Journal of information and communication convergence engineering

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

DOI QR Code

Performance Comparison of Machine-learning Models for Analyzing Weather and Traffic Accident Correlations

  • Li Zi Xuan (School of Software, Kunsan National University) ;
  • Hyunho Yang (School of Software, Kunsan National University)
  • Received : 2023.06.12
  • Accepted : 2023.08.29
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Owing to advancements in intelligent transportation systems (ITS) and artificial-intelligence technologies, various machine-learning models can be employed to simulate and predict the number of traffic accidents under different weather conditions. Furthermore, we can analyze the relationship between weather and traffic accidents, allowing us to assess whether the current weather conditions are suitable for travel, which can significantly reduce the risk of traffic accidents. In this study, we analyzed 30000 traffic flow data points collected by traffic cameras at nearby intersections in Washington, D.C., USA from October 2012 to May 2017, using Pearson's heat map. We then predicted, analyzed, and compared the performance of the correlation between continuous features by applying several machine-learning algorithms commonly used in ITS, including random forest, decision tree, gradient-boosting regression, and support vector regression. The experimental results indicated that the gradient-boosting regression machine-learning model had the best performance.

Keywords

Acknowledgement

This study was supported by an industry-academic cooperation R&D program funded by the LX Spatial Information Research Institute (LXSIRI, Republic of Korea) [Project Name: Prediction of water storage rate against drought in agricultural reservoirs using spatial information-based artificial intelligence analysis/Project Number: 2023-501).

References

  1. US News & World Report. (2023, January 10). US Study: One Year of Road Crashes Cost Society $340 Billion. [Online] Available: https://www.usnews.com/news/business/articles/2023-01-10/us-study-one-year-of-road-crashes-cost-society-340-billion.
  2. A. Zeroual, F. Harrou, and Y. Sun, "Predicting road traffic density using a machine learning-driven approach," in Proceedings of 2021 International Conference on Electrical, Computer and Energy Technologies (ICECET), Cape Town, South Africa, pp. 1-6, 2021. DOI: 10.1109/ICECET52533.2021.9698639.
  3. S. Ahmed, M. A. Hossain, M. M. I. Bhuiyan, and S. K. Ray, "A comparative study of machine learning algorithms to predict road accident severity," in Proceedings of 2021 20th International Conference on Ubiquitous Computing and Communications (IUCC/CIT/DSCI/SmartCNS), London, United Kingdom, pp. 390-397, 2021. DOI: 10.1109/IUCC-CIT-DSCI-SmartCNS55181.2021.00069.
  4. L. Liu, "A Short-term traffic flow prediction method based on S. V. R.," in Proceedings of 2021 2nd International Conference on Urban Engineering and Management Science (ICUEMS), Sanya, China, pp. 1-4, 2021. DOI: 10.1109/ICUEMS52408.2021.00008.
  5. M. N. Tahir and U. Rashid, "Demo: Intelligent transport system (ITS) assisted road weather & traffic services," in Proceedings of 2020 IEEE Vehicular Networking Conference (V.N.C.), NewYork, USA, pp. 1-2, 2020. DOI: 10.1109/VNC51378.2020.9318377.
  6. G. V. Sajan and P. Kumar, "Forecasting and analysis of train delays and impact of weather data using machine learning," in Proceedings of 2021 12th International Conference on Computing Communication and Networking Technologies (ICCCNT), Kharagpur, India, pp. 1-8, 2021. DOI: 10.1109/ICCCNT51525.2021.9580176.
  7. W. Ming Zhou, T. Shan, C. Chao, and Z. Jian dan, "Short-time traffic flow forecast with weather characteristics," in Proceedings of 2020 International Conference on Computer Communication and Network Security (CCNS), Xi'an, China, pp. 142-145, 2020. DOI: 10.1109/CCNS50731.2020.00039.
  8. Jacob, "Traffic-Accident-Data Dataset for machine learning" [Online] Available: https://www.kaggle.com/datasets/bobaaayoung/trafficaccidentdata.
  9. S. Zhang, "Urban traffic accident prediction research based on meteorological data," in Proceedings of 2022 International Conference on Machine Learning and Knowledge Engineering (MLKE), Guilin, China, pp. 130-133, 2022, DOI: 10.1109/MLKE55170.2022.00031.
  10. M. Hellweg, J.-W. Acevedo-Valencia, Z. Paschal Idi, J. Nachtigall, T. Kretsch, and C. Stiller, "Using floating car data for more precise road weather forecasts," in Proceedings of 2020 IEEE 91st Vehicular Technology Conference (VTC2020-Spring), Antwerp, Belgium, pp. 1-3, 2020. DOI: 10.1109/VTC2020-Spring48590.2020.9129401.