Machine Learning Algorithms for Automatic Classification of Marmoset Vocalizations

Author(s)

Turesson, Hjalmar K. ; Ribeiro, Sidarta ; Pereira, Danillo R. ; Papa, Joao P. ; de Albuquerque, Victor Hugo C.

• Document type: Journal article
• Source: PLoS One; v. 11, n. 9 SEP 21 2016.
• Web of Science Citations: 11

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 F-1-score > 0.84) using the Optimum Path Forest classifier. Dataset and algorithms are made publicly available. (AU)

• FAPESP's process: 15/50319-9 - Meta-heuristic-based optimization of probabilistic neural networks
• Grantee: João Paulo Papa
• Support type: Regular Research Grants
• FAPESP's process: 13/07699-0 - Research, Innovation and Dissemination Center for Neuromathematics - NeuroMat
• Grantee: Jefferson Antonio Galves
• Support type: Research Grants - Research, Innovation and Dissemination Centers - RIDC
• FAPESP's process: 14/16250-9 - On the parameter optimization in machine learning techniques: advances and paradigms
• Grantee: João Paulo Papa
• Support type: Regular Research Grants