Abstract

The growing popularity of wearable sensors has generated large quantities of temporal physiological and activity data. Ability to analyze this data offers new opportunities for real-time health monitoring and forecasting. However, temporal physiological data presents many analytic challenges: the data is noisy, contains many missing values, and each series has a different length. Most methods proposed for time series analysis and classification do not handle datasets with these characteristics nor do they offer interpretability and explainability, a critical requirement in the health domain. We propose an unsupervised method for learning representations of time series based on common patterns identified within them. The patterns are interpretable and extracted using Byte Pair Encoding compression technique. Since the patterns are variable in length, the method can capture both long-term and short-term …

Date

November 29, 2022

Authors

Nazgol Tavabi, Kristina Lerman

Book

Multimodal AI in healthcare: A paradigm shift in health intelligence

Pages

227-243

Publisher

Springer International Publishing