Pub Date : 2017-04-01DOI: 10.1109/ICNISC.2017.00039
Xiu-Zhi Yang, Zhiming Zhou
The existence of cracks is fatal in many industries, in order to ensure the safety of production, it is necessary to regularly detect components, find cracks and take measures. The initiation and propagation of fatigue crack is a gradual process, so how to predict fatigue crack life and monitor the fatigue crack propagation in real time are a practical problem. In this paper, the real-time monitoring of extended virtual instrument data acquisition system was created by Labview on the fatigue crack based on PLC micro-controller, the signal of crack detection sensor incoming preliminary processing concurrent to the PC (computer), advance relevant parameters to different material stored in the host computer, through the Labview software. According to the data processing parameters, the host computer alarms when the crack length exceeds the warned value, and the real-time crack length is saved to the specified path for subsequent analysis. The real-time fatigue crack monitoring system has important practical application value in the monitoring, early warning and recording of crack in engineering application.
{"title":"Design of Crack Detection System","authors":"Xiu-Zhi Yang, Zhiming Zhou","doi":"10.1109/ICNISC.2017.00039","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00039","url":null,"abstract":"The existence of cracks is fatal in many industries, in order to ensure the safety of production, it is necessary to regularly detect components, find cracks and take measures. The initiation and propagation of fatigue crack is a gradual process, so how to predict fatigue crack life and monitor the fatigue crack propagation in real time are a practical problem. In this paper, the real-time monitoring of extended virtual instrument data acquisition system was created by Labview on the fatigue crack based on PLC micro-controller, the signal of crack detection sensor incoming preliminary processing concurrent to the PC (computer), advance relevant parameters to different material stored in the host computer, through the Labview software. According to the data processing parameters, the host computer alarms when the crack length exceeds the warned value, and the real-time crack length is saved to the specified path for subsequent analysis. The real-time fatigue crack monitoring system has important practical application value in the monitoring, early warning and recording of crack in engineering application.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130266734","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00050
Xiao Wei, Q. Lu
This paper studied and implemented a set of economic operation evaluation system of wind, solar and energy storage combined power generation unit. Firstly, according to the meteorological conditions, the unit output model was set up. Under the established coordinated operation strategy, wind, solar and energy storage combined power generation system was taken into grid as power generation unit with rated capacity. Then, starting from aspects of technical and economic benefit, financial benefit and social benefit, it constructed a comprehensive economic benefit index system. A comprehensive evaluation model was established by combining the subjective and objective value assignment method. Finally, through the development of the evaluation system, it completed the output simulation run on the power generation unit, in addition, it conducted visual analysis and display on evaluation results of different capacity matching schemes. The results showed that the research and development of the system could combine the performance characteristics of wind, solar and energy storage combined power generation technology to form the economic operation evaluation model of the power generation unit which conformed to the scale-up grid entrance, through the scientific process, it could form the evaluation result and then display this in a variety of chart forms to provide decision support for researchers.
{"title":"Study on the Economic Evaluation Model of Wind, Solar and Energy Storage Combined Power Generation Unit","authors":"Xiao Wei, Q. Lu","doi":"10.1109/ICNISC.2017.00050","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00050","url":null,"abstract":"This paper studied and implemented a set of economic operation evaluation system of wind, solar and energy storage combined power generation unit. Firstly, according to the meteorological conditions, the unit output model was set up. Under the established coordinated operation strategy, wind, solar and energy storage combined power generation system was taken into grid as power generation unit with rated capacity. Then, starting from aspects of technical and economic benefit, financial benefit and social benefit, it constructed a comprehensive economic benefit index system. A comprehensive evaluation model was established by combining the subjective and objective value assignment method. Finally, through the development of the evaluation system, it completed the output simulation run on the power generation unit, in addition, it conducted visual analysis and display on evaluation results of different capacity matching schemes. The results showed that the research and development of the system could combine the performance characteristics of wind, solar and energy storage combined power generation technology to form the economic operation evaluation model of the power generation unit which conformed to the scale-up grid entrance, through the scientific process, it could form the evaluation result and then display this in a variety of chart forms to provide decision support for researchers.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127076558","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00033
Qi Shen, Hao Zhou, Shi-Wei Li, Zi-Hui Pei
Friend recommendation algorithm plays an important role in social networks. However, traditional recommendation algorithms do not take into account the drifting of user interests, and there are also some deficiencies when the recommendation's timeliness is considered. Aimed at this problem, the measure method of similarity was improved by combining with the characteristics of user interest's change with time. A time decay model was introduced to measure the predictive value. At the same time, the method refines the preference of the target users according to the homogeneity theory through the interest preference of friends. Through experiments on Sina microblog data set, and the results show that the algorithm to achieve better recommendation effect on precision, recall and F value.
{"title":"Friend Recommendation Algorithm Based on Interest Classification with Time Decay","authors":"Qi Shen, Hao Zhou, Shi-Wei Li, Zi-Hui Pei","doi":"10.1109/ICNISC.2017.00033","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00033","url":null,"abstract":"Friend recommendation algorithm plays an important role in social networks. However, traditional recommendation algorithms do not take into account the drifting of user interests, and there are also some deficiencies when the recommendation's timeliness is considered. Aimed at this problem, the measure method of similarity was improved by combining with the characteristics of user interest's change with time. A time decay model was introduced to measure the predictive value. At the same time, the method refines the preference of the target users according to the homogeneity theory through the interest preference of friends. Through experiments on Sina microblog data set, and the results show that the algorithm to achieve better recommendation effect on precision, recall and F value.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134159946","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00038
Yonghua Xu, Yi Guo, Zhihong Wang, Wei Sun
For the problem of entity extraction on dirty data in customs import and export domain, this paper proposes a data cleaning method based on specific rules and machine learning for commodity named entity extraction. First, KNN (k-Nearest Neighbor) classification algorithm is used to solve mismatches of attributes and their values of fields in domain data tuple. second, commodity named entities and sub attributes of fields are extracted by specific rules and CRF (conditional random field algorithm) model, proposed method can extract correct sub-attributes of each entity. Experiment results proved the advantages of proposed method in comparison with other methods in terms of precision and recall.
{"title":"Entity Extraction of Customs Clearance Data Based on CRF and Specific Rules","authors":"Yonghua Xu, Yi Guo, Zhihong Wang, Wei Sun","doi":"10.1109/ICNISC.2017.00038","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00038","url":null,"abstract":"For the problem of entity extraction on dirty data in customs import and export domain, this paper proposes a data cleaning method based on specific rules and machine learning for commodity named entity extraction. First, KNN (k-Nearest Neighbor) classification algorithm is used to solve mismatches of attributes and their values of fields in domain data tuple. second, commodity named entities and sub attributes of fields are extracted by specific rules and CRF (conditional random field algorithm) model, proposed method can extract correct sub-attributes of each entity. Experiment results proved the advantages of proposed method in comparison with other methods in terms of precision and recall.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133926859","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00018
Yu He, Pengbo Si, Enchang Sun, Yan-hua Zhang, Shuo Liu
As the rapid development of mobile communication technologies and the on-road information and entertainment demands, a growing number of vehicles equipped with communication, computing, caching and positioning devices will enable a huge network of connect vehicles, or vehicular network, with advanced capabilities to deliver not only the packets for the vehicle networks themselves, but also delay-tolerant data to increase the utilization efficiency of the vehicular network resource. In this paper, we introduce the concept of software-defined networking, computing and caching into vehicular networks to manage the delay-tolerant data deliver tasks from the Internet. We formulate this task management as an optimization problem and solve it by exploiting the optimal actions. Extensive simulation results are also presented to demonstrate the significant performance improvement of the proposed management.
{"title":"Joint Task Management in Connected Vehicle Networks by Software-Defined Networking, Computing and Caching","authors":"Yu He, Pengbo Si, Enchang Sun, Yan-hua Zhang, Shuo Liu","doi":"10.1109/ICNISC.2017.00018","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00018","url":null,"abstract":"As the rapid development of mobile communication technologies and the on-road information and entertainment demands, a growing number of vehicles equipped with communication, computing, caching and positioning devices will enable a huge network of connect vehicles, or vehicular network, with advanced capabilities to deliver not only the packets for the vehicle networks themselves, but also delay-tolerant data to increase the utilization efficiency of the vehicular network resource. In this paper, we introduce the concept of software-defined networking, computing and caching into vehicular networks to manage the delay-tolerant data deliver tasks from the Internet. We formulate this task management as an optimization problem and solve it by exploiting the optimal actions. Extensive simulation results are also presented to demonstrate the significant performance improvement of the proposed management.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"77 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116054191","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00064
Yang Fang, Wenxin Hu
Convolutional Neural Networks (CNN) is known for its features extraction from images. Extreme Learning Machine (ELM), has been adopted in various researching fields for its fast learning. CNN-KELM has overcome the KELM'S shortage of extracting features as this model uses CNN to detect the input image before classifying with KELM. Our improved CKELM includes rank based pooling strategy and GPU training. We make experiments to evaluate our proposal on dataset CIFAR and result proves that our pooling methods perform better than traditional ones.
{"title":"Going Deeper with CKELM","authors":"Yang Fang, Wenxin Hu","doi":"10.1109/ICNISC.2017.00064","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00064","url":null,"abstract":"Convolutional Neural Networks (CNN) is known for its features extraction from images. Extreme Learning Machine (ELM), has been adopted in various researching fields for its fast learning. CNN-KELM has overcome the KELM'S shortage of extracting features as this model uses CNN to detect the input image before classifying with KELM. Our improved CKELM includes rank based pooling strategy and GPU training. We make experiments to evaluate our proposal on dataset CIFAR and result proves that our pooling methods perform better than traditional ones.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124008227","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00059
Xiaoling Xia, Bing Nan, Cui Xu
With the urban transport development in the recent years, frequent traffic accidents and other problems need to be improved. Understanding the causes of traffic accidents and making an early alarm model for the driver will be crucial to solve traffic accident problems in some way. In this paper, we focus on the factors that can be collected in real-time and process the factors using data mining technologies. Finally, we evaluate the performance of different classifiers. The results show that our feature processing is effective in improving the classification accuracy and we can use the model to predict the severity of traffic accident furthermore prevent traffic accidents.
{"title":"Real-Time Traffic Accident Severity Prediction Using Data Mining Technologies","authors":"Xiaoling Xia, Bing Nan, Cui Xu","doi":"10.1109/ICNISC.2017.00059","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00059","url":null,"abstract":"With the urban transport development in the recent years, frequent traffic accidents and other problems need to be improved. Understanding the causes of traffic accidents and making an early alarm model for the driver will be crucial to solve traffic accident problems in some way. In this paper, we focus on the factors that can be collected in real-time and process the factors using data mining technologies. Finally, we evaluate the performance of different classifiers. The results show that our feature processing is effective in improving the classification accuracy and we can use the model to predict the severity of traffic accident furthermore prevent traffic accidents.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124792780","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00031
Haiyan Yang, Hua-An Zhao, Ping Zhou
This research is aimed to realize a high accurate crowd segmentation. Currently video surveillance systems are widely used at various places. With the rapid development of computer vision technologies, automatic identification and tracking techniques have been applied to surveillance system. For the crowd segmentation, e not only use the optical flow but also use streakflow. The reason is that the streakflow information is better than the optical flow. We choose Simple Flow which is a non-iterative optical flow technique and running times increase sub-linearly with the number of pixels to denoise and analyze crowd motion accurately. The accuracy of segmentation will be shown where the streaklflow is higher than that of only the optical flow segmentation by some experimental results.
{"title":"Crowd Segmentation Using SimpleFlow","authors":"Haiyan Yang, Hua-An Zhao, Ping Zhou","doi":"10.1109/ICNISC.2017.00031","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00031","url":null,"abstract":"This research is aimed to realize a high accurate crowd segmentation. Currently video surveillance systems are widely used at various places. With the rapid development of computer vision technologies, automatic identification and tracking techniques have been applied to surveillance system. For the crowd segmentation, e not only use the optical flow but also use streakflow. The reason is that the streakflow information is better than the optical flow. We choose Simple Flow which is a non-iterative optical flow technique and running times increase sub-linearly with the number of pixels to denoise and analyze crowd motion accurately. The accuracy of segmentation will be shown where the streaklflow is higher than that of only the optical flow segmentation by some experimental results.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124905346","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00021
Zuoxue Liu, Rui Jin
The Ad Hoc network based on TDMA has the advantages of fast and flexible networking, operational level controllable and no conflict transmission, in which MAC layer protocol directly determines the performance of Ad Hoc network. In TDMA mode, the MAC layer protocol mainly studies the time slot allocation, and there have been a large number of protocols related to slot allocation. According to the characteristics of different slot allocation protocols, this paper introduces the typical protocols, compares them with the advantages and disadvantages, and summarizes the main technical points about designing the slot allocation protocol.
{"title":"Research on Time Slot Allocation Protocols of Ad Hoc Network Based on TDMA","authors":"Zuoxue Liu, Rui Jin","doi":"10.1109/ICNISC.2017.00021","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00021","url":null,"abstract":"The Ad Hoc network based on TDMA has the advantages of fast and flexible networking, operational level controllable and no conflict transmission, in which MAC layer protocol directly determines the performance of Ad Hoc network. In TDMA mode, the MAC layer protocol mainly studies the time slot allocation, and there have been a large number of protocols related to slot allocation. According to the characteristics of different slot allocation protocols, this paper introduces the typical protocols, compares them with the advantages and disadvantages, and summarizes the main technical points about designing the slot allocation protocol.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128739603","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 : 2017-04-01DOI: 10.1109/ICNISC.2017.00055
Fei Gao, Yun-Cen Zhao, Lu Zhang, G. Wang
ue to the vehicle road adhesion coefficient recognition is an important subject in research on dynamics and control of vehicle, put forward the improved algorithm to identify each tire of the road adhesion coefficient. Get the vehicle adhesion coefficient in the comprehensive compensation double nonlinearity characterization method of yaw rate deviation and lateral acceleration deviation based on vehicle road adhesion coefficient, the relationship between the vehicle road adhesion coefficient, the vehicle utilization adhesion coefficient, tire utilization adhesion coefficient, and slip rate and the friction coefficient of the slope, identify the adhesion coefficient of each the road tire. Through the Matlab/simulink software to build simulation model, verify the improved algorithm on the low adhesion road. Results show that in the low adhesion road, the improved algorithm can effectively identify each tire adhesion coefficient of road.
{"title":"The Improved Algorithm for Identifying the Vehicle Road Adhesion Coefficient","authors":"Fei Gao, Yun-Cen Zhao, Lu Zhang, G. Wang","doi":"10.1109/ICNISC.2017.00055","DOIUrl":"https://doi.org/10.1109/ICNISC.2017.00055","url":null,"abstract":"ue to the vehicle road adhesion coefficient recognition is an important subject in research on dynamics and control of vehicle, put forward the improved algorithm to identify each tire of the road adhesion coefficient. Get the vehicle adhesion coefficient in the comprehensive compensation double nonlinearity characterization method of yaw rate deviation and lateral acceleration deviation based on vehicle road adhesion coefficient, the relationship between the vehicle road adhesion coefficient, the vehicle utilization adhesion coefficient, tire utilization adhesion coefficient, and slip rate and the friction coefficient of the slope, identify the adhesion coefficient of each the road tire. Through the Matlab/simulink software to build simulation model, verify the improved algorithm on the low adhesion road. Results show that in the low adhesion road, the improved algorithm can effectively identify each tire adhesion coefficient of road.","PeriodicalId":429511,"journal":{"name":"2017 International Conference on Network and Information Systems for Computers (ICNISC)","volume":"07 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127137694","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：