We argue that driving styles demand adaptive classifications, and such mechanisms are essential for adaptive and personalized Human-Vehicle Interaction systems. To this end, we conduct an in-depth study to demystify complicated interactions between driving behaviors and styles.
Our studies start with rigorous examinations of the impacts from different DBSCAN configurations, representative driver groups, time-series variations, road conditions and etc. After that, we make 8 key findings through our studies in total.
Our goal is to demystify complicated interactions between driving behaviors and driving styles, to reveal the opportunities for adaptive and personalized Human-Vehicle Interactions.
- First normalize all driving statistics based on the specific insights.
- Then, we use Density-Based Spatial Clustering of Applications with Noise (DBSCAN), for adaptive classifications of driving styles and hidden patterns of driving behaviors.
Yu Zhang, mentored by Xiangjun Peng