Researchers from the Digital Health Team at Samsung Research America (SRA) are developing new AI technologies to understand users’ health status.
Measured from wearable devices, biosignals such as sleep, heart rate, and physical activity offer health insights for appropiate health guidance.
“Biosignals are inherently dynamic, with unique time-varying physiological properties. The key contribution of this research lies in proving the viability of health foundation models capable of capturing both the inter-signal relationships and their underlying temporal structures,” Subbu Venkatraman, head, of the Digital Health research lab, Digital Health Team Samsung Research America, said.
AI technologies for health management
Samsung researchers recently introduced two foundation models based on wearable data:
- xMAE (Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning): Aims to learn the temporal relationship between different biosignals
- HiMAE (Hierarchical Masked Autoencoder): Seeks to understand health patterns across different time scales in wearable time-series data.
Samsung said both studies advance health AI models that better understand the physiological relationships and temporal structure of biosignals.
Samsung’s work on xMAE and HiMAE models was accepted to the International Conference on Machine Learning (ICML) and the International Conference on Learning Representations (ICLR), respectively.
Sharanya Desai, head, digital health algorithms, Digital Health Team, Samsung Research America, said: “We will continue to develop and advance health foundation models that can be applied to a variety of biosignals and health features that can operate on-device with limited sensors and computing resources.”
