Sparse Spike Encoding of Channel Responses for Energy Efficient Human Activity Recognition

TL;DR

This paper introduces a spiking neural network-based autoencoder that efficiently encodes channel responses for human activity recognition, achieving high accuracy with significantly reduced energy consumption on edge devices.

Contribution

It presents a novel spiking convolutional autoencoder trained with SNNs to encode channel responses, eliminating preprocessing and improving energy efficiency and accuracy in HAR.

Findings

Achieves 96% F1 score comparable to hybrid methods.

Produces 81.1% sparse spike encoding.

Encoding improves HAR accuracy and efficiency.

Abstract

ISAC enables pervasive monitoring, but modern sensing algorithms are often too complex for energy-constrained edge devices. This motivates the development of learning techniques that balance accuracy performance and energy efficiency. Spiking Neural Networks (SNNs) are a promising alternative, processing information as sparse binary spike trains and potentially reducing energy consumption by orders of magnitude. In this work, we propose a spiking convolutional autoencoder (SCAE) that learns tailored spike-encoded representations of channel impulse responses (CIR), jointly trained with an SNN for human activity recognition (HAR), thereby eliminating the need for Doppler domain preprocessing. The results show that our SCAE-SNN achieves F1 scores comparable to a hybrid approach (almost 96%), while producing substantially sparser spike encoding (81.1% sparsity). We also show that encoding CIR data prior to classification improves both HAR accuracy and efficiency. The code is available at https://github.com/ele-ciccia/SCAE-SNN-HAR.