BibTex format
@article{Rezvani,
author = {Rezvani, R and Kouchaki, S and Nilforooshan, R and Sharp, DJ and Barnaghi, P},
title = {Semi-supervised Learning for Identifying the Likelihood of Agitation in People with Dementia},
url = {http://arxiv.org/abs/2105.10398v1},
}
RIS format (EndNote, RefMan)
TY - JOUR
AB - Interpreting the environmental, behavioural and psychological data fromin-home sensory observations and measurements can provide valuable insightsinto the health and well-being of individuals. Presents of neuropsychiatric andpsychological symptoms in people with dementia have a significant impact ontheir well-being and disease prognosis. Agitation in people with dementia canbe due to many reasons such as pain or discomfort, medical reasons such as sideeffects of a medicine, communication problems and environment. This paperdiscusses a model for analysing the risk of agitation in people with dementiaand how in-home monitoring data can support them. We proposed a semi-supervisedmodel which combines a self-supervised learning model and a Bayesian ensembleclassification. We train and test the proposed model on a dataset from aclinical study. The dataset was collected from sensors deployed in 96 homes ofpatients with dementia. The proposed model outperforms the state-of-the-artmodels in recall and f1-score values by 20%. The model also indicates bettergeneralisability compared to the baseline models.
AU - Rezvani,R
AU - Kouchaki,S
AU - Nilforooshan,R
AU - Sharp,DJ
AU - Barnaghi,P
TI - Semi-supervised Learning for Identifying the Likelihood of Agitation in People with Dementia
UR - http://arxiv.org/abs/2105.10398v1
ER -
