基于粗糙集-AHP-BP神经网络预测事故概率
|
摘要
车辆运行受多种风险因素共同作用,通过对G4京港澳(K1510—K1841)事故数据分析,建立风险因素体系,并利用粗糙集、事故危险度对风险因素实现重要性度量,利用AHP分析法确定风险因素权重,并通过BP神经网络实现不同风险条件下事故概率预测,实验证明,AHP-BP神经网络是预测风险条件下事故概率的有效模型。
Vehicles' safety on the road is affected by multiple risk factors.The paper has studied the Beijing-Hong Kong-Macao accident data,built risk systems of the vehicle operation,and then used roughsets and accident risk analysis to realize the importance of measuring the risk factors.Based on this,AHP is used to calculate the weight of risk factors,and to better understand risk level.BP neutral network is used to predict the probability of accident.The paper has concluded that the AHP-BP neutral network is an effective model to predict the accident probability,which is of great significance to prevent the accident on the road.
Vehicles' safety on the road is affected by multiple risk factors.The paper has studied the Beijing-Hong Kong-Macao accident data,built risk systems of the vehicle operation,and then used roughsets and accident risk analysis to realize the importance of measuring the risk factors.Based on this,AHP is used to calculate the weight of risk factors,and to better understand risk level.BP neutral network is used to predict the probability of accident.The paper has concluded that the AHP-BP neutral network is an effective model to predict the accident probability,which is of great significance to prevent the accident on the road.
引文
[1]HERMANS E,BOSSCHE F V D,WETS G.Uncertainty assessment of the road safety index[J].Reliability Engineering&System Safety,2009,94(7):1220-1228.
[2]TAIMUR U,FU L.A disaggregate model for quantifying the safety effects of winter road maintenance activities at an operational level[J].Accident;analysis and prevention,2012,368-378.
[3]吴焱,钱振邦,王建军,等.高速公路交通安全风险评价与敏感性分析[J].长安大学学报(自然科学版),2014,34(4):134-147.
[4]陈艳艳,李向楠,孙智源,等.基于Logistics回归的道路交通事故影响因素辨识方法[J].交通科技与经济,2018,20(5):1-5.
[5]李涛,王立晓,左志.基于极限学习机的交通事故严重程度预测[J].交通科技与经济,2018,20(5):6-11.
[6]肖虎.山区公路交通安全风险评估相关研究[D].成都:西南交通大学,2011.
[7]侯树展,孙小端,贺玉龙,等.高速公路交通事故严重程度与交通流特征的关系研究[J].中国安全科学学报,2011,21(9):106.
[8]徐晶.高速公路交通安全微观评价方法及应用研究[D].北京:北京交通大学,2011.
[9]EMMANUELLE D,JACQUES J F C,SYLVAIN L,et al.Latent risk and trend models for the evolution of annual fatality numbers in 30European countries[J].Accident;analysis and prevention,2014,327-336.
[10]KHATTAK A,WANG X,ZHANG H.Incident management integration tool:dynamically predicting incident durations,secondary incident occurrence and incident delays[J].Intelligent Transport Systems Iet,2012,6(2):204-214.
[11]KAHAKI S M M,NORDIN M D J,ASHTARI A H.Incident detection algorithm based on radon transform using high-resolution remote sensing imagery[C]//International Conference on Electrical Engineering&Informatics.IEEE,2011.
[12]PAWLAK Z.Rough sets[J].International Journal of Computer and Information Sciences,1982,11:341-356.
[13]夏菁,金犇.基于粗糙集和遗传算法的驼峰超速连挂事故分析[J].交通科技与经济,2016,18(4).
[14]SAATY T L,VARGAS L G.An Analytic Network Process Model for Financial-Crisis Forecasting[M]//Decision Making with the Analytic Network Process,2013.
[15]王文剑.BP神经网络模型的优化[J].计算机工程与设计,2000,21(6):8-10.
[16]董威.粗糙集理论及其数据挖掘应用[M].沈阳:东北大学出版社,2014.
[2]TAIMUR U,FU L.A disaggregate model for quantifying the safety effects of winter road maintenance activities at an operational level[J].Accident;analysis and prevention,2012,368-378.
[3]吴焱,钱振邦,王建军,等.高速公路交通安全风险评价与敏感性分析[J].长安大学学报(自然科学版),2014,34(4):134-147.
[4]陈艳艳,李向楠,孙智源,等.基于Logistics回归的道路交通事故影响因素辨识方法[J].交通科技与经济,2018,20(5):1-5.
[5]李涛,王立晓,左志.基于极限学习机的交通事故严重程度预测[J].交通科技与经济,2018,20(5):6-11.
[6]肖虎.山区公路交通安全风险评估相关研究[D].成都:西南交通大学,2011.
[7]侯树展,孙小端,贺玉龙,等.高速公路交通事故严重程度与交通流特征的关系研究[J].中国安全科学学报,2011,21(9):106.
[8]徐晶.高速公路交通安全微观评价方法及应用研究[D].北京:北京交通大学,2011.
[9]EMMANUELLE D,JACQUES J F C,SYLVAIN L,et al.Latent risk and trend models for the evolution of annual fatality numbers in 30European countries[J].Accident;analysis and prevention,2014,327-336.
[10]KHATTAK A,WANG X,ZHANG H.Incident management integration tool:dynamically predicting incident durations,secondary incident occurrence and incident delays[J].Intelligent Transport Systems Iet,2012,6(2):204-214.
[11]KAHAKI S M M,NORDIN M D J,ASHTARI A H.Incident detection algorithm based on radon transform using high-resolution remote sensing imagery[C]//International Conference on Electrical Engineering&Informatics.IEEE,2011.
[12]PAWLAK Z.Rough sets[J].International Journal of Computer and Information Sciences,1982,11:341-356.
[13]夏菁,金犇.基于粗糙集和遗传算法的驼峰超速连挂事故分析[J].交通科技与经济,2016,18(4).
[14]SAATY T L,VARGAS L G.An Analytic Network Process Model for Financial-Crisis Forecasting[M]//Decision Making with the Analytic Network Process,2013.
[15]王文剑.BP神经网络模型的优化[J].计算机工程与设计,2000,21(6):8-10.
[16]董威.粗糙集理论及其数据挖掘应用[M].沈阳:东北大学出版社,2014.