Abstract: Despite everything that has been done to improve road safety in India to date, there are always problems lurking around every corner. This circumstance has shown a problem with traffic accidents, affecting public health and the economy of the country. In the past, it was assumed that road accidents and fatalities could not be avoided, but in today's technological age, anything is almost possible. Our research aims to reduce mortality rates by developing a prediction model that considers factors like carriageway/roadway hazards, light conditions, day of the week, special conditions at the accident scene, road class, junction control, junction details, road surface condition, road type, and weather conditions. Machine learning techniques such as random forests (RF), logistic regression (LR), and naive Bayes (NB) were used to create these models. The goal of this research is to analyze data on road accidents in India utilizing the best compatible machine learning classification approaches for estimating road accidents through data mining. Our findings suggest that logistic regression outperformed other machine learning algorithms in terms of accuracy.
|
DOI:
10.17148/IJARCCE.2022.11639
