A 2-$\mu$J, 12-class, 91% Accuracy Spiking Neural Network Approach For Radar Gesture Recognition

TL;DR

This paper presents a novel energy-efficient spiking neural network approach for radar gesture recognition, achieving over 91% accuracy and demonstrating significant power savings suitable for IoT applications.

Contribution

The paper introduces a new radar-SNN training strategy, uses quantized weights for hardware efficiency, and reports energy consumption, advancing radar gesture recognition with low-power SNNs.

Findings

Achieved 91% accuracy on radar datasets.

Demonstrated power-efficient implementation with quantized weights.

Reported energy consumption per classification for real-world feasibility.

Abstract

Radar processing via spiking neural networks (SNNs) has recently emerged as a solution in the field of ultra-low-power wireless human-computer interaction. Compared to traditional energy- and area-hungry deep learning methods, SNNs are significantly more energy efficient and can be deployed in the growing number of compact SNN accelerator chips, making them a better solution for ubiquitous IoT applications. We propose a novel SNN strategy for radar gesture recognition, achieving more than 91% of accuracy on two different radar datasets. Our work significantly differs from previous approaches as 1) we use a novel radar-SNN training strategy, 2) we use quantized weights, enabling power-efficient implementation in real-world SNN hardware, and 3) we report the SNN energy consumption per classification, clearly demonstrating the real-world feasibility and power savings induced by SNN-based radar processing. We release evaluation code to help future research.