Traffic crashes are modelled using different techniques and contributing factors. In this work, several ensemble machine learning algorithms were used to model crash severity at urban roundabouts using data from 15 roundabouts in Jordan. The original dataset covers four years, from 2017 to 2021. A total of 15 variables were collected and used in this work. Results indicated that ten variables are important. The various models show their ability to classify traffic crash severity with a high overall accuracy range from 96% to 98%. Results indicated that driver fault and age are the most significant contributing factors for crash severity.
Machine learning K-nearest neighborhood Support vector machine Safety Driver age driver fault
Primary Language | English |
---|---|
Subjects | Environmental and Sustainable Processes |
Journal Section | Articles |
Authors | |
Early Pub Date | December 26, 2023 |
Publication Date | December 30, 2023 |
Published in Issue | Year 2023 |