Proceedings of the 5th International Conference on Computer Science and Application Engineering最新文献_第8页

Real-Time Entity Resolution by Forest-Based Indexing in Database Systems with Vertical Fragmentations 垂直碎片数据库系统中基于森林索引的实时实体解析

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487142

Liang Zhu, Jiapeng Yang, Xin Song, Yu Wang, Yonggang Wei

引用次数: 0

Research on Mixed-Precision Quantization and Fault-Tolerant of Deep Neural Networks 深度神经网络混合精度量化与容错研究

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487135

Zhaoxin Wang, Jing Wang, Kun Qian

{"title":"Research on Mixed-Precision Quantization and Fault-Tolerant of Deep Neural Networks","authors":"Zhaoxin Wang, Jing Wang, Kun Qian","doi":"10.1145/3487075.3487135","DOIUrl":"https://doi.org/10.1145/3487075.3487135","url":null,"abstract":"As deep neural networks become more and more common in mission-critical applications, such as smart medical care, drones, and autonomous driving, ensuring their reliable operation becomes critical. The data in the hardware memory is susceptible to bit-flip due to external factors, which leads to a decrease in the inference accuracy of the deep neural network deployed on the hardware. We solve this problem from the perspective of the deep neural network itself, We use a reinforcement learning algorithm to search for the optimal bit width for the weights of each layer of the deep neural network. According to this bit width strategy, the deep neural network is quantified, which maximizes the limitation of data fluctuations caused by bit-flip and improves the fault-tolerance of the neural network. The fault-tolerance of the network model compared with the original model, the solution proposed in this paper improves the fault-tolerance of LeNet5 model by 8.5x , the fault tolerance of MobileNetV2 model by 15.6x , the fault tolerance of VGG16 model by 14.5x , and the accuracy decreases negligibly.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131736504","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 Breast Cancer Patients’ Survival Prediction Model Using mRMR Feature Selection with Artificial Neural Network 基于人工神经网络mRMR特征选择的乳腺癌患者生存预测模型

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487131

W. Xing, Kangping Wang, Hui Sun, Yan Wang

引用次数: 0

The Finger Flexion Related Feature Extraction Method Based on Wavelet Time-Frequency Analysis in ECoG Signals 基于小波时频分析的手指屈曲相关特征提取方法

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487099

Haokun Shi, Pengfei Yu, Haiyan Li

{"title":"The Finger Flexion Related Feature Extraction Method Based on Wavelet Time-Frequency Analysis in ECoG Signals","authors":"Haokun Shi, Pengfei Yu, Haiyan Li","doi":"10.1145/3487075.3487099","DOIUrl":"https://doi.org/10.1145/3487075.3487099","url":null,"abstract":"In the brain-computer interface system, the feature extraction of brain signals is a crucial procedure. Especially in the multi-channel brain signals such as Electroencephalogram (EEG), Electrocorticography (ECoG), the channel which has the most correlation with the goal human activity and intention is the priority concern. However, because of the complicated extraction to the feature of the human fine part movements, most of the previous studies are aiming at the imaginary or real activity of large body parts, and their features are usually used in classification tasks. Thus, in order to extract the feature which has a higher linear correlation with fine body part such as fingers, this paper proposes a method combining wavelet time-frequency analysis and principal component analysis (PCA) to extract finger flexion related feature. In the first step, the multi-channel signals will be pre-processed. Then the time-frequency spectrum of each channel's signal is calculated by continuous wavelet transform. After that the spectrum is optimized, and the first wavelet time-frequency spectrum principal component (Wtspc) is extracted by PCA. At last, the Wtspc, which has the highest correlation to the corresponding finger flexion, is chosen as the final feature. The experiment results indicate that the Wtspc feature which extracted by our method has a higher correlation than original signals and typical time-domain features in the previous studies. Particularly, in the local finger flexion period, the Wtspc feature highly demonstrates a linear correlation with corresponding finger flexion.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121928550","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

Design of the Safe Driving and Acquisition Module for Nodeless Three-phase AC Switch Machines 无节点三相交流开关机安全驱动与采集模块的设计

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487181

Meili Xing, H. Ding, Xiguo Ren, Binbin Huang, Qi Ao, Yiping Xiao

引用次数: 0

Architecture Scheme of DevOps for Cross Network and Multiple Environment Collaboration 面向跨网络多环境协作的DevOps体系结构方案

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487116

Li Liu, Dongmei Xie, YunChang Cheng, Gongliang Li

引用次数: 2

Conversation Recommender System Based on Knowledge Graph and Time-series Feature 基于知识图谱和时间序列特征的会话推荐系统

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487149

Xiaoyi Wang, Yaguang Li, Jie Liu

引用次数: 1

Research on Data Governance Framework for Fire Department 消防部门数据治理框架研究

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487110

Zhenpeng An, Di Zhang, Yunjie Liang

引用次数: 1

Research on Real-time Virtualization Technology for Control System 控制系统实时虚拟化技术研究

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487080

Xiangying Kong, Xinran Kong

{"title":"Research on Real-time Virtualization Technology for Control System","authors":"Xiangying Kong, Xinran Kong","doi":"10.1145/3487075.3487080","DOIUrl":"https://doi.org/10.1145/3487075.3487080","url":null,"abstract":"In recent years, the combination of multi-core processor and virtualization technology promotes the rapid application of virtualization technology in the field of real-time control. While virtualization technology gives full play to the performance of multi-core processors and improves the robustness and flexibility of application systems, the real-time performance loss caused by application virtualization has always been concerned by people. On the basis of discussing the concept of real-time control system, the principle of virtualization technology and the existing approaches of real-time virtualization technology, the real-time connotation of the virtualized control system is defined. This paper analyzes the real-time and applicable scenarios of two application schemes, namely, large-scale virtualization based on private cloud and single-node virtualization based on HyperVisor, the related real-time virtualization technology and application scenarios are discussed, and builds a test environment, and measures the interrupt response time and event response time of the corresponding schemes. The former can only meet the application with millisecond real-time performance, while the latter still has sub-microsecond real-time performance, which can meet most real-time system requirements.","PeriodicalId":354966,"journal":{"name":"Proceedings of the 5th International Conference on Computer Science and Application Engineering","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-10-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122220643","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: 1

A Product-form C-logit Stochastic Traffic Assignment Model 一个乘积型C-logit随机交通分配模型

Proceedings of the 5th International Conference on Computer Science and Application Engineering Pub Date : 2021-10-19 DOI: 10.1145/3487075.3487176

Ning Lv, Wen-yi Zhang, Jihui Ma

引用次数: 0