Clustering outdoor soundscapes using fuzzy ants

A classification algorithm for environmental sound recordings or ldquosoundscapesrdquo is outlined. An ant clustering approach is proposed, in which the behavior of the ants is governed by fuzzy rules. These rules are optimized by a genetic algorithm specially designed in order to achieve the optimal set of homogeneous clusters. Soundscape similarity is expressed as fuzzy resemblance of the shape of the sound pressure level histogram, the frequency spectrum and the spectrum of temporal fluctuations. These represent the loudness, the spectral and the temporal content of the soundscapes. Compared to traditional clustering methods, the advantages of this approach are that no a priori information is needed, such as the desired number of clusters, and that a flexible set of soundscape measures can be used. The clustering algorithm was applied to a set of 1116 acoustic measurements in 16 urban parks of Stockholm. The resulting clusters were validated against visitorpsilas perceptual measurements of soundscape quality.