Direct Linear Discriminant Analysis Research Articles

Near-Infrared Spectroscopy Combined with Fuzzy Improved Direct Linear Discriminant Analysis for Nondestructive Discrimination of Chrysanthemum Tea Varieties.

The quality of chrysanthemum tea has a great connection with its variety. Different types of chrysanthemum tea have very different efficacies and functions. Moreover, the discrimination of chrysanthemum tea varieties is a significant issue in the tea industry. Therefore, to correctly and non-destructively categorize chrysanthemum tea samples, this study attempted to design a novel feature extraction method based on the fuzzy set theory and improved direct linear discriminant analysis (IDLDA), called fuzzy IDLDA (FIDLDA), for extracting the discriminant features from the near-infrared (NIR) spectral data of chrysanthemum tea. To start with, a portable NIR spectrometer was used to collect NIR data for five varieties of chrysanthemum tea, totaling 400 samples. Secondly, the raw NIR spectra were processed by four different pretreatment methods to reduce noise and redundant data. Thirdly, NIR data dimensionality reduction was performed by principal component analysis (PCA). Fourthly, feature extraction from the NIR spectra was performed by linear discriminant analysis (LDA), IDLDA, and FIDLDA. Finally, the K-nearest neighbor (KNN) algorithm was applied to evaluate the classification accuracy of the discrimination system. The experimental results show that the discrimination accuracies of LDA, IDLDA, and FIDLDA could reach 87.2%, 94.4%, and 99.2%, respectively. Therefore, the combination of near-infrared spectroscopy and FIDLDA has great application potential and prospects in the field of nondestructive discrimination of chrysanthemum tea varieties.

On the Equivalence of Linear Discriminant Analysis and Least Squares Regression.

Studying the relationship between linear discriminant analysis (LDA) and least squares regression (LSR) is of great theoretical and practical significance. It is well-known that the two-class LDA is equivalent to an LSR problem, and directly casting multiclass LDA as an LSR problem, however, becomes more challenging. Recent study reveals that the equivalence between multiclass LDA and LSR can be established based on a special class indicator matrix, but under a mild condition which may not hold under the scenarios with low-dimensional or oversampled data. In this article, we show that the equivalence between multiclass LDA and LSR can be established based on arbitrary linearly independent class indicator vectors and without any condition. In addition, we show that LDA is also equivalent to a constrained LSR based on the data-dependent indicator vectors. It can be concluded that under exactly the same mild condition, such two regressions are both equivalent to the null space LDA method. Illuminated by the equivalence of LDA and LSR, we propose a direct LDA classifier to replace the conventional framework of LDA plus extra classifier. Extensive experiments well validate the above theoretic analysis.

Accurate Classification of Chunmee Tea Grade Using NIR Spectroscopy and Fuzzy Maximum Uncertainty Linear Discriminant Analysis.

The grade of tea is closely related to tea quality, so the identification of tea grade is an important task. In order to improve the identification capability of the tea grade system, a fuzzy maximum uncertainty linear discriminant analysis (FMLDA) methodology was proposed based on maximum uncertainty linear discriminant analysis (MLDA). Based on FMLDA, a tea grade recognition system was established for the grade recognition of Chunmee tea. The process of this system is as follows: firstly, the near-infrared (NIR) spectra of Chunmee tea were collected using a Fourier transform NIR spectrometer. Next, the spectra were preprocessed using standard normal variables (SNV). Then, direct linear discriminant analysis (DLDA), maximum uncertainty linear discriminant analysis (MLDA), and FMLDA were used for feature extraction of the spectra, respectively. Finally, the k-nearest neighbor (KNN) classifier was applied to classify the spectra. The k in KNN and the fuzzy coefficient, m, were discussed in the experiment. The experimental results showed that when k = 1 and m = 2.7 or 2.8, the accuracy of the FMLDA could reach 98.15%, which was better than the other two feature extraction methods. Therefore, FMLDA combined with NIR technology is an effective method in the identification of tea grade.

Wrapper Based Linear Discriminant Analysis (LDA) for Intrusion Detection in IIoT

The internet has become a part of every human life. Also, various devices that are connected through the internet are increasing. Nowadays, the Industrial Internet of things (IIoT) is an evolutionary technology interconnecting various industries in digital platforms to facilitate their development. Moreover, IIoT is being used in various industrial fields such as logistics, manufacturing, metals and mining, gas and oil, transportation, aviation, and energy utilities. It is mandatory that various industrial fields require highly reliable security and preventive measures against cyber-attacks. Intrusion detection is defined as the detection in the network of security threats targeting privacy information and sensitive data. Intrusion Detection Systems (IDS) have taken an important role in providing security in the field of computer networks. Prevention of intrusion is completely based on the detection functions of the IDS. When an IIoT network expands, it generates a huge volume of data that needs an IDS to detect intrusions and prevent network attacks. Many research works have been done for preventing network attacks. Every day, the challenges and risks associated with intrusion prevention are increasing while their solutions are not properly defined. In this regard, this paper proposes a training process and a wrapper-based feature selection With Direct Linear Discriminant Analysis LDA (WDLDA). The implemented WDLDA results in a rate of detection accuracy (DRA) of 97% and a false positive rate (FPR) of 11% using the Network Security Laboratory-Knowledge Discovery in Databases (NSL-KDD) dataset.

DMLDA-LocLIFT: Identification of multi-label protein subcellular localization using DMLDA dimensionality reduction and LIFT classifier

Multi-label proteins occur in two or more subcellular locations, which play a vital role in cell development and metabolism. Prediction and analysis of multi-label subcellular localization (SCL) can present new perspective with drug target identification and new drug design. However, the prediction of multi-label protein SCL using biological experiments is expensive and labor-intensive. Therefore, predicting large-scale SCL with machine learning methods has turned into a popular study topic in bioinformatics. In this study, a novel multi-label learning methods for protein SCL prediction, called DMLDA-LocLIFT, is proposed. Firstly, the dipeptide composition (DC), encoding based on grouped weight (EBGW), pseudo amino acid composition (PseAAC), gene ontology (GO) and pseudo-position specific scoring matrix (PsePSSM) are employed to encode subcellular protein sequences. Then, using direct multi-label linear discriminant analysis (DMLDA) to get rid of noise information of the fused feature vector. Lastly, the first-best feature vectors are input into the multi-label learning with Label-specIfic FeaTures (LIFT) classifier to predict. The leave-one-out cross validation (LOOCV) shows that the overall actual accuracy on Gram-negative bacteria, Gram-positive bacteria, plant datasets, virus dataset and human dataset are 98.6%, 99.6%, 97.9%, 94.7% and 96.1% respectively, which are obviously better than other state-of-the-art prediction methods. The proposed model can effectively predict SCL of multi-label proteins and provide references for experimental identification of SCL. The source codes and datasets are available at https://github.com/QUST-AIBBDRC/DMLDA-LocLIFT/.

Stride towards aging problem in face recognition by applying hybrid local feature descriptors

In our proposed research, we developed a discriminative model for addressing the challenge of face recognition with respect to age variation by utilizing periocular region. Initially, we represent each face by using a densely sampled local feature description technique, in which multi-block local binary pattern (MB-LBP) and weber local descriptor (WLD) are adopted as the local descriptors. In this approach, extract the feature of entire facial image by the aid of both local descriptors. Since the feature space of both the MBLBP and WLD is vast, we develop an advanced multi-feature discriminant analysis to process these two local feature spaces in a unified framework. By random sampling, the training set as well as the feature space, multiple linear discriminant analysis (LDA) based K-nearest neighbor (K-NN) classifiers are constructed and then combined to generate a robust decision via a fusion rule. In the proposed method, the MORPH and FG-NET datasets are utilized for the experimental evaluation. In the MORPH dataset, our proposed method is compared with existing methods such as SIFT, Multi scale method based on morphology, signed grey level difference (SD), LBP, scale-invariant classification, gabor, hidden factor analysis (HFA), modified HFA (MHFA) and learning discriminant face descriptors (LFD). The accuracy of face and periocular region for our method is 98.83% and 98.32%. The existing method such as sparse null linear discriminate analysis (SNLDA), direct LDA, principle component analysis + LDA, cross-age reference coding (CARC), HFA and sparse representation classification (SRC) are compared with the proposed method and obtained the recognition rate is 96.74% and 97.89%. In parameter evaluation we get following values: recall is 93.34% and 96.56%, precision is 95.49% and 94.76%, F-score is 94.40% and 92.17% for face and periocular region. In the FG-NET dataset, our proposed method is compared with existing methods such as SIFT, LBP, MLBP, MWLD and multi-feature discriminant analysis (MFDA). The average accuracy in face region and the periocular region is 65.32% and 68.92%. Our proposed method produce recognition rate as 98.11% and 97.87% for face region and periocular region when compared with SNLDA, DLDA, SRC, PCA + LDA and Coupled Auto-encoder Networks (CAN). In parameter evaluation we get following values: recall is 90.85% and 91.65%, precision is 92.35% and 94.56%, F-score is 91.59% and 90.84% for face and periocular region. Our Method has error rate as 1.7% and our error rate is less when contrasted with Agarwal et al. (21%), Wallis et al. (11.5%), Wang et al. (4.515%) and Leibe et al. (2.5%) techniques.

LDA Extension via Oblique Projection

The classical linear discriminant analysis (LDA) was previously modified by orthogonal projection into null space LDA (N_LDA) and direct LDA (D_LDA) for solving small sample size (SSS) problem. In this paper, the author proposes an extension of LDA by oblique projection, wherein N_LDA and D_LDA are included as special cases, to reduce discriminative information loss resulted from single N_LDA or D_LDA. The effectiveness of the proposed algorithm is tested by image forensics and face recognition.

IMPROVEMENT OF THE PERFORMANCE OF FINGERPRINT VERIFICATION USING A COMBINATORIAL APPROACH

Fingerprint verification systems have attracted much attention in secure organizations; however, conventional methods still suffer from unconvincing recognition rate for noisy fingerprint images. To design a robust verification system, in this paper, wavelet and contourlet transforms (CTS) were suggested as efficient feature extraction techniques to elicit a coverall set of descriptive features to characterize fingerprint images. Contourlet coefficients capture the smooth contours of fingerprints while wavelet coefficients reveal its rough details. Due to the high dimensionality of the elicited features, across group variance (AGV), greedy overall relevancy (GOR) and Davis–Bouldin fast feature reduction (DB-FFR) methods were adopted to remove the redundant features. These features were applied to three different classifiers including Boosting Direct Linear Discriminant Analysis (BDLDA), Support Vector Machine (SVM) and Modified Nearest Neighbor (MNN). The proposed method along with state-of-the-art methods were evaluated, over the FVC2004 dataset, in terms of genuine acceptance rate (GAR), false acceptance rate (FAR) and equal error rate (EER). The features selected by AGV were the most significant ones and provided 95.12% GAR. Applying the selected features, by the GOR method, to the modified nearest neighbor, resulted in average EER of [Formula: see text]%, which outperformed the compared methods. The comparative results imply the statistical superiority ([Formula: see text]) of the proposed approach compared to the counterparts.

A view-invariant gait recognition algorithm based on a joint-direct linear discriminant analysis

This paper proposes a view-invariant gait recognition algorithm, which builds a unique view invariant model taking advantage of the dimensionality reduction provided by the Direct Linear Discriminant Analysis (DLDA). Proposed scheme is able to reduce the under-sampling problem (USP) that appears usually when the number of training samples is much smaller than the dimension of the feature space. Proposed approach uses the Gait Energy Images (GEIs) and DLDA to create a view invariant model that is able to determine with high accuracy the identity of the person under analysis independently of incoming angles. Evaluation results show that the proposed scheme provides a recognition performance quite independent of the view angles and higher accuracy compared with other previously proposed gait recognition methods, in terms of computational complexity and recognition accuracy.

Cross View Gait Recognition Using Joint-Direct Linear Discriminant Analysis.

This paper proposes a view-invariant gait recognition framework that employs a unique view invariant model that profits from the dimensionality reduction provided by Direct Linear Discriminant Analysis (DLDA). The framework, which employs gait energy images (GEIs), creates a single joint model that accurately classifies GEIs captured at different angles. Moreover, the proposed framework also helps to reduce the under-sampling problem (USP) that usually appears when the number of training samples is much smaller than the dimension of the feature space. Evaluation experiments compare the proposed framework’s computational complexity and recognition accuracy against those of other view-invariant methods. Results show improvements in both computational complexity and recognition accuracy.

One-dimensional vs. two-dimensional based features: Plant identification approach

The number of endangered species has been increased due to shifts in the agricultural production, climate change, and poor urban planning. This has led to investigating new methods to address the problem of plant species identification/classification. In this paper, a plant identification approach using 2D digital leaves images was proposed. The approach used two features extraction methods based on one-dimensional (1D) and two-dimensional (2D) and the Bagging classifier. For the 1D-based methods, Principal Component Analysis (PCA), Direct Linear Discriminant Analysis (DLDA), and PCA+LDA techniques were applied, while 2DPCA and 2DLDA algorithms were used for the 2D-based method. To classify the extracted features in both methods, the Bagging classifier, with the decision tree as a weak learner was used. The five variants, i.e. PCA, PCA+LDA, DLDA, 2DPCA, and 2DLDA, of the approach were tested using the Flavia public dataset which consists of 1907 colored leaves images. The accuracy of these variants was evaluated and the results showed that the 2DPCA and 2DLDA methods were much better than using the PCA, PCA+LDA, and DLDA. Furthermore, it was found that the 2DLDA method was the best one and the increase of the weak learners of the Bagging classifier yielded a better classification accuracy. Also, a comparison with the most related work showed that our approach achieved better accuracy under the same dataset and same experimental setup.

Hyperspectral Images Terrain Classification in Combination Spectrum DLDA Subspace

Hyperspectral images face the problem of high dimensionality and lowsamples number, which results in unsatisfied recognition efficiency, thus dimensionalityreduction is needed before terrain classification. A novel hyperspectral imagesfeature extraction method is presented for dimensionality reduction. Firstly,take discrete Fourier transformation (DFT) of each pixel spectral curve, andcombine the amplitude spectrum and corresponding phase spectrum; then directlinear discriminant analysis (DLDA) is performed in the combination spectrumspace to extract features. Minimum distance classifier is used to evaluate thefeature extraction performance in the achievedcombination spectrum DLDA subspace. The experimental results for airbornevisible/infrared imaging spectrometer (AVIRIS) hyperspectral image show that,comparing with the spectral DLDA subspace method, the present method canimprove the terrain classification efficiency.

Face recognition using Gabor-based direct linear discriminant analysis and support vector machine

This paper presents a novel and uniform framework for face recognition. This framework is based on a combination of Gabor wavelets, direct linear discriminant analysis (DLDA) and support vector machine (SVM). First, feature vectors are extracted from raw face images using Gabor wavelets. These Gabor-based features are robust against local distortions caused by the variance of illumination, expression and pose. Next, the extracted feature vectors are projected to a low-dimensional subspace using DLDA technique. The Gabor-based DLDA feature vectors are then applied to SVM classifier. A new kernel function for SVM called hyperhemispherically normalized polynomial (HNP) is also proposed in this paper and its validity on the improvement of classification accuracy is theoretically proved and experimentally tested for face recognition. The proposed algorithm was evaluated using the FERET database. Experimental results show that the proposed face recognition system outperforms other related approaches in terms of recognition rate.

Hyperspectral Images Terrain Classification Based on Power Transformation

In order to make the class distribution be close to Gaussian distribution, a hyperspectral images terrain classification method is presented base on power transformation (PT). Firstly PT is performed to original hyperspectral data to improve the class distribution Gaussianity, and then direct linear discriminant analysis (dLDA) is used to extract features, finally Bayesian classifier is designed in the achieved feature subspace for recognition. Experimental results based on airborne visible/infrared imaging spectrometer (AVIRIS) hyperspectral image show that, with data power transformed, the recognition rate of Bayesian classifier is dramatically improved, and the feature extraction effect of dLDA is enhanced to a certain degree.

Face recognition using nonparametric-weighted Fisherfaces

Abstract This study presents an appearance-based face recognition scheme called the nonparametric-weighted Fisherfaces (NW-Fisherfaces). Pixels in a facial image are considered as coordinates in a high-dimensional space and are transformed into a face subspace for analysis by using nonparametric-weighted feature extraction (NWFE). According to previous studies of hyperspectral image classification, NWFE is a powerful tool for extracting hyperspectral image features. The Fisherfaces method maximizes the ratio of between-class scatter to that of within-class scatter. In this study, the proposed NW-Fisherfaces weighted the between-class scatter to emphasize the boundary structure of the transformed face subspace and, therefore, enhances the separability for different persons' face. The proposed NW-Fisherfaces was compared with Orthogonal Laplacianfaces, Eigenfaces, Fisherfaces, direct linear discriminant analysis, and null space linear discriminant analysis methods for tests on five facial databases. Experimental results showed that the proposed approach outperforms other feature extraction methods for most databases.

Collarette Region Recognition based on Wavelets and Direct Linear Discriminant Analysis

recognition is seen as a highly reliable biometric technology. The performance of iris recognition is severely impacted when encountering poor quality images. The selection of the features subset and the classification is an important issue for iris biometrics. Here, we explored the contribution of collarette region in identifying a person. We applied five level haar wavelet decomposition for collarette region feature extraction and used the second level approximation coefficients combined with fifth level vertical coefficients for better accuracy. Then, we applied Direct Linear Discriminant Analysis (DLDA) to produce discriminative low-dimensional feature vectors. The approach is evaluated on CASIA Iris Interval database and we achieved 98.96% accuracy using the collarette region which is a significant improvement in the performance of recognition.

Ensemble based multi-linear discriminant analysis with boosting and nearest neighbor

The tensor based classifier has attracted a great deal of interest, due to its representation of input objects in a natural form in overcoming small sample size problems and in providing high classification accuracy. Multi-Linear Discriminant Analysis (MLDA) is an efficient classifier, which employs tensor properties to simplify computation and improve accuracy. In this study, a boosting framework is exploited to further improve a tensor-based MLDA classifier. In the boosting framework, several weak learners are trained with different distribution of training samples and, then, integrated with suitable weights to build a strong classifier with a high generalization capacity. In our proposed method, namely BMLDA (Boosted MLDA), the MLDA classifiers are weakened and considered as feature projection components (weak learners) in the boosting framework. Finally, a Nearest Neighbor (NN) classifier makes the final decision and enables the BMLDA to act as a multi-class classifier. To assess BMLDA, several versions of Linear Discriminant Analysis (LDA) classifiers, such as boosted direct LDA, direct LDA, subclass-LDA, MLDA and LDA, were implemented. Empirical evaluations on two real applications demonstrated that the proposed BMLDA outperformed its competitors. The proposed method is beneficial in exploiting the boosting framework to accommodate tensor-based learners that totally construct a powerful multi-class ensemble classifier with much higher performance.

Equivalence Between LDA/QR and Direct LDA

Singularity problems of scatter matrices in Linear Discriminant Analysis (LDA) are challenging and have obtained attention during the last decade. Linear Discriminant Analysis via QR decomposition (LDA/QR) and Direct Linear Discriminant analysis (DLDA) are two popular algorithms to solve the singularity problem. This paper establishes the equivalent relationship between LDA/QR and DLDA. They can be regarded as special cases of pseudo-inverse LDA. Similar to LDA/QR algorithm, DLDA can also be considered as a two-stage LDA method. Interestingly, the first stage of DLDA can act as a dimension reduction algorithm. The experiment compares LDA/QR and DLDA algorithms in terms of classification accuracy, computational complexity on several benchmark datasets and compares their first stages. The results confirm the established equivalent relationship and verify their capabilities in dimension reduction.

A Real-Time Face Recognition System Based on BDPCA Plus BDDLDA

Abstract Holistic-based methods, especially principal component analysis(PCA) and linear discriminant analysis(LDA), are very popularly used in face recognition. In last several years, the direct LDA(D-LDA) method was suggested to overcome the so-call “small simple size” problem. Besides, the researchers suggest bidirectional PCA(BDPCA) method, which may be more real-time and effective than PCA, and proposed BDPCA plus LDA (BDPCA+LDA). In the same way, we suggest bidirectional D-LDA(BDDLDA) should be faster than D-LDA, and proposed BDPCA plus BDDLDA (BDPCA+BDDLDA). In this paper, we present a real-time face recognition system for operating system authentication based on BDPCA+BDDLDA. A face database, which was collected with a CCD camera on the laptop, is used to evaluate this system. Experimental results show that this practical system is real-time and effective.

Normalized Direct Linear Discriminant Analysis with its Application to Face Recognition

The dimensionality of sample is often larger than the number of training samples for highdimensional pattern recognition such as face recognition. Here linear discriminant analysis (LDA) cannot be performed directly because of the singularity of the within-class scatter matrix. This is socalled “small sample size” (SSS) problem. PCA plus LDA (FDA) and Direct LDA (DLDA) are two popular methods to solve the SSS problem of LDA. In this paper, we point out the relationship of these two methods and discuss the deficiency of DLDA. Then a normalized direct linear discriminant analysis (NDLDA) method which overcomes DLDA’s deficiency is proposed. Experiments on ORL, YALE and AR face databases show NDLDA’s superiority over DLDA and FDA.