ECG-based biometric under different psychological stress states

Highlights

• We propose a biometric method that combines manual and automatic features, which provides the possibility of biometric identification under different stress conditions.

• We propose a new indicator stress classification Coefficient(SCC) to evaluate the impact of different psychological stress on HRV features. The smaller stress classification Coefficient(SCC), the smaller the influence of different psychological pressures on HRV features.

• We propose a method to reduce the influence of different psychological pressures on HRV features. We cluster the HRV features with the GMM model, and use the GMM clustering center parameters to process the HRV features to reduce the stress classification Coefficient(SCC), which means reducing the impact of different psychological pressures on HRV features.

Abstract

Background and objective

In recent years, people have been exploring methods for biometric identification through electrocardiogram (ECG) signals. Under the same psychological pressure state, biometric identification through ECG signals is a traditional verification method. However, ECG signals are affected by changes in psychological stress, and ECG-Based biometric under different psychological stress states are still challenging. In this paper, we propose a method combining manual and automatic features for ECG-based biometric under different psychological stress states. And propose a new indicator Stress Classification Coefficient (SCC) that assesses the effect of different psychological stress on heart rate variability (HRV) features.

Methods

In our method, we obtain manual features to be a three-step process: first, HRV features obtained from the ECG signals. Second, based on HRV features, the mental state of the experimental subjects is assessed by using the Gaussian mixture model (GMM). Finally, use cluster centers to process the original HRV features to reduce the Stress Classification Coefficient (SCC). Also, the one-dimensional convolutional neural network is constructed to automatically extract the implied features of ECG signals. Finally, the manual feature and the automatic feature are combined, and the final recognition result is obtained through the support vector machine (SVM) model. The major attribute of the proposed method is that it can perform ECG biometric under different psychological stress states. The combination of manual and automatic features expands the application scenarios of ECG-based biometric.

Results

Based on this method, we used the Montreal stress model with calculation experiment in the laboratory to induce stress on 23 healthy students (10 women and 13 men, aged 20–37), and obtain their ECG signals under different stress conditions. Through this method to recognize the above data, an average recognition rate of more than 95% can be achieved, the average F1 score is 0.97.

Conclusions

The proposed method in this article is a promising approach to deal with the effects of different psychological stresses on ECG-Based biometric. It provides the possibility of ECG-Based biometric under different psychological stress.

Introduction

Biometric recognition technology is a method for identification or verification based on human physiological or behavioral characteristics, including facial, fingerprint, iris, finger veins, gait, and so on [1]. Among them, biometric recognition through electrocardiogram (ECG) signals has the following advantages: ①ECG signals are got by heart activity, and activity check is the prerequisite for ECG acquisition and ECG recognition ②ECG is difficult to copy or deceive, which leads to the high security of ECG biological data. ③Easy to collect ECG signals. With the development of sensor technology, ECG signals can be collected through the wearable device [2].

However, because ECG signals are affected by changes in psychological stress, biometric recognition under different stress states is still challenging.

In this paper, we aim at ECG biometrics under different psychological stress states, proposes a biometric method combining manual features and automatic features, and proposes a new indicator Stress Classification Coefficient (SCC) used to evaluate the impact of different psychological stress states on heart rate variability (HRV) features.

First, we collect the ECG signal of the experimental subject through our self-made wearable device and preprocess the data to reduce the noise interference caused by the wearing of the device. Secondly, the Pan-Tompkins (PT) algorithm is used to identify the R feature points of the ECG signal, and the short-term HRV features in the ECG signal are extracted using the acquired RR interval signal [3]. Then clustering of Gaussian Mixture Model (GMM) is performed according to the HRV feature information. Because HRV features are regulated by sympathetic nerves, they will shift HRV features under different stress conditions. The clustering results of the GMM model can be used to evaluate the mental state of the experimental subjects.

Then use cluster center parameters of the GMM model to process the original HRV features, thereby reducing Stress Classification Coefficient(SCC), which means reducing the impact of different psychological stress states on HRV features. Simultaneously, we use a one-dimensional convolutional network to extract in-depth features from the ECG timing signals. Finally, the manual and automatic features are combined, and the final identification is performed through the support vector machine (SVM) model.

The novelty, contribution, and characteristics of the proposed method are as follows.

• ① We propose a biometric method that combines manual and automatic features, which provides the possibility of biometric identification under different stress conditions.

• ② We propose a new indicator Stress Classification Coefficient(SCC) to evaluate the impact of different psychological stress on HRV features. The smaller the Stress Classification Coefficient(SCC), the smaller the influence of different psychological pressures on HRV features.

• ③ We propose a method to reduce the influence of different psychological pressures on HRV features. We cluster the HRV features with the GMM model, and use the GMM clustering center parameters to process the HRV features to reduce the Stress Classification Coefficient(SCC), which means reducing the impact of different psychological pressures on HRV features.

The rest of this paper is organized as follows. In Section 2, we will mainly discuss some related methods of ECG recognition and stress recognition. We will introduce the details of this method in Section 3. Subsequently, in Section 4, the experimental results of this method in the test data set are introduced. In Section 5, we discuss and summarize this research.