Skip navigation
Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp016q182k24s
Title: M.O.M: My Own Map HMM Techniques for Predicting Wandering in Alzheimer’s and Dementia Patients
Authors: Stouffer, Kaitlin
Advisors: Martonosi, Margaret
Department: Computer Science
Class Year: 2013
Abstract: With the number of people suffering from Alzheimer’s Disease and Dementia expected to grow over the next couple decades, the need for assistive technologies to help promote their independent living is both imperative and imminent. Here, I focus specifically on the issue of wandering in these patients and propose the basis for a mobile application that could predict when they are wandering. I describe an approach to wandering prediction that involves the use of Hidden Markov Model (HMM) variants to encapsulate movement patterns and distinguish low probability movement sequences as wandering. Specifically, I consider a physics based HMM utilizing both speed and directional information to model movement and an HMM that models movement trajectories with smooth, polynomial curves. I describe the overall structure of these variants and evaluate their performance on both artificial GPS data logs as well as those taken from a real individual.
Extent: 41 pages
URI: http://arks.princeton.edu/ark:/88435/dsp016q182k24s
Access Restrictions: Walk-in Access. This thesis can only be viewed on computer terminals at the Mudd Manuscript Library.
Type of Material: Princeton University Senior Theses
Language: en_US
Appears in Collections:Computer Science, 1988-2016

Files in This Item:
File SizeFormat 
Kaitlin Stouffer.pdf3.79 MBAdobe PDF    Request a copy


Items in Dataspace are protected by copyright, with all rights reserved, unless otherwise indicated.