fuzzyCom: Privacy-Aware Trajectory Data Compression Using Fuzzy Sets in Edge Vehicular Networks

In traffic application scenarios such as real-time trajectory mining and prediction, the transmission and storage of large-scale original trajectory data engulf vehicular networks in terms of wireless transmission and time overhead, as well as easy leakage of users' sensitive location information. A novel trajectory data compression framework using fuzzy sets is proposed, which makes use of the computing and storage capabilities of vehicles and edge gateways. In our methods, raw trajectory data are compressed into fuzzy strings and then further compressed using coding techniques. Our scheme not only reduces the amount of data transmission but also protects users' location/trajectory privacy. Extensive evaluations based on real-world trajectory data sets show that our framework outperforms other baselines in terms of compression ratio, delay and information loss.