Prediction of Road Accidents Using Machine Learning Technique
Saravanan Alagarsamy, M. Malathi, M. Manonmani, T. Sanathani, A. Senthil Kumar
Abstract
The statistics of the World Health Organization (WHO) adage that in India, more than 150,000 people lost their life due reason of road accidents and in the world, per year, nearly 50 million people were affected in the accidents occurring on the roadside also the ratio is gradually increasing every year. The proposed machine learning techniques are used to provide risk information to the users traveling in unfamiliar locations. Most probably occurring road accident locations are identified and that particular region is indicated as black pot. Alert information is forwarded to the users that indicate in the format of black spot through the map, because whenever the user is traveling to the new location, probably the map will be used. The risk/frequently occurring accident region is indicated for the users traveling to the location which is not familiar. The proposed random forest combined with the Gaussian distribution method is used to give the prior information and save the life of many people traveling in the regions having more risks.