Improved Sparse Representation based Robust Hybrid Feature Extraction Models with Transfer and Deep Learning for EEG Classification

ENIC: Ensemble and Nature Inclined Classification with Sparse Depiction based Deep and Transfer Learning for Biosignal Classification

The clinical assistant diagnosis has a high requirement for the visual effect of medical images. However, the low frequency subband coefficients obtained by the NSCT decomposition are not sparse, which is not conducive to maintaining the details of the source image. To solve these problems, a medical image fusion algorithm combined with sparse representation and pulse coupling neural network is proposed. First, the source image is decomposed into low and high frequency subband coefficients by NSCT transform. Secondly, the K singular value decomposition (K-SVD) method is used to train the low frequency subband coefficients to get the overcomplete dictionary D, and the orthogonal matching pursuit (OMP) algorithm is used to sparse the low frequency subband coefficients to complete the fusion of the low frequency subband sparse coefficients. Then, the pulse coupling neural network (PCNN) is excited by the spatial frequency of the high frequency subband coefficients, and the fusion coefficients of the high frequency subband coefficients are selected according to the number of ignition times. Finally, the fusion medical image is reconstructed by NSCT inverter. The experimental results and analysis show that the algorithm of gray and color image fusion is about 34% and 10% higher than the contrast algorithm in the edge information transfer factor QAB/F index, and the performance of the fusion result is better than the existing algorithm.

K-Singular Value Decomposition (K-SVD) is an excellent feature analysis method, but it has a large amount of calculation and low algorithm efficiency. To solve the above problems, a dictionary learning method for image block classification training is proposed. This method uses image entropy as the classification index of image samples, selects more complex texture image blocks with more analytical value, and uses Discrete Cosine Transform- Discrete Wavelet Transformation (DCT-DWT) dictionary to train them in K-Singular Value Decomposition. Through the feedback of sparse coefficients, the threshold value is dynamically changed and the precision of sparse coding is controlled. In the sparse solution, a variable-step Orthogonal Matching Pursuit (OMP) algorithm is used. The experimental comparison shows that the classification K-Singular Value Decomposition dictionary learning algorithm runs faster, and the Peak signal-to-noise Ratio (PSNR) and Structural Similarity (SSIM) value of the reconstructed image are higher.

Branch-and-bound algorithm for optimal sparse canonical correlation analysis

Canonical correlation analysis (CCA) has been widely used in pattern recognition and machine learning. However, both CCA and its extensions sometimes cannot give satisfactory results. In this paper, we propose a new CCA-type method termed sparse representation based discriminative CCA (SPDCCA) by incorporating sparse representation and discriminative information simultaneously into traditional CCA. In particular, SPDCCA not only preserves the sparse reconstruction relationship within data based on sparse representation, but also preserves the maximum-margin based discriminative information, and thus it further enhances the classification performance. Experimental results on Yale, Extended Yale B, and ORL datasets show that SPDCCA outperforms both CCA and its extensions including KCCA, LPCCA and LDCCA in face recognition.

In this paper we consider the problem of representing a speech signal with an adaptive transform that captures the main features of the data. The transform is orthogonal by construction, and is found to give a sparse representation of the data being analysed. The orthogonality property implies that evaluation of both the forward and inverse transform involve a simple matrix multiplication. The proposed dictionary learning algorithm is compared to the K singular value decomposition (K-SVD) method, which is found to yield very sparse representations, at the cost of a high approximation error. The proposed algorithm is shown to have a much lower computational complexity than K-SVD, while the resulting signal representation remains relatively sparse.

This work aims to propose an approach for pruning a bagging ensemble regression (BER) model based on sparse representation, which we call sparse representation pruning (SRP). Firstly, a BER model with a specific number of subensembles should be trained. Then, the BER model is pruned by our sparse representation idea. For this type of regression problems, pruning means to remove the subensembles that do not have a significant effect on prediction of the output. The pruning problem is casted as a sparse representation problem, which will be solved by orthogonal matching pursuit (OMP) algorithm. Experiments show that the pruned BER with only 20% of the initial subensembles has a better generalization compared to a complete BER.

Marine controlled source electromagnetic (CSEM) is an efficient method to explore ocean resources. The amplitudes of marine CSEM signals decay rapidly with the measuring offsets. The signal is easily contaminated by various kinds of noise when the offset is large. These noise include instrument internal noise, dipole vibration noise, seawater motion noise and environmental noise Suppressing noise is the key to improve data quality and interpretation accuracy. Sparse representation based denoising method has been used for denoising for a long time. provides a new way to remove noise. Under the framework of sparse representation, the denoising effect is closely related to the chosen transform matrix. This matrix is called dictionary and its column named atom. In general, the stronger the correlation between signal and dictionary is, the sparser representation will be, and further the better the denoising effect will be. In this article, a new method based on dictionary learning is proposed for marine CSEM denoising. Firstly, the signal segments suffering little from noise are captured to compose the training set. Then the learned dictionary is trained from the training set via K-singular value decomposition (K-SVD) algorithm. Finally, the learned dictionary is used to sparsely represent the contaminated signal and reconstruct the filtered one. The effectiveness of the proposed approach is verified by a synthetic data denoising experiment, in which windowed-Fourier-transform (WFT) and wavelet-transform (WT) denoising methods and three dictionaries (discrete-sine-transform (DST) dictionary, DST-wavelet merged dictionary and the learned dictionary) under a sparse representation framework are tested. The results demonstrate the superiority of the proposed dictionary-learning-based denoising method. Finally, the proposed approach is applied to field data denoising process, coupled with DST and DST-wavelet dictionaries based denoising methods. The outcomes further proves that the propsoed approach is effective and superior for marine CSEM data denoising.

Identification of intracardiac masses in echocardiograms is one important task in cardiac disease diagnosis. To improve diagnosis accuracy, a novel fully automatic classification method based on the sparse representation is proposed to distinguish intracardiac tumor and thrombi in echocardiography. First, a region of interest is cropped to define the mass area. Then, a unique globally denoising method is employed to remove the speckle and preserve the anatomical structure. Subsequently, the contour of the mass and its connected atrial wall are described by the K-singular value decomposition and a modified active contour model. Finally, the motion, the boundary as well as the texture features are processed by a sparse representation classifier to distinguish two masses. Ninety-seven clinical echocardiogram sequences are collected to assess the effectiveness. Compared with other state-of-the-art classifiers, our proposed method demonstrates the best performance by achieving an accuracy of 96.91%, a sensitivity of 100%, and a specificity of 93.02%. It explicates that our method is capable of classifying intracardiac tumors and thrombi in echocardiography, potentially to assist the cardiologists in the clinical practice.

In this paper, the classification of three Induction Motor conditions using the Orthogonal Matching Pursuit algorithm is presented. The OMP algorithm was implemented into a Field Programmable Gate Array to obtain the Sparse representation of the signal given a Dictionary. Then, the signal information obtained from the Sparse representation is evaluated and classified. The dictionaries were obtained by K-Singular Value Decomposition (K-SVD) algorithm developed in Matlab software. The FPGA implementation is low-complexity, cheap on hardware, compact, and works at 100MHz.

We applied and optimized the sparse representation (SR) approaches in the computer-aided diagnosis (CAD) to classify normal tissues and five kinds of diffuse lung disease (DLD) patterns: consolidation, ground-glass opacity, honeycombing, emphysema, and nodule. By using the K-SVD which is based on the singular value decomposition (SVD) and orthogonal matching pursuit (OMP), it can achieve a satisfied recognition rate, but too much time was spent in the experiment. To reduce the runtime of the method, the K-Means algorithm was substituted for the K-SVD, and the OMP was simplified by searching the desired atoms at one time (OMP1). We proposed three SR based methods for evaluation: SR1 (K-SVD+OMP), SR2 (K-Means+OMP), and SR3 (K-Means+OMP1). 1161 volumes of interest (VOIs) were used to optimize the parameters and train each method, and 1049 VOIs were adopted to evaluate the performances of the methods. The SR based methods were powerful to recognize the DLD patterns (SR1: 96.1%, SR2: 95.6%, SR3: 96.4%) and significantly better than the baseline methods. Furthermore, when the K-Means and OMP1 were applied, the runtime of the SR based methods can be reduced by 98.2% and 55.2%, respectively. Therefore, we thought that the method using the K-Means and OMP1 (SR3) was efficient for the CAD of the DLDs.

We extend the notion of sparse representation to the case where the atoms are not vectors, but cones, hence infinite sets. The sparse representation is linear, as usual, but the most convenient vector is chosen from each selected cone. We give a cone version of Orthogonal Matching Pursuit (OMP) and show that its complexity is only a few times larger than that of OMP. The new cone OMP can be used for anomaly detection; we apply it with very good results to the detection of abnormal heartbeats.

Iterative Nearest Neighbors

Human age, gender and ethnicity are valuable demographic information about a population. These measures are also considered important soft biometric traits for human recognition or search. Usually the three traits are studied separately. A recent study [9] shows that the three traits can be estimated simultaneously based on a multi-label regression formulation. The linear and kernel partial least squares (PLS) models are adopted to solve the multi-label regression problem in [9]. In this study, we investigate the canonical correlation analysis (CCA) based methods, including linear CCA, regularized CCA (rCCA), and kernel CCA (KCCA), and compare to the PLS models in solving the joint estimation problem. Interestingly, we found a consistent ranking of the five methods in estimating age, gender, and ethnicity. More importantly, we found that the CCA based methods can derive an extremely low dimensionality in estimating age, gender and ethnicity, which has not been shown in previous research, to the best of our knowledge. The experiments are conducted on a very large database of more than 55,000 face images.

Aiming at the problems of complex data processing and difficult identification caused by noise interference and other factors in the process of fault type identification of distribution network, this paper proposes a fault type identification method of distribution network based on sparse representation. The collection of fault data does not rely on the Shannon Theory. The collected time domain three-phase voltage(TPV) and zero-sequence voltage(ZSV) are divided into training sets and test sets. Learn the characteristic information of the fault voltage of the training set by the K-SVD dictionary learning algorithm, and construct an over-complete dictionary that accurately matches the essential characteristics of various types of faults. Based on learning dictionaries, the orthogonal matching pursuit (OMP) algorithm is used to perform adaptive dictionary sparse decomposition of the original time-domain fault data of the test set, and the fault signal is decomposed into the product of the overcomplete dictionary and the sparse vector. Combined with the classification method based on sparse Representation(SRC), the classification of the reconstructed fault signal is achieved. The proposed fault classification method does not need to construct fault signal features manually and avoids the tedious process of fault signal feature screening. It has strong adaptability and is not susceptible to transition resistance and noise. MATLAB/Simulink simulation verifies the effectiveness and accuracy of the proposed method.