K-means clustering hybridized with nature inspired optimization algorithm: A review.

KM clustering is the most popular technique that finds each cluster's hidden intrinsic pattern in a given real-life application dataset. But it has some limitations, like its run time complexity is very high for high dimensional data sets, and this clustering is very sensitive to its initial centroids. This traditional approach requires the number of clusters, k, in advance for KM, which will not give good quality of clusters, and at the time, this algorithm converges to local optimal solution. So, for solving the problem of local optimal solutions, this paper presented some of the updated NI meta-heuristic algorithms, which has been hybridized with the KM clustering. This hybridized algorithm converges to global optimal solutions rather than local optima in a large search space. Further, we discussed some python API packages from scikit-learn.org for hybrid KM clustering that gives good quality of clusters, and at last, we describe some comparative analyses of KM clustering with integrated KM (KM+NIC). Most of the integrated KM show better accuracy results compared to traditional KM clustering. [ABSTRACT FROM AUTHOR]