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

Forecasting of Traffic Accident Occurrence Pattern Using LSTM

LSTM을 이용한 교통사고 발생 패턴 예측

  • 노유진 (도로교통공단 운전면허본부) ;
  • 배상훈 (부경대학교 공간정보시스템공학과)
  • Received : 2021.05.13
  • Accepted : 2021.06.24
  • Published : 2021.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

There are many lives lost due traffic accidents, and which have not decreased despite advances in technology. In order to prevent traffic accidents, it is necessary to accurately forecast how they will change in the future. Until now, traffic accident-frequency forecasting has not been a major research field, but has been analyzed microscopically by traditional methods, mainly based on statistics over a previous period of time. Despite the recent introduction of AI to the traffic accident field, the focus is mainly on forecasting traffic flow. This study converts into time series data the records from 1,339,587 traffic accidents that occurred in Korea from 2014 to 2019, and uses the AI algorithm to forecast the frequency of traffic accidents based on driver's age and time of day. In addition, the forecast values and the actual values were compared and verified based on changes in the traffic environment due to COVID-19. In the future, these research results are expected to lead to improvements in policies that prevent traffic accidents.

교통사고로 인한 많은 인명피해가 발생하고 있으나, 첨단 기술의 발전에도 불구하고 교통사고 발생은 줄어들지 않고 있다. 교통사고를 사전에 예방하기 위해서는 향후 사고가 어떻게 변화하여 갈 것인지를 정확하게 예측할 필요가 있다. 지금까지 교통사고 발생 빈도 예측은 주요 연구 분야가 아니었으며 주로 과거 일정 기간의 통계를 기반으로 전통적인 방법으로 미시적으로 분석되어 왔다. 최근 AI 기술이 교통사고 분야에 도입 되었음에도 불구하고 주로 교통 흐름 예측에 초점을 맞추고 있어, 본 연구에서는 2014년부터 2019년까지 국내에서 발생한 1,339,587건의 교통사고 기록을 시계열 데이터로 변환하고 AI 알고리즘 LSTM을 이용하여 연령별, 시간별 교통사고 발생 빈도를 예측하였다. 또한 코로나-19로 인한 교통 환경의 변화에 맞추어 예측값과 실제값을 비교 검증하였다. 향후 이러한 연구결과가 교통사고 예방의 정책개선으로 이어지고 사고 예방에 활용 될 것으로 기대된다.

Keywords

References

  1. Armstrong J. S.(1985), Long-rang Forcasting: From Cristal Ball to Computer, 2nd, ed, Wiley.
  2. Bengio Y., Courville A. and Vincent P.(2013), "Representation Learning : A Review and New Perspectives," IEEE Trans. PAMI, Special issue Learning Deep Architectures, vol. 35, no. 8, pp.1798-1828.
  3. Benoit F.(2019), Road accidents in Switzerland forecasting - A brief comparison between Facebook Prophet and LSTM neural networks, Towards Data Science.
  4. Chris Olah, https://colah.github.io/posts/2015-08-Understanding-LSTMs/, 2021.05.21.
  5. Christian S., Christian A. T. and Dumitru E.(2013), "Deep neural networks for object detection," Advances in neural processing systems.
  6. Christopher O.(2015), Understanding LSTM Networks.
  7. Chung J., Gulcehre C., Cho K. and Bengio Y.(2014), "Empirical evaluation of gated recurrent neural netwotks on sequence modeling," arXiv preprint arXiv:1412.3555.
  8. Guangyuan P., Fu L. and Thakali L.(2017), "Development of a global road safety performance function using deep neural networks," International Journal of Transportation Science and Technology, vol. 6, no. 3. pp.159-173. https://doi.org/10.1016/j.ijtst.2017.07.004
  9. Han J. S.(2019), A Study on the Development of a Traffic Accident Risk Prediction Model Using Deep Learning Techniques, Korea University, pp.12-17.
  10. Hinton G. E., Osindero S. and Teh Y. W.(2006), "The A fast learning algorithm for deep belief nets," Neural Computation, vol. 18, no. 7, pp.1527-1554. https://doi.org/10.1162/neco.2006.18.7.1527
  11. Hochreiter S. and Schmidhuber J.(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. Honglei Ren. et al.(2017), "A deep learning approach to the prediction of short-term traffic accident risk,"arXiv preprint arXiv:1710.09543.
  13. Jakub Kvita, https://kvitajakub.github.io/2016/04/14/rnn-diagrams/, 2021.04.12.
  14. Jang W. J.(2019), Applications of deep learning methods in transportation research, Koti, pp.13-21.
  15. Jason B.(2020), Deep Learning for Time Series Forecasting, Machine Learning Mastery, pp.123-160.
  16. Koroad(2020), Traffic accident statistical analysis, http://taas.koroad.or.kr
  17. KOTI(2018), "Results of Investigation on Victims of Traffic Accidents and Improvement Plans for Victim Support System," National Assembly Traffic Safety Forum.
  18. Krizhevsky A.(2009), "Convolutional Deep Belief Networks on CIFAR-10," Unpublished Manuscript, vol. 1, pp.1-9.
  19. Lee K. and Roh J.(2015), "Development of Traffic Accident Prediction Model Using Probability Parameter - Targeted at 4 Intersections in the Metropolitan Area and Busan Metropolitan City," Journal of the Korean ITS Society, vol. 14, no. 5, pp.101-111.
  20. Lee S., Kim J. and Kim T.(2003), "Development of urban road traffic accident prediction model in the planning stage according to road and traffic characteristics," Journal of the Korean Traffic Association, vol. 21, no. 4, pp.133-144.
  21. Makridakis S., Spiliotis E. and Assimakopoulos V.(2018), "Statistical and Machine Learning forecasting methods: Concerns and ways forward," PLoS ONE, vol. 13, no. 3, e0194889, https://doi.org/10.1371/journal.pone.0194889.
  22. National Police Agency(2004), A Study on the Revision of Traffic Accident Statistics, National Police Agency, pp.39-69.
  23. Nikhil B. and Nicholas L.(2017), Fundamentals of Deep Learning, O'reilly, pp.88-115.
  24. Oh J., Yoon I. Hwang J., Choi J. and Han E.(2014), "A comparative study of the performance of the traffic accident prediction model at the intersection of the four districts using nonlinear regression analysis, artificial neural network, and structural equation," Journal of the Korean Traffic Association, vol. 32, no. 3, pp.266-279.
  25. Reimers N. and Gurevych(2017), "Optimal hyper-parameters for deep lstm-networks for sequence labering tasks," arXiv preprint arXiv:1707.06799.
  26. Ryu J. D.(2018), Development of Expressway Traffic Accident Prediction Model Using Deep Learning, AJOU University, vol. 17, no. 4, pp.14-25.
  27. Sameen M. I. and Pradhan B.(2017), "Severity Prediction of Traffic Accidents with Recurrent Neural Networks," Applied Sciences, vol. 7, no. 6, 476. https://doi.org/10.3390/app7060476
  28. Tomas M., Martin K., Lukas B., Jan H. C. and Sanjeev K.(2010), Recurrent neural network based language model, Interspeech, pp.1045-1048.
  29. Witten I. H. et. al.(2011), Data Mining : Practical Machine Learning Tools and Techniques, Third Edition, Morgan Kaufimann, Boston.
  30. Zhihao Z. et al.(2020), "Traffic Accident Prediction Based on LSTM-GBRT Model," Journal of Control Science and Engineering, vol. 2020, https://doi.org/10.1155/2020/4206919.