Federated Deep Learning for Tailgating Behaviour Detection in Intelligent Transportation Systems

Tailgating, which occurs when a vehicle follows another at an unsafe distance, is a major contributor to rear-end collisions, especially on roads with dense traffic, frequent lane changes, and limited infrastructure, creating hazardous conditions. Modern intelligent transportation systems and connected vehicle technologies help monitor and reduce unsafe behaviours. Still, conventional deep learning methods rely on centralised training, which raises concerns about privacy, scalability, and delays. This framework integrates collaborative training with federated learning and a bidirectional long short-term memory network to detect tailgating accurately. Realistic vehicle trajectory data were generated using the Simulation of Urban mobility tool to replicate diverse driving scenarios, including urban and highway conditions. Key features such as following distance, relative speed, braking distance, time headway, vehicle speed, and driver reaction distance were derived to model driving behaviour. Baseline models, including convolutional neural networks, recurrent neural networks, and long short-term memory networks, were developed for comparison. The results show that the framework combining federated learning and a bidirectional long short-term memory network achieved detection accuracy above 91.98%, outperforming centralised training and baseline models. The study shows that a collaborative, decentralised approach can capture bidirectional temporal dependencies in driving sequences, ensuring driving data remains local while supporting real-time detection.