DOI QR코드

DOI QR Code

Macro-Level Accident Prediction Model using Mobile Phone Data

이동통신 자료를 활용한 거시적 교통사고 예측 모형 개발

  • Kwak, Ho-Chan (Future Transport Policy Research Division, Korea Railroad Research Institute) ;
  • Song, Ji Young (Future Transport Policy Research Division, Korea Railroad Research Institute) ;
  • Lee, In Mook (Future Transport Policy Research Division, Korea Railroad Research Institute) ;
  • Lee, Jun (Future Transport Policy Research Division, Korea Railroad Research Institute)
  • 곽호찬 (한국철도기술연구원 미래교통정책본부) ;
  • 송지영 (한국철도기술연구원 미래교통정책본부) ;
  • 이인묵 (한국철도기술연구원 미래교통정책본부) ;
  • 이준 (한국철도기술연구원 미래교통정책본부)
  • Received : 2018.04.16
  • Accepted : 2018.08.17
  • Published : 2018.08.31

Abstract

Macroscopic accident analyses have been conducted to incorporate transportation safety into long-term transportation planning. In macro-level accident prediction model, exposure variable(e.g. a settled population) have been used as fundamental explanatory variable under the concept that each trip will be subjected to a probable risk of accident. However, a settled population may be embedded error by exclusion of active population concept. The objective of this research study is to develop macro-level accident prediction model using floating population variable(concept of including a settled population and active population) collected from mobile phone data. The concept of accident prediction models is introduced utilizing exposure variable as explanatory variable in a generalized linear regression with assumption of a negative binomial error structure. The goodness of fit of model using floating population variable is compared with that of the each models using population and the number of household variables. Also, log transformation models are additionally developed to improve the goodness of fit. The results show that the log transformation model using floating population variable is useful for capturing the relationships between accident and exposure variable and generally perform better than the models using other existing exposure variables. The developed model using floating population variable can be used to guide transportation safety policy decision makers to allocate resources more efficiently for the regions(or zones) with higher risk and improve urban transportation safety in transportation planning step.

Keywords

References

  1. J. Lee, M. Abdel-Aty and X. Jiang, "Multivariate Crash Modeling for Motor Vehicle and Non-motorized Modes at the Macroscopic Level", Accid. Anal. & Prev., Vol. 78, pp. 146-154, 2015. https://doi.org/10.1016/j.aap.2015.03.003
  2. J. H. Kim, Y. S. Ko and J. K. Kim, "Application and Implication of Mobile Big Data in Land and Transportation Fields", KRIHS Policy Brief, Vol. 499, pp. 1-6, 2015.
  3. K. T. Kim, I. M. Lee, H-. C. Kwak and J. H. Min, "Application Study of Telecommunication Record Data in Floating Population Estimation", Seoul Studies, Vol. 16, No. 3, pp. 181-191, 2015.
  4. K. T. Kim, I. Lee, H. C. Kwak and J. H. Min, "An Estimation of Occupancy Population Using the Expanded Mobile Phone Data", Journal of Korean Society of Transportation, Vol. 34, No. 3, pp. 222-233, 2016. https://doi.org/10.7470/jkst.2016.34.3.222
  5. K. Kim, I. Lee, J. H. Min and H. C. Kwak, "Trip Generation Analysis Using Mobile Phone Data", Journal of Korean Society for Railway, Vol. 18, No. 5, pp. 481-488, 2015. https://doi.org/10.7782/JKSR.2015.18.5.481
  6. A. Hadayeghi, A. S. Shalaby and B. N. Persaud, "Macrolevel Accident Prediction Models for Evaluating Safety of Urban Transportation Systems", Transp. Res. Rec., Vol. 1840, pp. 87-95, 2003. https://doi.org/10.3141/1840-10
  7. A. Naderan and J. Shahi, "Aggregate Crash Prediction Models: Introducing Crash Generation Concept", Accid. Anal. & Prev., Vol. 42, pp. 339-346, 2010. https://doi.org/10.1016/j.aap.2009.08.020
  8. A. Hadayeghi, A. S. Shalaby and B. N. Persaud, "Development of Planning Level Transportation Safety Tools Using Geographically Weighted Poisson Regression", Accid. Anal. & Prev., Vol. 42, pp. 676-688, 2010. https://doi.org/10.1016/j.aap.2009.10.016
  9. T. Lee, H. C. Kwak, D-. K. Kim and S. Y. Kho, "Development of a Safety Performance Function for Expressway Tollgates", Journal of Korean Society of Transportation, Vol. 33, No. 1, pp. 81-89, 2015. https://doi.org/10.7470/jkst.2015.33.1.81
  10. S. K. Son, A. H. Cho and B. H. Park, "Truck Accident Models of Circular Intersections by Type of Accident and Conflict", J. Korean Soc. Saf., Vol. 32, No. 3, pp. 123-129, 2017. https://doi.org/10.14346/JKOSOS.2017.32.3.123
  11. S. S. Han and B. H. Park, "Accident Models of Circular Intersections by Weather Condition in Korea", J. Korea Soc. Saf., Vol. 27, No. 6, pp. 178-184, 2012. https://doi.org/10.14346/JKOSOS.2012.27.6.178
  12. S. P. Miaou, "The Relationship Between Truck Accidents and Geometric Design of Road Sections: Poisson Versus Negative Binomial Regressions", Accid. Anal. & Prev., Vol. 26, No. 4, pp. 471-482, 1994. https://doi.org/10.1016/0001-4575(94)90038-8
  13. J. Fox, "Applied Regression Analysis and Generalized Linear Models", Sage Publications, 1997.
  14. B. K. Brimley, M. Saito and G. G. Schultz, "Calibration of Highway Safety Manual Safety Performance Function", Transp. Res. Rec., Vol. 2279, pp. 82-89, 2012. https://doi.org/10.3141/2279-10
  15. D. L. McFadden, "The Theory and Practice of Disaggregate Demand Forecasting for Various Modes of Urban Transportation", Washington Department of Transportation, 1976.