Classification of Echolocation Calls from 14 Species of Bat by Support Vector Machines and Ensembles of Neural Networks

Algorithms

Robert D. Redgwell¹  Joseph M. Szewczak³  Gareth Jones² 

[1] School of Biological Sciences, University of Auckland, Private Bag 92019, Auckland, New Zealand; E-mail:;School of Biological Sciences, University of Bristol, Woodland Road, Bristol BS8 1UG, UK; E-mail:;Department of Biological Sciences, Humboldt State University, 1 Harpst St., Arcata, California 95521, USA; E-mail:

关键词: ensembles;    neural networks;    support vector machines;    echolocation calls;    bats;   

DOI  :  10.3390/a2030907

来源: mdpi

【 摘 要 】

Calls from 14 species of bat were classified to genus and species using discriminant function analysis (DFA), support vector machines (SVM) and ensembles of neural networks (ENN). Both SVMs and ENNs outperformed DFA for every species while ENNs (mean identification rate – 97%) consistently outperformed SVMs (mean identification rate – 87%). Correct classification rates produced by the ENNs varied from 91% to 100%; calls from six species were correctly identified with 100% accuracy. Calls from the five species of Myotis, a genus whose species are considered difficult to distinguish acoustically, had correct identification rates that varied from 91 – 100%. Five parameters were most important for classifying calls correctly while seven others contributed little to classification performance.

【 授权许可】

CC BY   
© 2009 by the authors; licensee Molecular Diversity Preservation International, Basel, Switzerland.