Awareness of Wrong-Lane Accident Detection using Random Forest Compared with SVM Algorithm with Increased Accuracy
DOI:
https://doi.org/10.47750/pnr.2022.13.S04.084Keywords:
Support Vector Machine, Random Forest, Accident Detection, Wrong-Lane, Data Mining, Classification, Innovative Kernel Based Approach.Abstract
Aim: The proposed study aims to perform detection of wrong-lane accidents utilizing the Support Vector Machine (SVM) algorithm and compare accuracy with the Random Forest (RF) algorithm.
Materials and Methods: Support Vector Machine is applied on a road accident dataset that consists of 1834 records. A machine learning strategy for detecting wrong-lane accidents has been suggested and developed that compares Support Vector Machine with Random Forest. Sample size was calculated as 21 in each group using G power. Sample size was calculated using clinical analysis, with alpha and beta values of 0, 05 and 0.5, 95% confidence, 80% pre-test power and enrolment ratio is 1. The accuracy of the detection of wrong-lane accidents was evaluated and recorded.
Results: The accuracy was maximum in detection of wrong-lane accidents using Support Vector Machine (89.90%) with minimum mean error when compared with Random Forest (89.77%) and attained significance value of p = 0.02.
Conclusion: The study proves that Support Vector Machine Algorithm exhibits better accuracy than Random Forest in detection of wrong-lane accidents .
