Pedestrian route prediction from GPS logs /
Files
(Published version)
Date
2012
Authors
Smith, Gavin,
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
thesis
Citation
Statement of Responsibility
Conference Name
Abstract
Pedestrian movement prediction and in particular, route prediction, can provide valuable information to location-aware services, enabling, for instance, ahead-of-time notifications specific to the route, data preparation and efficient pre-fetching and data caching. Predicting human movement, however, is a complex task and this thesis extends state- of-the-art in a promising approach, namely prediction based on the construction and application of statistical models and data mining techniques to large volumes of historic mobility traces. Such data is rapidly becoming available in vast quantities, with movement data able to be contributed back by a growing number of location-aware consumer devices such as smart phones.
School/Discipline
University of South Australia. School of Computer and Information Science
School of Computer and Information Science
School of Computer and Information Science
Dissertation Note
Thesis (PhD)--University of South Australia, 2012.
Provenance
Copyright 2012 Gavin Smith. This work is made available under the Creative Commons Attribution-NonCommercial-NoDerivs Australia 3.0 licence (http://creativecommons.org/licenses/by-nc-nd/3.0/au/)
Description
vi, 251 leaves :
illustrations (chiefly colour).
Includes bibliographic references.
illustrations (chiefly colour).
Includes bibliographic references.
Access Status
506 0#$fstar $2Unrestricted online access