discriminant analysis and soft independent modeling of class analogy, were applied to MS data. The cross-validation procedure has shown excellent results in terms of the prediction ability because both models have correctly classified all samples for each category. Copyright © 2016 John Wiley & Sons, Ltd. Copyright © 2016 John Wiley & Sons, Ltd.

Reliable Entity Subtyping in Non-small Cell Lung Cancer by Matrix-assisted Laser Desorption/Ionization Imaging Mass Spectrometry on Formalin-fixed Paraffin-embedded Tissue Specimens*

PubMed Central

Kriegsmann, Mark; Casadonte, Rita; Kriegsmann, Jörg; Dienemann, Hendrik; Schirmacher, Peter; Hendrik Kobarg, Jan; Schwamborn, Kristina; Stenzinger, Albrecht; Warth, Arne; Weichert, Wilko

2016-01-01

Histopathological subtyping of non-small cell lung cancer (NSCLC) into adenocarcinoma (ADC), and squamous cell carcinoma (SqCC) is of utmost relevance for treatment stratification. However, current immunohistochemistry (IHC) based typing approaches on biopsies are imperfect, therefore novel analytical methods for reliable subtyping are needed. We analyzed formalin-fixed paraffin-embedded tissue cores of NSCLC by Matrix-assisted laser desorption/ionization (MALDI) imaging on tissue microarrays to identify and validate discriminating MALDI imaging profiles for NSCLC subtyping. 110 ADC and 98 SqCC were used to train a Linear Discriminant Analysis (LDA) model. Results were validated on a separate set of 58 ADC and 60 SqCC. Selected differentially expressed proteins were identified by tandem mass spectrometry and validated by IHC. The LDA classification model incorporated 339 m/z values. In the validation cohort, in 117 cases (99.1%) MALDI classification on tissue cores was in accordance with the pathological diagnosis made on resection specimen. Overall, three cases in the combined cohorts were discordant, after reevaluation two were initially misclassified by pathology whereas one was classified incorrectly by MALDI. Identification of differentially expressed peptides detected well-known IHC discriminators (CK5, CK7), but also less well known differentially expressed proteins (CK15, HSP27). In conclusion, MALDI imaging on NSCLC tissue cores as small biopsy equivalents is capable to discriminate lung ADC and SqCC with a very high accuracy. In addition, replacing multislide IHC by an one-slide MALDI approach may also save tissue for subsequent predictive molecular testing. We therefore advocate to pursue routine diagnostic implementation strategies for MALDI imaging in solid tumor typing. PMID:27473201

Reliable Entity Subtyping in Non-small Cell Lung Cancer by Matrix-assisted Laser Desorption/Ionization Imaging Mass Spectrometry on Formalin-fixed Paraffin-embedded Tissue Specimens.

PubMed

Kriegsmann, Mark; Casadonte, Rita; Kriegsmann, Jörg; Dienemann, Hendrik; Schirmacher, Peter; Hendrik Kobarg, Jan; Schwamborn, Kristina; Stenzinger, Albrecht; Warth, Arne; Weichert, Wilko

2016-10-01

Histopathological subtyping of non-small cell lung cancer (NSCLC) into adenocarcinoma (ADC), and squamous cell carcinoma (SqCC) is of utmost relevance for treatment stratification. However, current immunohistochemistry (IHC) based typing approaches on biopsies are imperfect, therefore novel analytical methods for reliable subtyping are needed. We analyzed formalin-fixed paraffin-embedded tissue cores of NSCLC by Matrix-assisted laser desorption/ionization (MALDI) imaging on tissue microarrays to identify and validate discriminating MALDI imaging profiles for NSCLC subtyping. 110 ADC and 98 SqCC were used to train a Linear Discriminant Analysis (LDA) model. Results were validated on a separate set of 58 ADC and 60 SqCC. Selected differentially expressed proteins were identified by tandem mass spectrometry and validated by IHC. The LDA classification model incorporated 339 m/z values. In the validation cohort, in 117 cases (99.1%) MALDI classification on tissue cores was in accordance with the pathological diagnosis made on resection specimen. Overall, three cases in the combined cohorts were discordant, after reevaluation two were initially misclassified by pathology whereas one was classified incorrectly by MALDI. Identification of differentially expressed peptides detected well-known IHC discriminators (CK5, CK7), but also less well known differentially expressed proteins (CK15, HSP27). In conclusion, MALDI imaging on NSCLC tissue cores as small biopsy equivalents is capable to discriminate lung ADC and SqCC with a very high accuracy. In addition, replacing multislide IHC by an one-slide MALDI approach may also save tissue for subsequent predictive molecular testing. We therefore advocate to pursue routine diagnostic implementation strategies for MALDI imaging in solid tumor typing. © 2016 by The American Society for Biochemistry and Molecular Biology, Inc.

Feature extraction and selection from volatile compounds for analytical classification of Chinese red wines from different varieties.

PubMed

Zhang, Jian; Li, Li; Gao, Nianfa; Wang, Depei; Gao, Qiang; Jiang, Shengping

2010-03-10

This work was undertaken to evaluate whether it is possible to determine the variety of a Chinese wine on the basis of its volatile compounds, and to investigate if discrimination models could be developed with the experimental wines that could be used for the commercial ones. A headspace solid-phase microextraction gas chromatographic (HS-SPME-GC) procedure was used to determine the volatile compounds and a blind analysis based on Ac/Ais (peak area of volatile compound/peak area of internal standard) was carried out for statistical purposes. One way analysis of variance (ANOVA), principal component analysis (PCA) and stepwise linear discriminant analysis (SLDA) were used to process data and to develop discriminant models. Only 11 peaks enabled to differentiate and classify the experimental wines. SLDA allowed 100% recognition ability for three grape varieties, 100% prediction ability for Cabernet Sauvignon and Cabernet Gernischt wines, but only 92.31% for Merlot wines. A more valid and robust way was to use the PCA scores to do the discriminant analysis. When we performed SLDA this way, 100% recognition ability and 100% prediction ability were obtained. At last, 11 peaks which selected by SLDA from raw analysis set had been identified. When we demonstrated the models using commercial wines, the models showed 100% recognition ability for the wines collected directly from winery and without ageing, but only 65% for the others. Therefore, the varietal factor was currently discredited as a differentiating parameter for commercial wines in China. Nevertheless, this method could be applied as a screening tool and as a complement to other methods for grape base liquors which do not need ageing and blending procedures. 2010 Elsevier B.V. All rights reserved.

A comparison between ten advanced and soft computing models for groundwater qanat potential assessment in Iran using R and GIS

NASA Astrophysics Data System (ADS)

Naghibi, Seyed Amir; Pourghasemi, Hamid Reza; Abbaspour, Karim

2018-02-01

Considering the unstable condition of water resources in Iran and many other countries in arid and semi-arid regions, groundwater studies are very important. Therefore, the aim of this study is to model groundwater potential by qanat locations as indicators and ten advanced and soft computing models applied to the Beheshtabad Watershed, Iran. Qanat is a man-made underground construction which gathers groundwater from higher altitudes and transmits it to low land areas where it can be used for different purposes. For this purpose, at first, the location of the qanats was detected using extensive field surveys. These qanats were classified into two datasets including training (70%) and validation (30%). Then, 14 influence factors depicting the region's physical, morphological, lithological, and hydrological features were identified to model groundwater potential. Linear discriminant analysis (LDA), quadratic discriminant analysis (QDA), flexible discriminant analysis (FDA), penalized discriminant analysis (PDA), boosted regression tree (BRT), random forest (RF), artificial neural network (ANN), K-nearest neighbor (KNN), multivariate adaptive regression splines (MARS), and support vector machine (SVM) models were applied in R scripts to produce groundwater potential maps. For evaluation of the performance accuracies of the developed models, ROC curve and kappa index were implemented. According to the results, RF had the best performance, followed by SVM and BRT models. Our results showed that qanat locations could be used as a good indicator for groundwater potential. Furthermore, altitude, slope, plan curvature, and profile curvature were found to be the most important influence factors. On the other hand, lithology, land use, and slope aspect were the least significant factors. The methodology in the current study could be used by land use and terrestrial planners and water resource managers to reduce the costs of groundwater resource discovery.

Genetic network inference as a series of discrimination tasks.

PubMed

Kimura, Shuhei; Nakayama, Satoshi; Hatakeyama, Mariko

2009-04-01

Genetic network inference methods based on sets of differential equations generally require a great deal of time, as the equations must be solved many times. To reduce the computational cost, researchers have proposed other methods for inferring genetic networks by solving sets of differential equations only a few times, or even without solving them at all. When we try to obtain reasonable network models using these methods, however, we must estimate the time derivatives of the gene expression levels with great precision. In this study, we propose a new method to overcome the drawbacks of inference methods based on sets of differential equations. Our method infers genetic networks by obtaining classifiers capable of predicting the signs of the derivatives of the gene expression levels. For this purpose, we defined a genetic network inference problem as a series of discrimination tasks, then solved the defined series of discrimination tasks with a linear programming machine. Our experimental results demonstrated that the proposed method is capable of correctly inferring genetic networks, and doing so more than 500 times faster than the other inference methods based on sets of differential equations. Next, we applied our method to actual expression data of the bacterial SOS DNA repair system. And finally, we demonstrated that our approach relates to the inference method based on the S-system model. Though our method provides no estimation of the kinetic parameters, it should be useful for researchers interested only in the network structure of a target system. Supplementary data are available at Bioinformatics online.

Multivariate analysis of volatile compounds detected by headspace solid-phase microextraction/gas chromatography: A tool for sensory classification of cork stoppers.

PubMed

Prat, Chantal; Besalú, Emili; Bañeras, Lluís; Anticó, Enriqueta

2011-06-15

The volatile fraction of aqueous cork macerates of tainted and non-tainted agglomerate cork stoppers was analysed by headspace solid-phase microextraction (HS-SPME)/gas chromatography. Twenty compounds containing terpenoids, aliphatic alcohols, lignin-related compounds and others were selected and analysed in individual corks. Cork stoppers were previously classified in six different classes according to sensory descriptions including, 2,4,6-trichloroanisole taint and other frequent, non-characteristic odours found in cork. A multivariate analysis of the chromatographic data of 20 selected chemical compounds using linear discriminant analysis models helped in the differentiation of the a priori made groups. The discriminant model selected five compounds as the best combination. Selected compounds appear in the model in the following order; 2,4,6 TCA, fenchyl alcohol, 1-octen-3-ol, benzyl alcohol and benzothiazole. Unfortunately, not all six a priori differentiated sensory classes were clearly discriminated in the model, probably indicating that no measurable differences exist in the chromatographic data for some categories. The predictive analyses of a refined model in which two sensory classes were fused together resulted in a good classification. Prediction rates of control (non-tainted), TCA, musty-earthy-vegetative, vegetative and chemical descriptions were 100%, 100%, 85%, 67.3% and 100%, respectively, when the modified model was used. The multivariate analysis of chromatographic data will help in the classification of stoppers and provide a perfect complement to sensory analyses. Copyright © 2010 Elsevier Ltd. All rights reserved.

Standoff detection of chemical and biological threats using laser-induced breakdown spectroscopy.

PubMed

Gottfried, Jennifer L; De Lucia, Frank C; Munson, Chase A; Miziolek, Andrzej W

2008-04-01

Laser-induced breakdown spectroscopy (LIBS) is a promising technique for real-time chemical and biological warfare agent detection in the field. We have demonstrated the detection and discrimination of the biological warfare agent surrogates Bacillus subtilis (BG) (2% false negatives, 0% false positives) and ovalbumin (0% false negatives, 1% false positives) at 20 meters using standoff laser-induced breakdown spectroscopy (ST-LIBS) and linear correlation. Unknown interferent samples (not included in the model), samples on different substrates, and mixtures of BG and Arizona road dust have been classified with reasonable success using partial least squares discriminant analysis (PLS-DA). A few of the samples tested such as the soot (not included in the model) and the 25% BG:75% dust mixture resulted in a significant number of false positives or false negatives, respectively. Our preliminary results indicate that while LIBS is able to discriminate biomaterials with similar elemental compositions at standoff distances based on differences in key intensity ratios, further work is needed to reduce the number of false positives/negatives by refining the PLS-DA model to include a sufficient range of material classes and carefully selecting a detection threshold. In addition, we have demonstrated that LIBS can distinguish five different organophosphate nerve agent simulants at 20 meters, despite their similar stoichiometric formulas. Finally, a combined PLS-DA model for chemical, biological, and explosives detection using a single ST-LIBS sensor has been developed in order to demonstrate the potential of standoff LIBS for universal hazardous materials detection.

Improved pulse shape discriminator for fast neutron-gamma ray detection system

NASA Technical Reports Server (NTRS)

Lockwood, J. A.; St. Onge, R.

1969-01-01

Discriminator in nuclear particle detection system distinguishes nuclear particle type and energy among many different nuclear particles. Discriminator incorporates passive, linear circuit elements so that it will operate over a wide dynamic range.

Texture- and deformability-based surface recognition by tactile image analysis.

PubMed

Khasnobish, Anwesha; Pal, Monalisa; Tibarewala, D N; Konar, Amit; Pal, Kunal

2016-08-01

Deformability and texture are two unique object characteristics which are essential for appropriate surface recognition by tactile exploration. Tactile sensation is required to be incorporated in artificial arms for rehabilitative and other human-computer interface applications to achieve efficient and human-like manoeuvring. To accomplish the same, surface recognition by tactile data analysis is one of the prerequisites. The aim of this work is to develop effective technique for identification of various surfaces based on deformability and texture by analysing tactile images which are obtained during dynamic exploration of the item by artificial arms whose gripper is fitted with tactile sensors. Tactile data have been acquired, while human beings as well as a robot hand fitted with tactile sensors explored the objects. The tactile images are pre-processed, and relevant features are extracted from the tactile images. These features are provided as input to the variants of support vector machine (SVM), linear discriminant analysis and k-nearest neighbour (kNN) for classification. Based on deformability, six household surfaces are recognized from their corresponding tactile images. Moreover, based on texture five surfaces of daily use are classified. The method adopted in the former two cases has also been applied for deformability- and texture-based recognition of four biomembranes, i.e. membranes prepared from biomaterials which can be used for various applications such as drug delivery and implants. Linear SVM performed best for recognizing surface deformability with an accuracy of 83 % in 82.60 ms, whereas kNN classifier recognizes surfaces of daily use having different textures with an accuracy of 89 % in 54.25 ms and SVM with radial basis function kernel recognizes biomembranes with an accuracy of 78 % in 53.35 ms. The classifiers are observed to generalize well on the unseen test datasets with very high performance to achieve efficient material recognition based on its deformability and texture.

Development and validation of a clinically applicable score to classify cachexia stages in advanced cancer patients

PubMed Central

Zhou, Ting; Wang, Bangyan; Liu, Huiquan; Yang, Kaixiang; Thapa, Sudip; Zhang, Haowen; Li, Lu

2018-01-01

Abstract Background Cachexia is a multifactorial syndrome that is highly prevalent in advanced cancer patients and leads to progressive functional impairments. The classification of cachexia stages is essential for diagnosing and treating cachexia. However, there is a lack of simple tools with good discrimination for classifying cachexia stages. Therefore, our study aimed to develop a clinically applicable cachexia staging score (CSS) and validate its discrimination of clinical outcomes for different cachexia stages. Methods Advanced cancer patients were enrolled in our study. A CSS comprising the following five components was developed: weight loss, a simple questionnaire of sarcopenia (SARC‐F), Eastern Cooperative Oncology Group, appetite loss, and abnormal biochemistry. According to the CSS, patients were classified into non‐cachexia, pre‐cachexia, cachexia, and refractory cachexia stages, and clinical outcomes were compared among the four groups. Results Of the 297 participating patients, data from 259 patients were ultimately included. Based on the CSS, patients were classified into non‐cachexia (n = 69), pre‐cachexia (n = 68), cachexia (n = 103), and refractory cachexia (n = 19) stages. Patients with more severe cachexia stages had lower skeletal muscle indexes (P = 0.002 and P = 0.004 in male and female patients, respectively), higher prevalence of sarcopenia (P = 0.017 and P = 0.027 in male and female patients, respectively), more severe symptom burden (P < 0.001), poorer quality of life (P < 0.001 for all subscales except social well‐being), and shorter survival times (P < 0.001). Conclusions The CSS is a simple and clinically applicable tool with excellent discrimination for classifying cachexia stages. This score is extremely useful for the clinical treatment and prognosis of cachexia and for designing clinical trials. PMID:29372594

Sex determination of the Acadian Flycatcher using discriminant analysis

USGS Publications Warehouse

Wilson, R.R.

1999-01-01

I used five morphometric variables from 114 individuals captured in Arkansas to develop a discriminant model to predict the sex of Acadian Flycatchers (Empidonax virescens). Stepwise discriminant function analyses selected wing chord and tail length as the most parsimonious subset of variables for discriminating sex. This two-variable model correctly classified 80% of females and 97% of males used to develop the model. Validation of the model using 19 individuals from Louisiana and Virginia resulted in 100% correct classification of males and females. This model provides criteria for sexing monomorphic Acadian Flycatchers during the breeding season and possibly during the winter.

Fast discrimination of traditional Chinese medicine according to geographical origins with FTIR spectroscopy and advanced pattern recognition techniques

NASA Astrophysics Data System (ADS)

Li, Ning; Wang, Yan; Xu, Kexin

2006-08-01

Combined with Fourier transform infrared (FTIR) spectroscopy and three kinds of pattern recognition techniques, 53 traditional Chinese medicine danshen samples were rapidly discriminated according to geographical origins. The results showed that it was feasible to discriminate using FTIR spectroscopy ascertained by principal component analysis (PCA). An effective model was built by employing the Soft Independent Modeling of Class Analogy (SIMCA) and PCA, and 82% of the samples were discriminated correctly. Through use of the artificial neural network (ANN)-based back propagation (BP) network, the origins of danshen were completely classified.

Raman spectroscopy for highly accurate estimation of the age of refrigerated porcine muscle

NASA Astrophysics Data System (ADS)

Timinis, Constantinos; Pitris, Costas

2016-03-01

The high water content of meat, combined with all the nutrients it contains, make it vulnerable to spoilage at all stages of production and storage even when refrigerated at 5 °C. A non-destructive and in situ tool for meat sample testing, which could provide an accurate indication of the storage time of meat, would be very useful for the control of meat quality as well as for consumer safety. The proposed solution is based on Raman spectroscopy which is non-invasive and can be applied in situ. For the purposes of this project, 42 meat samples from 14 animals were obtained and three Raman spectra per sample were collected every two days for two weeks. The spectra were subsequently processed and the sample age was calculated using a set of linear differential equations. In addition, the samples were classified in categories corresponding to the age in 2-day steps (i.e., 0, 2, 4, 6, 8, 10, 12 or 14 days old), using linear discriminant analysis and cross-validation. Contrary to other studies, where the samples were simply grouped into two categories (higher or lower quality, suitable or unsuitable for human consumption, etc.), in this study, the age was predicted with a mean error of ~ 1 day (20%) or classified, in 2-day steps, with 100% accuracy. Although Raman spectroscopy has been used in the past for the analysis of meat samples, the proposed methodology has resulted in a prediction of the sample age far more accurately than any report in the literature.

Distinguishing prostate cancer from benign confounders via a cascaded classifier on multi-parametric MRI

NASA Astrophysics Data System (ADS)

Litjens, G. J. S.; Elliott, R.; Shih, N.; Feldman, M.; Barentsz, J. O.; Hulsbergen-van de Kaa, C. A.; Kovacs, I.; Huisman, H. J.; Madabhushi, A.

2014-03-01

Learning how to separate benign confounders from prostate cancer is important because the imaging characteristics of these confounders are poorly understood. Furthermore, the typical representations of the MRI parameters might not be enough to allow discrimination. The diagnostic uncertainty this causes leads to a lower diagnostic accuracy. In this paper a new cascaded classifier is introduced to separate prostate cancer and benign confounders on MRI in conjunction with specific computer-extracted features to distinguish each of the benign classes (benign prostatic hyperplasia (BPH), inflammation, atrophy or prostatic intra-epithelial neoplasia (PIN). In this study we tried to (1) calculate different mathematical representations of the MRI parameters which more clearly express subtle differences between different classes, (2) learn which of the MRI image features will allow to distinguish specific benign confounders from prostate cancer, and (2) find the combination of computer-extracted MRI features to best discriminate cancer from the confounding classes using a cascaded classifier. One of the most important requirements for identifying MRI signatures for adenocarcinoma, BPH, atrophy, inflammation, and PIN is accurate mapping of the location and spatial extent of the confounder and cancer categories from ex vivo histopathology to MRI. Towards this end we employed an annotated prostatectomy data set of 31 patients, all of whom underwent a multi-parametric 3 Tesla MRI prior to radical prostatectomy. The prostatectomy slides were carefully co-registered to the corresponding MRI slices using an elastic registration technique. We extracted texture features from the T2-weighted imaging, pharmacokinetic features from the dynamic contrast enhanced imaging and diffusion features from the diffusion-weighted imaging for each of the confounder classes and prostate cancer. These features were selected because they form the mainstay of clinical diagnosis. Relevant features for each of the classes were selected using maximum relevance minimum redundancy feature selection, allowing us to perform classifier independent feature selection. The selected features were then incorporated in a cascading classifier, which can focus on easier sub-tasks at each stage, leaving the more difficult classification tasks for later stages. Results show that distinct features are relevant for each of the benign classes, for example the fraction of extra-vascular, extra-cellular space in a voxel is a clear discriminator for inflammation. Furthermore, the cascaded classifier outperforms both multi-class and one-shot classifiers in overall accuracy for discriminating confounders from cancer: 0.76 versus 0.71 and 0.62.

Discrimination of nuclear explosions and earthquakes from teleseismic distances with a local network of short period seismic stations using artificial neural networks

NASA Astrophysics Data System (ADS)

Tiira, Timo

1996-10-01

Seismic discrimination capability of artificial neural networks (ANNs) was studied using earthquakes and nuclear explosions from teleseismic distances. The events were selected from two areas, which were analyzed separately. First, 23 nuclear explosions from Semipalatinsk and Lop Nor test sites were compared with 46 earthquakes from adjacent areas. Second, 39 explosions from Nevada test site were compared with 27 earthquakes from close-by areas. The basic discriminants were complexity, spectral ratio and third moment of frequency. The spectral discriminants were computed in five different ways to obtain all the information embedded in the signals, some of which were relatively weak. The discriminants were computed using data from six short period stations in Central and southern Finland. The spectral contents of the signals of both classes varied considerably between the stations. The 66 discriminants were formed into 65 optimum subsets of different sizes by using stepwise linear regression. A type of ANN called multilayer perceptron (MLP) was applied to each of the subsets. As a comparison the classification was repeated using linear discrimination analysis (LDA). Since the number of events was small the testing was made with the leave-one-out method. The ANN gave significantly better results than LDA. As a final tool for discrimination a combination of the ten neural nets with the best performance were used. All events from Central Asia were clearly discriminated and over 90% of the events from Nevada region were confidently discriminated. The better performance of ANNs was attributed to its ability to form complex decision regions between the groups and to its highly non-linear nature.

Aptitude Level and Performance on Intramodal and Intermodal Form Discrimination Tasks. Technical Report.

ERIC Educational Resources Information Center

Kress, Gary

The increased number of marginal aptitude trainees inducted into the Army has created the need for adequately and efficiently training these men. This report presents the finding of research that compared high and low aptitude men--classified on the basis of scores from the Armed Forces Qualification Test (AFQT)--on two form discrimination tasks…

Kernel PLS-SVC for Linear and Nonlinear Discrimination

NASA Technical Reports Server (NTRS)

Rosipal, Roman; Trejo, Leonard J.; Matthews, Bryan

2003-01-01

A new methodology for discrimination is proposed. This is based on kernel orthonormalized partial least squares (PLS) dimensionality reduction of the original data space followed by support vector machines for classification. Close connection of orthonormalized PLS and Fisher's approach to linear discrimination or equivalently with canonical correlation analysis is described. This gives preference to use orthonormalized PLS over principal component analysis. Good behavior of the proposed method is demonstrated on 13 different benchmark data sets and on the real world problem of the classification finger movement periods versus non-movement periods based on electroencephalogram.

Advanced Subspace Techniques for Modeling Channel and Session Variability in a Speaker Recognition System

DTIC Science & Technology

2012-03-01

with each SVM discriminating between a pair of the N total speakers in the data set. The (( + 1))/2 classifiers then vote on the final...classification of a test sample. The Random Forest classifier is an ensemble classifier that votes amongst decision trees generated with each node using...Forest vote , and the effects of overtraining will be mitigated by the fact that each decision tree is overtrained differently (due to the random

Automated classification of maxillofacial cysts in cone beam CT images using contourlet transformation and Spherical Harmonics.

PubMed

Abdolali, Fatemeh; Zoroofi, Reza Aghaeizadeh; Otake, Yoshito; Sato, Yoshinobu

2017-02-01

Accurate detection of maxillofacial cysts is an essential step for diagnosis, monitoring and planning therapeutic intervention. Cysts can be of various sizes and shapes and existing detection methods lead to poor results. Customizing automatic detection systems to gain sufficient accuracy in clinical practice is highly challenging. For this purpose, integrating the engineering knowledge in efficient feature extraction is essential. This paper presents a novel framework for maxillofacial cysts detection. A hybrid methodology based on surface and texture information is introduced. The proposed approach consists of three main steps as follows: At first, each cystic lesion is segmented with high accuracy. Then, in the second and third steps, feature extraction and classification are performed. Contourlet and SPHARM coefficients are utilized as texture and shape features which are fed into the classifier. Two different classifiers are used in this study, i.e. support vector machine and sparse discriminant analysis. Generally SPHARM coefficients are estimated by the iterative residual fitting (IRF) algorithm which is based on stepwise regression method. In order to improve the accuracy of IRF estimation, a method based on extra orthogonalization is employed to reduce linear dependency. We have utilized a ground-truth dataset consisting of cone beam CT images of 96 patients, belonging to three maxillofacial cyst categories: radicular cyst, dentigerous cyst and keratocystic odontogenic tumor. Using orthogonalized SPHARM, residual sum of squares is decreased which leads to a more accurate estimation. Analysis of the results based on statistical measures such as specificity, sensitivity, positive predictive value and negative predictive value is reported. The classification rate of 96.48% is achieved using sparse discriminant analysis and orthogonalized SPHARM features. Classification accuracy at least improved by 8.94% with respect to conventional features. This study demonstrated that our proposed methodology can improve the computer assisted diagnosis (CAD) performance by incorporating more discriminative features. Using orthogonalized SPHARM is promising in computerized cyst detection and may have a significant impact in future CAD systems. Copyright © 2016 Elsevier Ireland Ltd. All rights reserved.

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

PubMed

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

2010-12-01

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

Classification of pulmonary emphysema from chest CT scans using integral geometry descriptors

NASA Astrophysics Data System (ADS)

van Rikxoort, E. M.; Goldin, J. G.; Galperin-Aizenberg, M.; Brown, M. S.

2011-03-01

To gain insight into the underlying pathways of emphysema and monitor the effect of treatment, methods to quantify and phenotype the different types of emphysema from chest CT scans are of crucial importance. Current standard measures rely on density thresholds for individual voxels, which is influenced by inspiration level and does not take into account the spatial relationship between voxels. Measures based on texture analysis do take the interrelation between voxels into account and therefore might be useful for distinguishing different types of emphysema. In this study, we propose to use Minkowski functionals combined with rotation invariant Gaussian features to distinguish between healthy and emphysematous tissue and classify three different types of emphysema. Minkowski functionals characterize binary images in terms of geometry and topology. In 3D, four Minkowski functionals are defined. By varying the threshold and size of neighborhood around a voxel, a set of Minkowski functionals can be defined for each voxel. Ten chest CT scans with 1810 annotated regions were used to train the method. A set of 108 features was calculated for each training sample from which 10 features were selected to be most informative. A linear discriminant classifier was trained to classify each voxel in the lungs into a subtype of emphysema or normal lung. The method was applied to an independent test set of 30 chest CT scans with varying amounts and types of emphysema with 4347 annotated regions of interest. The method is shown to perform well, with an overall accuracy of 95%.

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

PubMed

Zollanvari, Amin; Dougherty, Edward R

2014-06-01

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

A procedure for classifying textural facies in gravel‐bed rivers

USGS Publications Warehouse

Buffington, John M.; Montgomery, David R.

1999-01-01

Textural patches (i.e., grain‐size facies) are commonly observed in gravel‐bed channels and are of significance for both physical and biological processes at subreach scales. We present a general framework for classifying textural patches that allows modification for particular study goals, while maintaining a basic degree of standardization. Textures are classified using a two‐tier system of ternary diagrams that identifies the relative abundance of major size classes and subcategories of the dominant size. An iterative procedure of visual identification and quantitative grain‐size measurement is used. A field test of our classification indicates that it affords reasonable statistical discrimination of median grain size and variance of bed‐surface textures. We also explore the compromise between classification simplicity and accuracy. We find that statistically meaningful textural discrimination requires use of both tiers of our classification. Furthermore, we find that simplified variants of the two‐tier scheme are less accurate but may be more practical for field studies which do not require a high level of textural discrimination or detailed description of grain‐size distributions. Facies maps provide a natural template for stratifying other physical and biological measurements and produce a retrievable and versatile database that can be used as a component of channel monitoring efforts.

Feature selection and classification of multiparametric medical images using bagging and SVM

NASA Astrophysics Data System (ADS)

Fan, Yong; Resnick, Susan M.; Davatzikos, Christos

2008-03-01

This paper presents a framework for brain classification based on multi-parametric medical images. This method takes advantage of multi-parametric imaging to provide a set of discriminative features for classifier construction by using a regional feature extraction method which takes into account joint correlations among different image parameters; in the experiments herein, MRI and PET images of the brain are used. Support vector machine classifiers are then trained based on the most discriminative features selected from the feature set. To facilitate robust classification and optimal selection of parameters involved in classification, in view of the well-known "curse of dimensionality", base classifiers are constructed in a bagging (bootstrap aggregating) framework for building an ensemble classifier and the classification parameters of these base classifiers are optimized by means of maximizing the area under the ROC (receiver operating characteristic) curve estimated from their prediction performance on left-out samples of bootstrap sampling. This classification system is tested on a sex classification problem, where it yields over 90% classification rates for unseen subjects. The proposed classification method is also compared with other commonly used classification algorithms, with favorable results. These results illustrate that the methods built upon information jointly extracted from multi-parametric images have the potential to perform individual classification with high sensitivity and specificity.

Improving the accuracy in detection of clustered microcalcifications with a context-sensitive classification model.

PubMed

Wang, Juan; Nishikawa, Robert M; Yang, Yongyi

2016-01-01

In computer-aided detection of microcalcifications (MCs), the detection accuracy is often compromised by frequent occurrence of false positives (FPs), which can be attributed to a number of factors, including imaging noise, inhomogeneity in tissue background, linear structures, and artifacts in mammograms. In this study, the authors investigated a unified classification approach for combating the adverse effects of these heterogeneous factors for accurate MC detection. To accommodate FPs caused by different factors in a mammogram image, the authors developed a classification model to which the input features were adapted according to the image context at a detection location. For this purpose, the input features were defined in two groups, of which one group was derived from the image intensity pattern in a local neighborhood of a detection location, and the other group was used to characterize how a MC is different from its structural background. Owing to the distinctive effect of linear structures in the detector response, the authors introduced a dummy variable into the unified classifier model, which allowed the input features to be adapted according to the image context at a detection location (i.e., presence or absence of linear structures). To suppress the effect of inhomogeneity in tissue background, the input features were extracted from different domains aimed for enhancing MCs in a mammogram image. To demonstrate the flexibility of the proposed approach, the authors implemented the unified classifier model by two widely used machine learning algorithms, namely, a support vector machine (SVM) classifier and an Adaboost classifier. In the experiment, the proposed approach was tested for two representative MC detectors in the literature [difference-of-Gaussians (DoG) detector and SVM detector]. The detection performance was assessed using free-response receiver operating characteristic (FROC) analysis on a set of 141 screen-film mammogram (SFM) images (66 cases) and a set of 188 full-field digital mammogram (FFDM) images (95 cases). The FROC analysis results show that the proposed unified classification approach can significantly improve the detection accuracy of two MC detectors on both SFM and FFDM images. Despite the difference in performance between the two detectors, the unified classifiers can reduce their FP rate to a similar level in the output of the two detectors. In particular, with true-positive rate at 85%, the FP rate on SFM images for the DoG detector was reduced from 1.16 to 0.33 clusters/image (unified SVM) and 0.36 clusters/image (unified Adaboost), respectively; similarly, for the SVM detector, the FP rate was reduced from 0.45 clusters/image to 0.30 clusters/image (unified SVM) and 0.25 clusters/image (unified Adaboost), respectively. Similar FP reduction results were also achieved on FFDM images for the two MC detectors. The proposed unified classification approach can be effective for discriminating MCs from FPs caused by different factors (such as MC-like noise patterns and linear structures) in MC detection. The framework is general and can be applicable for further improving the detection accuracy of existing MC detectors.

A geobotanical investigation based on linear discriminant and profile analyses of airborne Thematic Mapper Simulator data

NASA Technical Reports Server (NTRS)

Schwaller, Mathew R.

1987-01-01

This paper discusses the application of linear discriminant and profile analyses to detailed investigation of an airborne Thematic Mapper Simulator (TMS) image collected over a geobotanical test site. The test site was located on the Keweenaw Peninsula of Michigan's Upper Peninsula, and remote sensing data collection coincided with the onset of leaf senescence in the regional deciduous flora. Linear discriminant analysis revealed that sites overlying soil geochemical anomalies were distinguishable from background sites by the reflectance and thermal emittance of the tree canopy imaged in the airborne TMS data. The correlation of individual bands with the linear discriminant function suggested that the TMS thermal Channel 7 (10.32-12.33 microns) contributed most, while TMS Bands 2 (0.53-0.60 microns), 3 (0.63-0.69 microns), and 5 (1.53-1.73 microns) contributed somewhat more modestly to the separation of anomalous and background sites imaged by the TMS. The observed changes in canopy reflectance and thermal emittance of the deciduous flora overlying geochemically anomalous areas are consistent with the biophysical changes which are known or presumed to occur as a result of injury induced in metal-stressed vegetation.

Classification of Malaysia aromatic rice using multivariate statistical analysis

NASA Astrophysics Data System (ADS)

Abdullah, A. H.; Adom, A. H.; Shakaff, A. Y. Md; Masnan, M. J.; Zakaria, A.; Rahim, N. A.; Omar, O.

2015-05-01

Aromatic rice (Oryza sativa L.) is considered as the best quality premium rice. The varieties are preferred by consumers because of its preference criteria such as shape, colour, distinctive aroma and flavour. The price of aromatic rice is higher than ordinary rice due to its special needed growth condition for instance specific climate and soil. Presently, the aromatic rice quality is identified by using its key elements and isotopic variables. The rice can also be classified via Gas Chromatography Mass Spectrometry (GC-MS) or human sensory panels. However, the uses of human sensory panels have significant drawbacks such as lengthy training time, and prone to fatigue as the number of sample increased and inconsistent. The GC-MS analysis techniques on the other hand, require detailed procedures, lengthy analysis and quite costly. This paper presents the application of in-house developed Electronic Nose (e-nose) to classify new aromatic rice varieties. The e-nose is used to classify the variety of aromatic rice based on the samples odour. The samples were taken from the variety of rice. The instrument utilizes multivariate statistical data analysis, including Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and K-Nearest Neighbours (KNN) to classify the unknown rice samples. The Leave-One-Out (LOO) validation approach is applied to evaluate the ability of KNN to perform recognition and classification of the unspecified samples. The visual observation of the PCA and LDA plots of the rice proves that the instrument was able to separate the samples into different clusters accordingly. The results of LDA and KNN with low misclassification error support the above findings and we may conclude that the e-nose is successfully applied to the classification of the aromatic rice varieties.

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

Abdullah, A. H.; Adom, A. H.; Shakaff, A. Y. Md

Aromatic rice (Oryza sativa L.) is considered as the best quality premium rice. The varieties are preferred by consumers because of its preference criteria such as shape, colour, distinctive aroma and flavour. The price of aromatic rice is higher than ordinary rice due to its special needed growth condition for instance specific climate and soil. Presently, the aromatic rice quality is identified by using its key elements and isotopic variables. The rice can also be classified via Gas Chromatography Mass Spectrometry (GC-MS) or human sensory panels. However, the uses of human sensory panels have significant drawbacks such as lengthy trainingmore » time, and prone to fatigue as the number of sample increased and inconsistent. The GC–MS analysis techniques on the other hand, require detailed procedures, lengthy analysis and quite costly. This paper presents the application of in-house developed Electronic Nose (e-nose) to classify new aromatic rice varieties. The e-nose is used to classify the variety of aromatic rice based on the samples odour. The samples were taken from the variety of rice. The instrument utilizes multivariate statistical data analysis, including Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and K-Nearest Neighbours (KNN) to classify the unknown rice samples. The Leave-One-Out (LOO) validation approach is applied to evaluate the ability of KNN to perform recognition and classification of the unspecified samples. The visual observation of the PCA and LDA plots of the rice proves that the instrument was able to separate the samples into different clusters accordingly. The results of LDA and KNN with low misclassification error support the above findings and we may conclude that the e-nose is successfully applied to the classification of the aromatic rice varieties.« less

A custom hardware classifier for bruised apple detection in hyperspectral images

NASA Astrophysics Data System (ADS)

Cárdenas, Javier; Figueroa, Miguel; Pezoa, Jorge E.

2015-09-01

We present a custom digital architecture for bruised apple classification using hyperspectral images in the near infrared (NIR) spectrum. The algorithm classifies each pixel in an image into one of three classes: bruised, non-bruised, and background. We extract two 5-element feature vectors for each pixel using only 10 out of the 236 spectral bands provided by the hyperspectral camera, thereby greatly reducing both the requirements of the imager and the computational complexity of the algorithm. We then use two linear-kernel support vector machine (SVM) to classify each pixel. Each SVM was trained with 504 windows of size 17×17-pixel taken from 14 hyperspectral images of 320×320 pixels each, for each class. The architecture then computes the percentage of bruised pixels in each apple in order to adequately classify the fruit. We implemented the architecture on a Xilinx Zynq Z-7010 field-programmable gate array (FPGA) and tested it on images from a NIR N17E push-broom camera with a frame rate of 25 fps, a band-pixel rate of 1.888 MHz, and 236 spectral bands between 900 and 1700 nanometers in laboratory conditions. Using 28-bit fixed-point arithmetic, the circuit accurately discriminates 95.2% of the pixels corresponding to an apple, 81% of the pixels corresponding to a bruised apple, and 96.4% of the background. With the default threshold settings, the highest false positive (FP) for a bruised apple is 18.7%. The circuit operates at the native frame rate of the camera, consumes 67 mW of dynamic power, and uses less than 10% of the logic resources on the FPGA.

Latina/o or Mexicana/o?: The Relationship between Socially Assigned Race and Experiences with Discrimination

PubMed Central

Vargas, Edward D.; Winston, Nadia C.; Garcia, John A.; Sanchez, Gabriel R.

2016-01-01

Discrimination based on one’s racial or ethnic background is one of the oldest and most perverse practices in the United States. While much of this research has relied on self-reported racial categories, a growing body of research is attempting to measure race through socially-assigned race. Socially-assigned or ascribed race measures how individuals feel they are classified by other people. This paper draws on the socially assigned race literature and explores the impact of socially assigned race on experiences with discrimination using a 2011 nationally representative sample of Latina/os (n=1,200). While much of the current research on Latina/os has been focused on the aggregation across national origin group members, this paper marks a deviation by using socially-assigned race and national origin to understand how being ascribed as Mexican is associated with experiences of discrimination. We find evidence that being ascribed as Mexican increases the likelihood of experiencing discrimination relative to being ascribed as White or Latina/o. Furthermore, we find that being miss-classified as Mexican (ascribed as Mexican, but not of Mexican origin) is associated with a higher likelihood of experiencing discrimination compared to being ascribed as white, ascribed as Latina/o, and correctly ascribed as Mexican. We provide evidence that socially assigned race is a valuable complement to self-identified race/ethnicity for scholars interested in assessing the impact of race/ethnicity on a wide range of outcomes. PMID:27709119

Linear Classifier with Reject Option for the Detection of Vocal Fold Paralysis and Vocal Fold Edema

NASA Astrophysics Data System (ADS)

Kotropoulos, Constantine; Arce, Gonzalo R.

2009-12-01

Two distinct two-class pattern recognition problems are studied, namely, the detection of male subjects who are diagnosed with vocal fold paralysis against male subjects who are diagnosed as normal and the detection of female subjects who are suffering from vocal fold edema against female subjects who do not suffer from any voice pathology. To do so, utterances of the sustained vowel "ah" are employed from the Massachusetts Eye and Ear Infirmary database of disordered speech. Linear prediction coefficients extracted from the aforementioned utterances are used as features. The receiver operating characteristic curve of the linear classifier, that stems from the Bayes classifier when Gaussian class conditional probability density functions with equal covariance matrices are assumed, is derived. The optimal operating point of the linear classifier is specified with and without reject option. First results using utterances of the "rainbow passage" are also reported for completeness. The reject option is shown to yield statistically significant improvements in the accuracy of detecting the voice pathologies under study.

Application of quantum-behaved particle swarm optimization to motor imagery EEG classification.

PubMed

Hsu, Wei-Yen

2013-12-01

In this study, we propose a recognition system for single-trial analysis of motor imagery (MI) electroencephalogram (EEG) data. Applying event-related brain potential (ERP) data acquired from the sensorimotor cortices, the system chiefly consists of automatic artifact elimination, feature extraction, feature selection and classification. In addition to the use of independent component analysis, a similarity measure is proposed to further remove the electrooculographic (EOG) artifacts automatically. Several potential features, such as wavelet-fractal features, are then extracted for subsequent classification. Next, quantum-behaved particle swarm optimization (QPSO) is used to select features from the feature combination. Finally, selected sub-features are classified by support vector machine (SVM). Compared with without artifact elimination, feature selection using a genetic algorithm (GA) and feature classification with Fisher's linear discriminant (FLD) on MI data from two data sets for eight subjects, the results indicate that the proposed method is promising in brain-computer interface (BCI) applications.

Classification of smoke tainted wines using mid-infrared spectroscopy and chemometrics.

PubMed

Fudge, Anthea L; Wilkinson, Kerry L; Ristic, Renata; Cozzolino, Daniel

2012-01-11

In this study, the suitability of mid-infrared (MIR) spectroscopy, combined with principal component analysis (PCA) and linear discriminant analysis (LDA), was evaluated as a rapid analytical technique to identify smoke tainted wines. Control (i.e., unsmoked) and smoke-affected wines (260 in total) from experimental and commercial sources were analyzed by MIR spectroscopy and chemometrics. The concentrations of guaiacol and 4-methylguaiacol were also determined using gas chromatography-mass spectrometry (GC-MS), as markers of smoke taint. LDA models correctly classified 61% of control wines and 70% of smoke-affected wines. Classification rates were found to be influenced by the extent of smoke taint (based on GC-MS and informal sensory assessment), as well as qualitative differences in wine composition due to grape variety and oak maturation. Overall, the potential application of MIR spectroscopy combined with chemometrics as a rapid analytical technique for screening smoke-affected wines was demonstrated.

Low-contrast underwater living fish recognition using PCANet

NASA Astrophysics Data System (ADS)

Sun, Xin; Yang, Jianping; Wang, Changgang; Dong, Junyu; Wang, Xinhua

2018-04-01

Quantitative and statistical analysis of ocean creatures is critical to ecological and environmental studies. And living fish recognition is one of the most essential requirements for fishery industry. However, light attenuation and scattering phenomenon are present in the underwater environment, which makes underwater images low-contrast and blurry. This paper tries to design a robust framework for accurate fish recognition. The framework introduces a two stage PCA Network to extract abstract features from fish images. On a real-world fish recognition dataset, we use a linear SVM classifier and set penalty coefficients to conquer data unbalanced issue. Feature visualization results show that our method can avoid the feature distortion in boundary regions of underwater image. Experiments results show that the PCA Network can extract discriminate features and achieve promising recognition accuracy. The framework improves the recognition accuracy of underwater living fishes and can be easily applied to marine fishery industry.

Automatic classification of visual evoked potentials based on wavelet decomposition

NASA Astrophysics Data System (ADS)

Stasiakiewicz, Paweł; Dobrowolski, Andrzej P.; Tomczykiewicz, Kazimierz

2017-04-01

Diagnosis of part of the visual system, that is responsible for conducting compound action potential, is generally based on visual evoked potentials generated as a result of stimulation of the eye by external light source. The condition of patient's visual path is assessed by set of parameters that describe the time domain characteristic extremes called waves. The decision process is compound therefore diagnosis significantly depends on experience of a doctor. The authors developed a procedure - based on wavelet decomposition and linear discriminant analysis - that ensures automatic classification of visual evoked potentials. The algorithm enables to assign individual case to normal or pathological class. The proposed classifier has a 96,4% sensitivity at 10,4% probability of false alarm in a group of 220 cases and area under curve ROC equals to 0,96 which, from the medical point of view, is a very good result.

Joint Entropy for Space and Spatial Frequency Domains Estimated from Psychometric Functions of Achromatic Discrimination

PubMed Central

Silveira, Vladímir de Aquino; Souza, Givago da Silva; Gomes, Bruno Duarte; Rodrigues, Anderson Raiol; Silveira, Luiz Carlos de Lima

2014-01-01

We used psychometric functions to estimate the joint entropy for space discrimination and spatial frequency discrimination. Space discrimination was taken as discrimination of spatial extent. Seven subjects were tested. Gábor functions comprising unidimensionalsinusoidal gratings (0.4, 2, and 10 cpd) and bidimensionalGaussian envelopes (1°) were used as reference stimuli. The experiment comprised the comparison between reference and test stimulithat differed in grating's spatial frequency or envelope's standard deviation. We tested 21 different envelope's standard deviations around the reference standard deviation to study spatial extent discrimination and 19 different grating's spatial frequencies around the reference spatial frequency to study spatial frequency discrimination. Two series of psychometric functions were obtained for 2%, 5%, 10%, and 100% stimulus contrast. The psychometric function data points for spatial extent discrimination or spatial frequency discrimination were fitted with Gaussian functions using the least square method, and the spatial extent and spatial frequency entropies were estimated from the standard deviation of these Gaussian functions. Then, joint entropy was obtained by multiplying the square root of space extent entropy times the spatial frequency entropy. We compared our results to the theoretical minimum for unidimensional Gábor functions, 1/4π or 0.0796. At low and intermediate spatial frequencies and high contrasts, joint entropy reached levels below the theoretical minimum, suggesting non-linear interactions between two or more visual mechanisms. We concluded that non-linear interactions of visual pathways, such as the M and P pathways, could explain joint entropy values below the theoretical minimum at low and intermediate spatial frequencies and high contrasts. These non-linear interactions might be at work at intermediate and high contrasts at all spatial frequencies once there was a substantial decrease in joint entropy for these stimulus conditions when contrast was raised. PMID:24466158

Joint entropy for space and spatial frequency domains estimated from psychometric functions of achromatic discrimination.

PubMed

Silveira, Vladímir de Aquino; Souza, Givago da Silva; Gomes, Bruno Duarte; Rodrigues, Anderson Raiol; Silveira, Luiz Carlos de Lima

2014-01-01

We used psychometric functions to estimate the joint entropy for space discrimination and spatial frequency discrimination. Space discrimination was taken as discrimination of spatial extent. Seven subjects were tested. Gábor functions comprising unidimensionalsinusoidal gratings (0.4, 2, and 10 cpd) and bidimensionalGaussian envelopes (1°) were used as reference stimuli. The experiment comprised the comparison between reference and test stimulithat differed in grating's spatial frequency or envelope's standard deviation. We tested 21 different envelope's standard deviations around the reference standard deviation to study spatial extent discrimination and 19 different grating's spatial frequencies around the reference spatial frequency to study spatial frequency discrimination. Two series of psychometric functions were obtained for 2%, 5%, 10%, and 100% stimulus contrast. The psychometric function data points for spatial extent discrimination or spatial frequency discrimination were fitted with Gaussian functions using the least square method, and the spatial extent and spatial frequency entropies were estimated from the standard deviation of these Gaussian functions. Then, joint entropy was obtained by multiplying the square root of space extent entropy times the spatial frequency entropy. We compared our results to the theoretical minimum for unidimensional Gábor functions, 1/4π or 0.0796. At low and intermediate spatial frequencies and high contrasts, joint entropy reached levels below the theoretical minimum, suggesting non-linear interactions between two or more visual mechanisms. We concluded that non-linear interactions of visual pathways, such as the M and P pathways, could explain joint entropy values below the theoretical minimum at low and intermediate spatial frequencies and high contrasts. These non-linear interactions might be at work at intermediate and high contrasts at all spatial frequencies once there was a substantial decrease in joint entropy for these stimulus conditions when contrast was raised.

Robust L1-norm two-dimensional linear discriminant analysis.

PubMed

Li, Chun-Na; Shao, Yuan-Hai; Deng, Nai-Yang

2015-05-01

In this paper, we propose an L1-norm two-dimensional linear discriminant analysis (L1-2DLDA) with robust performance. Different from the conventional two-dimensional linear discriminant analysis with L2-norm (L2-2DLDA), where the optimization problem is transferred to a generalized eigenvalue problem, the optimization problem in our L1-2DLDA is solved by a simple justifiable iterative technique, and its convergence is guaranteed. Compared with L2-2DLDA, our L1-2DLDA is more robust to outliers and noises since the L1-norm is used. This is supported by our preliminary experiments on toy example and face datasets, which show the improvement of our L1-2DLDA over L2-2DLDA. Copyright © 2015 Elsevier Ltd. All rights reserved.

Attractor structure discriminates sleep states: recurrence plot analysis applied to infant breathing patterns.

PubMed

Terrill, Philip Ian; Wilson, Stephen James; Suresh, Sadasivam; Cooper, David M; Dakin, Carolyn

2010-05-01

Breathing patterns are characteristically different between infant active sleep (AS) and quiet sleep (QS), and statistical quantifications of interbreath interval (IBI) data have previously been used to discriminate between infant sleep states. It has also been identified that breathing patterns are governed by a nonlinear controller. This study aims to investigate whether nonlinear quantifications of infant IBI data are characteristically different between AS and QS, and whether they may be used to discriminate between these infant sleep states. Polysomnograms were obtained from 24 healthy infants at six months of age. Periods of AS and QS were identified, and IBI data extracted. Recurrence quantification analysis (RQA) was applied to each period, and recurrence calculated for a fixed radius in the range of 0-8 in steps of 0.02, and embedding dimensions of 4, 6, 8, and 16. When a threshold classifier was trained, the RQA variable recurrence was able to correctly classify 94.3% of periods in a test dataset. It was concluded that RQA of IBI data is able to accurately discriminate between infant sleep states. This is a promising step toward development of a minimal-channel automatic sleep state classification system.

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.

A chemiluminescence sensor array for discriminating natural sugars and artificial sweeteners.

PubMed

Niu, Weifen; Kong, Hao; Wang, He; Zhang, Yantu; Zhang, Sichun; Zhang, Xinrong

2012-01-01

In this paper, we report a chemiluminescence (CL) sensor array based on catalytic nanomaterials for the discrimination of ten sweeteners, including five natural sugars and five artificial sweeteners. The CL response patterns ("fingerprints") can be obtained for a given compound on the nanomaterial array and then identified through linear discriminant analysis (LDA). Moreover, each pure sweetener was quantified based on the emission intensities of selected sensor elements. The linear ranges for these sweeteners lie within 0.05-100 mM, but vary with the type of sweetener. The applicability of this array to real-life samples was demonstrated by applying it to various beverages, and the results showed that the sensor array possesses excellent discrimination power and reversibility.

Chinese vinegar classification via volatiles using long-optical-path infrared spectroscopy and chemometrics.

PubMed

Dong, D; Zheng, W; Jiao, L; Lang, Y; Zhao, X

2016-03-01

Different brands of Chinese vinegar are similar in appearance, color and aroma, making their discrimination difficult. The compositions and concentrations of the volatiles released from different vinegars vary by raw material and brewing process and thus offer a means to discriminate vinegars. In this study, we enhanced the detection sensitivity of the infrared spectrometer by extending its optical path. We measured the infrared spectra of the volatiles from 5 brands of Chinese vinegar and observed the spectral characteristics corresponding to alcohols, esters, acids, furfural, etc. Different brands of Chinese vinegar had obviously different infrared spectra and could be classified through chemometrics analysis. Furthermore, we established classification models and demonstrated their effectiveness for classifying different brands of vinegar. This study demonstrates that long-optical-path infrared spectroscopy has the ability to discriminate Chinese vinegars with the advantages that it is fast and non-destructive and eliminates the need for sampling. Copyright © 2015 Elsevier Ltd. All rights reserved.

Dimensional feature weighting utilizing multiple kernel learning for single-channel talker location discrimination using the acoustic transfer function.

PubMed

Takashima, Ryoichi; Takiguchi, Tetsuya; Ariki, Yasuo

2013-02-01

This paper presents a method for discriminating the location of the sound source (talker) using only a single microphone. In a previous work, the single-channel approach for discriminating the location of the sound source was discussed, where the acoustic transfer function from a user's position is estimated by using a hidden Markov model of clean speech in the cepstral domain. In this paper, each cepstral dimension of the acoustic transfer function is newly weighted, in order to obtain the cepstral dimensions having information that is useful for classifying the user's position. Then, this paper proposes a feature-weighting method for the cepstral parameter using multiple kernel learning, defining the base kernels for each cepstral dimension of the acoustic transfer function. The user's position is trained and classified by support vector machine. The effectiveness of this method has been confirmed by sound source (talker) localization experiments performed in different room environments.

An Innovative Approach for The Integration of Proteomics and Metabolomics Data In Severe Septic Shock Patients Stratified for Mortality.

PubMed

Cambiaghi, Alice; Díaz, Ramón; Martinez, Julia Bauzá; Odena, Antonia; Brunelli, Laura; Caironi, Pietro; Masson, Serge; Baselli, Giuseppe; Ristagno, Giuseppe; Gattinoni, Luciano; de Oliveira, Eliandre; Pastorelli, Roberta; Ferrario, Manuela

2018-04-27

In this work, we examined plasma metabolome, proteome and clinical features in patients with severe septic shock enrolled in the multicenter ALBIOS study. The objective was to identify changes in the levels of metabolites involved in septic shock progression and to integrate this information with the variation occurring in proteins and clinical data. Mass spectrometry-based targeted metabolomics and untargeted proteomics allowed us to quantify absolute metabolites concentration and relative proteins abundance. We computed the ratio D7/D1 to take into account their variation from day 1 (D1) to day 7 (D7) after shock diagnosis. Patients were divided into two groups according to 28-day mortality. Three different elastic net logistic regression models were built: one on metabolites only, one on metabolites and proteins and one to integrate metabolomics and proteomics data with clinical parameters. Linear discriminant analysis and Partial least squares Discriminant Analysis were also implemented. All the obtained models correctly classified the observations in the testing set. By looking at the variable importance (VIP) and the selected features, the integration of metabolomics with proteomics data showed the importance of circulating lipids and coagulation cascade in septic shock progression, thus capturing a further layer of biological information complementary to metabolomics information.

Raman spectroscopy of normal oral buccal mucosa tissues: study on intact and incised biopsies

NASA Astrophysics Data System (ADS)

Deshmukh, Atul; Singh, S. P.; Chaturvedi, Pankaj; Krishna, C. Murali

2011-12-01

Oral squamous cell carcinoma is one of among the top 10 malignancies. Optical spectroscopy, including Raman, is being actively pursued as alternative/adjunct for cancer diagnosis. Earlier studies have demonstrated the feasibility of classifying normal, premalignant, and malignant oral ex vivo tissues. Spectral features showed predominance of lipids and proteins in normal and cancer conditions, respectively, which were attributed to membrane lipids and surface proteins. In view of recent developments in deep tissue Raman spectroscopy, we have recorded Raman spectra from superior and inferior surfaces of 10 normal oral tissues on intact, as well as incised, biopsies after separation of epithelium from connective tissue. Spectral variations and similarities among different groups were explored by unsupervised (principal component analysis) and supervised (linear discriminant analysis, factorial discriminant analysis) methodologies. Clusters of spectra from superior and inferior surfaces of intact tissues show a high overlap; whereas spectra from separated epithelium and connective tissue sections yielded clear clusters, though they also overlap on clusters of intact tissues. Spectra of all four groups of normal tissues gave exclusive clusters when tested against malignant spectra. Thus, this study demonstrates that spectra recorded from the superior surface of an intact tissue may have contributions from deeper layers but has no bearing from the classification of a malignant tissues point of view.

In vivo Raman spectroscopic identification of premalignant lesions in oral buccal mucosa

NASA Astrophysics Data System (ADS)

Singh, S. P.; Deshmukh, Atul; Chaturvedi, Pankaj; Murali Krishna, C.

2012-10-01

Cancers of oral cavities are one of the most common malignancies in India and other south-Asian countries. Tobacco habits are the main etiological factors for oral cancer. Identification of premalignant lesions is required for improving survival rates related to oral cancer. Optical spectroscopy methods are projected as alternative/adjunct for cancer diagnosis. Earlier studies have demonstrated the feasibility of classifying normal, premalignant, and malignant oral ex-vivo tissues. We intend to evaluate potentials of Raman spectroscopy in detecting premalignant conditions. Spectra were recorded from premalignant patches, contralateral normal (opposite to tumor site), and cancerous sites of subjects with oral cancers and also from age-matched healthy subjects with and without tobacco habits. A total of 861 spectra from 104 subjects were recorded using a fiber-optic probe-coupled HE-785 Raman spectrometer. Spectral differences in the 1200- to 1800-cm-1 region were subjected to unsupervised principal component analysis and supervised linear discriminant analysis followed by validation with leave-one-out and an independent test data set. Results suggest that premalignant conditions can be objectively discriminated with both normal and cancerous sites as well as from healthy controls with and without tobacco habits. Findings of the study further support efficacy of Raman spectroscopic approaches in oral-cancer applications.

Face recognition using total margin-based adaptive fuzzy support vector machines.

PubMed

Liu, Yi-Hung; Chen, Yen-Ting

2007-01-01

This paper presents a new classifier called total margin-based adaptive fuzzy support vector machines (TAF-SVM) that deals with several problems that may occur in support vector machines (SVMs) when applied to the face recognition. The proposed TAF-SVM not only solves the overfitting problem resulted from the outlier with the approach of fuzzification of the penalty, but also corrects the skew of the optimal separating hyperplane due to the very imbalanced data sets by using different cost algorithm. In addition, by introducing the total margin algorithm to replace the conventional soft margin algorithm, a lower generalization error bound can be obtained. Those three functions are embodied into the traditional SVM so that the TAF-SVM is proposed and reformulated in both linear and nonlinear cases. By using two databases, the Chung Yuan Christian University (CYCU) multiview and the facial recognition technology (FERET) face databases, and using the kernel Fisher's discriminant analysis (KFDA) algorithm to extract discriminating face features, experimental results show that the proposed TAF-SVM is superior to SVM in terms of the face-recognition accuracy. The results also indicate that the proposed TAF-SVM can achieve smaller error variances than SVM over a number of tests such that better recognition stability can be obtained.

Relative sensitivity of depth discrimination for ankle inversion and plantar flexion movements.

PubMed

Black, Georgia; Waddington, Gordon; Adams, Roger

2014-02-01

25 participants (20 women, 5 men) were tested for sensitivity in discrimination between sets of six movements centered on 8 degrees, 11 degrees, and 14 degrees, and separated by 0.3 degrees. Both inversion and plantar flexion movements were tested. Discrimination of the extent of inversion movement was observed to decline linearly with increasing depth; however, for plantar flexion, the discrimination function for movement extent was found to be non-linear. The relatively better discrimination of plantar flexion movements than inversion movements at around 11 degrees from horizontal is interpreted as an effect arising from differential amounts of practice through use, because this position is associated with the plantar flexion movement made in normal walking. The fact that plantar flexion movements are discriminated better than inversion at one region but not others argues against accounts of superior proprioceptive sensitivity for plantar flexion compared to inversion that are based on general properties of plantar flexion such as the number of muscle fibres on stretch.

LMD Based Features for the Automatic Seizure Detection of EEG Signals Using SVM.

PubMed

Zhang, Tao; Chen, Wanzhong

2017-08-01

Achieving the goal of detecting seizure activity automatically using electroencephalogram (EEG) signals is of great importance and significance for the treatment of epileptic seizures. To realize this aim, a newly-developed time-frequency analytical algorithm, namely local mean decomposition (LMD), is employed in the presented study. LMD is able to decompose an arbitrary signal into a series of product functions (PFs). Primarily, the raw EEG signal is decomposed into several PFs, and then the temporal statistical and non-linear features of the first five PFs are calculated. The features of each PF are fed into five classifiers, including back propagation neural network (BPNN), K-nearest neighbor (KNN), linear discriminant analysis (LDA), un-optimized support vector machine (SVM) and SVM optimized by genetic algorithm (GA-SVM), for five classification cases, respectively. Confluent features of all PFs and raw EEG are further passed into the high-performance GA-SVM for the same classification tasks. Experimental results on the international public Bonn epilepsy EEG dataset show that the average classification accuracy of the presented approach are equal to or higher than 98.10% in all the five cases, and this indicates the effectiveness of the proposed approach for automated seizure detection.

Two-dimensional morphometric analysis of young Asian females to determine attractiveness.

PubMed

Pothanikat, Joseph John K; Balakrishna, Ramdas; Mahendra, P; Neeta, J

2015-01-01

Attractive people do not seem to consistently possess such ideal characteristics or share common features. There is no general consensus about the linear and angular characteristics that discriminate between attractive and normal persons. This study determines how young Asian women considered to be attractive differ in their twodimensional facial characteristics from normal women of the same age and race. Frontal and lateral photographs of 70 young Asian females were taken under standardized setting and were given to 15 judges who did not know the subjects in the study, to rate the attractiveness of each photograph. All 70 photographs were arranged in descending order of their total score by all the judges and were classified into three groups. Three angular, 8 linear measurements, and 3 ratios were compared between these groups. This study showed that most attractive group had least convex face, larger forehead, and wider faces. Conversely, the middle facial height was larger in the least attractive group. The ratio of middle third to total face of the most attractive group is higher than the average attractive ones. The ratio of lower third to total face of the most attractive group is lower than the average attractive ones.

On the design of classifiers for crop inventories

NASA Technical Reports Server (NTRS)

Heydorn, R. P.; Takacs, H. C.

1986-01-01

Crop proportion estimators that use classifications of satellite data to correct, in an additive way, a given estimate acquired from ground observations are discussed. A linear version of these estimators is optimal, in terms of minimum variance, when the regression of the ground observations onto the satellite observations in linear. When this regression is not linear, but the reverse regression (satellite observations onto ground observations) is linear, the estimator is suboptimal but still has certain appealing variance properties. In this paper expressions are derived for those regressions which relate the intercepts and slopes to conditional classification probabilities. These expressions are then used to discuss the question of classifier designs that can lead to low-variance crop proportion estimates. Variance expressions for these estimates in terms of classifier omission and commission errors are also derived.

Classifying adolescent attention-deficit/hyperactivity disorder (ADHD) based on functional and structural imaging.

PubMed

Iannaccone, Reto; Hauser, Tobias U; Ball, Juliane; Brandeis, Daniel; Walitza, Susanne; Brem, Silvia

2015-10-01

Attention-deficit/hyperactivity disorder (ADHD) is a common disabling psychiatric disorder associated with consistent deficits in error processing, inhibition and regionally decreased grey matter volumes. The diagnosis is based on clinical presentation, interviews and questionnaires, which are to some degree subjective and would benefit from verification through biomarkers. Here, pattern recognition of multiple discriminative functional and structural brain patterns was applied to classify adolescents with ADHD and controls. Functional activation features in a Flanker/NoGo task probing error processing and inhibition along with structural magnetic resonance imaging data served to predict group membership using support vector machines (SVMs). The SVM pattern recognition algorithm correctly classified 77.78% of the subjects with a sensitivity and specificity of 77.78% based on error processing. Predictive regions for controls were mainly detected in core areas for error processing and attention such as the medial and dorsolateral frontal areas reflecting deficient processing in ADHD (Hart et al., in Hum Brain Mapp 35:3083-3094, 2014), and overlapped with decreased activations in patients in conventional group comparisons. Regions more predictive for ADHD patients were identified in the posterior cingulate, temporal and occipital cortex. Interestingly despite pronounced univariate group differences in inhibition-related activation and grey matter volumes the corresponding classifiers failed or only yielded a poor discrimination. The present study corroborates the potential of task-related brain activation for classification shown in previous studies. It remains to be clarified whether error processing, which performed best here, also contributes to the discrimination of useful dimensions and subtypes, different psychiatric disorders, and prediction of treatment success across studies and sites.

Antiprotozoan lead discovery by aligning dry and wet screening: prediction, synthesis, and biological assay of novel quinoxalinones.

PubMed

Martins Alho, Miriam A; Marrero-Ponce, Yovani; Barigye, Stephen J; Meneses-Marcel, Alfredo; Machado Tugores, Yanetsy; Montero-Torres, Alina; Gómez-Barrio, Alicia; Nogal, Juan J; García-Sánchez, Rory N; Vega, María Celeste; Rolón, Miriam; Martínez-Fernández, Antonio R; Escario, José A; Pérez-Giménez, Facundo; Garcia-Domenech, Ramón; Rivera, Norma; Mondragón, Ricardo; Mondragón, Mónica; Ibarra-Velarde, Froylán; Lopez-Arencibia, Atteneri; Martín-Navarro, Carmen; Lorenzo-Morales, Jacob; Cabrera-Serra, Maria Gabriela; Piñero, Jose; Tytgat, Jan; Chicharro, Roberto; Arán, Vicente J

2014-03-01

Protozoan parasites have been one of the most significant public health problems for centuries and several human infections caused by them have massive global impact. Most of the current drugs used to treat these illnesses have been used for decades and have many limitations such as the emergence of drug resistance, severe side-effects, low-to-medium drug efficacy, administration routes, cost, etc. These drugs have been largely neglected as models for drug development because they are majorly used in countries with limited resources and as a consequence with scarce marketing possibilities. Nowadays, there is a pressing need to identify and develop new drug-based antiprotozoan therapies. In an effort to overcome this problem, the main purpose of this study is to develop a QSARs-based ensemble classifier for antiprotozoan drug-like entities from a heterogeneous compounds collection. Here, we use some of the TOMOCOMD-CARDD molecular descriptors and linear discriminant analysis (LDA) to derive individual linear classification functions in order to discriminate between antiprotozoan and non-antiprotozoan compounds as a way to enable the computational screening of virtual combinatorial datasets and/or drugs already approved. Firstly, we construct a wide-spectrum benchmark database comprising of 680 organic chemicals with great structural variability (254 of them antiprotozoan agents and 426 to drugs having other clinical uses). This series of compounds was processed by a k-means cluster analysis in order to design training and predicting sets. In total, seven discriminant functions were obtained, by using the whole set of atom-based linear indices. All the LDA-based QSAR models show accuracies above 85% in the training set and values of Matthews correlation coefficients (C) vary from 0.70 to 0.86. The external validation set shows rather-good global classifications of around 80% (92.05% for best equation). Later, we developed a multi-agent QSAR classification system, in which the individual QSAR outputs are the inputs of the aforementioned fusion approach. Finally, the fusion model was used for the identification of a novel generation of lead-like antiprotozoan compounds by using ligand-based virtual screening of 'available' small molecules (with synthetic feasibility) in our 'in-house' library. A new molecular subsystem (quinoxalinones) was then theoretically selected as a promising lead series, and its derivatives subsequently synthesized, structurally characterized, and experimentally assayed by using in vitro screening that took into consideration a battery of five parasite-based assays. The chemicals 11(12) and 16 are the most active (hits) against apicomplexa (sporozoa) and mastigophora (flagellata) subphylum parasites, respectively. Both compounds depicted good activity in every protozoan in vitro panel and they did not show unspecific cytotoxicity on the host cells. The described technical framework seems to be a promising QSAR-classifier tool for the molecular discovery and development of novel classes of broad-antiprotozoan-spectrum drugs, which may meet the dual challenges posed by drug-resistant parasites and the rapid progression of protozoan illnesses. Copyright © 2014 Elsevier Ltd. All rights reserved.

Discrimination and classification of acute lymphoblastic leukemia cells by Raman spectroscopy

NASA Astrophysics Data System (ADS)

Managò, Stefano; Valente, Carmen; Mirabelli, Peppino; De Luca, Anna Chiara

2015-05-01

Currently, a combination of technologies is typically required to identify and classify leukemia cells. These methods often lack the specificity and sensitivity necessary for early and accurate diagnosis. Here, we demonstrate the use of Raman spectroscopy to identify normal B cells, collected from healthy patients, and three ALL cell lines (RS4;11, REH and MN60 at different differentiation level, respectively). Raman markers associated with DNA and protein vibrational modes have been identified that exhibit excellent discriminating power for leukemia cell identification. Principal Component Analysis was finally used to confirm the significance of these markers for identify leukemia cells and classifying the data. The obtained results indicate a sorting accuracy of 96% between the three leukemia cell lines.

How Can Dolphins Recognize Fish According to Their Echoes? A Statistical Analysis of Fish Echoes

PubMed Central

Yovel, Yossi; Au, Whitlow W. L.

2010-01-01

Echo-based object classification is a fundamental task of animals that use a biosonar system. Dolphins and porpoises should be able to rely on echoes to discriminate a predator from a prey or to select a desired prey from an undesired object. Many studies have shown that dolphins and porpoises can discriminate between objects according to their echoes. All of these studies however, used unnatural objects that can be easily characterized in human terminologies (e.g., metallic spheres, disks, cylinders). In this work, we collected real fish echoes from many angles of acquisition using a sonar system that mimics the emission properties of dolphins and porpoises. We then tested two alternative statistical approaches in classifying these echoes. Our results suggest that fish species can be classified according to echoes returning from porpoise- and dolphin-like signals. These results suggest how dolphins and porpoises can classify fish based on their echoes and provide some insight as to which features might enable the classification. PMID:21124908

How can dolphins recognize fish according to their echoes? A statistical analysis of fish echoes.

PubMed

Yovel, Yossi; Au, Whitlow W L

2010-11-19

Echo-based object classification is a fundamental task of animals that use a biosonar system. Dolphins and porpoises should be able to rely on echoes to discriminate a predator from a prey or to select a desired prey from an undesired object. Many studies have shown that dolphins and porpoises can discriminate between objects according to their echoes. All of these studies however, used unnatural objects that can be easily characterized in human terminologies (e.g., metallic spheres, disks, cylinders). In this work, we collected real fish echoes from many angles of acquisition using a sonar system that mimics the emission properties of dolphins and porpoises. We then tested two alternative statistical approaches in classifying these echoes. Our results suggest that fish species can be classified according to echoes returning from porpoise- and dolphin-like signals. These results suggest how dolphins and porpoises can classify fish based on their echoes and provide some insight as to which features might enable the classification.