Bus travel time prediction model with ν - support vector regression

Author

Wang, Jing-Nan ; Chen, Xu-Mei ; Guo, Shu-Xia

Author_Institution

MOE Key Lab. for Urban Transp. Complex Syst. Theor. & Technol., Beijing JiaoTong Univ. Beijing, Beijing, China

fYear

2009

fDate

4-7 Oct. 2009

Firstpage

1

Lastpage

6

Abstract

Bus travel time prediction is a vital part for both bus operation optimizing system and information service system. This paper reviews existing bus travel time prediction models and analyzes the strengths and weaknesses of each model. A bus travel time prediction model based on nu - Support Vector Regression is proposed, which uses the departure time of bus from origin stop that can reflect traffic conditions for a certain degree as the input data. The performance of the proposed model is tested it in a case study of Express bus line 104 in Beijing. The result validates the effectiveness and efficiency of the model.

Keywords

prediction theory; regression analysis; road traffic; support vector machines; traffic information systems; Beijing Express bus line 104; bus travel time prediction model; information service system; nu-support vector regression; Artificial neural networks; Intelligent transportation systems; Laboratories; Machine learning; Predictive models; Road transportation; Support vector machines; Testing; Traffic control; USA Councils; ν - support vector regression; Machine Learning Techniques; bus travel time; prediction; support vector machines;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Transportation Systems, 2009. ITSC '09. 12th International IEEE Conference on

Conference_Location

St. Louis, MO

Print_ISBN

978-1-4244-5519-5

Electronic_ISBN

978-1-4244-5520-1

Type

conf

DOI

10.1109/ITSC.2009.5309844

Filename

5309844