Abstract
Although biometrics systems using an electrocardiogram (ECG) have been actively researched, there is a characteristic that the morphological features of the ECG signal are measured differently depending on the measurement environment. In general, post-exercise ECG is not matched with the morphological features of the pre-exercise ECG because of the temporary tachycardia. This can degrade the user recognition performance. Although normalization studies have been conducted to match the post- and pre-exercise ECG, limitations related to the distortion of the P wave, QRS complexes, and T wave, which are morphological features, often arise. In this paper, we propose a method for matching pre- and post-exercise ECG cycles based on time and frequency fusion normalization in consideration of morphological features and classifying users with high performance by an optimized system. One cycle of post-exercise ECG is expanded by linear interpolation and filtered with an optimized frequency through the fusion normalization method. The fusion normalization method aims to match one post-exercise ECG cycle to one pre-exercise ECG cycle. The experimental results show that the average similarity between the pre- and post-exercise states improves by 25.6% after normalization, for 30 ECG cycles. Additionally, the normalization algorithm improves the maximum user recognition performance from 96.4 to 98%.
Highlights
Security technology is evolving along with artificial intelligence technology
The technical organization of a user recognition system that uses ECG includes the creation of a database (DB) using the measured ECG, signal processing to remove noise from the original ECG signal, segmentation based on the fiducial and non-fiducial points, feature extraction and reduction of feature vector dimensions in the segmented areas, and recognition of users using classification results predicted by classifiers
ECG signals arein characterized behavioral features and are measured differently depending on the subject’s condition. They measured in the relaxed as welldifferently as in otherdepending states and ECG signals are characterized by are behavioral features and arestate measured are analyzed by the user recognition systems after normalization
Summary
Security technology is evolving along with artificial intelligence technology. Biometrics technology using bio-information based on physical characteristics is analyzed with high recognition performance but has been a social issue due to forgery and alteration events and accidents [12,13]. The ECG, a representative bio-signal inside the body, is unique to each individual, owing to the electrophysiological factors of the heart, as well as its location, size, and physical condition Because it is an electrical signal, it is affected by behavioral features and varies according to the measurement environment [19]. Studies on normalization have been conducted to match post- and pre-exercise ECGs, they experience problems such as distortions of the P wave, QRS complexes, and T wave, which are morphological features as well as unique biometric information. The experimental method, experiment results, and future research directions are discussed in Section 4, and the conclusions are drawn in Section 5, stressing the originality of this study
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
