Article
Computer Science, Software Engineering
Uttam Singh Bist, Nanhay Singh
Summary: This article primarily focuses on the fundamentals and optimization techniques of support vector machines (SVMs) and its variants. It discusses the major issues and challenges in different variations of SVMs, as well as the advancements and optimizations made in SVM models and their kernels.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
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
Jing Dong, Liu Yang, Chang Liu, Wei Cheng, Wenwu Wang
Summary: Discriminative dictionary learning (DDL) is an approach to solving pattern classification problems by learning dictionaries from training samples. This study proposes a new DDL algorithm that enhances discrimination by introducing a discriminative term associated with coding coefficients. The algorithm employs a structured dictionary pair and support vector machines (SVMs) for joint learning, and a classification scheme based on reconstruction error and SVMs.
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
Biotechnology & Applied Microbiology
Yifeng Dou, Wentao Meng
Summary: This paper introduces the research, prediction, and diagnosis methods of breast cancer, using the improved optimization algorithm GSP_SVM, which shows excellent performance in breast cancer diagnosis and improves the diagnostic efficiency of medical institutions.
FRONTIERS IN BIOENGINEERING AND BIOTECHNOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
A. Ponmalar, V Dhanakoti
Summary: This paper presents a novel technique to enhance intrusion detection by addressing the complexities of heterogeneous security data in big data. The proposed methodology significantly improves accuracy and can identify different types of attacks. Comparisons with baseline models demonstrate the effectiveness of the approach.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Liming Liu, Maoxiang Chu, Rongfen Gong, Li Zhang
Summary: The improved nonparallel support vector machine (INPSVM) proposed in this article inherits the advantages of nonparallel support vector machine (NPSVM) while also offering incomparable benefits over twin support vector machine (TSVM). INPSVM effectively eliminates noise effects and achieves higher classification accuracy for both linear and nonlinear datasets compared to other algorithms. Experimental results demonstrate the superior efficiency, accuracy, and robustness of INPSVM.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Minghao Wu, Tongling Jiang, Min Guo, Yunyun Duan, Zhizheng Zhuo, Jinyuan Weng, Cong Xie, Jun Sun, Junjie Li, Dan Cheng, Xing Liu, Jiang Du, Xianchang Zhang, Yi Zhang, Yaou Liu
Summary: APTw MRI and its derived radiomics show potential for predicting IDH mutation and grading adult-type diffuse gliomas, providing valuable information for personalized clinical diagnostics and treatment strategies.
EUROPEAN RADIOLOGY
(2023)
Article
Engineering, Multidisciplinary
Han-shan Li
Summary: This study proposes a new recognition method for projectiles by combining particle swarm optimization support vector machine and spatial-temporal constraints of six sky-screen detection sensors. By analyzing the measurement principle and signal characteristics, the existing problems in projectile recognition are addressed. Experimental results validate the feasibility of the proposed algorithm.
DEFENCE TECHNOLOGY
(2023)
Article
Environmental Sciences
Guangxin Liu, Liguo Wang, Danfeng Liu, Lei Fei, Jinghui Yang
Summary: This article proposes a non-parallel SVM model, which improves the classification effect and generalization performance for hyperspectral images by adding an additional empirical risk minimization term and bias constraint.
Article
Automation & Control Systems
Zhenchao Ma, Laurence Tianruo Yang, Qingchen Zhang
Summary: This study proposes a Support Multimode Tensor Machine (SMTM) algorithm that generalizes the formulation of traditional Support Tensor Machine (STM) by applying multimode product. Experiments conducted on various datasets validate the superior performance of SMTM in multiple classification tasks and suggest the potential of the proposed model for multiple classification in industrial big data.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2021)
Article
Computer Science, Artificial Intelligence
Bagesh Kumar, Ayush Sinha, Sourin Chakrabarti, O. P. Vyas
Summary: In this paper, a fast training method for OCSSVM is proposed, which enhances its scalability without compromising precision significantly. Experimental results show that the proposed method achieves the best tradeoff between training time and accuracy, providing similar accuracies to regular OCSSVM and better scalability compared to existing state-of-the-art one-class classifiers.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Management
Asuncion Jimenez-Cordero, Juan Miguel Morales, Salvador Pineda
Summary: Feature selection has become a challenging issue in machine learning, particularly in classification problems. Support Vector Machine is a widely used technique in classification tasks, with various methodologies proposed for selecting the most relevant features in SVM. The authors introduce an embedded feature selection method based on a min-max optimization problem to balance model complexity and classification accuracy, showcasing efficiency and usefulness in benchmark datasets.
EUROPEAN JOURNAL OF OPERATIONAL RESEARCH
(2021)
Article
Automation & Control Systems
Guolin Yu, Jun Ma, Chenzhen Xie
Summary: This paper proposes a Hessian scatter regularized twin support vector machine (HSR-TSVM) based on Laplacian regularization. HSR-TSVM can better maintain the local topology of the samples and improve classification performance by utilizing the structural information of samples. Furthermore, a least-squares version of HSR-TSVM called HSR-LSTSVM is proposed to improve computational efficiency.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Liming Liu, Ping Li, Maoxiang Chu, Shuming Liu
Summary: In this paper, we propose a robust nonparallel support vector machine model (R-NPSVM+) under the privileged information learning setting. R-NPSVM+ integrates privileged information into NPSVM to improve classification accuracy and uses robust loss functions to enhance model robustness. Experimental results demonstrate that R-NPSVM+ outperforms other classical algorithms, especially when samples are corrupted by noise and outliers.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Information Systems
Alamgir Sardar, Saiyed Umer, Ranjeet K. R. Rout, Shui-Hua Wang, M. Tanveer
Summary: This article proposes a secure face recognition system for IoT-enabled Healthcare, which provides reliable security and smart treatment through face biometrics and template protection techniques. The system has been tested on benchmark face databases and compared with state-of-the-art methods, showing its novelty.
ACM TRANSACTIONS ON SENSOR NETWORKS
(2023)
Article
Computer Science, Artificial Intelligence
Haifeng Sima, Feng Gao, Yudong Zhang, Junding Sun, Ping Guo
Summary: In this paper, a collaborative optimization parallel convolution network consisting of 3D-2D CNN is proposed for accurate classification of hyperspectral images. The experimental results show that this method outperforms the state-of-the-art methods and has better generalization capability.
INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
(2023)
Article
Computer Science, Artificial Intelligence
Sonali Samal, Yu-Dong Zhang, Thippa Reddy Gadekallu, Bunil Kumar Balabantaray
Summary: The rampant spread of explicit content across social media can harm society. Therefore, it is crucial to be vigilant in detecting and curtailing sexually explicit content. The proposed ABP embedded Swin transformer-based YOLOv3 (ASYv3) model achieved high accuracy and precision in detecting obscene areas in images.
Article
Computer Science, Information Systems
Geng Chen, Jingli Sun, Qingtian Zeng, Gang Jing, Yudong Zhang
Summary: In this paper, a joint edge computing and caching method based on D3QN is proposed to solve the problem of limited computing and storage resources for self-driving vehicles in IOV. The proposed algorithm models the processes of offloading tasks and caching them to the base station as optimization problems, taking into account system latency, energy consumption, and cache space constraints. The simulation results show that the algorithm improves system performance in terms of latency, energy consumption, cache utilization, and probability of unfinished tasks.
Article
Mathematics
Shtwai Alsubai, Abdullah Alqahtani, Adel Binbusayyis, Mohemmed Sha, Abdu Gumaei, Shuihua Wang
Summary: Diabetic retinopathy is a leading cause of blindness and vision loss in adults. Screening for this disease is essential to identify cases that require treatment. Integrating quantum computing with conventional image classification methods has the potential to improve classification accuracy. This study proposes a quantum-based deep convolutional neural network for the classification of diabetic retinopathy.
Article
Computer Science, Artificial Intelligence
Qi Zhu, Jing Yang, Shuihua Wang, Daoqiang Zhang, Zheng Zhang
Summary: Brain network analysis is an effective method for brain disease diagnosis. This paper proposes a multi-modal non-Euclidean brain network analysis method based on community detection and convolutional autoencoder. It can address the challenges of the non-Euclidean nature of brain networks and the suboptimal utilization of complementary information from distinct modalities.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTATIONAL INTELLIGENCE
(2023)
Editorial Material
Engineering, Multidisciplinary
Yudong Zhang, Zhengchao Dong
Article
Computer Science, Artificial Intelligence
Navid Ghassemi, Afshin Shoeibi, Marjane Khodatars, Jonathan Heras, Alireza Rahimi, Assef Zare, Yu-Dong Zhang, Ram Bilas Pachori, Manuel Gorriz
Summary: The outbreak of COVID-19 has had a significant impact on people worldwide. Accurately diagnosing and isolating patients is crucial in fighting this pandemic, and medical imaging, particularly CT imaging, has been a focus of research due to its accuracy and availability. This paper presents a method using pre-trained deep neural networks and a CycleGAN model for data augmentation, achieving state-of-the-art performance with 99.60% accuracy. A dataset of 3163 images from 189 patients, collected from suspected COVID-19 cases, has been publicly made available for evaluation. The method's reliability is further assessed using calibration metrics and the Grad-CAM technique for explaining its decisions.
APPLIED SOFT COMPUTING
(2023)
Article
Automation & Control Systems
Xu Wang, Yao Zhang, Wei Liang, Wei Chen, Haohua Xiu, Lei Ren, Guowu Wei, Luquan Ren
Summary: This article introduces a new polycentric hybrid knee prosthesis that can switch between high-torque and low-torque activities. The prosthesis uses a multibar linkage and servo-controlled telescopic slide rails for mode transition. It provides geometric stability in stance and improves toe clearance in swing. In active mode, the prosthesis offers high transmission ratio and continuous peak torque, and impedance control is employed to regulate joint torque. The polycentric mechanism provides smoother and more comfortable interactions. Stair ascent tests show similar joint angle and torque profiles to able-bodied individuals.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Review
Computer Science, Artificial Intelligence
M. Tanveer, M. A. Ganaie, Iman Beheshti, Tripti Goel, Nehal Ahmad, Kuan-Ting Lai, Kaizhu Huang, Yu-Dong Zhang, Javier Del Ser, Chin-Teng Lin
Summary: Over the years, Machine Learning models have been successfully used for predicting brain age accurately based on neuroimaging data. This review comprehensively analyzes the adoption of deep learning for brain age estimation and explores different deep learning architectures and frameworks used in this field. The paper aims to establish a common reference for newcomers and experienced researchers interested in utilizing deep learning models for brain age estimation.
INFORMATION FUSION
(2023)
Article
Computer Science, Hardware & Architecture
Yu-Dong Zhang, Yanrong Pei, Juan Manuel Gorriz
Summary: COVID-19 has caused 6.42 million deaths and over 586 million confirmed positive cases as of August 10, 2022. A 12-layer CNN-based backbone network called SCNN, utilizing the Swish activation function, is proposed. The SCNN model outperforms other backbone networks and achieves high sensitivity, specificity, and accuracy in diagnosing COVID-19. A web app based on the SCNN model is developed for users to upload images and obtain prediction results.
MOBILE NETWORKS & APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Xiang Yu, Zeyu Ren, David S. Guttery, Yu-Dong Zhang
Summary: Breast cancer is a common and serious health threat in the UK. Early detection is crucial for effective treatment. Image-based methods, such as mammography, offer less invasive and time-consuming alternatives to biopsy. Our study developed a novel breast mass classification system called DF-dRVFL, which showed promising results in classifying breast masses with high accuracy and efficiency.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Engineering, Multidisciplinary
Yaoyao Lin, Ali Asghar Heidari, Shuihua Wang, Huiling Chen, Yudong Zhang
Summary: The Hunger Games Search (HGS) is an innovative optimizer inspired by social animals' collaborative foraging activities. This study proposes two adjusted strategies, LS-OBL and RM, to enhance the original HGS algorithm. Experimental results demonstrate the effectiveness of these strategies and show that the improved algorithm, RLHGS, outperforms other state-of-the-art algorithms in various test suites. The application of RLHGS to real-world engineering optimization problems further supports its efficiency and value.
Review
Automation & Control Systems
Xinxin Zhang, Menghan Hu, Yudong Zhang, Guangtao Zhai, Xiao-Ping Zhang
Summary: In recent years, optical imaging techniques have been widely recognized for their ability to measure vital signals such as heart rate, respiratory rate, oxygen saturation, and blood pressure, which are important indicators of human health. Various optical imaging methods including RGB imaging, thermal imaging, hyperspectral imaging, depth imaging, and multimodal imaging provide spatial information and have extensive applications in remote physiological signal monitoring. This survey provides a comprehensive overview of the principles, data analysis methods, advantages, disadvantages, applications, and future prospects of optical imaging methods for vital signal measurement.
ADVANCED INTELLIGENT SYSTEMS
(2023)
Review
Computer Science, Artificial Intelligence
Zeyu Ren, Shuihua Wang, Yudong Zhang
Summary: Supervised learning aims to establish multiple mappings between training data and outputs through building a function or model, while weakly supervised learning is more applicable for medical image analysis due to the lack of sufficient labels. This review provides an overview of the latest progress in weakly supervised learning for medical image analysis, including incomplete, inexact, and inaccurate supervision, as well as introduces related works on different applications. Challenges and future developments of weakly supervised learning in medical image analysis are also discussed.
CAAI TRANSACTIONS ON INTELLIGENCE TECHNOLOGY
(2023)