What question did this study set out to answer?

To develop an integrated, data-driven supervised machine learning framework that estimates driving instability risk by coupling road infrastructure condition with dynamic traffic flow metrics.

August 19, 2026Autonomous Intelligent SystemsOpen Access

Integrating road infrastructure condition into intelligent transportation systems: a machine learning-based infrastructure-aware risk prediction approach

View Full Paper

Ask AI

Bookmark

Authors

MHMayssa HamdaniHasselt University NJNafaa JabeurGerman University of Technology PYProf. Dr. Ansar YasarHasselt University

Discussion

Member takes

Overview

Machine learning analysis demonstrates improved driving risk prediction by combining road pavement quality with traffic data, indicating key benefits for intelligent transportation systems.

Key Points

To develop an integrated, data-driven supervised machine learning framework that estimates driving instability risk by coupling road infrastructure condition with dynamic traffic flow metrics.
Integrated segment-level Pavement Condition Index (PCI) data with real-world dynamic traffic observations in New York City.
Trained a supervised machine learning model using measures of traffic congestion, speed variation, and pavement deterioration to predict hourly instability risk.
Evaluated model performance against a traffic-only baseline using a temporally separated test set and applied SHAP for feature explainability.
The infrastructure-aware model achieved an ROC-AUC of 0.9804 and PR-AUC of 0.9074, outperforming the traffic-only baseline (ROC-AUC 0.8785, PR-AUC 0.5833).
SHAP explainability analysis identified pavement condition and traffic congestion as the most influential features with comparable contributions to instability prediction.

Cite This Study

Hamdani et al. (2026) studied this question.

synapsesocial.com/papers/6a85633c03308d306e2d6487 https://doi.org/10.1007/s43684-026-00137-0

View Full Paper

Ask AI

Bookmark

August 19, 2026Autonomous Intelligent SystemsOpen Access

Integrating road infrastructure condition into intelligent transportation systems: a machine learning-based infrastructure-aware risk prediction approach

View Full Paper

Ask AI

Bookmark

Authors

MHMayssa HamdaniHasselt University NJNafaa JabeurGerman University of Technology PYProf. Dr. Ansar YasarHasselt University

Discussion

Member takes

Overview

Machine learning analysis demonstrates improved driving risk prediction by combining road pavement quality with traffic data, indicating key benefits for intelligent transportation systems.

Key Points

To develop an integrated, data-driven supervised machine learning framework that estimates driving instability risk by coupling road infrastructure condition with dynamic traffic flow metrics.
Integrated segment-level Pavement Condition Index (PCI) data with real-world dynamic traffic observations in New York City.
Trained a supervised machine learning model using measures of traffic congestion, speed variation, and pavement deterioration to predict hourly instability risk.
Evaluated model performance against a traffic-only baseline using a temporally separated test set and applied SHAP for feature explainability.
The infrastructure-aware model achieved an ROC-AUC of 0.9804 and PR-AUC of 0.9074, outperforming the traffic-only baseline (ROC-AUC 0.8785, PR-AUC 0.5833).
SHAP explainability analysis identified pavement condition and traffic congestion as the most influential features with comparable contributions to instability prediction.

Cite This Study

Hamdani et al. (2026) studied this question.

synapsesocial.com/papers/6a85633c03308d306e2d6487 https://doi.org/10.1007/s43684-026-00137-0

View Full Paper

Ask AI

Bookmark