Representation Learning of Daily Movement Data Using Text Encoders

TL;DR

This paper introduces a novel method for representing daily movement data from dementia patients by converting activities into text and using language models to generate meaningful embeddings, enabling personalized healthcare insights.

Contribution

The study proposes a text-based encoding approach for time-series activity data, leveraging language models to improve clustering and deviation detection in healthcare monitoring.

Findings

Effective clustering of participant activity patterns

Identification of activity deviations for personalized care

Enhanced data searchability using vector embeddings

Abstract

Time-series representation learning is a key area of research for remote healthcare monitoring applications. In this work, we focus on a dataset of recordings of in-home activity from people living with Dementia. We design a representation learning method based on converting activity to text strings that can be encoded using a language model fine-tuned to transform data from the same participants within a $30$-day window to similar embeddings in the vector space. This allows for clustering and vector searching over participants and days, and the identification of activity deviations to aid with personalised delivery of care.