Fisher Discriminant Ratio Research Articles

Use of the separation property to derive Liquid State Machines with enhanced classification performance

Liquid State Machines constitute a powerful computational tool for carrying out complex real time computations on continuous input streams. Their performance is based on two properties, approximation and separation. While the former depends on the selection of class functions for the readout maps, the latter needs to be evaluated for a particular liquid architecture. In the current paper we show how the Fisher's Discriminant Ratio can be used to effectively measure the separation of a Liquid State Machine. This measure is then used as a fitness function in an evolutionary framework that searches for suitable liquid properties and architectures in order to optimize the performance of the trained readouts. Evaluation results demonstrate the effectiveness of the proposed approach.

SGI-110, a Novel Hypomethylating Agent, Induces the WNT Inhibitor Secreted Frizzled Related Protein-2 (SFRP2), and Down Regulates β-Catenin in Acute Myeloid Leukemia (AML) Cells

Abstract 1290 Introduction:SGI-110 (Astex Pharmaceuticals, Inc.) is a dinucleotide hypomethylating agent whose active metabolite is decitabine (DAC). This drug demonstrates superior pharmacokinetics relative to the parent drug as a result of resistance to modification by cytidine deaminase, and is being investigated in myeloid malignancy in the phase I/II setting. We and others have demonstrated that WNT inhibitory genes including SFRP2 are epigenetically silenced in AML and that exposure to DNA methyltransferase inhibitors such as 5-Azacitidine (AZA) and DAC can re-express these genes and down-regulate β-catenin signaling in AML cell lines. We hypothesized that treatment with SGI-110 would have a similar effect upon the epigenetically silenced WNT inhibitor SFRP2 and further would down-regulate β-catenin signaling in AML cells in vitro. Methods:The AML cell lines HL60 and U937 were cultured in vitro using standard techniques and treated with phosphate buffered saline, 0.1, 1 or 5 μM SGI-110, 2μM AZA or 0.5μM DAC. Results presented are pooled data from a minimum of three biological replicates. Samples were harvested on day 5 and viable cells, DNA, RNA and protein obtained. β-catenin levels and cellular localization were quantified using imaging flow cytometry (ImageStream), DNA was extracted and bisulfite converted for analysis of gene specific and global DNA methylation by pyrosequencing (LINE-1, SFRP2), RNA was converted to cDNA for analysis by RT-PCR, and protein was obtained to confirm ImageStream results by Western blot. Nuclear translocation of β-catenin, indicative of its signaling activity, was assessed in individual cells by ImageStream using a similarity score: a log-transformed Pearson’s correlation coefficient between the digitized images of immunostained β-catenin and a nuclear stain (DAPI). Shifts in the population (n=5,000) distributions of this similarity score were assessed by a resolution metric (Fishers discriminant ratio, Rd). Results:Treatment of AML cell lines with 5μM SGI-110 was toxic, and in line with previous experiments in AML cell lines, above the IC90. Treatment at the lowest dose of SGI-110 had minimal effects upon viability, methylation, and mRNA and protein expression in both cell lines tested. Treatment with SGI-110 at the 1μM dose resulted in reductions in LINE-1 methylation in HL60 cells by 21% (from 82% to 61%), compared to 8% with AZA (to 74%) and 20% with DAC (to 62%). In U937 cells, LINE-1 methylation decreased by 40% (from 67% to 27%) after SGI-110 treatment compared to a 25% reduction with AZA (to 42%) and a 30% reduction with DAC (to 36%). SFRP2 methylation in HL60 and U937 decreased from 86 and 88% at baseline to 66 and 60% with SGI-110 at the 1μM dose, compared to 68% with AZA and to 61% with DAC. Expression of SFRP2 mRNA was observed following treatment with 1μM SGI-110 and with DAC, but was limited following AZA treatment. ImageStream analysis of total cellular β-catenin in HL-60 and U937 cells demonstrated 2.4-fold and 1.2-fold reductions in total β-catenin following 1μM SGI-110 treatment. These results were similar to those seen with DAC (1.8-fold and 1.3-fold in HL-60 and U937 cells respectively). AZA treatment appeared to have a greater effect on total β-catenin in U937 cells (1.3-fold reduction) than in HL-60 cells (0.84-fold reduction). Western blot confirmed reductions in β-catenin protein. We also observed decreased nuclear translocation of β-catenin after treatment of HL-60 and U937 cells with 1 μM SGI-110 (Rd = −0.58 and −0.21 respectively; the negative sign indicates a change in cellular distribution from the nucleus to the cytoplasm). Changes were comparable to those observed with DAC (Rd = −0.75 and −0.26 in HL-60 and U937 cells respectively). AZA treatment of U937 cells resulted in a shift in cellular distribution (Rd = −0.20) similar to that for DAC and SGI-110 but had no effect on β-catenin distribution in HL-60 cells (Rd= 0.00). Conclusions:SGI-110 is a novel DNMT inhibitor which demonstrates robust effects on LINE-1 methylation, SFRP2 mRNA expression, and β-catenin level and localization consistent with epigenetically mediated re-expression of the WNT inhibitor SFRP2. Both upregulated β-catenin signaling and SFRP2 methylation have been demonstrated to correlate with inferior survival in patients with myeloid malignancies. Re-expression of epigenetically silenced WNT inhibitory genes such as SFRP2 may abrogate β-catenin signaling in AML cells. Disclosures:Karpf:Astex Pharmaceuticals: Research Funding. Griffiths:Celgene: Honoraria; Astex Pharmaceuticals: Research Funding.

Gait Recognition Across Various Walking Speeds Using Higher Order Shape Configuration Based on a Differential Composition Model

Gait has been known as an effective biometric feature to identify a person at a distance. However, variation of walking speeds may lead to significant changes to human walking patterns. It causes many difficulties for gait recognition. A comprehensive analysis has been carried out in this paper to identify such effects. Based on the analysis, Procrustes shape analysis is adopted for gait signature description and relevant similarity measurement. To tackle the challenges raised by speed change, this paper proposes a higher order shape configuration for gait shape description, which deliberately conserves discriminative information in the gait signatures and is still able to tolerate the varying walking speed. Instead of simply measuring the similarity between two gaits by treating them as two unified objects, a differential composition model (DCM) is constructed. The DCM differentiates the different effects caused by walking speed changes on various human body parts. In the meantime, it also balances well the different discriminabilities of each body part on the overall gait similarity measurements. In this model, the Fisher discriminant ratio is adopted to calculate weights for each body part. Comprehensive experiments based on widely adopted gait databases demonstrate that our proposed method is efficient for cross-speed gait recognition and outperforms other state-of-the-art methods.

Functional brain image classification using association rules defined over discriminant regions

This letter shows a novel computer aided diagnosis (CAD) system for the early diagnosis of Alzheimer’s Disease (AD). The proposed method evaluates the reliability of association rules (ARs) aiming to discover interesting associations between attributes in functional brain imaging, i.e. single photon emission computed tomography (SPECT) and positron emission tomography (PET). AR mining firstly requires a masking process for reducing the computational cost, which is based on Fisher discriminant ratio (FDR), in order to identify “transactions” or relationships among discriminant brain areas. Once the activation map is achieved by means of activation estimation (AE), the resulting regions of interest (ROIs) are subjected to AR discovery with a specified minimum support and confidence. Finally, the proposed CAD system performs image classification by evaluating the number of previously mined rules from controls that are verified by each subject. Several experiments were carried out on two different image modalities (SPECT and PET) in order to highlight the generalization ability of the proposed method. The AR-based method yields an accuracy up to 92.78% (with 87.5% sensitivity and 100% specificity) and 91.33% (with 82.67% sensitivity and 100% specificity) for SPECT and PET, respectively, thus outperforming recently developed methods for early diagnosis of AD.

Adequate number of consumers in a liking test. Insights from resampling in seven studies

The recommended number of consumers to be enrolled in a hedonic test comparing several products usually ranges from 50 to 100, at least if no liking segmentation is sought. This paper seeks to examine whether such a panel size range is adequate, by means of 7 trials with different levels of product space complexity. Five types of products were tested: Two varied in fattiness and sweetness and were tested under the same conditions in two separate laboratories (4 trials); the remaining three, varying in taste and texture, were each tested in a different laboratory (3 trials). Each of the 7 trials was run by a different laboratory. Each of the seven laboratories enrolled in its trial 150 consumers who gave liking scores on a set of 5 or 6 products. The method used to derive adequate panel size consists in removing k subjects from the 150 in the original panel and then measuring the loss of information in product comparisons. Four criteria to be maximized were used: The correlation between the two vectors of product mean scores, the RV coefficient between the two product spaces, the Fisher discrimination ratio among products and the concordance rate in product pair comparisons. For each k,k=0,…,130 by 10, one thousand incomplete panels were simulated by resampling with replacement. Results showed that adequate panel size varied from 20 to 150. Since the level of heterogeneity in consumer preferences was rather similar across trials, panel size should depend on product sensory differences. The variation in panel size recommendation was thus mostly due to the level of complexity of the product space.

Approximate distributed clustering by learning the confidence radius on Fisher discriminant ratio

Presented is a new clustering algorithm with approximate distributed clustering over a peer-to-peer (P2P) network. The Fisher discriminant ratio is used to dynamically learn the confidence radius based on the data distribution in every local peer. Experimental results show that the proposed approach can achieve better clustering accuracies than the DFEKM algorithm while preserving much lower bandwidth consumptions.

Classification of Cognitive States from fMRI data using Fisher Discriminant Ratio and Regions of Interest

Classification of Cognitive States from fMRI data using Fisher Discriminant Ratio and Regions of Interest

Using multifractal analysis of ultra-weak photon emission from germinating wheat seedlings to differentiate between two grades of intoxication with potassium dichromate

The aim of the present study was to test whether the multifractal properties of ultra-weak photon emission (UPE) from germinating wheat seedlings (Triticum aestivum) change when the seedlings are treated with different concentrations of the toxin potassium dichromate (PD). To this end, UPE was measured (50 seedlings in one Petri dish, duration: approx. 16.6- 28 h) from samples of three groups: (i) control (group C, N = 9), (ii) treated with 25 ppm of PD (group G25, N = 32), and (iii) treated with 150 ppm of PD (group G150, N = 23). For the multifractal analysis, the following steps where performed: (i) each UPE time series was trimmed to a final length of 1000 min; (ii) each UPE time series was filtered, linear detrended and normalized; (iii) the multifractal spectrum (f(α)) was calculated for every UPE time series using the backward multifractal detrended moving average (MFDMA) method; (iv) each multifractal spectrum was characterized by calculating the mode (αmode) of the spectrum and the degree of multifractality (Δα); (v) for every UPE time series its mean, skewness and kurtosis were also calculated; finally (vi) all obtained parameters where analyzed to determine their ability to differentiate between the three groups. This was based on Fisher's discriminant ratio (FDR), which was calculated for each parameter combination. Additionally, a non-parametric test was used to test whether the parameter values are significantly different or not. The analysis showed that when comparing all the three groups, FDR had the highest values for the multifractal parameters (αmode, Δα). Furthermore, the differences in these parameters between the groups were statistically significant (p < 0.05). The classical parameters (mean, skewness and kurtosis) had lower FDR values than the multifractal parameters in all cases and showed no significant difference between the groups (except for the skewness between group C and G150). In conclusion, multifractal analysis enables changes in UPE time series to be detected even when they are hidden for normal linear signal analysis methods. The analysis of changes in the multifractal properties might be a basis to design a classification system enabling the intoxication of cell cultures to be quantified based on UPE measurements.

NMF-SVM Based CAD Tool Applied to Functional Brain Images for the Diagnosis of Alzheimer's Disease

This paper presents a novel computer-aided diagnosis (CAD) technique for the early diagnosis of the Alzheimer's disease (AD) based on nonnegative matrix factorization (NMF) and support vector machines (SVM) with bounds of confidence. The CAD tool is designed for the study and classification of functional brain images. For this purpose, two different brain image databases are selected: a single photon emission computed tomography (SPECT) database and positron emission tomography (PET) images, both of them containing data for both Alzheimer's disease (AD) patients and healthy controls as a reference. These databases are analyzed by applying the Fisher discriminant ratio (FDR) and nonnegative matrix factorization (NMF) for feature selection and extraction of the most relevant features. The resulting NMF-transformed sets of data, which contain a reduced number of features, are classified by means of a SVM-based classifier with bounds of confidence for decision. The proposed NMF-SVM method yields up to 91% classification accuracy with high sensitivity and specificity rates (upper than 90%). This NMF-SVM CAD tool becomes an accurate method for SPECT and PET AD image classification.

Automated Diagnosis of Alzheimer Disease using the Scale-Invariant Feature Transforms in Magnetic Resonance Images

In this paper we present an automated method for diagnosing Alzheimer disease (AD) from brain MR images. The approach uses the scale-invariant feature transforms (SIFT) extracted from different slices in MR images for both healthy subjects and subjects with Alzheimer disease. These features are then clustered in a group of features which they can be used to transform a full 3-dimensional image from a subject to a histogram of these features. A feature selection strategy was used to select those bins from these histograms that contribute most in classifying the two groups. This was done by ranking the features using the Fisher's discriminant ratio and a feature subset selection strategy using the genetic algorithm. These selected bins of the histograms are then used for the classification of healthy/patient subjects from MR images. Support vector machines with different kernels were applied to the data for the discrimination of the two groups, namely healthy subjects and patients diagnosed by AD. The results indicate that the proposed method can be used for diagnose of AD from MR images with the accuracy of %86 for the subjects aged from 60 to 80 years old and with mild AD.

Assessing the diagnostic information in the response patterns of a temperature-modulated tin oxide gas sensor

The transient response patterns of a tin oxide chemoresistive gas sensor, temperature-modulated by the application of staircase voltage waveforms to its microheater, to five different volatile organic compounds were compared with respect to their target gas discriminating features. These patterns were divided into a number of segments, each corresponding to a temperature transition at the surface of the tin oxide pallet. The effectiveness of the gas discriminating information content of each segment was quantitatively assessed utilizing Fisher's discriminant ratio calculations in a 3D feature space. It was established that the amount of the useful information in a response segment depended on the corresponding temperature transition; larger pallet temperature transitions rendered more diagnostic information. Similar assessments were carried out for the different combinations of these segments. The results facilitated, for the first time, a comparative analysis of the levels of the correlated (redundant) and uncorrelated information in the different response segments. It was shown that the response segments occurring at or near the nominal operating temperature of the sensor contained most of the effective information, while those at low temperatures contained mostly the redundant or indiscriminative information. The results help minimize the temperature modulation duration required for gas recognition.

Principal component analysis-based techniques and supervised classification schemes for the early detection of Alzheimer's disease

In Alzheimer's disease (AD) diagnosis process, functional brain image modalities such as Single-Photon Emission Computed Tomography (SPECT) and Positron Emission Tomography (PET) have been widely used to guide the clinicians. However, the current evaluation of these images entails a succession of manual reorientations and visual interpretation steps, which attach in some way subjectivity to the diagnostic. In this work, a complete computer aided diagnosis (CAD) system for an automatic evaluation of the neuroimages is presented. Principal component analysis (PCA)-based methods are proposed as feature extraction techniques, enhanced by other linear approaches such as linear discriminant analysis (LDA) or the measure of the Fisher discriminant ratio (FDR) for feature selection. The final features allow to face up the so-called small sample size problem and subsequently they are used for the study of neural networks (NN) and support vector machine (SVM) classifiers. The combination of the presented methods achieved accuracy results of up to 96.7% and 89.52% for SPECT and PET images, respectively, which means a significant improvement over the results obtained by the classical voxels-as-features (VAF) reference approach.

On the distance concentration awareness of certain data reduction techniques

We make a first investigation into a recently raised concern about the suitability of existing data analysis techniques when faced with the counter-intuitive properties of high dimensional data spaces, such as the phenomenon of distance concentration. Under the structural assumption of a generic linear model with a latent variable and an additive unstructured noise, we find that dimension reduction that explicitly guards against distance concentration recovers the well-known techniques of Fisher's linear discriminant analysis, Fisher's discriminant ratio and a variant of projection pursuit. Extrapolation to regression uncovers a close link to sure independence screening, which is a recently proposed technique for variable selection in ultra-high dimensional feature spaces. Hence, these techniques may be seen as distance concentration aware, despite they have not been explicitly designed to have this property. Throughout our analysis, other than the dependency structure implied by the mentioned linear model, we make no assumptions about the distributions of the variables involved.

Analysis of SPECT brain images for the diagnosis of Alzheimer's disease based on NMF for feature extraction

This letter presents a novel computer-aided diagnosis (CAD) technique for the early diagnosis of Alzheimer's disease (AD) based on non-negative matrix factorization (NMF) analysis applied to single photon emission computed tomography (SPECT) images. A baseline normalized SPECT database containing normalized data for both AD patients and healthy reference patients is selected for this study. The SPECT database is analyzed by applying the Fisher discriminant ratio (FDR) for feature selection and NMF for feature extraction of relevant components of each subject. The main goal of these preprocessing steps is to reduce the large dimensionality of the input data and to relieve the so called “curse of dimensionality” problem. The resulting NMF-transformed set of data, which contains a reduced number of features, is classified by means of a support vector machines based classification technique (SVM). The proposed NMF + SVM method yields up to 94% classification accuracy, with high sensitivity and specificity values (upper than 90%), becoming an accurate method for SPECT image classification. For the sake of completeness, comparison between another recently developed principal component analysis (PCA) plus SVM method and the proposed method is also provided, yielding results for the NMF + SVM approach that outperform the behavior of the reference PCA + SVM or conventional voxel-as-feature (VAF) plus SVM methods.

Novel Multiclass Classifiers Based on the Minimization of the Within-Class Variance

In this paper, a novel class of multiclass classifiers inspired by the optimization of Fisher discriminant ratio and the support vector machine (SVM) formulation is introduced. The optimization problem of the so-called minimum within-class variance multiclass classifiers (MWCVMC) is formulated and solved in arbitrary Hilbert spaces, defined by Mercer's kernels, in order to find multiclass decision hyperplanes/surfaces. Afterwards, MWCVMCs are solved using indefinite kernels and dissimilarity measures via pseudo-Euclidean embedding. The power of the proposed approach is first demonstrated in the facial expression recognition of the seven basic facial expressions (i.e., anger, disgust, fear, happiness, sadness, and surprise plus the neutral state) problem in the presence of partial facial occlusion by using a pseudo-Euclidean embedding of Hausdorff distances and the MWCVMC. The experiments indicated a recognition accuracy rate achieved up to 99%. The MWCVMC classifiers are also applied to face recognition and other classification problems using Mercer's kernels.

Classification of Induction Machine Faults by Optimal Time–Frequency Representations

This paper presents a new diagnosis method of induction motor faults based on time-frequency classification of the current waveforms. This method is based on a representation space, a selection criterion, and a decision criterion. In order to define the representation space, an optimized time-frequency representation (TFR) is designed from the time-frequency ambiguity plane. The selection criterion is based on Fisher's discriminant ratio, which allows one to maximize the separability between classes representing different faults. A distinct TFR is designed for each class. The following two classifiers were used for decision criteria: the Mahalanobis distance and the hidden Markov model. The flexibility of this method allows an accurate classification independent from the level of load. This method is validated on a 5.5-kW induction motor test bench.

Time–Frequency Analysis for Efficient Fault Diagnosis and Failure Prognosis for Interior Permanent-Magnet AC Motors

The detection of noncatastrophic faults in conjunction with other factors can be used to determine the remaining life of an electric drive. As the frequency and severity of these faults increase, the working life of the drive decreases, leading to eventual failure. In this paper, four methods to identify developing electrical faults are presented and compared. They are based on the short-time Fourier transform, undecimated-wavelet analysis, and Wigner and Choi-Williams distributions of the field-oriented currents in permanent-magnet ac drives. The different fault types are classified using the linear-discriminant classifier and k-means classification. The comparison between the different methods is based on the number of correct classifications and Fisher's discriminant ratio. Multiple-class discrimination analysis is also introduced to remove redundant information and minimize storage requirements.

Minimum Class Variance Support Vector Machines

In this paper, a modified class of support vector machines (SVMs) inspired from the optimization of Fisher's discriminant ratio is presented, the so-called minimum class variance SVMs (MCVSVMs). The MCVSVMs optimization problem is solved in cases in which the training set contains less samples that the dimensionality of the training vectors using dimensionality reduction through principal component analysis (PCA). Afterward, the MCVSVMs are extended in order to find nonlinear decision surfaces by solving the optimization problem in arbitrary Hilbert spaces defined by Mercer's kernels. In that case, it is shown that, under kernel PCA, the nonlinear optimization problem is transformed into an equivalent linear MCVSVMs problem. The effectiveness of the proposed approach is demonstrated by comparing it with the standard SVMs and other classifiers, like kernel Fisher discriminant analysis in facial image characterization problems like gender determination, eyeglass, and neutral facial expression detection.

Simplified fuzzy ARTMAP classification of individuals using optimal VEP channels

In previous studies, identification of individuals using 61 channel Visual Evoked Potential (VEP) signals from the brain has been shown to be feasible. These studies used neural network classification of gamma band spectral power of VEP signals from

Dimensionality Reduction of a Pathological Voice Quality Assessment System Based on Gaussian Mixture Models and Short-Term Cepstral Parameters

Voice diseases have been increasing dramatically in recent times due mainly to unhealthy social habits and voice abuse. These diseases must be diagnosed and treated at an early stage, especially in the case of larynx cancer. It is widely recognized that vocal and voice diseases do not necessarily cause changes in voice quality as perceived by a listener. Acoustic analysis could be a useful tool to diagnose this type of disease. Preliminary research has shown that the detection of voice alterations can be carried out by means of Gaussian mixture models and short-term mel cepstral parameters complemented by frame energy together with first and second derivatives. This paper, using the F-Ratio and Fisher's discriminant ratio, will demonstrate that the detection of voice impairments can be performed using both mel cesptral vectors and their first derivative, ignoring the second derivative.