All Issue

2019 Vol.37, Issue 5 Preview Page

Article

Long-term Prediction of Freeway Travel Time Using Route Travel Data

고속도로 이동경로별 중장기 통행시간 예측 방법론 개발

Jooyoung LEE1
,
Sanghoon SON2
,
Hyungjoo KIM3*
이 주영1
,
손 상훈2
,
김 형주3*
1Ph.D Course, The Cho Chun Shik Graduate School of Green Transportation, KAIST, Daejeon 34051, Korea
2Research Fellow, Regional Planning and Environment Division, Jeju Research Institute, Jeju 63147, Korea
3Senior Researcher, Advanced Institute of Convergence Technology, AICT, Gyeonggi 13449, Korea
1KAIST 조천식녹색교통대학원 박사과정
2제주연구원 미래전략연구부 책임연구원
3차세대융합기술연구원 경기도자율주행센터 선임연구원
* Corresponding Author
31 October 2019. pp. 399-409
PDF XML Citation
Abstract

Predicted travel time is important factor to help commuters make route choices and departure time decisions. Especially, it has an effect of dispersing the demand on the road. Previous research have been focused on providing information on the expected arrival time for a single route with a link travel time prediction. There is a limit to the study of travel time prediction by different routes that affects user’s actual decision making. In this study, we have studied long-term travel time prediction using route travel data. We used self-organizing map clustering algorithm and the input variables of the model were day of the week, weather, daily traffic volume. Long-term travel time prediction for the Jungbu Naeryuk expressway, Cheongwon-Sangju expressway, Gyeongbu expressway is conducted and prediction results of k-NN were used for comparison of the predicted results. The prediction error of the travel time for each route was reduced and it showed a high error reduction in the Jungbu Naeryuk Expressway which has the most traffic volume of Seoul-Daegu section. In this paper, we proposed a method to overcome the limitation of the link-based travel time prediction. It can be used for route choices and departure time decisions of individual commuters by providing reliable travel time prediction for each route.

Keywords
long-term prediction
route travel data
self-organizing map
travel time prediction
weather information

고속도로 통행시간 예측 정보는 이용자의 통행계획 수립과 통행경로 선택에 중요한 요인으로 작용하며 도로에 집중된 교통수요 집중을 분산시키는 효과를 가진다. 기존 통행시간 예측 연구는 단기적 관점의 링크 통행시간 예측 연구로 단일 경로에 대한 도착예정시간 정보를 제공하는데 중점을 두고 있는데 이용자의 실제 통행 의사결정에 영향을 미치는 이동경로별 통행시간 예측 측면에서 한계를 보였다. 이에 본 연구에서는 경로형 데이터를 활용하여 이동경로별 중장기 통행시간 예측 연구를 실시한다. 이를 위하여 입력변수로 고속도로 통행시간에 영향을 주는 요소인 요일, 기상, 일 단위 교통량 등을 활용하였으며, 분석방법으로는 머신러닝 기반 자기조직화지도 클러스터링 알고리즘을 활용하였다. 서울-대구 구간의 대부분의 이동경로인 중부내륙, 청원-상주, 경부선 등에 대한 중장기 통행시간 예측을 수행하였으며, 예측 결과의 비교 ‧ 검증을 위해서 k-NN 예측결과를 활용하였다. 분석결과 각 이동경로별 통행시간 예측오차가 감소하였으며, 특히 서울-대구 통행 경로 중에서 가장 많은 통행을 가지는 중부내륙 고속도로에서 높은 오차감소를 보였다. 본 연구는 기존의 단기적 링크기반의 통행시간 예측의 부정확한 한계를 극복할 수 있는 방법으로 이동경로별 신뢰성 있는 통행시간 예측정보를 제공함으로써 개별 통행자의 경로선택 및 출발시간 선택 등에 유용하게 활용되어질 수 있을 것으로 판단된다.

키워드
중장기 예측
경로형 데이터
자기조직화지도
통행시간 예측
기상정보
References
1
Caliński T., Harabasz J. (1974), A Dendrite Method for Cluster Analysis, Communications in Statistics-theory and Methods, 3(1), 1-27.
10.1080/03610927408827101
2
Chen M., Liu X., Xia J., Chien S. I. (2004), A Dynamic Bus-arrival Time Prediction Model Based on APC Data, Computer-Aided Civil and Infrastructure Engineering, 19(5), 364-376.
10.1111/j.1467-8667.2004.00363.x
3
Chou C.-H., Huang Y., Huang C.-Y., Tseng V. S. (2019) Long-Term Traffic Time Prediction Using Deep Learning with Integration of Weather Effect, Advances in Knowledge Discovery and Data Mining, 123-135.
10.1007/978-3-030-16145-3_10
4
Expressway Public Data Portal, Korea Expressway Corporation, http://data.ex.co.kr
5
Improvement of Traffic Information System and Prediction Project (2017), Korea Expressway Corporation.
6
Jeong E., Oh C., Hong S. (2013), Prediction of Speed by Rain Intensity using Road Weather Information System and Vehicle Detection System data, The Journal of The Korea Institute of Intelligent Transport Systems, 12(4), 44-55.
10.12815/kits.2013.12.4.044
7
Jeong E., Oh C., Kim Y. (2015), Development of a Mid-/Long-term Prediction Algorithm for Traffic Speed Under Foggy Weather Conditions, J. Korean Soc. Transp., 33(3), Korean Society of Transportation, 256-267.
10.7470/jkst.2015.33.3.256
8
Kim B., An S., Son J., Park H. (2016a) Cluster analysis for highway speed according to patterns and effects, Korean Journal of Applied Statistics, 29(5), 949-960.
10.5351/KJAS.2016.29.5.949
9
Kim H., Jang K. (2013) Short-Term Prediction of Travel Time Using DSRC on Highway, Journal of the Korean Society of Civil Engineers, 33(6), 2465-2471.
10.12652/Ksce.2013.33.6.2465
10
Kim H., Kim Y., Jang K. (2017) Systematic Relation of Estimated Travel Speed and Actual Travel Speed, IEEE Transactions on Intell. Transp. Syst., 18(10), 2780-2789.
10.1109/TITS.2017.2713983
11
Kim H., Park S., Jang K. (2016b) Short-term Traffic States Prediction Using k-Nearest Neighbor Algorithm: Focused on Urban Expressway in Seoul, J. Korean Soc. Transp., 34(2), Korean Society of Transportation, 107-122.
10.7470/jkst.2016.34.2.158
12
Kim J. (2009), Estimating Origin-Destination Travel Time of Freeway, Transportation Research, 16(2), 41-52.
10.34143/jtr.2009.16.2.41
13
Kim J., Kim, Y. (2015), A Study on the Application of Measures of Travel Time Variability by Analysis of Travel Time Distribution According to Weather Factor, The Journal of The Korea Institute of Intelligent Transport Systems, 14(6), 1-13.
10.12815/kits.2015.14.6.001
14
Kohonen T. (1990), The Self-organizing Map, Proceedings of the IEEE, 78(9), 1464-1480.
10.1109/5.58325
15
Kwon J., Coifman B., Bickel P. (2000), Day-to-day Travel-time Trends and Travel-time Prediction From Loop-detector Data, Transportation Research Record, Transp. Res. Rec., 1717, 120-129.
10.3141/1717-15
16
Lee J., Gu E. Kim H., Jang K. (2017), Long-term Prediction of Bus Travel Time using Bus Information System Data, J. Korean Soc. Transp., 35(4), Korean Society of Transportation, 346-357.
10.7470/jkst.2017.35.4.348
17
Lee S., Kim, H. (2019), Detour Pattern on the Expressway using Route Travel Data, Korea Institute of Intelligent Transport Systems Conference.
18
Li, R., Rose, G., Chen, H., Shen, J. (2017) Effective Long-term Travel Time Prediction with Fuzzy Rules for Tollway, Neural Comput. Appl., 1-13.
10.1007/s00521-017-2899-6
19
Long K., Yao W., Gu J., Wu W., Lee D.H. (2019), Predicting Freeway Travelling Time Using Multiple-Source Data, Appl. Sci., 9(1), 1-17.
10.3390/app9010104
20
Nookala L. S. (2006), Weather Impact on Traffic Conditions and Travel Time Prediction, Doctoral Dissertation, University of Minnesota, Duluth.
21
Qiao W., Haghani A., Mamedi M. (2013), A Nonparametric Model for Short-Term Travel Time Prediction Using Bluetooth Data, Journal of Intelligent Transportation Systems, 17(2), 165-175, Taylor and Francis Group.
10.1080/15472450.2012.748555
22
Rice J., Van Zwet E. (2004), A Simple and Effective Method for Predicting Travel Times on Freeways, IEEE Transactions on Intelligent Transportation Systems, 5(3), 200-207.
10.1109/TITS.2004.833765
23
Shin K., Shim S., Choi K., Kim S. (2014), Expressway Travel Time Prediction Using K-Nearest Neighborhood, Journal of the Korean Society of Civil Engineers, 34(6), 1873-1879.
10.12652/Ksce.2014.34.6.1873
24
Tak S., Kim S., Jang K., Yeo H. (2014), Real-Time Travel Time Prediction Using Multi-level k-Nearest Neighbor Algorithm and Data Fusion Method, Computing in Civil and Building Engineering, American Society of Civil Engineers, Orlando, Florida.
10.1061/9780784413616.231
25
Vanajakshi L., Rilett L. (2007), Support Vector Machine Technique for the Short Term Prediction of Travel Time, Proceedings of the IEEE Intelligent Vehicles Symposium, 600-605.
10.1109/IVS.2007.4290181
26
Vesanto J. (1999), SOM-based Data Visualization Methods, Intelligent Data Analysis, 3(2), 111-126.
10.3233/IDA-1999-3203
27
Wu C.-H., Ho J.-M., Lee D. (2005), Travel-Time Prediction With Support Vector Regression, IEEE Transactions on Intell. Transp. Syst., 5(4), 276-281.
10.1109/TITS.2004.837813
28
Yang J.-S. (2005), Travel Time Prediction using the GPS Test Vehicle and Kalman Filtering Techniques, Proceedings of the American Control Conference, 2128-2133.
Information
  • Publisher :Korean Society of Transportation
  • Publisher(Ko) :대한교통학회
  • Journal Title :Journal of Korean Society of Transportation
  • Journal Title(Ko) :대한교통학회지
  • Volume : 37
  • No :5
  • Pages :399-409
  • Received Date : 2019-05-21
  • Revised Date : 2019-07-22
  • Accepted Date : 2019-10-14
  • DOI :https://doi.org/10.7470/jkst.2019.37.5.399
Journal Informaiton Journal of Korean Society of Transportation Journal of Korean Society of Transportation
Archives
: 2015 Vol.34~
  • NRF
  • KOFST
  • crossref cited-by
  • crosscheck
  • orcid
  • open access
  • ccl
Journal Informaiton Journal Informaiton - close