Creating a behavioural classification module for acceleration data

Using a captive surrogate for difficult to observe species

Hamish Campbell, Lianli Gao, Owen R Bidder, Jane Hunter, Craig Franklin

Research output: Contribution to journalArticleResearchpeer-review

9 Downloads (Pure)

Abstract

Distinguishing specific behavioural modes from data collected by animal-borne tri-axial accelerometers can be a time-consuming and subjective process. Data synthesis can be further inhibited when the tri-axial acceleration data cannot be paired with the corresponding behavioural mode through direct observation. Here, we explored the use of a tame surrogate (domestic dog) to build a behavioural classification module, and then used that module to accurately identify and quantify behavioural modes within acceleration collected from other individuals/species. Tri-axial acceleration data were recorded from a domestic dog whilst it was commanded to walk, run, sit, stand and lie-down. Through video synchronisation, each tri-axial acceleration sample was annotated with its associated behavioural mode; the feature vectors were extracted and used to build the classification module through the application of support vector machines (SVMs). This behavioural classification module was then used to identify and quantify the same behavioural modes in acceleration collected from a range of other species (alligator, badger, cheetah, dingo, echidna, kangaroo and wombat). Evaluation of the module performance, using a binary classification system, showed there was a high capacity (>90%) for behaviour recognition between individuals of the same species. Furthermore, a positive correlation existed between SVM capacity and the similarity of the individual’s spinal length-to-height above the ground ratio (SL:SH) to that of the surrogate. The study describes how to build a behavioural classification module and highlights the value of using a surrogate for studying cryptic, rare or endangered species.
Original languageEnglish
Pages (from-to)4501-4506
Number of pages6
JournalJournal of Experimental Biology
Volume216
Issue number24
DOIs
Publication statusPublished - 2013
Externally publishedYes

Fingerprint

taxonomy
Echidna
Acinonyx
Tachyglossidae
Dogs
dingoes
Mustelidae
Alligators and Crocodiles
Macropodidae
Acinonyx jubatus
Endangered Species
alligators
badgers
dogs
accelerometer
rare species
endangered species
Observation
synthesis
animal

Cite this

@article{85d00c4977f74e3ba43734656efa4dd6,
title = "Creating a behavioural classification module for acceleration data: Using a captive surrogate for difficult to observe species",
abstract = "Distinguishing specific behavioural modes from data collected by animal-borne tri-axial accelerometers can be a time-consuming and subjective process. Data synthesis can be further inhibited when the tri-axial acceleration data cannot be paired with the corresponding behavioural mode through direct observation. Here, we explored the use of a tame surrogate (domestic dog) to build a behavioural classification module, and then used that module to accurately identify and quantify behavioural modes within acceleration collected from other individuals/species. Tri-axial acceleration data were recorded from a domestic dog whilst it was commanded to walk, run, sit, stand and lie-down. Through video synchronisation, each tri-axial acceleration sample was annotated with its associated behavioural mode; the feature vectors were extracted and used to build the classification module through the application of support vector machines (SVMs). This behavioural classification module was then used to identify and quantify the same behavioural modes in acceleration collected from a range of other species (alligator, badger, cheetah, dingo, echidna, kangaroo and wombat). Evaluation of the module performance, using a binary classification system, showed there was a high capacity (>90{\%}) for behaviour recognition between individuals of the same species. Furthermore, a positive correlation existed between SVM capacity and the similarity of the individual’s spinal length-to-height above the ground ratio (SL:SH) to that of the surrogate. The study describes how to build a behavioural classification module and highlights the value of using a surrogate for studying cryptic, rare or endangered species.",
author = "Hamish Campbell and Lianli Gao and Bidder, {Owen R} and Jane Hunter and Craig Franklin",
year = "2013",
doi = "10.1242/jeb.089805",
language = "English",
volume = "216",
pages = "4501--4506",
journal = "Journal of Experimental Biology",
issn = "0022-0949",
publisher = "The Company of Biologists",
number = "24",

}

Creating a behavioural classification module for acceleration data : Using a captive surrogate for difficult to observe species. / Campbell, Hamish; Gao, Lianli; Bidder, Owen R; Hunter, Jane; Franklin, Craig.

In: Journal of Experimental Biology, Vol. 216, No. 24, 2013, p. 4501-4506.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Creating a behavioural classification module for acceleration data

T2 - Using a captive surrogate for difficult to observe species

AU - Campbell, Hamish

AU - Gao, Lianli

AU - Bidder, Owen R

AU - Hunter, Jane

AU - Franklin, Craig

PY - 2013

Y1 - 2013

N2 - Distinguishing specific behavioural modes from data collected by animal-borne tri-axial accelerometers can be a time-consuming and subjective process. Data synthesis can be further inhibited when the tri-axial acceleration data cannot be paired with the corresponding behavioural mode through direct observation. Here, we explored the use of a tame surrogate (domestic dog) to build a behavioural classification module, and then used that module to accurately identify and quantify behavioural modes within acceleration collected from other individuals/species. Tri-axial acceleration data were recorded from a domestic dog whilst it was commanded to walk, run, sit, stand and lie-down. Through video synchronisation, each tri-axial acceleration sample was annotated with its associated behavioural mode; the feature vectors were extracted and used to build the classification module through the application of support vector machines (SVMs). This behavioural classification module was then used to identify and quantify the same behavioural modes in acceleration collected from a range of other species (alligator, badger, cheetah, dingo, echidna, kangaroo and wombat). Evaluation of the module performance, using a binary classification system, showed there was a high capacity (>90%) for behaviour recognition between individuals of the same species. Furthermore, a positive correlation existed between SVM capacity and the similarity of the individual’s spinal length-to-height above the ground ratio (SL:SH) to that of the surrogate. The study describes how to build a behavioural classification module and highlights the value of using a surrogate for studying cryptic, rare or endangered species.

AB - Distinguishing specific behavioural modes from data collected by animal-borne tri-axial accelerometers can be a time-consuming and subjective process. Data synthesis can be further inhibited when the tri-axial acceleration data cannot be paired with the corresponding behavioural mode through direct observation. Here, we explored the use of a tame surrogate (domestic dog) to build a behavioural classification module, and then used that module to accurately identify and quantify behavioural modes within acceleration collected from other individuals/species. Tri-axial acceleration data were recorded from a domestic dog whilst it was commanded to walk, run, sit, stand and lie-down. Through video synchronisation, each tri-axial acceleration sample was annotated with its associated behavioural mode; the feature vectors were extracted and used to build the classification module through the application of support vector machines (SVMs). This behavioural classification module was then used to identify and quantify the same behavioural modes in acceleration collected from a range of other species (alligator, badger, cheetah, dingo, echidna, kangaroo and wombat). Evaluation of the module performance, using a binary classification system, showed there was a high capacity (>90%) for behaviour recognition between individuals of the same species. Furthermore, a positive correlation existed between SVM capacity and the similarity of the individual’s spinal length-to-height above the ground ratio (SL:SH) to that of the surrogate. The study describes how to build a behavioural classification module and highlights the value of using a surrogate for studying cryptic, rare or endangered species.

UR - http://www.scopus.com/inward/record.url?scp=84890683671&partnerID=8YFLogxK

U2 - 10.1242/jeb.089805

DO - 10.1242/jeb.089805

M3 - Article

VL - 216

SP - 4501

EP - 4506

JO - Journal of Experimental Biology

JF - Journal of Experimental Biology

SN - 0022-0949

IS - 24

ER -