International Journal of Highway Engineering (한국도로학회논문집)

Korean Society of Road Engineers (한국도로학회)
권호 표지
DOI QR코드

DOI QR Code

Analysis Period of Input Data for Improving the Prediction Accuracy of Express-Bus Travel Times

고속버스 통행시간 예측의 정확도 제고를 위한 입력자료 분석기간 선정 연구

  • 남승태 (한국도로공사 건설처) ;
  • 윤일수 (아주대학교 교통시스템공학과) ;
  • 이철기 (아주대학교 교통시스템공학과) ;
  • 오영태 (아주대학교 교통시스템공학과) ;
  • 최윤택 (한국도로공사 도로교통연구원) ;
  • 권건안 (교통안전공단 운영지원처)
  • Received : 2014.03.02
  • Accepted : 2014.08.01
  • Published : 2014.10.16
Download PDF
⟨ Previous Next ⟩

Abstract

PURPOSES : The travel times of expressway buses have been estimated using the travel time data between entrance tollgates and exit tollgates, which are produced by the Toll Collections System (TCS). However, the travel time data from TCS has a few critical problems. For example, the travel time data include the travel times of trucks as well as those of buses. Therefore, the travel time estimation of expressway buses using TCS data may be implicitly and explicitly incorrect. The goal of this study is to improve the accuracy of the expressway bus travel time estimation using DSRC-based travel time by identifying the appropriate analysis period of input data. METHODS : All expressway buses are equipped with the Hi-Pass transponders so that the travel times of only expressway buses can be extracted now using DSRC. Thus, this study analyzed the operational characteristics as well as travel time patterns of the expressway buses operating between Seoul and Dajeon. And then, this study determined the most appropriate analysis period of input data for the expressway bus travel time estimation model in order to improve the accuracy of the model. RESULTS : As a result of feasibility analysis according to the analysis period, overall MAPE values were found to be similar. However, the MAPE values of the cases using similar volume patterns outperformed other cases. CONCLUSIONS : The best input period was that of the case which uses the travel time pattern of the days whose total expressway traffic volumes are similar to that of one day before the day during which the travel times of expressway buses must be estimated.

Keywords

References

  1. Joo, I., A Case Study on Crime Prediction using Time Series Models, Journal of Korea Security Science Association, Vol. 30, pp. 139-169, 2012.
  2. Kang, J. and Namkoong, S., Development of The Freeway Operating Time Prediction Model Using Toll Collection System Data, Journal of Korean Society of Transportation, Vol. 20, No. 4, pp. 151-162, 2002.
  3. Kang, K. and Jeng, W., Easy Statistics, Orae, 2013.
  4. Korea Expressway Corporation, Practical Development of Expressway Traffic Condition Detection System, 2009.
  5. Korea Expressway Corporation, Study on the Enhancement of the Traffic Condition Forecasting Support System, 2010.
  6. Lee, D., Understanding Prediction Methods, Korea Information Industry, 1999.
  7. Lee, H., Development of A Microscopic Simulation Model for Traffic Information Collection & Service System Based On Dedicated Short Range Communication, Master Thesis, Ajou University, 2009.
  8. Olivier, D. M. and Faouzi, N. E. E., Innovative Processing of Toll Collection Data, LICIT Report No. 0604, 2006
  9. Olsson, C., Eriksson, A. and Hartley, R., Outlier Removal Using Duality. In CVPR, 2010.
  10. Park, E. and Kim, H., Identifying Some Relationships between the Probe and the Loop Detector Data for Better Estimation of Link Travel Time, in Proc. the Korea Institute of Intelligent Transport System, pp. 209-214, 2005.
  11. Sim, S., Choi, K., Lee, K., Link Travel Time Estimation and Evaluation of Applicability of Traffic Information collection Based RFID Probe Data, the Journal of the Korea Institute of Intelligent Transport Systems, Vol. 6, No. 2, pp. 15-25, 2007.
  12. The Korea Transport Institute, Survey Results of Traffic Condition Forecasting Information, 2010.
  13. Yoon, Y., Understanding Prediction Methods, Jayou Academy, 1995.
  14. Yoshikazu, O., Hideki, U. and Masao, K., Travel Time Predicition Method for Expressway Using Toll Collection System Data, Proceedings of 7th ITS World Congress, Torino, 2000.