Show simple item record

dc.contributor.advisorDavenport, Mark
dc.contributor.authorBranham, Sara M.
dc.date.accessioned2020-11-09T17:01:45Z
dc.date.available2020-11-09T17:01:45Z
dc.date.created2020-08
dc.date.submittedAugust 2020
dc.identifier.urihttp://hdl.handle.net/1853/63904
dc.description.abstractGPS collection has become increasingly popular with the rise of mobile devices and applications. This data is collected for an incredibly wide range of reasons, including applications like Google Maps providing directions, weather applications providing weather predictions, Uber or Lyft providing transportation, or service providers seeking to better understand their users. While GPS data has many uses in our society, there exist enormous obstacles surrounding long term data collection, namely how to acquire uniformly sampled device data. We propose using Transformers and GRUs with added Attention to extract long term habits for individual users in the context of nonuniform GPS data. These models are traditionally used for Neural Machine Translation (NMT), so they are well equipped for nonuniform problem spaces.
dc.format.mimetypeapplication/pdf
dc.publisherGeorgia Institute of Technology
dc.subjectTransformers
dc.subjectTrajectory prediction
dc.subjectSparse GPS prediction
dc.subjectGRUs
dc.subjectAttention
dc.titleTrajectory Prediction for Nonuniform Geospatial Mobile Device Data
dc.typeUndergraduate Research Option Thesis
dc.description.degreeUndergraduate
dc.contributor.departmentComputer Science
dc.contributor.departmentComputer Science
dc.contributor.committeeMemberKonda, Roshan
dc.contributor.committeeMemberAhad, Nauman
dc.date.updated2020-11-09T17:01:45Z


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record