Improved Accuracy of Calculation of Vehicle Crash Severity in Highways using Random Forest over Logistic Regression Algorithm

Abstract

Aim: To improve the accuracy rate of vehicle crash severity in highways using Random forest over Logistic Regression. Materials and Methods: Random forest and Logistic Regression with sample size of (N=10) is executed with varying training and testing splits for calculating the accuracy for accident crash severity with g power as 75%, threshold 0.000 and confidence interval 95%. The performance of the classifiers are evaluated based on their accuracy rate using accident severity dataset. Results: The accuracy for calculating accident crash severity in Random Forest(91%) and Logistic Regression (89%) is obtained(P<0.005). Conclusion: Prediction of accident crash severity using Random Forest (RF) algorithm appears to be significantly better than Logistic Regression (LR) with improved accuracy