Death, injury, and disability resulting from road traffic accidents remain significant global public health issues. Both developed and developing nations face challenges stemming from growing human and vehicle populations. Consequently, mitigating the severity of traffic accidents is a critical focus for traffic agencies and administrations. This study utilizes a missing value imputation algorithm and Naïve Bayes conditional independence to predict potential injuries following a traffic accident at a specific location in real-time. Using historical traffic accident data from Australia, the research aims to estimate the likely severity of traffic accidents after they occur. The goal is to assist decision-makers in allocating appropriate resources to aid injured individuals at the accident scenes.
Real-Time Road Crash Severity Prediction for Optimized Resource Allocation
Communic.Comp.Inf.Science
International Conference on Neural Information Processing ; 2024 ; Auckland, New Zealand December 02, 2024 - December 06, 2024
22.06.2025
10 pages
Aufsatz/Kapitel (Buch)
Elektronische Ressource
Englisch
Real-Time Framework to Predict Crash Likelihood and Cluster Crash Severity
Transportation Research Record | 2023
|A stable and optimized neural network model for crash injury severity prediction
Online Contents | 2014
|An evaluation of road crash injury severity measures
Online Contents | 1996
|British Library Conference Proceedings | 1998
|