Please use this identifier to cite or link to this item: http://arks.princeton.edu/ark:/88435/dsp016q182k24s
DC FieldValueLanguage
dc.contributor.authorStouffer, Kaitlin-
dc.date.accessioned2013-07-26T16:07:31Z-
dc.date.available2013-07-26T16:07:31Z-
dc.date.created2013-05-06-
dc.date.issued2013-07-26-
dc.identifier.urihttp://arks.princeton.edu/ark:/88435/dsp016q182k24s-
dc.description.abstractWith 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.en_US
dc.format.extent41 pagesen_US
dc.language.isoen_USen_US
dc.titleM.O.M: My Own Map HMM Techniques for Predicting Wandering in Alzheimer’s and Dementia Patientsen_US
dc.typePrinceton University Senior Theses-
pu.date.classyear2013en_US
pu.departmentComputer Scienceen_US
pu.pdf.coverpageSeniorThesisCoverPage-
dc.rights.accessRightsWalk-in Access. This thesis can only be viewed on computer terminals at the <a href=http://mudd.princeton.edu>Mudd Manuscript Library</a>.-
pu.mudd.walkinyes-
Appears in Collections:Computer Science, 1988-2020

Files in This Item:
File SizeFormat