AI Aided Noise Processing of Spintronic Based IoT Sensor for Magnetocardiography Application

TL;DR

This paper presents an IoT device with a spintronic sensor for magnetocardiography, employing deep learning to effectively denoise bio-magnetic signals, enabling portable and low-power heart monitoring in remote healthcare.

Contribution

It introduces a novel spintronic sensor-based IoT system combined with a deep learning model for noise reduction in magnetocardiography signals, advancing portable cardiac monitoring technology.

Findings

Deep learning effectively denoises bio-magnetic signals.

The combined CNN-GRU model captures and eliminates sensor noise.

Simulation results show promising performance in signal quality.

Abstract

As we are about to embark upon the highly hyped "Society 5.0", powered by the Internet of Things (IoT), traditional ways to monitor human heart signals for tracking cardio-vascular conditions are challenging, particularly in remote healthcare settings. On the merits of low power consumption, portability, and non-intrusiveness, there are no suitable IoT solutions that can provide information comparable to the conventional Electrocardiography (ECG). In this paper, we propose an IoT device utilizing a spintronic ultra-sensitive sensor that measures the magnetic fields produced by cardio-vascular electrical activity, i.e. Magentocardiography (MCG). After that, we treat the low-frequency noise generated by the sensors, which is also a challenge for most other sensors dealing with low-frequency bio-magnetic signals. Instead of relying on generic signal processing techniques such as averaging or filtering, we employ deep-learning training on bio-magnetic signals. Using an existing dataset of ECG records, MCG labels are synthetically constructed. A unique deep learning structure composed of combined Convolutional Neural Network (CNN) with Gated Recurrent Unit (GRU) is trained using the labeled data moving through a striding window, which is able to smartly capture and eliminate the noise features. Simulation results are reported to evaluate the effectiveness of the proposed method that demonstrates encouraging performance.