Clustering driver behavior using dynamic time warping and hidden Markov model

Based on on-board diagnostics and Global Position System installed in taxicabs, driver behavior data is collected. Left turn data on six similar curves are extracted, and speed, acceleration, yaw rate, and sideslip angle of drivers in time series are selected as clustering indexes. Initial clustering is implemented by Dynamic Time Warping (DTW) and Hierarchical Clustering, and the clustering results are put into the Hidden Markov Model (HMM) to iteratively optimize the results for achieving convergence. Driver behavior patterns over time while driving on the curves and the statistical characteristics of different groups are examined. All indexes including lateral vehicle control and longitudinal vehicle control have a significant difference in different groups, indicating that the clustering method of DTW and HMM can effectively classify driver behavior. Finally, the driving behavior in different groups is further investigated and classified based on characteristics related to safe and ecological driving. This method can be applied by automobile insurance companies, and for the development of specific training courses for drivers to optimize their driving behavior.

Automated summary

This study utilizes on-board diagnostics and GPS data collected from taxicabs to analyze driver behavior. Clustering is initially performed using Dynamic Time Warping and Hierarchical Clustering, then refined using Hidden Markov Model for convergence. Results show significant differences in vehicle control indexes between different driver behavior groups, validating the effectiveness of DTW and HMM clustering methods. Further investigation classifies driving behavior based on safe and ecological driving characteristics, with potential applications for automobile insurance and driver training optimization.