Bus Arrival Time Prediction Based on the k-Nearest Neighbor Method

Author

Liu, Tao ; Ma, Jihui ; Guan, Wei ; Song, Yue ; Niu, Hu

Author_Institution

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

fYear

2012

fDate

23-26 June 2012

Firstpage

480

Lastpage

483

Abstract

In this paper, a modified k-nearest neighbor (k-NN) method integrating the cluster analysis and principal component analysis is applied to bus arrival time (BAT) prediction using historical bus GPS data. The methodology of the k-NN method based on processed GPS data is presented. To validate the introduced k-NN approach, empirical analysis based on data collected from the bus No. 16 of Beijing public transport holdings, Ltd. (BPT) is performed. The results show that the k-NN method has lower prediction error than the ANN model and is more powerful in the BAT prediction.

Keywords

learning (artificial intelligence); pattern classification; principal component analysis; transportation; Beijing public transport holdings; bus arrival time prediction; cluster analysis; historical bus GPS data; k-nearest neighbor method; principal component analysis; Artificial neural networks; Databases; Delay; Global Positioning System; Predictive models; Transportation; Vectors; bus arrival time prediction; cluster analysis; k-nearest neighbor; non-parameter regression; principal component analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Sciences and Optimization (CSO), 2012 Fifth International Joint Conference on

Conference_Location

Harbin

Print_ISBN

978-1-4673-1365-0

Type

conf

DOI

10.1109/CSO.2012.111

Filename

6274771