Neuromorphic Edge Computing for Biomedical Applications: Gesture Classification Using EMG Signals

Abstract

With the emergence of edge-computing platforms, the applications of smart wearable devices are immense. This technology can be incorporated in consumer products such as smartwatches and activity trackers, for continuous health monitoring, as well as for medical applications such as myoelectric prosthetics, to interpret the electric activity in the residual limb and achieve fast and precise control. However, wearable technologies require a lightweight, energy-efficient, and low-latency processing system in order to extend the devices' autonomy while maintaining a realistic user-feedback interaction. Neuromorphic processing, thanks to its event-based and asynchronous nature, presents ideal characteristics for compact brain-inspired low-power and ultra-fast computing systems that can enable a new generation of wearable devices. This article presents two spiking neural networks (SNNs) for event-based electromyography (EMG) gesture recognition and their evaluation on Intel's research neuromorphic chip Loihi. Specifically, the evaluation is done on the Kapoho Bay platform which embeds the Loihi processor in a Universal Serial Bus (USB) form factor device allowing for closed-loop edge computation. With accurate experimental evaluation, this article demonstrates that the proposed method is able to discriminate 12 different hand gestures using an eight-channel EMG sensor and exceeds state-of-the-art results. We obtained an accuracy of 74% on the commonly used NinaPro DB5 dataset, a processing latency of 5.7 ms for 300-ms EMG samples while consuming only 41 mW.