发布求助
文献互助 智能选刊 最新文献

2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)最新文献

筛选
英文 中文
SDN Based Intelligent Honeynet Network Model Design and Verification 基于SDN的智能蜜网模型设计与验证
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00019
Ruidong Li, Minjiao Zheng, Donglin Bai, Zhengduo Chen
{"title":"SDN Based Intelligent Honeynet Network Model Design and Verification","authors":"Ruidong Li, Minjiao Zheng, Donglin Bai, Zhengduo Chen","doi":"10.1109/MLISE54096.2021.00019","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00019","url":null,"abstract":"To solve the problems of high cost and inflexibility of traditional honeynet, next-generation honeynet based on SDN attracts the attention of researchers. This paper proposes a three layers' network model of next-generation intelligent honeynet via SDN. Based on this model, the intelligent honeynet includes “two mechanisms and three modules”. The “two mechanisms” are attack migration mechanism and topology management mechanism. The “three modules” are attack detection module, policy generation module and honeynet management module. Then, this paper implements a concept demonstration honeynet to valid the concepts and methods proposed by this paper. Finally, to verify the validity of concept demonstration honeynet, two experiments are presented. Results show that the network model enhances the traditional honeynet's ability to control malicious data traffic and traps attacks, and improves network deception.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"57 3","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133018450","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: 3
Compliant Robotic Assembly based on Deep Reinforcement Learning 基于深度强化学习的柔性机器人装配
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00009
Zhenning Zhou, Peiyuan Ni, Xiaoxiao Zhu, Q. Cao
{"title":"Compliant Robotic Assembly based on Deep Reinforcement Learning","authors":"Zhenning Zhou, Peiyuan Ni, Xiaoxiao Zhu, Q. Cao","doi":"10.1109/MLISE54096.2021.00009","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00009","url":null,"abstract":"Assembly with industrial robots in an unstructured environment is more and more desirable and going to play an indispensable role in modern manufacturing industries. The classical peg-in-hole robotic assembly has been extensively researched as a common industrial task, but high-precision robotic assembly, which means the assembly precision of mechanical parts required may exceed that of robots, remains an open problem. Meanwhile, the conventional impedance control method used in the current manufacturing, requires numerous parameters to be artificially tuned before deployment, tedious and awfully time-consuming. Moreover, it has a poor success rate. In this paper, we propose a novel method with off-policy, model-free deep reinforcement-learning for position-controlled robots to perform assembly tasks compliantly through training, and there is no need for manual tuning. Through conducting a series of comparative experiments, this method is proved to have a preferable performance and assembly efficiency.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133156450","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: 2
Personal credit risk identification based on combined machine learning model 基于组合机器学习模型的个人信用风险识别
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00008
X. Ruan, Ning Ding
{"title":"Personal credit risk identification based on combined machine learning model","authors":"X. Ruan, Ning Ding","doi":"10.1109/MLISE54096.2021.00008","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00008","url":null,"abstract":"Personal credit risk assessment is essentially based on the classification of indicators or characteristic variables related to personal credit. Currently, a single model is often used to classify normal customers and defaulting customers. However, the single model may face the risk of a higher type II error rate, that is, defaulting customers are misjudged as normal customers. From the perspective of the combined model, this paper uses the confidence-weighted voting strategy to give a single model different weights to construct a C5.0-SVM combined model. The study finds that the total classification accuracy of the C5.0-SVM combined model is higher than that of the single model, and the type II error rate is lower than that of the single model.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117198038","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
Electric fire early warning system of gymnasium building based on multi-sensor data fusion technology 基于多传感器数据融合技术的体育馆电气火灾预警系统
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00071
Wei Zhang
{"title":"Electric fire early warning system of gymnasium building based on multi-sensor data fusion technology","authors":"Wei Zhang","doi":"10.1109/MLISE54096.2021.00071","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00071","url":null,"abstract":"The generalization ability of the early warning model used in the traditional electrical fire early warning system is insufficient, which leads to a large difference between the fire probability of the early warning output and the expected output probability. This paper proposes an electrical fire early warning system for gymnasium buildings based on multi-sensor data fusion technology. In the hardware part, the regional fire detector and fire warning controller are designed to collect the fire signals in the surrounding environment in real time. In the software part, mutual information entropy is used to judge the correlation and independence of fire features, and fire warning feature parameters are selected to design fire signal recognition algorithm to complete the detection of early warning feature parameters. On this basis, the multi-sensor data fusion technology is used to establish the fire early warning model and complete the data fusion of fire characteristic parameters, so as to realize the fire recognition and early warning. The experimental results show that the output fire probability of the electrical fire early warning system is basically consistent with the actual fire probability, and is lower than the average error of the traditional system output, which is conducive to the accurate detection of fire in sports venues.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115069345","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: 4
Simulation Research of the Dynamic Characteristics of the Horse Head of Pumping Unit with Loose Connection Fault 连接松动故障抽油机马头动态特性仿真研究
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00047
Lu-Jun Li, Yungong Li, Shaowen Zhao, Xin Jin
{"title":"Simulation Research of the Dynamic Characteristics of the Horse Head of Pumping Unit with Loose Connection Fault","authors":"Lu-Jun Li, Yungong Li, Shaowen Zhao, Xin Jin","doi":"10.1109/MLISE54096.2021.00047","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00047","url":null,"abstract":"The connection between the horse head and the walking beam of the beam pumping unit often becomes loose, which can cause serious consequences of cracks or breaks in the horse head. However, there is no research on the characteristics and diagnostic methods of loose horse head connections. In this paper, we established a three-dimensional simulation model of the Beam pumping unit and with impulses phenomenon as the core, studied their degree, time, direction and other characteristics when pins are loose. We found that the loose connection will cause the horse head to produce transient impulse at a specific working angle, and the impulse is affected by the degree of looseness. Some conclusions that can be used as reference basis for fault diagnosis are drawn.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125460175","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
Man-machine interaction simulation of four-bar linkage lumbar spine therapeutic instrument based on OpenSim and MATLAB 基于OpenSim和MATLAB的四连杆腰椎治疗仪人机交互仿真
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00080
X. Zu, Zhenning Zhou, Q. Cao, Xueguan Gao, Xiaoxiao Zhu
{"title":"Man-machine interaction simulation of four-bar linkage lumbar spine therapeutic instrument based on OpenSim and MATLAB","authors":"X. Zu, Zhenning Zhou, Q. Cao, Xueguan Gao, Xiaoxiao Zhu","doi":"10.1109/MLISE54096.2021.00080","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00080","url":null,"abstract":"The smart wearable cervical/lumbar spine exoskeleton therapeutic instrument is a therapeutic instrument designed for patients with spine degenerative disease. This paper introduces the algorithm and verification of a compliant control strategy used to control this therapeutic instrument that has four-bar linkage mechanism. The admittance control strategy is adopted in the controlling process and uses different algorithm for different treatment mode. The verification of effectiveness of this control strategy is realized by joint simulation of OpenSim and MATLAB.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125014663","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
MRSF: A Meta-analysis Method Based on Random Sign Flip MRSF:基于随机符号翻转的元分析方法
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00036
Chunyan Tong, Zhaogong Zhang
{"title":"MRSF: A Meta-analysis Method Based on Random Sign Flip","authors":"Chunyan Tong, Zhaogong Zhang","doi":"10.1109/MLISE54096.2021.00036","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00036","url":null,"abstract":"With the continuous development of life science, the 21st century has become an era of biological big data. In the post-genome era, the focus of research begins to shift to large-scale genome analysis and the comparison and integration of various data, resulting in the emergence of genome-wide association analysis (GWAS). It uses single nucleotide polymorphisms (SNPs) as molecular genetic markers to analyze them at the genome-wide level to find genetic variations that affect complex traits. However, due to the differences in research methods, sample sizes and other factors, multiple GWAs for the same research problem often have different research results. An effective and comprehensive solution is to use Meta-analysis to conduct quantitative and comprehensive evaluation of these results, so as to identify significant variations more accurately. With the increasing application of meta-analysis in clinical medicine and genetic research, a large number of relevant theoretical algorithms have been studied, but higher sensitivity and lower type I error rate are still the goals of scholars. Based on this, this paper studied the existing Meta-analysis methods in depth, and proposed a MRSF algorithm based on random symbol flip to solve the defect that conventional statistical hypothesis might lead to higher false solidity in the traditional method, and compared the other four p-value combination methods on the triglyceride gene data set. The experimental results showed that, The MRSF approach overall has a better ability to identify valid variants.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128536557","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
Motion Analysis of Clamping Part of A Cable Climbing Device for Power Transmission Line 输电线路攀缆装置夹紧部分运动分析
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00098
Feng Yu, Ding Chenlong, Wu Kai, H. Wenxin, Wu Shaolei, Wang Wei
{"title":"Motion Analysis of Clamping Part of A Cable Climbing Device for Power Transmission Line","authors":"Feng Yu, Ding Chenlong, Wu Kai, H. Wenxin, Wu Shaolei, Wang Wei","doi":"10.1109/MLISE54096.2021.00098","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00098","url":null,"abstract":"During traditional maintenance of power transmission line, it was rose to the corresponding height through the elevator manipulated by maintenance workers, which the risk of these works is high, so we put forward a kind of overhead power transmission line NC climbing working device that can replace some parts of maintenance works. The device is mainly used for clearing obstacles on 10kV power transmission line. In order to fit this device can rise to the middle of power transmission line, the combination structure of linear actuator and linkages are used to clamp the two sides of power transmission line. After researching, we find clamping part is the key of realizing expectant motion and confirming parameters, so in this article we make motion analysis of clamping part combined software MATLAB.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126086301","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
Data acquisition and feature analysis based on sEMG 基于表面肌电信号的数据采集与特征分析
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00083
Jinglong Zhang, Mulin Tong, Yun Fang, Jing Meng, Jingfeng Liu, Zhongjun Zhu, Ying Chang
{"title":"Data acquisition and feature analysis based on sEMG","authors":"Jinglong Zhang, Mulin Tong, Yun Fang, Jing Meng, Jingfeng Liu, Zhongjun Zhu, Ying Chang","doi":"10.1109/MLISE54096.2021.00083","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00083","url":null,"abstract":"In this paper, the sEMG signal of human lower limb movement intention obtained by acquisition technology is taken as the research object, the collected sEMG signal data is sorted out, and then the data is extracted, and finally the movement mode analysis based on sEMG signal is completed. The specific research contents are as follows: first, choose a reasonable movement mode, according to its movement characteristics, reasonable division of leg movement cycle. Secondly, according to the structure of the sensor, the appropriate wearing position is selected. The feature extraction and analysis of sEMG signal are carried out combined with sensor device. Finally, the collected sEMG signal data is sorted out, and combined with experience, the feature analysis based on sEMG signal is completed.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125954823","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 distance teaching system of College Chinese course based on Data Mining 基于数据挖掘的大学语文远程教学系统设计
2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) Pub Date : 2021-07-01 DOI: 10.1109/MLISE54096.2021.00087
Fangfang Ji
{"title":"Design of distance teaching system of College Chinese course based on Data Mining","authors":"Fangfang Ji","doi":"10.1109/MLISE54096.2021.00087","DOIUrl":"https://doi.org/10.1109/MLISE54096.2021.00087","url":null,"abstract":"The data throughput of conventional distance teaching system is low, and the length of course search path is long. Therefore, this paper proposes the design of distance teaching system of College Chinese course based on data mining, and optimizes the system software on the basis of conventional system hardware. Select the appropriate data mining tools, filter the course resources in the web page information, and then integrate the pre-processed course resources and set up a system database. Through the neural network, the course resources with high degree of association are clustered, and service nodes and leaf nodes are selected to transfer resource data remotely. Experimental results show that the design system increases the data throughput, reduces the length of the search path, and improves the transmission performance of curriculum resources.","PeriodicalId":430495,"journal":{"name":"2021 International Conference on Machine Learning and Intelligent Systems Engineering (MLISE)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133282764","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
首页 上一页 下一页 尾页
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整，为了账户安全，请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们：info@booksci.cn Book学术提供免费学术资源搜索服务，方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号：604180095
Book学术官方微信
小红书