检索结果-内蒙古大学图书馆

21st IEEE International Symposium on Parallel and Distributed Processing with Applications, 13th IEEE International Conference on Big Data and Cloud Computing, 16th IEEE International Conference on Social Computing and Networking and 13th International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2023

作者： Qin, Sihang Gu, Xianjun Jun, Xing Li, Haitao Huang, Mengqi Dai, Weiqi Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China State Grid Wuhan Power Supply Company China

ISBN: (纸本)9798350329223

Federated learning, an emerging distributed learning framework, has gained prominence recently. However, two challenges arise when applying federated learning to medical data. The first challenge stems from the inability of model-generating nodes to ensure computational fairness. The second challenge involves the potential leakage of private information through gradient differences. This paper introduces a federated learning system that leverages Software Guard Extensions (SGX) and blockchain technology to enhance the fairness and security of federated learning for analyzing chest imaging data. The modeling of imaging factors for chest radiography data can effectively regulate the data quality of semi-trusted nodes. A blockchain smart contract is employed for data quality-aware proof, and the quality-aware block undergoes a two-stage rewriting process across distinct nodes. A notary membership model achieves notarized cluster consensus for imaging informatics data. The multi-channel layer model quantifies the distribution of computational workload across participating nodes within the medical consortium. Upon successful verification of the enclave command in the aggregation cycle, traceable and packaged signatures are generated to support computational fairness. To ensure robust information security, SGX remote authentication is used between downstream and upstream nodes. The federated learning system, built upon SGX and blockchain, has been implemented using the Fabric federated chain platform. The ResNet model underwent training through cross-sectional federated learning to effectively classify novel coronavirus lung medical image data. Following this, multiple experimental control and security analyses were conducted, revealing that the time loss incurred due to crossing channels is approximately 21.31%, while the time overhead of SGX remains within 5.2%, as allowed by the number of nodes. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Memristor-based in-situ convolutional strategy for accurate braille recognition

引用

science China Materials 2024年第12期67卷 3986-3993页

作者： Xianghong Zhang Congyao Qin Wenhong Peng Ningpu Qin Enping Cheng Jianxin Wu Yuyang Fan Qian Yang Huipeng Chen Institute of Optoelectronic Display National&Local United Engineering Lab of Flat Panel Display TechnologyFuzhou UniversityFuzhou 350002China Zhicheng College Fuzhou UniversityFuzhou 350002China Fujian Science&Technology Innovation Laboratory for Optoelectronic Information of China Fuzhou 350100China State Key Laboratory of ASIC and System School of MicroelectronicsFudan UniversityShanghai 200433China

Signal processing has entered the era of big data,and improving processing efficiency becomes *** computing architectures face computational efficiency limitations due to the separation of storage and *** circuits based on multi-conductor devices enable full hardware convolutional neural networks(CNNs),which hold great potential to improve computational ***,when processing large-scale convolutional computations,there is still a significant amount of device redundancy,resulting in low computational power consumption and high computational ***,we innovatively propose a memristor-based in-situ convolutional strategy,which uses the dynamic changes in the conductive wire,doping area,and polarization area of memristors as the process of convolutional operations,and uses the time required for conductance switching of a single device as the computation result,embodying convolutional computation through the unique spiked digital signal of the *** strategy reasonably encodes complex analog signals into simple digital signals through a memristor,completing the convolutional computation at the device level,which is essential for complex signal processing and computational efficiency *** on the implementation of device-level convolutional computing,we have achieved feature recognition and noise filtering for braille *** believe that our successful implementation of convolutional computing at the device level will promote the construction of complex CNNs with large-scale convolutional computing capabilities,bringing innovation and development to the field of neuromorphic computing.

关键词： convolutional computing multi-conductor memristor conductive filaments

来源：评论

学校读者我要写书评

暂无评论

Ingredient-Guided RGB-D Fusion Network for Nutritional Assessment

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 156-166页

作者： Feng, Zhihui Xiong, Hao Min, Weiqing Hou, Sujuan Duan, Huichuan Liu, Zhonghua Jiang, Shuqiang Shandong Normal University School of Information Science and Enginering Jinan250358 China Macquarie University Centre for Health Informatics Macquarie ParkNSW2109 Australia Chinese Academy of Sciences Key Laboratory of Intelligent Information Processing Institute of Computing Technology Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Zhejiang Ocean University School of Information Engineering Zhoushan316022 China

The nutritional value of agricultural products is an important indicator for evaluating their quality, which directly affects people's dietary choices and overall well-being. Nutritional assessment studies provide a scientific basis for the production, processing, and marketing of food by analyzing the nutrients they contain. Traditional methods often struggle with suboptimal accuracy and can be time consuming, as well as a shortage of professionals. The progress in artificial intelligence has revolutionized dietary health by offering more accessible methods for food nutritional assessment using vision-based approaches. However, existing vision-based methods using RGB images often face challenges due to varying lighting conditions, impacting the accuracy of nutritional assessment. An alternative is the RGB-D fusion method, which combines RGB images and depth maps. Yet, these methods typically rely on simple fusion techniques that do not ensure precise assessment. Additionally, current vision-based methods struggle to detect small components like oils and sugars on food surfaces, crucial for determining ingredient information and ensuring accurate nutritional assessment. In this pursuit, we propose a novel ingredient-guided RGB-D fusion network that integrates RGB images with depth maps and enables more reliable nutritional assessment guided by ingredient information. Specifically, the multifrequency bimodality fusion module is designed to leverage the correlation between the RGB image and the depth map within the frequency domain. Furthermore, the progressive-fusion module and ingredient-guided module leverage ingredient information to explore the potential correlation between ingredients and nutrients, thereby enhancing the guidance for nutritional assessment learning. We evaluate our approach on a variety of ablation settings on Nutrition5k, where it consistently outperforms state-of-the-art methods. © 2023 IEEE.

关键词： Medicinal chemistry

来源：评论

学校读者我要写书评

暂无评论

Cross-domain Monitoring of Underwater Targets Based on Q-learning for Heterogeneous Unmanned Vehicles 41

Cross-domain Monitoring of Underwater Targets Based on Q-lea...

引用

第41届中国控制会议

作者： Jingsheng Lin Jing Yan Xian Yang Xiaoyuan Luo Institute of Electrical Engineering Yanshan University Key Laboratory of Ocean Observation Technology Ministry of Natural Resources National Marine Technology Center Institute of Information Science and Engineering Yanshan University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

The timely detection of targets in uncharted territory,followed by tracking and monitoring of the targets are an important part of ocean monitoring *** cross-domain monitoring approach refers to the way of monitoring target in all directions in the sky and *** of the existing studies are based on collaborative monitoring within the same *** monitoring complements effectively the existing monitoring methods,which collects richer and more comprehensive *** this paper,the monitoring process is divided into two stages:target search and target *** underwater vehicle(AUV),unmanned surface vehicle(USV) and Unmanned aerial vehicle(UAV) are used as research objects of the collaborative algorithm in cross-domain *** cost function and status of each vehicle are *** collaborative target tracking algorithm is designed by *** effectiveness of the algorithm is verified by *** proves that the method used in this paper is feasible and can satisfy various constraints.

关键词： Cross-domain monitoring Q-learning cooperative path planning unmanned aerial vehicle unmanned surface vehicle autonomous underwater vehicle

来源：评论

学校读者我要写书评

暂无评论

Predictive Fuzzy Control Using Particle Swarm Optimization for Magnetic Levitation system 16th

Predictive Fuzzy Control Using Particle Swarm Optimization f...

引用

16th Annual Conference of China Electrotechnical Society, CES 2021

作者： Bu, Fanqi Xu, Jie College of National Key Laboratory of Science and Technology on Vessel Integrated Power System Naval University of Engineering Wuhan430033 China

ISBN: (纸本)9789811915277

The magnetic levitation system (MLS) has the characteristics of time-delay, open-loop unstable and non-linear. Considering the poor robustness and ability to tack ideal position of conventional algorithms, a predictive fuzzy proportional-integral-derivative (PID) with particle swarm optimization (PSO-PFPID) controller was proposed. With the recursive least squares (RLS) algorithm, a controlled auto-regressive integrated moving-average (CARIMA) model is identified on line and it serves for the predictive model of the generalized predictive control (GPC). Then the predicted optimal control law in the future time is served as the input of fuzzy PID (FPID). To enhance the dynamic and steady performance of the predictive fuzzy PID (PFPID) controller at the same time, the softening coefficient α and forgetting factor μ of the PFPID controller are globally optimized offline with the particle swarm optimization (PSO) algorithm. Finally, the maglev ball system is employed as the controlled object of the simulation and experiment and the mathematical model in balance points at the equilibrium point. Compared with PID, cascade GPC PID(PPID), simple PFPID, the PSO-PFPID controller has better robustness and make the controlled object stable in the case of mismatch. It can effectively adapt to system parameters changes. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

Q-learning Based Obstacle Avoidance Control of Autonomous Underwater Vehicle with Binocular Vision 41

Q-learning Based Obstacle Avoidance Control of Autonomous Un...

引用

第41届中国控制会议

作者： Liang Zhang Jing Yan Xian Yang Xiaoyuan Luo Institute of Electrical Engineering Yanshan University Key Laboratory of Ocean Observation Technology Ministry of Natural ResourcesNational Marine Technology Center Institute of Information Science and Engineering Yanshan University

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Autonomous Underwater Vehicle(AUV) is widely used in various marine tasks,in which the autonomous obstacle avoidance function is the key technology to achieve autonomous motion such as path planning and trajectory *** obstacle avoidance requires AUV to effectively detect obstacle information and select the optimal control strategy through autonomous judgment to achieve the obstacle avoidance *** the ocean environment is very complex,full of uncertainty and danger,the underwater information obtained by using acoustic detection technology is very limited,which makes the control of underwater robot very *** address this problem,this paper proposes a method for obstacle avoidance by binocular visual parallax control(BVPC) *** addition,the motion control of the robot is realized by Q learning(QL).In particular,the control strategy can be applied to different underwater unknown scenarios instead of a specific one,improving the wide applicability of this control ***,the effectiveness of the proposed scheme is verified by simulation.

关键词： Autonomous underwater vehicle(AUV) Q-learning Binocular parallax obstacle avoidance control

来源：评论

学校读者我要写书评

暂无评论

Pose Knowledge distill guidance: Effective Pose guide learning for Person Re-Identification

Pose Knowledge distill guidance: Effective Pose guide learni...

引用

2024 International Workshop on Artificial Intelligence for Signal, Image Processing and Multimedia, AI-SIPM 2024

作者： Trinh, Quoc-Huy Thi, Phuoc-Thao Vo Tran, Minh-Triet Nguyen, Hai-Dang Faculty of Information Technology University of Science VNU-HCM Ho Chi Minh Viet Nam University of Science VNU-HCM Ho Chi Minh Viet Nam Software Engineering Laboratory University of Science VNU-HCM Ho Chi Minh Viet Nam

ISBN: (纸本)9798400705489

The robust human representation embedding is the key challenge of the person-identification task. Although the previous methods achieve competitive results, they still depend on the appearance feature which can be failed in the pedestrian surveillance camera due to the changing of the human's appearance. To overcome this limitation, we introduce Pose Knowledge distill guidance, an effective pose guide learning for the Person Re-Identification framework that leverages pose knowledge guidance through Knowledge distillation to yield more generalized feature embeddings. Because of the significance of human pose in distinguishing individuals, apart from the appearance knowledge, our framework also guides the model to learn the pose information, consequently reducing the overreliance on the appearance of the human and thereby enhancing the model's robustness. Furthermore, the pose knowledge guides transfer the pose knowledge to the Re-Identification model without no increasing the computation cost for the backbone. Through our framework, the re-identification model demonstrates competitive performance, as evidenced by its state-of-the-art results on two datasets: Market-1501 and CuHK03. These results attest to the effectiveness of our approach. © 2024 ACM.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Sailfish Optimization with Deep Learning Based Oral Cancer Classification Model

引用

Computer systems science & engineering 2023年第4期45卷 753-767页

作者： Mesfer Al Duhayyim Areej A.Malibari Sami Dhahbi Mohamed K.Nour Isra Al-Turaiki Marwa Obayya Abdullah Mohamed Department of Computer Science College of Sciences and Humanities-AflajPrince Sattam bin Abdulaziz UniversityAl-Kharj16278Saudi Arabia Department of Industrial and Systems Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Department of Computer Science College of Science&Art at MahayilKing Khalid UniversityAbha62529Saudi Arabia Department of Computer Science College of Computing and Information SystemUmm Al-Qura UniversityMecca24382Saudi Arabia Department of Information Technology College of Computer and Information SciencesKing Saud UniversityRiyadh4545Saudi Arabia Department of Biomedical Engineering College of EngineeringPrincess Nourah bint Abdulrahman UniversityRiyadh11671Saudi Arabia Research Centre Future University in EgyptNew Cairo11845Egypt

Recently,computer aided diagnosis(CAD)model becomes an effective tool for decision making in healthcare *** advances in computer vision and artificial intelligence(AI)techniques have resulted in the effective design of CAD models,which enables to detection of the existence of diseases using various imaging *** cancer(OC)has commonly occurred in head and neck *** identification of OC enables to improve survival rate and reduce mortality ***,the design of CAD model for OC detection and classification becomes ***,this study introduces a novel Computer Aided Diagnosis for OC using Sailfish Optimization with Fusion based Classification(CADOC-SFOFC)*** proposed CADOC-SFOFC model determines the existence of OC on the medical *** accomplish this,a fusion based feature extraction process is carried out by the use of VGGNet-16 and Residual Network(ResNet)***,feature vectors are fused and passed into the extreme learning machine(ELM)model for classification ***,SFO algorithm is utilized for effective parameter selection of the ELM model,consequently resulting in enhanced *** experimental analysis of the CADOC-SFOFC model was tested on Kaggle dataset and the results reported the betterment of the CADOC-SFOFC model over the compared methods with maximum accuracy of 98.11%.Therefore,the CADOC-SFOFC model has maximum potential as an inexpensive and non-invasive tool which supports screening process and enhances the detection efficiency.

关键词： Oral cancer computer aided diagnosis deep learning fusion model seagull optimization classification

来源：评论

学校读者我要写书评

暂无评论

Research on Blockchain-based Access Control technology for Medical Data 4

Research on Blockchain-based Access Control Technology for M...

引用

4th International Conference on Blockchain technology and information Security, ICBCTIS 2024

作者： Li, Yan Zhang, Guofeng Feng, Bin Yang, Shihao Zhao, Chuan Wang, Peng Shen, Cong Zhang, Yanan School of Information Science and Engineering University of Jinan Shandong Jinan250022 China School of Information Science and Technology Taishan University Shandong Taian271000 China Shandong Provincial Key Laboratory of Network-based Intelligent Computing Shandong Jinan250022 China College of Electronic Information Shandong Xiandai University Shandong Jinan250104 China

ISBN: (纸本)9798331528324

Medical data sharing can provide secure, trust-worthy and high-quality health care services to a wide range of patients and healthcare providers, but the data sharing process faces the risk of identity and information security leakage. This study begins by examining access control technologies for health data sharing, emphasizing the analysis of blockchain-based solutions for securing various types of medical data. It reviews and assesses the current state of these technologies across four dimensions-attributes, signatures, roles, and multi-smart contracts-and further develops a blockchain-based system for controlling access to medical data. Finally, it summarizes and analyzes the challenges faced by medical data sharing, and provides an outlook on the future development of the technology. This study is of great sig- nificance in guiding the deep integration of blockchain technology and medical digitization, and guaranteeing the secu-rity of medical data throughout its life cycle. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

On-chip terahertz orbital angular momentum demultiplexer

引用

Photonics Research 2024年第5期12卷 1044-1054页

作者： XIAOHAN JIANG WANYING LIU QUAN XU YUANHAO LANG YIKAI FU FAN HUANG HAITAO DAI YANFENG LI XUEQIAN ZHANG JIANQIANG GU JIAGUANG HAN WEILI ZHANG Center for Terahertz Waves College of Precision Instrument and Optoelectronics Engineeringand Key Laboratory of Optoelectronics Information and Technology(Ministry of Education)Tianjin UniversityTianjin 300072China Tianjin Key Laboratory of Low Dimensional Materials Physics and Preparing Technology School of ScienceTianjin UniversityTianjin 300072China Guangxi Key Laboratory of Optoelectronic Information Processing School of Optoelectronic EngineeringGuilin University of Electronic TechnologyGuilin 541004China School of Electrical and Computer Engineering Oklahoma State UniversityStillwaterOklahoma 74078USA

The terahertz regime is widely recognized as a fundamental domain with significant potential to address the demands of next-generation wireless *** parallel,mode division multiplexing based on orbital angular momentum(OAM)shows promise in enhancing bandwidth utilization,thereby expanding the overall communication channel *** this study,we present both theoretical and experimental demonstrations of an on-chip terahertz OAM *** device effectively couples and steers seven incident terahertz vortex beams into distinct high-quality focusing surface plasmonic beams,and the focusing directions can be arbitrarily *** proposed design strategy integrates space-to-chip mode conversion,OAM recognition,and on-chip routing in a compact space with subwavelength thickness,exhibiting versatility and superior performance.

关键词： demultiplexer momentum angular

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：