Two-Stage Representation Learning for Analyzing Movement Behavior Dynamics in People Living with Dementia

Jin Cui, Alexander Capstick, Payam Barnaghi, Gregory Scott

Keywords: Time series representation learning, Remote healthcare monitoring, Dementia, Two-stage transformational learning, Personalized care interventions

TL;DR: This paper presents a novel two-stage approach using language models and PageRank to analyze time-series data from dementia patients' daily activities.

Abstract: In remote healthcare monitoring, time series representation learning reveals critical patient behavior patterns from high-frequency data. This study analyzes home activity data from individuals living with dementia by proposing a two-stage, self-supervised learning approach tailored to uncover low-rank structures. The first stage converts time-series activities into text sequences encoded by a pre-trained language model, providing a rich, high-dimensional representation. In the second stage, these vectors are transformed into a low-dimensional latent state space using a PageRank-based method. This PageRank vector captures latent state transitions, effectively compressing complex behavior data into a succinct form that enhances model interpretability. This low-rank representation not only enhances interpretability but also facilitates clustering and transition analysis, revealing key behavioral patterns correlated with clinical metrics such as MMSE and ADAS-Cog scores. Our findings demonstrate the framework’s potential in supporting cognitive status prediction, personalized care interventions, and large-scale health monitoring.

Submission Number: 12