Uncorrelated Linear Discriminant Analysis Research Articles

Rethinking Sweetener Discovering: Multiparameter Modeling of Molecular Docking Results between the T1R2-T1R3 Receptor and Compounds with Different Tastes.

Molecular docking has been widely applied in the discovery of new sweeteners, yet the interpretation of computational results sometimes remains difficult. Here, the interaction between the T1R2-T1R3 sweet taste receptor and 66 tasting compounds, including 26 sweet, 19 bitter, and 21 sour substances was investigated by batch molecular docking processes. Statistical analysis of the docking results generated two novel methods of interpreting taste properties. Quantitative correlation between relative sweetness (RS) and docking results created a multiparameter model to predict sweetness intensity, whose correlation coefficient r = 0.74 is much higher than r = 0.17 for the linear correlation model between sweetness and binding energy. The improved correlation indicated that docking results besides binding energy contain undiscovered information about the ligand-protein interaction. Qualitative discriminant analysis of different tasting molecules generated an uncorrelated linear discriminant analysis (UDLA) model, which achieved an overall 93.1% accuracy in discriminating the taste of molecules, with specific accuracy for verifying sweet, bitter, and sour compounds reaching 88.0%, 92.1%, and 100%. These unprecedented models provide a unique perspective for interpreting computational results and may inspire future research on sweetener discovery.

Bearing Fault Diagnosis Based on Discriminant Analysis Using Multi-View Learning

Bearing fault diagnosis has been a challenge in rotating machinery and has gained considerable attention. In order to correctly classify faults, the conventional fault diagnosis methods are mostly based on vibration signals. However, features extracted from a single view of vibration signals may leave out useful information, which can cause the incompleteness of intrinsic information and increase the risk of the performance degradation of fault classifications. In this paper, a novel bearing fault diagnosis method, discriminant analysis using multi-view learning (DAML), is proposed to tackle this issue. Multi-view datasets referring to vibration and acoustic signals are obtained by carrying out a fast Fourier transform (FFT). Then, multi-view feature (MVF) representation, including view-invariant and category discriminative information in a common subspace, is achieved based on canonical correlation analysis (CCA) and uncorrelated linear discriminant analysis (ULDA). Ultimately, with the help of the K-nearest neighbor (KNN) classifier built on the multi-view features, bearing faults are identified. The extensive experimental results show that DAML can identify the bearing fault accurately and outperforms other competitive approaches.

Neuromuscular disorders detection through time-frequency analysis and classification of multi-muscular EMG signals using Hilbert-Huang transform

Electromyographic (EMG) signal analysis plays a vital role in diagnosing neuromuscular disorders (NMD). It is based on the clinician’s experience in interpreting the signal’s shape and acoustic properties. For accurate detection of these disorders, developing new techniques to analyze these signals comprehensively has increased.This paper presents a machine learning strategy (ML) to classify EMG signals to automatically detecting the presence of neuropathy, myopathy, or absence of disease efficiently. A database of 938 signals acquired from different muscles divided symmetrically into these three classes was used. The method decomposes each signal into amplitude or frequency modulated sub-bands and extracts from them time-frequency features using the Hilbert Transform. Non-parametric statistical analysis and Uncorrelated Linear Discriminant Analysis (ULDA) were used for feature selection and data’s dimensionality reduction. Three different techniques of ML were used in the classification; LDA, TREE, and KNN. Five decomposition methods were evaluated: empirical mode decomposition (EMD), ensemble EMD (EEMD), complementary EEMD (CEEMD), empirical wavelet transform (EWT), and variational mode decomposition (VMD).The best results were achieved by using EEMD with the KNN with an accuracy of 99.5%. A sensitivity of 99.6% to the neuropathic and 98.8% for myopathic. A specificity of 99.2% and a positive predictive value of 99.6%. This study has the highest classification performance with such variability and extensive data, outperforming the state-of-the-art neuromuscular disorders classification. Consequently, the proposed methodology adequately interprets the information extracted from the quantitative time-frequency analysis, showing its validity to support the clinician in detecting and diagnosing NMD highly efficiently.

Performance Evaluation of SRELM on Bio-signal Pattern Recognition Using Two Electromyography Channels

The classification accuracy of pattern recognition is determined by the extracted features and the utilized classifiers. Many efforts have been conducted to obtain the best features either by introducing a new feature or proposing a new projection method to increase class separability. Recently, spectral regression extreme learning machine (SRELM) has been introduced to improve the class separability of the features. However, the evaluation of SRELM was only focused on the myoelectric or electromyography pattern recognition from many EMG channels. In practical application, the user is more convenient with less number of channels. Then, the problem is whether the SRELM would be able to work efficiently for less EMG channels. The objective of this paper is to examine the performance of SRELM for bio-signal pattern recognition using two EMG channels. The EMG electrodes were located on flexor policies lounges and flexor digitorium superficial muscles of ten healthy subjects. Various time domain features were involved with various sizes. SRELM will project these features to more recognize features before being feed to multiple classifiers. Those classifiers are randomized Variable Translation Wavelet Neural Networks (RVT-WNN), extreme learning machine(ELM), support vector machine (SVM), and linear discriminant analysis (LDA). The performance of SREM was compared to other feature methods, such as LDA, uncorrelated LDA (ULDA), orthogonal fuzzy neighborhood dimensionality reduction (OFNDA), and spectral regression discriminant analysis (SRDA). The experimental results show that SRELM performed well when dealing with different class numbers by classification accuracy of around 95.67% for ten class movements and performed better than SRDA.

Evaluation of feature extraction techniques and classifiers for finger movement recognition using surface electromyography signal.

Electromyography (EMG) in a bio-driven system is used as a control signal, for driving a hand prosthesis or other wearable assistive devices. Processing to get informative drive signals involves three main modules: preprocessing, dimensionality reduction, and classification. This paper proposes a system for classifying a six-channel EMG signal from 14 finger movements. A feature vector of 66 elements was determined from the six-channel EMG signal for each finger movement. Subsequently, various feature extraction techniques and classifiers were tested and evaluated. We compared the performance of six feature extraction techniques, namely principal component analysis (PCA), linear discriminant analysis (LDA), uncorrelated linear discriminant analysis (ULDA), orthogonal fuzzy neighborhood discriminant analysis (OFNDA), spectral regression linear discriminant analysis (SRLDA), and spectral regression extreme learning machine (SRELM). In addition, we also evaluated the performance of seven classifiers consisting of support vector machine (SVM), linear classifier (LC), naive Bayes (NB), k-nearest neighbors (KNN), radial basis function extreme learning machine (RBF-ELM), adaptive wavelet extreme learning machine (AW-ELM), and neural network (NN). The results showed that the combination of SRELM as the feature extraction technique and NN as the classifier yielded the best classification accuracy of 99%, which was significantly higher than those from the other combinations tested. Graphical abstract Mean of classification accuracies for 14 finger movements obtained with various pairs of SRELM and classifier.

Myoelectric control of upper limb prostheses using linear discriminant analysis and multilayer perceptron neural network with back propagation algorithm

Electromyogram (EMG) signals or myoelectric signals (MESs) have two prominent areas in the field of biomedical instrumentation. EMG signals are primarily used to analyse the neuromuscular diseases such as myopathy and neuropathy. In addition, the EMG signal can be utilised in myoelectric control systems - where the external devices like upper limb prostheses, intelligent wheelchairs, and assistive robots can be controlled by acquiring surface EMG signals. The aim of present work is to obtain classification accuracy first by using linear discriminant analysis (LDA) classifier where principal component analysis (PCA) and uncorrelated linear discriminant analysis (ULDA) feature reduction techniques are used for upper limb prostheses control application. Next, the multilayer perceptron (MLP) neural network with back propagation algorithm is used to calculate the classification accuracy for upper limb prostheses control.

紫外分光光度法结合化学计量学方法对复方氨酚烷胺类药物的分析

紫外分光光度法操作简便、信息量大，是一种应用广泛的分析方法。本文将紫外分光光度法结合化学计量学方法对复方氨酚烷胺类药物的紫外图谱进行了分析。应用非相关线性判别分析方法对3个厂家的复方氨酚烷胺类药物进行了分类，效果良好。然后运用偏最小二乘法，预测了复方氨酚烷胺类药物中对乙酰氨基酚和马来酸氯苯那敏两种组分的含量，结果准确。所以，紫外分光光度法结合化学计量学方法在药物的分类鉴别和成分分析方面有着广阔的应用前景。 Ultraviolet (UV) spectrophotometry is a widely used analytical method, which is easy to operate and has a large amount of information. In this paper, the UV spectra of compound paracetamol and amantadine hydrochloride were analyzed by UV spectrophotometry and chemometrics. The un-correlated linear discriminant analysis method was used to classify the compound paracetamol and amantadine hydrochloride from three manufacturers, and the effect was good. Then the partial least squares method was used to predict the contents of acetaminophen and chlorpheniramine maleate in the compound paracetamol and amantadine hydrochloride, and the results were accurate. Therefore, the UV spectrophotometry combined with chemometrics methods has broad application prospects in the classification and identification of drugs and component analysis.

Prediction of pork storage time using Fourier transform near infrared spectroscopy and Adaboost‐ULDA

AbstractPork storage time is related to its freshness. To discriminate the pork storage time rapidly, Adaboost‐ULDA algorithm was proposed to classify the Fourier transform near infrared reflectance (FT‐NIR) spectra of pork samples acquired by a Fourier transform near‐infrared spectrophotometer. Adaboost‐ULDA can not only extract discriminant information from FT‐NIR spectra but also construct a strong classifier with weak classifiers to classify spectra. Adaboost‐ULDA is a powerful classifier by combining uncorrelated linear discriminant analysis (ULDA) with Adaboost. Experimental results showed that Adaboost‐ULDA achieved the highest classification accuracy (100%) and classification accuracies were obtained as 87.9, 89.4, and 97.7% in principal component analysis (PCA) plus linear discriminant analysis (LDA), ULDA, and Adaboost‐PCA + LDA, respectively. In addition, the experiments demonstrated that the classification time of Adaboost‐ULDA was much less than that of Adaboost‐PCA + LDA. The overall results show that Adaboost‐ULDA combined with FT‐NIR is a feasible method in predicting the pork storage time.Practical applicationsFreshness is an important quality characteristic to pork's quality for food industry. Pork storage time is associated with its freshness. From the food safety point of view, it is significant and meaningful to predict the pork storage time. In our research, the proposed Adaboost‐ULDA coupled with Fourier transform near‐infrared reflectance spectroscopy can successfully predict the pork storage time. The results demonstrate the application prospect of this method to the quality control of pork products.

Pattern Recognition Methods Combined with Raman Spectra Applied to Distinguish Serums from Lung Cancer Patients and Healthy People

Raman spectroscopy was used to distinguish the serums from lung cancer patients and healthy people, through spectral pretreatment method combined with pattern recognition methods including principal component analysis (PCA), partial least squares-discriminant analysis (PLS-DA), un-correlated linear discriminant analysis (ULDA), etc. Through the comparisons of the results, it can be found that ULDA and LDA combined with multiple scatter correction (MSC) pretreatment method successfully distinguish the patients of lung cancer and healthy people. The method has academic significance and promising clinical application value.

Sparse Uncorrelated Linear Discriminant Analysis for Undersampled Problems

Linear discriminant analysis (LDA) as a well-known supervised dimensionality reduction method has been widely applied in many fields. However, the lack of sparsity in the LDA solution makes interpretation of the results challenging. In this paper, we propose a new model for sparse uncorrelated LDA (ULDA). Our model is based on the characterization of all solutions of the generalized ULDA. We incorporate sparsity into the ULDA transformation by seeking the solution with minimum ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -norm from all minimum dimension solutions of the generalized ULDA. The problem is then formulated as an ℓ <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sub> -minimization problem with orthogonality constraint. To solve this problem, we devise two algorithms: 1) by applying the linearized alternating direction method of multipliers and 2) by applying the accelerated linearized Bregman method. Simulation studies and high-dimensional real data examples demonstrate that our algorithms not only compute extremely sparse solutions but also perform well in classification.

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

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.

Multiview Uncorrelated Discriminant Analysis.

Multiview learning is more robust than single-view learning in many real applications. Canonical correlation analysis (CCA) is a popular technique to utilize information stemming from multiple feature sets. However, it does not exploit label information effectively. Later multiview linear discriminant analysis (MLDA) was proposed through combining CCA and linear discriminant analysis (LDA). Due to the successful application of uncorrelated LDA (ULDA), which seeks optimal discriminant features with minimum redundancy, we propose a new supervised learning method called multiview ULDA (MULDA) in this paper. This method combines the theory of ULDA with CCA. Then we adapt discriminant CCA (DCCA) instead of the CCA in MLDA and MULDA, and discuss about the effect of this modification. Furthermore, we generalize these methods to the nonlinear case by kernel-based learning techniques. The new method is called kernel multiview uncorrelated discriminant analysis (KMUDA). Then we modify kernel multiview discriminant analysis and KMUDA by replacing Kernel CCA with Kernel DCCA. Our methods are tested on different real datasets and compared with other state-of-the-art methods. Experimental results validate the effectiveness of our methods.

Incremental Linear Discriminant Analysis: A Fast Algorithm and Comparisons.

It has always been a challenging task to develop a fast and an efficient incremental linear discriminant analysis (ILDA) algorithm. For this purpose, we conduct a new study for linear discriminant analysis (LDA) in this paper and develop a new ILDA algorithm. We propose a new batch LDA algorithm called LDA/QR. LDA/QR is a simple and fast LDA algorithm, which is obtained by computing the economic QR factorization of the data matrix followed by solving a lower triangular linear system. The relationship between LDA/QR and uncorrelated LDA (ULDA) is also revealed. Based on LDA/QR, we develop a new incremental LDA algorithm called ILDA/QR. The main features of our ILDA/QR include that: 1) it can easily handle the update from one new sample or a chunk of new samples; 2) it has efficient computational complexity and space complexity; and 3) it is very fast and always achieves competitive classification accuracy compared with ULDA algorithm and existing ILDA algorithms. Numerical experiments based on some real-world data sets demonstrate that our ILDA/QR is very efficient and competitive with the state-of-the-art ILDA algorithms in terms of classification accuracy, computational complexity, and space complexity.

Is uncorrelated linear discriminant analysis really a new method?

Fisher's linear discriminant analysis and linear discriminant analysis (LDA) are powerful methods in multivariate data analysis. Recently, a method called “uncorrelated linear discriminant analysis (ULDA)” has attracted attention in the chemometrics community. It has been stated that the major difference between ULDA and LDA is that the discriminant vectors of ULDA must satisfy an “S-orthogonality” constraint. This has led to the impression that ULDA is a different method from LDA. A number of papers published in the chemometrics field and others have generally accepted this statement. However, it can be shown that the so-called ULDA method is equivalent to Fisher's linear discriminant analysis or one simple case of LDA. There is a need to resolve the confusion surrounding ULDA in the chemometrics community. This work clarifies this confusion from a mathematical perspective and demonstrates equivalence using real experimental data sets.

Sparse Canonical Correlation Analysis: New Formulation and Algorithm

In this paper, we study canonical correlation analysis (CCA), which is a powerful tool in multivariate data analysis for finding the correlation between two sets of multidimensional variables. The main contributions of the paper are: 1) to reveal the equivalent relationship between a recursive formula and a trace formula for the multiple CCA problem, 2) to obtain the explicit characterization for all solutions of the multiple CCA problem even when the corresponding covariance matrices are singular, 3) to develop a new sparse CCA algorithm, and 4) to establish the equivalent relationship between the uncorrelated linear discriminant analysis and the CCA problem. We test several simulated and real-world datasets in gene classification and cross-language document retrieval to demonstrate the effectiveness of the proposed algorithm. The performance of the proposed method is competitive with the state-of-the-art sparse CCA algorithms.

Plasma fatty acid metabolic profiles for traditional Chinese medicine syndrome differentiation in diabetic patients using uncorrelated linear discriminant analysis

Diabetes is a common metabolic syndrome which presents a serious threat to human health. Traditional Chinese medicine (TCM) has been widely paid attention to its advantages and characteristics in the diagnosis and the treatment of diabetes. A strategy of classifying five TCM syndromes in diabetes (Qi-deficiency, Yin-deficiency, Qi- and Yin-deficiency, Damp heat and Blood stasis) was employed based on plasma fatty acid metabolic profiles, lipid metabolism indicators and chemometrics methods. Using orthogonal signal correction-partial least squares (OSC-PLS) method, the five syndromes were obviously distinguished from those of the health control, which confirmed there existed metabolite differences in different traditional Chinese medicine syndromes. Furthermore, a new method, uncorrelated linear discriminant analysis (ULDA), was applied in the discrimination of health control, TCM deficiency syndromes (Qi-deficiency, Yin-deficiency, Qi- and Yin-deficiency) and TCM empirical syndromes (Damp heat, Blood stasis), which demonstrated better clustering results, the correct rate reached 95.7%. The four potential biomarkers, C20: 2, C20: 5, triglycerides (TG) and high density lipoprotein (HDL), performed large contributions to the classification which can provide important information assisting TCM clinical diagnosis.

Efficient optimally regularized discriminant analysis

Regularized discriminant analysis (RDA) and its special case uncorrelated linear discriminant analysis (ULDA) are important subspace learning methods proposed recently to handle the small sample size (SSS) problem of linear discriminant analysis (LDA). One important unsolved issue of RDA is how to automatically determine an appropriate regularization parameter without resorting to unscalable procedures like cross-validation (CV). In this paper, we develop a novel efficient algorithm to automatically estimate the regularization parameter based on a geometric interpretation of RDA. We further provide a formal analysis of the proposed method, and show that it is robust to the perturbation in the feature space of the training data. The extensive experiments on various benchmark datasets verify the scalability and effectiveness of our approach, compared with the state-of-the-art algorithms.

INVESTIGATING LONG-TERM EFFECTS OF FEATURE EXTRACTION METHODS FOR CONTINUOUS EMG PATTERN CLASSIFICATION

Based on recent advances in modern multifunction myoelectric control devices, a combination of effective feature extraction and classification methods is required to enhance the high classification performance, especially in accuracy viewpoint. However, for realizing practical applications of myoelectric control, the effect of long-term usage or reusability is one of the challenging issues that should be more carefully considered, whereas only a few works have investigated this effect in recent. In this study, the behavior of the state-of-the-art multiple feature extraction methods was investigated with the fluctuating electromyography (EMG) signals recorded during four different days with a large number of trials and subjects. To this end, seven multiple feature sets were compared consisting features based on time domain and time-scale representation. Two major points were emphasized: (1) the optimal robust feature set for continuous (both transient and steady-state signals) EMG pattern classification and (2) the effect of fluctuating EMG signals with feature extraction methods for long-term usage. From the classification results, time domain feature sets yielded better performance than time-scale feature sets. The classification accuracies of the time-domain-feature sets had always achieved above 80% by using linear discriminant analysis (LDA) as a classifier and uncorrelated LDA (ULDA) as a dimensionality reduction, whereas the classification accuracies of the time-scale-feature sets were lower than 70% for the fluctuating EMG signals. The effect of dimensionality reduction for the classification of fluctuating EMG signals was also discussed.

Discrimination of type 2 diabetes mellitus corresponding to different traditional Chinese medicine syndromes based on plasma fatty acid profiles and chemometric methods

Aims of the studyTraditional Chinese medicine (TCM) has a long history and particular advantages in the diagnosis and treatment of type 2 diabetes mellitus (T2DM). Syndrome differentiation is the foundation and essence of TCM theories. The aims of the study are to discriminate T2DM corresponding to different syndromes (Qi-deficiency, Qi and Yin-deficiency and Damp heat) and discover syndrome-related biomarkers using metabolomics technology. Materials and methodsPlasma fatty acid profiles of 85 clinical samples were established by high performance liquid chromatography (HPLC). Moreover, some of the lipid parameters, including total cholesterol (TC), triglycerides (TG), high-density lipoprotein (HDL) and low-density lipoprotein (LDL), were obtained through clinical testing methods. Orthogonal signal correction-partial least squares (OSC-PLS) and uncorrelated linear discriminant analysis (ULDA) were employed to establish two-class models for three different syndromes. ResultsCompared with the plasma fatty acid profiles of healthy controls, the characteristic fatty acids of three TCM syndromes were discovered (p<0.01). Totally, the plasma fatty acids of T2DM were up-regulated, while significant differences existed in different syndromes. Results of ULDA indicate that the three TCM syndromes could be effectively separated by the plasma fatty acid profiles and the syndrome-related biomarkers were also screened. ConclusionsThe fact that three TCM syndromes can be separated indicates certain metabolic differences in different TCM syndromes of T2DM really exist and such differences can be manifested by fatty acids and lipid parameters. The results benefit modern biological interpretation of the three TCM syndromes and in a sense the diagnosis and treatment of diabetes.

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

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.