Urban Intersection Safety Risk Index: Machine Learning Methods for Real-Time Classification

Fall, T., Massicotte, D., Dessureault, J. S. et Ouameur, M. A. (2025). Urban Intersection Safety Risk Index: Machine Learning Methods for Real-Time Classification. Dans 2025 25th International Conference on Digital Signal Processing (DSP) DOI 10.1109/DSP65409.2025.11075008.

Prévisualisation

PDF Télécharger (1MB) | Prévisualisation

Résumé

The safety of urban intersections is a critical concern for city planners. Technological advancements, such as LiDAR sensors, enable better risk assessment for road users. This study proposes a hybrid model that combines Post-Encroachment Time (PET) data with unsupervised machine learning techniques, specifically DBSCAN clustering, to detect traffic anomalies. A generalized Pareto distribution (GPD) is then applied to estimate a risk index. Finally, categorical safety risk classification is performed using an optimizable neural network (ONN), support vector machine (OSVM), efficient logistic regression (ELR), and Gaussian Naive Bayes (GNB). The impact of these methods is evaluated in real-time for urban traffic management in Trois-Rivieres, Quebec, Canada. This work aims to assist decision-makers in urban traffic planning and accident prevention.

Type de document:	Document issu d'une conférence ou d'un atelier
Mots-clés libres:	Support vector machines Urban areas Machine learning Digital signal processing Real-time systems Time measurement Safety Risk management Indexes Anomaly detection Surrogate measures Post-Encroachment Time (PET) DBSCAN Pareto distribution Classification
Date de dépôt:	20 août 2025 18:13
Dernière modification:	20 août 2025 18:13
Version du document déposé:	Post-print (version corrigée et acceptée)
URI:	https://depot-e.uqtr.ca/id/eprint/12219

Actions (administrateurs uniquement)

Éditer la notice