Traffic Speed Prediction Under Non-Recurrent Congestion: Based on LSTM Method and BeiDou Navigation Satellite System Data

doi:10.1109/MITS.2019.2903431

	Traffic Speed Prediction Under Non-Recurrent Congestion: Based on LSTM Method and BeiDou Navigation Satellite System Data
	Zhao, Jiandong 1,2; Gao, Yuan 3; Bai, Zhiming 3; Lu, Shuhan 3; Wang, Hao 4
	2019-06-01
发表期刊	IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE
ISSN	1939-1390
卷号	11 期号:2 页码:70-81
摘要	The full utilization of Location-Based Vehicle Sensor Data (LB-VSD) can improve the efficiency of traffic control and management. Currently, LB-VSD is widely applied to the prediction of traffic speed. Like the GPS system, BeiDou satellite navigation system (BDS) can collect LB-VSD. In China, the key operation vehicles on the expressway are equipped with BDS to monitor the travel path. This provides a basis for predicting the traffic speed on expressway accurately. In this paper, considering the abnormal data collected by BDS, the screening and processing rules are made, and then the traffic speed sequence is extracted. Considering the data-missing problem caused by equipment failure or abnormal data elimination and the data sparse problem caused by small size of sample, a filling method based on trend-historical data is proposed. Traffic flow evolution is a complex process. Sudden accidents or bad weather can cause a sudden change in traffic flow and non-recurrent traffic congestion. The prediction accuracy of traditional machine learning methods is low when non-recurrent congestion occurred. In order to solve this problem, this paper adopts a deep learning model-Long Short-Term Memory (LSTM) to predict the traffic speed. Moreover, three-regime algorithm is used while building the prediction model. The prediction method is compared with Support Vector Regression (SVR) method. The results show that the prediction accuracy of the proposed method is higher than that of SVR algorithm, and the robustness is better in the case of non-recurrent traffic congestion.
DOI	10.1109/MITS.2019.2903431
收录类别	SCI
语种	英语
WOS研究方向	Engineering ; Transportation
WOS类目	Engineering, Electrical & Electronic ; Transportation Science & Technology
WOS记录号	WOS:000466040900009
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计	被引频次：72[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/4228
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zhao, Jiandong
作者单位	1.Beijing Jiaotong Univ, Sch Traff & Transportat, Beijing, Peoples R China 2.Beijing Jiaotong Univ, Key Lab Urban Transportat Complex Syst Theory & T, Minist Educ, Beijing, Peoples R China 3.Beijing Jiaotong Univ, Sch Mech Elect & Control Engn, Beijing, Peoples R China 4.Chinese Acad Sci, Inst Comp Technol, Jining Branch, Jining, Peoples R China
推荐引用方式 GB/T 7714	Zhao, Jiandong,Gao, Yuan,Bai, Zhiming,et al. Traffic Speed Prediction Under Non-Recurrent Congestion: Based on LSTM Method and BeiDou Navigation Satellite System Data[J]. IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE,2019,11(2):70-81.
APA	Zhao, Jiandong,Gao, Yuan,Bai, Zhiming,Lu, Shuhan,&Wang, Hao.(2019).Traffic Speed Prediction Under Non-Recurrent Congestion: Based on LSTM Method and BeiDou Navigation Satellite System Data.IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE,11(2),70-81.
MLA	Zhao, Jiandong,et al."Traffic Speed Prediction Under Non-Recurrent Congestion: Based on LSTM Method and BeiDou Navigation Satellite System Data".IEEE INTELLIGENT TRANSPORTATION SYSTEMS MAGAZINE 11.2(2019):70-81.