Vis enkel innførsel

dc.contributor.authorVabø, Rune
dc.contributor.authorMoen, Endre
dc.contributor.authorSmolinski, Szymon
dc.contributor.authorHusebø, Åse
dc.contributor.authorHandegard, Nils Olav
dc.contributor.authorMalde, Ketil
dc.date.accessioned2021-12-02T10:37:01Z
dc.date.available2021-12-02T10:37:01Z
dc.date.created2021-11-30T10:44:08Z
dc.date.issued2021
dc.identifier.citationEcological Informatics. 2021, .en_US
dc.identifier.issn1574-9541
dc.identifier.urihttps://hdl.handle.net/11250/2832540
dc.description.abstractFor several fish species, age and other important biological information is manually inferred from visual scrutinization of scales, and reliable automatic methods are not widely available. Here, we apply Convolutional Neural Networks (CNN) with transfer learning on a novel dataset of 9056 images of Atlantic salmon scales for four different prediction tasks. We predicted fish origin (wild/farmed), spawning history (previous spawner/non-spawner), river age, and sea age. We obtained high prediction accuracy for fish origin (96.70%), spawning history (96.40%), and sea age (86.99%), but lower accuracy for river age (63.20%). Against six human expert readers with an additional dataset of 150 scales, the CNN showed the second-highest percentage agreement for sea age (94.00%, range 87.25±97.30%), but the lowest agreement for river age (66.00%, range 66.00– 84.68%). Estimates of river age by expert readers exhibited higher variance and lower levels of agreement compared to sea age and may indicate why this task is also more difficult for the CNN. Automatic interpretation of scales may provide a cost- and time-efficient method of predicting fish age and life-history traits.en_US
dc.language.isoengen_US
dc.titleAutomatic interpretation of salmon scales using deep learningen_US
dc.typePeer revieweden_US
dc.typeJournal articleen_US
dc.description.versionpublishedVersionen_US
dc.source.pagenumber10en_US
dc.source.journalEcological Informaticsen_US
dc.identifier.doi10.1016/j.ecoinf.2021.101322
dc.identifier.cristin1961489
dc.relation.projectNorges forskningsråd: 270966en_US
cristin.ispublishedtrue
cristin.fulltextoriginal
cristin.qualitycode1


Tilhørende fil(er)

Thumbnail

Denne innførselen finnes i følgende samling(er)

Vis enkel innførsel