Classification of Sperm Whale Clicks (Physeter Macrocephalus) with Gaussian- Kernel-Based Networks

• Published in: Algorithms
• Main Authors: Van der Schaar, Mike Connor Roger Malcolm, Delory, Eric, André, Michel
• Other Authors: Centre Tecnològic de Vilanova i la Geltrú, Universitat Politècnica de Catalunya. LAB - Laboratori d'Aplicacions Bioacústiques
• Format: Article in Journal/Newspaper
• Language: English
• Published: 2009
• Subjects: Àrees temàtiques de la UPC::Física::Acústica; Àrees temàtiques de la UPC::Física::Acústica::Sonar; Àrees temàtiques de la UPC::Física::Acústica::Sons subaquàtics; Sperm whale; Underwater acoustics > Mathematical models; Catxalots > Identificació; Acústica submarina > Models matemàtics; Physeter macrocephalus
• Online Access: http://hdl.handle.net/2117/11857; https://doi.org/10.3390/a2031232

With the aim of classifying sperm whales, this report compares two methods that can use Gaussian functions, a radial basis function network, and support vector machines which were trained with two different approaches known as C-SVM and º-SVM. The methods were tested on data recordings from seven different male sperm whales, six containing single click trains and the seventh containing a complete dive. Both types of classifiers could distinguish between the clicks of the seven different whales, but the SVM seemed to have better generalisation towards unknown data, at the cost of needing more information and slower performance. Postprint (published version)