Neuromorphic implementation of ECG anomaly detection using delay chains

TL;DR

This paper presents a neuromorphic approach using delay chains in spiking neural networks to efficiently analyze long-duration ECG signals in real-time, suitable for low-power wearable devices.

Contribution

It introduces a novel method of extending memory in spiking neural networks with delay chains to handle long temporal signals without external buffers.

Findings

Successfully mapped multi-second ECG signals into neural activity.

Demonstrated preservation of temporal information in neuromorphic processing.

Validated approach on ECG anomaly detection with promising results.

Abstract

Real-time analysis and classification of bio-signals measured using wearable devices is computationally costly and requires dedicated low-power hardware. One promising approach is to use spiking neural networks implemented using in-memory computing architectures and neuromorphic electronic circuits. However, as these circuits process data in streaming mode without the possibility of storing it in external buffers, a major challenge lies in the processing of spatio-temporal signals that last longer than the time constants present in the network synapses and neurons. Here we propose to extend the memory capacity of a spiking neural network by using parallel delay chains. We show that it is possible to map temporal signals of multiple seconds into spiking activity distributed across multiple neurons which have time constants of few milliseconds. We validate this approach on an ECG anomaly detection task and present experimental results that demonstrate how temporal information is properly preserved in the network activity.