Who is Driving? Event-Driven Driver Identification and Impostor Detection through Support Vector Machine

Driver identification and impostor detection suffer different challenges, including costly and invasive data collection. Existing methods incur additional costs due to their data dependency on complex and expensive sensory systems. This article proposes an event-driven framework for driver identification and impostor detection. That utilizes the Global Positioning System as the only data source. The proposed framework uses the Support Vector Machine as the supervised classification method. A modified RBF kernel is proposed to pursue a highly accurate framework for a large number of drivers. For the impostor detection task, this research proposes the use of a generalized negative class and devise an algorithm for building one. Two sets of experiments are performed to test the framework using a publicly accessible dataset and an indigenously collected dataset. The empirical study shows an average 94% recall for ten drivers and 90% for 24 drivers. Impostor driver is detected with more than 90% accuracy for more than three drivers.