WSEAS Transactions on Environment and Development
Print ISSN: 1790-5079, E-ISSN: 2224-3496
Volume 22, 2026
Urban Traffic Incident Detection based on an Improved Extreme Learning Machine Algorithm
Authors: ,
Search Articles
Abstract: Incidents on urban roads are the primary cause of well-known problems, including traffic congestion, pollution, and travel delays. Hence, Fast incident detection is necessary for improved real-time management. This paper proposes an automatic incident detection (AID) algorithm that hybridizes the Particle Swarm Optimization (PSO) algorithm with the regularized Extreme Learning Machine (RELM). The PSO is used to optimize the initial matrix weights and output thresholds. This leads to enhanced detection accuracy and rapidity. The proposed algorithm achieves a fast and good detection performance compared to Support Vector Machine (SVM), Random Forest (RF), and standard ELM.
Keywords:
Incident Detection, Extreme Learning Machine, Particle swarm optimization, Urban roads, Machine learning, Simulation of urban road mobility
Pages: 644-651
DOI: 10.37394/232015.2026.22.57