Title:	Modeling of BRT System Travel Time Prediction Using AVL Data and ANN Approach
Authors:	Baradaranshahidin, Milad Shabani, Shahin Khalilzadeh, Mohammadreza Tahmasbi Ashtiani, Saman Tajaddini, Siavash Azimipour, Mohammad
Citation:	BARADARANSHAHIDIN, M. SHABANI, S. KHALILZADEH, M. TAHMASBI ASHTIANI, S. TAJADDINI, S. AZIMIPOUR, M. Modeling of BRT System Travel Time Prediction Using AVL Data and ANN Approach. European Transport / Trasporti Europei, 2021, roč. 84, č. 6, s. 1-16. ISSN: 1825-3997
Issue Date:	2021
Publisher:	Institute for Transport Studies in the European Economic Integration
Document type:	článek article
URI:	2-s2.0-85123735748 http://hdl.handle.net/11025/51202
ISSN:	1825-3997
Keywords in different language:	Bus Rapid Transit (BRT);Travel Time Prediction;Artificial Neural Network (ANN);Linear Regression;Automatic Vehicle Location (AVL)
Abstract in different language:	Improving the quality of public transportation systems and encouraging passengers to use them are effective solutions for reducing transportation problems in metropolitan. Prediction of travel time and providing information to passengers are significant factors in this process. In this research not only the travel time components in Bus Rapid Transit (BRT) system were investigated but also an Artificial Neural Network (ANN) model and a regression model for travel time prediction were presented. To enhance this aim, data was collected by AVL data and field observation and after investigating the primary independent variables, the significant ones were determined using statistical analysis, then ANN development was done. Moreover, linear regression method was used for this purpose. The results prove that although both models have high level of prediction accuracy, ANN model outperform the regression model and the accuracy for the route sections with no signalized intersections is higher than the others.
Rights:	© Institute for Transport Studies in the European Economic Integration
Appears in Collections:	Články / Articles (KGM) OBD

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.