2022 IEEE 8th International Conference on Computer and Communications (ICCC)最新文献_第10页

Research and Implementation of Asynchronous Transmission and Update Strategy for Federated Learning 面向联邦学习的异步传输与更新策略研究与实现

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065902

Yudong Jia, Ningbo Zhang

{"title":"Research and Implementation of Asynchronous Transmission and Update Strategy for Federated Learning","authors":"Yudong Jia, Ningbo Zhang","doi":"10.1109/ICCC56324.2022.10065902","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065902","url":null,"abstract":"In today's era, there is a growing concern about data privacy and security. Data is the foundation of machine learning, and due to the complexity of the reality, data often exists in silos. The great development of computing and storage capacity of edge devices has made it possible to train machine learning models on edge devices with data. Federated learning is a special kind of distributed machine learning in which multiple distributed clients use local data to train a model and upload the resulting model parameters to a central server for aggregation and iteration to finally obtain a global model with good generalization performance. The interaction between the clients and the server is model parameters rather than the data itself, which effectively protects data privacy and security. After research, it is found that Federated Learning is mainly divided into two aggregation models: synchronous aggregation and asynchronous aggregation. In this paper, the classical FedAvg synchronous federated average aggregation algorithm is analyzed. The central server needs to wait for all participating nodes to be trained before aggregating and updating the model, which is inconvenient to achieve global synchronization on resource heterogeneous clients. To improve the utilization of computational resources, FedAsync, an asynchronous federated learning aggregation mechanism with a receivable window based on dual weights, which are data volume size weight and staleness weight, is proposed. And FedAvg and FedAsync are tested and analyzed. Based on this, the impact on federated learning due to asynchronous data arrival rate and limited communication resources is further explored.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129072251","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Towards Development of a Novel DevOps Platform for Ultra-Large-Scale Commercial Applications: Part 1- System Design 面向超大规模商业应用的新型DevOps平台的开发:第一部分-系统设计

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065670

Mengxia Chen, Jiangang Tong, Lanying Shi, Man Li, Wensheng Yao, Huan Liang

引用次数: 0

Ultrafast Ultrasound Speckle Tracking Using the Dynamical Kernels for Improved Blood Flow Velocity Profiling 利用动态核改进血流速度谱的超快超声斑点跟踪

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065614

Yue Zhang, Bingbing He, Yufeng Zhang, Zhiyao Li, Xun Lang, Junhua Zhang

{"title":"Ultrafast Ultrasound Speckle Tracking Using the Dynamical Kernels for Improved Blood Flow Velocity Profiling","authors":"Yue Zhang, Bingbing He, Yufeng Zhang, Zhiyao Li, Xun Lang, Junhua Zhang","doi":"10.1109/ICCC56324.2022.10065614","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065614","url":null,"abstract":"The accurate measurement of blood flow velocities is of great importance for the prevention, early diagnosis, and course monitoring of atherosclerosis. Unlike the conventional speckle tracking using the pre-defined kernels (STPK), an improved speckle tracking using the dynamical kernels (STDK) based on ultrafast ultrasound is proposed to improve the accuracy and efficiency of the blood flow velocity profile (BFVP) estimation in this work. The novelty of this study is that the coordinate of the current tracked kernel in the reference frame is dynamically adjusted according to the coordinate of the best matching of the last tracked kernel in the comparison frame. This modification is not only fault-tolerant to a certain degree for speckle decorrelation, but also reduces the time consumption produced by traversing the whole search regions. The performance of the proposed STDK was validated via simulations. Compared with the STPK-based results, the NRMSE and acquisition time of the STDK-based results decrease by 48.39% and 36.8% on average, respectively. Therefore, the proposed STDK method has been proven to improve the accuracy, efficiency of the BFVP estimation, which is helpful for clinical diagnosis and treatment of related diseases.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133964444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Self-Attention Based SRGAN for Super-Resolution of Astronomical Image 基于自关注的天文图像超分辨率SRGAN

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065737

Wanjun Li, Zhe Liu, Hongtao Deng

引用次数: 0

A Distributed Positioning Scheme Based on Neural Network for Radiation Source 基于神经网络的辐射源分布式定位方案

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065926

Jiawen Yin, Guomei Zhang, Yue Li, Guobing Li

{"title":"A Distributed Positioning Scheme Based on Neural Network for Radiation Source","authors":"Jiawen Yin, Guomei Zhang, Yue Li, Guobing Li","doi":"10.1109/ICCC56324.2022.10065926","DOIUrl":"https://doi.org/10.1109/ICCC56324.2022.10065926","url":null,"abstract":"To avoid the high calculating requirement of the central node in the centralized positioning system, a distributed scheme with multiple localization sub-networks to localize an unknown radiation source (RS) is discussed in this paper. Furthermore, in order to reduce the adverse effect of the potential information loss in the parameter estimation of the traditional two-step localization algorithm, a neural network to deduce the objective position from the hybrid localization parameters is designed for each sub-network to replace the solving of positioning equations involved in the two-step localizer. Finally, in order to obtain more accurate localization results, two fusion methods based on the weighted sum and the neural network are given at the final control center to fuse the localization results of all the sub-networks. The experimental results show that the proposed scheme significantly outperforms the traditional single-parameter based two-step localization method even though the latter one adopts the centralized positioning strategy. Furthermore, the neural network based fusion method can improve the final positioning precision obviously for signal to noise ratio (SNR) higher than 10dB.","PeriodicalId":263098,"journal":{"name":"2022 IEEE 8th International Conference on Computer and Communications (ICCC)","volume":"131 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122452707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Sorting and Power Allocation-Based THP Precoding Algorithm in VLC System VLC系统中基于排序和功率分配的THP预编码算法

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065730

Furong Zhu, Liwei Yang, Wencong Lai, Junning Zhang, Xue Liang, Yanling Cai

引用次数: 0

Networking Architecture and Key Technologies of Flat Security and Stability Control System 平面安全稳定控制系统的组网结构及关键技术

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065962

Kaiqiang Gao, Huixia Ding, Yanan Wang, Geng Zhang, Wei Han, Xuerang Guo, Wenyan Duan

引用次数: 0

Enhancing Spatially Coupled Serially Concatenated Codes via Multidimensional Coupling 通过多维耦合增强空间耦合串行级联码

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065783

Feng Wang, Chaojie Yang, H. Du, Shancheng Zhao

引用次数: 1

Multi-scale Convolution Transformer for Human Activity Detection 用于人体活动检测的多尺度卷积变压器

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10065954

Dejun Gao, Lei Wang

引用次数: 1

Fountain Codes with Superposition Feedback 带有叠加反馈的喷泉代码

2022 IEEE 8th International Conference on Computer and Communications (ICCC) Pub Date : 2022-12-09 DOI: 10.1109/ICCC56324.2022.10066046

Dai Jia, Junli Jia

引用次数: 0