JAABA: interactive machine learning for automatic annotation of animal behavior.
Nat Methods
; 10(1): 64-7, 2013 Jan.
Article
en En
| MEDLINE
| ID: mdl-23202433
ABSTRACT
We 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.
Texto completo:
1
Colección:
01-internacional
Banco de datos:
MEDLINE
Asunto principal:
Conducta Animal
/
Algoritmos
/
Inteligencia Artificial
/
Diagnóstico por Computador
/
Drosophila melanogaster
/
Larva
Tipo de estudio:
Diagnostic_studies
Límite:
Animals
Idioma:
En
Revista:
Nat Methods
Asunto de la revista:
TECNICAS E PROCEDIMENTOS DE LABORATORIO
Año:
2013
Tipo del documento:
Article
País de afiliación:
Estados Unidos