KSCE Journal of Civil and Environmental Engineering Research (대한토목학회논문집)

Korean Society of Civil Engeneers (대한토목학회)
권호 표지
DOI QR코드

DOI QR Code

Expressway Travel Time Prediction Using K-Nearest Neighborhood

KNN 알고리즘을 활용한 고속도로 통행시간 예측

  • 신강원 (경성대학교 도시공학과) ;
  • 심상우 (아주대학교 TOD기반 지속가능 도시.교통 연구센터) ;
  • 최기주 (아주대학교 교통시스템공학과) ;
  • 김수희 (한국도로공사 도로교통연구원)
  • Received : 2014.07.29
  • Accepted : 2014.10.14
  • Published : 2014.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

There are various methodologies to forecast the travel time using real-time data but the K-nearest neighborhood (KNN) method in general is regarded as the most one in forecasting when there are enough historical data. The objective of this study is to evaluate applicability of KNN method. In this study, real-time and historical data of toll collection system (TCS) traffic flow and the dedicated short range communication (DSRC) link travel time, and the historical path travel time data are used as input data for KNN approach. The proposed method investigates the path travel time which is the nearest to TCS traffic flow and DSRC link travel time from real-time and historical data, then it calculates the predicted path travel time using weight average method. The results show that accuracy increased when weighted value of DSRC link travel time increases. Moreover the trend of forecasted and real travel times are similar. In addition, the error in forecasted travel time could be further reduced when more historical data could be available in the future database.

실시간 자료를 반영한 통행시간 예측 기법은 다양하지만 관련 연구 검토 결과 과거이력데이터가 충분하다면 타 모형에 비해 K 최대근접이웃(K-Nearest Neighbors)의 정확도가 우수하므로 본 연구에서는 이에 대한 적용 방법 도출 및 가능성 평가를 목적으로 한다. 본 연구에서는 KNN의 입력 자료로 TCS 교통량 및 DSRC 구간통행시간의 실시간 및 과거 이력자료, 경로통행시간 이력자료를 활용하였다. 통행시간 예측치는 TCS 교통량 및 DSRC 구간통행시간의 실시간 자료와 유사한 경로통행시간을 탐색한 후 이를 가중평균하여 산출하였다. 예측 기법을 적용한 결과 DSRC 구간통행시간의 가중치가 증가할수록 정확도는 증가하였으며, 이는 실시간 교통상황 변화를 DSRC 구간통행시간이 잘 반영하기 때문이다. 그러나 TCS 교통량을 기반으로 한 경우 역시 정확도의 차이가 크지 않으며, 변화 추이도 유사하게 나타났다. 이러한 결과를 볼 때 향후 대용량의 과거이력자료가 축적될 경우 예측오차는 더욱 감소될 것으로 기대된다.

Keywords

References

  1. Ban, X. J., Li, Y., Skabardonis, A. and Margulici, J. D. (2010). "Performance evaluation of travel-time estimation methods for real-time traffic applications." J. of Intell. Transp. Syst., Vol. 14, No. 2, pp. 54-67. https://doi.org/10.1080/15472451003719699
  2. Chen, X., Gong, H. and Wang, J. (2012). "BRT vehicle travel time prediction based on SVM and kalman filter." J. of Transp. Syst. Eng. and Inf. Technol., Vol. 12, No. 4, pp. 29-34.
  3. Innamaa, S. (2005). "Short-term prediction of travel time using neural networks on an interurban highway." Transp., Vol. 32, No. 6, pp. 649-669. https://doi.org/10.1007/s11116-005-0219-y
  4. Jeong, R. and Rilett, L. R. (2004). "Bus arrival time prediction using artificial neural network model." Proc. of the 7th Int. IEEE Conf. on Intell. Transp. Syst., Washington D.C., USA, pp. 988-993.
  5. Kang, J. and Namkoong, S. (2002). "Development of the freeway operating time prediction model using toll collection system data." J. of Korean Soc. Transp., Vol. 20, No. 4, pp. 151-162 (in Korean).
  6. Kim, H. and Jang, K. (2013). "Short-term prediction of travel time using DSRC on highway." J. of the Korean Soc. Civil Eng., Vol. 33, No. 6, pp. 2465-2471 (in Korean). https://doi.org/10.12652/Ksce.2013.33.6.2465
  7. Lam, W. H. K., Tang, Y. F., Chan, K. S. and Tam, M. L. (2006). "Short-term hourly traffic forecasts using Hong Kong annual traffic census." Transp., Vol. 33, No. 3, pp. 291-310. https://doi.org/10.1007/s11116-005-0327-8
  8. Lee, C., Park, J. and Kho, S. (2002). "Prediction of path travel time using kalman filter." J. of the Korean Soc. Civil Eng., Vol. 22, No. 5-D, pp. 871-880 (in Korean).
  9. Lee, E. and Kim, J. (2002). "Development of a freeway travel time forecasting model for long distance section with due regard to time-lag." J. Korean Soc. Transp., Vol. 20, No. 4, pp. 51-61 (in Korean).
  10. Lee, Y. (2009). "Freeway travel time forecasting using artificial neural networks with cluster method." 12th Int. Conf. on Inf. Fusion, Seattle, USA, pp. 1331-1338.
  11. Lee, Y., Kim, S. and Youn, J. (2005). "Multi-step ahead link travel time prediction using data fusion." J. Korean Soc. Transp., Vol. 23, No. 4, pp. 71-79 (in Korean).
  12. Lim, S. and Lee, C. (2011), "Data fusion algorithm improves travel time predictions." IET Intell. Transp. Syst., Vol. 5, No. 4, pp. 302-309. https://doi.org/10.1049/iet-its.2011.0014
  13. Lim, S., Lee, H., Park, S. and Heo, T. (2013). "A study of travel time prediction using k-nearest neighborhood method." The Korean J. of Applied Statistics, Vol. 26, No. 5, pp. 835-845 (in Korean). https://doi.org/10.5351/KJAS.2013.26.5.835
  14. Mehmet, Y. and Nikolas, G. (2013). "Experienced travel time prediction for congested freeways." Transp. Res. Part B, Vol. 53, pp. 45-63. https://doi.org/10.1016/j.trb.2013.03.006
  15. Nigovski, D., Nishiuma, N., Goto, Y. and Kumazawa, H. (2005). "Univariate short-term prediction of road travel time." Proc. of the 8th IEEE Conf. on Intell. Transp. Syst., Vienna, Austria, pp. 1074-1079.
  16. Oh, S., Kim, M. and Baek, Y. (2003). "Development of a freeway travel time estimating and forecasting model using traffic volume." J. of Korean Soc. Transp., Vol. 21, No. 5, pp. 83-95 (in Korean).
  17. Park, S., Jeong, Y. and Kim, C. (2006). "Development and evaluation of real-time travel time forecasting model: Nonparametric Regression Analysis for the Seoul Transit System." J. of Korean Soc. Transp., Vol. 24, No. 1, pp. 109-120 (in Korean).
  18. Rice, J. and Zwet, V. E. (2004). "A simple and effective method for predicting travel times on freeways." IEEE trans. on Intell. Transp. Syst., Vol. 5, No. 3, pp. 200-207. https://doi.org/10.1109/TITS.2004.833765
  19. Smith, B. and Demetsky, M. (1997). "Traffic flow forecasting: Comparison of Modeling Approaches." J. of Transp. Eng., Vol. 123, No. 4, pp. 261-266. https://doi.org/10.1061/(ASCE)0733-947X(1997)123:4(261)
  20. Smith, B., Williams, B. and Oswald, K. (2002). "Comparison of parametric and non parametric models for traffic flow forecasting." Transp. Res. Part C, Vol. 10, No. 4, pp. 303-321.
  21. Wei, C. H. and Lee, Y. (2007). "Development of freeway travel time forecasting models by integrating different sources of traffic data." IEEE Trans. Veh. Technol., Vol. 56, No. 6II, pp. 3682-3694. https://doi.org/10.1109/TVT.2007.901965
  22. Xie, C., Cheu, R. and Lee, D. (2004). "Improving arterial link travel time estimation by data fusion." Proc. of 84th TRB Annual Meeting, Washington D.C., USA.
  23. You, J. and Kim, T. (2000). "Development and evaluation of a hybrid travel time forecasting model." Transp. Res. Part C, Vol. 8, No. 1-6, pp. 231-256.
  24. Yu, J. (2008). "Real-time travel time estimation model using pointbased and link-based data." J. of Korean Soc. Road Eng., Vol. 10, No. 1, pp. 155-164 (in Korean).
  25. Zhang, X. and Rice, J. (2003). "Short-term travel time prediction." Transp. Res. Part C, Vol. 11, No. 3-4, pp. 187-210.