2020 2nd World Symposium on Artificial Intelligence (WSAI)最新文献_第2页

Nonlinear Activation in Deep Residual Networks 深度残差网络的非线性激活

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143282

Qijun Zhang, SongLing Fu, Dan Li

引用次数: 0

WSAI 2020 Copyright Page WSAI 2020版权页面

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/wsai49636.2020.9143274

引用次数: 0

Comparison on Vandermond and Cauchy MDS Array Codes in Distributed Storage Systems 分布式存储系统中Vandermond和Cauchy MDS阵列码的比较

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143308

Xiangshou Yu, Hanxu Hou, G. Han

{"title":"Comparison on Vandermond and Cauchy MDS Array Codes in Distributed Storage Systems","authors":"Xiangshou Yu, Hanxu Hou, G. Han","doi":"10.1109/WSAI49636.2020.9143308","DOIUrl":"https://doi.org/10.1109/WSAI49636.2020.9143308","url":null,"abstract":"Binary maximum distance separable (MDS) array codes are an important class of MDS codes with low computational complexity, as only XOR operations are involved in the encoding/decoding procedures. Most existing binary MDS array codes are constructed based on Vandermonde matrix or Cauchy matrix, as we have efficient decoding methods for Vandermonde and Cauchy linear systems. We call the array codes with encoding matrix being Vandermonde matrix and Cauchy matrix as Vandermonde MDS array codes and Cauchy MDS array codes, respectively. In this paper, we implement Vandermonde MDS array codes and Cauchy MDS array codes, and evaluate their encoding and decoding performance. Our implemented results show that Vandermonde MDS array codes have better encoding/decoding performance than that of Cauchy MDS array codes. Specifically, the encoding rate of Vandermonde MDS array codes is about 58% higher than that of Cauchy MDS array codes, and the decoding rate of Vandermonde MDS array codes is about 70% higher than that of Cauchy MDS array codes. In our implementation, the efficient decoding method is based on the LU factorization of Vandermonde matrix and Cauchy matrix. Thus, only some pattern of the decoding procedure of Vandermonde MDS array codes is considered in this paper.","PeriodicalId":346385,"journal":{"name":"2020 2nd World Symposium on Artificial Intelligence (WSAI)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117237538","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

Research and Implementation of Discrete Algorithm Based on Breakpoint Importance 基于断点重要性的离散算法研究与实现

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143318

Yang Lu, Ni Yuan, Gao Yudong, Cai Gongshan

{"title":"Research and Implementation of Discrete Algorithm Based on Breakpoint Importance","authors":"Yang Lu, Ni Yuan, Gao Yudong, Cai Gongshan","doi":"10.1109/WSAI49636.2020.9143318","DOIUrl":"https://doi.org/10.1109/WSAI49636.2020.9143318","url":null,"abstract":"Rough set theory can guide the data mining process, and its advantage is that it can directly generate decision rules without prior knowledge. However, rough set theory stipulates that the values to be processed must be discrete. If the recognized values are continuous, the discretization must be performed before data processing. Based on the research on the basic concepts of the rough set theory and the discretization algorithm, the mathematical formula is quoted, that is, the number of data sets that can be divided by the given breakpoints. The importance of each breakpoint in the information table can be weighed to distinguish them. The greater the number, the higher the importance, and then adding breakpoints to the candidate set in turn, and then redividing the equivalent breakpoints for the given breakpoints to determine whether each data in the equivalence set has the same decision. If the decision values are the same, then use this as the basis for discretization; but if the decision values are different, return the importance of calculating the breakpoint and re-divide, and finally obtain the discretized data for subsequent processing.","PeriodicalId":346385,"journal":{"name":"2020 2nd World Symposium on Artificial Intelligence (WSAI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128849758","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

Traffic Flow Prediction Based on Residual Analysis 基于残差分析的交通流预测

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143284

Liyan Xiong, Binghua Hu, Xiaohui Huang, Weichun Huang

引用次数: 0

Automated Analysis of Seizure Behavior in Video: Methods and Challenges 视频中癫痫行为的自动分析:方法和挑战

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143279

Jing Tian, Weiyu Yu, Jin-Hsien Chen, Junke Lin, Mingfeng Wen, Yingxin Li, Jianxin Zhong, Keqiang Chen, Xuchu Feng

引用次数: 1

5G MEC Gateway System Design and Application in Industrial Communication 5G MEC网关系统在工业通信中的设计与应用

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143280

Ziwei Jia, Dongdong Li, Weimin Zhang, Lingli Pang

{"title":"5G MEC Gateway System Design and Application in Industrial Communication","authors":"Ziwei Jia, Dongdong Li, Weimin Zhang, Lingli Pang","doi":"10.1109/WSAI49636.2020.9143280","DOIUrl":"https://doi.org/10.1109/WSAI49636.2020.9143280","url":null,"abstract":"In industrial production, mass data transmission and processing are required with an increase in production data, which causes large-scale and complicated wiring in the manufacturing industry. However, it is difficult to achieve improved performance through traditional wireless communication technologies. 5G, a leading communication technology, with its Ultra-Reliable Low Latency Communication (uRLLC) combined with Multi-access Edge Computing (MEC), provides huge potential for the service with requirements for higher bandwidth, lower latency, and more computation. The Local Area Network type (LAN-type) Service supported by the 5G system reduces the net distance, which further decreases latency and provides data security. Based on this, in this paper, a 5G MEC gateway system is proposed to realize local wireless communication in a factory. The gateway system includes an intranet Address Resolution Mechanism, which is designed to resolve User Equipment IP addresses, a MEC server, which acts as a switch for packets broadcasting, and network tunnels, which are established between gateways to transmit data in the 5G LAN. In addition, the implemented testbed includes Raspberry Pi, which acts as the gateway, and the OpenVPN server, which runs in the MEC. Finally, two cases are shown to transfer Profinet and OPC UA data with this system.","PeriodicalId":346385,"journal":{"name":"2020 2nd World Symposium on Artificial Intelligence (WSAI)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130533842","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: 5

A Differential Evolution Approach for Camera Space Manipulation 一种相机空间操纵的差分进化方法

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143312

Yu Xie, Wei Wang, Chunxia Zhao, S. Skaar, Qinglong Wang

引用次数: 2

An Optimization Method with a Hybrid Objective Function for Scheduling a Flow Shop Problem 流车间调度问题的混合目标函数优化方法

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143311

Jian Zheng, Yuichi Kobayashi, Takashi Yanagida, Kawada Yasushi, Yoshiyasu Takahashi

{"title":"An Optimization Method with a Hybrid Objective Function for Scheduling a Flow Shop Problem","authors":"Jian Zheng, Yuichi Kobayashi, Takashi Yanagida, Kawada Yasushi, Yoshiyasu Takahashi","doi":"10.1109/WSAI49636.2020.9143311","DOIUrl":"https://doi.org/10.1109/WSAI49636.2020.9143311","url":null,"abstract":"As manufacturing and servicing operations have been increasingly becoming complicated, scheduling which directly effects the manufacturing cost, production quality, level of services is becoming more challenging. By far, various scheduling methods have been developed in order to support decision making in scheduling. It is noted that, however, when a well-tuned scheduling method is applied to different circumstances where scheduling preference of decision makers may be different laborious parameter tuning of the method is required. Such parameter tuning to some extent limits applicability of the scheduling method. To eliminate parameter tuning of scheduling methods, in this study, we proposed a scheduling optimization method with the hybrid objective function. By using small-scale historical schedules evaluated by decision makers, a learning-based objective function is trained to evaluate new schedules. Moreover, to restrain the evaluation errors of the learning-based method which may be caused by the imbalanced training data, the priori objective function is exploited and integrated into the learning-based objective function. The proposed method is validated by a classical scheduling problem, the flow shop scheduling problem with two machines and multiple objectives. Validation results show that, the method outperforms the methods with individual priori objective and learning-based functions. Therefore, by using small-scale evaluation result, the proposed method can capture preference changes of decision makers and avoid laborious parameter tuning of the optimization method.","PeriodicalId":346385,"journal":{"name":"2020 2nd World Symposium on Artificial Intelligence (WSAI)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131614852","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

Hash Retrieval Method for Recaptured Images Based on Convolutional Neural Network 基于卷积神经网络的重捕获图像哈希检索方法

2020 2nd World Symposium on Artificial Intelligence (WSAI) Pub Date : 2020-06-01 DOI: 10.1109/WSAI49636.2020.9143281

Jing Li, Xuan Wang, Shouxun Liu

引用次数: 0