Cuckoo Search Clustering Algorithm: A novel strategy of biomimicry

Abstract

A novel, nature inspired, unsupervised classification method, based on the most recent metaheuristic algorithm, stirred by the breeding strategy of the parasitic bird, the cuckoo, is introduced in this paper. The proposed Cuckoo Search Clustering Algorithm (CSCA) yields good results on benchmark dataset. Inspired by the results, the proposed algorithm is validated on two real time remote sensing satellite- image datasets for extraction of the water body, which itself is a quite complex problem. The CSCA makes use of Davies-Bouldin index (DBI) as fitness function. Also a method for generation of new cuckoos used in this algorithm is introduced. The resulting algorithm is conceptually simpler, takes less parameter than other nature inspired algorithms, and, after some parameter tuning, yields very good results.