Pub Date : 2019-08-01DOI: 10.1109/ICSGEA.2019.00027
Li Chenyan, Nie Jing, Su Hui-Wei
With the gradually wide application of Internet of things on green building, Internet of Building Energy System (iBES) has gained more and more attention and application in the green building. Based on conception, technology and standard of the Internet of things, it acquires building energy consumption data through a series of sensors in the Intelligent Gateway (IG) and unifies a data standard. After data aggregation and software process, an effective building consumption data report can be provided in time, further adjusting building energy consumption in order to attain the goal of energy saving and consumption reducing. Application results show that, using the Internet of things technology for building power adjustment, reduce energy consumption, reduce carbon dioxide emissions, are a valuable technique.
{"title":"Research of Carbon Emission Reduction on the Green Building Based on the Internet of Things","authors":"Li Chenyan, Nie Jing, Su Hui-Wei","doi":"10.1109/ICSGEA.2019.00027","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00027","url":null,"abstract":"With the gradually wide application of Internet of things on green building, Internet of Building Energy System (iBES) has gained more and more attention and application in the green building. Based on conception, technology and standard of the Internet of things, it acquires building energy consumption data through a series of sensors in the Intelligent Gateway (IG) and unifies a data standard. After data aggregation and software process, an effective building consumption data report can be provided in time, further adjusting building energy consumption in order to attain the goal of energy saving and consumption reducing. Application results show that, using the Internet of things technology for building power adjustment, reduce energy consumption, reduce carbon dioxide emissions, are a valuable technique.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116716503","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 : 2019-08-01DOI: 10.1109/ICSGEA.2019.00070
Zheng Mali, Chen Huaxi
In recent years, artificial intelligence and large data are attracting increasing public attention, what's more, their practical application is greatly expected by the public. Currently, "artificial intelligence plus large data" is being put into practice gradually in the class-teaching of some certain colleges, with some desirable achievements made. Supported by artificial intelligence and large data, mathematical thinking abilities of related college students have developed profoundly, and accordingly, their comprehensive accomplishment has been strengthened. Based on this, this paper makes the analysis of existing problems in public Maths course teaching of engineering colleges of China, then introduces the development of artificial intelligence plus large data and their relations with public Maths course teaching of engineering colleges, and lastly makes scientific and reasonable exploration into the application of "artificial intelligence plus large data" in public Maths course teaching of engineering colleges, for the purpose of offering some proper help in public Maths course education of engineering colleges of China.
{"title":"On Application of \"Artificial Intelligence Plus Large Data\" in Public Maths Course Teaching of Engineering Colleges","authors":"Zheng Mali, Chen Huaxi","doi":"10.1109/ICSGEA.2019.00070","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00070","url":null,"abstract":"In recent years, artificial intelligence and large data are attracting increasing public attention, what's more, their practical application is greatly expected by the public. Currently, \"artificial intelligence plus large data\" is being put into practice gradually in the class-teaching of some certain colleges, with some desirable achievements made. Supported by artificial intelligence and large data, mathematical thinking abilities of related college students have developed profoundly, and accordingly, their comprehensive accomplishment has been strengthened. Based on this, this paper makes the analysis of existing problems in public Maths course teaching of engineering colleges of China, then introduces the development of artificial intelligence plus large data and their relations with public Maths course teaching of engineering colleges, and lastly makes scientific and reasonable exploration into the application of \"artificial intelligence plus large data\" in public Maths course teaching of engineering colleges, for the purpose of offering some proper help in public Maths course education of engineering colleges of China.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115850771","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 : 2019-08-01DOI: 10.1109/ICSGEA.2019.00026
Shuo Wang, Xiuyan Peng
To meet the needs of power producers in production, operation and bidding for access to the Internet under new situation, we e develop the operation decision support system for power generation enterprises. The system includes cost characteristic analysis module, bidding analysis module, quotation strategy module, real-time quotation system module, real-time cost tracking module and transaction evaluation system module. In the key electricity price forecasting module, the cost analysis algorithm based on genetic optimization algorithm and bidding strategy based on game theory are developed. The testing results show that the operation decision support system of the power generation enterprises runs well and the forecast price is more accurate, which provides the technical basis for the power generation company to compete on the Internet and it provides strong support for future survival and development.
{"title":"Research and Development of Decision Support System for Electricity Price Prediction of Power Generation Enterprises","authors":"Shuo Wang, Xiuyan Peng","doi":"10.1109/ICSGEA.2019.00026","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00026","url":null,"abstract":"To meet the needs of power producers in production, operation and bidding for access to the Internet under new situation, we e develop the operation decision support system for power generation enterprises. The system includes cost characteristic analysis module, bidding analysis module, quotation strategy module, real-time quotation system module, real-time cost tracking module and transaction evaluation system module. In the key electricity price forecasting module, the cost analysis algorithm based on genetic optimization algorithm and bidding strategy based on game theory are developed. The testing results show that the operation decision support system of the power generation enterprises runs well and the forecast price is more accurate, which provides the technical basis for the power generation company to compete on the Internet and it provides strong support for future survival and development.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123463389","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 : 2019-08-01DOI: 10.1109/ICSGEA.2019.00071
Wang Wenzhen
With the continuous growth of music resources, the problem of recommending suitable music for users has become a research hotspot. In this paper, association rules and music genes are added to music collaborative filtering personalized recommendation system to establish a hybrid recommendation model. The structure of the model is described and the recommendation process and recommendation algorithm of personalized recommendation are described in detail. By analyzing users' interests and preferences for different music gene features, the algorithm comprehensively analyses users' behavior, and uses the similarity of interests among different users to construct the neighborhood relationship among them. The recommendation algorithm is validated by combining two factors, and the expected recommendation results are achieved.
{"title":"Personalized Music Recommendation Algorithm Based on Hybrid Collaborative Filtering Technology","authors":"Wang Wenzhen","doi":"10.1109/ICSGEA.2019.00071","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00071","url":null,"abstract":"With the continuous growth of music resources, the problem of recommending suitable music for users has become a research hotspot. In this paper, association rules and music genes are added to music collaborative filtering personalized recommendation system to establish a hybrid recommendation model. The structure of the model is described and the recommendation process and recommendation algorithm of personalized recommendation are described in detail. By analyzing users' interests and preferences for different music gene features, the algorithm comprehensively analyses users' behavior, and uses the similarity of interests among different users to construct the neighborhood relationship among them. The recommendation algorithm is validated by combining two factors, and the expected recommendation results are achieved.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130897084","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 : 2019-08-01DOI: 10.1109/ICSGEA.2019.00045
Han Xuelian
To quickly and accurately retrieve the required music songs from the mass music database, this paper introduces the framework of content-based audio retrieval system and its related characteristics and difficulties. Then it describes the process of human voice humming feature processing on the voice platform within the framework of the system. On the simulation music platform, the retrieval algorithm based on the combination of notes and fundamental frequency is studied and analyzed for songs with background music, combined with the relevant characteristics of audio signals. The accuracy of humming retrieval can be improved by using more accurate iterative alignment algorithm of stress shift. The experiments show that the average retrieval time of humming retrieval system is significantly reduced by using the retrieval strategy.
{"title":"Content-Based Music Retrieval Algorithm and Simulation Analysis","authors":"Han Xuelian","doi":"10.1109/ICSGEA.2019.00045","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00045","url":null,"abstract":"To quickly and accurately retrieve the required music songs from the mass music database, this paper introduces the framework of content-based audio retrieval system and its related characteristics and difficulties. Then it describes the process of human voice humming feature processing on the voice platform within the framework of the system. On the simulation music platform, the retrieval algorithm based on the combination of notes and fundamental frequency is studied and analyzed for songs with background music, combined with the relevant characteristics of audio signals. The accuracy of humming retrieval can be improved by using more accurate iterative alignment algorithm of stress shift. The experiments show that the average retrieval time of humming retrieval system is significantly reduced by using the retrieval strategy.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127291861","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 : 2019-08-01DOI: 10.1109/ICSGEA.2019.00110
Xin Chen, Jing Li
To further improve the detection accuracy of SSD object detection algorithm, in this paper, a high efficient single shot multibit detector (HE-SSD) algorithm is proposed, which based on SSD for solving the low accuracy of classical single-stage object detection SSD algorithm. Firstly, an efficient and dense network is designed to improve the detection accuracy. Secondly, in order to improve the robustness of the algorithm and solve the problem of positive and negative sample imbalance in the detection process, the Focal Loss function is used to suppress the weight of the easily classified samples in the loss function. Finally, the accuracy of SSD algorithm for small object detection is improved by data augmentation. In the experiment, the network structure is deployed through the Pytorch deep learning framework, compared the effects of SGD and Adabound optimization methods on training loss to verify the superiority of convergence of the proposed algorithm. The experimental results show that HE-SSD algorithm is more accurate than SSD in PASCAL VOC dataset.
{"title":"Research on an Efficient Single-Stage Multi-object Detection Algorithm","authors":"Xin Chen, Jing Li","doi":"10.1109/ICSGEA.2019.00110","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00110","url":null,"abstract":"To further improve the detection accuracy of SSD object detection algorithm, in this paper, a high efficient single shot multibit detector (HE-SSD) algorithm is proposed, which based on SSD for solving the low accuracy of classical single-stage object detection SSD algorithm. Firstly, an efficient and dense network is designed to improve the detection accuracy. Secondly, in order to improve the robustness of the algorithm and solve the problem of positive and negative sample imbalance in the detection process, the Focal Loss function is used to suppress the weight of the easily classified samples in the loss function. Finally, the accuracy of SSD algorithm for small object detection is improved by data augmentation. In the experiment, the network structure is deployed through the Pytorch deep learning framework, compared the effects of SGD and Adabound optimization methods on training loss to verify the superiority of convergence of the proposed algorithm. The experimental results show that HE-SSD algorithm is more accurate than SSD in PASCAL VOC dataset.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"175 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116394233","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 : 2019-08-01DOI: 10.1109/ICSGEA.2019.00091
Weihua Zhang, Wei Wang, Li Zhu, Ruiying Zheng, Xing Liu
With the rapid development of web technology and the popularity of Internet technology in the public, people continue to use computers to store a variety of information, the amount of data stored is growing, and the kind are becoming more and more abundant. At the same time, the diversity of data storage has increased the diversity of unstructured data. The basic characteristics of unstructured data are diverse data formats, large data storage, and fast growth. This paper first summarizes the content and characteristics of unstructured data, then analyzes the key to unstructured data retrieval, and designs and develops a Python-based unstructured data retrieval system using Python language.
{"title":"Python-Based Unstructured Data Retrieval System","authors":"Weihua Zhang, Wei Wang, Li Zhu, Ruiying Zheng, Xing Liu","doi":"10.1109/ICSGEA.2019.00091","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00091","url":null,"abstract":"With the rapid development of web technology and the popularity of Internet technology in the public, people continue to use computers to store a variety of information, the amount of data stored is growing, and the kind are becoming more and more abundant. At the same time, the diversity of data storage has increased the diversity of unstructured data. The basic characteristics of unstructured data are diverse data formats, large data storage, and fast growth. This paper first summarizes the content and characteristics of unstructured data, then analyzes the key to unstructured data retrieval, and designs and develops a Python-based unstructured data retrieval system using Python language.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126589809","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 : 2019-08-01DOI: 10.1109/ICSGEA.2019.00133
Lingfang Huang
This paper improves the security management and control ability of campus network management, studies the security management control model of campus network management, and puts forward a security evaluation and evading model of campus network management based on big data. The management security data mining is carried out by using the statistical analysis method of campus network transmission traffic, and the constraint distribution model of campus network management security control is constructed. Big data fusion and association rule mining methods are used to evaluate the security of campus network management quantitatively, and the data of campus network management security evaluation are tested by grouping regression, and the correlation dimension characteristic quantity of traffic transmission sequence of campus network management is extracted. This paper analyzes the cross-correlation characteristic quantity of the output traffic of campus network management and evaluates the network security according to the anomaly of the characteristic to realize the optimization control of campus network security management. The simulation results show that the traffic anomaly prediction ability is higher and the network intrusion detection ability is stronger by using this method in campus network security management.
{"title":"Research on Campus Network Security Management Technology Based on Big Data","authors":"Lingfang Huang","doi":"10.1109/ICSGEA.2019.00133","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00133","url":null,"abstract":"This paper improves the security management and control ability of campus network management, studies the security management control model of campus network management, and puts forward a security evaluation and evading model of campus network management based on big data. The management security data mining is carried out by using the statistical analysis method of campus network transmission traffic, and the constraint distribution model of campus network management security control is constructed. Big data fusion and association rule mining methods are used to evaluate the security of campus network management quantitatively, and the data of campus network management security evaluation are tested by grouping regression, and the correlation dimension characteristic quantity of traffic transmission sequence of campus network management is extracted. This paper analyzes the cross-correlation characteristic quantity of the output traffic of campus network management and evaluates the network security according to the anomaly of the characteristic to realize the optimization control of campus network security management. The simulation results show that the traffic anomaly prediction ability is higher and the network intrusion detection ability is stronger by using this method in campus network security management.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127240258","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 : 2019-08-01DOI: 10.1109/ICSGEA.2019.00038
Sijie Chen, C. Zhai, Zewei Li, Jiaxin Zhang, Xinghua Pan
In order to effectively improve the problems existing in the current road traffic information acquisition device, such as too much equipment, low utilization ratio, serious information overlap and low detection rate, the integrated design and transformation of the traditional traffic information acquisition device is carried out, and a new type of traffic information acquisition device, the integrated traffic information detector, which integrates radar acquisition technology, video acquisition technology and Radio Frequency Identification (RFID) is designed. The integrated traffic information detector of lightning network can not only collect the intersection required by the road comprehensively, accurately and in real time, but also through the multi-source data fusion processing of the information collected by radar, video and RFID reader. Through information, and can adapt to a variety of complex detection environment. At the same time, it also fully considers the general direction of traffic in the future fifth generation mobile communication technology (5G: 5th-Generation) environment, equipped with wireless network module suitable for 5G, combined with the high capacity, low delay and high reliable high speed transmission rate under the future 5G network, to further promote the popularization and development of vehicle networking technology in the future.
{"title":"Integrated Design of Traditional Traffic Information Acquisition Device","authors":"Sijie Chen, C. Zhai, Zewei Li, Jiaxin Zhang, Xinghua Pan","doi":"10.1109/ICSGEA.2019.00038","DOIUrl":"https://doi.org/10.1109/ICSGEA.2019.00038","url":null,"abstract":"In order to effectively improve the problems existing in the current road traffic information acquisition device, such as too much equipment, low utilization ratio, serious information overlap and low detection rate, the integrated design and transformation of the traditional traffic information acquisition device is carried out, and a new type of traffic information acquisition device, the integrated traffic information detector, which integrates radar acquisition technology, video acquisition technology and Radio Frequency Identification (RFID) is designed. The integrated traffic information detector of lightning network can not only collect the intersection required by the road comprehensively, accurately and in real time, but also through the multi-source data fusion processing of the information collected by radar, video and RFID reader. Through information, and can adapt to a variety of complex detection environment. At the same time, it also fully considers the general direction of traffic in the future fifth generation mobile communication technology (5G: 5th-Generation) environment, equipped with wireless network module suitable for 5G, combined with the high capacity, low delay and high reliable high speed transmission rate under the future 5G network, to further promote the popularization and development of vehicle networking technology in the future.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128749414","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 : 2019-08-01DOI: 10.1109/icsgea.2019.00055
Cheng Zha
Due to the difference of the speaker's language, speech emotion recognition tasks often face the situation that training data are not fully representative of test data. Therefore, the space extended by a kernel function. might not sufficient to describe different properties of data and thus produce a satisfactory decision function. In this wok, we apply multiple kernel learning to recognize the speech emotion of cross-language. Compared to SVM, multiple kernel learning can achieve better performance in cross-language speech emotion recognition tasks.
{"title":"Cross-Language Speech Emotion Recognition via Multiple Kernel Learning","authors":"Cheng Zha","doi":"10.1109/icsgea.2019.00055","DOIUrl":"https://doi.org/10.1109/icsgea.2019.00055","url":null,"abstract":"Due to the difference of the speaker's language, speech emotion recognition tasks often face the situation that training data are not fully representative of test data. Therefore, the space extended by a kernel function. might not sufficient to describe different properties of data and thus produce a satisfactory decision function. In this wok, we apply multiple kernel learning to recognize the speech emotion of cross-language. Compared to SVM, multiple kernel learning can achieve better performance in cross-language speech emotion recognition tasks.","PeriodicalId":201721,"journal":{"name":"2019 International Conference on Smart Grid and Electrical Automation (ICSGEA)","volume":"70 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127323426","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：