Orthogonal Linear Discriminant Analysis Research Articles

Rapid capture and quantification of food-borne spores based on the double-enhanced Fe3O4@PEI@Ag@PEI core-shell structure SERS sensor

To realize rapid capture and quantification of food-borne spores and prevent their potential harm, Fe3O4@PEI@Ag@PEI core-shell structure nanoparticles were combined with flower-like AgNPs for double enhancement and efficient capture of spores. The developed sensor showed excellent reproducibility and SERS enhancement factor (AEF) is 4.6 × 104. Orthogonal partial least-squares discrimination analysis and linear discriminant analysis accurately identified the three spores (Bacillus subtilis, Bacillus cereus, and Clostridium perfringens), and the qualitative identification accuracy of linear discriminant analysis was 100 %. Efficient enrichment of B. subtilis spores was realized within 5 min, with a detection limit of 3 cfu/mL. Spiked tests revealed that this sensor was effective in detecting spores in milk, orange juice, and water samples, with recovery ratio of 95.2−103.9 % and relative standard deviation of 3.1−7.7 %. Thus, the developed sensor was accurate and reliable, and could achieve rapid identification and quantitative detection of food-borne spores.

Discrimination of Radix Astragali from Different Growth Patterns, Origins, Species, and Growth Years by an H1-NMR Spectrogram of Polysaccharide Analysis Combined with Chemical Pattern Recognition and Determination of Its Polysaccharide Content and Immunological Activity.

The fraud phenomenon is currently widespread in the traditional Chinese medicine Radix Astragali (RA) market, especially where high-quality RA is substituted with low-quality RA. In this case, focused on polysaccharides from RA, the classification models were established for discrimination of RA from different growth patterns, origins, species, and growth years. 1H Nuclear Magnetic Resonance (H1-NMR) was used to establish the spectroscopy of polysaccharides from RA, which were used to distinguish RA via chemical pattern recognition methods. Specifically, orthogonal partial least squares discriminant analysis (OPLS-DA) and linear discriminant analysis (LDA) were used to successfully establish the classification models for RA from different growth patterns, origins, species, and growth years. The satisfactory parameters and high accuracy of internal and external verification of each model exhibited the reliable and good prediction ability of the developed models. In addition, the polysaccharide content and immunological activity were also tested, which was evaluated by the phagocytic activity of RAW 264.7. And the result showed that growth patterns and origins significantly affected the quality of RA. However, there was no significant difference in the aspects of origins and growth years. Accordingly, the developed strategy combined with chemical information, biological activity, and multivariate statistical method can provide new insight for the quality evaluation of traditional Chinese medicine.

Scatter matrix decomposition for jointly sparse learning

Orthogonal Linear Discriminant Analysis (OLDA) based on generalized Eigen-equation is widely used in the field of computer vision and pattern recognition. However, the performance of OLDA for feature extraction and classification needs to be improved as it lacks sparsity for better interpretation of the features. Moreover, computing the orthogonal sparse projections based on LDA is very difficult and is still unsolved. To solve these problems, in this paper, we propose a method called Jointly Sparse Orthogonal Linear Discriminant Analysis (JSOLDA). Different from the existing OLDA, JSOLDA is proposed from a novel viewpoint of scatter matrix decomposition. Theoretical analysis shows that OLDA can be derived by the constrained scatter matrix decomposition. In addition, by imposing L2,1-norm on the penalty term, the proposed JSOLDA can obtain the jointly sparse orthogonal projections to perform feature extraction. We also design an iterative algorithm to obtain the optimal solution. Systematic theoretical analysis between the OLDA and JSOLDA are uncovered. Both of convergence and computational complexity are also discussed. Experimental results on four data sets (i.e., COIL100, USPS, ICADAR2003 and CMU PIE) indicate that JSOLDA outperforms several well-known LDA-based and L2,1-norm based methods.

Rapid Identification of Benign Gallbladder Diseases Using Serum Surface-Enhanced Raman Spectroscopy Combined with Multivariate Statistical Analysis.

In this study, we looked at the viability of utilizing serum to differentiate between gallbladder (GB) stones and GB polyps using Surface-enhanced Raman spectroscopy (SERS), which has the potential to be a quick and accurate means of diagnosing benign GB diseases. Rapid and label-free SERS was used to conduct the tests on 148 serum samples, which included those from 51 patients with GB stones, 25 patients with GB polyps and 72 healthy persons. We used an Ag colloid as a Raman spectrum enhancement substrate. In addition, we employed orthogonal partial least squares discriminant analysis (OPLS-DA) and principal component linear discriminant analysis (PCA-LDA) to compare and diagnose the serum SERS spectra of GB stones and GB polyps. The diagnostic results showed that the sensitivity, specificity, and area under curve (AUC) values of the GB stones and GB polyps based on OPLS-DA algorithm reached 90.2%, 97.2%, 0.995 and 92.0%, 100%, 0.995, respectively. This study demonstrated an accurate and rapid means of combining serum SERS spectra with OPLS-DA to identify GB stones and GB polyps.

Determination of Pork Meat Storage Time Using Near-Infrared Spectroscopy Combined with Fuzzy Clustering Algorithms.

The identification of pork meat quality is a significant issue in food safety. In this paper, a novel strategy was proposed for identifying pork meat samples at different storage times via Fourier transform near-infrared (FT-NIR) spectroscopy and fuzzy clustering algorithms. Firstly, the FT-NIR spectra of pork meat samples were collected by an Antaris II spectrometer. Secondly, after spectra preprocessing with multiplicative scatter correction (MSC), the orthogonal linear discriminant analysis (OLDA) method was applied to reduce the dimensionality of the FT-NIR spectra to obtain the discriminant information. Finally, fuzzy C-means (FCM) clustering, K-harmonic means (KHM) clustering, and Gustafson–Kessel (GK) clustering were performed to establish the recognition model and classify the feature information. The highest clustering accuracies of FCM and KHM were both 93.18%, and GK achieved a clustering accuracy of 65.90%. KHM performed the best in the FT-NIR data of pork meat considering the clustering accuracy and computation. The overall experiment results demonstrated that the combination of FT-NIR spectroscopy and fuzzy clustering algorithms is an effective method for distinguishing pork meat storage times and has great application potential in quality evaluation of other kinds of meat.

RETRACTED: Online adaptive water management fault diagnosis of PEMFC based on orthogonal linear discriminant analysis and relevance vector machine

Abstract A data-driven strategy for characterizing the water management failure in a Proton Exchange Membrane Fuel Cell (PEMFC) is presented in this paper. To carry out the diagnosis of water management failure, first the original single cell voltages are projected into lower-dimension features by applying orthogonal linear discriminant analysis (OLDA). Then, a classification methodology termed relevance vector machine (RVM) is employed to classify the lower-dimension features into different categories that indicate the respective health states of the system. The initially trained projecting vectors and classifiers lose their efficiency gradually the characteristics of PEMFC system change, such as the cell voltages decaying with time due to the normal degradation due to aging. An online adaptive diagnostic strategy based on the posterior probability of RVM is proposed, so as to keep the diagnostic accuracy over time. The efficiency and reliability of this online adaptive diagnostic strategy is validated using an experimental database from a 90-cell PEMFC stack.

Subspace Learning and Feature Selection via Orthogonal Mapping

A plethora of dimensionality reduction (DR) techniques, stemming from statistics, machine learning, or graph theory, has been developed. Their ultimate objective is to eliminate data redundancy without a significant information loss. A general formulation, known as graph embedding, offers a unified framework for describing several well-known DR algorithms. In this paper, the inclusion of several DR algorithms within this unified framework is demonstrated. The enforcement of orthogonality to the projection matrix within this framework is proven to be of vital importance, since Orthogonal Neighborhood Preserving Projections, Orthogonal Locality Preserving Projections, Orthogonal Isometric Projection, Orthogonal Linear Discriminant Analysis, and Orthogonal Local Tangent Space Alignment algorithms outperform their non-orthogonal counterparts, e.g., Neighborhood Preserving Embedding, Locality Preserving Projections, Isometric Mapping, Linear Discriminant Analysis, and Local Tangent Space Alignment. One may simultaneously also impose the $\ell _{2,1}$ norm regularization on the projection matrix, seeking for row-sparsity. This leads to the known Joint Feature Selection and Subspace Learning (JFSSL) framework. All DR algorithms are employed within JFSSL. It is proven that the use of orthogonal mapping algorithms within JFSSL against their non-orthogonal counterparts does not improve the recognition rate of NN classifier.

Supervised Dimensionality Reduction Methods via Recursive Regression.

In this article, the recursive problems of both orthogonal linear discriminant analysis (OLDA) and orthogonal least squares regression (OLSR) are investigated. Different from other works, the associated recursive problems are addressed via a novel recursive regression method, which achieves the dimensionality reduction in the orthogonal complement space heuristically. As for the OLDA, an efficient method is developed to obtain the associated optimal subspace, which is closely related to the orthonormal basis of the optimal solution to the ridge regression. As for the OLSR, the scalable subspace is introduced to build up an original OLSR with optimal scaling (OS). Through further relaxing the proposed problem into a convex parameterized orthogonal quadratic problem, an effective approach is derived, such that not only the optimal subspace can be achieved but also the OS could be obtained automatically. Accordingly, two supervised dimensionality reduction methods are proposed via obtaining the heuristic solutions to the recursive problems of the OLDA and the OLSR.

Non-destructive identification of maize haploid seeds using nonlinear analysis method based on their near-infrared spectra

The identification of maize haploid seeds is a significant process in genetic research and modern maize breeding. Adopting near-infrared spectroscopy technology to distinguish haploid seeds from hybrid seeds has the advantages of being non-destructive, rapid and low cost. However, due to the influence of light, temperature, humidity, near-infrared intensity, instrument and dynamic change of seed activity, the near-infrared spectra of maize seeds showed high dimensional nonlinear characteristics. In this study, to make full use of the class label information, a nonlinear feature analytical method for haploid maize seeds identification based on Supervised Virtual Sample Kernel Locality Preserving Projection (SVSKLPP) has been proposed. The experimental results showed that the nonlinear identification model SVSKLPP achieved strong classification performance to identify the maize haploid seeds. Moreover, compared with the linear feature extraction methods Principal Component Analysis, Orthogonal Linear Discriminant Analysis, Locality Preserving Projection, Supervised Virtual Sample Locality Preserving Projection and nonlinear feature extraction methods Kernel Locality Preserving Projection, Isomap, Locally Linear Embedding, Laplacian Eigenmaps and Local Tangent Space Alignment, the SVSKLPP model achieved a better performance. The average accuracy, sensitivity and specificity using method SVSKLPP were 97.1%, 98.8% and 95.4% respectively, and it also had high robustness. The overall results show that the SVSKLPP-NIR methodology was efficient in accurately identifying haploid maize seeds, thus demonstrating its capabilities for application in haploid breeding for crop variety improvement.

Orthogonal sparse linear discriminant analysis

ABSTRACTLinear 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.

Self-weighted discriminative feature selection via adaptive redundancy minimization

Abstract In this paper, a novel self-weighted orthogonal linear discriminant analysis (SOLDA) method is firstly proposed, such that optimal weight can be automatically achieved to balance both between-class and within-class scatter matrices. Since correlated features tend to have similar rankings, multiple adopted criteria might lead to the state that top ranked features are selected with large correlations, such that redundant information is brought about. To minimize associated redundancy, an original regularization term is introduced to the proposed SOLDA problem to penalize the high-correlated features. Different from other methods and techniques, we optimize redundancy matrix as a variable instead of setting it as a priori, such that correlations among all the features can be adaptively evaluated. Additionally, a brand new recursive method is derived to achieve the selection matrix heuristically, such that closed form solution can be obtained with holding the orthogonality. Consequently, self-weighted discriminative feature selection via adaptive redundancy minimization (SDFS-ARM) method can be summarized, such that non-redundant discriminative features could be selected correspondingly. Eventually, the effectiveness of the proposed SDFS-ARM method is further validated by the empirical results.

Self-Weighted Supervised Discriminative Feature Selection.

In this brief, a novel self-weighted orthogonal linear discriminant analysis (SOLDA) problem is proposed, and a self-weighted supervised discriminative feature selection (SSD-FS) method is derived by introducing sparsity-inducing regularization to the proposed SOLDA problem. By using the row-sparse projection, the proposed SSD-FS method is superior to multiple sparse feature selection approaches, which can overly suppress the nonzero rows such that the associated features are insufficient for selection. More specifically, the orthogonal constraint ensures the minimal number of selectable features for the proposed SSD-FS method. In addition, the proposed feature selection method is able to harness the discriminant power such that the discriminative features are selected. Consequently, the effectiveness of the proposed SSD-FS method is validated theoretically and experimentally.

High-dimensional feature extraction using bit-plane decomposition of local binary patterns for robust face recognition

Transforming an original image into a high-dimensional (HD) feature has been proven to be effective in classifying images. This paper presents a novel feature extraction method utilizing the HD feature space to improve the discriminative ability for face recognition. We observed that the local binary pattern can be decomposed into bit-planes, each of which has scale-specific directional information of the face image. Each bit-plane not only has the inherent local-structure of the face image but also has an illumination-robust characteristic. By concatenating all the decomposed bit-planes, we generate an HD feature vector with an improved discriminative ability. To reduce the computational complexity while preserving the incorporated local structural information, a supervised dimension reduction method, the orthogonal linear discriminant analysis, is applied to the HD feature vector. Extensive experimental results show that existing classifiers with the proposed feature outperform those with other conventional features under various illumination, pose, and expression variations.

Spectral–spatial feature extraction using orthogonal linear discriminant analysis for classification of hyperspectral data

ABSTRACTHyperspectral image classification is among the most frequent topics of research in recent publications. This paper proposes a new supervised linear feature extraction method for classification of hyperspectral images using orthogonal linear discriminant analysis in both spatial and spectral domains. In fact, an orthogonal filter set and a spectral data transformation are designed simultaneously by maximizing the class separability. The important characteristic of the presented approach is that the proposed filter set is supervised and considers the class separability when extracting the features, thus it is more appropriate for feature extraction compared with other filters such as Gabor. In order to compare the proposed method with some existing methods, the extracted spatial–spectral features are fed into a support vector machine classifier. Some experiments on the widely used hyperspectral images, namely Indian Pines, Pavia University, and Salinas data sets, reveal that the proposed approach leads to state-of-the-art performance when compared to other recent approaches.

LBP-ferns-based feature extraction for robust facial recognition

Most facial recognition (FR) systems first extract discriminative features from a facial image and then perform classification. This paper proposes a method aimed at representing human facial traits and a low-dimensional feature extraction method using orthogonal linear discriminant analysis (OLDA). The proposed feature relies on a local binary pattern to represent texture information and random ferns to build a structural model. By concatenating its feature vectors, the proposed method achieves a high-dimensional descriptor of the input facial image. In general, the feature dimension is highly related to its discriminative ability. However, higher dimensionality is more complex to compute. Thus, dimensionality reduction is essential for practical FR applications. OLDA is employed to reduce the dimension of the extracted features and improve discriminative performance. With a representative FR database, the proposed method demonstrates a higher recognition rate and low computational complexity compared to existing FR methods. In addition, with a facial image database with disguises, the proposed algorithm demonstrates outstanding performance.

Feasibility study on nondestructively sensing meat's freshness using light scattering imaging technique

Rich nutrient matrix meat is the first-choice source of animal protein for many people all over the world, but it is also highly susceptible to spoilage due to chemical and microbiological activities. In this work, we attempted the feasibility study of rapidly and nondestructively sensing meat's freshness using a light scattering technique. First, we developed the light scattering system for image acquisition. Next, texture analysis was used for extracting characteristic variables from the region of interest (ROI) of a scattering image. Finally, a novel classification algorithm adaptive boosting orthogonal linear discriminant analysis (AdaBoost–OLDA) was proposed for modeling, and compared with two classical classification algorithms linear discriminant analysis (LDA) and support vector machine (SVM). Experimental results showed that classification results by AdaBoost–OLDA algorithm are superior to LDA and SVM algorithms, and eventually achieved 100% classification rate in the calibration and prediction sets. This work demonstrates that the developed light scattering technique has the potential in noninvasively sensing meat's freshness.

Feasibility of analyzing frost-damaged and non-viable maize kernels based on near infrared spectroscopy and chemometrics

The current detection methods for maize seed damage and viability assessment are usually time-consuming, tedious, and costly. In this investigation, near infrared spectroscopy (NIRS), a nondestructive and rapid analytical method, was explored to analyze frost-damaged and non-viable seeds. Principal component analysis (PCA), partial least squares (PLS) and orthogonal linear discriminant analysis (OLDA) were combined to extract feature from near infrared (NIR) spectra. PLS + OLDA can extract difference characteristics of normal and frost-damaged seeds more efficiently than PCA + OLDA. Three classification algorithms were utilized and compared: Support vector machine (SVM), biomimetic pattern recognition (BPR), and mahalanobis distance (MD). BPR can classify normal and frost-damaged seeds better and achieved the highest average accuracy of 97%. Discrimination model of viable and non-viable seeds in frost-damaged seeds based on SVM, BPR and MD were built and achieved accuracies of 94%, 97.25% and 89.5% respectively. BPR model yielded the most correct value in predicting germination rate of validation set, and improved the germination rate of validation set dramatically from 27.5% to 100% by screening out non-viable seeds. NIRS and chemometrics as demonstrated in this paper can provide a novel method which can assess and improve quality of maize seed quickly and inexpensively.

Novel hybrid soft computing pattern recognition system SVM–GAPSO for classification of eight different hand motions

In this manuscript, we proposed an intelligent hybrid pattern recognition system to classify eight hand motions. Two evolutionary algorithms: genetic algorithm (GA) and particle swarm optimization (PSO) were combined with support vector machine (SVM) to construct a novel model (GAPSO–SVM). The proposed hybrid system able to obtain a high performance in handling learning task with SVM by selecting the optimal parameters of radial basis function (RBF–SVM) and choosing the optimal decomposition level of the mother wavelet function. In this study, energy of wavelet coefficients (EWC) were extracted from surface electromyographic (sEMG) signals, which collected from forearm's muscles. Moreover, due to the reason that the effectiveness of myoelectric pattern recognition system also depends on the degree of dimensionality reduction of the selected feature vector (FV), we investigated the performance of different feature projection algorithms: neighborhood preserving embedding (NPE), principle component analysis (PCA), independent components analysis (ICA) and orthogonal linear discriminant analysis (OLDA). The result shows that the proposed hybrid model predicts with greater accuracy and reliability in comparison to other three classifiers: support vector machines (SVM), fuzzy least squares support vector machines (LS–SVM) and K-nearest neighbor (K-NN). The highest achieved average accuracy rate was 98.7% by employing SVM-GAPSO classifier based on PCA.

A New and Fast Implementation of Orthogonal LDA Algorithm and Its Incremental Extension

Linear discriminant analysis (LDA) is one of the most popular dimension reduction methods and has been widely used in many applications. In the last decades many LDA-based dimension reduction algorithms have been reported. Among these methods, orthogonal LDA (OLDA) is a famous one and several different implementations of OLDA have been proposed. In this paper, we propose a new and fast implementation of OLDA. Compared with the other OLDA implementations, our proposed implementation of OLDA is the fastest one when the dimensionality d is larger than the sample size n. Then, based on our proposed implementation of OLDA, we present an incremental OLDA algorithm which can accurately update the projection matrix of OLDA when new samples are added into the training set. The effectiveness of our proposed new OLDA algorithm and its incremental version are demonstrated by some real-world data sets.

Fast orthogonal linear discriminant analysis with application to image classification

Compared to linear discriminant analysis (LDA), its orthogonalized version is a more effective statistical learning tool for dimension reduction, which devotes to better separating the data points from different classes in the lower-dimensional subspace. However, existing orthogonalized LDA techniques suffer from various drawbacks, including the requirement for expensive computing time. This paper develops an efficient orthogonal dimension reduction approach, referred to as fast orthogonal linear discriminant analysis (FOLDA), which is based on existing orthogonal linear discriminant analysis (OLDA) algorithms. However, different from previous efforts, the new approach applies the QR decomposition and the regression to solve for a new orthogonal projection vector at each iteration, leading to the by far cheaper computational cost. FOLDA achieves comparable recognition rate to existing OLDA algorithms due to the incorporation of the idea and spirit behind the latter ones. Experimental results on image databases, such as MINST, COIL20, MEPG-7 and OUTEX, show the effectiveness and efficiency of our algorithm.