Google Research launches SensorFM: a general-purpose foundation model for wearable health data

ME AI News, Google Research has released SensorFM, a large-scale foundation model pre-trained on over 100 trillion minutes of multimodal sensor data from 5 million consenting participants across over 100 countries and over 20 models of Fitbit and Pixel Watch devices. SensorFM learns universal human physiological representations, transferable to 35 health prediction tasks covering cardiovascular, metabolic, sleep, mental health, and lifestyle domains, supporting efficient label adaptation and data imputation, and can serve as a foundational tool for personal health agents. This model aims to address the issue that traditional wearable health models target a single endpoint and are difficult to generalize. 🔗 Read original: via AI HOT ·
View Original
This page may contain third-party content, which is provided for information purposes only (not representations/warranties) and should not be considered as an endorsement of its views by Gate, nor as financial or professional advice. See Disclaimer for details.
  • Reward
  • Comment
  • Repost
  • Share
Comment
Add a comment
Add a comment
No comments
  • Pinned