Skip to content

Research at St Andrews

Assessing the utility and limitations of accelerometers and machine learning approaches in classifying behaviour during lactation in a phocid seal

Research output: Contribution to journalArticle

Standard

Assessing the utility and limitations of accelerometers and machine learning approaches in classifying behaviour during lactation in a phocid seal. / Schuert, Courtney; Pomeroy, Patrick; Twiss, Sean.

In: Animal Biotelemetry, Vol. 6, 14, 16.10.2018.

Research output: Contribution to journalArticle

Harvard

Schuert, C, Pomeroy, P & Twiss, S 2018, 'Assessing the utility and limitations of accelerometers and machine learning approaches in classifying behaviour during lactation in a phocid seal' Animal Biotelemetry, vol. 6, 14. https://doi.org/10.1186/s40317-018-0158-y

APA

Schuert, C., Pomeroy, P., & Twiss, S. (2018). Assessing the utility and limitations of accelerometers and machine learning approaches in classifying behaviour during lactation in a phocid seal. Animal Biotelemetry, 6, [14]. https://doi.org/10.1186/s40317-018-0158-y

Vancouver

Schuert C, Pomeroy P, Twiss S. Assessing the utility and limitations of accelerometers and machine learning approaches in classifying behaviour during lactation in a phocid seal. Animal Biotelemetry. 2018 Oct 16;6. 14. https://doi.org/10.1186/s40317-018-0158-y

Author

Schuert, Courtney ; Pomeroy, Patrick ; Twiss, Sean. / Assessing the utility and limitations of accelerometers and machine learning approaches in classifying behaviour during lactation in a phocid seal. In: Animal Biotelemetry. 2018 ; Vol. 6.

Bibtex - Download

@article{0f248f599a4c4bc186581e384fc9de41,
title = "Assessing the utility and limitations of accelerometers and machine learning approaches in classifying behaviour during lactation in a phocid seal",
abstract = "Background: Classifying behaviour with animal-borne accelerometers is quickly becoming a popular tool for remotely observing behavioural states in a variety of species. Most accelerometry work in pinnipeds has focused on classifying behaviour at sea often quantifying behavioural trade-offs associated with foraging and diving in income breeders. Very little work to date has been done to resolve behaviour during the critical period of lactation in a capital breeder. Capital breeding phocids possess finite reserves that they must allocate appropriately to maintain themselves and their new offspring during their brief nursing period. Within this short time, fine-scale behavioural trade-offs can have significant fitness consequences for mother and offspring and must be carefully managed. Here, we present a case study in extracting and classifying lactation behaviours in a wild, breeding pinniped, the grey seal (Halichoerus grypus).Results:  Using random forest models, we were able to resolve 4 behavioural states that constitute the majority of a female grey seals’ activity budget during lactation. Resting, alert, nursing, and a form of pup interaction were extracted and classified reliably. For the first time, we quantified the potential confounding variance associated with individual differences in a wild context as well as differences due to sampling location in a largely inactive model species.Conclusions:  At this stage, the majority of a female grey seal’s activity budget was classified well using accelerometers, but some rare and context-dependent behaviours were not well captured. While we did find significant variation between individuals in behavioural mechanics, individuals did not differ significantly within themselves; inter-individual variability should be an important consideration in future efforts. These methods can be extended to other efforts to study grey seals and other pinnipeds who exhibit a capital breeding system. Using accelerometers to classify behaviour during lactation allows for fine-scale assessments of time and energy trade-offs for species with fixed stores.",
keywords = "Accelerometer, Grey seal, Maternal behaviour, Breeding behaviour, Machine learning, Classification",
author = "Courtney Schuert and Patrick Pomeroy and Sean Twiss",
note = "Funding for this work was provided by the Durham Doctoral Studentship scheme at Durham University and supported by Natural Environment Research Council’s core funding to the Sea Mammal Research Unit at the University of St. Andrews.",
year = "2018",
month = "10",
day = "16",
doi = "10.1186/s40317-018-0158-y",
language = "English",
volume = "6",
journal = "Animal Biotelemetry",
issn = "2050-3385",
publisher = "BioMed Central",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Assessing the utility and limitations of accelerometers and machine learning approaches in classifying behaviour during lactation in a phocid seal

AU - Schuert, Courtney

AU - Pomeroy, Patrick

AU - Twiss, Sean

N1 - Funding for this work was provided by the Durham Doctoral Studentship scheme at Durham University and supported by Natural Environment Research Council’s core funding to the Sea Mammal Research Unit at the University of St. Andrews.

PY - 2018/10/16

Y1 - 2018/10/16

N2 - Background: Classifying behaviour with animal-borne accelerometers is quickly becoming a popular tool for remotely observing behavioural states in a variety of species. Most accelerometry work in pinnipeds has focused on classifying behaviour at sea often quantifying behavioural trade-offs associated with foraging and diving in income breeders. Very little work to date has been done to resolve behaviour during the critical period of lactation in a capital breeder. Capital breeding phocids possess finite reserves that they must allocate appropriately to maintain themselves and their new offspring during their brief nursing period. Within this short time, fine-scale behavioural trade-offs can have significant fitness consequences for mother and offspring and must be carefully managed. Here, we present a case study in extracting and classifying lactation behaviours in a wild, breeding pinniped, the grey seal (Halichoerus grypus).Results:  Using random forest models, we were able to resolve 4 behavioural states that constitute the majority of a female grey seals’ activity budget during lactation. Resting, alert, nursing, and a form of pup interaction were extracted and classified reliably. For the first time, we quantified the potential confounding variance associated with individual differences in a wild context as well as differences due to sampling location in a largely inactive model species.Conclusions:  At this stage, the majority of a female grey seal’s activity budget was classified well using accelerometers, but some rare and context-dependent behaviours were not well captured. While we did find significant variation between individuals in behavioural mechanics, individuals did not differ significantly within themselves; inter-individual variability should be an important consideration in future efforts. These methods can be extended to other efforts to study grey seals and other pinnipeds who exhibit a capital breeding system. Using accelerometers to classify behaviour during lactation allows for fine-scale assessments of time and energy trade-offs for species with fixed stores.

AB - Background: Classifying behaviour with animal-borne accelerometers is quickly becoming a popular tool for remotely observing behavioural states in a variety of species. Most accelerometry work in pinnipeds has focused on classifying behaviour at sea often quantifying behavioural trade-offs associated with foraging and diving in income breeders. Very little work to date has been done to resolve behaviour during the critical period of lactation in a capital breeder. Capital breeding phocids possess finite reserves that they must allocate appropriately to maintain themselves and their new offspring during their brief nursing period. Within this short time, fine-scale behavioural trade-offs can have significant fitness consequences for mother and offspring and must be carefully managed. Here, we present a case study in extracting and classifying lactation behaviours in a wild, breeding pinniped, the grey seal (Halichoerus grypus).Results:  Using random forest models, we were able to resolve 4 behavioural states that constitute the majority of a female grey seals’ activity budget during lactation. Resting, alert, nursing, and a form of pup interaction were extracted and classified reliably. For the first time, we quantified the potential confounding variance associated with individual differences in a wild context as well as differences due to sampling location in a largely inactive model species.Conclusions:  At this stage, the majority of a female grey seal’s activity budget was classified well using accelerometers, but some rare and context-dependent behaviours were not well captured. While we did find significant variation between individuals in behavioural mechanics, individuals did not differ significantly within themselves; inter-individual variability should be an important consideration in future efforts. These methods can be extended to other efforts to study grey seals and other pinnipeds who exhibit a capital breeding system. Using accelerometers to classify behaviour during lactation allows for fine-scale assessments of time and energy trade-offs for species with fixed stores.

KW - Accelerometer

KW - Grey seal

KW - Maternal behaviour

KW - Breeding behaviour

KW - Machine learning

KW - Classification

U2 - 10.1186/s40317-018-0158-y

DO - 10.1186/s40317-018-0158-y

M3 - Article

VL - 6

JO - Animal Biotelemetry

T2 - Animal Biotelemetry

JF - Animal Biotelemetry

SN - 2050-3385

M1 - 14

ER -

Related by author

  1. Changes in stable isotope compositions during fasting in phocid seals

    Habran, S., Damseaux, F., Pomeroy, P., Debier, C., Crocker, D., Lepoint, G. & Das, K., 30 Jan 2019, In : Rapid Communications in Mass Spectrometry. 33, 2, p. 176-184 9 p.

    Research output: Contribution to journalArticle

  2. EIRPHOT : A critical assessment of Wales’ grey seal ( Halichoerus grypus ) photo - identification database .

    Langley, I. J., Rosas Da Costa Oliver, T. V., Stringell, T., Morris, C., Hiby, L. & Pomeroy, P., 21 Jan 2019, Bangor: Natural Resources Wales. 94 p. (evidence report series; no. 280)

    Research output: Book/ReportCommissioned report

  3. Seal carrion is a predictable resource for coastal ecosystems

    Quaggiotto, M-M., Barton, P. S., Morris, C. D., Moss, S. E. W., Pomeroy, P. P., McCafferty, D. J. & Bailey, D. M., Apr 2018, In : Acta Oecologica. 88, p. 41-51 11 p.

    Research output: Contribution to journalArticle

  4. Intraseasonal temporal variation of reproductive effort for male grey seals

    Bishop, A. M., Stewart, J. E., Pomeroy, P. & Twiss, S., Dec 2017, In : Animal Behaviour. 134, p. 167-175

    Research output: Contribution to journalArticle

  5. Rapid changes in Atlantic grey seal milk from birth to weaning – immune factors and indicators of metabolic strain

    Lowe, A. D., Bawazeer, S., Watson, D. G., McGill, S., Burchmore, R. J. S., Pomeroy, P. & Kennedy, M. W., 23 Nov 2017, In : Scientific Reports. 7, 11 p., 16093.

    Research output: Contribution to journalArticle

Related by journal

  1. Animal Biotelemetry (Journal)

    Christian Rutz (Member of editorial board)
    1 Sep 2015 → …

    Activity: Publication peer-review and editorial work typesEditor of research journal

  2. Animal Biotelemetry (Journal)

    Christian Rutz (Guest editor)
    2015 → …

    Activity: Publication peer-review and editorial work typesEditor of research journal

Related by journal

  1. Automated peak detection method for behavioral event identification: detecting Balaenoptera musculus and Grampus griseus feeding attempts

    Sweeney, D. A., Deruiter, S. L., McNamara-Oh, Y. J., Marques, T. A., Arranz, P. & Calambokidis, J., 4 Apr 2019, In : Animal Biotelemetry. 7, 10 p., 7.

    Research output: Contribution to journalArticle

  2. Images as proximity sensors: the incidence of conspecific foraging in Antarctic fur seals

    Hooker, S. K., Barychka, T., Jessopp, M. J. & Staniland, I. J., 29 Sep 2015, In : Animal Biotelemetry. 3, 11 p., 37.

    Research output: Contribution to journalArticle

  3. Processing and visualising association data from animal-borne proximity loggers

    Bettaney, E., James, R., St Clair, J. & Rutz, C., 29 Aug 2015, In : Animal Biotelemetry. 3, 27.

    Research output: Contribution to journalArticle

  4. Sound production and associated behavior of tagged fin whales (Balaenoptera physalus) in the Southern California Bight

    Stimpert, A., DeRuiter, S., Falcone, E., Joseph, J., Douglas, A. B., Moretti, D. J., Friedlander, A. S., Calambokidis, J., Gailey, G., Tyack, P. L. & Goldbogen, J. A., 3 Aug 2015, In : Animal Biotelemetry. 3, 12 p., 23.

    Research output: Contribution to journalArticle

ID: 255932668