FERST: A Full ECG Reception System for User Authentication using Two-stage Deep Learning

We are being increasingly surrounded by electronic devices that need reliable authentication before they can be accessed. While typed passwords, face and fingerprint-based authentication are popular today, we explore the possibility of using additional bio-origin signals, especially electrocardiogram (ECG) signals that can be collected without an active engagement and attention of the human user. Our proposed approach, abbreviated as FERST, uses a two-stage deep learning framework for signal processing and classification. The acquired and pre-equalized ECG signal is transferred from a wearable device through arm-wrist-palm galvanic coupled channel. The first part of the reception framework consists of a denoising autoencoder (DAE) that filters this noisy ECG signal. Then, the second stage includes a convolutional neural network (CNN) to classify and authenticate the denoised ECG signal as present/absent in a prior database used for training. The overall design goal of our approach is to achieve acceptable authentication performance with simple hardware, which further decreases network complexity and enables miniaturization of the end-to-end system. Results reveal that the FERST provides (i) 82% improvement in inference time relative to state-of-the-art adaptive filtration methods, (ii) outperforms the state-of-the-art with 99.7% classification accuracy on a standardized ECG library dataset and (iii) a relatively high classification accuracy of 99.2% for different arm-wrist-palm channel dimensions.