SPARROW: A Spatial Clustering Algorithm using Swarm Intelligence

G. Folino and G. Spezzano (Italy)


Data mining, spatial clustering, artificial life, swarmintelligence.


Swarm intelligence is a property of systems of unintelligent agents exhibiting collectively intelligent behaviour. Ants colonies, flocks of birds, termites, swarms of bees etc. are agent-based insect models that exhibit a collective intelligent behaviour that can be used as a metaphor for solving problems. In this paper we present a new parallel algorithm that uses the new swarm intelligence based techniques to investigate clustering in spatial data. The algorithm, called SPARROW, combines a smart exploratory strategy based on a flock of birds that move around a cellular landscape that contains the data set with a density-based cluster algorithm to discover clusters of arbitrary shape and size in spatial data. Agents use modified rules of the standard flock algorithm to transform an agent into a hunter foraging for clusters in spatial data. Clusters are discovered applying the heuristic principles of the spatial clustering algorithm DBSCAN. We have applied this algorithm on two synthetic data and we have measured, through computer simulation, the impact of the flocking search strategy on performance.

Important Links:

Go Back