Repository logo
 
Publication

JAABA: interactive machine learning for automatic annotation of animal behavior

dc.contributor.authorKabra, Mayank
dc.contributor.authorRobie, Alice A
dc.contributor.authorRivera-Alba, Marta
dc.contributor.authorBranson, Steven
dc.contributor.authorBranson, Kristin
dc.date.accessioned2016-05-12T10:43:51Z
dc.date.available2016-05-12T10:43:51Z
dc.date.issued2013-01
dc.description.abstractWe present a machine learning-based system for automatically computing interpretable, quantitative measures of animal behavior. Through our interactive system, users encode their intuition about behavior by annotating a small set of video frames. These manual labels are converted into classifiers that can automatically annotate behaviors in screen-scale data sets. Our general-purpose system can create a variety of accurate individual and social behavior classifiers for different organisms, including mice and adult and larval Drosophila.pt_PT
dc.identifier.citationKabra, M., Robie, A. A., Rivera-Alba, M., Branson, S., Branson, K. (2013). JAABA: interactive machine learning for automatic annotation of animal behavior. Nat Meth, 10(1), 64–67.pt_PT
dc.identifier.doi10.1038/nmeth.2281pt_PT
dc.identifier.urihttp://hdl.handle.net/10400.7/601
dc.language.isoengpt_PT
dc.peerreviewedyespt_PT
dc.publisherNature Publishing Grouppt_PT
dc.relationNão existe menção de financiadores nem de patrocionadores no documento.pt_PT
dc.relation.publisherversionhttp://www.nature.com/nmeth/journal/v10/n1/full/nmeth.2281.htmlpt_PT
dc.subjectBehavioural methodspt_PT
dc.subjectExperimental organismspt_PT
dc.subjectMachine learningpt_PT
dc.titleJAABA: interactive machine learning for automatic annotation of animal behaviorpt_PT
dc.typejournal article
dspace.entity.typePublication
oaire.citation.endPage67pt_PT
oaire.citation.issue1pt_PT
oaire.citation.startPage64pt_PT
oaire.citation.titleNature Methodspt_PT
oaire.citation.volume10pt_PT
rcaap.rightsopenAccesspt_PT
rcaap.typearticlept_PT

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
~$braRobieJAABAManuscript_v15.docx
Size:
162 B
Format:
Microsoft Word XML
Description:
artigo principal
License bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.71 KB
Format:
Item-specific license agreed upon to submission
Description:

Collections