CNN-LSTM Driving Style Classification Model Based on Driver Operation Time Series Data

Driving style recognition plays a crucial role in enhancing the effectiveness of intelligent transportation systems and advanced driver assistance systems (ADAS). As vehicles become increasingly connected and autonomous, there is a growing demand for personalized and adaptive solutions that can respond to individual driver behaviors. Traditional methods such as rule-based systems and static models struggle to interpret the dynamic and sequential nature of driving behavior. With the rise of machine learning, particularly deep learning techniques, new opportunities have emerged for real-time, data-driven behavioral analysis. This research builds on these advancements by introducing a hybrid CNN-LSTM model designed to accurately classify driving styles from time-series data.