Road Crash Injury Severity Prediction Using a Graph Neural Network Framework
Open Access
- 5 March 2024
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 37540-37556
Abstract
Crash severity prediction is a challenging research area, where the objective is to accurately assess the extent of severity of an injury resulting from road traffic accidents. The main aim of existing studies is to precisely assess the potential severity of crashes under diverse circumstances, such as weather conditions, vehicle attributes, road characteristics and layout, and traffic control factors. This effort aids authorities in establishing effective emergency response systems. The novelty and objective of our work involve contributing to this research area by employing a graph architecture to capture relationships among various crash records to uncover any hidden patterns that traditional ML models might overlook. The current study extends existing knowledge by leveraging Graph Neural Networks (GNN) and comparing their performance to popular ensemble-based models, which include Extreme Gradient Boosting (XGBoost) and Random Forest (RF) and Artificial Neural Networks (ANNs). Real data from the United Kingdom (UK) was employed to achieve our goal. All models underwent training using the training dataset, followed by performance evaluation using diverse metrics such as the accuracy, precision, recall, f1-score, Matthews Correlation Coefficient (MCC), confusion matrix, and computational cost on the test dataset. Overall, our proposed GNN-based model demonstrated better performance when compared to other models. Specifically, the GNN model outperformed all other models across all metrics. For instance, the accuracy stood at 85.55% for GNN as compared to 83.36%, 83.18%, and 83.27% for XGBoost, RF, and ANNs models, respectively. The GNN model assisted in identifying hidden patterns by considering non-linear relationships among crash records. Thus, the model had the potential to improve its ability to predict severe accidents, which could in turn significantly improve emergency response efforts and reduce the likelihood of severe accidents resulting in fatalities.Keywords
Funding Information
- Universiti Putra Malaysia through Putra Grant Scheme (GP/2020/9692500)
- Ministry of Higher Education Malaysia through the Fundamental Research Grant Scheme (FRGS/1/2023/ICT06/UPM/02/1)
This publication has 70 references indexed in Scilit:
- An attribute-weighted isometric embedding method for categorical encoding on mixed dataApplied Intelligence, 2023
- Forecasting road traffic accident using deep artificial neural network approach in case of Oromia Special ZoneSoft Computing, 2023
- Accident Prediction Modelling and Crash Scene Investigation2022
- Hierarchy-based semantic embeddings for single-valued & multi-valued categorical variablesJournal of Intelligent Information Systems, 2021
- Clustering Mixed-Type Data with Correlation-Preserving Embedding2021
- Deep neural network-based predictive modeling of road accidentsNeural Computing and Applications, 2020
- Graph Representation Learning2020
- Multi-Layer Perceptron Artificial Neural Network Based IoT Botnet Traffic Classification2019
- Modeling Traffic Accident Severity Using Neural Networks and Support Vector Machines2019
- Accident severity analysis using ordered probit modelJournal of Advanced Transportation, 2007