ABSTRACT
Travel time information assists road users in making informed travel decisions such as mode choice, route choice and/or time of travel. This study explores the use of GPS data from buses and Wi-Fi and Bluetooth data from a sample of vehicles, for accurate estimation of the travel time of all vehicles on the roadway. A 5.5 km road stretch in Chennai city was selected as study stretch and data were collected for a week’s period. The present study develops models using linear regression and artificial neural network (ANN) techniquesFto estimate stream travel time using bus travel time obtained from GPS. ANN performed better compared to the linear regression for all sizes of segments. Most of the Indian cities have an integrated network of buses traveling on most of the road segments with on-board tracking devices, making this a useful development for real-time travel time estimation.
Acknowledgments
The authors 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.
Disclosure statement
No potential conflict of interest was reported by the authors.