IABCC: An improved Artificial Bee Colony algorithm for clustering

Data Clustering is the process of grouping data objects into set of disjoint classes called clusters so that objects within a class are highly similar with one another and dissimilar with the objects in other classes. recent years, some swarm intelligence-based approaches for clustering were proposed and achieved encouraging results. Artificial bee colony algorithm (ABC) is a relatively new optimization technique which has been shown to be competitive to other population-based algorithms. However, there is still an insufficiency in ABC regarding its solution search equation, which is good at exploration but poor at exploitation. In the ABC algorithm, new solution is produced by random change of the old solution. In this paper, the local search of ABC algorithm is improved by the new mechanism that causes probability of produce of solution with the highest fitness to be increased. In the IABCC algorithm, all dimension of the solution are weighted based on the distance value of each dimension of cluster center with corresponding dimension of the mean point of data. this algorithm has been tested on several standard real Datasets and compared with popular heuristic algorithms in clustering. Numerical results reveal that the proposed algorithm has better performance than other existing algorithms.

Keywords:

Artificial Bee Colony , exploitation , local search , Clustering