Representation Learning of Daily Movement Data Using Text Encoders

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Capstick, Alexander, Cui, Tianyu, Chen, Yu, Barnaghi, Payam
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866910756583243776
author Capstick, Alexander
Cui, Tianyu
Chen, Yu
Barnaghi, Payam
author_facet Capstick, Alexander
Cui, Tianyu
Chen, Yu
Barnaghi, Payam
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04494
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Representation Learning of Daily Movement Data Using Text Encoders
Capstick, Alexander
Cui, Tianyu
Chen, Yu
Barnaghi, Payam
Machine Learning
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.
title Representation Learning of Daily Movement Data Using Text Encoders
topic Machine Learning
url https://arxiv.org/abs/2405.04494