Article
Computer Science, Artificial Intelligence
Shili Peng, Wenwu Wang, Yinli Chen, Xueling Zhong, Qinghua Hu
Summary: This article presents a new idea for addressing the challenge of unifying classification and regression in machine learning. It proposes converting the classification problem into a regression problem and using regression methods to solve key problems in classification. Experimental results demonstrate that the proposed method outperforms existing algorithms in terms of prediction accuracy and model uncertainty.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Wenwen Qiang, Hongjie Zhang, Jingxing Zhang, Ling Jing
Summary: The paper introduces a novel twin support vector machine, TSVM-M-3, for multi-class classification and a new RKT for large-scale classification. TSVM-M-3 considers the first and second-order moments of positive points loss and introduces an adjusting factor when constructing decision hyperplanes; RKT uses a density-dependent data selection method to reduce modeling error.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Liuyuan Chen, Kanglei Zhou, Junchang Jing, Haiju Fan, Juntao Li
Summary: This work proposes a fast regularization parameter tuning algorithm for the twin multi-class support vector machine. By adopting a novel sample data set partition strategy and utilizing linear equations and block matrix theory, the regularization parameters are continuously updated, and the relationship between the Lagrangian multipliers and the regularization parameters is proven. Finally, different events are defined to seek for the starting event for the next iteration, and the effectiveness of the proposed method is validated through experiments.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Ting Wang, Yitian Xu, Xuhua Liu
Summary: This paper proposes a multi-task twin spheres support vector machine with maximum margin (MTMMTSVM) for imbalanced data classification. It constructs two homocentric hyper-spheres for each task and explores the commonality and individuality of each task. Compared with the latest multi-task algorithms, MTMMTSVM achieves superior performance on imbalanced datasets and has a shorter training time.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Yinan Guo, Zirui Zhang, Fengzhen Tang
Summary: Feature selection is important in machine learning to reduce complexity and simplify interpretation. A novel non-linear method proposed in this paper uses kernelized multi-class support vector machines and fast recursive feature elimination to select features that work well for all classes, resulting in lower computational time complexity.
PATTERN RECOGNITION
(2021)
Article
Computer Science, Information Systems
Jinseong Park, Yujin Choi, Junyoung Byun, Jaewook Lee, Saerom Park
Summary: In this paper, a multi-class classification method using kernel supports and a dynamical system under differential privacy is proposed. For small datasets, kernel methods, such as kernel support vector machines (SVMs), show good generalization performance with high-dimensional feature mapping. However, kernel SVMs have a fundamental weakness in achieving differential privacy because they construct decision functions based on a subset of the training data called support vectors. To address these limitations, a two-phase classification algorithm based on support vector data description (SVDD) is developed. It generates a differentially private SVDD (DP-SVDD) by perturbing the sphere center in a high-dimensional feature space and partitions the input space using a dynamical system for classification.
INFORMATION SCIENCES
(2023)
Article
Mathematics
Jianli Shao, Xin Liu, Wenqing He
Summary: The article introduces the use of data-adaptive SVM for instance classification in multi-class classification problems and proposes a multi-class data-dependent kernel function to enhance classification accuracy. Through simulation studies and real dataset, the excellent performance of the method is demonstrated, especially in detecting rare class instances.
Article
Computer Science, Information Systems
Jie Sun, Hamido Fujita, Yujiao Zheng, Wenguo Ai
Summary: This paper focuses on multiclass financial distress prediction using SVM and decomposition fusion methods, showing that OVO-SVM outperforms OVR-SVM and ECOC-SVM in overall performance and is preferred. Data preprocessing mechanisms can greatly enhance the model performance, while OVO-SVM is more competitive for predicting financial pseudosoundness and moderate financial distress compared to human expertise.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Yinglong Ma, Xiaofeng Liu, Lijiao Zhao, Yue Liang, Peng Zhang, Beihong Jin
Summary: This paper introduces a hierarchical multi-label text classification method based on hybrid embedding, combining graph embedding and word embedding; using a level-by-level HMTC approach and conducting extensive experiments on five large-scale real-world datasets, the results show that the method is competitive in classification accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Information Systems
Shuangxi Wang, Hongwei Ge, Jinlong Yang, Yubing Tong
Summary: The paper proposed the relaxed group low-rank regression model to address the adverse effects of noise, effectively capturing hidden structural information of samples. By utilizing group low-rank constraint and graph embedding constraint, the model showed more tolerance to noise and outliers, ensuring the original samples were converted into a more compact and discriminative characteristic space.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Zhongfeng Qin, Qiqi Li
Summary: Support vector machines have been widely used in binary classification, but they struggle with handling imprecise observations in practical applications. This paper proposes a hard margin uncertain support vector machine that uses uncertain variables to describe imprecise observations. The model defines the distance between an uncertain vector and a hyperplane and introduces the concept of a linearly alpha-separable data set. Through maximum margin criterion, the model can classify new observations using the optimal hyperplane derived from the model. A numerical example is provided to illustrate the uncertain support vector machine.
FUZZY OPTIMIZATION AND DECISION MAKING
(2023)
Article
Computer Science, Artificial Intelligence
Chandan Gautam, Aruna Tiwari, Pratik K. Mishra, Sundaram Suresh, Alexandros Iosifidis, M. Tanveer
Summary: This paper introduces a hierarchical OCC architecture using multiple graph-embedded KRR-based autoencoders to project input features into a new feature space and apply a regression-based one-class classifier. Experimental results on 21 balanced and 20 imbalanced datasets confirm the effectiveness of the proposed method over existing kernel-based classifiers.
COGNITIVE COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Zheming Gao, Shu-Cherng Fang, Xuerui Gao, Jian Luo, Negash Medhin
Summary: This paper proposes a kernel-free least squares twin support vector machine model for multi-class classification, which utilizes a special fourth order polynomial surface and one-versus-all classification strategy, with l(2) regularization to accommodate various levels of nonlinearity in datasets. Theoretical analysis and computational results demonstrate the superior performance of the proposed model, particularly for imbalanced datasets.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Hongmei Ju, Huan Yi
Summary: The paper introduces the importance of Least Squares Support Vector Machine (LSSVM) in solving classification problems, and proposes an improved fuzzy sparse multi-class LSSVM (IF-S-M-LSSVM) for multi-class classification problems. By using a non-iterative sparse algorithm and adding a fuzzy membership degree, the new model shows advantages in terms of training speed and classification accuracy.
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Ran An, Yitian Xu, Xuhua Liu
Summary: TSVM is suitable for STL problems, while MTL explores shared information between multiple tasks for better classification. The proposed rough MT-v-TSVM assigns different penalties to misclassified samples based on their positions, combining the advantages of rough v-TSVM and preserving the individuality of tasks.
APPLIED SOFT COMPUTING
(2021)
Article
Engineering, Biomedical
Muhammad Uzair Zahid, Serkan Kiranyaz, Moncef Gabbouj
Summary: This study proposes a novel approach for inter-patient ECG classification using a compact 1D Self-ONN by exploiting morphological and timing information in heart cycles. The proposed method achieves the highest classification performance ever achieved, surpassing state-of-the-art deep models with minimal computational complexity. The results demonstrate that a compact and superior network model can achieve global ECG classification even without patient-specific information.
IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING
(2023)
Article
Engineering, Electrical & Electronic
Feng Zhang, Xiaoyue Jiang, Zhaoqiang Xia, Moncef Gabbouj, Jinye Peng, Xiaoyi Feng
Summary: This paper proposes a single image-based intrinsic image decomposition method using encoder-decoder structures, which explores different component-oriented feature constraints and feature selection processes. The non-local color compensation network (NCCNet) is introduced to address the computational issue between hue and value channels, and a non-local attention scheme is proposed to describe the relations of non-adjacent regions. The mutual constraint between albedo and shading is also explored, and a unified mutual exclusion loss function is proposed for training.
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Mete Ahishali, Mehmet Yamac, Serkan Kiranyaz, Moncef Gabbouj
Summary: In this study, a representation-based regression method is proposed to predict distances between detected objects in an observed scene. By improving the CSEN model and introducing compressive learning, the proxy mapping stage and convolutional layers are jointly optimized. Experimental results demonstrate the significant performance improvement of the proposed method in distance estimation.
Article
Computer Science, Artificial Intelligence
Fahad Sohrab, Alexandros Iosifidis, Moncef Gabbouj, Jenni Raitoharju
Summary: In this paper, a novel subspace learning framework for one-class classification is proposed, which presents the problem in the form of graph embedding. The framework includes the previously proposed subspace one-class techniques as special cases and provides further insight on optimization goals. It allows for the incorporation of other meaningful optimization goals and offers alternative solutions to the previously used gradient-based technique. Experimental results demonstrate improved performance compared to baselines and recently proposed methods.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Mehmet Yamac, Mete Ahishali, Serkan Kiranyaz, Moncef Gabbouj
Summary: This study proposes a novel approach for support estimation of a sparse signal by learning to map non-zero locations from denser measurements. The proposed convolutional sparse support estimator networks (CSENs) are designed to achieve state-of-the-art performance levels with reduced computational complexity.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Ilyes Mrad, Ridha Hamila, Aiman Erbad, Moncef Gabbouj
Summary: In the past decade, the usage of machine learning techniques has significantly increased in various applications. Federated Learning (FL) is a collaborative technique that addresses important issues such as data privacy, energy consumption, and limited availability of clean spectral slots. This work investigates the performance of FL updates with edge devices connected to a leading device (LD) using a non-orthogonal multiple access (NOMA) uplink scheme, and analyzes its effect on convergence round and accuracy of the FL model.
PERVASIVE AND MOBILE COMPUTING
(2023)
Article
Computer Science, Information Systems
Muhammad Asif Khan, Ridha Hamila, Aiman Erbad, Moncef Gabbouj
Summary: This article introduces a method for distributed inference over IoT devices and edge server, reducing computational load and energy consumption by employing early split strategy and late split strategy.
IEEE SYSTEMS JOURNAL
(2023)
Article
Multidisciplinary Sciences
Emmi Antikainen, Joonas Linnosmaa, Adil Umer, Niku Oksala, Markku Eskola, Mark van Gils, Jussi Hernesniemi, Moncef Gabbouj
Summary: This study utilized deep learning techniques to predict increased risk of death in cardiovascular disease patients using electronic health records. The results showed that the XLNet model outperformed the BERT model in predicting mortality, capturing more positive cases.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Artificial Intelligence
Moncef Gabbouj, Serkan Kiranyaz, Junaid Malik, Muhammad Uzair Zahid, Turker Ince, Muhammad E. H. Chowdhury, Amith Khandakar, Anas Tahir
Summary: In this study, a 1-D Self-Organized ONNs (Self-ONNs) network with generative neurons is proposed to improve peak detection performance and computational efficiency. Compared to traditional methods, this approach achieves better performance in handling low-quality and noisy signals, with lower computational complexity.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Ardavan Elahi, Ali Falahati, Farhad Pakdaman, Mehdi Modarressi, Moncef Gabbouj
Summary: With the rise of technologies like smart cities, Internet of things (IoT), and 5G, there has been a significant increase in visual data at the edges and remote nodes. Traditional video compression solutions optimized for human vision are not efficient for machine vision tasks, so this paper presents a methodology to optimize the existing video compression standard, HEVC, for object detection tasks. By collecting a dataset of compressed videos with different compression ratios and corresponding object detection performance, a trade-off point between bitrate and object detection performance is defined. The resulting model can predict this trade-off point accurately, resulting in significant bitrate reduction compared to high-quality video for object detection.
2023 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS, ISCAS
(2023)
Article
Engineering, Electrical & Electronic
Li Yu, Junyang Li, Farhad Pakdaman, Miaogen Ling, Moncef Gabbouj
Summary: No-Reference Image Quality Assessment aims to evaluate image perceptual quality based on human perception. Many studies have used Transformers to simulate the human visual system by assigning different self-attention mechanisms to distinguish image regions. However, the quadratic computational complexity of self-attention is time-consuming and expensive. We propose a lightweight attention mechanism using decomposed large-kernel convolutions to extract multiscale features, and a novel feature enhancement module to simulate the human visual system. Additionally, we compensate for information loss caused by image resizing with supplementary features from natural scene statistics. Experimental results on five standard datasets demonstrate that our proposed method outperforms existing approaches while significantly reducing computational costs.
IEEE SIGNAL PROCESSING LETTERS
(2023)
Article
Engineering, Electrical & Electronic
Li Yu, Wenshuai Chang, Shiyu Wu, Moncef Gabbouj
Summary: This paper proposes a Transformer-based method for enhancing the quality of compressed videos. The method utilizes SSTF module and CAQE module to extract spatial and temporal features, and achieves efficient fusion of temporal information, resulting in improved performance.
IEEE TRANSACTIONS ON BROADCASTING
(2023)
Article
Computer Science, Artificial Intelligence
Yu Xue, Chenyi Zhang, Ferrante Neri, Moncef Gabbouj, Yong Zhang
Summary: The study proposes a feature selection method called EAR-FS based on an attention mechanism and hybrid metaheuristic, which reduces the number of features in high-dimensional data while ensuring classification accuracy.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Mehmet Yamac, Ugur Akpinar, Erdem Sahin, Moncef Gabbouj, Serkan Kiranyaz
Summary: Efforts in compressive sensing (CS) literature can be categorized into finding a measurement matrix that preserves compressed information effectively and finding a reliable reconstruction algorithm. While traditional CS methods use random matrices and iterative optimizations, recent deep learning-based solutions accelerate recovery and improve accuracy. However, jointly learning the entire measurement matrix remains challenging. This work introduces a separable multi-linear learning method for the CS matrix, which improves performance compared to block-wise CS, especially at low measurement rates.
IEEE TRANSACTIONS ON IMAGE PROCESSING
(2023)
Article
Computer Science, Artificial Intelligence
Serkan Kiranyaz, Junaid Malik, Mehmet Yamac, Mert Duman, Ilke Adalioglu, Esin Guldogan, Turker Ince, Moncef Gabbouj
Summary: In this article, the authors propose a new neural network model called Self-ONNs, which utilize super neurons to increase the receptive field size and improve information flow. The use of super neurons allows for non-localized kernel operations without adding computational complexity, resulting in superior learning and generalization capability.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
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)