Bus Arrival Time Prediction Model Based on Support Vector Machine and Kalman Filter

Authors presented the bus arrival time prediction model based on support vector machine £¨SVM£© and Kalman filter technique. The SVM which had three input features including, time-of-day, weather and segment was used to predict the baseline of bus running time from historical trip data. Applying the newest bus running information, combined with baseline time of SVM input, Kalman filter was used to predict bus arrival time dynamically. Bus arrival time forecasted by the proposed model was assessed with the data of transit route number 7 in Dalian Economic and Technological Development Zone in China. Results show that the model is a powerful tool for bus arrival time prediction.

• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/issn/10017372
• Corporate Authors:

  Key Laboratory of Structural Engineering and Vibration of Ministry of Educ

  ,    
• Authors:
  • BIN, Y U
  • ZHONG-ZHEN, YANG
  • QING-CHENG, ZENG
• Publication Date: 2008-3

Language

• Chinese

Media Info

• Pagination: 89-92,97
• Serial:
  • CHINA JOURNAL OF HIGHWAY AND TRANSPORT
  • Volume: 2,21
  • Issue Number: 90
  • Publisher: XI'AN HIGHWAY UNIVERSITY
  • ISSN: 1001-7372

Subject/Index Terms

• TRT Terms: Buses; Filters; Forecasting; Scale models; Traffic engineering
• Uncontrolled Terms: Arrival times; Support vector machines
• ITRD Terms: 1272: Bus; 132: Estimation; 7182: Filter; Kalman filter; 6205: Model (not math); 132: Prediction; 655: Traffic engineering
• Subject Areas: Bridges and other structures; Public Transportation; I71: Traffic Theory;

Filing Info

• Accession Number: 01324677
• Record Type: Publication
• Source Agency: Transport Research Centre (CDV)
• Files: ITRD
• Created Date: Jan 4 2011 9:50AM