A long short-term memory-based framework for crash detection on freeways with traffic data of different temporal resolutions. (June 2020)

• Record Type: Journal Article
• Authors: Jiang, Feifeng; Yuen, Kwok Kit Richard; Lee, Eric Wai Ming
• Is Part Of: Accident analysis and prevention. Volume 141(2020)
• Publication Date: 2020-06
• Subjects: Crash detection -- Deep learning methods -- Long short-term memory networks -- Traffic condition -- Different temporal resolutions; Accidents -- Prevention -- Periodicals; Accident Prevention -- Periodicals; Accidents -- Prévention -- Périodiques; 363.106
• DOI: 10.1016/j.aap.2020.105520
• Languages: English
• ISSNs: 0001-4575

Abstract

Highlights: A deep learning-based framework is proposed for crash detection. Traffic data of different temporal resolutions are used to improve performance. The framework obtains desirable performance on crash detection and transferability. The framework performs better than machine learning methods and LSTM models. The effect of important parameters on model performance is discussed. Abstract: Traffic crash detection is a major component of intelligent transportation systems. It can explore inner relationships between traffic conditions and crash risk, prevent potential crashes, and improve road safety. However, there exist some limitations in current studies on crash detection: (1) The commonly used machine learning methods cannot simulate the evolving transitions of traffic conditions before crash occurrences; (2) Current models collected traffic data of only one temporal resolution, which cannot fully represent traffic trends in different time intervals. Therefore, this study proposes a Long short-term memory (LSTM) based framework considering traffic data of different temporal resolutions (LSTMDTR) for crash detection. LSTM is an effective deep learning method to capture the long-term dependency and dynamic transitions of pre-crash conditions. Three LSTM networks considering traffic data of different temporal resolutions are constructed, which can comprehensively indicate traffic variations in different time intervals. A fully-connected layer is used to combine the outputs of three LSTM networks, and a dropout layer is used to reduce overfitting and improve prediction performance. The LSTMDTR model is implemented on datasets of I880-N and I805-N in California, America. The results indicate that the LSTMDTR model can obtain satisfactory performance on crash detection, with the highest crash accuracy of 70.43 %. LSTMDTR models constructed on one freeway can be transferred to other similar freeways, with 65.12 % of crash accuracy on transferability. Compared with machine learning methods and LSTM models with one or two temporal resolutions, the LSTMDTR model has been validated to perform better on crash detection and transferability. A proper number of neurons in the LSTMDTR model should be determined in real applications considering acceptable detection performance and computation time. The dropout technique can reduce overfitting and improve the generalization ability of the LSTMDTR model, increasing crash accuracy from 64.49 % to 70.43 %.