Driving Style Recognition under Connected Circumstance Using a Supervised Hierarchical Bayesian Model

In recent years, the automated driving system has been known to be one of most popular research topics artificial intelligence (AI) and intelligent transportation (ITS). The journey experience on vehicles could improved by individualization understanding. Although previous studies have proposed methods for styles understanding, classification not addressed thoroughly. Therefore, in this study, a supervised method is understand behavioral structure latent incorporating prior knowledge. Firstly, novel established encoding raw data mining. Then, Labeled Latent Dirichlet Allocation (LLDA) from individual with behaviors. Finally, Safety Pilot Model Deployment (SPMD) are used validate performance model. Experimental results show that model uncovers effectively shows good agreement real situations, which provides theoretical guidance behavior recognition better vehicles.