A fuzzy-neural system for identification of species-specific alarm calls of Gunnison's prairie dogs

Abstract

In this study we describe the design and application of an automated classification system that utilizes artificial intelligence to corroborate the finding that Gunnison's prairie dogs have different alarm calls for different species of predators. This corroboration is strong because it utilizes an entirely different analysis technique than that used in the original research by Slobodchikoff et al. [Slobodchikoff, C.N., Fischer, C., Shapiro, J., 1986. Predator-specific alarm calls of prairie dogs. Am. Zool. 26, 557] or in subsequent study done by Slobodchikoff et al. [Slobodchikoff, C.N., Kiriazis, J., Fischer, C., Creef, E., 1991. Semantic information distinguishing individual predators in the alarm calls of Gunnison's prairie dogs. Anim. Behav. 42, 713–719]. The study described here also is more completely automated than earlier study in this area. This automation allowed a large volume of field data to be processed where all measurements of relevant parameters were performed through software control. Previous study processed a smaller data set and utilized manual measurement techniques. The new classification system, which combines fuzzy logic and an artificial neural network, classified alarm calls correctly according to the eliciting predator species, achieving accuracy levels ranging from 78.6 to 96.3% on raw field data digitized with low quality audio equipment.