Urban Arterial Travel Time Prediction Using Support Vector Regression
Travel time is one of the most appropriate traffic measures that can be provided to road users for easy understanding and decision making. This paper presents a simple method to predict travel time on urban arterial roads. Travel time prediction methods include historical methods, model based methods, and data driven approaches. Of these, data driven approaches capture the uncertainty and non-linearity of traffic time series better and hence could be used for travel time prediction under Indian traffic conditions effectively. Among data driven approaches, support vector regression (SVR) models predict travel times with reasonable accuracy, especially when the amount of data is less or the variability in the data is high. However, studies on the use of SVR for travel time prediction under Indian traffic conditions are limited. In this paper, SVR technique was used to predict the travel time using data collected from Bluetooth sensors placed at specific locations on an urban arterial corridor in Chennai, India. The optimum number of inputs, appropriate kernel function, cost parameter and width of tolerance for the SVR model were determined. The results obtained show that the SVR performed better than an Artificial Neural Network model and moving average approach.
KeywordsTravel time prediction Support vector regression Bluetooth data Sensitivity analysis Heterogeneous traffic
The authors acknowledge the opportunity provided by the 4th Conference of the Transportation Research Group of India (4th CTRG) held at IIT Bombay, Mumbai, India between 17th December, 2017 and 20th December, 2017 to present the work that forms the basis of this manuscript. The authors also acknowledge the support for this study as a part of the project RB/16-17/CIE/001/TATC/LELI under the Development of a Dynamic Traffic Congestion Prediction System for Indian Cities, funded by Tata Consultancy Services.
- 3.IIT M (2014) Traffic data collection and analysis for the research study on Advanced Traveller Information System (ATIS) for Indian cities. Tech. rep. https://coeut.iitm.ac.in/Final%20Report%20R01.pdf
- 5.Liang Z, Ling-Xiang Z (2006) Link travel time estimation model fusing data from mobile and stationary detector based on BP neural network. In: Communications, Circuits and Systems Proceedings, International Conference on, vol 3. IEEE, pp 2146–2149Google Scholar
- 6.Mori U, Mendiburu A, Alvarez M, Lozano JA (2015) A review of travel time estimation and forecasting for advanced traveller information systems. Transp A Transp Sci 11(2):119–157Google Scholar
- 7.Nikovski D, Nishiuma N, Goto Y, Kumazawa H (2005) Univariate short-term prediction of road travel times. In: Intelligent Transportation Systems. Proceedings. IEEE, pp 1074–1079, 13 Sep 2005Google Scholar
- 13.Theja P, Vanajakshi L (2010) Short term prediction of traffic parameters using support vector machines technique. In: Emerging Trends in Engineering and Technology (ICETET), 3rd International Conference on 2010 November 19. IEEE, pp 70–75Google Scholar
- 15.Vanajakshi L, Rilett LR (2007) Support vector machine technique for the short term prediction of travel time. In: Intelligent Vehicles Symposium. IEEE, pp 600–605, 13 June 2007Google Scholar