Studying from a trillion minutes of sensor knowledge
To construct the pre-training corpus, we sampled de-identified knowledge from 5 million individuals who had consented to using their knowledge for well being and wellness analysis, captured between September 2024 and September 2025. The dataset spans greater than 100 nations, all 50 U.S. states, and over 20 Fitbit and Pixel Watch gadget fashions. From every individual we drew a number of weeks of knowledge, yielding over two billion hours — greater than a trillion minutes — of minute-resolution indicators.
SensorFM ingests 34 one-minute combination options derived from 5 sensor modalities: photoplethysmography (PPG), accelerometry, electrodermal exercise (EDA), pores and skin temperature, and altimetry. Collectively these seize coronary heart fee and heart-rate variability, blood-oxygen saturation, sleep levels, movement and steps, pores and skin conductance, and temperature over a full 24-hour window.
Reasonably than counting on labels, SensorFM learns by self-supervised reconstruction, constructing on the LSM-2 strategy and its Adaptive and Inherited Masking (AIM) framework. This can be a essential design alternative, as a result of lacking and fragmented knowledge (e.g., stretches of time the place knowledge will not be accessible) is the norm with wearable units, brought on by quite a lot of elements similar to sensors’ power-cycle, units coming off the wrist, energy saving modes of operation, and sensors switching on and off. Typical self-supervised strategies assume full, uninterrupted inputs and so are pressured to both impute the gaps (which might introduce bias) or discard incomplete home windows (which throws away invaluable knowledge). AIM takes neither path: it treats real-world missingness as a pure artifact and learns immediately from incomplete recordings, combining the tokens inherited from real gaps with these artificially masked for the reconstruction goal and treating the 2 as equal. The result’s a illustration that’s missingness-aware by building. SensorFM doesn’t simply tolerate fragmented knowledge, it makes use of it productively, because the generative outcomes under present.