skip to main content
Idioma:

R package for animal behavior classification from accelerometer data—rabc

Yu, Hui ; Klaassen, Marcel

Ecology and Evolution, 2021-09, Vol.11 (18), p.12364-12377 [Periódico revisado por pares]

England: John Wiley & Sons, Inc

Texto completo disponível

Citações Citado por
  • Título:
    R package for animal behavior classification from accelerometer data—rabc
  • Autor: Yu, Hui ; Klaassen, Marcel
  • Assuntos: accelerometer ; Accelerometers ; Accuracy ; Animal behavior ; animal behavior classification ; Aquatic birds ; Classification ; Classifiers ; Data collection ; data visualization ; Datasets ; Feature selection ; interactive process ; Machine learning ; Multimedia industry ; Original Research ; Scientific visualization ; Visualization ; Visualization (Computers) ; Workflow ; XGBoost
  • É parte de: Ecology and Evolution, 2021-09, Vol.11 (18), p.12364-12377
  • Notas: ObjectType-Article-1
    SourceType-Scholarly Journals-1
    ObjectType-Feature-2
    content type line 23
  • Descrição: Increasingly, animal behavior studies are enhanced through the use of accelerometry. To allow translation of raw accelerometer data to animal behaviors requires the development of classifiers. Here, we present the “rabc” (r for animal behavior classification) package to assist researchers with the interactive development of such animal behavior classifiers in a supervised classification approach. The package uses datasets consisting of accelerometer data with their corresponding animal behaviors (e.g., for triaxial accelerometer data along the x, y and z axes arranged as “x, y, z, x, y, z,…, behavior”). Using an example dataset collected on white stork (Ciconia ciconia), we illustrate the workflow of this package, including accelerometer data visualization, feature calculation, feature selection, feature visualization, extreme gradient boost model training, validation, and, finally, a demonstration of the behavior classification results. Other than the serial functions to turn raw accelerometer data into behaviors, this package also provides interactive visualization tools to assist in handling and interpreting the accelerometer input data, deciding on appropriate behavior categories for classification and understanding the classification results. In brief, this package promotes the integration of the user's expert knowledge on their own research system in developing advanced behavior classification models.
  • Editor: England: John Wiley & Sons, Inc
  • Idioma: Inglês
Links
Voltar para lista de resultados

  • Realização: ABCD-USP USP   Logos de Redes Sociais: Freepik

Buscando em bases de dados remotas. Favor aguardar.