Human Identification Using Electrocardiogram Signal as a Biometric Trait

Human Identification Using Electrocardiogram Signal as a Biometric Trait

Anwar E. Ibrahim, Salah Abdel-Mageid, Nadra Nada, Marwa A. Elshahed
Copyright: © 2022 |Pages: 17
DOI: 10.4018/IJSDA.287113
Article PDF Download
Open access articles are freely available for download

Abstract

Biometrics is an interesting study due to the incredible progress in security. Electrocardiogram (ECG) signal analysis is an active research area for diagnoses. Various techniques have been proposed in human identification system based on ECG. This work investigates in ECG as a biometric trait which based on uniqueness represented by physiological and geometrical of ECG signal of person.In this paper, a proposed non-fiducial identification system is presented with comparative study using Radial Basis Functions (RBF) neural network, Back Propagation (BP) neural network and Support Vector Machine (SVM) as classification methods. The Discrete Wavelet Transform method is applied to extract features from the ECG signal. The experimental results show that the proposed scheme achieves high identification rate compared to the existing techniques. Furthermore, the two classifiers RBF and BP are integrated to achieve higher rate of human identification.
Article Preview
Top

1. Introduction

Science is the basis of life since its inception, and the technologies produced which in turn led to the development of various inventions to facilitate human life and raise its well-being. Therefore, science is the basis of the technology that has entered the details of human life. The importance of science lies in being the cornerstone of many practical applications that contribute to providing the basic needs of human beings and improving their standard of living. Various sciences and the technology that they have produced have always contributed to making the life of the individual easier, such as the techniques using systems dynamics which facilitate the life of the hypothesis (Guma, et al., 2018; Aslani, et al., 2018; Iqbal, & Abdullah, 2018; Omamo, et al., 2018).

Security became an interesting area for creativity due to the incredible progress in information technology. Three available approaches to prove a person's identity are something you have (physical object as magnetic card, keys, and so on), something you know (a pre-defined knowledge, as a password) and something you are (measurable personal traits as biometric). Secure increasing for identity proof by using a combination of these approaches.

Biometrics is a method of recognizing a person based on physiological or behavioral characteristics; therefore, it is difficult to be lost or forgotten and cannot be stolen or mimic. There are physiological characteristics that are related to the shape of the body such as face, electrocardiogram (ECG), fingerprints, hand geometry, DNA, and iris. While there are behavioral characteristics that are related to the behavior of the person such as handwriting, voice, and gate (Harshit, et al., 2014).

Medical biometrics considers another category of new biometric recognition method that includes signals which are used in clinical diagnostics. Examples of medical biometric signals are the electrocardiogram (ECG), phonocardiogram (PPG), electroencephalogram (EEG), blood volume pressure (BVP) (Agrafioti, et al., 2011).

The biometric system operates in one of two modes verification or identification after the enrollment process for database building as shown in figure 1. In verification mode, the captured biometric characteristic of the person compared with the individual biometric template of a given Personal Identification Number (PIN), which is stored in the system database and retrieved using the PIN (one to one comparison). In identification mode, the system recognizes an individual by searching the entire template database for a match (one-to-many comparison) (Prabhakar, et al., 2003).

Figure 1.

Enrolment, verification and identification processes

IJSDA.287113.f01

False Rejection Rate (FRR(t)) and False Acceptance Rate (FAR(t)) are two common types of errors companion to the biometric systems which are functions on the desired security level (acceptance threshold t). FRR (t) is the frequency of rejections for verifiable persons and it is an increasing function, while FAR(t) is the frequency of accesses for imposters and it is a decreasing function. Equal Error Rate (EER) denotes the system error when FRR equals FAR while Zero FAR denotes FRR when FAR equals zero and Zero FRR denotes FAR when FRR equals zero as shown in figure. 2.

Figure 2.

The relation between threshold and False Acceptance Rate (FAR) and False Rejection Rate (FRR)

IJSDA.287113.f02

Failure to Enrol rate (FTE) error happens when obtaining data cannot enter into the biometric system because it is considered as boor quality or invalid. Failure To capture rate (FTC) error happens during data acquisition where the system sensor fails to detect the biometric trait (Sareen, 2014).

Complete Article List

Search this Journal:
Reset
Volume 12: 1 Issue (2024): Forthcoming, Available for Pre-Order
Volume 11: 5 Issues (2022)
Volume 10: 4 Issues (2021)
Volume 9: 4 Issues (2020)
Volume 8: 4 Issues (2019)
Volume 7: 4 Issues (2018)
Volume 6: 4 Issues (2017)
Volume 5: 4 Issues (2016)
Volume 4: 4 Issues (2015)
Volume 3: 4 Issues (2014)
Volume 2: 4 Issues (2013)
Volume 1: 4 Issues (2012)
View Complete Journal Contents Listing