From data to decision: a privacy-preserving framework for intelligent transportation systems with edge AI

Abstract

Abstract Intelligent transportation systems (ITS) bring down several advantages, like traffic management, congestion control, road safety, economic and environmental benefits, and several others. However, ITS faces several challenges, such as data collection and integration, scalability, performance, and privacy concerns. This study proposes a privacy-preserving framework for ITSs, and a secure hybrid DBSCAN algorithm has been introduced in a trusted execution environment (TEE) to improve the performance and privacy in ITS. The algorithm combines the features of hierarchical, streaming, and distributed DBSCAN variants that generate clusters in real time for the identification of congestion zones, abnormal events, and incident hotspots with high granularity, while protecting sensitive data through secure enclave processing. A simulation testbed is deployed using SUMO and NS-3. The hybrid Density-Based Spatial Clustering of Applications with Noise (DBSCAN) outperforms standard models, achieving 97.5 to 99.1% congestion detection accuracy and 96.2 to 98.3% incident detection accuracy while handling low-to-severe traffic conditions. Along with noteworthy reductions in edge processing latency of up to 68% and network overhead lowered by 75%, witnessed in severe traffic congestion in a simulated 2 km × 2 km urban testbed. The framework contributes to integrating secure edge computing mechanisms with intelligent traffic management systems. It offers a promising framework for future smart city deployments, evaluated through high-fidelity co-simulation and laboratory-scale validation on commercial edge hardware.