Classification of Echolocation Calls from 14 Species of Bat by Support Vector Machines and Ensembles of Neural Networks
Open Access
- 9 July 2009
- journal article
- research article
- Published by MDPI AG in Algorithms
- Vol. 2 (3) , 907-924
Abstract
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.Keywords
This publication has 30 references indexed in Scilit:
- Human vs. machine: identification of bat species from their echolocation calls by humans and by artificial neural networksCanadian Journal of Zoology, 2008
- Echolocation call intensity in the aerial hawking batEptesicus bottae(Vespertilionidae) studied using stereo videogrammetryJournal of Experimental Biology, 2005
- Variability in echolocation call design of 26 Swiss bat species: consequences, limits and options for automated field identification with a synergetic pattern recognition approachMammalia, 2004
- 3D analysis of facial morphologyAmerican Journal of Medical Genetics Part A, 2004
- Identification of twenty‐two bat species (Mammalia: Chiroptera) from Italy by analysis of time‐expanded recordings of echolocation callsJournal of Zoology, 2002
- Influence of age, sex and body size on echolocation calls of Mediterranean and Mehely’s horseshoe bats, Rhinolophus euryale and R. mehelyi (Chiroptera: Rhinolophidae)Mammalia, 2001
- Variation in the echolocation calls of the hoary bat (Lasiurus cinereus): influence of body size, habitat structure, and geographic locationCanadian Journal of Zoology, 1999
- IDENTIFICATION OF BRITISH BAT SPECIES BY MULTIVARIATE ANALYSIS OF ECHOLOCATION CALL PARAMETERSBioacoustics, 1997
- Support-vector networksMachine Learning, 1995
- Neural Networks and the Bias/Variance DilemmaNeural Computation, 1992