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

TinyCardioUNet, a lightweight UNet from researchers Seungwoo Han, Ingon Chanpornpakdi, Motoi Noda, Puwadej Leelasiri, Ibuki Hiruma and Toshihisa Tanaka, reconstructs electrocardiography (ECG) from a chest-worn six-axis inertial measurement unit (IMU) using a graph neural network bottleneck that encodes inter-axis dependencies and tensor decomposition with automatic variational Bayesian rank selection for parameter reduction. On a public dataset the model reaches 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. The work, posted as arXiv:2609.29322v1 in cs.LG, targets continuous heart rate monitoring without electrodes.

TinyCardioUNet: IMU-to-ECG Translation with Graph-Encoded Inter-Axis Dependencies and Tensor Decomposition-Based Parameter Reduction By Seungwoo Han, Ingon Chanpornpakdi, Motoi Noda, Puwadej Leelasiri, Ibuki Hiruma, Toshihisa TanakaSource: arXiv cs.LG https://arxiv.org/list/cs.LG/recent arXiv:2609.29322v1 Announce Type: new 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 https://www.machinebrief.com/glossary/neural-network that encodes inter-axis dependencies, and employs tensor decomposition with automatic variational Bayesian rank selection for parameter https://www.machinebrief.com/glossary/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. Get AI news in your inbox Daily digest of what matters in AI.