Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for Interpretability

Background/Objectives: This paper presents a Residual Neural Network (ResNet) based framework tailored for structured traffic accident data, aiming to improve accident severity prediction. The proposed model leverages residual learning to effectively model intricate relationships between numerical a...

Full description

Saved in:
Bibliographic Details
Main Authors: Ilyass Benfaress, Afaf Bouhoute, Ahmed Zinedine
Format: Article
Language:English
Published: MDPI AG 2024-11-01
Series:AI
Subjects:
Online Access:https://www.mdpi.com/2673-2688/5/4/124
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846106275909206016
author Ilyass Benfaress
Afaf Bouhoute
Ahmed Zinedine
author_facet Ilyass Benfaress
Afaf Bouhoute
Ahmed Zinedine
author_sort Ilyass Benfaress
collection DOAJ
description Background/Objectives: This paper presents a Residual Neural Network (ResNet) based framework tailored for structured traffic accident data, aiming to improve accident severity prediction. The proposed model leverages residual learning to effectively model intricate relationships between numerical and categorical variables, resulting in a notable increase in prediction accuracy. Methods: A comparative analysis was performed with other Deep Learning (DL) architectures, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Darknet, and Extreme Inception (Xception), showing superior performance of the proposed Resnet. Key factors influencing accident severity were identified, with Shapley Additive Explanations (SHAP) values helping to address the need for transparent and explainable Artificial Intelligence (AI) in critical decision-making areas. Results: The generalizability of the ResNet model was assessed by training it, initially, on a UK road accidents dataset and validating it on a distinct dataset from India. The model consistently demonstrated high predictive accuracy, underscoring its robustness across diverse contexts, despite regional differences. Conclusions: These results suggest that the adapted ResNet model could significantly enhance traffic safety evaluations and contribute to the formulation of more effective traffic management strategies.
format Article
id doaj-art-69e1363d801e47e0854ffdd3d27ff64b
institution Kabale University
issn 2673-2688
language English
publishDate 2024-11-01
publisher MDPI AG
record_format Article
series AI
spelling doaj-art-69e1363d801e47e0854ffdd3d27ff64b2024-12-27T14:05:04ZengMDPI AGAI2673-26882024-11-01542568258510.3390/ai5040124Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for InterpretabilityIlyass Benfaress0Afaf Bouhoute1Ahmed Zinedine2Faculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fez 30050, MoroccoFaculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fez 30050, MoroccoFaculty of Sciences Dhar El Mahraz, Sidi Mohamed Ben Abdellah University, Fez 30050, MoroccoBackground/Objectives: This paper presents a Residual Neural Network (ResNet) based framework tailored for structured traffic accident data, aiming to improve accident severity prediction. The proposed model leverages residual learning to effectively model intricate relationships between numerical and categorical variables, resulting in a notable increase in prediction accuracy. Methods: A comparative analysis was performed with other Deep Learning (DL) architectures, including Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM), Darknet, and Extreme Inception (Xception), showing superior performance of the proposed Resnet. Key factors influencing accident severity were identified, with Shapley Additive Explanations (SHAP) values helping to address the need for transparent and explainable Artificial Intelligence (AI) in critical decision-making areas. Results: The generalizability of the ResNet model was assessed by training it, initially, on a UK road accidents dataset and validating it on a distinct dataset from India. The model consistently demonstrated high predictive accuracy, underscoring its robustness across diverse contexts, despite regional differences. Conclusions: These results suggest that the adapted ResNet model could significantly enhance traffic safety evaluations and contribute to the formulation of more effective traffic management strategies.https://www.mdpi.com/2673-2688/5/4/124traffic accident severityexplainable Artificial IntelligenceResNet architectureSHAPMachine Learningdeep learning
spellingShingle Ilyass Benfaress
Afaf Bouhoute
Ahmed Zinedine
Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for Interpretability
AI
traffic accident severity
explainable Artificial Intelligence
ResNet architecture
SHAP
Machine Learning
deep learning
title Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for Interpretability
title_full Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for Interpretability
title_fullStr Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for Interpretability
title_full_unstemmed Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for Interpretability
title_short Enhancing Traffic Accident Severity Prediction Using ResNet and SHAP for Interpretability
title_sort enhancing traffic accident severity prediction using resnet and shap for interpretability
topic traffic accident severity
explainable Artificial Intelligence
ResNet architecture
SHAP
Machine Learning
deep learning
url https://www.mdpi.com/2673-2688/5/4/124
work_keys_str_mv AT ilyassbenfaress enhancingtrafficaccidentseveritypredictionusingresnetandshapforinterpretability
AT afafbouhoute enhancingtrafficaccidentseveritypredictionusingresnetandshapforinterpretability
AT ahmedzinedine enhancingtrafficaccidentseveritypredictionusingresnetandshapforinterpretability