Article
Computer Science, Information Systems
Xuqin Wei, Yun Shi, Weiyin Gong, Yanyun Guan
Summary: This paper introduces a novel image classification algorithm that uses an improved image representation method to generate virtual samples and designs a weight fusion scheme. The proposed algorithm improves the accuracy of image classification.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Cigdem Serifoglu Yilmaz, Volkan Yilmaz, Oguz Gungor
Summary: The study investigated the performance of various conventional and state-of-the-art pansharpening techniques, finding that methods in the Multiresolution Analysis (MRA), Deep Learning (DL), Colour-Based (CB) and Variational Optimization (VO) categories exhibited the best pansharpening performances, while hybrid and Component Substitution (CS)-based techniques showed poorer performances.
INFORMATION FUSION
(2022)
Article
Remote Sensing
Mingrui Chen, Xiaoqing Wang, Yin Yu, Xinzhe Yuan
Summary: In this study, a water body separability enhancement algorithm based on sparse representation is proposed to address the confusion issue between inland water bodies and other areas in synthetic aperture radar (SAR) images. By fusing a noisy high-resolution image with a low-resolution image processed by a denoising algorithm, the proposed algorithm effectively removes thermal noise and speckle noise while maintaining the edge texture of the water body. Experimental results demonstrate a significant improvement in the separability of inland water bodies in SAR images.
INTERNATIONAL JOURNAL OF REMOTE SENSING
(2022)
Article
Computer Science, Information Systems
Xiaomei Qin, Yuxi Ban, Peng Wu, Bo Yang, Shan Liu, Lirong Yin, Mingzhe Liu, Wenfeng Zheng
Summary: This paper analyzes the causes of defocusing in a video microscope and proposes a new multi-focus image fusion method based on sparse representation (DWT-SR). By utilizing GPU parallel operation, the algorithm's running time is reduced, resulting in higher image contrast and more detailed representation.
Article
Computer Science, Artificial Intelligence
Xiaosong Li, Fuqiang Zhou, Haishu Tan
Summary: The proposed image fusion method is based on three-layer decomposition and sparse representation, which effectively fuses and denoises high-frequency components by adaptively designing sparse reconstruct error parameters. Additionally, the structure-texture decomposition model and carefully designed fusion rules are used to fully utilize details and energy in low-frequency components. The experimental results show that this method can effectively address clean and noisy image fusion problems and outperform some state-of-the-art methods in subjective visual and quantitative evaluations.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Qiu Hu, Shaohai Hu, Fengzhen Zhang
Summary: A novel fusion framework with two-scale image reconstruction is proposed for preserving structure information and detailed information of each source multi-modality image. Experimental results demonstrate that the proposed method outperforms existing methods in terms of edge texture clarity and visual effect.
Article
Environmental Sciences
Le Sun, Qihao Cheng, Zhiguo Chen
Summary: The study proposed an HSI super-resolution model based on spectral smoothing prior and tensor tubal row-sparse representation, termed SSTSR, which reconstructs HSI with high spatial resolution and spectral resolution through nonlocal priors, tensor decomposition, and regularization. Experimental results showed that the method outperformed many advanced HSI super-resolution methods.
Article
Physics, Multidisciplinary
Liangliang Li, Hongbing Ma
Summary: The paper proposed a novel multimodal medical image fusion method using PCNN and WSEML, decomposing images through NSCT to process low- and high-frequency components, and integrating them to obtain a fused image. Experimental results show that the method performs well in multimodal medical image fusion, with significant advantages in objective evaluation indexes.
Article
Biology
Qiaoqiao Li, Weilan Wang, Guoyue Chen, Dongdong Zhao
Summary: The study proposes a novel medical image fusion approach based on segment graph filter and sparse representation, which achieves comparable fusion performance to state-of-the-art methods in terms of both subjective visual performance and objective quantification.
COMPUTERS IN BIOLOGY AND MEDICINE
(2021)
Article
Engineering, Electrical & Electronic
Wenqing Wang, Xiao Ma, Han Liu, Yuxing Li, Wei Liu
Summary: This study introduces a novel fusion method based on joint convolutional analysis and synthesis (JCAS) sparse representation, which can effectively reduce spatial artifacts and blurring effects in multi-focus image fusion, producing clearer edge details.
SIGNAL PROCESSING-IMAGE COMMUNICATION
(2021)
Article
Radiology, Nuclear Medicine & Medical Imaging
Nahed Tawfik, Heba A. Elnemr, Mahmoud Fakhr, Moawad I. Dessouky, Fathi E. Abd El-Samie
Summary: Medical image fusion is a process of merging important information from different modality images to create a more informative fused image. Deep learning methods have achieved significant breakthroughs in the field of image fusion. This paper proposes a medical image fusion method based on stacked sparse auto-encoder (SSAE) and non-subsampled contourlet transform (NSCT), which has been evaluated on various medical image modalities.
JOURNAL OF DIGITAL IMAGING
(2022)
Article
Engineering, Biomedical
Leiner Barba-J, Lorena Vargas-Quintero, Jose A. Calder PRIMEon-Agudelo
Summary: This paper introduces a transform-based fusion scheme for bone SPECT/CT image analysis, using the Hermite transform for image feature coding. Two different fusion strategies were designed based on coefficient content, and the final fused image was recovered using the inverse transform.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Physics, Multidisciplinary
Bingzhe Wei, Xiangchu Feng, Kun Wang, Bian Gao
Summary: A novel fusion method that combines CNN and SR for multi-focus image fusion has been proposed, resulting in a more accurate and informative fused image. Experimental results demonstrate that this method clearly outperforms existing methods in terms of visual perception and objective evaluation metrics, while also significantly reducing computational complexity.
Article
Computer Science, Artificial Intelligence
Haiyue Zhang, Daoyun Xu, Yongbin Qin
Summary: In this study, a novel representation algorithm based on logarithmic function was proposed to enhance image classification accuracy. The fusion of original and novel representations led to lower error rates in classification algorithms coupled with LFNR, especially outperforming other sparse representation algorithms. The no-parameter property of LFNR was also highlighted as a notable feature.
TRAITEMENT DU SIGNAL
(2021)
Article
Chemistry, Analytical
Liangliang Li, Hongbing Ma
Summary: The study introduces a novel multisource remote sensing image fusion algorithm that integrates contrast saliency map and SML in the NSST domain. Experimental results demonstrate that the proposed technique performs well in terms of contrast enhancement and detail preservation.
Article
Automation & Control Systems
Jian Sun, Guanqiu Qi, Neal Mazur, Zhiqin Zhu
Summary: With the rapid increase in data measurement from power grids, machine learning research in transient control has gained significant attention. This article proposes a sparse neural network based reinforcement learning scheme for optimizing the transient stability enhancement of power grids with energy storage systems. The simulation results confirm the feasibility, advantages, and adaptability of the proposed method.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2022)
Article
Engineering, Electrical & Electronic
Ruirui Chen, Yanjing Sun, Liping Liang, Wenchi Cheng
Summary: This paper investigates the use of unmanned aerial vehicles (UAVs) in assisting data acquisition for the Internet of Things (IoT). It proposes a deployment scheme with quality-of-service (QoS) guarantee to optimize the placement of UAVs and maximize their average data rate. The proposed algorithms minimize the number of UAVs while covering a large number of ground devices.
IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY
(2022)
Article
Computer Science, Software Engineering
Yuanyuan Li, Ziyu Wang, Li Yin, Zhiqin Zhu, Guanqiu Qi, Yu Liu
Summary: This paper proposes a dual encoding-decoding structure of X-shaped network (X-Net) that integrates the characteristics of CNNs and Transformer. It can serve as a good alternative to the traditional pure convolutional medical image segmentation network.
Article
Computer Science, Artificial Intelligence
Fancheng Zeng, Guanqiu Qi, Zhiqin Zhu, Jian Sun, Gang Hu, Matthew Haner
Summary: This paper proposes a load-frequency control strategy based on ADES reinforcement learning, which uses convex neural networks to convert nonlinear optimization problems into convex optimization problems, avoiding local optimums, improving controller response, and effectively reducing the frequency deviation of power grids under DoS attacks.
Article
Computer Science, Artificial Intelligence
Xiao Yun, Qunqun Wang, Xiaozhou Cheng, Kaili Song, Yanjing Sun
Summary: This paper proposes an improved dual-branch mutual learning fusion network to address the problems in domain adaptive pedestrian re-identification. By increasing the difference between dual networks and enhancing their feature expressiveness, the proposed method outperforms other methods in recognition accuracy.
APPLIED INTELLIGENCE
(2023)
Article
Telecommunications
Song Li, Min Li, Ruirui Chen, Yanjing Sun
Summary: This paper investigates the state update problem in a multi-antenna cellular IoT and introduces the concept of age of transmission. The problem is formulated as a restless multi-armed bandit problem, and a scheduling strategy based on the Whittle index and complete subgraph detection is proposed to avoid interference between nodes.
CHINA COMMUNICATIONS
(2022)
Article
Telecommunications
Jiasi Zhou, Yanjing Sun, Chintha Tellambura
Summary: This letter proposes a rate splitting-based secure transmit approach for cache-enabled cloud radio access networks. By optimizing message splitting, RRH clustering, and beamforming, the minimum secrecy rate is maximized and the transmit constraints are met, achieving significant gains.
IEEE COMMUNICATIONS LETTERS
(2022)
Article
Computer Science, Artificial Intelligence
Kaiwen Dong, Yanjing Sun, Xiaozhou Cheng, Xiaolin Wang, Bin Wang
Summary: In this paper, the authors propose a structure-context complementary network (SCC-Net) for human pose estimation, which consists of an enhanced attention mechanism and an atrous convolution-based module. The proposed modules, namely cross-coordinate attention bottleneck (CCAB) and waterfall residual atrous pooling (WRAP), improve the performance of body joint detection by addressing challenges such as occlusion and background confusion. The experimental results on benchmark datasets demonstrate the effectiveness of the proposed modules and the holistic SCC-Net.
APPLIED INTELLIGENCE
(2023)
Article
Computer Science, Theory & Methods
Shujuan Wang, Run Liu, Huafeng Li, Guanqiu Qi, Zhengtao Yu
Summary: Due to incomplete appearance features, matching occluded pedestrians under multiple cross-camera views is a long-term challenge. This paper introduces the idea of adversarial attack into occluded person re-ID and proposes an adversarial training framework to defend against obstacles and improve pedestrian identity matching. The proposed framework broadens research horizons in robust model design and achieves better performance on occluded re-ID datasets.
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2023)
Article
Engineering, Electrical & Electronic
Hua Xu, Wenjuan Shi, Yanjing Sun
Summary: This paper designs an underwater MI communication system based on Quasi-cyclic LDPC (QC-LDPC) codes. It proposes a novel algorithm named underwater magnetic induction protograph (UWMIP) extrinsic information transfer algorithm to evaluate the performance of the given QC-LDPC code. Additionally, a differential evolution UWMIP (DE-UWMIP) algorithm is presented to search for optimized QC-LDPC codes with the best distance threshold. Simulation results demonstrate the effectiveness of the proposed algorithm and its application in designing the underwater MI communication system.
PHYSICAL COMMUNICATION
(2023)
Article
Telecommunications
Yunyun Li, Yanjing Sun, Qingyan Ren, Song Li
Summary: Autonomous underwater vehicle (AUV)-assisted data collection is an efficient approach to implementing smart ocean. However, two critical issues, AUV yaw and sensor node movement, hinder data collection in time-varying ocean currents. To address these issues, we propose an adaptive AUV-assisted data collection strategy. This strategy considers the energy consumption of the AUV and the value of information (VoI) over sensor nodes, and maximizes the VoI-energy ratio through optimization. Furthermore, the AUV yaw problem is solved by determining the reachable region and optimal cruising direction in different ocean current environments.
CHINA COMMUNICATIONS
(2023)
Article
Computer Science, Information Systems
Bowen Wang, Yanjing Sun, Haejoon Jung, Long D. Nguyen, Nguyen-Son Vo, Trung Q. Duong
Summary: In this paper, a method is proposed to optimize mobile edge computing using digital twin, and to make offloading decisions based on real-time predictions under uncertainty.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2023)
Article
Telecommunications
Qingyan Ren, Yanjing Sun, Song Li, Bin Wang, Zhengda Yu
Summary: This paper proposes an energy-efficient data collection method for underwater wireless sensor networks (WSNs) using underwater magnetic induction-assisted acoustic cooperative multiple-input-multiple-output (MIMO) technique. It focuses on forming cooperative MIMO and establishing relay links to improve network coverage and extend network lifetime.
CHINA COMMUNICATIONS
(2023)
Article
Biology
Zhiqin Zhu, Zheng Yao, Xin Zheng, Guanqiu Qi, Yuanyuan Li, Neal Mazur, Xinbo Gao, Yifei Gong, Baisen Cong
Summary: Drug-target affinity (DTA) prediction is an emerging and effective method in drug development research to evaluate the efficacy and safety of candidate drugs. However, existing DTA prediction models lack information on interactions between molecular substructures, impacting prediction accuracy and interpretability. Therefore, TDGraphDTA is introduced, using Transformer and Diffusion to predict drug-target interactions by incorporating multi-scale information interaction and graph optimization.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Computer Science, Information Systems
Yu Zhou, Weikang Gong, Yanjing Sun, Leida Li, Jinjian Wu, Xinbo Gao
Summary: Panoramic image quality assessment (PIQA) is crucial for technologies providing immersive visual experience. Most existing PIQA methods ignore the special characteristics of stitching distortions caused by imperfect algorithms, resulting in unsatisfactory performance. To address this, we propose an effective stitched PIQA method consisting of an imaginary reference generation module and a hierarchical quality prediction module. Extensive experiments demonstrate the superiority of our method in evaluating the quality of stitched panoramic images.
IEEE TRANSACTIONS ON MULTIMEDIA
(2023)