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

arXiv: https://arxiv.org/abs/2609.29322 · HTML: https://mlsanity.com/paper/2609.29322/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 24 Sep 2026.

## Builds on (most cited first, 7 of 7)

- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [WaveNet: A Generative Model for Raw Audio](https://mlsanity.com/paper/1609.03499/) (2016)
- [Symbolic Discovery of Optimization Algorithms](https://mlsanity.com/paper/2302.06675/) (2023)
- [Compression of Deep Convolutional Neural Networks for Fast and Low Power Mobile Applications](https://mlsanity.com/paper/1511.06530/) (2015)
- [Wave-U-Net: A Multi-Scale Neural Network for End-to-End Audio Source Separation](https://mlsanity.com/paper/1806.03185/) (2018)
- [Tensor Regression Networks with various Low-Rank Tensor Approximations](https://mlsanity.com/paper/1712.09520/) (2017)

## Abstract (arXiv)

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 36.0k parameters and remains comparatively robust to additive noise, demonstrating accurate ECG reconstruction with a compact model.