CardioWheel: ECG Biometrics on the Steering Wheel
Monitoring physiological signals while driving is a recent trend in the automotive industry. We present CardioWheel, a state-of-the-art machine learning solution for driver biometrics based on electrocardiographic signals (ECG). The presented system perva
- PDF / 503,850 Bytes
- 4 Pages / 439.37 x 666.142 pts Page_size
- 89 Downloads / 225 Views
CardioID Technologies Lda, Lisbon, Portugal Instituto de Telecomunica¸co ˜es, Lisbon, Portugal [email protected]
Abstract. Monitoring physiological signals while driving is a recent trend in the automotive industry. We present CardioWheel, a state-ofthe-art machine learning solution for driver biometrics based on electrocardiographic signals (ECG). The presented system pervasively acquires heart signals from the users hands through sensors embedded in the steering wheel, to recognize the driver’s identity. It combines unsupervised and supervised machine learning algorithms, and is being tested in real-world scenarios, illustrating one of the potential uses of this technology. Keywords: Electrocardiographic signals (ECG) motive industry · Personalization · Security
1
·
Biometrics
·
Auto-
Introduction
Automatic personalization of car settings, based on the driver’s identity, is becoming a standard in the automotive industry. Examples of these adjustable settings include seat and mirror positions, favorite radio stations, address lists, among others. Traditionally, this problem has been tackled by resorting to something the user has, like a personal physical key. Recently, with the arrival of connected car systems, such as Android Auto and Apple Carplay, driver authentication is routed through the smartphone, which typically has an associated user identity. Moreover, integration with cloud services increases the range of personalization systems, leveraging the available digital footprint of the user. Biometric recognition, which makes use of intrinsic measurable properties of the user, is an alternative authentication method with undisputed advantages. The inclusion of biometrics into cars is not new [2,10], though it has not been widely adopted, mainly due to usability issues. Our system uses the heart signal to enable driver recognition, in a similar fashion as with a fingerprint. The electrocardiographic (ECG) signal is acquired from the driver’s hands with sensors embedded in the steering wheel, continuously and unobtrusively while the user is driving. This allows for biometrics to be integrated in cars in an innovative way. c Springer International Publishing Switzerland 2015 A. Bifet et al. (Eds.): ECML PKDD 2015, Part III, LNAI 9286, pp. 267–270, 2015. DOI: 10.1007/978-3-319-23461-8 27
268
2
A. Louren¸co et al
Target Users
According to a recent report [1], half of all surveyed consumers purchase cars based on the brand’s technological reputation. In the survey, consumers demonstrated how information and technology are crucial throughout the car experience. Additionally, consumers are willing to disclose personal information for customization, security and savings, with 60% of the population willing to provide biometric information, such as fingerprints and DNA samples, in return for personalized security or car security. Major brands are starting to introduce biometric technology in their products. For example, Ford [3], in a patent approved in January 2015, outlines a system that uses a smartpho
Data Loading...
