George Netscher

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2016-204

December 15, 2016

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-204.pdf

In this report, we discuss a project beginning August 2014 and ending in December 2016 through which four applications of machine learning to dementia care were explored. The purpose of this project was to determine how advances in machine learning could be applied to commercially available off-the-shelf sensing equipment to make a positive impact in care for individuals with Alzheimer’s disease and related dementias (ADRD), a cause personally important to the author and the research advisor. The project will be discussed for an audience familiar with the state-of-the-art in machine learning but unfamiliar with the open problems in dementia care. The first chapter gives background on Alzheimer’s disease and the context for the current work in terms of the current challenges faced by the Alzheimer’s research community. The following four chapters each discuss one application. The first discusses how a wearable system can be designed to support daily monitoring of individuals affected by Alzheimer’s disease to study functional changes which can occur as the disease progresses. The second discusses how analysis of speech can be used to detect the presence of dementia. The third discusses how video monitoring can be used to detect safety-critical events with a particular focus on falls. The fourth provides preliminary pilot study results from the application of video monitoring in one 40-resident memory care community. The final chapter concludes by discussing the gaps between the available technology and the current needs and poses suggestions for future work to bridge the gaps.

Advisors: Alexandre Bayen and Trevor Darrell

---

BibTeX citation:

@mastersthesis{Netscher:EECS-2016-204,
    Author= {Netscher, George},
    Title= {Applications of Machine Learning to Support Dementia Care through Commercially Available Off-the-Shelf Sensing},
    School= {EECS Department, University of California, Berkeley},
    Year= {2016},
    Month= {Dec},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-204.html},
    Number= {UCB/EECS-2016-204},
    Abstract= {In this report, we discuss a project beginning August 2014 and ending in December 2016 through which four applications of machine learning to dementia care were explored. The purpose of this project was to determine how advances in machine learning could be applied to commercially available off-the-shelf sensing equipment to make a positive impact in care for individuals with Alzheimer’s disease and related dementias (ADRD), a cause personally important to the author and the research advisor. The project will be discussed for an audience familiar with the state-of-the-art in machine learning but unfamiliar with the open problems in dementia care. The first chapter gives background on Alzheimer’s disease and the context for the current work in terms of the current challenges faced by the Alzheimer’s research community. The following four chapters each discuss one application. The first discusses how a wearable system can be designed to support daily monitoring of individuals affected by Alzheimer’s disease to study functional changes which can occur as the disease progresses. The second discusses how analysis of speech can be used to detect the presence of dementia. The third discusses how video monitoring can be used to detect safety-critical events with a particular focus on falls. The fourth provides preliminary pilot study results from the application of video monitoring in one 40-resident memory care community. The final chapter concludes by discussing the gaps between the available technology and the current needs and poses suggestions for future work to bridge the gaps.},
}

EndNote citation:

%0 Thesis
%A Netscher, George 
%T Applications of Machine Learning to Support Dementia Care through Commercially Available Off-the-Shelf Sensing
%I EECS Department, University of California, Berkeley
%D 2016
%8 December 15
%@ UCB/EECS-2016-204
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2016/EECS-2016-204.html
%F Netscher:EECS-2016-204