TY - JOUR
T1 - Prediction of Bus Travel Time Over Unstable Intervals between Two Adjacent Bus Stops
AU - As, Mansur
AU - Mine, Tsunenori
AU - Yamaguchi, Tsubasa
N1 - Funding Information:
The probe data used in this study were provided by NISHITETSU Bus Company in Fukuoka, Japan. This work is partially supported by JSPS KAKENHI Grant Number JP15H05708.
Funding Information:
The probe data used in this study were provided by NISHITETSU Bus Company in Fukuoka, Japan. This work is partially supported by JSPS KAKENHI Grant Number JP15H05708. Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Publisher Copyright:
© 2018, Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2020/1/1
Y1 - 2020/1/1
N2 - This paper addresses the problem of predicting bus travel time over unstable intervals between two adjacent bus stops using two types of machine learning techniques: ANN and SVR methods. Our model considers the variability of travel time because the travel time is often influenced by stochastic factors, which increase the variance of travel time over an interval between inter-time periods. The factors also affect the variance of the travel time over the interval at the same time period between inter-days. In addition, the factors show some correlation of travel time over the interval between time periods in a day. The performance of the proposed model is validated with real bus probe data collected from November 21st to December 20th, 2013, provided by Nishitetsu Bus Company, Fukuoka, Japan. We demonstrated the impact of two types of input variables for the prediction in off- and on-peak (rush hour) periods. The results show that the two types of inputs can effectively improve the prediction accuracy. Moreover, we compared the proposed method with our previous methods. The experimental results show the validity of our proposed method.
AB - This paper addresses the problem of predicting bus travel time over unstable intervals between two adjacent bus stops using two types of machine learning techniques: ANN and SVR methods. Our model considers the variability of travel time because the travel time is often influenced by stochastic factors, which increase the variance of travel time over an interval between inter-time periods. The factors also affect the variance of the travel time over the interval at the same time period between inter-days. In addition, the factors show some correlation of travel time over the interval between time periods in a day. The performance of the proposed model is validated with real bus probe data collected from November 21st to December 20th, 2013, provided by Nishitetsu Bus Company, Fukuoka, Japan. We demonstrated the impact of two types of input variables for the prediction in off- and on-peak (rush hour) periods. The results show that the two types of inputs can effectively improve the prediction accuracy. Moreover, we compared the proposed method with our previous methods. The experimental results show the validity of our proposed method.
UR - http://www.scopus.com/inward/record.url?scp=85077704348&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85077704348&partnerID=8YFLogxK
U2 - 10.1007/s13177-018-0169-3
DO - 10.1007/s13177-018-0169-3
M3 - Article
AN - SCOPUS:85077704348
SN - 1868-8659
VL - 18
SP - 53
EP - 64
JO - International Journal of Intelligent Transportation Systems Research
JF - International Journal of Intelligent Transportation Systems Research
IS - 1
ER -