A Rapid Pattern-Recognition Method for Driving Types Using Clustering-Based Support Vector Machines
This work addresses the need for efficient driver behavior analysis in automotive safety systems, but it is incremental as it combines existing methods (k-means and SVM) for a specific application.
The paper tackled the problem of rapidly recognizing driver types (aggressive vs. moderate) during curve negotiation by developing a k-means clustering-based SVM method, which achieved effective classification with shorter recognition time compared to standard SVM.
A rapid pattern-recognition approach to characterize driver's curve-negotiating behavior is proposed. To shorten the recognition time and improve the recognition of driving styles, a k-means clustering-based support vector machine ( kMC-SVM) method is developed and used for classifying drivers into two types: aggressive and moderate. First, vehicle speed and throttle opening are treated as the feature parameters to reflect the driving styles. Second, to discriminate driver curve-negotiating behaviors and reduce the number of support vectors, the k-means clustering method is used to extract and gather the two types of driving data and shorten the recognition time. Then, based on the clustering results, a support vector machine approach is utilized to generate the hyperplane for judging and predicting to which types the human driver are subject. Lastly, to verify the validity of the kMC-SVM method, a cross-validation experiment is designed and conducted. The research results show that the $ k $MC-SVM is an effective method to classify driving styles with a short time, compared with SVM method.