TinyCardioUNet: IMU-to-ECG Translation with Graph-Encoded Inter-Axis Dependencies and Tensor Decomposition-Based Parameter Reduction

2026-09-24

AI Summary

This study addresses the technical challenge of reconstructing electrocardiogram (ECG) signals from chest-mounted inertial measurement unit (IMU) data for electrode-free continuous heart rate monitoring. We propose a lightweight UNet model integrating graph neural networks (GNNs) and tensor decomposition. The method directly utilizes full six-axis IMU data without channel selection, employing GNNs to encode inter-axis dependencies and variational Bayesian inference to achieve automatic rank selection in tensor decomposition for substantial parameter compression. With only 36,000 parameters, the proposed architecture attains a reconstruction accuracy of 0.098 RMSE and a correlation coefficient of 0.677, while maintaining robustness under noisy conditions. These results validate the effectiveness of ultra-compact architectures for physiological signal estimation.

Abstract

Estimating electrocardiography (ECG) from a chest-worn inertial measurement unit (IMU) enables continuous heart rate (HR) monitoring without the discomfort of electrodes. We propose TinyCardioUNet, a lightweight UNet that uses all six IMU axes without prior channel selection, refines its bottleneck with a graph neural network that encodes inter-axis dependencies, and employs tensor decomposition with automatic variational Bayesian rank selection for parameter reduction. On a public dataset, TinyCardioUNet achieves an RMSE of $0.098$ and a Pearson correlation coefficient of $0.677$ with only $36.0$k parameters and remains comparatively robust to additive noise, demonstrating accurate ECG reconstruction with a compact model.

Problem

• ECG estimation
• IMU
• heart rate monitoring
• wearable sensing

Innovation

• IMU-to-ECG Translation
• Graph Neural Network
• Tensor Decomposition
• Lightweight UNet
• Variational Bayesian Rank Selection