检索结果-内蒙古大学图书馆

Gradient sparsification for efficient wireless federated learning with differential privacy

science China(Information sciences) 2024年第4期67卷 272-288页

作者： Kang WEI Jun LI Chuan MA Ming DING Feng SHU Haitao ZHAO Wen CHEN Hongbo ZHU School of Electronic and Optical Engineering Nanjing University of Science and Technology Zhejiang Lab Key Laboratory of Computer Network and Information Integration(Southeast University) Ministry of Education Data61 Commonwealth Scientific and Industrial Research Organisation School of Information and Communication Engineering Hainan University School of Communications and Information Engineering Nanjing University of Posts and Telecommunications School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University

Federated learning(FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers from the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to the limited transmission bandwidth and model performance degradation while using differential privacy(DP)protection. In this paper, we propose a gradient sparsification empowered FL framework with DP over wireless channels, to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client's local model, thereby mitigating the performance degradation induced by DP and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client's DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real-life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin, and delay-minimization algorithms.

关键词： federated learning differential privacy gradient sparsification Lyapunov drift convergence analysis

来源：评论

学校读者我要写书评

暂无评论

Impact of exposure time and power intensity on cell viability in 3D bioprinting 12

Impact of exposure time and power intensity on cell viabilit...

引用

Laser 3D Manufacturing XII 2025

作者： Tavares-Negrete, Jorge A. Babayigit, Ceren Boyraz, Ozdal Esfandyarpour, Rahim Laboratory for Integrated Nano Bio Electronics Innovation The Henry Samueli School of Engineering University of California IrvineCA92697 United States Department of Biomedical Engineering The University of California IrvineCA92697 United States Department of Electrical Engineering and Computer Science The University of California IrvineCA92697 United States Department of Mechanical and Aerospace Engineering The University of California IrvineCA92697 United States Henry Samueli School of Engineering University of California IrvineCA92697 United States

ISBN: (纸本)9781510684560

In 3D bioprinting, the photopolymerization of bioinks is a critical step in building desired structures with high precision. The chosen parameters, such as exposure time and light intensity during photopolymerization of the bioinks, significantly influence the resolution, cell viability, and proliferation of the bioprinted constructs. This study investigates how varying exposure times (10-30 s) and light intensities (0.04-0.11 mW/mm^2) in a laser-based bioprinter affect the performance of 3T3 fibroblasts embedded in GelMA bioinks. The metabolic activity and cell morphology of the bioprinted constructs were assessed over a week-long culture period. The findings reveal a clear relationship between longer exposure times and reduced cell viability. On day 7, samples exposed for extended periods exhibited the lowest metabolic activity, with differences of around 40% between treatments. In contrast, samples exposed to different light intensities resulted in variations below 15% in metabolic activity. GelMA bioinks exhibited less favorable outcomes under prolonged exposure, with cells displaying more rounded and less proliferative morphologies. In contrast, lower exposure times promoted more elongated cell shapes and network formation. These results highlight the importance of optimizing exposure time and light intensity to preserve cell wellness in 3D bioprinted constructs. © 2025 SPIE.

关键词： Cell culture

来源：评论

学校读者我要写书评

暂无评论

Spectrally-Efficient Beamforming Design for STAR-RIS-Aided URLLC NOMA Systems

引用

IEEE Transactions on Communications 2024年第7期72卷 4414-4431页

作者： Katwe, Mayur Vitthalrao Deshpande, Rasika Singh, Keshav Pan, Cunhua Ghare, Pradnya H. Duong, Trung Q. National Institute of Technology Raipur Department of Electronics and Communication Engineering Chattisgarh Raipur492010 India Institute of Communications Engineering National Sun Yat-sen University Kaohsiung804201 Taiwan Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Visvesvaraya National Institute of Technology Department of Electronics and Communication Engineering Nagpur440027 India Memorial University of Newfoundland Faculty of Engineering and Applied Science St. John'sNLA1B 3X5 Canada Queen's University Belfast School of Electronics Electrical Engineering and Computer Science BelfastBT7 1NN United Kingdom

Next-generation wireless applications are expected to enable extended ultra-reliable low-latency communication (URLLC) to support high data rates along with ultra-reliability and low-latency features beyond the capabilities of existing core services. There is a need to transition from conventional architectures to more efficient and robust multiple-access schemes to meet these consolidated requirements in resource-constrained systems. This study explores the utilization of simultaneous transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) in non-orthogonal multiple access (NOMA) systems to enable spectrally efficient URLLC, even under the imperfect channel state information. In particular, we focus on maximizing spectral efficiency by jointly designing robust beamforming at the base station and STAR-RIS subject to given URLLC requirements. Due to the non-convexity of the formulated problem, we propose an alternating optimization framework that obtains sub-optimal solutions to the problems of beamforming design at the BS and STAR-RIS, respectively by exploiting S-procedure and successive convex approximation. Simulation results confirm that the STAR-RIS-NOMA system can significantly boost the spectral efficiency by 10-15% compared to conventional reflecting-only RIS while guaranteeing the strict URLLC requirements. Specifically, among all the possible modes of STAR-RIS, the time-splitting mode provides better spectral efficiency than other modes owing to its better interference management. 0090-6778 © 2024 IEEE.

关键词： Beamforming

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Radiomics Analysis for Prostate Cancer Detection Harnessing Machine and Deep Learning Models 22

Large-Scale Radiomics Analysis for Prostate Cancer Detection...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Mylona, Eugenia Zaridis, Dimitrios I. Kalantzopoulos, Charalampos N. Pezoulas, Vasileios C. Tachos, Nikolaos S. Matsopoulos, George K. Regge, Daniele Papanikolaou, Nikolaos Tsiknakis, Manolis Marias, Kostas Fotiadis, Dimitrios I. Biomedical Research Institute Forth IoanninaGR 45110 Greece University of Ioannina Unit of Medical Technology Intelligent Information Systems Greece School of Electrical & Computer Engineering National Technical University of Athens Biomedical Engineering Laboratory Athens15780 Greece Candiolo Cancer Institute FPO-IRCCS Department of Radiology Strada Provinciale Candiolo Turin10060 Italy Champalimaud Foundation Computational Clinical Imaging Group Portugal Institute of Computer Science Forth Computational Biomedicine Laboratory HeraklionGR 70013 Greece Hellenic Mediterranean University Department of Electrical and Computer Engineering HeraklionGR 71004 Greece

ISBN: (纸本)9798331520526

Prostate cancer (PCa) is the second most common cancer in men, making early detection crucial for effective treatment. This study explores the efficacy of machine learning (ML) and deep learning (DL) models in detecting PCa lesions using radiomics features derived from multiparametric MRI data. Leveraging a dataset of 7621 retrospective and 2132 prospective cases from 12 clinical centers across Europe, we compared the performance of various ML (LASSO, Random Forest, SVM, XGBoost) and DL models (CNN, MLP, Transformer, CNN&MLP). Radiomic features were extracted and refined through a robust feature selection process. Models' performance was evaluated through nested cross-validation (CV) and externally. The CNN&MLP model achieved the highest ROC AUC (0.86) and PR AUC (0.90) in CV, while LASSO showed consistent generalization in external validation. Our findings indicate that DL models excel in high-dimensional data analysis but face challenges in generalizing to external datasets, highlighting the importance of external validation for clinical applicability. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Three-dimensional reconstruction of mobile binocular stereo vision based on push-broom line structured light for a workpiece surface

引用

Journal of the Optical Society of America A: Optics and Image science, and vision 2023年第11期40卷 2096-2107页

作者： Wang, Yue Han, Xueyou Rui, Jing Zhang, Hailan Yin, Lei Zhang, Xuefeng Wang, Xiangjun School of Computer Science and Technology Anhui University of Technology Maanshan China Anhui Engineering Research Center for Intelligent Applications and Security of Industrial Internet Anhui University of Technology Maanshan243032 China School of Electrical and Information Engineering Anhui University of Technology Maanshan China The 53th Research Institute of China Electronics Technology Group Corporation Tianjin China State Key Laboratory of Precision Measuring Technology and Instruments Tianjin University Tianjin China Key Laboratory ofMOEMS of the Ministry of Education Tianjin University Tianjin China

Stereo vision technology based on line structured light can effectively solve the problem of a three-dimensional (3D) reconstruction of a smooth surface. A method for 3D reconstruction of mobile binocular stereo vision based on push-broom line structured light for a workpiece surface is presented in this paper. The subpixel coordinates of the light strip centers of the line structured light are obtained by the Steger algorithm while the binocular module moves along the guide rail, and the polar constraint is used to achieve the matching of the extracted light strip centers. As a result, the3Dcoordinates of the light strip centers in each location can be calculated because of the known interior and external parameters of the binocular module. To obtain the 3D point cloud data of the entire surface, a relative pose optimization method with respect to the initial frame is proposed, which accurately estimates the pose of the cameras in each location with respect to that in the initial location and unifies the 3D coordinates of the light strip centers in each location to the datum coordinates. The relative pose optimization method first estimates the rough values by using the direct linear transform method, and then iteratively calculates the refined solutions based on the principle of minimizing the re-projection errors. Simulation data and substantial experimental results validate the effectiveness of our method. Our method is compared to the direct linear transform method and the frame-by-frame transfer method, and the root mean square error (RMSE) of the distance from 3D point cloud to fitted plane is used to evaluate the 3D reconstruction accuracy. The repeatability experiment shows that the RMSE fromour method is as lowas 0.83mm. © 2023 Optica Publishing Group.

关键词： Location

来源：评论

学校读者我要写书评

暂无评论

What limits limits?

引用

National science Review 2021年第1期8卷 11-14页

作者： Yong-Chun Liu Kun Huang Yun-Feng Xiao Lan Yang Cheng-Wei Qiu State Key Laboratory of Low-Dimensional Quantum Physics Department of Physics Frontier Science Center for Quantum Information Tsinghua University Department of Optics and Optical Engineering University of Science and Technology of China State Key Laboratory for Mesoscopic Physics and Frontiers Science Center for Nano-optoelectronics School of Physics Peking University Department of Electrical and Systems Engineering Washington University Department of Electrical and Computer Engineering National University of Singapore

There are fundamental rules and principles setting the limits of physical systems. It triggers an interesting thought—can we break the limits under specific circumstances? A realistic system can only provide limited functionalities because its performance is physically constrained by some fundamental principles.‘Breaking the limit’, which usually implies that the capability of a system could be enhanced significantly,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of digital twin technology in mining machinery education

引用

International Journal of Mechanical engineering Education 2025年

作者： Su, Chang Huang, Hao Wei, Zhongliang Xu, Naizhong State Key Laboratory of Mining Response and Disaster Prevention and Control in Deep Coal Mine Anhui University of Science and Technology Huainan China School of Mechanical and Electrical Engineering Anhui University of Science and Technology Huainan China School of Computer Science and Engineering Anhui University of Science and Technology Huainan China School of Miningand Engineering Anhui University of Science and Technology Huainan China

This paper investigates the application of digital twin technology in the teaching of mining machinery. Digital twin technology, an innovative approach that has significantly transformed engineering education and practice, creates dynamic digital replicas of physical entities in virtual environments. This allows for the simulation, prediction, and optimization of system performance without the need for physical intervention. In mechanical engineering education, digital twins provide students with real-time, interactive learning experiences, enabling a more intuitive understanding of complex mechanical structures. Students can conduct experiments and make modifications within a virtual setting, enhancing both learning efficiency and reducing experimental costs. Furthermore, this technology offers a scalable and replicable model for the future of engineering education. © The Author(s) 2025.

关键词： Virtual environments

来源：评论

学校读者我要写书评

暂无评论

Open-World Semi-Supervised Learning for Node Classification

Open-World Semi-Supervised Learning for Node Classification

引用

International Conference on Data engineering

作者： Yanling Wang Jing Zhang Lingxi Zhang Lixin Liu Yuxiao Dong Cuiping Li Hong Chen Hongzhi Yin School of Information Renmin University of China Zhongguancun Laboratory Alibaba Group Department of Computer Science and Technology Tsinghua University School of Information Technology and Electrical Engineering The University of Queensland

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

Open-world semi-supervised learning (Open-world SSL) for node classification, that classifies unlabeled nodes into seen classes or multiple novel classes, is a practical but under-explored problem in the graph community. As only seen classes have human labels, they are usually better learned than novel classes, and thus exhibit smaller intra-class variances within the embedding space (named as imbalance of intra-class variances between seen and novel classes). Based on empirical and theoretical analysis, we find the variance imbalance can negatively impact the model performance. Pre-trained feature encoders can alleviate this issue via producing compact representations for novel classes. However, creating general pre-trained encoders for various types of graph data has been proven to be challenging. As such, there is a demand for an effective method that does not rely on pre-trained graph encoders. In this paper, we propose an IMbalance-A ware method named OpenIMA for Open-world semi-supervised node classification, which trains the node classification model from scratch via contrastive learning with bias-reduced pseudo labels. Extensive experiments on seven popular graph benchmarks demonstrate the effectiveness of OpenIMA, and the source code has been available on GitHub 1 1 https://***/RUCKBReasoning/OpenIMA.

关键词： Analytical models Source coding Contrastive learning Semisupervised learning Benchmark testing Data engineering

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classification

arXiv

引用

arXiv 2025年

作者： Yang, Wennuo Wu, Shiling Zhou, Yuzhi Luo, Cheng He, Xilin Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China HBUG Lab University of Exeter United Kingdom

Multivariate Time Series Classification (MTSC) enables the analysis if complex temporal data, and thus serves as a cornerstone in various real-world applications, ranging from healthcare to finance. Since the relationship among variables in MTS usually contain crucial cues, a large number of graph-based MTSC approaches have been proposed, as the graph topology and edges can explicitly represent relationships among variables (channels), where not only various MTS graph representation learning strategies but also different Graph Neural Networks (GNNs) have been explored. Despite such progresses, there is no comprehensive study that fairly benchmarks and investigates the performances of existing widely-used graph representation learning strategies/GNN classifiers in the application of different MTSC tasks. In this paper, we present the first benchmark which systematically investigates the effectiveness of the widely-used three node feature definition strategies, four edge feature learning strategies and five GNN architecture, resulting in 60 different variants for graph-based MTSC. These variants are developed and evaluated with a standardized data pipeline and training/validation/testing strategy on 26 widely-used suspensor MTSC datasets. Our experiments highlight that node features significantly influence MTSC performance, while the visualization of edge features illustrates why adaptive edge learning outperforms other edge feature learning methods. The code of the proposed benchmark is publicly available at https://***/CVI-yangwn/*** Codes 68T10 © 2025, CC BY.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

ECG abnormality detection Based on Multi-domain combination features and LSTM 4

ECG abnormality detection Based on Multi-domain combination ...

引用

4th International Conference on computer engineering and Application, ICCEA 2023

作者： Liu, Qingshan Gao, Cuiyun Zhao, Yang Huang, Songqun Zhang, Yuqing Lu, Zhonghai Anhui Jianzhu University Power Quality Analysis and Load Detection Technology Laboratory Hefei China Second Military Medical University Department of Cardiovasology Changhai Hospital Shanghai China Kth Royal Institute of Technology School of Electrical Engineering and Computer Science Stockholm Sweden

ISBN: (纸本)9798350347548

Most scholars use fixed-length sample to ECG abnormalities based on MIT-BIH dataset, which lead to information loss. To address this problem, this paper proposes a method for ECG abnormality detection based on TSH-L method. The TSH-L method include:(1) Use the 3R ECG sample selection method to select ECG samples.(2) Extract multi-domain combination features including time-domain features, frequency domain features and time-frequency domain features.(3) LSTM is used for classification, and the algorithm is trained and tested based on the MIT-BIH dataset, obtain relatively optimal features as spliced normalized fusion features including kurtosis, skewness and RR interval time domain features, STFT-based sub-band spectrum features, and harmonic ratio features. Experiments show that: TSH-L method proposed in the paper has a high accuracy of 97.74% for the detection of ECG abnormalities of MIT-BIH dataset. The method 3R-TSH-L proposed in this paper is expected to be widely used in family-oriented healthcare. © 2023 IEEE.

关键词： Electrocardiograms

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：