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

2026-02-06

AI Summary

This work addresses the challenge of achieving both high accuracy and energy efficiency in human activity recognition on resource-constrained edge devices. The authors propose a Spiking Convolutional Autoencoder (SCAE) that performs sparse spiking encoding directly on Channel Impulse Response (CIR) signals and is jointly trained end-to-end with a Spiking Neural Network (SNN). This approach eliminates the need for preprocessing in the Doppler domain—a common requirement in conventional methods—while maintaining a high recognition performance of 96% F1-score. Notably, the proposed method achieves a spiking sparsity of 81.1%, substantially improving energy efficiency compared to traditional solutions.

Technology Category

• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Planning, Routing, and Scheduling: Activity and Plan Recognition
• Machine Learning: Learning on the Edge & Model Compression

Application Category

• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

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.

Problem

• Human Activity Recognition
• Energy Efficiency
• Spiking Neural Networks
• Channel Impulse Response
• Edge Devices

Innovation

• Spiking Neural Networks
• Sparse Spike Encoding
• Channel Impulse Response
• Human Activity Recognition
• Energy Efficiency