Analysis of freeway accident frequency using multivariate adaptive regression splines

摘要：

　　This study applies nonparametric multivariate adaptive regression splines (MARS) modeling technique to explore the effects of non-behavior factors including highway geometrics characteristics,traffic factors as well as environmental conditions on freeway accidents.2007-2008 accident data of National Freeway 1 in Taiwan were collected for analysis.The results indicate that horizontal alignment,vertical alignment,average daily traffic volume (ADT),heavy vehicle ADT and annual precipitation have are nonlinear effects on freeway accidents.

关键词： freeway accident frequency linear regression data mining multivariate adaptive regression splines (MARS)

作者: Li-yen CHANG Hsing-chung CHU Da-jie LIN Pei LUI

作者单位: Graduate Institute of Marketing and Logistics/Transportation,National Chia-Yi University,580 Sin-Min Department of Transportation Technology and Management,Feng Chia University,100 Wen-Hwa Road,Taichun

会议类型: 国际会议

会议名称: 2012 International Symposium on Safety Science and Technology (2012安全科学与技术国际会议)

会议地点: 南京

会议语种:英文

页码: 824-829

在线出版日期: 2012-10-23（万方平台首次上网日期，不代表论文的发表时间）