Study on the Quantitative Method of Oversaturated Intersection

Abstract:

Oversaturation in the modern urban traffic often happens. In order to describe the degree of oversaturation, the indexes of intersection oversaturation degree are put forward include dissipation time, stranded queue, overflow queue and travel speed. On the basis of selected indexes, the genetic algorithm support vector machine (GA-SVM) model was proposed to quantify the degree of oversaturation. In this method the genetic algorithm is used to select the model parameters. The GA-SVM model built is used to quantify the degree of oversaturation. Combining with the volume of intersections in Guangzhou city the method is calculated and simulated through programming. The simulation results show that GA-SVM method is effective and the accuracy of GA-SVM is higher than support vector machine (SVM).This method provides a theoretical basis for the analysis of traffic system under over-saturated traffic conditions.

• Periodical: Applied Mechanics and Materials (Volumes 587-589)
• Pages: 2100-2104
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.587-589.2100
• Online since: July 2014
• Authors: Qin Liu*, Jian Min Xu, Kai Lu
• Keywords: Genetic Algorithm (GA), Oversaturation Degree, Support Vector Machine (SVM), Traffic Information Engineering, Traffic State

References

[1] Gazis, D.C., Potts, R.B. The oversaturated intersection. In: Proceedings of the 2nd International Symposium on the Theory of Road Traffic Flow. Organization for Economic Cooperation and Development, Paris. 1965, 221–237.

[2] Abu-Lebdeh, G., Benekohal, R.F. Genetic algorithms for traffic signal control and queue management of oversaturated two-way arterials [J]. Transportation Research Record, 2000, 1727: 61-67.

DOI: 10.3141/1727-08

[3] Abu-Lebdeh, G., Benekohal, R.F. Design and evaluation of dynamic traffic management strategies for congested conditions[J]. Transportation Research Part A 2003, 37 : 109–127.

DOI: 10.1016/s0965-8564(02)00006-x

[4] Roger P. Roess, Elena S. Prassas, William R. McShane. Traffic Engineering [M]. Upper Saddle River: Prentice Education，Inc., (2004).

[5] Perrin J, Martin P T, Coleman B. Monitoring Commuter Congestion on Surface Streets in Real Time[J]. Transportation Research Record, 2002, (1811): 107-114.

DOI: 10.3141/1811-13

[6] Sharma A, Bullock D M, Bonneson J A. Input-Output and Hybrid Techniques for Real-Time Prediction of Delay and Maximum Queue Length at Signalized Intersections[J]. Transportation Research Record: Journal of the Transportation Research Board, 2007, (2035).

DOI: 10.3141/2035-08

[7] ME Hallenbeck, JM Ishimaru, K D Davis. Arterial Performance Monitoring Using Stop Bar Sensor Data[C]. TRB 2008 Annual Meeting, Washington DC.

[8] LIN Yu, YANG Xiaoguang, MA Yingying. Measurement Methodology of Discrete Traffic Flow Congestion on Urban Surface Streets[J]. Journal of Tongji University(Natural Science), 2007，35（03）：336－340.

[9] YANG Zhao-sheng, GONG Bo-wen, LIN Ci-yun, ZHANG Xin-wei. Logit Model Application in Expressway Traffic Condition Prediction[J]. Journal of Beijing University of Technology, 2009(04): 486-492.

[10] Qian Zhe, Xu Jian-min. Identification of Oversaturated Traffic Conditions Based on Loop Detection[J]. Journal of South China University of Technology(Natural Science Edition, 2013, 41（8）: 93-98.