Article
Computer Science, Information Systems
Thuong Van Nguyen, An Gia Vien, Chul Lee
Summary: We proposed a real-time dehazing algorithm based on multiscale guided filtering. By constructing an image pyramid and iteratively upsampling, we achieved efficient estimation of transmission map and atmospheric light. Extending the algorithm to real-time video dehazing also reduced flickering artifacts and showed comparable or better performance than state-of-the-art algorithms.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Chemistry, Analytical
Sherif Abdelfattah, Mohamed Baza, Mohamed Mahmoud, Mostafa M. Fouda, Khalid Abualsaud, Elias Yaacoub, Maazen Alsabaan, Mohsen Guizani
Summary: Machine learning, especially SVM, has been widely used in medical diagnosis. However, privacy protection and intellectual property preservation are still challenging. This paper proposes a modified encryption cryptosystem to address these issues and successfully fulfills security, privacy, and accuracy objectives in medical diagnosis.
Article
Computer Science, Artificial Intelligence
Tong Gao, Hao Chen
Summary: In this study, a multicycle disassembly-based decomposition algorithm (MCD-DA) is proposed to efficiently solve the training problem of multiclass support vector machine (SVM). MCD-DA constructs a graph model to re-express the constraints in multiclass SVM, partitions the complex feasible region into simple sub-feasible regions, and designs multiple cycle-based disassembly strategies to update the working variables analytically. Experimental results demonstrate that MCD-DA outperforms typical optimization algorithms for more sample cases.
PATTERN RECOGNITION
(2023)
Article
Computer Science, Artificial Intelligence
Xin Huang, Xiaodong Zhang, Yiwei Xiong, Fei Dai, Yingjie Zhang
Summary: In this paper, a novel intelligent diagnosis framework is proposed for accurately identifying the crack severity of turbine blades. The framework combines multiscale sparse filtering (MSF)-based unsupervised sparse feature learning and multi-kernel support vector machine for information fusion (MKSVMIF). Signal processing methods, including the enhanced EEMD-based multiwavelet packet energy entropy (EEMD-WPEE), are used to eliminate interference and retain fault-related characteristics. Extensive experiments on a blade-rotor simulation rig validate the effectiveness of the proposed framework in quantitatively detecting different blade crack severities.
ADVANCED ENGINEERING INFORMATICS
(2023)
Article
Chemistry, Analytical
Abdul Razaque, Mohamed Ben Haj Frej, Muder Almi'ani, Munif Alotaibi, Bandar Alotaibi
Summary: This paper introduces a land use classification method based on improved SVM-RBF and SVM-Linear, evaluating the impact of parameter optimization on accuracy through cross-validation. The results show that these new methods have higher accuracy, reliability, and fault tolerance compared to traditional and state-of-the-art algorithms.
Article
Computer Science, Hardware & Architecture
Ruizhong Du, Yun Li, Xiaoyan Liang, Junfeng Tian
Summary: This paper proposes a lightweight support vector machine intrusion detection model based on Cloud-Fog Collaboration(CFC-SVM), which addresses the issues of fog nodes being closer to user equipment, having heterogeneous nodes, limited storage capacity resources, and greater vulnerability to intrusion. The model utilizes Principal Component Analysis (PCA) to reduce dimensionality, eliminates attribute correlation, and reduces training time. Experimental results using the KDD CUP 99 dataset demonstrate that the proposed model outperforms other similar algorithms in terms of detection time, detection rate, and accuracy, effectively solving the problem of intrusion detection in the fog environment.
MOBILE NETWORKS & APPLICATIONS
(2022)
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
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
Genyun Sun, Xueqian Rong, Aizhu Zhang, Hui Huang, Jun Rong, Xuming Zhang
Summary: This paper proposes a SVM classifier based on multi-scale Mahalanobis kernel, which improves the classification accuracy by optimizing parameters and enhancing global cognitive learning ability. Experimental results show that this method performs better in classifying high-resolution remote sensing images.
COGNITIVE COMPUTATION
(2021)
Article
Computer Science, Artificial Intelligence
Xiaochen Zhou, Xudong Wang
Summary: Fed-KSVM is a federated learning scheme designed for training low-memory-consumption kernel SVM models. By decomposing the training process into subproblems and using an incremental learning algorithm, it achieves reduced memory consumption on edge devices. Additionally, by constructing a global model after training the local models, the scheme reduces communication costs while maintaining high accuracy.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Information Systems
Tiep M. Hoang, Trung Q. Duong, Hoang Duong Tuan, Sangarapillai Lambotharan, Lajos Hanzo
Summary: This article presents a framework for converting wireless signals into structured datasets for detecting active eavesdropping attacks at the physical layer using machine learning algorithms.
Article
Mathematics, Interdisciplinary Applications
Yanran Wang, Jonghyuk Baek, Yichun Tang, Jing Du, Mike Hillman, Jiun-Shyan Chen
Summary: This work presents an automated approach for constructing digital representations of composites with complex microstructures. It uses Support Vector Machine (SVM) classification for discretization and introduces an Interface-Modified Reproducing Kernel Particle Method (IM-RKPM) for approximating weak discontinuities across material interfaces. The proposed method is effective in image-based modeling of polymer-ceramic composite microstructures.
COMPUTATIONAL MECHANICS
(2023)
Review
Operations Research & Management Science
M. Tanveer, T. Rajani, R. Rastogi, Y. H. Shao, M. A. Ganaie
Summary: TWSVM and TSVR are emerging machine learning techniques for classification and regression challenges. TWSVM classifies data points using two nonparallel hyperplanes, while TSVR is based on TWSVM and solves two SVM-type problems. Although there has been progress in research on these techniques, there is limited literature on the comparison of different variants of TSVR.
ANNALS OF OPERATIONS RESEARCH
(2022)
Article
Computer Science, Artificial Intelligence
Chen Ding, Tian-Yi Bao, He-Liang Huang
Summary: The study proposes a quantum-inspired classical algorithm for LS-SVM, utilizing an improved sampling technique for classification. The theoretical analysis indicates that the algorithm can achieve classification with logarithmic runtime for low-rank, low-condition number, and high-dimensional data matrices.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Management
Haimonti Dutta
Summary: In the era of big data, a scalable support vector machine (SVM) algorithm is an important tool for machine learning researchers. This paper presents a distributed algorithm, called the gossip-based subgradient (GADGET) SVM, for learning linear SVMs in the primal form. The algorithm can be executed locally on sites of a distributed system, and it has fast convergence speed and low message complexity. Empirical results show that the algorithm performs comparably to other state-of-the-art solvers.
MANAGEMENT SCIENCE
(2022)
Article
Computer Science, Information Systems
Haidong Wang, Xuan He, Zhiyong Li, Jin Yuan, Shutao Li
Summary: This study proposes an end-to-end MOT network called joint detection and association network (JDAN) that can simultaneously perform object detection and data association, resulting in improved tracking performance by optimizing the overall task.
ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Jinyang Liu, Renwei Dian, Shutao Li, Haibo Liu
Summary: This study proposes a saliency guided deep-learning framework for pixel-level image fusion, which can simultaneously deal with different tasks and generate fusion images that are more in line with visual perception by extracting meaningful information through fusion weights.
INFORMATION FUSION
(2023)
Article
Geochemistry & Geophysics
Zhuoyi Zhao, Xiang Xu, Jun Li, Shutao Li, Antonio Plaza
Summary: Nowadays, CNN-based DL models have gained popularity in HSIC and achieved high accuracy due to their hierarchical and nonlinear feature learning patterns. However, deeper network structures may demand more parameters and training samples. To overcome these problems, we propose a lightweight network model using the GSC module, which reduces parameters and is suitable for HSI data. Experimental results show that our model has low training cost and achieves competitive accuracy with fewer samples compared to existing models.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Ze Song, Xiaohui Wei, Xudong Kang, Shutao Li, Jinyang Liu
Summary: In this study, we propose a cross-temporal context learning network called CCLNet, which leverages intratemporal and intertemporal long-range dependencies to fully exploit cross-temporal context information. Our method achieves improved change detection performance, especially in complex and diverse changing scenes.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Anjing Guo, Renwei Dian, Shutao Li
Summary: In recent years, fusing a low-resolution hyperspectral image (LR-HSI) with a high-resolution multispectral image (HR-MSI) from different satellites has been proven to be an effective method for improving HSI resolution. However, the LR-HSI and HR-MSI obtained from different satellites may not satisfy existing observation models and it is difficult to register them. To address these issues, a deep-learning-based framework is proposed, which includes image registration, blur kernel learning, and image fusion. The proposed framework demonstrates superior performance in HSI registration and fusion accuracy through extensive experiments.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Haolong Fu, Shixun Wang, Puhong Duan, Changyan Xiao, Renwei Dian, Shutao Li, Zhiyong Li
Summary: Visible-infrared object detection aims to improve detector performance by fusing the complementarity of visible and infrared images. To overcome the limitation of existing methods that only utilize local intramodality information, we propose a feature-enhanced long-range attention fusion network (LRAF-Net) that leverages the long-range dependence between different modalities.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Jiacheng Lin, Xianwen Dai, Ke Nai, Jin Yuan, Zhiyong Li, Xu Zhang, Shutao Li
Summary: Traditional personal image privacy protection often suffers from overprotection, resulting in unnecessary information loss. This paper introduces a new task called "Referring Personal Image Privacy Protection" (RP-IPP) which aims to protect a designated person in an image based on user's text or voice input. A lightweight yet effective personal protection network, Balanced Referring Personal PrivacyNet (BRPPNet), is proposed, which includes a Multi-scale Feature Fusion Module (MFFM) and a Balanced-BCE loss to accurately localize the referred person. Experimental results demonstrate the superiority of BRPPNet over existing approaches for RP-IPP.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Geochemistry & Geophysics
Congyu Li, Jiaqi Liu, Xinxin Liu, Xudong Kang, Shutao Li
Summary: This study proposes a novel flood detection model based on time-series variation analysis and integrates it with fuzzy-based methods to develop an unsupervised flood-mapping framework. The framework also includes a flooded short vegetation activation model to improve accuracy in complex regions. Experimental results show that the proposed method outperforms other methods in terms of quantitative evaluation and visual performance, demonstrating its effectiveness, stability, and universality.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Geochemistry & Geophysics
Yan Mo, Xudong Kang, Shuo Zhang, Puhong Duan, Shutao Li
Summary: This paper proposes a coarse-to-fine image registration approach for infrared and visible images in a dual-sensor unmanned aerial vehicle (UAV) imaging system, addressing the issues of uneven distribution of extracted features, low repeatability, and ambiguous features.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Jinyang Liu, Shutao Li, Haibo Liu, Renwei Dian, Xiaohui Wei
Summary: In this paper, a lightweight pixel-level unified image fusion (L-PUIF) network is proposed to achieve more efficient and accurate image fusion. The experimental results show that L-PUIF achieves better fusion efficiency and has practicality in high-level computer vision tasks.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Ze Song, Xudong Kang, Xiaohui Wei, Shutao Li
Summary: Camouflaged object detection is always faced with the challenge of identifying object pixels embedded in the background. Existing deep learning methods lack the ability to effectively utilize the context information around different pixels. In this paper, a pixel-centric context perception network (PCPNet) is proposed to address this problem. PCPNet customizes personalized context for each pixel based on the automatic estimation of its surroundings. Experimental results demonstrate the superiority of PCPNet in camouflaged object detection compared to other state-of-the-art methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Geochemistry & Geophysics
Huiling Gao, Shutao Li, Jun Li, Renwei Dian
Summary: This research proposes a dual-branch network with attention mechanisms for multispectral image pan-sharpening. By improving the linear transformation and decomposition methods, it enhances the performance of pan-sharpening and improves the physical interpretability.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Artificial Intelligence
Renwei Dian, Anjing Guo, Shutao Li
Summary: The paper introduces a zero-shot learning method for HSI sharpening, which estimates the spectral and spatial responses of imaging sensors and uses subsampled HSI and MSI for inference to improve sharpening performance. Additionally, dimension reduction is applied to the HSI to reduce the model size, and an imaging model-based loss function is designed to enhance fusion performance.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2023)
Article
Computer Science, Artificial Intelligence
Haibo Liu, Chenguo Feng, Renwei Dian, Shutao Li
Summary: A spatial-spectral transformer-based U-net (SSTF-Unet) approach is proposed in this paper to achieve the fusion of high-resolution hyperspectral images and high-resolution multispectral images by capturing the association between distant features and exploring the intrinsic information of the images. The method utilizes spatial and spectral self-attention and incorporates multiple fusion blocks for multiscale feature fusion.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Qiya Song, Bin Sun, Shutao Li
Summary: Automatic speech recognition (ASR) is a crucial interface in intelligent systems, but its performance is often affected by external noise. Audio-visual speech recognition (AVSR) utilizes visual information to enhance ASR in noisy conditions. This article proposes a multimodal sparse transformer network (MMST) that incorporates sparse self-attention mechanism and motion features to improve AVSR performance.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)