A Vocal-Based Analytical Method for Goose Behaviour Recognition
Since human-wildlife conflicts are increasing, the development of cost-effective methods for reducing damage or conflict levels is important in wildlife management. A wide range of devices to detect and deter animals causing conflict are used for this purpose, although their effectiveness is often h...
Published in: | Sensors |
---|---|
Main Authors: | , , , |
Format: | Text |
Language: | English |
Published: |
Molecular Diversity Preservation International
2012
|
Subjects: | |
Online Access: | https://doi.org/10.3390/s120303773 |
id |
ftmdpi:oai:mdpi.com:/1424-8220/12/3/3773/ |
---|---|
record_format |
openpolar |
spelling |
ftmdpi:oai:mdpi.com:/1424-8220/12/3/3773/ 2023-08-20T04:05:41+02:00 A Vocal-Based Analytical Method for Goose Behaviour Recognition Kim Arild Steen Ole Roland Therkildsen Henrik Karstoft Ole Green 2012-03-21 application/pdf https://doi.org/10.3390/s120303773 EN eng Molecular Diversity Preservation International Physical Sensors https://dx.doi.org/10.3390/s120303773 https://creativecommons.org/licenses/by/3.0/ Sensors; Volume 12; Issue 3; Pages: 3773-3788 support vector machines goose behaviour pattern recognition vocalisations GFCC Text 2012 ftmdpi https://doi.org/10.3390/s120303773 2023-07-31T20:28:30Z Since human-wildlife conflicts are increasing, the development of cost-effective methods for reducing damage or conflict levels is important in wildlife management. A wide range of devices to detect and deter animals causing conflict are used for this purpose, although their effectiveness is often highly variable, due to habituation to disruptive or disturbing stimuli. Automated recognition of behaviours could form a critical component of a system capable of altering the disruptive stimuli to avoid this. In this paper we present a novel method to automatically recognise goose behaviour based on vocalisations from flocks of free-living barnacle geese (Branta leucopsis). The geese were observed and recorded in a natural environment, using a shielded shotgun microphone. The classification used Support Vector Machines (SVMs), which had been trained with labeled data. Greenwood Function Cepstral Coefficients (GFCC) were used as features for the pattern recognition algorithm, as they can be adjusted to the hearing capabilities of different species. Three behaviours are classified based in this approach, and the method achieves a good recognition of foraging behaviour (86–97% sensitivity, 89–98% precision) and a reasonable recognition of flushing (79–86%, 66–80%) and landing behaviour(73–91%, 79–92%). The Support Vector Machine has proven to be a robust classifier for this kind of classification, as generality and non-linearcapabilities are important. We conclude that vocalisations can be used to automatically detect behaviour of conflict wildlife species, and as such, may be used as an integrated part of awildlife management system. Text Branta leucopsis MDPI Open Access Publishing Sensors 12 3 3773 3788 |
institution |
Open Polar |
collection |
MDPI Open Access Publishing |
op_collection_id |
ftmdpi |
language |
English |
topic |
support vector machines goose behaviour pattern recognition vocalisations GFCC |
spellingShingle |
support vector machines goose behaviour pattern recognition vocalisations GFCC Kim Arild Steen Ole Roland Therkildsen Henrik Karstoft Ole Green A Vocal-Based Analytical Method for Goose Behaviour Recognition |
topic_facet |
support vector machines goose behaviour pattern recognition vocalisations GFCC |
description |
Since human-wildlife conflicts are increasing, the development of cost-effective methods for reducing damage or conflict levels is important in wildlife management. A wide range of devices to detect and deter animals causing conflict are used for this purpose, although their effectiveness is often highly variable, due to habituation to disruptive or disturbing stimuli. Automated recognition of behaviours could form a critical component of a system capable of altering the disruptive stimuli to avoid this. In this paper we present a novel method to automatically recognise goose behaviour based on vocalisations from flocks of free-living barnacle geese (Branta leucopsis). The geese were observed and recorded in a natural environment, using a shielded shotgun microphone. The classification used Support Vector Machines (SVMs), which had been trained with labeled data. Greenwood Function Cepstral Coefficients (GFCC) were used as features for the pattern recognition algorithm, as they can be adjusted to the hearing capabilities of different species. Three behaviours are classified based in this approach, and the method achieves a good recognition of foraging behaviour (86–97% sensitivity, 89–98% precision) and a reasonable recognition of flushing (79–86%, 66–80%) and landing behaviour(73–91%, 79–92%). The Support Vector Machine has proven to be a robust classifier for this kind of classification, as generality and non-linearcapabilities are important. We conclude that vocalisations can be used to automatically detect behaviour of conflict wildlife species, and as such, may be used as an integrated part of awildlife management system. |
format |
Text |
author |
Kim Arild Steen Ole Roland Therkildsen Henrik Karstoft Ole Green |
author_facet |
Kim Arild Steen Ole Roland Therkildsen Henrik Karstoft Ole Green |
author_sort |
Kim Arild Steen |
title |
A Vocal-Based Analytical Method for Goose Behaviour Recognition |
title_short |
A Vocal-Based Analytical Method for Goose Behaviour Recognition |
title_full |
A Vocal-Based Analytical Method for Goose Behaviour Recognition |
title_fullStr |
A Vocal-Based Analytical Method for Goose Behaviour Recognition |
title_full_unstemmed |
A Vocal-Based Analytical Method for Goose Behaviour Recognition |
title_sort |
vocal-based analytical method for goose behaviour recognition |
publisher |
Molecular Diversity Preservation International |
publishDate |
2012 |
url |
https://doi.org/10.3390/s120303773 |
genre |
Branta leucopsis |
genre_facet |
Branta leucopsis |
op_source |
Sensors; Volume 12; Issue 3; Pages: 3773-3788 |
op_relation |
Physical Sensors https://dx.doi.org/10.3390/s120303773 |
op_rights |
https://creativecommons.org/licenses/by/3.0/ |
op_doi |
https://doi.org/10.3390/s120303773 |
container_title |
Sensors |
container_volume |
12 |
container_issue |
3 |
container_start_page |
3773 |
op_container_end_page |
3788 |
_version_ |
1774716377173590016 |