Abstract Recent studies have predicted that in 2030, traffic accidents will be the fifth leading cause of death worldwide. The costs of fatalities and driver injuries due to traffic accidents greatly affect the society. These insights call for investigating various aspects of traffic accident data analysis and modeling in numerous geographic regions (Sameen and Pradhan 2017a, b, c; Sameen et al. 2016). In particular, several researchers paid increasing attention to determining factors that greatly affect the severity of driver injuries caused by traffic accidents. Many approaches, such as logistic regression (LR) (Al-Ghamdi 2002), artificial neural networks (ANNs) (Delen et al. 2006; Moghaddam et al. 2011), support vector machines (SVMs) (Li et al. 2008, 2012), and Bayesian methods (Xie et al. 2009; de Oña et al. 2011), were explored to model traffic accident data.
Modeling Traffic Accident Severity Using Neural Networks and Support Vector Machines
2019-04-03
7 pages
Article/Chapter (Book)
Electronic Resource
English
Traffic accident severity prediction method based on recurrent neural network
European Patent Office | 2024
|Traffic accident severity assessment method based on single-vehicle traffic accident database
European Patent Office | 2023
|Traffic Sign Array Decomposition Using Support Vector Machines
British Library Conference Proceedings | 2008
|Traffic forecasting using least squares support vector machines
Taylor & Francis Verlag | 2009
|