Extracting patterns from large movement data sets using hybrid spatio-temporal filtering: a case study of geovisual analytics in support of fisheries enforcement activities

Enguehard, René A. (2012) Extracting patterns from large movement data sets using hybrid spatio-temporal filtering: a case study of geovisual analytics in support of fisheries enforcement activities. Masters thesis, Memorial University of Newfoundland.

[English] PDF (Migrated (PDF/A Conversion) from original format: (application/pdf)) - Accepted Version Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. Download (38MB) [English] PDF - Accepted Version Available under License - The author retains copyright ownership and moral rights in this thesis. Neither the thesis nor substantial extracts from it may be printed or otherwise reproduced without the author's permission. (Original Version)

Abstract

The ubiquitous nature of location tracking technologies has resulted in an increase in movement data being collected. These data are used in many contexts, such as understanding animal migration, aiding in fisheries enforcement, or managing fleets of taxicabs. Such large volumes of data call for more efficient data visualization and analysis methods. This research provides a general approach to the analysis of movement data, named Hybrid Spatio-temporal Filtering (HSF), which allows analysts to filter data based on characteristics of movement within a geovisual analytics environment. Filtering signatures are defined by combining movement path complexity (fractal dimension) and velocity, to extract behavioural patterns from data sets. An evaluation within a fisheries enforcement case study (using VMS data), and comparison to other approaches, confirmed the approach is useful, easy to use, and superior to some other approaches. This research demonstrates the value of signature-building filtering approaches for large movement data sets.

Actions (login required)

View Item