An Efficient Hybrid Evolutionary Algorithm for Cluster Analysis

Clustering problems appear in a wide range of unsupervised classification applications such as pattern recognition, vector quantization, data mining and knowledge discovery. The k-means algorithm is one of the most widely used clustering techniques. Unfortunately, k-means is extremely sensitive to the initial choice of centers and a poor choice of centers may lead to a local optimum that is quite inferior to the global optimum. This paper presents an efficient hybrid evolutionary optimization algorithm based on combining Ant Colony Optimization (ACO) and Simulated Annealing (SA), called ACO-SA, for cluster analysis. The performance is evaluated through several benchmark data sets. The simulation results show that the proposed algorithm outperforms the previous approaches such as SA, ACO and k-means for partitional clustering problem.