Shiyu Zhang, Zhao Zhang, Fuzhen Zhuang, Zhiping Shi, Xu Han
{"title":"Compressing Knowledge Graph Embedding with Relational Graph Auto-encoder","authors":"Shiyu Zhang, Zhao Zhang, Fuzhen Zhuang, Zhiping Shi, Xu Han","doi":"10.1109/ICEIEC49280.2020.9152323","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152323","url":null,"abstract":"Knowledge graphs (KGs) are extremely useful resources for varieties of applications. However, with the large and steadily growing sizes of modern KGs, knowledge graph embeddings (KGE), which represent entities and relations in KGs into 32-bit floating-point vectors, become more and more expensive in terms of memory. To this end, in this paper, we propose a general framework to compress the embeddings from real-valued vectors to binary ones while preserving the inherent information of KGs. Specifically, the proposed framework utilizes relational graph auto-encoders as well as the Gumbel-Softmax trick to obtain the compressed representations. Our framework can be applied to a number of existing KGE models. Particularly, we extend state-of-the-art models TransE, DistMult, and ConvE in this paper. Finally, extensive experiments show that the proposed method successfully reduces the memory size of the embeddings by 92% while only leading to a loss of no more than 5% in the knowledge graph completion task.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127097036","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}
{"title":"Facial Expression Recognition based on The Fusion of CNN and SIFT Features","authors":"Huibai Wang, Si-yang Hou","doi":"10.1109/ICEIEC49280.2020.9152361","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152361","url":null,"abstract":"Facial expression recognition is an important part of computer vision. In order to improve the accuracy of expression recognition, and at the same time overcome the problem that a single feature cannot fully represent the details of facial expressions, this paper proposes CNN and SIFT feature fusion algorithms: 1) using a custom CNN network, combined with the idea of the Inception module, that is, adding 1×1 convolution, can more efficiently use computing resources, extract more global facial expression information under the same amount of calculation; 2) use cascade regression to calibrate the facial facial structure points, and then extract SIFT features, so that the key points are concentrated on expression contributions In a large area, the two features merge with each other and complement each other. Finally, the fused features are classified using Softmax to improve the accuracy of facial expression recognition. Tested on the CK+, JAFFE and FER2013 data sets, the experimental results show that this method is an efficient method of facial expression recognition.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127439981","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}
{"title":"Cross-domain Anomaly Detection for Power Industrial Control System","authors":"Yanjie Li, Xiaoyu Ji, Chenggang Li, Xiaofeng Xu, Wei Yan, Xu Yan, Yanjiao Chen, Wenyuan Xu","doi":"10.1109/ICEIEC49280.2020.9152334","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152334","url":null,"abstract":"In recent years, artificial intelligence has been widely used in the field of network security, which has significantly improved the effect of network security analysis and detection. However, because the power industrial control system is faced with the problem of shortage of attack data, the direct deployment of the network intrusion detection system based on artificial intelligence is faced with the problems of lack of data, low precision, and high false alarm rate. To solve this problem, we propose an anomaly traffic detection method based on cross-domain knowledge transferring. By using the TrAdaBoost algorithm, we achieve a lower error rate than using LSTM alone.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116992814","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}
Tao Wang, Aiping Li, Wenhao Xu, Jixing Yang, Zhi Zhang
{"title":"The Applied Research on WUI Fire Risk Prevention and Control","authors":"Tao Wang, Aiping Li, Wenhao Xu, Jixing Yang, Zhi Zhang","doi":"10.1109/ICEIEC49280.2020.9152223","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152223","url":null,"abstract":"Wildland-Urban Interface (WUI) fire is a new and important research field in forest fire fighting. This paper summarizes research status of WUI fire risk prevention and control, analyzes disaster inducement factors for it, and simply describes two typical WUI fire cases in China. Finally, two measures to improve the level of WUI fire risk monitoring and control are suggested, from aspects of improving academic research and building informatization system of risk monitoring and early warning, seperately.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121306269","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}
{"title":"Task Scheduling Optimization Based on Firefly Algorithm in Storm","authors":"Wen-Qi Duan, Liang Zhou","doi":"10.1109/ICEIEC49280.2020.9152349","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152349","url":null,"abstract":"As an open source distributed real-time computing framework, Storm has been widely used in social network, e-commerce, stock analysis and other fields. The default scheduler of Storm try to distribute all executors of topology among all worker nodes via an even strategy using a round-robin algorithm, which may result in performance bottleneck due to high topology processing latency and low throughput. Aiming at optimizating it, we design a task scheduling optimization based on firefly algorithm to reallocate tasks to more suitable nodes according to a task scheduling scheme. We use the location of firefly to represent a feasible scheduling scheme, and the fluorescence brightness represents the node’s ability to process tasks, while the process of finding the best task scheduling scheme is simulated as the process of firefly approaching the brightest position. The Experimental results show that compared to the default scheduling algorithm, the scheduling algorithm we proposed has better task scheduling efficiency, less average processing time and higher throughput, which can optimize the performance of the cluster.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"64 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122748643","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}
{"title":"Design of Relief Materials Storage and Transportation System Based on Blockchain Technology","authors":"Wei Guo, Pingyan Wei, Jixing Yang","doi":"10.1109/ICEIEC49280.2020.9152269","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152269","url":null,"abstract":"Blockchain technology has many features such as decentralization, traceability, tamper proof, and transparency. In this paper, a Relief Materials Storage and Transportation System based on blockchain technology is proposed. The blockchain and smart contract is studied to ensure the security of information exchange in the system. The technical architecture of the system is analyzed to be helpful for improving system efficiency and security.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126503182","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}
{"title":"Research on the Construction Method of Knowledge Graph for Electric Power Wireless Private Network","authors":"Q. Ou, Weijun Zheng, Weiwu Qi, Jinghui Fang, Zhe Liu, Yukun Zhu","doi":"10.1109/ICEIEC49280.2020.9152356","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152356","url":null,"abstract":"With the continuous increase of the scale of the power grid and the rapid development of the smart grid, the coverage of the wireless power private network has gradually expanded. How to make full use of the data information of the intelligent terminal of the power grid to realize unattended network monitoring and automatic operation and maintenance is an urgent problem to be solved at present. The knowledge graph construction model proposed in this article is to combine machine learning algorithms to convert huge and scattered terminal device data information and fault case data into professional domain knowledge graphs and store them in graph databases. In order to use knowledge reasoning to realize the treatment of grid faults in the region and assist decision-making. In this way, network failure prediction and decision guidance to the operation and maintenance personnel are realized. And improve the efficiency of power grid problem handling, save a lot of manpower monitoring, making the overall security control of the power grid better control.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124325691","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}
{"title":"Research on Intelligent Operation and Maintenance Management of Rail Telescopic Regulator","authors":"H. Chang, Yulin Zhao, Zhiqiang Rao, Yichen Li","doi":"10.1109/ICEIEC49280.2020.9152337","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152337","url":null,"abstract":"The regional track structure of the beam-end telescopic adjuster on the long-span bridges and the rail-lifting device at the beam joint is prone to disease. Through the in-depth discussion and research on the application of Building Information Model (BIM) technology in the high-speed railway rails telescopic regulator project, combining the regulator health monitoring with BIM technology, a BIM-based regulator monitoring method was proposed. It uses edge computing to preprocess the data, adopts a hierarchical design, combines each functional domain with each layer of BIM in parallel. It establishes a universal security chain association model, and it conducts chain domain and global domain analysis of the data. On this basis, according to the Construction Operations Building Information Exchange (COBie) standard, an as-built delivery information model is established to integrate and transfer data. It seamlessly transfers the construction and management process information about the rail telescopic regulator and BIM to the operation and maintenance stages. In this way, the real-time assessment and early warning of the rail telescopic regulator and the coordinated management of intelligent decision-making are realized, laying a foundation for future intelligent operation and maintenance.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123133699","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}
{"title":"Research on Low Cost Student Electronic Archives Management System in High-concurrency Environment","authors":"Zeyuan Cui, Bo Cui","doi":"10.1109/ICEIEC49280.2020.9152351","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152351","url":null,"abstract":"The Student Electronic Archives Management System (SEAMS) is one of the core systems used to carry out student work in colleges and universities. In recent years, with the increasing scale of Chinese universities, the existing SEAMS cannot handle the increased number of visits in their high-concurrency environments because of their outdated architecture. This paper analyzed the reasons and influences of the poor performance of the existing SEAMS, as well as the requirements of the SEAMS in colleges and universities and put forward a new SEAMS which works well in high-concurrency environments. The hybrid database and message queuing mechanism are used in the system to realize a high-performance and flexible SEAMS. The test results show that the efficiency improves significantly compared to single database and threaded system with request per second (RPS) above 9000.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129459527","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}
{"title":"Mitigating the Impacts of False Data Injection Attacks in Smart Grids using Deep Convolutional Neural Networks","authors":"Q.Y. Ge, C. Jiao","doi":"10.1109/ICEIEC49280.2020.9152355","DOIUrl":"https://doi.org/10.1109/ICEIEC49280.2020.9152355","url":null,"abstract":"The smart grid is vulnerable to cyberattacks due to the integration of information and communication technologies (ICT). The false data injection attack (FDIA) is a type of cyberattack that is against the state estimation of the power grid. It is imperative to mitigate the impacts of such a stealthy attack. In this paper, a deep convolutional neural network scheme was proposed. It has been evaluated on the IEEE 39-bus system using real-world load data and performs better than existed approaches.","PeriodicalId":352285,"journal":{"name":"2020 IEEE 10th International Conference on Electronics Information and Emergency Communication (ICEIEC)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121333954","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}