Road Traffic Accident Severity Prediction Using Machine Learning

Arvind; DR.M.CHARLES AROCKIARAJ

Road Traffic Accident Severity Prediction Using Machine Learning

June 2024

Vol-10, Issue-3

Paper ID: 24451

ISSN: 2395-4396

Downloads: 0

Abstract & Details

Research Area

Computer Engineering

Keywords

Road traffic accidents Severity prediction Accident analysis Machine learning Predictive modeling Traffic safety Risk assessment Data mining Feature engineering Decision trees Random forest Neural networks Crash severity Injury prediction Traffic collision Accident classification Feature selection Pattern recognition Predictive analytics Accident investigation

Abstract

This paper delivers into the significant research road accidents represent a global challenge resulting in fatalities, injuries, and significant economic losses. Various countries and international bodies have implemented technologies, systems, and policies aimed at accident prevention. The integration of big traffic data and artificial intelligence holds promise for predicting and mitigating accident risks. Existing research predominantly explores the influence of road geometry, environmental conditions, and weather on accidents, often neglecting crucial human factors such as alcohol and drug use, age, and gender, which significantly impact accident severity. This study addresses these factors comprehensively, employing a range of single and ensemble machine learning (ML) methods to predict accident severity. Comparative analysis reveals that Random Forest (RF) consistently outperforms logistic regression (LR), K-nearest neighbor (KNN), naive Bayes (NB), extreme gradient boosting (XG Boost), and adaptive boosting (AdaBoost), achieving accuracy rates of 86.64% for binary and 67.67% for multiclass classifications. Ensemble methods generally surpass single-mode ML techniques in accuracy, with RF, XG Boost, and AdaBoost demonstrating superior performance. These findings contribute valuable insights into accident factors and severity assessment, offering potential applications in traffic safety and risk management.

License

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.

Author Information

#	Name	Institute / Affiliation
1	Arvind	AMC Engineering College
2	DR.M.CHARLES AROCKIARAJ	AMC Engineering College

How to Cite

Use the following formats to cite this article in your research.

APA Style

Arvind & AROCKIARAJ, DR.M.CHARLES (2024). Road Traffic Accident Severity Prediction Using Machine Learning. International Journal of Advance Research and Innovative Ideas In Education, 10(3), 6400-6402.

MLA Style

Arvind, and DR.M.CHARLES AROCKIARAJ. "Road Traffic Accident Severity Prediction Using Machine Learning." International Journal of Advance Research and Innovative Ideas In Education, vol. 10, no. 3, 2024, pp. 6400-6402.

IEEE Style

Arvind and DR.M.CHARLES AROCKIARAJ, "Road Traffic Accident Severity Prediction Using Machine Learning," International Journal of Advance Research and Innovative Ideas In Education, vol. 10, no. 3, pp. 6400-6402, 2024.

Vancouver Style

Arvind, AROCKIARAJ DR.M.CHARLES. Road Traffic Accident Severity Prediction Using Machine Learning. International Journal of Advance Research and Innovative Ideas In Education. 2024;10(3):6400-6402.

Harvard Style

Arvind & AROCKIARAJ, DR.M.CHARLES (2024) 'Road Traffic Accident Severity Prediction Using Machine Learning', International Journal of Advance Research and Innovative Ideas In Education, 10(3), pp. 6400-6402.

Chicago Style

Arvind and DR.M.CHARLES AROCKIARAJ. "Road Traffic Accident Severity Prediction Using Machine Learning." International Journal of Advance Research and Innovative Ideas In Education 10, no. 3 (2024): 6400-6402.

Turabian Style

Arvind and DR.M.CHARLES AROCKIARAJ. "Road Traffic Accident Severity Prediction Using Machine Learning." International Journal of Advance Research and Innovative Ideas In Education 10, no. 3 (2024): 6400-6402.