期刊
JOURNAL OF INTELLIGENT TRANSPORTATION SYSTEMS
卷 23, 期 2, 页码 161-174出版社
TAYLOR & FRANCIS INC
DOI: 10.1080/15472450.2018.1536978
关键词
Accident duration prediction; Bayesian network; cost-sensitive; KNN regression
资金
- National Natural Science Foundation of China [61772560, 61876190, 61872306]
- Scientific Research Project for Professors in Central South University, China [904010001]
With the development of urbanization, road congestion has become increasingly serious, and an important cause is the traffic accidents. In this article, we aim to predict the duration of traffic accidents given a set of historical records and the feature of the new accident, which can be collected from the vehicle sensors, in order to help guide the congestion and restore the road. Existing work on predicting the duration of accidents seldom consider the imbalance of samples, the interaction of attributes, and the cost-sensitive problem sufficiently. Therefore, in this article, we propose a two-level model, which consists of a cost-sensitive Bayesian network and a weighted K-nearest neighbor model, to predict the duration of accidents. After data preprocessing and variance analysis on the traffic accident data of Xiamen City in 2015, the model uses some important discrete attributes for classification, and then utilizes the remaining attributes for K-nearest neighbor regression prediction. The experiment results show that our proposed approach to predicting the duration of accidents achieves higher accuracy compared with classical models.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据