Event Related Biometrics: Towards an Unobtrusive Sensing Seat System for Continuous Human Authentication Marcello Ferro 1,* , Giovanni Pioggia 2 , Member, IEEE, Alessandro Tognetti 1 , Gabriele Dalle Mura 1 and Danilo De Rossi 1 1 Interdepartmental Research Center "E. Piaggio" Faculty of Engineering, University of Pisa, Italy 2 Institute of Clinical Physiology (IFC) National Council of Research (CNR) of Pisa, Italy Abstract—The present work is focused on the improvement of a Sensing Seat system previously developed by the authors for the initial authentication purpose in office and car scenarios. The goal is to obtain an event-related continuous authentication system, where the human subject should not take care of the system itself so that he is free to perform his normal actions. The system is realized by means of a sensing cover where conductive elastomers are used as strain sensors. The deformation of the cover caused by the body shape while actions are performed by the subject are used to obtain time-dependent relevant features. Such information are then analyzed by suitable classifiers that are able to perform the real-time continuous authentication task. A measurement campaign was carried out using data from 24 human subjects employed in an office scenario while a set of 22 actions were performed. The authentication capabilities of the system are reported in terms of acceptance and rejection rates, showing a high degree of correct classification. Index Terms—strain sensor, sensing seat, event-related human authentication, monitoring, security, biometrics I. I NTRODUCTION The use of biometrics for access control in restricted infras- tructures has been very extensively researched during the last four decades. The present work focused on the development of a Sensing Seat system for real-time event-related continuous human authentication purpose. Several companies are currently working in order to realize comfortable interactive seats. These systems, some of them al- ready on the market [1], [2], [3], [4], use different technologies and materials, but they share the use of sensors that measure the pressure exerted on the seat by the passenger. Actually, no existing system based on sensing seat is able to perform the human authentication task and no result on this topic, even if in a preliminary stage, was found in literature review. The existing systems, some of them are reported below, are more focused on comfort monitoring, pressure mapping, air-bag activation and event-related tasks. However, the information * Corresponding author: Dr. Marcello Ferro, Ph.D. Interdepartmental Re- search Center “E. Piaggio”, Faculty of Engineering, University of Pisa, Via Diotisalvi 2, 56100 Pisa, Italy. E-mail: marcello.ferro@ing.unipi.it supplied by these systems may be used to extract features useful for the authentication task. Additionally, patents [5], [6], [7] and academy works [8], [9], [10] were found on this topic. For many systems it was not possible to find accurate test results in terms of classification capabilities in biometrics tasks. In this work, the authors show the design and realization of an unobtrusive and versatile sensing seat system for human authentication that can be employed in different scenarios such as truck and car pilots, airplane pilots, plant and office personnel, and, in general, environments where the security is mandatory and a soft seat is available. A Sensing Seat system [11] was initially developed by the authors, where the enrollment and the authentication procedures were carried out with the cooperation of the user, according to the instructions supplied by the system. The mentioned prototype is able to supply a one-dimensional deformation profile, and, after a feature extraction process, the system performs the initial human authentication task. A new prototype is being developed to obtain a continuous authentication, without interfering with the user actions and according to the detection of predefined events. According to this purpose, the previous Sensing Seat prototype was upgraded and a new control system was developed to handle the issues regarding the continuous authentication as well as the event notifications of an high-level core system. The new prototype was tested during a measurement campaign in a smart room environment equipped with 5 cameras: 29 subjects were analyzed in an office scenario, over 2 sessions consisting in 6 repetitions each. A total of 22 actions were taken into account. The video streams were subsequently analyzed to obtain the annotation data to simulate the event notification mechanism. The test results show an high recognition degree, suggesting that, potentially, a more complex hardware system may result in more reliable results. According to this, the authors designed and realized a new Sensing Seat hardware system, where sensor information can supply data about the two-dimensional seat cover deformation. As the new prototype will be ready, a new measurement campaign will be conducted and the event-related authentication results will be compared to the ones obtained with the previous prototype. The proposed system, as part of the ACTIBIO project for multi-modal event-related human authentication [12], has been preliminarily tested in simulated office scenario and it will be tested in office and car pilots. ACTIBIO aims to research and 2009 Ninth International Conference on Intelligent Systems Design and Applications 978-0-7695-3872-3/09 $26.00 © 2009 IEEE DOI 10.1109/ISDA.2009.256 679 Authorized licensed use limited to: CNR Area Ricerca Pisa. Downloaded on March 09,2010 at 11:44:10 EST from IEEE Xplore. Restrictions apply.