Proceedings ArticleDOI
Use of GPS Probe Data and Passenger Data for Prediction of Bus Transit Travel Time
Y Ramakrishna,P Ramakrishna,Lakshmanan,R. Sivanandan +3 more
- Vol. 320, pp 124-133
Reads0
Chats0
TLDR
Use of passenger data and speed data from probe buses helped improve the performance of the model and multiple linear regression models which do well in such recurrent traffic conditions were developed.Abstract:
It is believed that passenger data influences bus travel time in cities of developing countries such as India. Thus, this paper focuses on the application of probe vehicle speed data and passenger data for predicting bust transit travel time. The improvement brought about by the probe vehicle speed data and passenger data in prediction of travel time over the use of only GPS data is also studied. Along with passenger data, GPS data was collected using probe buses on one of the busiest bus routes on weekday evening peak hours in Chennai city, India. Preliminary data analysis revealed that similar traffic conditions prevail over the route during the evening peak hours on all weekdays. Thus, multiple linear regression models which do well in such recurrent traffic conditions were developed. Results conclude that use of passenger data and speed data from probe buses helped improve the performance of the model.read more
Citations
More filters
Journal ArticleDOI
Bus travel time prediction with real-time traffic information
TL;DR: This work proposes a novel segment-based approach to predict bus travel times using a combination of real-time taxi and bus datasets, that can automatically divide bus routes into dwelling and transit segments and improves the accuracy of bus travel time prediction.
Journal ArticleDOI
Learning to Predict Bus Arrival Time From Heterogeneous Measurements via Recurrent Neural Network
TL;DR: This paper proposes to exploit the long-range dependencies among the multiple time steps for bus arrival prediction via recurrent neural network (RNN) through RNN with long short-term memory block to correct the prediction for a station by the correlated multiple passed stations.
Journal ArticleDOI
Probabilistic Prediction of Bus Headway Using Relevance Vector Machine Regression
TL;DR: With the probabilistic bus headway prediction information, transit riders can better schedule their trips to avoid late and early arrivals at bus stops, while transit operators can adopt the targeted correction actions to maintain regular headway for bus bunching prevention.
Journal ArticleDOI
Bus Dwell Time Modeling Using Gene Expression Programming
TL;DR: A gene expression programming (GEP)-based approach that shows prospects how to estimate bus dwell time (BDT) more accurately and overcome some of the issues associated with the multiple linear regression (MLR) method is proposed in this article.
Proceedings ArticleDOI
Public bus arrival time prediction based on traffic information management system
TL;DR: A statistical approach to predict the public bus arrival time based on traffic information management system is presented, which has been proved relatively accurate and efficient by experiments.
References
More filters
Journal ArticleDOI
Travel time studies with global positioning and geographic information systems: an integrated methodology
Cesar Quiroga,Darcy M. Bullock +1 more
TL;DR: A new methodology for performing travel time studies using global positioning system (GPS) and geographic information system ( GIS) technologies is described, as well as analyses that illustrate the capabilities of the GPS/GIS methodology.
Journal ArticleDOI
Experimental Study of Real-Time Bus Arrival Time Prediction with GPS Data:
Wei-Hua Lin,Jian Zeng +1 more
TL;DR: An experimental study has been conducted on forecasting the arrival time of the next bus with automatic vehicle location techniques, and results show that at the site where the study is being conducted, the dwell time at time-check stops is most relevant to the performance of an algorithm.
Proceedings ArticleDOI
Transferability of travel time models and provision of real-time arrival time information
TL;DR: Results indicate that models should not be applied to different routes without investigating the need for recalibration and it appears that a model recalibrated on limited data will perform well compared to a route specific model.