Wearable sensors have become ubiquitous thanks to a variety of health tracking features. The resulting continuous and longitudinal measurements from everyday life generate large volumes of data. However, making sense of these observations for scientific and actionable insights is non-trivial. Inspired by the empirical success of generative modeling, where large neural networks learn powerful representations from vast amounts of text, image, video, or audio data, we investigate the scaling properties of wearable sensor foundation models across compute, data, and model size. Using a dataset of up to 40 million hours of in-situ heart rate, heart rate variability, accelerometer, electrodermal activity, skin temperature, and altimeter per-minute data from over 165,000 people, we create LSM, a multimodal foundation model built on the largest wearable-signals dataset with the most extensive range of sensor modalities to date. Our results establish the scaling laws of LSM for tasks such as imputation, interpolation and extrapolation across both time and sensor modalities. Moreover, we highlight how LSM enables sample-efficient downstream learning for tasks including exercise and activity recognition.

Akshay Paruchuri, Jake Garrison, Shun Liao, John B Hernandez, Jacob Sunshine, Tim Althoff, Xin Liu, Daniel McDuff. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

White noise machines are among the most popular devices to facilitate infant sleep. We introduce the first contactless system that uses white noise to achieve motion and respiratory monitoring in infants. Our system is designed for smart speakers that can monitor an infant's sleep using white noise. The key enabler underlying our system is a set of novel algorithms that can extract the minute infant breathing motion as well as position information from white noise which is random in both the time and frequency domain. We describe the design and implementation of our system, and present experiments with a life-like infant simulator as well as a clinical study at the neonatal intensive care unit with five new-born infants. Our study demonstrates that the respiratory rate computed by our system is highly correlated with the ground truth with a correlation coefficient of 0.938.

In this poster accompanying the MobiCom 2019 paper, we describes how to enable infant monitoring capability using white noise. Specifically, we design a set of novel algorithms that can extract the minute infant breathing motion as well as position information from white noise which is random in both the time and frequency domain. Our study demonstrates that the system achieves high correlation between the measured respiratory rate and the ground truth.