Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.129
Liwen Song, Jiahui Qi, Min Wu
Abstract. Applying Clustering to non-convex data is a challenging task, and traditional clustering algorithms often fail to achieve good results. In this paper, an improved spectral clustering algorithm based on density sensitivity (DSISC algorithm) is proposed. By using the ensemble selection strategy for the mean shift algorithm, relatively good optional clusters are selected from the nonconvex data sets, and then the number of clusters is transported into the spectral clustering algorithm as input, and the density-sensitive distance is used as the similarity measure. The experimental results give us clear information that the DSISC is better than traditional mean shift algorithm and spectral clustering algorithms in normalized mutual information clustering error rate.
{"title":"Research on Density Sensitive Clustering Algorithm for Non-convex Sets","authors":"Liwen Song, Jiahui Qi, Min Wu","doi":"10.2991/ICMEIT-19.2019.129","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.129","url":null,"abstract":"Abstract. Applying Clustering to non-convex data is a challenging task, and traditional clustering algorithms often fail to achieve good results. In this paper, an improved spectral clustering algorithm based on density sensitivity (DSISC algorithm) is proposed. By using the ensemble selection strategy for the mean shift algorithm, relatively good optional clusters are selected from the nonconvex data sets, and then the number of clusters is transported into the spectral clustering algorithm as input, and the density-sensitive distance is used as the similarity measure. The experimental results give us clear information that the DSISC is better than traditional mean shift algorithm and spectral clustering algorithms in normalized mutual information clustering error rate.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131327949","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.138
J. Jia, Xiaoqiang Yan
For the rolling mill torque telemetry system, the battery power supply has a short duration, and the current supply by the collector ring can achieve long-term power supply, but it is difficult to achieve stable power supply for a long time due to limitations such as speed and wear. This paper designs a high-frequency induction power supply system to realize long-term stable power supply of sensors and signal transmitting modules on the measured axis. The WIFI signal transmission technology is used to realize the fast, efficient and stable wireless transmission of torque signals. The embedded programming of STM32F103 chip based on Cortex-M3 kernel architecture realizes the AD conversion, signal processing, WIFI transmitting and receiving control of torque signal. The system has been applied to the monitoring of main drive torque of many continuous rolling mills and achieved good results, which can replace expensive imported products.
{"title":"Development and Application of On-Line Torque Telemetry System for Rolling Mill based on WIFI Signal Transmission and High Frequency Induction Power Supply","authors":"J. Jia, Xiaoqiang Yan","doi":"10.2991/ICMEIT-19.2019.138","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.138","url":null,"abstract":"For the rolling mill torque telemetry system, the battery power supply has a short duration, and the current supply by the collector ring can achieve long-term power supply, but it is difficult to achieve stable power supply for a long time due to limitations such as speed and wear. This paper designs a high-frequency induction power supply system to realize long-term stable power supply of sensors and signal transmitting modules on the measured axis. The WIFI signal transmission technology is used to realize the fast, efficient and stable wireless transmission of torque signals. The embedded programming of STM32F103 chip based on Cortex-M3 kernel architecture realizes the AD conversion, signal processing, WIFI transmitting and receiving control of torque signal. The system has been applied to the monitoring of main drive torque of many continuous rolling mills and achieved good results, which can replace expensive imported products.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131501685","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.58
Zhian Lin, Chi Zhang
Abstract. This paper introduces the distributed transaction processing model and two-phase commit protocol, and analyses the shortcomings of the two-phase commit protocol. And then we proposed a new distributed transaction processing method which adds heartbeat mechanism into the twophase commit protocol. Using the method can improve reliability and reduce blocking in distributed transaction processing.
{"title":"A Transaction Processing Method for Distributed Database","authors":"Zhian Lin, Chi Zhang","doi":"10.2991/ICMEIT-19.2019.58","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.58","url":null,"abstract":"Abstract. This paper introduces the distributed transaction processing model and two-phase commit protocol, and analyses the shortcomings of the two-phase commit protocol. And then we proposed a new distributed transaction processing method which adds heartbeat mechanism into the twophase commit protocol. Using the method can improve reliability and reduce blocking in distributed transaction processing.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"226 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132472763","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.16
Xuandong Lei
The partial classification algorithm is mainly used to predict the popularity of network news and to explore the best model to predict the popularity of network news, so as to help network news service providers predict the popularity of news before publication. The popularity of network news is predicted according to the data analysis process: first, UCI data sets are pre-processed; secondly, feature selection is conducted for the data sets by using recursive feature elimination algorithm; then modelling and analysis is carried out, and finally through the confusion matrix, risk map and ROC (Receiver Operating Characteristic) chart performance evaluation, the performance of the model is compared and analyzed. Through comparison, it is found that random forest is the best prediction model.
{"title":"Prediction Model based on Internet News Buzzword Data","authors":"Xuandong Lei","doi":"10.2991/ICMEIT-19.2019.16","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.16","url":null,"abstract":"The partial classification algorithm is mainly used to predict the popularity of network news and to explore the best model to predict the popularity of network news, so as to help network news service providers predict the popularity of news before publication. The popularity of network news is predicted according to the data analysis process: first, UCI data sets are pre-processed; secondly, feature selection is conducted for the data sets by using recursive feature elimination algorithm; then modelling and analysis is carried out, and finally through the confusion matrix, risk map and ROC (Receiver Operating Characteristic) chart performance evaluation, the performance of the model is compared and analyzed. Through comparison, it is found that random forest is the best prediction model.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"148 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122193150","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.96
Yixiang Jiang, Wenjuan Wang, Chengting Zhang
With the development of industrial control network and the deep integration of industry and information technology, the rapid development of industrial control system has increased dramatically, which has brought huge economic and property losses to industrial control companies. Therefore, a traffic identification technology based on deep learning is proposed, which makes full use of the characteristics of industrial network traffic signs. Combined with experiments, this technology can classify network traffic and effectively identify abnormal traffic in industrial control system network. Compared with traditional classification methods, it not only improves the accuracy of traffic identification, but also reduces the time required for classification.
{"title":"Research on Traffic Recognition Algorithms for Industrial Control Networks based on Deep Learning","authors":"Yixiang Jiang, Wenjuan Wang, Chengting Zhang","doi":"10.2991/ICMEIT-19.2019.96","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.96","url":null,"abstract":"With the development of industrial control network and the deep integration of industry and information technology, the rapid development of industrial control system has increased dramatically, which has brought huge economic and property losses to industrial control companies. Therefore, a traffic identification technology based on deep learning is proposed, which makes full use of the characteristics of industrial network traffic signs. Combined with experiments, this technology can classify network traffic and effectively identify abnormal traffic in industrial control system network. Compared with traditional classification methods, it not only improves the accuracy of traffic identification, but also reduces the time required for classification.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122350423","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.50
Jie Wang, Yunyao Zhou
Congestion in urban makes too many commuters choose public transport for traveling. A large number of public transportation travel data can accurately calculate workplace and residence of the regular passengers. The label of workplace and residence helps to analyze urban migration and the distribution of workplace and residence.
{"title":"Algorithm and Application for Labeling Workplace and Residence based on Traffic Big Data","authors":"Jie Wang, Yunyao Zhou","doi":"10.2991/ICMEIT-19.2019.50","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.50","url":null,"abstract":"Congestion in urban makes too many commuters choose public transport for traveling. A large number of public transportation travel data can accurately calculate workplace and residence of the regular passengers. The label of workplace and residence helps to analyze urban migration and the distribution of workplace and residence.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121276092","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.40
Hao Shi, Fei Wan, Xiaokang Lei
This document gives formatting instructions for authors preparing papers for publication. With the arrival of the era of big data, the mature use of cloud computing and data mining technology, the big data mode have been widely applied in logistics. For military logistics, a smart military logistics ecosystem is built combining with big data, cloud computing and data mining. The collection, processing, mining technology of big data in military logistics are introduced. The promoting role of big data on military logistics is emphasized. The fusion method of big data and military logistics is expounding. The basic framework of smart military logistics ecosystem is built, and the application prospect of smart military logistics ecosystem is described.
{"title":"Research on Military Logistics based on Big Data","authors":"Hao Shi, Fei Wan, Xiaokang Lei","doi":"10.2991/ICMEIT-19.2019.40","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.40","url":null,"abstract":"This document gives formatting instructions for authors preparing papers for publication. With the arrival of the era of big data, the mature use of cloud computing and data mining technology, the big data mode have been widely applied in logistics. For military logistics, a smart military logistics ecosystem is built combining with big data, cloud computing and data mining. The collection, processing, mining technology of big data in military logistics are introduced. The promoting role of big data on military logistics is emphasized. The fusion method of big data and military logistics is expounding. The basic framework of smart military logistics ecosystem is built, and the application prospect of smart military logistics ecosystem is described.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127001956","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.48
K. Spicher, Boxing Li, D. Fang
This essay relates mainly to sporadic FC (forecasting) methods and error measures. The existing related FC methods of sporadic time series (STS), including the SES (Simple Exponential Smoothing), Croston’ s / SBA method and patented WSS method as well as two applicable error metrics APE and THEIL'S U are introduced briefly. Then the focus is laid on the analysis and presentation of a new forecasting yet unpublished method, SIMFAC (1), which is dedicated to STS and includes a new error metric, MEM (Matching Event Metric). For a more comprehensive comparison among methods, Cosine Similarity (CS) metric, will be introduced and applied in this essay.
{"title":"SIMFAC-A New Forecasting Method for Sporadic Time Series","authors":"K. Spicher, Boxing Li, D. Fang","doi":"10.2991/ICMEIT-19.2019.48","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.48","url":null,"abstract":"This essay relates mainly to sporadic FC (forecasting) methods and error measures. The existing related FC methods of sporadic time series (STS), including the SES (Simple Exponential Smoothing), Croston’ s / SBA method and patented WSS method as well as two applicable error metrics APE and THEIL'S U are introduced briefly. Then the focus is laid on the analysis and presentation of a new forecasting yet unpublished method, SIMFAC (1), which is dedicated to STS and includes a new error metric, MEM (Matching Event Metric). For a more comprehensive comparison among methods, Cosine Similarity (CS) metric, will be introduced and applied in this essay.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116782441","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.13
Sijie Cheng
The fifth-generation mobile communication network (5G) technology is a hot topic in the current mobile communication field, and the channel coding technology is the foundation to realize the reliable communication of 5G mobile system. This paper introduces the development of 5G technology and the development of standards, with emphasis on the features and applications of Turbo, LDPC and Polar codes, and compares these three technologies. Finally, the future development of 5G channel coding standard is prospected.
{"title":"Comparative Study on 5G Communication Channel Coding Technology","authors":"Sijie Cheng","doi":"10.2991/ICMEIT-19.2019.13","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.13","url":null,"abstract":"The fifth-generation mobile communication network (5G) technology is a hot topic in the current mobile communication field, and the channel coding technology is the foundation to realize the reliable communication of 5G mobile system. This paper introduces the development of 5G technology and the development of standards, with emphasis on the features and applications of Turbo, LDPC and Polar codes, and compares these three technologies. Finally, the future development of 5G channel coding standard is prospected.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"14 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129460852","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}
Pub Date : 2019-04-01DOI: 10.2991/ICMEIT-19.2019.22
Xuekun Hao, Wenfeng Ma, Xiaohao Mo
The paper studies the problem of distributed frequency decision problem in cognitive user (CU) network for optimizing satisfaction performance, based on the cognitive radio technology. For cognitive user, it can use both charged and free bands. Charged bands have to be paid and free bands have to be shared among cognitive users. Considering the work bandwidth limit and communication request for each cognitive user, our work is to maximize the network satisfaction performance of the cognitive user network which is defined as the satisfaction degree minus price paid. We propose a mixed cognitive frequency decision algorithm which could improve the network satisfaction performance. According to the experiment results, the proposed approach could work better compared with existing ones.
{"title":"The Mixed Cognitive Frequency Decision for Self-organized Networks","authors":"Xuekun Hao, Wenfeng Ma, Xiaohao Mo","doi":"10.2991/ICMEIT-19.2019.22","DOIUrl":"https://doi.org/10.2991/ICMEIT-19.2019.22","url":null,"abstract":"The paper studies the problem of distributed frequency decision problem in cognitive user (CU) network for optimizing satisfaction performance, based on the cognitive radio technology. For cognitive user, it can use both charged and free bands. Charged bands have to be paid and free bands have to be shared among cognitive users. Considering the work bandwidth limit and communication request for each cognitive user, our work is to maximize the network satisfaction performance of the cognitive user network which is defined as the satisfaction degree minus price paid. We propose a mixed cognitive frequency decision algorithm which could improve the network satisfaction performance. According to the experiment results, the proposed approach could work better compared with existing ones.","PeriodicalId":223458,"journal":{"name":"Proceedings of the 3rd International Conference on Mechatronics Engineering and Information Technology (ICMEIT 2019)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129508502","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：