Pub Date : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482147
Wen Wang, Yibin Gao, Gang Yang, Zhumao Lu, Guodong Li, Yuan Ren, Dawei Wang
GIS equipment is widely used in power network and its reliability directly affects the safe and stable operation of power network. In this paper, a case of breakdown fault of 220kV GIS basin insulator is analyzed deeply. The fault gas chamber position is determined according to the fault recording diagram, SF6 gas decomposition products and other fault characteristics. Combined with laser ultrasonic testing instrument and spot disintegration inspection, the reasons for breakdown of GIS busbar basin insulator are analyzed comprehensively. It is confirmed that the basin insulator has cracks caused by uneven tightening torque of nuts on both sides of flange and damp flange gap. The electric field is distorted at the crack, causing the discharge along the surface. Finally, according to the cause of the fault, the follow-up measures for this kind of fault are put forward.
{"title":"Fault Analysis of GIS Basin Insulator Based on Laser Ultrasonic Detection Technology","authors":"Wen Wang, Yibin Gao, Gang Yang, Zhumao Lu, Guodong Li, Yuan Ren, Dawei Wang","doi":"10.1109/IMCEC51613.2021.9482147","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482147","url":null,"abstract":"GIS equipment is widely used in power network and its reliability directly affects the safe and stable operation of power network. In this paper, a case of breakdown fault of 220kV GIS basin insulator is analyzed deeply. The fault gas chamber position is determined according to the fault recording diagram, SF6 gas decomposition products and other fault characteristics. Combined with laser ultrasonic testing instrument and spot disintegration inspection, the reasons for breakdown of GIS busbar basin insulator are analyzed comprehensively. It is confirmed that the basin insulator has cracks caused by uneven tightening torque of nuts on both sides of flange and damp flange gap. The electric field is distorted at the crack, causing the discharge along the surface. Finally, according to the cause of the fault, the follow-up measures for this kind of fault are put forward.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122858766","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482278
Zhihong Hu, Q. Tian, Hongbo Wang, Zhenyu He
In recent years, Artificial Neural Network (ANN) has been widely used in digital handwriting recognition by virtue of its strong fault-tolerant ability and classification ability. However, in traditional recognition methods, taking the number of image pixels as the input number of neurons will cause problems such as long learning and training time and low efficiency. This paper combines principal component analysis (PCA) algorithm with BP algorithm for handwritten digit recognition. After image preprocessing, PCA algorithm is used to reduce dimension of original data. The first 10 principal components, the first 30 principal components, the first 45 principal components, and the first 60 principal components are sent to the neural network as input neurons for training. Then, the test data set was used for testing. Finally, the simulation was analyzed from three dimensions: training efficiency, learning time and identification accuracy. The results show that when the number of input neurons is 60 and the number of hidden layer neurons is 30, the highest recognition rate is only 0.13% lower than that of the number of input neurons is 784, but the training time of the neural network is reduced by 94 seconds, and the efficiency is improved by 32%. When the number of hidden layer neurons is 50, the highest recognition rate is only 0.25% lower than that of input neurons is 784, but the time is reduced by 237 seconds and the efficiency is improved by 63%. This design solves the problem of low learning efficiency in digital recognition well.
{"title":"Handwritten number recognition based on PCA and neural network","authors":"Zhihong Hu, Q. Tian, Hongbo Wang, Zhenyu He","doi":"10.1109/IMCEC51613.2021.9482278","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482278","url":null,"abstract":"In recent years, Artificial Neural Network (ANN) has been widely used in digital handwriting recognition by virtue of its strong fault-tolerant ability and classification ability. However, in traditional recognition methods, taking the number of image pixels as the input number of neurons will cause problems such as long learning and training time and low efficiency. This paper combines principal component analysis (PCA) algorithm with BP algorithm for handwritten digit recognition. After image preprocessing, PCA algorithm is used to reduce dimension of original data. The first 10 principal components, the first 30 principal components, the first 45 principal components, and the first 60 principal components are sent to the neural network as input neurons for training. Then, the test data set was used for testing. Finally, the simulation was analyzed from three dimensions: training efficiency, learning time and identification accuracy. The results show that when the number of input neurons is 60 and the number of hidden layer neurons is 30, the highest recognition rate is only 0.13% lower than that of the number of input neurons is 784, but the training time of the neural network is reduced by 94 seconds, and the efficiency is improved by 32%. When the number of hidden layer neurons is 50, the highest recognition rate is only 0.25% lower than that of input neurons is 784, but the time is reduced by 237 seconds and the efficiency is improved by 63%. This design solves the problem of low learning efficiency in digital recognition well.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131193001","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482069
Wen-Hou Ma, Yong Yu, Jun Hu
When small caliber projectile is moving at high speed underwater, the water around the projectile will cavitate. The geometric shape of the warhead with the best drag coefficient corresponds to the supercavitating state where the projectile is completely enveloped by cavitation. In this paper, aiming at a small-caliber projectile, the three-section cone is selected as the basic projectile, and the shape of the projectile is optimized with the drag coefficient as the optimization objective. The neural network and sequential quadratic programming (SQP) algorithm are combined to reduce the calculation amount in the optimization process and improve the optimization efficiency. The drag coefficient of the optimized projectile is reduced by about 40% compared with the projectile before optimization, and it can form a supercavitation that envelops the entire projectile.
{"title":"Optimization of small caliber projectile based on neural network","authors":"Wen-Hou Ma, Yong Yu, Jun Hu","doi":"10.1109/IMCEC51613.2021.9482069","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482069","url":null,"abstract":"When small caliber projectile is moving at high speed underwater, the water around the projectile will cavitate. The geometric shape of the warhead with the best drag coefficient corresponds to the supercavitating state where the projectile is completely enveloped by cavitation. In this paper, aiming at a small-caliber projectile, the three-section cone is selected as the basic projectile, and the shape of the projectile is optimized with the drag coefficient as the optimization objective. The neural network and sequential quadratic programming (SQP) algorithm are combined to reduce the calculation amount in the optimization process and improve the optimization efficiency. The drag coefficient of the optimized projectile is reduced by about 40% compared with the projectile before optimization, and it can form a supercavitation that envelops the entire projectile.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131475686","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}
The diversified demand for power business urgently needs to be realized through 5G network. Among them, network slicing technology can provide a "customized" virtual network according to different demands of the power system. Starting from the power grid business demand, this paper introduces the networking mode and key technologies of 5G slice technology in detail. And discussed the power end - to - end slicing solutions. The performance of 5G network slicing is evaluated based on the actual scenarios, and the influence of a different combination of network isolation methods on the performance of 5G network slicing is proposed. Finally, the application of 5G slicing technology in the power system is rationalized and prospected.
{"title":"Exploration and application of 5G network slice in electric power","authors":"Qiang Zhang, Yaping Li, Zhijun Zhang, Peng Xie, Qingrui Guo, Xuerang Guo","doi":"10.1109/IMCEC51613.2021.9482150","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482150","url":null,"abstract":"The diversified demand for power business urgently needs to be realized through 5G network. Among them, network slicing technology can provide a \"customized\" virtual network according to different demands of the power system. Starting from the power grid business demand, this paper introduces the networking mode and key technologies of 5G slice technology in detail. And discussed the power end - to - end slicing solutions. The performance of 5G network slicing is evaluated based on the actual scenarios, and the influence of a different combination of network isolation methods on the performance of 5G network slicing is proposed. Finally, the application of 5G slicing technology in the power system is rationalized and prospected.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128107636","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482089
Yuxin Li, Wenbin Gu, Xianliang Wang, Zeyu Chen
Various information technologies provide the manufacturing system massive data, which can support the decision optimization of product lifecycle management. However, the lack of effective use for advanced technologies prevents manufacturing industry from being automated and intelligent. Therefore, this paper proposes the smart shop floor and implementation mechanism. Meanwhile, based on the clustering and reinforcement learning, the brain agent and scheduling agent are designed to determine the approriate rule according to the shop floor state information, thus realizing the data-driven real-time scheduling. Experimental results show that the smart shop floor can effectively deal with disturbance events and has better performance compared with composite dispatching rules.
{"title":"Data-driven scheduling for smart shop floor via reinforcement learning with model-based clustering algorithm","authors":"Yuxin Li, Wenbin Gu, Xianliang Wang, Zeyu Chen","doi":"10.1109/IMCEC51613.2021.9482089","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482089","url":null,"abstract":"Various information technologies provide the manufacturing system massive data, which can support the decision optimization of product lifecycle management. However, the lack of effective use for advanced technologies prevents manufacturing industry from being automated and intelligent. Therefore, this paper proposes the smart shop floor and implementation mechanism. Meanwhile, based on the clustering and reinforcement learning, the brain agent and scheduling agent are designed to determine the approriate rule according to the shop floor state information, thus realizing the data-driven real-time scheduling. Experimental results show that the smart shop floor can effectively deal with disturbance events and has better performance compared with composite dispatching rules.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133256257","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482155
Weihui Zhao, Tongqing Sun, Xiaochen Wang
In order to ensure the security of service information release in metro, an information security release scheme was proposed at the software level based on the center and station control structure of passenger information system, considering the whole progress of editing, auditing, storage, transmission and display. Operation identity audit was realized through the face recognition technology and information encryption was realized through a hybrid encryption technology based on China commercial cryptographic algorithm. The scheme improves the reliability of information sources, privacy of data, security of operation, and avoids potential risks caused by illegal and politically sensitive information displayed on the terminal screen due to account leakage and data tampering and other malicious acts.
{"title":"Research on Information Security Release Scheme of Metro Intelligent Passenger Service","authors":"Weihui Zhao, Tongqing Sun, Xiaochen Wang","doi":"10.1109/IMCEC51613.2021.9482155","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482155","url":null,"abstract":"In order to ensure the security of service information release in metro, an information security release scheme was proposed at the software level based on the center and station control structure of passenger information system, considering the whole progress of editing, auditing, storage, transmission and display. Operation identity audit was realized through the face recognition technology and information encryption was realized through a hybrid encryption technology based on China commercial cryptographic algorithm. The scheme improves the reliability of information sources, privacy of data, security of operation, and avoids potential risks caused by illegal and politically sensitive information displayed on the terminal screen due to account leakage and data tampering and other malicious acts.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"119 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133674654","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482261
Yue Li, Longqing Shi, Peihe Zhai, Deming Zhang, Haibin Fan
With the continuous development of electronic technology, large-scale centralized control technology has also been greatly improved, the traditional RS485 bus technology, in the equipment network performance, a bus can be hooked up to 32 node equipment, to a large extent, to meet a number of warehouses or monitoring stations of the centralized control requirements. However, because the longest transmission distance of the RS485 bus can reach 1200 meters, even after the relay can not transmit a few kilometers distance, it is difficult to meet the requirements of more remote monitoring and control. At present, Ethernet communication has been widely used in life and production, Ethernet wiring is also very extensive, so the Ethernet communication mode instead of RS485 bus transmission mode is more conducive to the realization of a wide range of remote distributed network system. In this paper, for temperature and humidity monitoring system, with the characteristics of Ethernet without rewiring and convenient installation, a distributed temperature and humidity monitoring system based on Ethernet is developed, and the single chip computer is used to collect nodes, and the temperature and humidity monitoring system is completed by the design of the minimum system, the design of temperature and humidity collection circuit, A/D conversion circuit, Then through the RS485 bus will have a separate address of the unit temperature and humidity monitoring system connected to a bus, through a RS485 to TCP/IP protocol converter can realize single-chip Ethernet communication, greenhouse data transmission to the PC, remote monitoring function.
{"title":"Design of distributed temperature and humidity monitoring system based on single-chip microcomputer","authors":"Yue Li, Longqing Shi, Peihe Zhai, Deming Zhang, Haibin Fan","doi":"10.1109/IMCEC51613.2021.9482261","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482261","url":null,"abstract":"With the continuous development of electronic technology, large-scale centralized control technology has also been greatly improved, the traditional RS485 bus technology, in the equipment network performance, a bus can be hooked up to 32 node equipment, to a large extent, to meet a number of warehouses or monitoring stations of the centralized control requirements. However, because the longest transmission distance of the RS485 bus can reach 1200 meters, even after the relay can not transmit a few kilometers distance, it is difficult to meet the requirements of more remote monitoring and control. At present, Ethernet communication has been widely used in life and production, Ethernet wiring is also very extensive, so the Ethernet communication mode instead of RS485 bus transmission mode is more conducive to the realization of a wide range of remote distributed network system. In this paper, for temperature and humidity monitoring system, with the characteristics of Ethernet without rewiring and convenient installation, a distributed temperature and humidity monitoring system based on Ethernet is developed, and the single chip computer is used to collect nodes, and the temperature and humidity monitoring system is completed by the design of the minimum system, the design of temperature and humidity collection circuit, A/D conversion circuit, Then through the RS485 bus will have a separate address of the unit temperature and humidity monitoring system connected to a bus, through a RS485 to TCP/IP protocol converter can realize single-chip Ethernet communication, greenhouse data transmission to the PC, remote monitoring function.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133736723","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482256
Jian Huang
In 2020, the World Health Organization confirmed the new coronavirus (COVID-19) as a pandemic infectious disease. This virus affects the lives of tens of millions of people. Many countries have adopted compulsory measures to require residents to work and live at home and avoid unnecessary contact with the outside world. During this period, people expressed their feelings about the epidemic through various online platforms. In this article, we conducted an effective sentiment analysis on Weibo. These Weibo data are from January 1, 2020 to February 20, 2020, all related to COVID-19. The sentiment analysis of epidemic speech is to analyze people's views on COVID-19 during the epidemic. The results of the study concluded that although the epidemic is gradually getting worse, most people don't take a negative attitude.
{"title":"Prediction of Emotional Tendency of COVID-19 Speech Based on Pre-training Model","authors":"Jian Huang","doi":"10.1109/IMCEC51613.2021.9482256","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482256","url":null,"abstract":"In 2020, the World Health Organization confirmed the new coronavirus (COVID-19) as a pandemic infectious disease. This virus affects the lives of tens of millions of people. Many countries have adopted compulsory measures to require residents to work and live at home and avoid unnecessary contact with the outside world. During this period, people expressed their feelings about the epidemic through various online platforms. In this article, we conducted an effective sentiment analysis on Weibo. These Weibo data are from January 1, 2020 to February 20, 2020, all related to COVID-19. The sentiment analysis of epidemic speech is to analyze people's views on COVID-19 during the epidemic. The results of the study concluded that although the epidemic is gradually getting worse, most people don't take a negative attitude.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"87 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134317629","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482174
Hanshi Shentu, Liuyang Yuan, Weibin Zhang
This paper focuses on a two-level supply chain coordination problem consisting of a single supplier and multiple manufacturers under an uncertain environment. Firstly, a new bi-level programming model is proposed. Secondly, an innovative two-stage stochastic planning is combined into the lower-level manufacturer model, and a Progressive Hedging Algorithm (PHA) is designed to solve it. Then, the solved solution is substituted into the upper-level model to find the optimal solution of the bi-level programming. Finally, numerical experiments are used to verify the feasibility of the model and the algorithm.
{"title":"A new Bi-level programming model for uncertain supply chain problems","authors":"Hanshi Shentu, Liuyang Yuan, Weibin Zhang","doi":"10.1109/IMCEC51613.2021.9482174","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482174","url":null,"abstract":"This paper focuses on a two-level supply chain coordination problem consisting of a single supplier and multiple manufacturers under an uncertain environment. Firstly, a new bi-level programming model is proposed. Secondly, an innovative two-stage stochastic planning is combined into the lower-level manufacturer model, and a Progressive Hedging Algorithm (PHA) is designed to solve it. Then, the solved solution is substituted into the upper-level model to find the optimal solution of the bi-level programming. Finally, numerical experiments are used to verify the feasibility of the model and the algorithm.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"190 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134269880","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 : 2021-06-18DOI: 10.1109/IMCEC51613.2021.9482334
Sen Jing, Min Li, Yue Sun, Yue Zhang
Compound attacks have become the most threatening form of network attacks. Intrusion detection systems can detect attacks but cannot predict attacks. In order to more accurately reflect the network security situation, this paper analyzes the shortcomings of traditional attack prediction algorithms, and proposes to establish a hidden Markov model based on the change of the host's security status with the change of the observation sequence. The Baum-Welch algorithm is used to optimize the configuration parameters of the evaluation model. Quantitative analysis is used to obtain the security situation of the entire network, and the parameters of the HMM model are optimized to make the calculation of the predicted attack probability more accurate and reduce the frequency of false alarms. In the experimental test based on real data, the feasibility of this method is verified.
{"title":"Research on Prediction of Attack Behavior Based on HMM","authors":"Sen Jing, Min Li, Yue Sun, Yue Zhang","doi":"10.1109/IMCEC51613.2021.9482334","DOIUrl":"https://doi.org/10.1109/IMCEC51613.2021.9482334","url":null,"abstract":"Compound attacks have become the most threatening form of network attacks. Intrusion detection systems can detect attacks but cannot predict attacks. In order to more accurately reflect the network security situation, this paper analyzes the shortcomings of traditional attack prediction algorithms, and proposes to establish a hidden Markov model based on the change of the host's security status with the change of the observation sequence. The Baum-Welch algorithm is used to optimize the configuration parameters of the evaluation model. Quantitative analysis is used to obtain the security situation of the entire network, and the parameters of the HMM model are optimized to make the calculation of the predicted attack probability more accurate and reduce the frequency of false alarms. In the experimental test based on real data, the feasibility of this method is verified.","PeriodicalId":240400,"journal":{"name":"2021 IEEE 4th Advanced Information Management, Communicates, Electronic and Automation Control Conference (IMCEC)","volume":"90 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133150813","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：