Generating colored 2-dimensional representations of sleep EEG with the KANTS clustering algorithm

• Authors: Carlos Miguel Fernandes;Antonio Mora;Juan Julian Merelo;Francisco Fernández;Agostinho Rosa
• Venue: Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
• Year: 2012

Evolutionary Computation and Swarm Intelligence (SI) are currently some of the scientific research fields where scientists and artists seek for tools and inspiration for creating what is known as generative art. Within the SI field, social insects and the concept of stigmergy, in particular, have inspired several significant artworks that question the borders and nature of creativity. This paper addresses generative art created with SI systems and presents a set of images that correspond to a working mechanism of an ant-based clustering algorithm, which uses data samples that interact via the environment and generate what we call abstract swarm paintings. The algorithm, called KANTS, consists in a simple set of equations that model the local behavior of the ants (data samples) in a way that, when travelling on a heterogeneous 2-dimensional lattice of vectors, they tend to form clusters according to the class of each sample. The algorithm was previously proposed for clustering. In this paper, KANTS is used outside a purely scientific framework and applied to data extracted from sleep-Electroencephalogram (EEG) signals. With such data, the lattice vectors have three variables, which are used for generating the RGB values of a colored image. Therefore, from the action of the swarm on the environment, we get 2-dimensional colored abstract sketches of human sleep. We call these images pherogenic drawings, since the data used for creating them are actually visual representations of the algorithm's pheromone maps. As a visualization and creative tool, the method is contextualized within the swarm art field.