ECG Authentication Method Based on Parallel Multi-Scale One-Dimensional Residual Network With Center and Margin Loss

Abstract

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 multiscale one-dimensional residual network is proposed in this paper. This network utilizes three convolutional kernels with different kernel sizes, achieving better classification accuracy than the conventional schemes. Moreover, two loss functions named center loss and margin loss are used during the training of the network. Compared with the conventional softmax loss, these two loss functions can further improve 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% of equal error rate (EER), respectively. Compared with other works, our proposed method improves 1.61% and 4.89% classification accuracy on the ECG-ID database and the MIT-BIH Arrhythmia database, respectively.

ECG Biometric Authentication: A Comparative Analysis

“…Furthermore, what is common to the literature shown in the tables is that single-channel ECG (one lead of sensor) contains sufficient information to be discriminated between different subjects for the support of biometric recognition. There are different types of feature extraction modalities [8], [15], [18], [19], [27] and various classifiers [12], [21], [23], [24], [28] have been utilized for ECG-based recognition. In the following section, we summarize the methodologies based on the features and classification schemes.…”

“…During authentication, the score is compared to a predefined threshold, and the claimed identity is accepted, if the score is greater. There are different types of classifiers such as Euclidean distance, support vector machines (SVMs), dynamic time warping (DTW), and hamming distance utilized in the literature [8], [15], [18], [19], [21], [23], [24], [27], [35], [41], [44], [46]. ECG identification Most of the deep learning approaches for ECG biometric systems have been studied in the literature review used a fully connected layer and softmax for a classifier.…”

Identity Recognition Based on the QRS Complex Dynamics of Electrocardiogram

“…, n) is the design constant, andW k T is constant neural network weights of the k-th training QRS complex modeling result. Then we can obtain the following error system corresponding to the dynamic model (11) and the test QRS complex:…”

“…Step 3: Construct a set of state estimators based on the training QRS complexes modeling results as (11), where the RBF networks input is the test QRS complex's state;…”

An Efficient Algorithm for Cardiac Arrhythmia Classification Using Ensemble of Depthwise Separable Convolutional Neural Networks

“…ECG signals can be easily acquired by putting one's finger on the sensor for about 30 s [1]. There are at least two types of important information contained in the ECG signal, including those related to health or biomedical [2][3][4] and those related to the person identification or biometrics [5][6][7]. Due to its convenience, many ECG classification algorithms have been developed, including handcraft [4,8,9] and machine learning [10][11][12][13][14][15] methods.…”