Search Results (25)

High-dimensional feature selection aims to identify compact and discriminative feature subsets from large feature spaces. In multi-objective feature selection (MOFS), this task remains challenging because the search space grows exponentially with dimensionality, and conventional binary evolutionary operators may generate ineffective perturbations in sparse high-dimensional spaces. To address these issues, this paper proposes CORAL, a rank-memory search framework for MOFS. CORAL uses a joint continuous score–cardinality representation to model feature priorities and subset sizes and applies Top-K decoding to obtain binary feature subsets. A rank-memory mechanism is introduced to extract feature occurrence information from elite solutions and guide score-space variation. In addition, elite local refinement and feature-number-stratified environmental selection are used to refine candidate subsets and maintain solutions across different sparsity regions. Experiments on 18 benchmark classification datasets show that CORAL achieves balanced performance in terms of solution-set quality, test classification performance, feature compactness, and computational efficiency. Ablation results further demonstrate the complementary roles of rank memory, elite local refinement, and stratified environmental selection. Full article

Applications in enclosed spaces such as vehicle cabin on-site detection, human–pet separation, and pet care have put forward higher requirements for non-contact target recognition. Millimeter-wave radar point clouds have advantages such as privacy friendliness and robustness against low light and occlusion. However, their point clouds are generally sparse, with obvious noise and multipath interference. Moreover, the fluctuation of point numbers over time makes alignment and feature learning difficult, which leads to performance degradation of existing point cloud classification methods in complex environments. To this end, this paper proposes a spatiotemporal joint classification framework for millimeter-wave point cloud sequences: An effective point mask mechanism is introduced in the spatial dimension to suppress the interference of invalid points generated by alignment on the neighborhood composition and feature aggregation and improve the reliability of local geometric representation; and to integrate attention-based time series modeling in the time dimension and enhance category separability by using cross-frame dynamic patterns. The experimental results show that the proposed method can achieve an accuracy rate of 97.8% in the three-classification tasks of Child, Cat and Dog and the ablation analysis verifies the key contributions of the mask mechanism and time series modeling to robust recognition. This framework provides a deployable and more generalized millimeter-wave point cloud solution for the identification of life forms in confined spaces. Full article

Early identification of acute gout is crucial, enabling healthcare professionals to implement targeted interventions for rapid pain relief and preventing disease progression, ensuring improved long-term joint function. In this study, we comprehensively explored the potential early detection of gout flares (GFs) based on nurses’ chief complaint notes in the Emergency Department (ED). Addressing the challenge of identifying GFs prospectively during an ED visit, where documentation is typically minimal, our research focused on employing alternative Natural Language Processing (NLP) techniques to enhance detection accuracy. We investigated GF detection algorithms using both sparse representations by traditional NLP methods and dense encodings by medical domain-specific Large Language Models (LLMs), distinguishing between generative and discriminative models. Three methods were used to alleviate the issue of severe data imbalances, including oversampling, class weights, and focal loss. Extensive empirical studies were performed on the Gout Emergency Department Chief Complaint Corpora. Sparse text representations like tf-idf proved to produce strong performances, achieving F1 scores higher than 0.75. The best deep learning models were RoBERTa-large-PM-M3-Voc and BioGPT, which had the best F1 scores for each dataset, with a 0.8 on the 2019 dataset and a 0.85 F1 score on the 2020 dataset, respectively. We concluded that although discriminative LLMs performed better for this classification task when compared to generative LLMs, a combination of using generative models as feature extractors and employing a support vector machine for classification yielded promising results comparable to those obtained with discriminative models. Full article

Among the numerous techniques followed to learn a linear classifier through the discriminative dictionary and sparse representations learning of signals, the techniques to learn a nonparametric Bayesian classifier jointly and discriminately with the dictionary and the corresponding sparse representations have drawn considerable attention from researchers. These techniques jointly learn two sets of sparse representations, one for the training samples over the dictionary and the other for the corresponding labels over the dictionary classifier. At the prediction stage, the representations of the test samples computed over the learned dictionary do not truly represent the corresponding labels, exposing weakness in the joint learning claim of these techniques. We mitigate this problem and strengthen the joint by learning a set of weights over the dictionary to represent the training data and further optimizing the same weights over the dictionary classifier to represent the labels of the corresponding classes of the training data. Now, at the prediction stage, the representation weights of the test samples computed over the learned dictionary also represent the labels of the corresponding classes of the test samples, resulting in the accurate reconstruction of the labels of the classes by the learned dictionary classifier. Overall, a reduction in the size of the Bayesian model’s parameters also improves training time. We analytically and nonparametrically derived the posterior conditional probabilities of the model from the overall joint probability of the model using Bayes’ theorem. We used the Gibbs sampler to solve the joint probability of the model using the derived conditional probabilities, which also supports our claim of efficient optimization of the coupled/joint dictionaries and the sparse representation parameters. We demonstrated the effectiveness of our approach through experiments on the standard datasets, i.e., the Extended YaleB and AR face databases for face recognition, Caltech-101 and Fifteen Scene Category databases for categorization, and UCF sports action database for action recognition. We compared the results with the state-of-the-art methods in the area. The classification accuracies, i.e., 93.25%, 89.27%, 94.81%, 98.10%, and 95.00%, of our approach on the datasets have increases of 0.5 to 2% on average. The overall average error margin of the confidence intervals in our approach is 0.24 compared with the second-best approach, JBDC, for which it is 0.34. The AUC–ROC scores of our approach are 0.98 and 0.992, which are better than those of others, i.e., 0.960 and 0.98, respectively. Our approach is also computationally efficient. Full article

Intelligent on-site fault diagnosis and professional vibration analysis are essential for the safety and stability of rotating machinery operation. This paper represents a fault diagnosis scheme based on two-stage compressed sensing for triaxial vibration data, which realizes fault diagnosis for rotating machinery based on compressed data and data reconstruction for professional vibration analysis. In the 1st stage, the triaxial vibration signals are compressed using a pre-designed hybrid measurement matrix; these compressed data can be used both for time-frequency transform and for vibration data reconstruction. In the 2nd stage, the frequency spectra of the triaxial vibration signals are fused and further compressed using another pre-designed joint measurement matrix, which inhibits the high-frequency noises simultaneously. Finally, the fused spectra are employed as feature vectors in sparse-representation-based classification, where the proposed batch matching pursuit (BMP) algorithm is utilized to calculate the sparse vectors. The two-stage compression scheme and the BMP algorithm minimize the computational cost of on-site fault diagnosis, which is suitable for edge computing platforms. Meanwhile, the compressed vibration data can be reconstructed, which provides evidence for professional vibration analysis. The method proposed in this study is validated by two practical case studies, in which the accuracies are 99.73% and 96.70%, respectively. Full article

Hyperspectral image (HSI) classification is one of the hot research topics in the field of remote sensing. The performance of HSI classification greatly depends on the effectiveness of feature learning or feature design. Traditional vector-based spectral–spatial features have shown good performance in HSI classification. However, when the number of labeled samples is limited, the performance of these vector-based features is degraded. To fully mine the discriminative features in small-sample case, a novel local matrix feature (LMF) was designed to reflect both the correlation between spectral pixels and the spectral bands in a local spatial neighborhood. In particular, the LMF is a linear combination of a local covariance matrix feature and a local correntropy matrix feature, where the former describes the correlation between spectral pixels and the latter measures the similarity between spectral bands. Based on the constructed LMFs, a simple Log-Euclidean distance-based linear kernel is introduced to measure the similarity between them, and an LMF-based kernel joint sparse representation (LMFKJSR) model is proposed for HSI classification. Due to the superior performance of region covariance and correntropy descriptors, the proposed LMFKJSR shows better results than existing vector-feature-based and matrix-feature-based support vector machine (SVM) and JSR methods on three well-known HSI data sets in the case of limited labeled samples. Full article

Joint sparse representation classification (JSRC) is a representative spectral–spatial classifier for hyperspectral images (HSIs). However, the JSRC is inappropriate for highly heterogeneous areas due to the spatial information being extracted from a fixed-sized neighborhood block, which is often unable to conform to the naturally irregular structure of land cover. To address this problem, a superpixel-based JSRC with nonlocal weighting, i.e., superpixel-based nonlocal weighted JSRC (SNLW-JSRC), is proposed in this paper. In SNLW-JSRC, the superpixel representation of an HSI is first constructed based on an entropy rate segmentation method. This strategy forms homogeneous neighborhoods with naturally irregular structures and alleviates the inclusion of pixels from different classes in the process of spatial information extraction. Afterwards, the superpixel-based nonlocal weighting (SNLW) scheme is built to weigh the superpixel based on its structural and spectral information. In this way, the weight of one specific neighboring pixel is determined by the local structural similarity between the neighboring pixel and the central test pixel. Then, the obtained local weights are used to generate the weighted mean data for each superpixel. Finally, JSRC is used to produce the superpixel-level classification. This speeds up the sparse representation and makes the spatial content more centralized and compact. To verify the proposed SNLW-JSRC method, we conducted experiments on four benchmark hyperspectral datasets, namely Indian Pines, Pavia University, Salinas, and DFC2013. The experimental results suggest that the SNLW-JSRC can achieve better classification results than the other four SRC-based algorithms and the classical support vector machine algorithm. Moreover, the SNLW-JSRC can also outperform the other SRC-based algorithms, even with a small number of training samples. Full article

This paper proposes a novel robust latent common subspace learning (RLCSL) method by integrating low-rank and sparse constraints into a joint learning framework. Specifically, we transform the data from source and target domains into a latent common subspace to perform the data reconstruction, i.e., the transformed source data is used to reconstruct the transformed target data. We impose joint low-rank and sparse constraints on the reconstruction coefficient matrix which can achieve following objectives: (1) the data from different domains can be interlaced by using the low-rank constraint; (2) the data from different domains but with the same label can be aligned together by using the sparse constraint. In this way, the new feature representation in the latent common subspace is discriminative and transferable. To learn a suitable classifier, we also integrate the classifier learning and feature representation learning into a unified objective and thus the high-level semantics label (data label) is fully used to guide the learning process of these two tasks. Experiments are conducted on diverse data sets for image, object, and document classifications, and encouraging experimental results show that the proposed method outperforms some state-of-the-arts methods. Full article

Automatic dating tools for historical documents can greatly assist paleographers and save them time and effort. This paper describes a novel method for estimating the date of historical Arabic documents that employs hierarchical fusions of multiple features. A set of traditional features and features extracted by a residual network (ResNet) are fused in a hierarchical approach using joint sparse representation. To address noise during the fusion process, a new approach based on subsets of multiple features is being considered. Following that, supervised and unsupervised classifiers are used for classification. We show that using hierarchical fusion based on subsets of multiple features in the KERTAS dataset can produce promising results and significantly improve the results. Full article

The representation-based algorithm has raised a great interest in hyperspectral image (HSI) classification. $l_1$-minimization-based sparse representation (SR) attempts to select a few atoms and cannot fully reflect within-class information, while $l_2$-minimization-based collaborative representation (CR) tries to use all of the atoms leading to mixed-class information. Considering the above problems, we propose the pairwise elastic net representation-based classification (PENRC) method. PENRC combines the $l_1$-norm and $l_2$-norm penalties and introduces a new penalty term, including a similar matrix between dictionary atoms. This similar matrix enables the automatic grouping selection of highly correlated data to estimate more robust weight coefficients for better classification performance. To reduce computation cost and further improve classification accuracy, we use part of the atoms as a local adaptive dictionary rather than the entire training atoms. Furthermore, we consider the neighbor information of each pixel and propose a joint pairwise elastic net representation-based classification (J-PENRC) method. Experimental results on chosen hyperspectral data sets confirm that our proposed algorithms outperform the other state-of-the-art algorithms. Full article

The original Hyperspectral image (HSI) has different degrees of Hughes phenomenon and mixed noise, leading to the decline of classification accuracy. To make full use of the spatial-spectral joint information of HSI and improve the classification accuracy, a novel dual feature extraction framework joint transform domain-spatial domain filtering based on multi-scale-superpixel-dimensionality reduction (LRS-HRFMSuperPCA) is proposed. Our framework uses the low-rank structure and sparse representation of HSI to repair the unobserved part of the original HSI caused by noise and then denoises it through a block-matching 3D algorithm. Next, the dimension of the reconstructed HSI is reduced by principal component analysis (PCA), and the dimensions of the reduced images are segmented by multi-scale entropy rate superpixels. All the principal component images with superpixels are projected into the reconstructed HSI in parallel. Secondly, PCA is once again used to reduce the dimension of all HSIs with superpixels in scale with hyperpixels. Moreover, hierarchical domain transform recursive filtering is utilized to obtain the feature images; ultimately, the decision fusion strategy based on a support vector machine (SVM) is used for classification. According to the Overall Accuracy (OA), Average Accuracy (AA) and Kappa coefficient on the three datasets (Indian Pines, University of Pavia and Salinas), the experimental results have shown that our proposed method outperforms other state-of-the-art methods. The conclusion is that LRS-HRFMSuperPCA can denoise and reconstruct the original HSI and then extract the space-spectrum joint information fully. Full article

Sparse representation classification (SRC) is being widely applied to target detection in hyperspectral images (HSI). However, due to the problem in HSI that high-dimensional data contain redundant information, SRC methods may fail to achieve high classification performance, even with a large number of spectral bands. Selecting a subset of predictive features in a high-dimensional space is an important and challenging problem for hyperspectral image classification. In this paper, we propose a novel discriminant feature learning (DFL) method, which combines spectral and spatial information into a hypergraph Laplacian. First, a subset of discriminative features is selected, which preserve the spectral structure of data and the inter- and intra-class constraints on labeled training samples. A feature evaluator is obtained by semi-supervised learning with the hypergraph Laplacian. Secondly, the selected features are mapped into a further lower-dimensional eigenspace through a generalized eigendecomposition of the Laplacian matrix. The finally extracted discriminative features are used in a joint sparsity-model algorithm. Experiments conducted with benchmark data sets and different experimental settings show that our proposed method increases classification accuracy and outperforms the state-of-the-art HSI classification methods. Full article

By means of joint sparse representation (JSR) and kernel representation, kernel joint sparse representation (KJSR) models can effectively model the intrinsic nonlinear relations of hyperspectral data and better exploit spatial neighborhood structure to improve the classification performance of hyperspectral images. However, due to the presence of noisy or inhomogeneous pixels around the central testing pixel in the spatial domain, the performance of KJSR is greatly affected. Motivated by the idea of self-paced learning (SPL), this paper proposes a self-paced KJSR (SPKJSR) model to adaptively learn weights and sparse coefficient vectors for different neighboring pixels in the kernel-based feature space. SPL strateges can learn a weight to indicate the difficulty of feature pixels within a spatial neighborhood. By assigning small weights for unimportant or complex pixels, the negative effect of inhomogeneous or noisy neighboring pixels can be suppressed. Hence, SPKJSR is usually much more robust. Experimental results on Indian Pines and Salinas hyperspectral data sets demonstrate that SPKJSR is much more effective than traditional JSR and KJSR models. Full article

Joint sparse representation has been widely used for hyperspectral image classification in recent years, however, the equal weight assigned to each neighbouring pixel is less realistic, especially for the edge areas, and one fixed scale is not appropriate for the entire image extent. To overcome these problems, we propose an adaptive local neighbour selection strategy suitable for hyperspectral image classification. We also introduce a multi-level joint sparse model based on the proposed adaptive local neighbour selection strategy. This method can generate multiple joint sparse matrices on different levels based on the selected parameters, and the multi-level joint sparse optimization can be performed efficiently by a simultaneous orthogonal matching pursuit algorithm. Tests on three benchmark datasets show that the proposed method is superior to the conventional sparsity representation methods and the popular support vector machines. Full article

The monogenic signal, which is defined as a linear combination of a signal and its Riesz-transformed one, provides a great opportunity for synthetic aperture radar (SAR) image recognition. However, the incredibly large number of components at different scales may result in too much of a burden for onboard computation. There is great information redundancy in monogenic signals because components at some scales are less discriminative or even have negative impact on classification. In addition, the heterogeneity of the three types of components will lower the quality of decision-making. To solve the problems above, a scale selection method, based on a weighted multi-task joint sparse representation, is proposed. A scale selection model is designed and the Fisher score is presented to measure the discriminative ability of components at each scale. The components with high Fisher scores are concatenated to three component-specific features, and an overcomplete dictionary is built. Meanwhile, the scale selection model produces the weight vector. The three component-specific features are then fed into a multi-task joint sparse representation classification framework. The final decision is made in terms of accumulated weighted reconstruction error. Experiments on the Moving and Stationary Target Acquisition and Recognition (MSTAR) dataset have proved the effectiveness and superiority of our method. Full article