KIPS Transactions on Software and Data Engineering (정보처리학회논문지:소프트웨어 및 데이터공학)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Proposed TATI Model for Predicting the Traffic Accident Severity

교통사고 심각 정도 예측을 위한 TATI 모델 제안

  • 추민지 (숙명여자대학교 IT공학과) ;
  • 박소현 (숙명여자대학교 빅데이터활용 연구센터) ;
  • 박영호 (숙명여자대학교 IT공학과)
  • Received : 2021.03.26
  • Accepted : 2021.06.26
  • Published : 2021.08.31
Download PDF
⟨ Previous Next ⟩

Abstract

The TATI model is a Traffic Accident Text to RGB Image model, which is a methodology proposed in this paper for predicting the severity of traffic accidents. Traffic fatalities are decreasing every year, but they are among the low in the OECD members. Many studies have been conducted to reduce the death rate of traffic accidents, and among them, studies have been steadily conducted to reduce the incidence and mortality rate by predicting the severity of traffic accidents. In this regard, research has recently been active to predict the severity of traffic accidents by utilizing statistical models and deep learning models. In this paper, traffic accident dataset is converted to color images to predict the severity of traffic accidents, and this is done via CNN models. For performance comparison, we experiment that train the same data and compare the prediction results with the proposed model and other models. Through 10 experiments, we compare the accuracy and error range of four deep learning models. Experimental results show that the accuracy of the proposed model was the highest at 0.85, and the second lowest error range at 0.03 was shown to confirm the superiority of the performance.

TATI 모델이란 Traffic Accident Text to RGB Image 모델로, 교통사고 심각 정도 예측을 위한 본 논문에서 제안하는 방법론이다. 교통사고 치사율은 매년 감소하는 추세이나 OECD 회원국 중 하위권에 속해있다. 교통사고 치사율 감소를 위해 많은 연구들이 진행되었고, 그 중에서 교통사고 심각 정도를 예측하여 발생 및 치사율을 줄이기 위한 연구가 꾸준하게 진행되고 있다. 이와 관련하여 최근에는 통계 모델과 딥러닝 모델을 활용하여 교통사고 심각 정도 예측을 하는 연구가 활발하다. 본 논문에서는 교통사고 심각 정도를 예측하기 위해서 교통사고 데이터를 컬러 이미지로 변환하고, CNN 모델을 통해 이를 수행한다. 성능 비교를 위해 제안하는 모델과 다른 모델들을 같은 데이터로 학습시키고, 예측결과를 비교하는 실험을 진행했다. 10번의 실험을 통해 4개의 딥러닝 모델의 정확도와 오차 범위를 비교하였다. 실험 결과에 따르면 제안하는 TATI 모델의 정확도가 0.85로 가장 높은 정확도를 보였고, 0.03으로 두 번째로 낮은 오차 범위를 보여 성능의 우수성을 확인하였다.

Keywords

Acknowledgement

이 논문은 2021년도 정부(미래창조과학부)의 재원으로 정보통신기술진흥센터의 지원을 받아 수행된 연구임(No.2016-0-00406. (기반 SW-창소씨앗 2단계)SIAT형 CCTV 클라우드 플랫폼 기술 개발).

References

  1. J. Gan, L. Li, D. Zhang, Z. Yi, and Q. Xiang, "An alternative method for traffic accident severity prediction: Using deep forests algorithm," Journal of Advanced Transportation, 2020.
  2. J. Orlovska, F. Novakazi, B. Lars-Ola, M. Karlsson, C. Wickman, and R. Soderberg, "Effects of the driving context on the usage of Automated Driver Assistance Systems (ADAS)-Naturalistic Driving Study for ADAS evaluation," Transportation Research Interdisciplinary Perspectives, Vol.4, 2020.
  3. S. J. Han, S. Y. Hwang, D. H. Ko, K. J. Eom, Y. S. Oh, and S. Y. Lee, "Research roadmap development for the big data based road accident cause analysis and policy," The Korea Transport Insttitue(KOTI), Issuepaper, Vol.17, No.5, 2017.
  4. G. Fountas and P. C. Anastasopoulos, "Analysis of accident injury-severity outcomes: The zero-inflated hierarchical ordered probit model with correlated disturbances," Analytic Methods in Accident Research, Vol.20, pp.30-45, 2018. https://doi.org/10.1016/j.amar.2018.09.002
  5. K. El-Basyouny and T. Sayed, "Collision prediction models using multivariate Poisson-lognormal regression," Accident Analysis & Prevention, Vol.41, No.4, pp.820-828, 2009. https://doi.org/10.1016/j.aap.2009.04.005
  6. T. K. Bahiru, D. K. Singh, and E. A. Tessfaw, "Comparative study on data mining classification algorithms for predicting road traffic accident severity," In Proceedings of 2018 Second International Conference on Inventive Communication and Computational Technologies (ICICCT), pp.1655-1660, 2018.
  7. V. Rovsek, M. Batista, and B. Bogunovic, "Identifying the key risk factors of traffic accident injury severity on Slovenian roads using a non-parametric classification tree," Transport, Vol.32, No.3, pp.272-281, 2017. https://doi.org/10.3846/16484142.2014.915581
  8. H. T. Abdelwahab and M. A. Abdel-Aty, "Development of artificial neural network models to predict driver injury severity in traffic accidents at signalized intersections," Transportation Research Record, Vol.1746, No.1, pp.6-13, 2001. https://doi.org/10.3141/1746-02
  9. M. M. Kunt, I. Aghayan, and N. Noii, "Prediction for traffic accident severity: Comparing the artificial neural network, genetic algorithm, combined genetic algorithm and pattern search methods," Transport, Vol.26, No.4, pp.353-366, 2011. https://doi.org/10.3846/16484142.2011.635465
  10. M. I. Sameen and B. Pradhan, "Severity prediction of traffic accidents with recurrent neural networks," Applied Sciences, Vol.7, No.6, pp.476-493, 2017. https://doi.org/10.3390/app7060476
  11. M. Zheng, T. Li, R. Zhu, J. Chen, Z. Ma, M. Tang, and Z. Wang, "Traffic accident's severity prediction: A deeplearning approach-based CNN network," IEEE Access, Vol.7, pp.39897-39910, 2019. https://doi.org/10.1109/ACCESS.2019.2903319
  12. P. T. Savolainen, F. L. Mannering, D. Lord, and M. A. Quddus, "The statistical analysis of highway crash-injury severities: A review and assessment of methodological alternatives," Accident Analysis & Prevention, Vol.43, No.5, pp.1666-1676, 2011. https://doi.org/10.1016/j.aap.2011.03.025
  13. A. B. Parsa, R. S. Chauhan, H. Taghipour, S. Derrible, and A. Mohammadian, "Applying Deep Learning to Detect Traffic Accidents in Real Time Using Spatiotemporal Sequential Data," arXiv preprint arXiv:1912.06991, 2019.
  14. Y. Chung, "Injury severity analysis in taxi-pedestrian crashes: An application of reconstructed crash data using a vehicle black box," Accident Analysis & Prevention, Vol.111, pp.345-353, 2018. https://doi.org/10.1016/j.aap.2017.10.016
  15. L. G. Cuenca, E. Puertas, N. Aliane, and J. F. Andres, "Traffic accidents classification and injury severity prediction," In Proceedings of 2018 3rd IEEE International Conference on Intelligent Transportation Engineering (ICITE), pp.52-57, 2018.
  16. M. M. Chen and M. C. Chen, "Modeling road accident severity with comparisons of logistic regression, decision tree and random forest," Information, Vol.11, No.5, 2020.
  17. L. Y. Chang and H. W. Wang, "Analysis of traffic injury severity: An application of non-parametric classification tree techniques," Accident Analysis & Prevention, Vol.38, No.5, pp.1019-1027, 2006. https://doi.org/10.1016/j.aap.2006.04.009
  18. R. O. Mujlli and J. De Ona, "A method for simplifying the analysis of traffic accidents injury severity on two-lane highways using Bayesian networks," Journal of Safety Research, Vol.42, No.5, pp.317-326, 2011. https://doi.org/10.1016/j.jsr.2011.06.010
  19. S. S. Dhaliwal, A. A. Nahid, and R. Abbas, "Effective intrusion detection system using XGBoost," Information, Vol.9, No.7, 2018.
  20. T. Chen and C. Guestrin, "Xgboost: A scalable tree boosting system," In Proceedings of the 22nd Acm Sigkdd International Conference on Knowledge Discovery and Data Mining, pp.785-794, 2016.
  21. J. H. Friedman, "Greedy function approximation: A gradient boosting machine," Annals of Statistics, pp.1189-1232, 2001.
  22. W. Y. Loh, "Classification and regression trees," Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, Vol.1, No.1, pp.14-23, 2011. https://doi.org/10.1002/widm.8
  23. M. Abadi, A. Agarwal, P. Barham, E. Brevdo, Z. Chen, C. Citro, and X. Zheng, "Tensorflow: Large-scale machine learning on heterogeneous distributed systems," arXiv preprint arXiv:1603.04467, 2016.
  24. T. Fawcett, "An introduction to ROC analysis," Pattern Recognition Letters, Vol.27, No.8, pp.861-874, 2006. https://doi.org/10.1016/j.patrec.2005.10.010