Heart Sounds Human Identification and Verification Approaches using Vector Quantization and Gaussian Mixture Models

Heart Sounds Human Identification and Verification Approaches using Vector Quantization and Gaussian Mixture Models

Neveen I. Ghali (Faculty of Science, Al-Azhar University, Cairo, Egypt), Rasha Wahid (Faculty of Science, Al-Azhar University, Cairo, Egypt) and Aboul Ella Hassanien (Scientific Research Group in Egypt (SRGE), Faculty of Computers and Information, Cairo University, Cairo, Egypt)
DOI: 10.4018/ijsbbt.2012100106
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

In this paper the possibility of using the human heart sounds as a human print is investigated. To evaluate the performance and the uniqueness of the proposed approach, tests using a high resolution auscultation digital stethoscope are done for nearly 80 heart sound samples. The verification approach consists of a robust feature extraction with a specified configuration in conjunction with Gaussian mixture modeling. The similarity of two samples is estimated by measuring the difference between their negative log-likelihood similarities of the features. The experimental results obtained show that the overall accuracy offered by the employed Gaussian mixture modeling reach up to 85%. The identification approach consists of a robust feature extraction with a specified configuration in conjunction with LBG-VQ. The experimental results obtained show that the overall accuracy offered by the employed LBG-VQ reach up to 88.7%.
Article Preview

1. Introduction

The need to identify persons correctly and irrevocably has existed for a very long time. The authorization to enter a building, to open a cupboard, to cross a border, to get money from a bank etc. is always connected to the identity of a person. It is therefore necessary to prove this identity in one way or another. This procedure is called verification. A person claims to be authorized or to have a certain identity, and this must then be verified (Wahid et al., in press).

Knowledge-based and possession-based authentication mechanisms imply that users need to carry or remember the authenticator in order to be granted access to a system, building, or service. For comparing these traditional authenticators with authentication through biometrics, it is often argued that keys could be lost, stolen or easily duplicated and passwords could be forgotten. A serious problem is that the link between the legitimate individual and the authenticator is weak, and the authentication system has no means to distinguish between a designated owner of the authenticator and an impostor or a guesser. On the other hand, the general view is that biometric traits have an advantage in that they cannot be stolen, easily guessed or forgotten (El-Bendary et al., 2010; Phua et al., 2006; Preez & Von Solms, 2005; Wahid et al., in press).

Biometrics are commonly categorized as either physiological or behavioral trait. Physiological traits (sometimes called passive traits) refer to fixed or stable human characteristics, such as fingerprints, shape and geometry of face, hands, fingers or ears, the pattern of veins, irises, teeth, the heart sound as well as samples of DNA. Physiological traits are generally existent on every individual and are distinctive and permanent, unless accidents, illnesses, genetic defects, or aging have altered or destroyed them. Behavioral traits (active traits) measure human characteristics represented by skills or functions performed by an individual. These include gait, voice, key-stroke and signature dynamics (Beritelli & Serrano, 2007; Cheng et al., 2011; El-Bendary et al., 2010; Wahid et al., in press).

Biometric recognition can be defined as automated methods for accurately recognizing individuals based on distinguishing physiological and/or behavioral traits. The technology of biometrics, in many different forms, is currently being used very widely for identification and authentication of individuals. In a non-automated way and on a smaller scale, parts of the human body and aspects of human behavior have been used for decades as a means of interpersonal recognition and authentication. For example, face recognition has been used for a long time in (non-automated) security and access applications. Safety, quality and technical compatibility of biometric technologies can be promoted through standards and standardization activities. Standards are essential for the deployment of biometric technologies on large-scale national and international applications (Wahid et al., in press).

The rest of the paper is organized as follows. Section 2 shows the related works. Section 3 Method and material introduces some perliminaries of the two propesed methods used for identification and verification processes. Experimental results are discussed in Section 4; Section 5 discusses heart signal human identification approach and verification approach in detail. While Section 6 concludes and presents future work.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 5: 2 Issues (2017): Forthcoming, Available for Pre-Order
Volume 4: 2 Issues (2016): Forthcoming, Available for Pre-Order
Volume 3: 1 Issue (2015)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing