Mobility Modelling through Trajectory Decomposition and Prediction

Show full item record

Permalink

http://urn.fi/URN:NBN:fi-fe2017112251774
Title: Mobility Modelling through Trajectory Decomposition and Prediction
Author: Faghihi, Farbod
Contributor: University of Helsinki, Faculty of Science, Department of Computer Science
Thesis level: master's thesis
Abstract: The ubiquity of mobile devices with positioning sensors make it possible to derive user's location at any time. However, constantly sensing the position in order to track the user's movement is not feasible, either due to the unavailability of sensors, or computational and storage burdens. In this thesis, we present and evaluate a novel approach for efficiently tracking user's movement trajectories using decomposition and prediction of trajectories. We facilitate tracking by taking advantage of regularity within the movement trajectories. The evaluation of our approach is done using three large-scale spatio-temporal datasets, from three different cities: San Francisco, Porto, and Beijing. Two of these datasets contain only cab traces and one contains all modes of transportation. Therefore, our approach is solely dependent on the inherent regularity within the trajectories regardless of the city or transportation mode.
URI: URN:NBN:fi-fe2017112251774
http://hdl.handle.net/10138/209604
Date: 2017
Subject: trajectory prediction
trajectory analysis
human mobility
mobility modelling
Discipline: Algorithms and Machine Learning
Algorithms and Machine Learning
Algorithms and Machine Learning


Files in this item

Total number of downloads: Loading...

Files Size Format View Description
Farbod_MScThesis.pdf 18.88Mb PDF View/Open pro gradu

This item appears in the following Collection(s)

Show full item record