Study on the Prediction Methods for the Number of Freeway Accidents during the Free-Tolling Holidays Based on Social-Network Information: A Case from Jiangsu Freeway

摘要

The freeway free-tolling policy leads to high traffic volumes, and it also has impact on the number of traffic accidents. With the information development of freeway operation and management, traffic accidents are released to the public by the social network in real-time. Utilizing social-network information and relevant statistical data, i.e., vehicle ownership, freeway mileage, GDP (gross domestic product) of Jiangsu Province, etc., this study analyzes the characteristic of freeway traffic accidents, and explores different prediction methods to forecast future traffic accident numbers. Firstly, a sensitivity analysis on factors that might have an influence on traffic accidents is carried out. Then, two prediction models including a statistical regression model and a neural-network model are presented. Lastly, using the freeways of Jiangsu Province, the accuracy of two prediction models is evaluated. The results show that the neural-network model is more accurate comparatively. This study could assist the operation and management of freeways.