Table of Contents Author Guidelines Submit a Manuscript
Journal of Biomedicine and Biotechnology
Volume 2012 (2012), Article ID 403987, 11 pages
Research Article

Using Medical History Embedded in Biometrics Medical Card for User Identity Authentication: Privacy Preserving Authentication Model by Features Matching

Department of Computer and Information Science, University of Macau, Taipa, Macau

Received 20 December 2011; Accepted 25 December 2011

Academic Editor: Sabah Mohammed

Copyright © 2012 Simon Fong and Yan Zhuang. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.


Many forms of biometrics have been proposed and studied for biometrics authentication. Recently researchers are looking into longitudinal pattern matching that based on more than just a singular biometrics; data from user’s activities are used to characterise the identity of a user. In this paper we advocate a novel type of authentication by using a user’s medical history which can be electronically stored in a biometric security card. This is a sequel paper from our previous work about defining abstract format of medical data to be queried and tested upon authentication. The challenge to overcome is preserving the user’s privacy by choosing only the useful features from the medical data for use in authentication. The features should contain less sensitive elements and they are implicitly related to the target illness. Therefore exchanging questions and answers about a few carefully chosen features in an open channel would not easily or directly expose the illness, but yet it can verify by inference whether the user has a record of it stored in his smart card. The design of a privacy preserving model by backward inference is introduced in this paper. Some live medical data are used in experiments for validation and demonstration.