The Journal of The Korea Institute of Intelligent Transport Systems (한국ITS학회 논문지)

The Korea Institute of Intelligent Transport Systems (한국ITS학회)
권호 표지
DOI QR코드

DOI QR Code

Study on the Classification Methodology for DSRC Travel Speed Patterns Using Decision Trees

의사결정나무 기법을 적용한 DSRC 통행속도패턴 분류방안

  • Received : 2013.12.27
  • Accepted : 2014.03.19
  • Published : 2014.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, travel speed patterns were deducted based on historical DSRC travel speed data using Decision Tree technique to improve availability of the massive amount of historical data. These patterns were designed to reflect spatio-temporal vicissitudes in reality by generating pattern units classified by months, time of day, and highway sections. The study area was from Seoul TG to Ansung IC sections on Gyung-bu highway where high peak time of day frequently occurs in South Korea. Decision Tree technique was applied to categorize travel speed according to day of week. As a result, five different pattern groups were generated: (Mon)(Tue Wed Thu)(Fri)(Sat)(Sun). Statistical verification was conducted to prove the validity of patterns on nine different highway sections, and the accuracy of fitting was found to be 93%. To reduce travel pattern errors against individual travel speed data, inclusion of four additional variables were also tested. Among those variables, 'traffic condition on previous month' variable improved the pattern grouping accuracy by reducing 50% of speed variance in the decision tree model developed.

본 논문의 목적은 DSRC 기반 통행속도 이력데이터를 활용하여 IC-IC 구간 단위의 통행패턴을 도출하는 것이며, 이를 통해 방대한 이력정보 데이터의 활용도를 높이고, 단순하지만 정확성 높은 방법으로 도로의 통행패턴을 용이하게 파악할 수 있게 하는 것이다. 통행패턴 분류는 의사결정나무 기법을 적용하였고, 월 시간대 구간 단위로 분리된 통행패턴을 생성하여 시 공간이 변화되어도 이에 대응 가능하도록 하였다. 경부고속도로 서울TG~안성IC 구간을 대상으로 의사결정나무 기법을 적용한 결과, 요일 기준으로 (월)(화 수 목)(금)(토)(일) 5개 그룹으로 고정 통행패턴이 분류되었다. 분류 결과를 영동, 중부, 중부내륙 고속도로의 9개 구간에 적용하여 통계적 검증을 수행한 결과 약 93%의 적합도를 갖는 것으로 나타났다. 의사결정나무를 통한 통행패턴 오차를 개선하기 위하여 4개의 추가변수를 도입한 결과, "직전월의 소통상황"을 설명변수로 추가할 경우 통행속도 분산이 약 50% 감소함을 확인하였고, 실제 상황에 적용할 경우 소통 원활 시의 오차가 약 4% 감소되었다.

Keywords

References

  1. M. K. Huh, C. No, W. Kim, and B. S. Son, "Development of an incident detection algorithm by using traffic flow pattern," Journal of Korean Society of Transportation,, vol. 28, pp.7-15, Dec. 2010.
  2. S. G. Song, Development of Long Distance Expressway Travel Time Prediction Models during Holiday Seasons, Graduate School of Ajou Univ., Suwon, 2010.
  3. Y. Ohba. "Travel time information calculation method for expressway using toll collection system data," in Proc. ITS int. Conf. Commun. 1999, pp.476-477, Tokyo, Japan, Oct. 1999.
  4. P. Y. Song, A Study on Structural Behavior Analysis and Maintenance Models of Long-span Bridges Considering Traffic Patterns, Graduate School of Ajou Univ., Suwon, 2011.
  5. J. H. Cho, B. S. Kim, S. H. Kim, and W. E. Kang, "Development of a daily pattern clustering algorithm using historical profiles", Journal of the Korea Institute of ITS, vol. 10, pp.11-23, Aug. 2011.
  6. J. W. Choi and Y. G. Yang, "An efficient filtering technique of GPS traffic data using historical data," Journal of Korea Spatial Information Society, vol. 10, pp.55-65, Sep. 2008.
  7. P. Lingras, "Statistical and genetic algorithms classification of highways," Journal of Transportation Engineering, vol. 127, No.3, pp. 237-243, June, 2001 https://doi.org/10.1061/(ASCE)0733-947X(2001)127:3(237)
  8. KECRI, Improvement of Traffic Data Collection, Analysis and Utilization from Vehicle Detection System on Freeway, 2006
  9. K. Ozbay and P. Kachroo, Incident Management in Intelligent Transportation Systems, Boston, MA: Artech House, 1999
  10. C. H. Shin and J. H. Kim, "Development of freeway incident duration prediction models," Journal of Korean Society of Transportation, vol. 20, pp.17-30, Jun. 2002.
  11. O. K. Ha, D. J. Park, J. Won, and C. Jung, "The prediction models for clearance times for the unexpected incidences according to traffic accident classifications in highway", Journal of the Korea Institute of ITS, vol. 9, pp.101-110, Feb. 2010.
  12. H. S. Kim, D. J. Park, C. Kim, C. Choi, and K. Kim, "An analysis of choice behavior for tour type of commercial vehicle using decision tree," Journal of Korean Society of Transportation, vol. 28, pp.43-54, Dec. 2010.
  13. J. W. Kang, K. J. Kum, and S. N. Son, "Drivers detour decision factor analysis with combined method of decision tree and neural network algorithm," Journal of the Korean Society of Road Engineers, vol.13, pp. 167-176, Sep. 2011. https://doi.org/10.7855/IJHE.2011.13.3.167
  14. T. A. Arentze and H. J. P. Timmermans, Incorporating parametric action decision trees in computational process models of activity-travel behavior:Theory and illustration, Advanced OR and AI Methods in Transportation, pp. 567-572, 2005.
  15. S. Y. Sohn and H. W. Shin, "Pattern recognition for road traffic accident severity in Korea", Journal of Ergonomics, Vol 44, pp.107-117, 2001. https://doi.org/10.1080/00140130120928
  16. KECRI, Core Technique Development and Development Plan Report of Hi-pass Transportation Information Systems, 2011.
  17. J. K. Kang, "Regional traffic information acquisition by non-intrusive automatic vehicle identification", Journal of Korea Institute of ITS, vol. 1, pp.22-32, Oct. 2002.