Modified S2 and Pattern Search Methods to Find Optimal Cluster Centroid for Multi-Variable Functions

Identification of useful clusters in large datasets has attracted considerable interest in clustering process. Since data in the World Wide Web is increasing exponentially that affects on clustering accuracy and decision making, change in the concept between every cluster occurs named concept drift. To detect the difference of cluster distributions between the current data subset and previous clustering result, an algorithm called Drifting Concept Detection (DCD) and proper data labeling need to be performed. To say that the data labeling was performed well, generated clusters must be efficient. Selecting initial cluster center (centroid) is the key factor that has high affection in generating effective clusters. The data with different properties exists in real world. Previous work was concentrated in the identification of optimal cluster centroid for the functions of multi variables using Simplex Search (S2) method and Pattern Search using Modified Sectioning method. These methods are extended by providing modified S2 and pattern search methods that finds optimal cluster centroid for the multi variable functions and tests for optimality and then apply any existing clustering algorithm to generate clusters.