Local alignment applied to grizzly bear gps tracking data

Date
2012
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Recent advances in GPS collar technologies for Grizzly bear tracking have produced a drastic increase in the volume of data available for scientific analysis. Machine learning methods seem suited to process this ever-increasing volume of data. Comprehensive understanding of the datasets, machine learning methods and similarity measures is fundamental for research of this kind. To automatically detect frequent movement patterns, the current work implemented three machine learning methods, a Location-Based Services (LBS), a simulated annealing, and a hybrid local alignment approach. Several dataset segmentations were tested to reduce the amount of calculations for similarity measures, without losing relevant data relationships. Mostly based on my fifteen yea.rs of professional experience in the industry of data.base administration and development, I found the current state of commercial data.base manĀ­agement systems (DBMS) mature enough to conduct fully integrated implementations. In my judgment, that assumption was validated by the results of the local alignment method.
Description
Bibliography: p. 145-175
A few pages are in colour.
Keywords
Citation
Ortiz Villagomez, A. R. (2012). Local alignment applied to grizzly bear gps tracking data (Master's thesis, University of Calgary, Calgary, Canada). Retrieved from https://prism.ucalgary.ca. doi:10.11575/PRISM/4739
Collections