The purpose of the proposed work is to identify the factors contributing to fatal accidents. This is achieved by analysing road accidents using Convolutional Neural Networks by considering appropriate features and effectively clustering the records. Several combinations of attributes of large datasets are analysed to discover hidden patterns that are the root cause for accidents. The chances of accident occurrence could be identified by considering various criteria like speed limit and injury severity, time of accidents and drunk driver, month and weather during the accident, lightness and speed limit, human factors, surface and light conditions. The experimental results on road accident data set FARS (Fatality Analysis Reporting System) generated risk factors that cause fatal accidents which will be helpful in generating safer driving principles.

Association Rules, Classification, Convolutional Neural Networks, Traffic Data

[1] K.Jayasudha and C.Chandrasekar, “An overview of data mining in road traffic and accident analysis”, Journal of Computer Applications, Vol.2, Issue.4, pp:32–37, 2009.

[2] Eric M Ossiander and Peter Cummings, “Freeway speed limits and traffic fatalities in Washington state”, Accident Analysis & Prevention, Vol.34, Issue.1, pp:13–18, 2002.

[3] William M Evanco, “The potential impact of rural mayday systems on vehicular crash fatalities”, Accident Analysis & Prevention, Vol.31, Issue.5, pp:455–462, 1999.

[4] KMA Solaiman, Md Mustafizur Rahman and Nashid Shahriar, “AVRA Bangladesh collection, analysis & visualization of road accident data in Bangladesh”, In Proceedings of International Conference on Informatics, Electronics & Vision, pp.1–6, IEEE, 2013.

[5] Sachin Kumar and Durga Toshniwal, “Analysing road accident data using association rule mining”, In Proceedings of International Conference on Computing, Communication and Security, pp.1–6, 2015.

[6] S.Krishnaveni and M.Hemalatha, “A perspective analysis of traffic accident using data mining techniques”, International Journal of Computer Applications, Vol.23, Issue.7, pp:40–48, 2011.

[7] Amira A El Tayeb, Vikas Pareek, and Abdelaziz Araar, “Applying association rules mining algorithms for traffic accidents in Dubai”, International Journal of Soft Computing and Engineering, 2015.

[8] L.Li, S.Shrestha and G.Hu, “Analysis of road traffic fatal accidents using data mining techniques”, IEEE 15th International Conference on Software Engineering Research Management and Applications (SERA), pp.363-370, 2017.

[9] Sami Ayramo, Pasi Pirtala, Janne Kauttonen, Kashif Naveed and Tommi Karkkainen, “Mining road traffic accidents”, Reports of the Department of Mathematical Information Technology Series C. Software and Computational Engineering, University of Jyvaskyla, pp.1-53, 2009.

[10] S. Shanthi and R. Geetha Ramani, “Classification of Vehicle Collision Patterns in Road Accidents using Data Mining Algorithms”, International Journal of Computer Applications (0975–8887), Vol.35, Issue.12, pp:30-37, 2011.

[11] S. Shanthi, R. Geetha Ramani, “Feature Relevance Analysis and Classification of Road Traffic Accident Data through Data Mining Techniques”, Proceedings of the World Congress on Engineering and Computer Science, Vol 1, 2012.

[12] Dharmendra Sharma and Suresh Jain, “Evaluation of Stemming and Stop Word Techniques on Text Classification Problem”, International Journal of Scientific Research in computer Science and Engineering, Vol.3, Issue.2, 2015.

[13] Mohnish Patel, Aasif Hasan, Sushil Kumar, “Preventing Discovering Association Rules For Large Data Base”, International Journal of Scientific Research in computer Science and Engineering Vol.1, Issue.3, 2013.

[14] Neeraj Chhabra, “Comparative Analysis of Different Wireless Technologies”, International Journal of Scientific Research in Network Security and Communication, Vol.1, Issue.5, 2013.

[15] V. Kapoor, “A New Cryptography Algorithm with an Integrated Scheme to Improve Data Security”, International Journal of Scientific Research in Network Security and Communication Vol.1, Issue.2, 2013.