The Identification of Intersection Entrance Accidents Based on Autoencoder

• Published in: Sustainability Vol. 15; no. 11; p. 8533
• Main Authors: Du, Yingcui, Sun, Feng, Jiao, Fangtong, Liu, Benxing, Wang, Xiaoqing, Zhao, Pengsheng
• Format: Journal Article
• Language: English
• Published: Basel MDPI AG 24.05.2023
• Subjects: Accident prediction; Accidents; Algorithms; Analysis; Decision trees; Deep learning; Identification; Machine learning; Methods; Neural networks; Paralysis; Peak periods; Quality of life; Regression analysis; Roads & highways; Support vector machines; Sustainability; Traffic accidents; Traffic accidents & safety; Traffic congestion; Traffic flow; Traffic intersections; Traffic models; Traffic volume; Transportation planning; Vehicles; Video recorders; China; United States > US; California
• ISSN: 2071-1050; 2071-1050
• DOI: 10.3390/su15118533

Traffic collisions are one of the leading causes of traffic congestion. In the case of urban intersections, traffic accidents can even result in widespread traffic paralysis. To solve this problem, we developed an autoencoder-based model for identifying intersection entrance accidents by analyzing the characteristics of traffic volume. The model uses the standard deviation of the intersection entrance lanes’ traffic volume as an input parameter and identifies intersection entrance accidents by comparing predicted data to actual measured data. In this paper, the detection rate and average detection time are chosen to evaluate the effectiveness of algorithms. The detection rate of the autoencoder model reaches 94.33%, 95.47%, and 81.64% during the morning peak, evening peak, and daylight off-peak periods, respectively. Compared to the support vector machine and the random forest, autoencoder has better performance. It is evident that the research presented in this paper can effectively enhance the detection effect and has a shorter detection time of intersection entrance accidents.