ECG Authentication Method Based On Residual Network With Category Distance Loss

To enhance the security level of digital information,the biometric authentication method based on Electrocardiographic(ECG)is gaining increasing attention in a wide range of applications.Compared with other biometric features,e.g.,fingerprint and face,the ECG signals have several advantages,such as higher security,simpler acquisition,liveness detection,and health information.Therefore,various methods for ECG-based authentication have been proposed.However,the generalization ability of these methods is limited because the feature extraction for the ECG signals in conventional methods is data dependent.To improve the generalization ability and achieve more stable results on different datasets,a parallel multi-scale one-dimensional residual network based on the category distance loss function is proposed in this paper.This network utilizes three convolutional kernels with different kernel sizes,achieving better classification accuracy than the conventional schemes.Moreover,a new loss function named category distance loss is used during the training of the network.Compared with the conventional softmax loss,this loss function focus on the intra-class compactness and inter-class dispersion,further improving the generalization ability of the extracted embedding features.Furthermore,we evaluate the effectiveness of our proposed method thoroughly on the ECG-ID database,the PTB Diagnostic ECG database,and the MIT-BIH Arrhythmia database,achieving 2.00%,0.59%,and 4.74%Equal Error Rate(EER),respectively.Compared with other works,our proposed method obtains 98.24%,100%,and 95.99%classification accuracy,respectively,improving 1.61%accuracy on the ECG-ID database and 4.89%accuracy on the MIT-BIH Arrhythmia database.