FPGA-based reservoir computing system for ECG denoising

ECG is corrupted by various noises such as baseline wander, channel noise, Electromyogram (EMG) noise, and power line interference (PLI). These noises make diagnosis difficult. In this paper, we implement an inexpensive, portable device that can remove noise from the corrupted ECG signals with high performance, speed, and privacy. First, we apply a Single Node Reservoir Computing (SNRC) architecture to clean the corrupted ECG signal with high performance. Second, we implement our technique on a portable inexpensive FPGA device that enables us to achieve high speed and privacy. In this manuscript, we simulate two noises: the typical EMG and PLI noises. To evaluate our technique, we use three performance metrics, namely, the output SNR improvement (SNRimp), the mean square error (MSE), and the percentage root mean square difference (PRD). The data is collected from the Massachusetts Institute of Technology-Boston's Beth Israel Hospital (MIT-BIH) arrhythmia database. With input SNR = 0 dB, the proposed system achieves SNRimp of 15.8 and PRD of 24.6, in the case of EMG noise and SNRimp of 25.7and PRD of 4.9, in the case of PLI noise. Comparison results to the related works show the advantages of the proposed system.