ECG-Based Subject Identification Using Common Spatial Pattern and SVM

Turky N Alotaiby,Latifah M Aljafar,Saleh A Alshebeili,Waleed M Alsabhan

doi:10.1155/2019/8934905

Abstract

In this paper, a nonfiducial electrocardiogram (ECG, the process of recording the electrical activity of the heart over a period of time using electrodes placed on the skin) identification system based on the common spatial pattern (CSP) feature extraction technique is presented. The single- and multilead ECG signals of each subject are divided into nonoverlapping segments, and different segment lengths (1, 3, 5, 7, 10, or 15 seconds) are investigated. Features are extracted from each signal segment through projection on a CSP projection matrix. The extracted features are then used to train a radial basis function kernel-based Support Vector Machine (SVM) classifier, which is then employed in the identification phase. The proposed identification system was evaluated on 10, 20, …, 200 reference subjects of the Physikalisch-Technische Bundesanstalt (PTB) ECG database. Using a single limb-based lead (I) with 200 reference subjects, the system achieved an identification rate of 95.15% and equal error rate of 0.1. The use of a single chest-based lead (V3) for 200 reference subjects resulted in an identification rate of 98.92% and equal error rate of 0.08.

Highlights

Biometric recognition aims at uniquely identifying the individuals based on their physiological and/or behavior characteristics such as fingerprint, face, retina, palm print, gait, or speech [1]
We present a new approach for subject identification that is based on the common spatial pattern (CSP) feature extraction technique using single- and multiECG signals
This paper presents an ECG identification system based on the CSP feature extraction technique

Summary

Introduction

Biometric recognition aims at uniquely identifying the individuals based on their physiological and/or behavior characteristics such as fingerprint, face, retina, palm print, gait, or speech [1]. The various biometrics that are currently being adopted exhibit different issues related to performance, measurability, robustness, and liveness detection [10,11,12,13,14]. The electrocardiogram (ECG) is one of the more recent means of biometric identification to be explored. An ECG is the physical interpretation of depolarization electrical activity that the heart muscles create. This electrical activity is propagated throughout the body as a wave [15]. This propagating wave produces a current that is unique for each individual and depends on the anatomic structure of the individual’s heart and body. The resulting current can be detected quite using skin electrodes

Methods

Results

Conclusion