Google unveils SensorFM for wearable health data

Google Research has launched SensorFM, a foundation model for wearable health data, trained on over a trillion minutes of sensor data from five million participants. This model aims to provide a general-purpose representation of human physiology, applicable to 35 health prediction tasks. SensorFM uses self-supervised learning to handle fragmented data, a common challenge with wearable devices. The model's ability to transfer across various health domains marks a shift towards more comprehensive and adaptable wearable health research.