a road accident prediction model using data mining techniques

K.P.Senthil M.E,G.Dhanush ,D.Vignesh

Published in International Journal of Advanced Research in Computer Science Engineering and Information Technology

ISSN: 2321-3337          Impact Factor:1.521         Volume:6         Issue:3         Year: 21 June,2022         Pages:1701-1710

International Journal of Advanced Research in Computer Science Engineering and Information Technology

Abstract

In the project, the machine learning based road accident based prediction system has been implemented. The analysis of the road accident is done by using various kind of visualization tools or packages called plotly, seaborn and matplotlib. K-means clustering is an unsupervised machine learning techniques which is used to cluster the road accident points the high number of traffic incidents and deaths these days, the ability to forecast the number of traffic accidents over a given time is important for the transportation department to make scientific decisions. In this scenario, it will be good to analyze the occurrence of accidents so that this can be further used to help us in coming up with techniques to reduce them. Even though uncertainty is a characteristic trait of majority of the accidents, over a period of time, there is a level of regularity that is perceived on observing the accidents occurring in a particular area. This regularity can be made use of in making well informed predictions on accident occurrences in an area and developing accident prediction models. In this paper, we have studied the inter relationships between road accidents, condition of a road and the role of environmental factors in the occurrence of an accident. We have made use of data mining techniques in developing an accident prediction model using Apriori algorithm and Support Vector Machines.

Kewords

Data Mining, Machine Learning, Exploratory Data Analysis, Apriori Algorithm, Support Vector Machines

Reference

[1] Suganya, E. and S. Vijayarani. “Analysis of road accidents in India using data mining classification algorithms.” 2017 International Conference on Inventive Computing and Informatics (ICICI) (2017): 1122-1126. [2] Anand, J. V. "A Methodology of Atmospheric Deterioration Forecasting and Evaluation through Data Mining and Business Intelligence." Journal of Ubiquitous Computing and Communication Technologies (UCCT) 2, no. 02 (2020): 79-87. [3] ArunPrasath, N and Muthusamy Punithavalli. “A review on road accident detection using data mining techniques.” International Journal of Advanced Research in Computer Science 9 (2018): 881-885. [4] Zheng CT, Liu C, Wong HS. (2018). Corpus based topic diffusion for short text clustering. Neurocomputing 275: 2444-2458. http://dx.doi.org/10.1504/IJIT.2018.090859. [5] Stewart M, Liu W, Cardell-Oliver R, Griffin M. (2017). An interactive web-based toolset for knowledge discovery from short text log data. In International Conference on Advanced Data Mining and Applications. Springer, pp. 853-858. http://dx.doi.org/10.1007/978-3- 319-69179- 4_61.