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

A Study on the Application of Machine Learning to Improve BIS (Bus Information System) Accuracy

BIS(Bus Information System) 정확도 향상을 위한 머신러닝 적용 방안 연구

  • Jang, Jun yong (Public Transportation Division, Sejong City hall) ;
  • Park, Jun tae (Dept. of Transportation Systems Engineering, University of Transportation Korea)
  • 장준용 (세종시청 대중교통과) ;
  • 박준태 (한국교통대학교 교통시스템공학과)
  • Received : 2022.03.18
  • Accepted : 2022.06.02
  • Published : 2022.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

Bus Information System (BIS) services are expanding nationwide to small and medium-sized cities, including large cities, and user satisfaction is continuously improving. In addition, technology development related to improving reliability of bus arrival time and improvement research to minimize errors continue, and above all, the importance of information accuracy is emerging. In this study, accuracy performance was evaluated using LSTM, a machine learning method, and compared with existing methodologies such as Kalman filter and neural network. As a result of analyzing the standard error for the actual travel time and predicted values, it was analyzed that the LSTM machine learning method has about 1% higher accuracy and the standard error is about 10 seconds lower than the existing algorithm. On the other hand, 109 out of 162 sections (67.3%) were analyzed to be excellent, indicating that the LSTM method was not entirely excellent. It is judged that further improved accuracy prediction will be possible when algorithms are fused through section characteristic analysis.

BIS(Bus Information System) 서비스는 대도시를 포함하여 중소도시까지 전국적으로 확대운영되는 추세이며, 이용자의 만족도는 지속적으로 향상되고 있다. 이와 함께 버스도착시간 신뢰성 향상 관련 기술개발, 오차 최소화를 위한 개선 연구가 지속되고 있으며 무엇보다 정보 정확도의 중요성이 부각되고 있다. 본 연구에서는 기계학습 방법인 LSTM을 이용하여 정확도 성능을 평가하였으며 기존 칼만필터, 뉴럴 네트워크 등 방법론과 비교하였다. 실제 여행시간과 예측값에 대해 표준오차를 분석한 결과 LSTM 기계학습 방법이 기존 알고리즘에 비해 정확도는 약 1% 높고, 표준오차는 약 10초 낮은 것으로 분석되었다. 반면 총 162개 구간 중 109개 구간(67.3%) 우수한 것으로 분석되어 LSTM 방법이 전적으로 우수한 것은 아닌 것으로 나타났다. 구간 특성 분석을 통한 알고리즘 융합시 더욱 향상된 정확도 예측이 가능할 것으로 판단된다.

Keywords

References

  1. Ashwini, B. P., Sumathi, R. and Sudhira, H. S.(2022), "Bus Travel Time Prediction: A Comparative Study of Linear and Non-Linear Machine Learning Models", Journal of Physics Conference Series, 2161, Canada.
  2. Baker, C. B. and Nied, A.(2014), "Predicting bus arrival using One Bus Away real-time data", Computer Science, p.204.
  3. Chang, H. H., Yoon, B. J. and Lee, J. S.(2019), "A Study on Development of Bus Arrival Time Prediction Algorithm by using Travel Time Pattern Recognition", Journal of the Korean Society of Civil Engineers, vol. 39, no. 6, pp.833-839. https://doi.org/10.12652/Ksce.2019.39.6.0833
  4. Chen, X., Lei, Y., Yushi, Z. and Jifu, G.(2009), "Analyzing urban bus service reliability at the stop, route, and network levels", Transportation Research Part A Policy and Practice, vol. 43, no. 8, pp.722-734. https://doi.org/10.1016/j.tra.2009.07.006
  5. Dancho, P. and Titus, Z.(2020), "Real-Time Public Transportation Prediction with Machine Learning Algorithms", IEEE International Conference on Consumer Electronics(ICCE), USA.
  6. Kim, W. G., Roh, C. G., Heo, M. G. and Son, B. S.(2009), "A Development of Bus Arrival Time Estimation Model", Seoul Studies, vol. 10, no. 2, pp.21-29.
  7. Lee, J. Y., Gu, E. M., Kim, H. J. and Jang, K. T.(2017), "Long-term Prediction of Bus Travel Time Using Bus Information System Data", Journal of Korean Society of Transportation, vol. 35, no. 4, pp.348-359. https://doi.org/10.7470/jkst.2017.35.4.348
  8. Li, Y., Pree, T. and Poon, T.(2021), "A Real-Time Bus Arrival Time Prediction System Based on Spark Framework and Machine Learning Approaches: A case study in Chiang Mai", Joint International Conference on Digital Arts, Media and Technology with ECTI Northern Section Conference on Electrical, Electronics, Computer and Telecommunication Engineering, Thailand.
  9. Patricia, H., Justin, A., Yvonne, C. and Richard, H.(2015), "Transit Travel Time Reliability: Shifting the Focus from Vehicles to Customers", Transportation Research Record: Journal of the Transportation Research Board, vol. 2535, no. 1, pp.35-44. https://doi.org/10.3141/2535-04
  10. Roh, C. G., Kim, W. G. and Son, B. S.(2010), "Development of Bus Arrival Time Estimation Model by Unit of Route Group", Journal of Korea Transportation Research Society, vol. 28, no. 1, pp.135-142.
  11. Schmidhuber, J. and Hochreiter, S.(1997), "Long short-term memory", Neural Computation, vol. 9, no. 8, pp.1735-1780. https://doi.org/10.1162/neco.1997.9.8.1735
  12. Wi, J. R.(2013), A Study on the Weighted Value Application Standard of Fusion Algorithm for the Estimate Bus Arrival Time Prediction, Master's Thesis, University of Seoul.
  13. Yang, M., Chen, C., Wang, L. and Yan, X.(2016), "Bus Arrival Time Prediction Using Support Vector Machine with Genetic Algorithm", Neural Network World, vol. 26, no. 3, pp.205-217. https://doi.org/10.14311/nnw.2016.26.011
  14. Yuan, Y., Shao, C., Cao, Z., He, Z., Zhu, C., Wang, Y. and Jang, V.(2020), "Bus Dynamic Travel Time Prediction: Using a Deep Feature Extraction Framework Based on RNN and DNN", Electronics, vol. 9, no. 11, pp.1-20.
  15. Zhang, X., Yan, M., Xie, B., Yang, H. and Ma, H.(2021), "An automatic real-time bus schedule redesign method based on bus arrival time prediction", Advanced Engineering Informatics, vol. 48, 101295, pp.1-15.