Please use this identifier to cite or link to this item: https://repositorio.ufrn.br/jspui/handle/123456789/21398
Title: Machine Learning Algorithmsfor Automatic Classification of Marmoset Vocalizations
Other Titles: Machine Learning Algorithmsfor Automatic Classification of Marmoset Vocalizations
Authors: Turesson, Hjalmar K.
Ribeiro, Sidarta
Pereira, Danillo R.
Papa, João P.
Albuquerque, Victor Hugo C. de
Keywords: Machine Learning Algorithms;Marmoset Vocalizations
Issue Date: Sep-2016
Citation: TURESSON, H.K.; RIBEIRO, S.; PEREIRA, D.R.; PAPA, J.P.; DE ALBUQUERQUE, V.H.C. Machine Learning Algorithms for Automatic Classification of Marmoset Vocalizations. PLoS ONE. v.11, n.9, p.e0163041, 2016. doi:10.1371/journal.pone.0163041
Abstract: Automatic classification of vocalization type could potentially become a useful tool for acoustic the monitoring of captive colonies of highly vocal primates. However, for classification to be useful in practice, a reliable algorithm that can be successfully trained on small datasets is necessary. In this work, we consider seven different classification algorithms with the goal of finding a robust classifier that can be successfully trained on small datasets. We found good classification performance (accuracy > 0.83 and F1-score > 0.84) using the Optimum Path Forest classifier. Dataset and algorithms are made publicly available.
metadata.dc.description.resumo: Automatic classification of vocalization type could potentially become a useful tool for acoustic the monitoring of captive colonies of highly vocal primates. However, for classification to be useful in practice, a reliable algorithm that can be successfully trained on small datasets is necessary. In this work, we consider seven different classification algorithms with the goal of finding a robust classifier that can be successfully trained on small datasets. We found good classification performance (accuracy > 0.83 and F1-score > 0.84) using the Optimum Path Forest classifier. Dataset and algorithms are made publicly available.
URI: http://hdl.handle.net/123456789/21398
Appears in Collections:ICe - Artigos publicados em periódicos

Files in This Item:
File Description SizeFormat 
SidartaRibeiro_ICE_2016_MachineLearning.pdf2,43 MBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.