Traffic Incident Duration Prediction Based on K-Nearest Neighbor

Abstract:

Prediction of incident duration is very important in Advanced Intelligent Traffic Incident Management and the accuracy of prediction can provide exact information for travellers. It is widely used in the area of ITS. In this paper, K-Nearest neighbor (KNN) is employed to predict the incident duration, which puts forward a new distance metric and weight determination method. This KNN model is created based on the incident data set collected by DVS-Center for Transport and Navigation, Ministry of Transport, Public Works and Management, the Netherlands. Moreover, a simulation based on Matlab is used for incident duration prediction and optimizing the best k value. Finally, an error analysis is made based on this simulation. As a result, this method (KNN) obtains high accuracy and has a better effect than Bayesian Decision Method-Based Tree Algorithm. So it can be effectively applied to intelligent traffic incident detection and clearance systems.

• Periodical: Applied Mechanics and Materials (Volumes 253-255)
• Pages: 1675-1681
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.253-255.1675
• Online since: December 2012
• Authors: Yuan Wen, Shu Yan Chen, Qin Yuan Xiong, Ru Bi Han, Shi Yu Chen
• Keywords: K-Nearest Neighbor Prediction, Traffic Incident Duration

References

[1] Xiaoqiang Zhao, Ruimin Li. Highway Engineering, 2010, 35(1),pp.42-44. (In Chinese)

[2] Golob, Thomas F, Wilfred W. Recker and John D. Leonard. Accident Analysis & Prevention.1987, 19(4),p.375~395.

[3] Garib, A., A. E. Radwan and H. Al-Deek. Journal of Transportation Engineering. 1997, 123(6), p.459~466.）

[4] Sullivan, E. C.Journal of Transportation Engineering. 1997, 123 p.267~275

[5] Giuliano ,Genevieve. Incident Characteristics, Frequency, and Duration on a High Volume Urban Freeway. （Transportation Research-A, 1989, 23(5) p.387~396.）

DOI: 10.1016/0191-2607(89)90086-1

[6] Ozbay, Kaan and Pushkin Kachroo. Incident Management in Intelligent Transportation. (Boston, MA: Artech House, 1999.）

[7] Cohen, S and Nouveliere, C. Modelling Incident Duration on An Urban Expressway. （IFAC/IFIP/FORS Symposium, Greece, p.297~301）

DOI: 10.1016/s1474-6670(17)43840-7

[8] Wang, M. Modeling freeway incident clearance time MS thesis. （Civil Engineering Dept, Northwestern University， 1991）

[9] Jones. Analysis of the frequency and duration of freeway accidents in Seattle .（ Accident Analysis and Prevention 23 (4),p.239~255）

DOI: 10.1016/0001-4575(91)90003-n

[10] Khattak, A J, J L Schofer, M Wang. A Simple Time Sequential Procedure for Predicting Freeway Incident Duration.（ IVHS Journal, 2(2) p.113~138）

DOI: 10.1080/10248079508903820

[11] Sethi. V., Koppehman, F.S., Fannery, C.P., Bhomderi, etc. Duration and travel time impacts of incidents. （ADVANCE Project technical Report. 1994. Northwestern University, Evanstion.）

[12] Tao Zhang, Xian Chen, Mei-ping Xie, etc. Systems Engineering---Theory & Practice, 2010, 30(2) pp.376-384 .(In Chinese)

[13] Beibei Jiyang. (2008)"Research on prediction method of traffic incident duration. "（Shanghai, Tongji University.）(In Chinese).

[14] Information on http://www.incidentmanagement.nl

[15] Information on http://baike.baidu.com/view/829823.htm(In Chinese)