检索结果-内蒙古大学图书馆

Efficient Image Super-Resolution With Feature Interaction Weighted Hybrid Network

IEEE Transactions on Multimedia 2025年 27卷 2256-2267页

作者： Li, Wenjie Li, Juncheng Gao, Guangwei Deng, Weihong Yang, Jian Qi, Guo-Jun Lin, Chia-Wen Beijing University of Posts and Telecommunications Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing100080 China Shanghai University School of Communication and Information Engineering Shanghai200444 China Nanjing University of Posts and Telecommunications IVIPLab Institute of Advanced Technology Nanjing210046 China Ministry of Education Key Laboratory of Artificial Intelligence Shanghai200240 China Soochow University Provincial Key Laboratory for Computer Information Processing Technology Suzhou215006 China Nanjing University of Science and Technology School of Computer Science and Technology Nanjing210094 China Westlake University Research Center for Industries of the Future School of Engineering Hangzhou310024 China OPPO Research SeattleWA98101 United States National Tsing Hua University Department of Electrical Engineering Institute of Communications Engneering Hsinchu300044 Taiwan

Lightweight image super-resolution aims to reconstruct high-resolution images from low-resolution images using low computational costs. However, existing methods result in the loss of middle-layer features due to activation functions. To minimize the impact of intermediate feature loss on reconstruction quality, we propose a Feature Interaction Weighted Hybrid Network (FIWHN), which comprises a series of Wide-residual Distillation Interaction Block (WDIB) as the backbone. Every third WDIB forms a Feature Shuffle Weighted Group (FSWG) by applying mutual information shuffle and fusion. Moreover, to mitigate the negative effects of intermediate feature loss, we introduce Wide Residual Weighting units within WDIB. These units effectively fuse features of varying levels of detail through a Wide-residual Distillation Connection (WRDC) and a Self-Calibrating Fusion (SCF). To compensate for global feature deficiencies, we incorporate a Transformer and explore a novel architecture to combine CNN and Transformer. We show that our FIWHN achieves a favorable balance between performance and efficiency through extensive experiments on low-level and high-level tasks. © 1999-2012 IEEE.

关键词： Transformers Convolutional neural networks Computational modeling Feature extraction Training Superresolution Adaptation models computer architecture Telecommunications Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Location Privacy Preservation Crowdsensing With Federated Reinforcement Learning

引用

IEEE Transactions on Dependable and Secure Computing 2025年第3期22卷 1877-1894页

作者： You, Zhichao Dong, Xuewen Liu, Ximeng Gao, Sheng Wang, Yongzhi Shen, Yulong Xidian University School of Computer Science and Technology The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education Xi'an710071 China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an710071 China Fuzhou University College of Computer and Data Science Fuzhou350025 China Central University of Finance and Economics School of Information Beijing102206 China California State Polytechnic University Pomona Department of Computer Information Systems PomonaCA91768 United States Xidian University School of Computer Science and Technology Xi'an710071 China Shaanxi Key Laboratory of Network and System Security Xi'an710071 China

Crowdsensing has become a popular method of sensing data collection while facing the problem of protecting participants' location privacy. Existing location-privacy crowdsensing mechanisms focus on static tasks and participants without considering sensing tasks' time requirements and participants' mobility, which cannot achieve satisfactory collected data quality and task completion in crowdsensing with dynamic tasks and participants. Inspired by this, we proposed a location-preservation crowdsensing mechanism, FedSense, considering dynamic tasks and participants based on federated learning (FL) and reinforcement learning (RL). In FedSense, through RL's outstanding decision-making ability, participants select sensing tasks to perform by well-trained RL models without uploading location information to servers for task allocation. We propose an independent tasks selection environment that defines actions, states, and rewards of RL to enable FedSense to achieve satisfactory task completion and data quality while preserving location privacy. Besides, FedSense applies an asynchronous FL aggregation algorithm that reduces participants' network stabilization and device computing ability requirements. Analysis proves that participants' location information does not leave the local device during the model training and task selection process, effectively avoiding privacy leakage. Simulation shows that compared with existing location-preservation crowdsensing mechanisms, FedSense achieves the highest task completion and sensing accuracy for dynamic tasks and participants. © 2024 IEEE.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Improved High-Speed Thermal Analysis Based on Two-Step Simulation for High-Frequency Transformers 14

Improved High-Speed Thermal Analysis Based on Two-Step Simul...

引用

14th Annual IEEE Applied Power Electronics Conference and Exposition, APEC 2025

作者： Yi, Zheyuan Sun, Kai Li, Qiang Liu, Zengyang Tsinghua University State Key Laboratory of Power System Department of Electrical Engineering Beijing China Delta Electronics Shanghai Co. Ltd. Shanghai China University Blacksburg Center for Power Electronics Systems The Bradley Department of Electrical and Computer Engineering Virginia Polytechnic Institute and State BlacksburgVA United States

ISBN: (纸本)9798331516116

Thermal analysis is a crucial and time-consuming step in the optimization design process of high-frequency transformers (HFTs). This paper proposes an improved thermal analysis method based on heat dissipation-conduction two-step simulation, significantly reducing the computation time while ensuring the accuracy of thermal analysis. Simulation results validate the accuracy and of the proposed method and demonstrate that the proposed method saves 82% of computation time for a single thermal analysis case compared to direct CFD. Experimental results further verify the accuracy of the proposed method. An exemplary application of the proposed method in the optimization design of the HFT illustrates a 98% reduction in computation time for thermal analysis during the optimization process. © 2025 IEEE.

关键词： Thermal modeling

来源：评论

学校读者我要写书评

暂无评论

A new quantum-inspired pattern based on Goldner-Harary graph for automated alzheimer’s disease detection

引用

Cognitive Neurodynamics 2025年第1期19卷 1-19页

作者： Sercek, Ilknur Sampathila, Niranjana Tasci, Irem Ekmekyapar, Tuba Tasci, Burak Barua, Prabal Datta Baygin, Mehmet Dogan, Sengul Tuncer, Turker Tan, Ru-San Acharya, U.R. Department of Digital Forensics Engineering College of Technology Firat University Elazig Turkey Department of Biomedical Engineering Manipal Academy of Higher Education Manipal India Department of Neurology School of Medicine Firat University Elazig 23119 Turkey Department of Neurology Malatya Training and Research Hospital Malatya 44000 Turkey Vocational School of Technical Sciences Firat University Elazig 23119 Turkey School of Business (Information System) University of Southern Queensland Toowoomba Australia Department of Computer Engineering College of Engineering Erzurum Technical University Erzurum Turkey Department of Cardiology National Heart Centre Singapore Singapore Singapore Duke-NUS Medical School Singapore Singapore School of Mathematics Physics and Computing University of Southern Queensland Springfield Australia

Alzheimer's disease (AD) is a common cause of dementia. We aimed to develop a computationally efficient yet accurate feature engineering model for AD detection based on electroencephalography (EEG) signal inputs. New method: We retrospectively analyzed the EEG records of 134 AD and 113 non-AD patients. To generate multilevel features, a multilevel discrete wavelet transform was used to decompose the input EEG-signals. We devised a novel quantum-inspired EEG-signal feature extraction function based on 7-distinct different subgraphs of the Goldner-Harary pattern (GHPat), and selectively assigned a specific subgraph, using a forward-forward distance-based fitness function, to each input EEG signal block for textural feature extraction. We extracted statistical features using standard statistical moments, which we then merged with the extracted textural features. Other model components were iterative neighborhood component analysis feature selection, standard shallow k-nearest neighbors, as well as iterative majority voting and greedy algorithm to generate additional voted prediction vectors and select the best overall model results. With leave-one-subject-out cross-validation (LOSO CV), our model attained 88.17% accuracy. Accuracy results stratified by channel lead placement and brain regions suggested P4 and the parietal region to be the most impactful. Comparison with existing methods: The proposed model outperforms existing methods by achieving higher accuracy with a computationally efficient quantum-inspired approach, ensuring robustness and generalizability. Cortex maps were generated that allowed visual correlation of channel-wise results with various brain regions, enhancing model explainability. © The Author(s) 2025.

关键词： Alzheimer’s disease Brain-computer interface EEG GHPat Goldner-Harary graph Signal classification

来源：评论

学校读者我要写书评

暂无评论

Small Signal Stability-Guaranteed Moving Target Defense Against Load Redistribution Attack On IoT-based Smart Grid

引用

IEEE Internet of Things Journal 2025年第11期12卷 17413-17429页

作者： Wang, Bingdong Zhang, Zhenyong Wang, Mufeng Liu, Mengxiang Ye, Rui Deng, Ruilong Zhang, Xin Guizhou University State Key Laboratory of Public Big Data College of Computer Science and Technology Guiyang550025 China China Industrial Control Systems Cyber Emergency Response Team Beijing100040 China University of Sheffield Department of Automatic Control and System Engineering Sheffield United Kingdom Guizhou Power Grid Co. Ltd. Intelligent Operation Center China Zhejiang University State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Hangzhou310027 China Huzhou Institute of Industrial Control Technology Huzhou313000 China

Moving target defense (MTD) is a promising approach to defend against load redistribution attacks on the internet-of-things (IoT)-based smart grid networks by probing the distorted state estimates with the distributed flexible AC transmission system. However, existing studies mainly focus on optimizing the performance of MTD and ignore the safety effect of it on the system’s operation. In this paper, we fill this gap by deeply analyzing the effect of MTD on the small signal stability and aim to alleviate the negative impact and guarantee its defending performance simultaneously. Firstly, the stability is formally described using the eigenvalue sensitivity. The relationship between the MTD-induced perturbation (MTDper) and the stability criteria is derived. Secondly, a new indicator is proposed to measure the effectiveness of MTDper. Thirdly, a constrained optimization problem is formulated to compute the bound of MTDper for guaranteeing the small signal stability. In addition, a surprising finding is that the stability margin can be improved and enhanced by optimizing the value of MTDper without losing the MTD’s effectiveness. Finally, we evaluate the performance of MTDper and its impact on the small signal stability with extensive simulations on the IEEE 30-bus, 39-bus, and 68-bus test power systems. © 2014 IEEE.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Resilient Cooperative Control of Multiple DC Microgrids With Interconnection Networks Against Cyber Attacks

IEEE Transactions on Industrial Cyber-Physical Systems

引用

IEEE Transactions on Industrial Cyber-Physical systems 2025年 3卷 116-126页

作者： Xiao, Feng Liu, Shiyu Wei, Bo Fang, Fang Qin, Jiahu North China Electric Power University State Key Laboratory of Alternate Electrical Power System with Renewable Energy Sources Beijing102206 China North China Electric Power University School of Control and Computer Engineering Beijing102206 China North China Electric Power University New Energy Generation National Engineering Research Center Beijing102206 China University of Science and Technology of China Department of Automation Hefei230027 China

The two control objectives of voltage regulation and precise current sharing are conflicting in multi-bus DC microgrids. In this paper, a distributed control strategy is proposed, and it can achieve accurate current sharing and regulate the voltage of a critical node to the rated value. However, such a distributed control system is susceptible to potential cyber attacks that could deteriorate microgrids performances by corrupting communication links or actuators. To overcome these difficulties, we design the interconnected communication networks to establish a resilient cooperative system of multiple microgrids against unknown bounded injection attacks. The proposed resilient control strategy can achieve the control objectives of maintaining voltage regulation and current sharing within each microgrids under different operating conditions, and the interconnected system consisting of multiple microgrids cooperates to mitigate the adverse effect of cyber attacks. The dynamics and stability of the overall close-loop system of the DC microgrids are analyzed, in the present or absent of cyber attacks. Simulation results validate the effectiveness of the proposed approach in two 4-bus DC microgrids. © 2023 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Cutting Skill Assessment by Motion Analysis Using Deep Learning and Spatial Marker Tracking

引用

IEEE Transactions on Biomedical engineering 2025年第6期72卷 1963-1972页

作者： Su, Bai-Quan Ma, Xu-Dong Li, Weihan Kuang, Zi-Ao Gong, Yi Wang, Gang Zhang, Qingqian Liu, Wenyong Li, Changsheng Gao, Li Wang, Junchen Beijing University of Posts and Telecommunications Medical Robotics Laboratory School of Automation Beijing100876 China University of Tokyo School of Mechanical Engineering Tokyo113-0033 Japan Beijing University of Posts and Telecommunications School of Computer Science Beijing100876 China Peking University General Surgery Department Beijing100191 China Beihang University Key Laboratory for Biomechanics and Mechanobiology of Chinese Education Ministry Beijing Advanced Innovation Centre for Biomedical Engineering School of Biological Science and Medical Engineering Beijing100083 China Beijing Institute of Technology School of Mechatronical Engineering Beijing100081 China Beijing Institute of Technology Beijing Advanced Innovation Center for Intelligent Robots and Systems Beijing100081 China Peking University Department of Periodontology National Stomatological Center School and Hospital of Stomatology National Clinical Research Center for Oral Diseases National Engineering Research Center of Oral Biomaterials and Digital Medical Devices Beijing100081 China Beihang University School of Mechanical Engineering and Automation Beijing100083 China

The assessment of surgical skill is crucial for indicating a surgeon's proficiency. While motion analysis of surgical tools is widely used in endoscopic surgery, it is not commonly applied to open surgery. Instead, open surgery skill assessment relies on observing the trajectory of surgical tools on tissue. This observation-based method often lacks clear standards, leading to inaccurate assessments. This paper presents a method for evaluating cutting skill in open surgery through scalpel motion analysis. A 3D multiple-facet ArUco code cube is designed, and a dataset of tip coordinate system poses for various scalpels in the ArUco code coordinate system (ACS) is established using the pivot calibration method. The YOLOv8 model and an image dataset of different scalpels are used to identify the scalpel type and select its tip position. The tip position is then transformed from ACS to a binocular camera coordinate system (BCS), representing the incision curve made by the scalpel. Five assessment metrics are proposed to quantify the surgeon's cutting skill: average incision curvature deviation, incision length difference, incision endpoint deviation, average incision deviation, and average cutting jerk. Experiments involving twenty expert and novice surgeons performing four common incisions (straight line, polyline, semicircle, and cross line) demonstrate the metrics' effectiveness. The metrics provide a clear, objective display of individual cutting skills, and a combined ranking reveals comparative skill levels. This study offers a precise method for evaluating surgeons' cutting skills with a scalpel in open surgery. © 1964-2012 IEEE.

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Advanced multi-nozzle electrohydrodynamic printing:mechanism,processing,and diverse applications at micro/nano-scale

引用

International Journal of Extreme Manufacturing 2025年第1期7卷 207-235页

作者： Yin Li Guangming Zhang Jinrun Zhang Daosen Song Chenxu Guo Wei Zhou Zhiguo Fu Xiaoyang Zhu Fei Wang Yongqing Duan Jingyan Dong Hongbo Lan Shandong Engineering Research Center for Additive Manufacturing Qingdao University of TechnologyQingdao 266520People’s Republic of China State Key Laboratory of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074People’s Republic of China Department of Industrial and System Engineering North Caroline State UniversityRaleighNC 27695United States of America

Electrohydrodynamic(EHD)jet printing represents a novel micro/nano-scale additive manufacturing process that utilises a high-voltage induced electric field between the nozzle and the substrate to print micro/nanoscale *** printing is particularly advantageous for the fabrication on flexible or non-flat substrates and of large aspect ratio micro/nanostructures and composite multi-material *** this,EHD printing has yet to be fully industrialised due to its low throughput,which is primarily caused by the limitations of serial additive printing *** parallel multi-nozzle array-based process has become the most promising option for EHD printing to achieve large-scale printing by increasing the number of nozzles to realise multichannel parallel *** paper reviews the recent development of multi-nozzle EHD printing technology,analyses jet motion with multi-nozzle,explains the origins of the electric field crosstalk effect under multi-nozzle and discusses several widely used methods for overcoming *** work also summarises the impact of different process parameters on multi-nozzle EHD printing and describes the current manufacturing process using multi-nozzle as well as the method by which they can be realised *** addition,it presents an additional significant utilisation of multi-nozzle printing aside from enhancing single-nozzle production efficiency,which is the production of composite phase change materials through ***,the future direction of multi-nozzle EHD printing development is discussed and envisioned.

关键词： electrohydrodynamic jetting crosstalk multi-nozzle nozzle array

来源：评论

学校读者我要写书评

暂无评论

YOLO-TCT: An Effective Network For Long-Tailed Cervical Cell Detection

YOLO-TCT: An Effective Network For Long-Tailed Cervical Cell...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Lv, Di Yi, Lin Liu, Li Chen, Yuze Chen, Xin Liu, Ran College of Computer Science Chongqing University Chongqing China Chongqing Key Laboratory of Translational Research for Cancer Metastasis and Individualized Treatment Chongqing University Cancer Hospital Chongqing China Department of Digital Medicine School of Biomedical Engineering and Medical Imaging Third Military Medical University Chongqing China

ISBN: (纸本)9798350368741

ÐThe Thinprep Cytologic Test (TCT) is a vital component in the early detection of cervical cancer. However, conventional manual screening methods are hindered by inefficiencies and high levels of subjectivity. This study presents YOLO-TCT, an enhanced YOLOv9 network designed for the automated detection of abnormal cervical cells in TCT smears. Our model features a novel detection head with an adaptive weighting mechanism and Hard Polarized Self Attention (HPSA) to improve the differentiation of subtle cell characteristics. Additionally, we enhance the network's ability to distinguish between foreground and background by incorporating a detection box quality factor into the classification loss function, and we introduce class parameters into the quality focal loss to address the class imbalance. Experimental evaluations on the CQTCT dataset reveal that YOLO-TCT achieves a mean Average Precision at IoU=0.5 (AP50) of 26.37% and a mean Average Recall (mAR) of 46.10%, with a significant improvement in recall rates for tail classes by over 26%. Notably, our model operates approximately five times faster than traditional R-CNN models while achieving superior precision and recall rates. These results underscore the effectiveness of our approach for real-time cervical cell detection in the context of long-tail distribution. The source code is accessible at https://***/threedteam/YOLO-TCT. © 2025 IEEE.

关键词： Biomedical Images Cervical Cell Detection Object Detection

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：