• Padmavathi R M
• Dr. Siddaraju

The production of the population extent and the lot of vehicles on the road creates visitors jam in city that is one the most transportation problem. Traffic jam can lead to bad issues such as creating accident risks due to the extension in transportation system. The clever city concept offers opportunities to deal with urban issues and to boost the citizens dwelling condition. In each and every year road site visitors accidents have end up one of the biggest national Medical hassle in the world. Numerous elements (driver, environment ,car etc.) are causes car crashes (RTAs) some of those elements are more imperative to finding out the accidents seriousness than others. The efficient Data mining alternatives can routinely be employed to alter and conclude such full size elements among human, vehicle and environment elements and hence to describe RTAs severity. In this analysis, three categorizing approach were applied: Decision tree(Random Forest, Random Tree,J48/C4.5,and CART) , ANN (Back-propagation) and SVM(polynomial kernel) to describe the big environmental aspects of RTAS that can be used to frame the prediction model these approach have been detected the usage of a actual dataset retrieved from the joined kingdom. A decision framework has been outline using the model originated through the random forest method that will help decision makers to extend the decision making approaches by concluding the severity of the accident. The preliminary outcomes confirmed that the maximum accuracy price was 80.6% using Random forest obeying by 61.4% using ANN then through 54.8% using SVM method.

Decision Making, Traffic Accidents Severity Prediction, Data Mining Methods, Knowledge based Systems

"A Compendium For Prediction Of Accidents Severity By Data Mining Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 6, page no.297-303, June 2019, Available :http://www.jetir.org/papers/JETIR1906O44.pdf

"A Compendium For Prediction Of Accidents Severity By Data Mining Approach", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 6, page no. pp297-303, June 2019, Available at : http://www.jetir.org/papers/JETIR1906O44.pdf