Long-Term Driving Behaviour Modelling for Driver Identification

Abstract

Driver identification constitutes an important enabling technology in intelligent transportation systems, allowing the development and the use of in-car personalised functionalities and thwarting unauthorised usage. In this work, we leverage the literature in authentication tasks (e.g. speaker recognition) and present a framework for driver identification which employs Support Vector Machine (SVM) and Universal Background Model schemes. Our framework operates on accelerator and break pedal signals, and thus augments other technologies, such as microphones or cameras, if present. Moreover, our framework is compatible with vehicles which are limited to traditional sensing modalities. We evaluate the framework on 15 hours of driving data for a total of 416 Km travelled, comprising of messages from the CAN bus of an electric vehicle and GPS traces from four different drivers travelling on the same route, obtaining an accuracy of over 95% in the identification rate. Furthermore, our evaluation shows that UBM schemes outperform classification approaches traditionally adopted in driver identification literature by a significant margin.

A Systematic Survey of Industrial Internet of Things Security: Requirements and Fog Computing Opportunities

“…The Fifth generation cellular network technology (5G) authentication scheme for smart devices proposed in [70] uses Cloud-based learning to dynamically identify and authenticate users based on behavioral patterns, showing another approach for minimizing user interaction. This concept has also been used in the field of intelligent vehicles whereby drivers are identified by their driving behavior [69].…”

Driver Distraction Detection Methods: A Literature Review and Framework

“…Ideally, a sensor indicates the level of distraction or the need to focus on the road before the driver feels increased effort or reduced performance [62]. However, for investigating distraction most researchers make use of non-intrusive sensors [63]. Non-intrusive methods are therefore preferred for monitoring the driver, and vision-based systems seem most attractive for both researchers and drivers [64].…”

SHAKE: SHared Acceleration Key Establishment for Resource-Constrained IoT Devices

“…Finally, acceleration profiles have also been used to prevent information leakage in wearables [22], as well as for security in different application domains that are far less resourceconstrained, including smartphone pairing [23], driver identification in smart cars [24], and smart bicycle locks [25].…”