{"title":"基于贝叶斯网络的中小学教学楼踩踏事故风险评估模型","authors":"R. Zou, Yu Zou, Bihai Zou, Xin Liu","doi":"10.1109/ICCICC46617.2019.9146072","DOIUrl":null,"url":null,"abstract":"Primary and secondary schools is a centralized area of population, and the teaching buildings are the main places where the campus stampede accidents occurred. In order to reduce the occurrence of stampede accidents in primary and secondary school teaching buildings and improve the pertinence of risk prevention and control, a risk assessment and analysis model based on Bayesian network (BN) was worked out. Firstly, the risk factors of the stampede accidents in teaching buildings were summarized, and the causal relationship of each factor was analyzed, thus the BN structure was built. Then, the network parameters are determined by the data collected in the reference and the expert assignment. Finally, diagnostic reasoning was used to test and debug the model. When the model was built, the risk of stampede accidents in primary and secondary school teaching buildings was assessed by causal reasoning, and the sensitive risk factors were found with sensitivity analysis based on GenIe 2.0. The results show that the occurrence probability of stampede accidents in a teaching building is 0.87%, and strengthening safety management, especially preparation of a comprehensive and effective emergency plan, can significantly reduce the occurrence probability of stampede accidents in teaching buildings.","PeriodicalId":294902,"journal":{"name":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2019-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"A Risk Assessment Model of Stampede Accidents in Primary and Secondary School Teaching Buildings Based on Bayesian Network\",\"authors\":\"R. Zou, Yu Zou, Bihai Zou, Xin Liu\",\"doi\":\"10.1109/ICCICC46617.2019.9146072\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Primary and secondary schools is a centralized area of population, and the teaching buildings are the main places where the campus stampede accidents occurred. In order to reduce the occurrence of stampede accidents in primary and secondary school teaching buildings and improve the pertinence of risk prevention and control, a risk assessment and analysis model based on Bayesian network (BN) was worked out. Firstly, the risk factors of the stampede accidents in teaching buildings were summarized, and the causal relationship of each factor was analyzed, thus the BN structure was built. Then, the network parameters are determined by the data collected in the reference and the expert assignment. Finally, diagnostic reasoning was used to test and debug the model. When the model was built, the risk of stampede accidents in primary and secondary school teaching buildings was assessed by causal reasoning, and the sensitive risk factors were found with sensitivity analysis based on GenIe 2.0. The results show that the occurrence probability of stampede accidents in a teaching building is 0.87%, and strengthening safety management, especially preparation of a comprehensive and effective emergency plan, can significantly reduce the occurrence probability of stampede accidents in teaching buildings.\",\"PeriodicalId\":294902,\"journal\":{\"name\":\"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)\",\"volume\":\"45 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2019-07-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ICCICC46617.2019.9146072\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2019 IEEE 18th International Conference on Cognitive Informatics & Cognitive Computing (ICCI*CC)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICCICC46617.2019.9146072","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
A Risk Assessment Model of Stampede Accidents in Primary and Secondary School Teaching Buildings Based on Bayesian Network
Primary and secondary schools is a centralized area of population, and the teaching buildings are the main places where the campus stampede accidents occurred. In order to reduce the occurrence of stampede accidents in primary and secondary school teaching buildings and improve the pertinence of risk prevention and control, a risk assessment and analysis model based on Bayesian network (BN) was worked out. Firstly, the risk factors of the stampede accidents in teaching buildings were summarized, and the causal relationship of each factor was analyzed, thus the BN structure was built. Then, the network parameters are determined by the data collected in the reference and the expert assignment. Finally, diagnostic reasoning was used to test and debug the model. When the model was built, the risk of stampede accidents in primary and secondary school teaching buildings was assessed by causal reasoning, and the sensitive risk factors were found with sensitivity analysis based on GenIe 2.0. The results show that the occurrence probability of stampede accidents in a teaching building is 0.87%, and strengthening safety management, especially preparation of a comprehensive and effective emergency plan, can significantly reduce the occurrence probability of stampede accidents in teaching buildings.