Real-time Highway Traffic Accident Prediction Based on the k-Nearest Neighbor Method

摘要：

The occurrence of a highway traffic accident is associated with the short-term turbulence of traffic flow. In this paper, we investigate how to identify the traffic accident potential by using the k-nearest neighbor method with real time traffic data. This is the first time the knearest neighbor method is applied in real-time highway traffic accident prediction. Traffic accident precursors and their calculation time slice duration are determined before classifying traffic patterns. The experimental results show the k-nearest neighbor method outperforming the conventional C-means clustering method.

关键词： real-time accident prediction highway accident prediction k-nearest neighbor method real-time traffic data pattern classification

作者: Yisheng Lv Shuming Tang Hongxia Zhao

作者单位: Institute of Automation Chinese Academy of Sciences Beijing, China Shandong University of Science and Technology Qingdao, China

会议类型: 国际会议

会议名称: 2009 International Conference on Measuring Technology and Mechatronics Automation(ICMTMA 2009)(2009年检测技术与机电自动化国际会议)

会议地点: 张家界

会议语种:英文

页码: 547-550

在线出版日期: 2009-04-11（万方平台首次上网日期，不代表论文的发表时间）