Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

A Short-Term Vehicle Speed Prediction using Bayesian Network Based Selective Data Learning

선별적 데이터 학습 기반의 베이지안 네트워크를 이용한 단기차량속도 예측

  • Park, Seong-ho (Information Technology Center, Pusan National University) ;
  • Yu, Young-jung (Department of Computer Engineering, Busan University of Foreign Studies) ;
  • Moon, Sang-ho (Department of Computer Engineering, Busan University of Foreign Studies) ;
  • Kim, Young-ho (Department of Road Transport Research, The Korea Transport Institute)
  • Received : 2015.08.10
  • Accepted : 2015.09.11
  • Published : 2015.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

The prediction of the accurate traffic information can provide an optimal route from the place of departure to a destination, therefore, this makes it possible to obtain a saving of time and money. To predict traffic information, we use a Bayesian network method based on probability model in this paper. Existing researches predicting the traffic information based on a Bayesian network generally used to study the data for all time. In this paper, however, only data corresponding to same time and day of the week to predict selectively will be used for learning. In fact, the experiment was carried out for 14 links zone in Seoul, also, the accuracy of the prediction results of the two different methods should be tested with MAPE (Mean Absolute Percentage Error) which is commonly used. In view of MAPE, experimental results show that the proposed method may calculate traffic prediction value with a higher accuracy than the method used to learn the data for all time zones.

정확한 교통정보의 예측은 출발지로부터 목적지까지의 최적경로를 제공할 수 있으며, 이로 인해 시간과 비용의 절감 효과를 얻을 수 있다. 본 논문에서는 다양한 교통정보 예측 방법 중 확률 모델을 기반으로 교통정보를 예측하는 베이지안 네트워크 방법을 이용한다. 기존 연구에서는 베이지안 네트워크 예측 방법이 모든 시간대에서의 데이터를 학습에 사용하는 것과는 달리, 본 논문에서는 예측하고자 하는 시간대와 동일한 요일과 시간에 해당하는 데이터만을 선별적으로 학습에 사용한다. 서로 다른 두 가지 학습방법에 따른 예측 결과의 정확도는 일반적으로 많이 사용되는 MAPE(Mean Absolute Percentage Error)로 검증하였으며, 서울 시내 14개의 링크 구간에 대해 실험을 진행하였다. 실험결과는 본 논문에서 제안한 방법이 모든 시간대의 데이터를 학습에 사용한 방법에 비해 MAPE의 관점에서 더 높은 정확도를 가진 교통 예측 값을 계산할 수 있음을 보여준다.

Keywords

References

  1. Cheol Oh, "A Study Toward Developing a Framework for Intelligent Transport Systems(ITS) Audit," KOTI, 2005.
  2. Shiliang Sun, Changshui Zhang, Guoqiang Yu, "A Bayesian Network Approach to Traffic Flow," IEEE Transaction on Intelligent Transportation Systems, Vol. 7, No. 1, 2006.
  3. Hironobu Kitaoka, Takahiro Shiga, Hiroko Mori etc., "Development of a Travel Time Prediction Method for the TOYAA G-BOOK Telematics Services," R&D Review of Toyata CRDL, Vol. 41, No. 4, 2007.
  4. Y. Yu and M. G. Cho, "A Short-Term Prediction Model for Forecasting Traffic Information Using Bayesian Network," Third 2008 International Conference on Convergence and Hybrid Information Technology, pp. 247-253, 2008.
  5. G. Q. Yu, J. M. Hu, C. S. Zhang, etc. "Short-Term Traffic Flow Forecasting based on Markov Chain Model," Proc. IEEE Intelligenct Vehicles Symp., Columbus, OH, 2003.
  6. J.W.C van Lint, S.P. Hoogendoorn, and H.J. van Zuylen, "Robust and Adaptable Travel Time Prediction with Neural Networks," Proc. 6th Annual ransport, 2000.
  7. Rui Wang, Hideki Nakamura, "Short erm Prediction Works in Traffic Engineering: The State-Of-The-Art," ITS World Congress, 2002.
  8. M. G. Cho, Y. Yu and S. Kim, "The System for Predicting the Traffic Flow with Real-Time Traffic Information," Lecture Note in Computer Science, Vol. 3980, 2006.
  9. M. A. Rasyidi, J. Kim and K. R. Ryu, "Short-erm Prediction of Vehicle Speed on Main City Roads using the k-Nearest Neighbor Algorithm," Journal of Intelligence and Information Systems, Vol. 20, No. 1, pp. 121-131, 2014. https://doi.org/10.13088/JIIS.2014.20.1.121