The Levy Walk (or Levy flight) is a concept from Biomathematics to describe the hunting–behaviour of many predatory species. It is a very efficient way to find prey in a very short time frame. We now want to use this concept in a clustering–context to – if you so will – ”hunt” for clusters. We describe how we convert this concept into an efficient way to find cluster centres by linking the data points through the path the Levy Walk takes. The clusters are then created by statistical analysis of the links between the data points. The result is a Clustering algorithm that works on massive datasets with extremely high level of noise. It is not dependent on any form of cluster shape and is almost free of parameters. The only choice one has to make is the precision of the Clustering, which in turn determines the runtime.

Top