Year: 2025
Type: article
Abstract: Traffic violations are a leading cause of road accidents and fatalities. Predicting driver violations in advance can help law enforcement agencies and traffic management systems take proactive measures to enhance road safety. This paper presents a Hierarchical Network-Based Method (HNBM) that integrates graph-based modeling, machine learning, and real-time data analytics to predict driver violations. The system constructs a hierarchical network by analyzing driver behavior, road conditions, historical violations, and traffic patterns. Machine learning techniques, such as Graph Neural Networks (GNNs), Random Forest, and Long Short-Term Memory (LSTM) networks, are applied to extract spatiotemporal features and predict the likelihood of violations. Experimental results on real-world traffic datasets demonstrate the model’s superior accuracy in identifying high-risk drivers compared to traditional approaches.
Source: Journal of engineering sciences.
Authors: CHITIBOINA HEMANTH KUMAR, SMT.A.KALPANA
Language: English
Topic: Traffic and Road Safety
Subfield: Safety, Risk, Reliability and Quality
Field: Engineering
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4409238299