View in EDS

Improving Road Safety Through Machine Learning Based Severity Prediction.

Saved in:
Bibliographic Details
Title: Improving Road Safety Through Machine Learning Based Severity Prediction.
Authors: A., Akil Chakravarthi, M., Kamalesh, S., Kanishka Devi, Kayalvizhi, S.
Source: Cuestiones de Fisioterapia; 2025, Vol. 54 Issue 4, p890-902, 13p
Subject Terms: MACHINE learning, TRAFFIC safety, TRAFFIC accidents, TRAFFIC engineering, ROAD safety measures
Abstract: An efficient predictive system that can precisely categorize accident severity and allow for targeted interventions is necessary given the increased frequency of traffic accidents. This study divides traffic accidents into two groups: ”Serious Injury” and ”Slight Injury”. It uses advanced machine learning methods to do this.. The prediction model was developed using a big dataset that included environmental parameters, road conditions, driver demographics, and vehicle attributes. A range of machine learning techniques, including ensemble and non- ensemble models, were investigated in order to determine the most accurate approach. The XGBoost classifier was determined to be the top-performing model following hyperparameter tuning optimization, attaining a high prediction accuracy of 99road surface features are important in influencing the severity of accidents, according to the model’s feature importance analysis. The outcomes show how effective machine learning frameworks are at promoting preventive safety measures and enhancing the distribution of resources for traffic control. This prediction model has the potential to greatly increase road safety by offering real- time, data-driven insights. It can also help traffic authorities and legislators make well- informed decisions to lessen the effect of serious traffic incidents [ABSTRACT FROM AUTHOR]
Copyright of Cuestiones de Fisioterapia is the property of Cuestiones de Fisioterapia and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database: Biomedical Index
Description
Abstract:An efficient predictive system that can precisely categorize accident severity and allow for targeted interventions is necessary given the increased frequency of traffic accidents. This study divides traffic accidents into two groups: ”Serious Injury” and ”Slight Injury”. It uses advanced machine learning methods to do this.. The prediction model was developed using a big dataset that included environmental parameters, road conditions, driver demographics, and vehicle attributes. A range of machine learning techniques, including ensemble and non- ensemble models, were investigated in order to determine the most accurate approach. The XGBoost classifier was determined to be the top-performing model following hyperparameter tuning optimization, attaining a high prediction accuracy of 99road surface features are important in influencing the severity of accidents, according to the model’s feature importance analysis. The outcomes show how effective machine learning frameworks are at promoting preventive safety measures and enhancing the distribution of resources for traffic control. This prediction model has the potential to greatly increase road safety by offering real- time, data-driven insights. It can also help traffic authorities and legislators make well- informed decisions to lessen the effect of serious traffic incidents [ABSTRACT FROM AUTHOR]
ISSN:11358599