Identifying the Main Factors Affecting Road Accidents in Iran Through Data Mining, Determining the Optimal Solution in Mitigation and Forecasting its Effectiveness Through Arima Models

Karami, Arya | 2018

606 Viewed
  1. Type of Document: M.Sc. Thesis
  2. Language: Farsi
  3. Document No: 51141 (01)
  4. University: Sharif University of Technology
  5. Department: Industrial Engineering
  6. Advisor(s): Akhavan Niaki, Taghi
  7. Abstract:
  8. Road accidents are unfortunate events that cause more thanl16000 deaths each year in Iran. Intercity accidents require a comprehensive plan to reduce casualties because the number of roads users are increasing and the accidents account for nearlyl65% of fatalities. In this study, we first tried to identify the status of Iran through a study of traffic accidents in the world, and then the research and activities carried out in Iran were analyzed to find new and effective solutions. Using the daily fatalities data froml2008 tol2014, and using the new methodology presented in this research based on the Discrete Fourier Transformation (DFT), the Box-Jenkins models and the Secant method, the fatalities of the spring ofl2015 were predicted. Focusing on the accidents ofl2014, central insurance of Iran database, Road Maintenance and Transportation Organization database and Iranian Traffic Police database were analyzed. After data preprocessing, the integration of these three databases took place. To discover the association rules, a new algorithm was developed that improved the Apriori algorithm. The proposed algorithm was used to extract knowledge from the existing big data. Finally, seventy of the most interesting extracted rules were chosen and provided the basis for proposing solutions to reduce casualties. After categorizing suggested solutions and preparing a questionnaire Analytical Hierarchy Process was accomplished. Among the important findings of this research are the solutions from the category of vehicle safety improvement solutions with the desired effectiveness in reducing fatalities in the scene of accidents. The fatality reduction in the execution of this category is expected to bel18
  9. Keywords:
  10. Analytical Hierarchy Process (AHP) ; Road Accidents ; Time Series Analysis ; Association Rules ; Discrete Fourier Transform ; Damage Reduction ; Box-Jenkins Time Series

 Digital Object List