ABSTRACT Smart transportation systems use VANETs for real‐time vehicle‐roadside infrastructure communication. These channels enable collision prevention, traffic synchronization, and cooperative driving. Network congestion, signal interference, hardware failures, and malicious assaults may create communication abnormalities in VANET systems due to their open and dynamic nature. The complex and quickly changing patterns of vehicle communication networks make static threshold or statistical anomaly detection methods insufficient. This paper presents a real‐time VANET communication channel monitoring system using AI‐IAD to overcome these constraints. AI‐IAD's hybrid AI architecture models dynamic vehicular communication behavior via adaptive feature fusion and edge‐assisted inference, making it innovative. The system uses multi‐metric learning to identify modest network behavior changes by monitoring packet delivery ratio, communication delay, signal intensity, and channel use. Unlike centralized detection systems, AI‐IAD uses edge‐based processing at roadside units (RSUs) to identify anomalies quickly and reduce network communication. The model also uses traffic‐aware adaptive learning to adapt to vehicle density, mobility patterns, and channel conditions in urban and highway situations. The Vehicular Reference Misbehavior (VeReMi) dataset, a benchmark dataset produced from actual traffic traces and DSRC communication logs, is used to test the proposed AI‐IAD platform. Testing in simulation‐based VANET scenarios shows that the AI‐IAD framework outperforms existing anomaly detection methods with 94.6% detection accuracy, 95.0% precision, and 94.2% recall. The framework's 3.9% false positive rate and 28 ms detection latency provide quick anomaly identification for safety‐critical applications. The system has 92.5% robustness and scalability in large vehicle networks, achieving steady convergence after 500 training epochs. These findings show that the AI‐IAD architecture considerably improves VANET communication channel reliability and security, enhancing intelligent transportation system resilience.
Li et al. (Wed,) studied this question.