At present, machine learning model is widely used in bank credit risk prediction, but there are still some problems in the actual use. Aiming at the limitations of single data source, static data and little data, we optimize the artificial neural network model. First, we use the network data mining technology and introduce the real-time news text data from the network as a dynamic supplement to the financial index data; The second is to use pre-training and fine-tuning strategy. Finally, we take 48 listed companies in agriculture, forestry, fishery and animal husbandry as the research objects for empirical analysis. By comparing the prediction accuracy and stability of the optimized model with that of the original model, we conclude that the optimized model has better precision improvement effect, higher data prediction stability and, more importantly, more outstanding performance in the prediction of nonperforming loans.
{"title":"Bank Credit Risk Analysis Based on Network Data Mining and Pre-training-fine-tuning ANN","authors":"Yong Hu, Menghan Fu, Jie Su, Ling Zhou","doi":"10.1145/3558819.3565214","DOIUrl":"https://doi.org/10.1145/3558819.3565214","url":null,"abstract":"At present, machine learning model is widely used in bank credit risk prediction, but there are still some problems in the actual use. Aiming at the limitations of single data source, static data and little data, we optimize the artificial neural network model. First, we use the network data mining technology and introduce the real-time news text data from the network as a dynamic supplement to the financial index data; The second is to use pre-training and fine-tuning strategy. Finally, we take 48 listed companies in agriculture, forestry, fishery and animal husbandry as the research objects for empirical analysis. By comparing the prediction accuracy and stability of the optimized model with that of the original model, we conclude that the optimized model has better precision improvement effect, higher data prediction stability and, more importantly, more outstanding performance in the prediction of nonperforming loans.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"26 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125927610","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}
Tingjiao Li, Xiaojun Zhang, Huan Pan, Weijun Zhu, J. Le
Transmission lines are very susceptible to failures caused by various reasons. This has always been a problem that plagues the stable operation of the system and safe power supply. At present, most transmission line fault diagnosis methods refer to a single fault information parameter, and often only consider the zero in the fault record. Sequence current information. Therefore, this paper proposes a transmission line multi-source fault data interconnection technology based on the operation inspection management and control platform, constructs the actual waveform database and related information database of transient traveling wave current under various fault causes of transmission line, uses wavelet packet analysis to extract the fault eigenvalues of different transmission line fault types, and uses machine learning algorithm complete the fault diagnosis of multi-source information fusion. Based on the fault characteristic value of the historical tripping line in Hunan area, the simulation results show that the correctness and effectiveness of the method in this paper are verified by actual calculation examples.
{"title":"Research on fault type diagnosis method of transmission line based on multi-source information fusion of operation inspection and control platform","authors":"Tingjiao Li, Xiaojun Zhang, Huan Pan, Weijun Zhu, J. Le","doi":"10.1145/3558819.3565113","DOIUrl":"https://doi.org/10.1145/3558819.3565113","url":null,"abstract":"Transmission lines are very susceptible to failures caused by various reasons. This has always been a problem that plagues the stable operation of the system and safe power supply. At present, most transmission line fault diagnosis methods refer to a single fault information parameter, and often only consider the zero in the fault record. Sequence current information. Therefore, this paper proposes a transmission line multi-source fault data interconnection technology based on the operation inspection management and control platform, constructs the actual waveform database and related information database of transient traveling wave current under various fault causes of transmission line, uses wavelet packet analysis to extract the fault eigenvalues of different transmission line fault types, and uses machine learning algorithm complete the fault diagnosis of multi-source information fusion. Based on the fault characteristic value of the historical tripping line in Hunan area, the simulation results show that the correctness and effectiveness of the method in this paper are verified by actual calculation examples.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"18 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126096220","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}
Yuli Song, He Sun, Jiaxing Wang, Wenhe Liu, Jianhui Zhang
The current mimic adjudication model is centered on a single adjudicator, and the adjudication algorithm is relatively single and static, which cannot cope with today's complex and changeable network environment. First, a distributed adjudication model is proposed to decentralize the adjudicator, each sub-arbiter is different from the previous use of all executive results, but randomly selects the output of the executive as the input incentive. Secondly, based on this model, a consensus mechanism algorithm is proposed to iteratively normalize the local adjudication results of the sub-arbiters to achieve the global optimal adjudication result. The analysis of the simulation experiment results shows that the algorithm proposed in this paper is more accurate than the traditional adjudication algorithm when multiple executors are online. The algorithm can further reduce the risk of common-mode escape and improve the security of the mimic defense system.
{"title":"Distributed Mimic Judgment Algorithm based on Multi-Strategy Decentralization Model","authors":"Yuli Song, He Sun, Jiaxing Wang, Wenhe Liu, Jianhui Zhang","doi":"10.1145/3558819.3565150","DOIUrl":"https://doi.org/10.1145/3558819.3565150","url":null,"abstract":"The current mimic adjudication model is centered on a single adjudicator, and the adjudication algorithm is relatively single and static, which cannot cope with today's complex and changeable network environment. First, a distributed adjudication model is proposed to decentralize the adjudicator, each sub-arbiter is different from the previous use of all executive results, but randomly selects the output of the executive as the input incentive. Secondly, based on this model, a consensus mechanism algorithm is proposed to iteratively normalize the local adjudication results of the sub-arbiters to achieve the global optimal adjudication result. The analysis of the simulation experiment results shows that the algorithm proposed in this paper is more accurate than the traditional adjudication algorithm when multiple executors are online. The algorithm can further reduce the risk of common-mode escape and improve the security of the mimic defense system.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123247685","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}
Image recognition is one of the key technologies in the information age. The use of image recognition technology can complete the tasks that cannot be realized by traditional sensor technology. At the same time, with the help of the fusion of image recognition and multi-source information, the monitoring effect can be better and accurate. With the continuous development of computer technology, the computing power of computer has been further improved, and the processing ability of information has been greatly improved. Relying on the intelligent image recognition algorithm, we can improve the recognition accuracy and reduce the recognition time, which will play an important role in the field of artificial intelligence in the future. This paper analyzes the current situation and characteristics of the development of intelligent image recognition technology, and puts forward corresponding suggestions for the realization and improvement of this technology.
{"title":"Research on computer intelligent image recognition technology","authors":"Yu Luo","doi":"10.1145/3558819.3565181","DOIUrl":"https://doi.org/10.1145/3558819.3565181","url":null,"abstract":"Image recognition is one of the key technologies in the information age. The use of image recognition technology can complete the tasks that cannot be realized by traditional sensor technology. At the same time, with the help of the fusion of image recognition and multi-source information, the monitoring effect can be better and accurate. With the continuous development of computer technology, the computing power of computer has been further improved, and the processing ability of information has been greatly improved. Relying on the intelligent image recognition algorithm, we can improve the recognition accuracy and reduce the recognition time, which will play an important role in the field of artificial intelligence in the future. This paper analyzes the current situation and characteristics of the development of intelligent image recognition technology, and puts forward corresponding suggestions for the realization and improvement of this technology.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123560516","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}
Maximum power point tracking (MPPT) is crucial for photovoltaic (PV) systems to adjust gain energy under various environmental conditions. However, the limitations of conventional MPPT will lead to the energy loss caused by steady-state three-level oscillations and dynamic slow response. Moreover, the traditional P&O has a drift problem in boosting irradiation intensity. The drift problem is serious when the irradiation intensity increases rapidly. A modified drift-free beta method combined with adaptive step-size and illumination factor is proposed to avoid the drift phenomenon and ameliorate the dynamic and steady-state capability. An intermediate variable beta (β) is introduced for fast convergence speed enhancement. Furthermore, the illumination amplitude factor is developed to improve the tracking accuracy and reduce the instability of sudden irradiation changes. By incorporating the sign of current variation, the drift issue is addressed. The effectiveness of the proposed control is validated in MATLAB with various conditions.
{"title":"Modified Drift-free Beta Method with Illumination Factor for Photovoltaic Systems","authors":"Huixiang Dai","doi":"10.1145/3558819.3565130","DOIUrl":"https://doi.org/10.1145/3558819.3565130","url":null,"abstract":"Maximum power point tracking (MPPT) is crucial for photovoltaic (PV) systems to adjust gain energy under various environmental conditions. However, the limitations of conventional MPPT will lead to the energy loss caused by steady-state three-level oscillations and dynamic slow response. Moreover, the traditional P&O has a drift problem in boosting irradiation intensity. The drift problem is serious when the irradiation intensity increases rapidly. A modified drift-free beta method combined with adaptive step-size and illumination factor is proposed to avoid the drift phenomenon and ameliorate the dynamic and steady-state capability. An intermediate variable beta (β) is introduced for fast convergence speed enhancement. Furthermore, the illumination amplitude factor is developed to improve the tracking accuracy and reduce the instability of sudden irradiation changes. By incorporating the sign of current variation, the drift issue is addressed. The effectiveness of the proposed control is validated in MATLAB with various conditions.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126620552","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}
In the context of continuous development of embedded technology and gradual implementation of industrial intelligence, intelligent devices based on embedded systems are widely used in smart homes, smart agriculture, smart factories, etc. In various application scenarios of intelligent devices, the environmental monitoring capability of the devices often measures the degree of intelligence of an industry, therefore, it is necessary to design a temperature detection system with high accuracy and real-time. Currently, temperature detection systems are often based on a microcontroller as the core, which is no longer applicable for application scenarios requiring high accuracy and real-time performance. Therefore, this paper aims to develop a low-power, low-cost temperature detection system with high accuracy and real-time based on SoC.
{"title":"Research and design of SoC-based environmental temperature detection system","authors":"Ye Zheng","doi":"10.1145/3558819.3565104","DOIUrl":"https://doi.org/10.1145/3558819.3565104","url":null,"abstract":"In the context of continuous development of embedded technology and gradual implementation of industrial intelligence, intelligent devices based on embedded systems are widely used in smart homes, smart agriculture, smart factories, etc. In various application scenarios of intelligent devices, the environmental monitoring capability of the devices often measures the degree of intelligence of an industry, therefore, it is necessary to design a temperature detection system with high accuracy and real-time. Currently, temperature detection systems are often based on a microcontroller as the core, which is no longer applicable for application scenarios requiring high accuracy and real-time performance. Therefore, this paper aims to develop a low-power, low-cost temperature detection system with high accuracy and real-time based on SoC.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"138 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115568922","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}
In order for computers to understand the semantics of human actions and give correct feedback, action recognition technology is used in interactive tasks. Unity can easily complete various three-dimensional interactive developments and create virtual simulation content with an active rate of up to 30%, occupying an important position in the virtual reality industry. Therefore, this software was chosen to complete the virtual reality interaction based on gesture recognition application. This article first builds the initial virtual reality interactive platform through Unity software, and then applies the gesture recognition method proposed above to the designed interactive platform, so that the computer can accurately understand the meaning of human actions when people are doing actions. This article mainly introduces the construction of the experimental platform of the entire virtual reality system and the real-time realization of the motion recognition system.
{"title":"Research on Key Technologies of Human Action Intelligent Recognition based on Virtual Reality","authors":"Huihong Chen","doi":"10.1145/3558819.3565205","DOIUrl":"https://doi.org/10.1145/3558819.3565205","url":null,"abstract":"In order for computers to understand the semantics of human actions and give correct feedback, action recognition technology is used in interactive tasks. Unity can easily complete various three-dimensional interactive developments and create virtual simulation content with an active rate of up to 30%, occupying an important position in the virtual reality industry. Therefore, this software was chosen to complete the virtual reality interaction based on gesture recognition application. This article first builds the initial virtual reality interactive platform through Unity software, and then applies the gesture recognition method proposed above to the designed interactive platform, so that the computer can accurately understand the meaning of human actions when people are doing actions. This article mainly introduces the construction of the experimental platform of the entire virtual reality system and the real-time realization of the motion recognition system.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"62 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116063307","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}
Lan Zhu, Huan-Ting Lin, Xia Chen, Wei Liang, Zhen Cheng, Dongheng Shao, Hui Yu, Y. Zheng, Weicheng Ma
The indoor positioning of the robot is a prerequisite for the robot to complete various tasks indoors. Human's own visual perception positioning is to provide self positioning and navigation after the brain analyzes and judges the information of various objects and the relative distance of various objects through the eyes. This paper innovatively allows the robot to imitate the habit of human beings in indoor visual perception and positioning, and uses the depth camera to recognize the distance information and the object recognition function of the yolov3 model. In the mapping stage, the global three-dimensional coordinates of the objects that can be recognized by the depth camera are marked. So that the robot can use the three-sided ranging method to locate in the actual positioning, and combine the data of wheel odometer and IMU. Using the particle filter algorithm that increases the priority particles, the robot can imitate the human's visual perception positioning indoors. Compared with other methods that need to analyze and match too many feature points for visual positioning, the amount of data stored in the early map construction in this paper is less, and the robot can be repositioned more quickly after encountering robot kidnapping and hijacking. Algorithms are more in line with human thinking and have stronger robustness and spatial portability.
{"title":"Indoor Robot Localization Based on Visual Perception and on Particle Filter Algorithm of Increasing Priority Particles","authors":"Lan Zhu, Huan-Ting Lin, Xia Chen, Wei Liang, Zhen Cheng, Dongheng Shao, Hui Yu, Y. Zheng, Weicheng Ma","doi":"10.1145/3558819.3565461","DOIUrl":"https://doi.org/10.1145/3558819.3565461","url":null,"abstract":"The indoor positioning of the robot is a prerequisite for the robot to complete various tasks indoors. Human's own visual perception positioning is to provide self positioning and navigation after the brain analyzes and judges the information of various objects and the relative distance of various objects through the eyes. This paper innovatively allows the robot to imitate the habit of human beings in indoor visual perception and positioning, and uses the depth camera to recognize the distance information and the object recognition function of the yolov3 model. In the mapping stage, the global three-dimensional coordinates of the objects that can be recognized by the depth camera are marked. So that the robot can use the three-sided ranging method to locate in the actual positioning, and combine the data of wheel odometer and IMU. Using the particle filter algorithm that increases the priority particles, the robot can imitate the human's visual perception positioning indoors. Compared with other methods that need to analyze and match too many feature points for visual positioning, the amount of data stored in the early map construction in this paper is less, and the robot can be repositioned more quickly after encountering robot kidnapping and hijacking. Algorithms are more in line with human thinking and have stronger robustness and spatial portability.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122000628","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}
Cycling Road time trial as a kind of Olympic events, many athletes every day hard training, to the medal launched impact. Meanwhile, besides completing targeted physical training and technical training provided by the coach, being familiar with the race track and reasonably planning their power output in the whole race process according to the road conditions of the race track and themselves may make an operator stand out from many competitors and improve the probability of winning. This paper, mainly through the establishment of the simulation model, fully consider the cyclist on the travel distance of the environment and the rider's energy, using multiple optimized particle swarm algorithm, gives the rider the process of the whole ride as far as possible the optimal ratio of power, to maximize its energy utilization, achieves the can in the shortest possible time to complete the competition.
{"title":"Design of a Cycling Rider Model based on Multi-objective Particle Swarm Optimization algorithm","authors":"Qian Li","doi":"10.1145/3558819.3565115","DOIUrl":"https://doi.org/10.1145/3558819.3565115","url":null,"abstract":"Cycling Road time trial as a kind of Olympic events, many athletes every day hard training, to the medal launched impact. Meanwhile, besides completing targeted physical training and technical training provided by the coach, being familiar with the race track and reasonably planning their power output in the whole race process according to the road conditions of the race track and themselves may make an operator stand out from many competitors and improve the probability of winning. This paper, mainly through the establishment of the simulation model, fully consider the cyclist on the travel distance of the environment and the rider's energy, using multiple optimized particle swarm algorithm, gives the rider the process of the whole ride as far as possible the optimal ratio of power, to maximize its energy utilization, achieves the can in the shortest possible time to complete the competition.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129544403","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}
Equipment management is essential for power grid enterprises to achieve scientific management, including project investment management, maintenance, operation management, and cost budget management. Screening standard power grid equipment is fundamental for power grid projects and power grid operations. This paper proposes to use an optimized C4.5 algorithm to screen typical assets. The optimized C4.5 algorithm simplifies calculating the information gain rate and is more efficient after running. In this article, all of 726 samples are used to exam the accuracy of the DT in the application of power grid typical equipment. The results show that the classification accuracy of the modified method is 93.17%, the classification error rate is 3.8%, and the classification omission rate is 4.12%.
{"title":"Typical Equipment Classification based on Optimized C4.5 Algorithm","authors":"Fei Lan, Huaqiang Shen, S. Jin, Quanhui Sun","doi":"10.1145/3558819.3565081","DOIUrl":"https://doi.org/10.1145/3558819.3565081","url":null,"abstract":"Equipment management is essential for power grid enterprises to achieve scientific management, including project investment management, maintenance, operation management, and cost budget management. Screening standard power grid equipment is fundamental for power grid projects and power grid operations. This paper proposes to use an optimized C4.5 algorithm to screen typical assets. The optimized C4.5 algorithm simplifies calculating the information gain rate and is more efficient after running. In this article, all of 726 samples are used to exam the accuracy of the DT in the application of power grid typical equipment. The results show that the classification accuracy of the modified method is 93.17%, the classification error rate is 3.8%, and the classification omission rate is 4.12%.","PeriodicalId":373484,"journal":{"name":"Proceedings of the 7th International Conference on Cyber Security and Information Engineering","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-09-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129878152","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：