期刊名称：International Journal of Advanced Computer Science and Applications(IJACSA)
印刷版ISSN：2158-107X
电子版ISSN：2156-5570
出版年度：2019
卷号：10
期号：1
页码：533-545
DOI：10.14569/IJACSA.2019.0100169
出版社：Science and Information Society (SAI)
摘要：In this paper, we introduce a human recognition system that utilizes lead I electrocardiogram (ECG). It proposes an efficient method for ECG analysis that corrects the signal and extract all major features of its waveform. FIR equiripple high pass filter is used for denoising ECG signal. R peak is detected using Haar wavelet transform. A novel class of features called as area under curve are computed from dominant fiducials of ECG waveform along with other known class of features such as interval features, amplitude features and angle features. The feasibility of an electrocardiogram as a new biometric is tested on selected features that reports the authentication performance 99.49% on QT database, 98.96% on PTB database and 98.48%on MIT-BIH arrhythmia database. The results obtained from the proposed approach surpasses the other conventional methods of biometric applications.
关键词：Electrocardiogram; biometric; area under curve features
