Application of shuffled frog-leaping algorithm on clustering

Evolutionary algorithms, such as shuffled frog leaping, are stochastic search methods that mimic natural biological evolution and/or the social behavior of species. Such algorithms have been developed to arrive at near-optimum solutions to complex and large-scale optimization problems which cannot be solved by gradient-based mathematical programming techniques. The shuffled frog-leaping algorithm draws its formulation from two other search techniques: the local search of the “particle swarm optimization” technique and the competitiveness mixing of information of the “shuffled complex evolution” technique. Cluster analysis is one of the attractive data mining techniques which is used in many fields. One popular class of data clustering algorithms is the center-based clustering algorithm. K-means is used as a popular clustering method due to its simplicity and high speed in clustering large datasets. However, k-means has two shortcomings: Dependency on the initial state and convergence to local optima and global solutions of large problems cannot be found with reasonable amount of computation effort. In order to overcome local optima problem, lots of studies are done in clustering. In this paper, we proposed an application of shuffled frog-leaping algorithm in clustering (SFLK-means). We compared SFLK-means with other heuristics algorithm in clustering, such as GAK, SA, TS, and ACO, by implementing them on several simulations and real datasets. Our finding shows that the proposed algorithm works better than others.