Latent Temporal Flows for Multivariate Analysis of Wearables Data
This work addresses the problem of accurate health monitoring from wearable data for healthcare applications, representing an incremental advancement with a novel method for a known bottleneck in handling high-dimensional time-series data.
The paper tackles the challenge of modeling dependent high-dimensional sensor signals from wearable devices by introducing Latent Temporal Flows, a method for multivariate time-series modeling that recovers low-dimensional latent representations and estimates a temporally-conditioned probabilistic model, resulting in at least a 10% performance improvement in multi-step forecasting benchmarks and the ability to identify cardio-respiratory fitness indicators from lower-level signals.
Increased use of sensor signals from wearable devices as rich sources of physiological data has sparked growing interest in developing health monitoring systems to identify changes in an individual's health profile. Indeed, machine learning models for sensor signals have enabled a diverse range of healthcare related applications including early detection of abnormalities, fertility tracking, and adverse drug effect prediction. However, these models can fail to account for the dependent high-dimensional nature of the underlying sensor signals. In this paper, we introduce Latent Temporal Flows, a method for multivariate time-series modeling tailored to this setting. We assume that a set of sequences is generated from a multivariate probabilistic model of an unobserved time-varying low-dimensional latent vector. Latent Temporal Flows simultaneously recovers a transformation of the observed sequences into lower-dimensional latent representations via deep autoencoder mappings, and estimates a temporally-conditioned probabilistic model via normalizing flows. Using data from the Apple Heart and Movement Study (AH&MS), we illustrate promising forecasting performance on these challenging signals. Additionally, by analyzing two and three dimensional representations learned by our model, we show that we can identify participants' $\text{VO}_2\text{max}$, a main indicator and summary of cardio-respiratory fitness, using only lower-level signals. Finally, we show that the proposed method consistently outperforms the state-of-the-art in multi-step forecasting benchmarks (achieving at least a $10\%$ performance improvement) on several real-world datasets, while enjoying increased computational efficiency.