A novel linear time clustering using heuristically improved mrk-medoids based on modified squirrel search algorithm

Abstract

ABSTRACT The rapid development of different techniques and the data are accumulated with distinctive properties with high dimensions and huge size. The most essential approach in data mining is clustering, which groups a set of data into clusters. The training of high-dimensional data and huge volume data in clustering models exhibits low computational efficiency and high computational cost. These clustering methods clarify the inherent properties and discover new information from the data. This proposal plans to design and develop the novel Heuristic-mrk-medoids (H-mrk-medoids) clustering for handling the linear time clustering of big data. The aggregation of data into chunks and optimisation of the centroid is done in the map phase, and clustering is performed by optimising the weighted centroid in the reduce phase. As a main contribution of the paper, the mrk-medoids are optimally tuned by the Modified Squirrel Search Algorithm (M-SSA), which ensures efficient clustering based on the fitness quality measure. The accuracy rate of the designed method is 99% and also the RMSE rate of the offered approach is 0.393095%. The result of the proposed approach has shown major improvements in the efficiency of clustering when compared to conventional linear time clustering models.