VARIANCE-BASED HARMONY SEARCH ALGORITHM FOR UNIMODAL AND MULTIMODAL OPTIMIZATION PROBLEMS WITH APPLICATION TO CLUSTERING

This article presents a novel variance-based harmony search algorithm (VHS) for solving optimization problems. VHS incorporates the concepts borrowed from the invasive weed optimization technique to improve the performance of the harmony search algorithm (HS). This eliminates the main problem of constant parameter setting in the algorithm proposed recently and named as explorative HS. It uses the variance of a current population as well as presents a solution vector to improvise the harmony memory. In addition, the dynamic pitch adjustment operator is used to avoid solution oscillation. The proposed algorithm is evaluated on 14 standard benchmark functions of various characteristics. The performance of the proposed algorithm is investigated and compared with classical HS, an improved version of HS, the global best HS, self-adaptive HS, explorative HS, and the recently proposed state-of-art gravitational search algorithm. Experimental results reveal that the proposed algorithm outperforms the above-mentioned approaches. The effects of scalability, noise, harmony memory size, and harmony memory consideration rate have also been investigated with the proposed algorithm. The proposed algorithm is then employed for a data clustering problem. Four real-life datasets selected from the UCI machine learning repository have been used. The results indicate that the VHS-based clustering outperforms the existing well-known clustering algorithms.