Yang Ma, Guangquan Cheng, Xingxing Liang, Yuan Wang, Yuzhen Zhou
Heterogeneous graph representation learning aims to learn meaningful representation vectors from heterogeneous networks in low dimension, so as to realize the extraction of structure and attribute features of the networks. Embedding vector is the basis and key of complex network analysis, which can be used in the downstream tasks. The key points in heterogeneous graph neural networks are: how to define heterogeneous neighbors and how to aggregate them. Although a lot of work has been devoted to homogeneous or heterogeneous network representation, the effective combination of network structure information and node attribute information, especially the effective use of meta-path containing specific semantic information is still rare. In this paper, we propose a meta-path-based heterogeneous graph neural network model. Firstly, we apply meta-path to sample the heterogeneous neighbors of each node in the network, and aggregate the features of the same type of nodes together to form type-related embedding; then, attention mechanism is applied to aggregate the neighbor information of different types of node; finally we train the end-to-end model by reducing the context loss. Experiments proved the validity of the model and significantly improved current results.
{"title":"Heterogeneous Graph Neural Networks Based on Meta-path","authors":"Yang Ma, Guangquan Cheng, Xingxing Liang, Yuan Wang, Yuzhen Zhou","doi":"10.1145/3446132.3446146","DOIUrl":"https://doi.org/10.1145/3446132.3446146","url":null,"abstract":"Heterogeneous graph representation learning aims to learn meaningful representation vectors from heterogeneous networks in low dimension, so as to realize the extraction of structure and attribute features of the networks. Embedding vector is the basis and key of complex network analysis, which can be used in the downstream tasks. The key points in heterogeneous graph neural networks are: how to define heterogeneous neighbors and how to aggregate them. Although a lot of work has been devoted to homogeneous or heterogeneous network representation, the effective combination of network structure information and node attribute information, especially the effective use of meta-path containing specific semantic information is still rare. In this paper, we propose a meta-path-based heterogeneous graph neural network model. Firstly, we apply meta-path to sample the heterogeneous neighbors of each node in the network, and aggregate the features of the same type of nodes together to form type-related embedding; then, attention mechanism is applied to aggregate the neighbor information of different types of node; finally we train the end-to-end model by reducing the context loss. Experiments proved the validity of the model and significantly improved current results.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"C-25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126479880","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}
Einstein Chess is a small game where winning chess depends on "luck". A good "luck" is supported by many complicated algorithms. One of the innovations of this article is to use TCP/IP socket technology to realize automatic computer game and provide higher efficiency for code testing.The second is that this article designs and implements three Einsteins game algorithms: a completely random chess strategy, a chess strategy based on a static evaluation function, and a dynamic chess strategy based on UCT. Experimental results show that the dynamic evaluation function based on UCT is better than the other two algorithms, and won the first prize in the 2020 Chinese University Student Computer Game Competition.
{"title":"Research and Realization of Einstein Chess Game System and Autoplay Machine Automatic Game","authors":"Yiwei Hao, D. Cai, Shuqin Li","doi":"10.1145/3446132.3446177","DOIUrl":"https://doi.org/10.1145/3446132.3446177","url":null,"abstract":"Einstein Chess is a small game where winning chess depends on \"luck\". A good \"luck\" is supported by many complicated algorithms. One of the innovations of this article is to use TCP/IP socket technology to realize automatic computer game and provide higher efficiency for code testing.The second is that this article designs and implements three Einsteins game algorithms: a completely random chess strategy, a chess strategy based on a static evaluation function, and a dynamic chess strategy based on UCT. Experimental results show that the dynamic evaluation function based on UCT is better than the other two algorithms, and won the first prize in the 2020 Chinese University Student Computer Game Competition.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122783630","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}
Laser active detection technology based on the "cat's eye effect" is becoming more and more important in the fields of photoelectric reconnaissance and tracking. It is an effective means for identifying and interfering with photoelectric reconnaissance targets. In order to improve the accuracy and detection speed of cat-eye effect target recognition, this paper proposes a cat-eye effect target recognition method based on deep convolutional neural network. In the process of identifying cat-eye targets: preprocess the detected active and passive images to find candidate target regions, use classification network to screen the candidate target regions, and finally identify cat-eye effect targets. The experiment verifies the advantages of this method over the traditional cat-eye effect target recognition algorithm. The proposed method has high accuracy, fast recognition speed, and can be used for real-time detection.
{"title":"The Cat's Eye Effect Target Recognition Method Based on deep convolutional neural network","authors":"Wenlong Chen, Laixian Zhang","doi":"10.1145/3446132.3446193","DOIUrl":"https://doi.org/10.1145/3446132.3446193","url":null,"abstract":"Laser active detection technology based on the \"cat's eye effect\" is becoming more and more important in the fields of photoelectric reconnaissance and tracking. It is an effective means for identifying and interfering with photoelectric reconnaissance targets. In order to improve the accuracy and detection speed of cat-eye effect target recognition, this paper proposes a cat-eye effect target recognition method based on deep convolutional neural network. In the process of identifying cat-eye targets: preprocess the detected active and passive images to find candidate target regions, use classification network to screen the candidate target regions, and finally identify cat-eye effect targets. The experiment verifies the advantages of this method over the traditional cat-eye effect target recognition algorithm. The proposed method has high accuracy, fast recognition speed, and can be used for real-time detection.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114181013","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}
With the construction of the electronic medical record system, medical record data begins to accumulate, and how to extract essential information from these resources has become a concern. And named entity recognition(NER) is the first step. With the help of doctors, we built a small Chinese electronic medical record annotation corpus. But the NER supervision method requires a large amount of manually labeled corpus. So to reduce the cost of it and make better use of the unlabeled corpus, this paper proposes a semi-supervised Chinese electronic medical record NER model based on ALBERT-BiLSTM-CRF which named CEMRNER. The model uses a Bidirectional Long Short Term Memory network (BiLSTM) and a Conditional Random Field model (CRF) to train the data and introduces the pre-training language model ALBERT to solve the problem of Chinese representation. At the same time, we propose a dual selected strategy to select the high confidence samples and expand the training set. The dual strategy can ensure the accuracy i automatically labeled data, and reduce the error iteration in semi-supervised learning. The experiment and analysis show that compared with other models, this method is more accurate and comprehensive. The precision, recall rate, and F1Score are 85.45%, 87.81%, and 86.61%, respectively. The paper proves that using a semi-supervised method and pre-training ALBERT can improve the accuracy of recognition under the condition of less labeled data.
{"title":"Research on Named Entity Recognition in Chinese EMR Based on Semi-Supervised Learning with Dual Selected Strategy","authors":"Jianzhuo Yan, Yanan Geng, Hongxia Xu, Yongchuan Yu, Shaofeng Tan, Dongdong He","doi":"10.1145/3446132.3446407","DOIUrl":"https://doi.org/10.1145/3446132.3446407","url":null,"abstract":"With the construction of the electronic medical record system, medical record data begins to accumulate, and how to extract essential information from these resources has become a concern. And named entity recognition(NER) is the first step. With the help of doctors, we built a small Chinese electronic medical record annotation corpus. But the NER supervision method requires a large amount of manually labeled corpus. So to reduce the cost of it and make better use of the unlabeled corpus, this paper proposes a semi-supervised Chinese electronic medical record NER model based on ALBERT-BiLSTM-CRF which named CEMRNER. The model uses a Bidirectional Long Short Term Memory network (BiLSTM) and a Conditional Random Field model (CRF) to train the data and introduces the pre-training language model ALBERT to solve the problem of Chinese representation. At the same time, we propose a dual selected strategy to select the high confidence samples and expand the training set. The dual strategy can ensure the accuracy i automatically labeled data, and reduce the error iteration in semi-supervised learning. The experiment and analysis show that compared with other models, this method is more accurate and comprehensive. The precision, recall rate, and F1Score are 85.45%, 87.81%, and 86.61%, respectively. The paper proves that using a semi-supervised method and pre-training ALBERT can improve the accuracy of recognition under the condition of less labeled data.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131623437","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 this paper we studied the health status of college students from the physiological and psychological aspects, and determined the evaluation indexes of sub healthy status in college students. Firstly, by using the literature analysis method, referring to the internationally recognized five health scales (EQ-5D, CSHS, SF-36, WHOQOL-100 and sub healthy status questionnaire), the relevant factors of College Students' physical and mental sub healthy were found out, and an items pool of candidate indicators of College Students' sub healthy was established. Then, using Delphi method, experts were invited to compare and judge the indicators of items pool and screen them to select reasonable and effective sub healthy evaluation indexes items. As a result, according to the indexes screening criteria, after two rounds of expert consultation, 7 first-class indicators and 54 second-class indicators were determined. Among them, 7 first-class indicators were physiological function, energy, exercise ability, physical symptoms, psychological cognition, emotion and psychological symptoms. The selected indicators can better respond to the actual needs of college students and meet the needs of constructing the sub healthy evaluation indexes scale for college students, so as to comprehensively evaluate the health status of college students and carry out accurate health management and service.
{"title":"Research on sub healthy evaluation index selection of college students based on Delphi Methodology","authors":"Liufen Peng, Miao Chen, J. Yang, B. Feng","doi":"10.1145/3446132.3446162","DOIUrl":"https://doi.org/10.1145/3446132.3446162","url":null,"abstract":"In this paper we studied the health status of college students from the physiological and psychological aspects, and determined the evaluation indexes of sub healthy status in college students. Firstly, by using the literature analysis method, referring to the internationally recognized five health scales (EQ-5D, CSHS, SF-36, WHOQOL-100 and sub healthy status questionnaire), the relevant factors of College Students' physical and mental sub healthy were found out, and an items pool of candidate indicators of College Students' sub healthy was established. Then, using Delphi method, experts were invited to compare and judge the indicators of items pool and screen them to select reasonable and effective sub healthy evaluation indexes items. As a result, according to the indexes screening criteria, after two rounds of expert consultation, 7 first-class indicators and 54 second-class indicators were determined. Among them, 7 first-class indicators were physiological function, energy, exercise ability, physical symptoms, psychological cognition, emotion and psychological symptoms. The selected indicators can better respond to the actual needs of college students and meet the needs of constructing the sub healthy evaluation indexes scale for college students, so as to comprehensively evaluate the health status of college students and carry out accurate health management and service.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"186 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124319114","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}
Feature selection has become an important research issue in the fields of pattern recognition, data mining and machine learning. When processing some high-dimensional data, traditional machine learning algorithms may not be able to get satisfactory results, while feature selection can filter features of high-dimensional data before model training, reduce the number of features, and thus reduce the impact of problems caused by high-dimensional data. Feature selection can simultaneously eliminate features that are less correlated with categories or redundant with selected features, so as to improve classification accuracy and learning and training efficiency of high-dimensional data tasks. However, existing methods may remove redundancy inadequately or excessively in some cases. Therefore, this paper proposes a criterion for the feature redundancy, and based on this criterion, designs an effective feature selection algorithm to remove redundant features on the premise of ensuring maximum relevance to the target variable. The effectiveness and efficiency of the proposed algorithm are verified by experimental comparison with other algorithms that can remove redundant features.
{"title":"A New Method for Redundancy Analysis in Feature Selection","authors":"Mei Wang, Xinrong Tao, Fei Han","doi":"10.1145/3446132.3446153","DOIUrl":"https://doi.org/10.1145/3446132.3446153","url":null,"abstract":"Feature selection has become an important research issue in the fields of pattern recognition, data mining and machine learning. When processing some high-dimensional data, traditional machine learning algorithms may not be able to get satisfactory results, while feature selection can filter features of high-dimensional data before model training, reduce the number of features, and thus reduce the impact of problems caused by high-dimensional data. Feature selection can simultaneously eliminate features that are less correlated with categories or redundant with selected features, so as to improve classification accuracy and learning and training efficiency of high-dimensional data tasks. However, existing methods may remove redundancy inadequately or excessively in some cases. Therefore, this paper proposes a criterion for the feature redundancy, and based on this criterion, designs an effective feature selection algorithm to remove redundant features on the premise of ensuring maximum relevance to the target variable. The effectiveness and efficiency of the proposed algorithm are verified by experimental comparison with other algorithms that can remove redundant features.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115130779","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}
Although progress has been made in image captioning, machine-generated captions and human-generated captions are still quite distinct. Machine-generated captions perform well based on automated metrics. However, they lack naturalness, an essential characteristic of human language, because they maximize the likelihood of training samples. We propose a novel model to generate more human-like captions than has been accomplished with prior methods. Our model includes an attention mechanism, a bidirectional language generation model, and a conditional generative adversarial network. Specifically, the attention mechanism captures image details by segmenting important information into smaller pieces. The bidirectional language generation model produces human-like sentences by considering multiple perspectives. Simultaneously, the conditional generative adversarial network increases sentence quality by comparing a set of captions. To evaluate the performance of our model, we compare human preferences for BraIN-generated captions with baseline methods. We also compare results with actual human-generated captions using automated metrics. Results show our model is capable of producing more human-like captions than baseline methods.
{"title":"BraIN: A Bidirectional Generative Adversarial Networks for image captions","authors":"Yuhui Wang, D. Cook","doi":"10.1145/3446132.3446406","DOIUrl":"https://doi.org/10.1145/3446132.3446406","url":null,"abstract":"Although progress has been made in image captioning, machine-generated captions and human-generated captions are still quite distinct. Machine-generated captions perform well based on automated metrics. However, they lack naturalness, an essential characteristic of human language, because they maximize the likelihood of training samples. We propose a novel model to generate more human-like captions than has been accomplished with prior methods. Our model includes an attention mechanism, a bidirectional language generation model, and a conditional generative adversarial network. Specifically, the attention mechanism captures image details by segmenting important information into smaller pieces. The bidirectional language generation model produces human-like sentences by considering multiple perspectives. Simultaneously, the conditional generative adversarial network increases sentence quality by comparing a set of captions. To evaluate the performance of our model, we compare human preferences for BraIN-generated captions with baseline methods. We also compare results with actual human-generated captions using automated metrics. Results show our model is capable of producing more human-like captions than baseline methods.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123469188","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}
Yanghui Fu, Xingxing Liang, Yang Ma, Kuihua Huang, Yan Li
The successful application of deep reinforcement learning in RTS games such as StarCraft II has inspired people to apply multi-agent deep reinforcement learning(MADRL) to more fields. In the field of wargame, hexagonal maps are often used for simulation, which can't adapt to the rapid development of wargame. In continuous space of wargame, we construct a ship-defense scenario that includes multiple aircraft and ships. We apply deep Q network(DQN) method to MADRL, CNN to extract the features of multiple entities, and a centralized and distributed decision-making training architecture to control the aircraft's fixed-wing module components. Experiment results demonstrate the effectiveness of the proposed formulation, which show that the CNN-based feature extraction model can effectively defeat the built-in rule bot with multiple levels, and the training effect of CNN-based is better than the feature extraction method by full connection.
{"title":"Coordinating Multi-Agent Deep Reinforcement Learning in Wargame","authors":"Yanghui Fu, Xingxing Liang, Yang Ma, Kuihua Huang, Yan Li","doi":"10.1145/3446132.3446137","DOIUrl":"https://doi.org/10.1145/3446132.3446137","url":null,"abstract":"The successful application of deep reinforcement learning in RTS games such as StarCraft II has inspired people to apply multi-agent deep reinforcement learning(MADRL) to more fields. In the field of wargame, hexagonal maps are often used for simulation, which can't adapt to the rapid development of wargame. In continuous space of wargame, we construct a ship-defense scenario that includes multiple aircraft and ships. We apply deep Q network(DQN) method to MADRL, CNN to extract the features of multiple entities, and a centralized and distributed decision-making training architecture to control the aircraft's fixed-wing module components. Experiment results demonstrate the effectiveness of the proposed formulation, which show that the CNN-based feature extraction model can effectively defeat the built-in rule bot with multiple levels, and the training effect of CNN-based is better than the feature extraction method by full connection.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"29 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123496012","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 recent years, with the accelerated expansion of applications in the UAV field and the continuous growth of the industry, the increasingly mature UAV market has also put forward new requirements for technological development. "UAV cluster technology" is rising at this moment and is getting more and more attention. The multi-UAV cluster test requires architecture to support it. In order to solve a large number of data stream access, communication and cost issues in the multi-UAV cluster system, it is based on the Internet of Things, wireless ad hoc network, database, etc. A support system for multiple drones. Analysis and demonstration show that, compared with previous related research, this new architecture is systematic and complete, and meets the special application environment of large business data flow and large infrastructure workload for multiple simulation drone cluster tests, and has high reliability and operability.
{"title":"Design and Research of Support System for Multiple Simulation UAVs","authors":"Dequn Zhao, Liqi Wu, Guangmin Sun, Haitao Zhu, Sheng Cheng, Xinyu Qu","doi":"10.1145/3446132.3446172","DOIUrl":"https://doi.org/10.1145/3446132.3446172","url":null,"abstract":"In recent years, with the accelerated expansion of applications in the UAV field and the continuous growth of the industry, the increasingly mature UAV market has also put forward new requirements for technological development. \"UAV cluster technology\" is rising at this moment and is getting more and more attention. The multi-UAV cluster test requires architecture to support it. In order to solve a large number of data stream access, communication and cost issues in the multi-UAV cluster system, it is based on the Internet of Things, wireless ad hoc network, database, etc. A support system for multiple drones. Analysis and demonstration show that, compared with previous related research, this new architecture is systematic and complete, and meets the special application environment of large business data flow and large infrastructure workload for multiple simulation drone cluster tests, and has high reliability and operability.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"214 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115568405","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}
Junjie Chen, Lingxiao Cheng, Enbo Cong, Chunlei Yang, Xuesi Li
With the development of the technology, the electrical system products is becoming more and more complicated and more and more diversified. It is more and more important to use the intelligent method to conduct the fault diagnosis and comprehensive evaluation to ensure the efficiency of the electrical system. This paper puts forward a fault diagnosis and comprehensive evaluation methods for the electrical system. The deep learning algorithm is used in the single fault factor evaluation for improving the accuracy of the single fault factor evaluation. Then, with the evaluation results, a fuzzy comprehensive evaluation model is designed and to obtain the whole performance evaluation result of the electrical system. The results of experiments demonstrate that the proposed method has better properties in efficiency than the competing methods.
{"title":"A Fault Diagnosis and Comprehensive Evaluation Methods for the Electrical System","authors":"Junjie Chen, Lingxiao Cheng, Enbo Cong, Chunlei Yang, Xuesi Li","doi":"10.1145/3446132.3446180","DOIUrl":"https://doi.org/10.1145/3446132.3446180","url":null,"abstract":"With the development of the technology, the electrical system products is becoming more and more complicated and more and more diversified. It is more and more important to use the intelligent method to conduct the fault diagnosis and comprehensive evaluation to ensure the efficiency of the electrical system. This paper puts forward a fault diagnosis and comprehensive evaluation methods for the electrical system. The deep learning algorithm is used in the single fault factor evaluation for improving the accuracy of the single fault factor evaluation. Then, with the evaluation results, a fuzzy comprehensive evaluation model is designed and to obtain the whole performance evaluation result of the electrical system. The results of experiments demonstrate that the proposed method has better properties in efficiency than the competing methods.","PeriodicalId":125388,"journal":{"name":"Proceedings of the 2020 3rd International Conference on Algorithms, Computing and Artificial Intelligence","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121551580","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：