{"slug": "tinycardiounet-imu-to-ecg-translation-with-graph-encoded-inter-axis-dependencies", "title": "TinyCardioUNet: IMU-to-ECG Translation with Graph-Encoded Inter-Axis Dependencies and Tensor Decomposition-Based Parameter Reduction", "summary": "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.", "body_md": "# TinyCardioUNet: IMU-to-ECG Translation with Graph-Encoded Inter-Axis Dependencies and Tensor Decomposition-Based Parameter Reduction\n\nBy Seungwoo Han, Ingon Chanpornpakdi, Motoi Noda, Puwadej Leelasiri, Ibuki Hiruma, Toshihisa TanakaSource: \n\n[arXiv cs.LG](https://arxiv.org/list/cs.LG/recent)\narXiv:2609.29322v1 Announce Type: new \nAbstract: 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 \n\n[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.\nGet AI news in your inbox\n\nDaily digest of what matters in AI.", "url": "https://wpnews.pro/news/tinycardiounet-imu-to-ecg-translation-with-graph-encoded-inter-axis-dependencies", "canonical_source": "https://www.machinebrief.com/news/tinycardiounet-imu-to-ecg-translation-with-graph-encoded-int-nts5", "published_at": "2026-09-25 04:00:00+00:00", "updated_at": "2026-09-25 05:00:53.467342+00:00", "lang": "en", "topics": ["machine-learning", "neural-networks", "ai-research"], "entities": ["TinyCardioUNet", "Seungwoo Han", "Ingon Chanpornpakdi", "Motoi Noda", "Puwadej Leelasiri", "Ibuki Hiruma", "Toshihisa Tanaka", "arXiv"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/tinycardiounet-imu-to-ecg-translation-with-graph-encoded-inter-axis-dependencies", "markdown": "https://wpnews.pro/news/tinycardiounet-imu-to-ecg-translation-with-graph-encoded-inter-axis-dependencies.md", "text": "https://wpnews.pro/news/tinycardiounet-imu-to-ecg-translation-with-graph-encoded-inter-axis-dependencies.txt", "jsonld": "https://wpnews.pro/news/tinycardiounet-imu-to-ecg-translation-with-graph-encoded-inter-axis-dependencies.jsonld"}}