Hybrid System's Model and Algorithm for Highway Traffic Monitoring

We propose a method for the early detection and localization of highway traffic congestion onset and its propagation using a stochastic linear hybrid system model (SLHS) and a state-dependent-transition hybrid estimation (SDTHE) algorithm. The SLHS model is used to model the congested and non-congested scenarios of the highway. Using the SDHTE algorithm, we estimate the states (continuous and discrete states) of the highway that will provide us with the traffic congestion information. The performance of the algorithm is analyzed using the correct detection and identification (CDID) indices, false alarm rate (FA) indices, time-to-detection (TTD) delays as well as the run time. We use a set of constructed data that represent the various congestion onset and propagation scenarios. The validation of the algorithm is done using real traffic data obtained from highway I-405 S in California using the Freeway Performance Measurement System (PEMS).