“…In contrast, electrocardiogram (ECG) signals, which exhibit unique physiological characteristics across subjects related to the placement and size of the heart, are difficult to spoof because the underlying biometric features are concealed during authentication and can only be obtained from physical measurements on the subject [ 12 , 13 , 14 ]. Since Biel et al [ 15 ] first studied using ECG signal processing for the biometric recognition, ECG-based biometric authentication has received great attention as a next-generation promising technique and been implemented with various approaches to improve the authentication performance for the past few decades [ 16 , 17 , 18 ]. However, ECG signals of a person may vary according to his/her physical state or health condition, possibly leading to authentication failure in some cases [ 19 , 20 , 21 ].…”