Header

UZH-Logo

Maintenance Infos

Capability of movement features extracted from GPS trajectories for the classification of fine-grained behaviors


Soleymani, Ali; van Loon, Emiel E; Weibel, Robert (2014). Capability of movement features extracted from GPS trajectories for the classification of fine-grained behaviors. In: 17th AGILE Conference on Geographic Information Science, Castellón, Spain, 3 June 2014 - 6 June 2014.

Abstract

Recent advances in tracking technologies provide an unprecedented opportunity for a better understanding of animal movement. Data from multiple sensors can be used to capture crucial factors deriving the behaviors of the animal. Typically, accelerometer data is used to describe and classify fine-grained behaviors, while GPS data are rather used to identify more large-scale mobility patterns. In this study, however, the main research question was to what extent fine-grained foraging behaviors of wading birds can be classified from GPS tracking data alone. The species used in this study was the Eurasian Oystercatcher, Haematopus ostralegus. First, a supervised classification approach is employed based on parameters extracted from accelerometer data to identify and label different behavioral categories. Then, we seek to establish how movement parameters, computed from GPS trajectories, can identify the previously labeled behaviors. A decision tree was developed to see which movement features specifically contribute to predicting foraging. The methods used in this study suggest that it is possible to extract, with high accuracy, fine-grained behaviors based on high-resolution GPS data, providing an opportunity to build a prediction model in cases where no additional sensor or observational data on behavior is available. The key to success, however, is a careful selection of the movement features used in the classification process, including cross-scale analysis.

Abstract

Recent advances in tracking technologies provide an unprecedented opportunity for a better understanding of animal movement. Data from multiple sensors can be used to capture crucial factors deriving the behaviors of the animal. Typically, accelerometer data is used to describe and classify fine-grained behaviors, while GPS data are rather used to identify more large-scale mobility patterns. In this study, however, the main research question was to what extent fine-grained foraging behaviors of wading birds can be classified from GPS tracking data alone. The species used in this study was the Eurasian Oystercatcher, Haematopus ostralegus. First, a supervised classification approach is employed based on parameters extracted from accelerometer data to identify and label different behavioral categories. Then, we seek to establish how movement parameters, computed from GPS trajectories, can identify the previously labeled behaviors. A decision tree was developed to see which movement features specifically contribute to predicting foraging. The methods used in this study suggest that it is possible to extract, with high accuracy, fine-grained behaviors based on high-resolution GPS data, providing an opportunity to build a prediction model in cases where no additional sensor or observational data on behavior is available. The key to success, however, is a careful selection of the movement features used in the classification process, including cross-scale analysis.

Statistics

Altmetrics

Downloads

84 downloads since deposited on 19 Nov 2014
47 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Conference or Workshop Item (Paper), not refereed, original work
Communities & Collections:07 Faculty of Science > Institute of Geography
Dewey Decimal Classification:910 Geography & travel
Language:English
Event End Date:6 June 2014
Deposited On:19 Nov 2014 16:58
Last Modified:16 Aug 2017 00:42
Publisher:AGILE
ISBN:978-90-816960-4-3
Official URL:http://www.agile-online.org/Conference_Paper/cds/agile_2014/agile2014_150.pdf

Download

Preview Icon on Download
Preview
Content: Published Version
Language: English
Filetype: PDF
Size: 479kB

TrendTerms

TrendTerms displays relevant terms of the abstract of this publication and related documents on a map. The terms and their relations were extracted from ZORA using word statistics. Their timelines are taken from ZORA as well. The bubble size of a term is proportional to the number of documents where the term occurs. Red, orange, yellow and green colors are used for terms that occur in the current document; red indicates high interlinkedness of a term with other terms, orange, yellow and green decreasing interlinkedness. Blue is used for terms that have a relation with the terms in this document, but occur in other documents.
You can navigate and zoom the map. Mouse-hovering a term displays its timeline, clicking it yields the associated documents.

Author Collaborations