Article
Automation & Control Systems
Chin Gi Soh, Ying Zhu
Summary: This paper proposes a sparse fused group lasso model for predicting the percentage purity of oil blends using Fourier-transform infrared spectroscopic data. The method improves the interpretability and prediction performance of the resultant models, while capturing group structure and coefficient structure smoothness.
CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Bo Jiang, Beibei Wang, Si Chen, Jin Tang, Bin Luo
Summary: This article proposes a Graph Sparse Neural Networks (GSNNs) model based on the theory of sparse representation, which conducts sparse aggregation to select reliable neighbors for message propagation. Furthermore, it introduces Exclusive Group Lasso GNNs (EGLassoGNNs) as a tight continuous relaxation model for optimizing GSNNs. Experimental results demonstrate the superior performance and robustness of the proposed EGLassoGNNs model.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Fatemeh Farokhmanesh, Mohammad Taghi Sadeghi
Summary: Deep learning, a significant subcategory of machine learning, aims to replace man-made features with automatically extracted features, facing the challenge of high dimensional feature space and potential overfitting. Sparse representation based methods, known for representing data with minimal non-zero coefficients, are attractive for regularization in deep neural networks. Experimental results show that combining methods like CRFS and SGL can lead to successful regularization in deep learning tasks.
NEURAL PROCESSING LETTERS
(2021)
Article
Chemistry, Multidisciplinary
Fangyun Bai, Kin Ming Puk, Jin Liu, Hongyu Zhou, Peng Tao, Wenyong Zhou, Shouyi Wang
Summary: In recent years, machine learning methods have been applied to various scientific and technological fields, including computational chemistry. In this study, a sparse group lasso method was used to develop a classification model for an allosteric protein in different functional states. The results show that the model achieved a significant improvement in accuracy while only selecting a small number of features. This study demonstrates the importance and necessity of rigorous feature selection and evaluation methods for complex chemical systems.
JOURNAL OF COMPUTATIONAL CHEMISTRY
(2022)
Article
Biology
Juntao Li, Ke Liang, Xuekun Song
Summary: This paper introduces a cancer diagnosis method LR-ASGL based on gene expression profile data, which addresses challenges in practical applications such as noise, gene grouping, and adaptive gene selection. Through experiments, the proposed method demonstrates significant advantages in prediction and gene selection.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Construction & Building Technology
Rongpeng Li, Fengdan Wang, Qingtian Deng, Yuzhu Xiao, Xinbo Li, Haiyang Li, Xueli Song
Summary: This paper proposes a novel joint sparse regularization model for structural damage identification, which utilizes the sparsity of the structural damage and the similarity information among different measurements to improve the identification performance.
ADVANCES IN STRUCTURAL ENGINEERING
(2022)
Article
Economics
Chenchen Ma, Yundong Tu
Summary: This paper reformulates the identification of multiple structural breaks in factor loadings as a problem of detecting structural breaks in a factor regression, where the estimated pseudo factor corresponding to the largest eigenvalue is regressed on the remaining estimated factors. A group fused Lasso based estimation procedure is proposed to identify the break dates, which is easy-to-implement and overcomes the drawbacks of existing methods. Theoretical properties of the proposed estimators are established, and simulations and a real data application demonstrate the practical merits of the procedure.
JOURNAL OF ECONOMETRICS
(2023)
Article
Computer Science, Artificial Intelligence
Jian Wang, Huaqing Zhang, Junze Wang, Yifei Pu, Nikhil R. Pal
Summary: This study presents a neural network-based feature selection scheme that controls the level of redundancy in selected features by integrating two penalties. Experimental results demonstrate the effectiveness of the proposed scheme in redundancy control.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Computer Science, Interdisciplinary Applications
Xiao Jiang, Lishan Qiao, Renato De Leone, Dinggang Shen
Summary: This paper proposes a novel method for jointly selecting nodes and edges from functional brain graphs (FBGs), which improves the classification performance and interpretation of the results.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2022)
Article
Computer Science, Artificial Intelligence
Wei Gao, Haizhong Yang
Summary: This study proposes a causality-based feature selection method by introducing time-varying Granger causal networks to capture the causal relationships in high-dimensional dynamic systems. It overcomes the limitations of sample scarcity and transforms the problem of learning Granger causal structures into a group variable selection problem. Experimental results demonstrate that the method is efficient in detecting changes and analyzing causal dependency structures in network evolution.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Bo Jiang, Beibei Wang, Bin Luo
Summary: In this paper, a novel Attribute selection guided Graph Neural Networks (AsGNNs) are proposed to extract meaningful features and eliminate noise for graph data representation. AsGNNs can be combined with any GNNs for feature selection in layer-wise propagation. Experimental results demonstrate the effectiveness of AsGNNs on semi-supervised learning tasks.
PATTERN RECOGNITION
(2023)
Article
Mathematics
Zhongzheng Wang, Guangming Deng, Jianqi Yu
Summary: The proposed group screening procedure based on the information gain ratio for a classification model is shown to have better screening performance and classification accuracy.
JOURNAL OF MATHEMATICS
(2022)
Article
Computer Science, Information Systems
Chenglong Zhang, Bingbing Jiang, Zidong Wang, Jie Yang, Yangfeng Lu, Xingyu Wu, Weiguo Sheng
Summary: In this paper, an efficient multi-view feature selection method (EMSFS) is proposed to address the issues in multi-view semi-supervised feature selection. EMSFS combines graph learning, label propagation, and multi-view feature selection within a unified framework. The method can adaptively learn a graph and exploit the similarity structure to enhance the reliability of the graph. It also achieves high computational efficiency.
INFORMATION SCIENCES
(2023)
Article
Computer Science, Artificial Intelligence
Zheng Wang, Yongjin Yuan, Rong Wang, Feiping Nie, Qinghua Huang, Xuelong Li
Summary: In this article, a new unsupervised feature selection method named PSDSL is proposed, which introduces a pseudo-label guided learning mechanism and combines the graph-based method with the idea of maximizing the scatter matrix to construct an objective function that improves the discrimination of selected features. The use of l(2,0) -norm constraint ensures row sparsity of the model and stability of the selected features.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Shixuan Zhou, Peng Song, Yanwei Yu, Wenming Zheng
Summary: Multi-view unsupervised feature selection (MUFS) is a popular research topic that aims to select a compact representative feature subset from multi-view data. However, most existing MUFS methods overlook the discriminative ability of multi-view data. This paper proposes a novel MUFS method called structural regularization based discriminative multi-view unsupervised feature selection (SDFS), which addresses these limitations and outperforms state-of-the-art MUFS models.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Lu Bai, Lixin Cui, Yuhang Jiao, Luca Rossi, Edwin R. Hancock
Summary: In this paper, a novel backtrackless aligned-spatial graph convolutional network (BASGCN) model is proposed for learning effective features for graph classification. This model addresses the issues of information loss and imprecise information representation in existing spatially-based graph convolutional network (GCN) models, and bridges the theoretical gap between traditional convolutional neural network (CNN) models and spatially-based GCN models. Experimental results demonstrate the effectiveness of the proposed model.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Computer Science, Artificial Intelligence
Xing Ai, Chengyu Sun, Zhihong Zhang, Edwin R. Hancock
Summary: The study proposes a novel GNN framework called TL-GNN, which combines subgraph-level information with node-level information to enrich the features captured by GNNs. The study also provides a mathematical analysis of the LPI problem and proposes a subgraph counting method based on the dynamic programming algorithm.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Artificial Intelligence
Chen Wang, Xiang Wang, Jiawei Zhang, Liang Zhang, Xiao Bai, Xin Ning, Jun Zhou, Edwin Hancock
Summary: This paper proposes a novel approach to estimate uncertainties in stereo matching end-to-end, using the NIG distribution to calculate uncertainties and additional loss functions to enhance sensitivity and smoothness. Experimental results show that this method improves stereo matching results, particularly performing well on out-of-distribution data.
PATTERN RECOGNITION
(2022)
Article
Computer Science, Artificial Intelligence
Lei Zhou, Yang Liu, Pengcheng Zhang, Xiao Bai, Lin Gu, Jun Zhou, Yazhou Yao, Tatsuya Harada, Jin Zheng, Edwin Hancock
Summary: Zero-shot learning aims to recognize novel classes by transferring semantic knowledge. The proposed bidirectional embedding based generative model introduces an information bottleneck constraint to preserve attribute information. Experimental results show that the method outperforms state-of-the-art methods on benchmark datasets.
Article
Computer Science, Artificial Intelligence
Zhihong Zhang, Dongdong Chen, Lu Bai, Jianjia Wang, Edwin R. Hancock
Summary: This article introduces the efficient representation of network structure using motifs and studies the distribution of subgraphs using statistical mechanics to understand the motif structure of a network. By mapping network motifs to clusters in a gas model, the partition function for a network is derived to calculate global thermodynamic quantities. Analytical expressions for the number of specific types of motifs and their associated entropy are presented. Numerical experiments on synthetic and real-world data sets evaluate the qualitative and quantitative characteristics of motif entropy derived from the partition function. The motif entropy for real-world networks, such as financial stock market networks, is found to be sensitive to the variance in network structure, indicating well-defined information-processing functions of network motifs.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Lu Bai, Lixin Cui, Zhihong Zhang, Lixiang Xu, Yue Wang, Edwin R. Hancock
Summary: This paper presents a novel framework for computing kernel-based similarity measures between dynamic time-varying financial networks, which is used to analyze financial time series. The commute time (CT) matrix is computed to identify a reliable set of correlated time series and their associated probability distributions. The dominant probability distributions are then used to construct a Shannon entropy time series, which is further used to develop an entropic dynamic time warping kernel for financial time series analysis. Experimental results demonstrate the effectiveness of the proposed method.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Dongdong Chen, Yuxing Dai, Lichi Zhang, Zhihong Zhang, Edwin R. Hancock
Summary: This paper presents a novel neural framework that converts the graph matching problem into a linear assignment problem in a high-dimensional space. By leveraging relative position information at the node level and high-order structural arrangement information at the subgraph level, the method improves the performance of graph matching tasks and establishes reliable node-to-node correspondences.
PATTERN RECOGNITION
(2023)
Article
Automation & Control Systems
Yuqing Ma, Xianglong Liu, Shihao Bai, Lei Wang, Aishan Liu, Dacheng Tao, Edwin R. Hancock
Summary: In this study, a generic inpainting framework is proposed to handle incomplete images with both contiguous and discontiguous large missing areas. By employing an adversarial modeling and regionwise operations, the framework is able to generate semantically reasonable and visually realistic images, outperforming existing methods on large contiguous and discontiguous missing areas, as demonstrated by qualitative and quantitative experiments.
IEEE TRANSACTIONS ON CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Lu Bai, Yuhang Jiao, Lixin Cui, Luca Rossi, Yue Wang, Philip S. Yu, Edwin R. Hancock
Summary: This paper proposes a new Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. Unlike state-of-the-art Graph Convolutional Neural Network (GCNN) models, the proposed QSGCNN model incorporates the process of identifying transitive aligned vertices between graphs and transforms arbitrary sized graphs into fixed-sized aligned vertex grid structures. The effectiveness of the proposed QSGCNN model is demonstrated through experiments on benchmark graph classification datasets.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Lixin Cui, Ming Li, Lu Bai, Yue Wang, Jing Li, Yanchao Wang, Zhao Li, Yunwen Chen, Edwin R. Hancock
Summary: This paper proposes a novel framework for computing Quantum-based Entropic Representations (QBER) for un-attributed graphs using Continuous-time Quantum Walk (CTQW). By transforming each original graph into a family of k-level neighborhood graphs, the framework captures multi-level topological information of the original global graph. The structure of each neighborhood graph is characterized using the Average Mixing Matrix (AMM) of CTQW, enabling the computation of Quantum Shannon Entropy and entropic signature. Experimental results demonstrate the effectiveness of the proposed approach in classification accuracies, outperforming other entropic complexity measuring methods, graph kernel methods, and graph deep learning methods.
PATTERN RECOGNITION
(2024)
Proceedings Paper
Computer Science, Artificial Intelligence
Jiawei Zhang, Xiang Wang, Xiao Bai, Chen Wang, Lei Huang, Yimin Chen, Lin Gu, Jun Zhou, Tatsuya Harada, Edwin R. Hancock
Summary: This paper proposes a method to improve the generalization capability of stereo matching networks in different domains by maintaining pixel-wise feature consistency through contrastive learning. The method constrains the consistency between learned features of matching pixel pairs and introduces whitening loss to preserve stereo feature consistency across domains. Experimental results show that the generalization of feature consistency between viewpoints in the same scene contributes to better stereo matching performance in unseen domains.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Lu Bai, Yuhang Jiao, Lixin Cui, Luca Rossi, Yue Wang, Philip S. Yu, Edwin R. Hancock
Summary: This paper proposes a novel Quantum Spatial Graph Convolutional Neural Network (QSGCNN) model that can directly learn a classification function for graphs of arbitrary sizes. The main idea is to define a new quantum-inspired spatial graph convolution associated with pre-transformed fixed-sized aligned grid structures of graphs, in terms of quantum information propagation between grid vertices of each graph. It effectively reduces the information loss or the notorious tottering problem arising in existing spatially-based Graph Convolutional Network (GCN) models.
2022 IEEE 38TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Silvia Tozza, Dizhong Zhu, William A. P. Smith, Ravi Ramamoorthi, Edwin R. Hancock
Summary: In this paper, we present a method for estimating shape from polarisation and shading information under unknown illumination conditions. We propose alternative photo-polarimetric constraints and demonstrate how to express them using a unified system of partial differential equations, which allows for linear least squares solutions. We also introduce new methods for estimating polarisation images, albedo, and refractive index, and evaluate their performance on both synthetic and real-world data, showing improvements over existing state-of-the-art methods.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Article
Geochemistry & Geophysics
W. A. P. Smith, P. Lewinska, M. A. Cooper, E. R. Hancock, J. A. Dowdeswell, D. M. Rippin
Summary: This paper studies the problem of structure-from-motion for images with varying principal point. Initialization and pose estimation methods specific to this scenario are proposed and the performance is demonstrated on challenging real-world examples.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Geography, Physical
Michael A. Cooper, Paulina Lewinska, William A. P. Smith, Edwin R. Hancock, Julian A. Dowdeswell, David M. Rippin
Summary: This study presents an approach to extract quantifiable information from archival aerial photographs to extend the record of change in central eastern Greenland Ice Sheet. The insights gained from a longer record of ice margin change are crucial for understanding glacier response to climate change. The study also focuses on relatively small and understudied outlet glaciers from the eastern margin of the ice sheet, revealing significant heterogeneity in their response with non-climatic controls playing a key role.
Article
Computer Science, Artificial Intelligence
Guang-Hai Liu, Zuo-Yong Li, Jing-Yu Yang, David Zhang
Summary: This article introduces a novel image retrieval method that improves retrieval performance by using sublimated deep features. The method incorporates orientation-selective features and color perceptual features, effectively mimicking these mechanisms to provide a more discriminating representation.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Fengguang Peng, Zihan Ding, Ziming Chen, Gang Wang, Tianrui Hui, Si Liu, Hang Shi
Summary: RGB-Thermal (RGB-T) semantic segmentation is an emerging task that aims to improve the robustness of segmentation methods under extreme imaging conditions by using thermal infrared modality. The challenges of foreground-background distinguishment and complementary information mining are addressed by proposing a cross modulation process with two collaborative components. Experimental results show that the proposed method achieves state-of-the-art performances on current RGB-T segmentation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Baihong Han, Xiaoyan Jiang, Zhijun Fang, Hamido Fujita, Yongbin Gao
Summary: This paper proposes a novel automatic prompt generation method called F-SCP, which focuses on generating accurate prompts for low-accuracy classes and similar classes. Experimental results show that our approach outperforms state-of-the-art methods on six multi-domain datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Huikai Liu, Ao Zhang, Wenqian Zhu, Bin Fu, Bingjian Ding, Shengwu Xiong
Summary: Adverse weather conditions present challenges for computer vision tasks, and image de-weathering is an important component of image restoration. This paper proposes a multi-patch skip-forward structure and a Residual Deformable Convolutional module to improve feature extraction and pixel-wise reconstruction.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Oliver M. Crook, Mihai Cucuringu, Tim Hurst, Carola-Bibiane Schonlieb, Matthew Thorpe, Konstantinos C. Zygalakis
Summary: The transportation LP distance (TLP) is a generalization of the Wasserstein WP distance that can be applied directly to color or multi-channelled images, as well as multivariate time-series. TLP interprets signals as functions, while WP interprets signals as measures. Although both distances are powerful tools in modeling data with spatial or temporal perturbations, their computational cost can be prohibitively high for moderate pattern recognition tasks. The linear Wasserstein distance offers a method for projecting signals into a Euclidean space, and in this study, we propose linear versions of the TLP distance (LTLP) that show significant improvement over the linear WP distance in signal processing tasks while being several orders of magnitude faster to compute than the TLP distance.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Haitao Tian, Shiru Qu, Pierre Payeur
Summary: This paper proposes a method of target-dependent classifier, which optimizes the joint hypothesis of domain adaptation into a target-dependent hypothesis that better fits with the target domain clusters through an unsupervised fine-tuning strategy and the concept of meta-learning. Experimental results demonstrate that this method outperforms existing techniques in synthetic-to-real adaptation and cross-city adaptation benchmarks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Qingsen Yan, Axi Niu, Chaoqun Wang, Wei Dong, Marcin Wozniak, Yanning Zhang
Summary: Deep learning-based methods have achieved remarkable results in the field of super-resolution. However, the limitation of paired training image sets has led researchers to explore self-supervised learning. However, the assumption of inaccurate downscaling kernel functions often leads to degraded results. To address this issue, this paper introduces KGSR, a kernel-guided network that trains both upscaling and downscaling networks to generate high-quality high-resolution images even without knowing the actual downscaling process.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Yifan Chen, Xuelong Li
Summary: Gait recognition is a popular technology for identification due to its ability to capture gait features over long distances without cooperation. However, current methods face challenges as they use a single network to extract both temporal and spatial features. To solve this problem, we propose a two-branch network that focuses on spatial and temporal feature extraction separately. By combining these features, we can effectively learn the spatio-temporal information of gait sequences.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Wei Shi, Wentao Zhang, Wei-shi Zheng, Ruixuan Wang
Summary: This article proposes a simple yet effective visualization framework called PAMI, which does not require detailed model structure and parameters to obtain visualization results. It can be applied to various prediction tasks with different model backbones and input formats.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Xiaobo Hu, Jianbo Su, Jun Zhang
Summary: This paper reviews the latest technologies in pattern recognition, highlighting their instabilities and failures in practical applications. From a control perspective, the significance of disturbance rejection in pattern recognition is discussed, and the existing problems are summarized. Finally, potential solutions related to the application of compensation on features are discussed to emphasize future research directions.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Andres Felipe Posada-Moreno, Nikita Surya, Sebastian Trimpe
Summary: Convolutional neural networks are widely used in critical systems, and explainable artificial intelligence has proposed methods for generating high-level explanations. However, these methods lack the ability to determine the location of concepts. To address this, we propose a novel method for automatic concept extraction and localization based on pixel-wise aggregations, and validate it using synthetic datasets.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Peng Bao, Jianian Li, Rong Yan, Zhongyi Liu
Summary: In this paper, a novel Dynamic Graph Contrastive Learning framework, DyGCL, is proposed to capture the temporal consistency in dynamic graphs and achieve good performance in node representation learning.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Kristian Schultz, Saptarshi Bej, Waldemar Hahn, Markus Wolfien, Prashant Srivastava, Olaf Wolkenhauer
Summary: Research indicates that deep generative models perform poorly compared to linear interpolation-based methods for synthetic data generation on small, imbalanced tabular datasets. To address this, a new approach called ConvGeN, combining convex space learning with deep generative models, has been proposed. ConvGeN improves imbalanced classification on small datasets while remaining competitive with existing linear interpolation methods.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Khondaker Tasrif Noor, Antonio Robles-Kelly
Summary: In this paper, the authors propose H-CapsNet, a capsule network designed for hierarchical image classification. The network effectively captures hierarchical relationships using dedicated capsules for each class hierarchy. A modified hinge loss is utilized to enforce consistency among the involved hierarchies. Additionally, a strategy for dynamically adjusting training parameters is presented to achieve better balance between the class hierarchies. Experimental results demonstrate that H-CapsNet outperforms competing hierarchical classification networks.
PATTERN RECOGNITION
(2024)
Article
Computer Science, Artificial Intelligence
Lei Liu, Guorun Li, Yuefeng Du, Xiaoyu Li, Xiuheng Wu, Zhi Qiao, Tianyi Wang
Summary: This study proposes a new agricultural image segmentation model called CS-Net, which uses Simple-Attention Block and Simpleformer to improve accuracy and inference speed, and addresses the issue of performance collapse of Transformers in agricultural image processing.
PATTERN RECOGNITION
(2024)