A Novel Hybrid Approach for Segmenting Driver Based on their Driving Style

Drivers present a diverse landscape with their distinct personalities, preferences, and driving habits influenced by many factors. While drivers exhibit a wide range of behaviors, identifiable patterns in driving styles enable the classification of drivers into discrete segments. Discrete segmentation provides a practical and effective way to categorize and address the differences in driving style. The segmentation approach offers many benefits, including simplification, measurement, proven methodology, customization, and safety. Numerous studies have investigated driving style classification using real-world vehicle data. These studies employed various methods to identify and categorize distinct driving patterns, including naturalist differences in driving and field operational tests. This paper presents a novel hybrid approach for segmenting driver behavior based on their driving patterns. We leverage vehicle acceleration data to create granular driver segments by combining event- and trip-based methodologies. Subsequently, a clustering analysis groups drivers based on their performance during key driving events. The effectiveness of our proposed method is validated through a rigorous evaluation using a virtual driving simulator and three predefined driver types. The proposed approach showed promising accuracy. This methodology provides a practical and effective way to categorize and address these differences. This approach not only simplifies the complexity of driver behaviors but also enables precise measurement and leverages proven methodologies from other industries, ultimately contributing to safer and more personalized driving experiences. Driving style classification is a versatile tool for advancing various driving-related research endeavors. This methodology holds significant potential for enhancing traffic safety, personalizing driving experiences, and optimizing fuel consumption.