Grey wolf optimizer combined with k-nn algorithm for clustering problem

The clustering problem is an important task in machine learning. Clustering algorithms allow for the division of the set into individual clusters on the basis of a specific measure. Such an idea is used for undescribed data, where its label must be automatically assigned. One of the most popular algorithms is the k-nearest neighbors. In this paper, we propose a modification of this algorithm by combining it with heuristics, i.e. the grey wolf optimizer. The idea assumes that individuals in heuristic will be understood as a sample and unknown classes as victims in heuristic. Then the heuristic operation is used for analyzing the set. The proposition was described in terms of original algorithms and proposed hybridization of them. Then it was tested on Iris Flower Dataset and obtained results were discussed in terms of its advantages.