Research on Classification and Recognition of Driving Styles Based on Feature Engineering

Abstract

Accurate classification and the effective recognition of driving styles are critical for improving control performance of the vehicle powertrain. In this research, a set of driving style classification and recognition methods is built based on the feature engineering. First, a specified road test is conducted considering the influence factors, and meanwhile, the corresponding driving data is collected, followed by a detailed evaluation of the driving styles. Then, the information entropy is applied to discretize the driving data, including the speed, acceleration, and opening degree of the accelerator pedal, and 44 feature quantities are extracted to characterize the driving style. By analyzing strong correlation and redundancy among the constructed feature quantities, the principal component analysis (PCA) is employed to reduce the dimension, and the fuzzy c-means (FCM) clustering algorithm is leveraged to classify the driving style. The successful classification rate reaches 92.16%, which is improved by 9.81% in comparison with traditional features. Finally, a parameter identification algorithm based on the support vector machine (SVM) is applied to identify the classified driving style, and the recognition accuracy reaches 92.86%, which is improved by 7.15% in comparison with traditional features, proving the feasibility of the proposed algorithm.