At the Edge of the Heart: ULP FPGA-Based CNN for On-Device Cardiac Feature Extraction in Smart Health Sensors for Astronauts

TL;DR

This paper introduces an ultra-low-power FPGA-based CNN solution for real-time cardiac feature extraction from Seismocardiography signals on resource-constrained wearable sensors, suitable for space applications.

Contribution

It presents a quantization-aware trained CNN with a systolic-array accelerator on FPGA, enabling efficient, accurate, and energy-efficient on-device cardiac analysis in space environments.

Findings

Achieved 98% validation accuracy in SCG feature classification.

Consumed only 8.55 mW power during inference.

Completed inference in 95.5 ms on FPGA hardware.

Abstract

The convergence of accelerating human spaceflight ambitions and critical terrestrial health monitoring demands is driving unprecedented requirements for reliable, real-time feature extraction on extremely resource-constrained wearable health sensors. We present an ultra-low-power (ULP) Field-Programmable Gate Array (FPGA) based solution for real-time Seismocardiography (SCG) feature classification using Convolutional Neural Networks (CNNs). Our approach combines quantization-aware training with a systolic-array accelerator to enable efficient integer-only inference on the Lattice iCE40UP5K FPGA, which offers an ideal platform for battery-powered deployments -- particularly in space environments -- thanks to its power efficiency and radiation resilience. The implementation achieves a validation accuracy of 98% while consuming only 8.55 mW, completing inference in 95.5 ms with minimal hardware resources (2,861 LUTs and 7 DSP blocks). These results demonstrate that fully on-device SCG-based cardiac feature extraction is feasible on resource-constrained hardware, enabling energy-efficient, autonomous health monitoring for astronauts in long-duration space missions.