A Chaotic Black Hole Optimization based Classification (CBHOC) for Large Dataset in Distributed Environment

  • Rajeev Pandey, Sanjay Silakari

Abstract

The heterogeneous atmosphere is well suited for numerous fields of distributed computing by performing the classification of data information of medical, educational, industries and innovation areas. The huge heterogeneous information is explored and analyzed by utilizing numerous classification strategies to raise the superiority of essential data shifting on distributed networks. In this paper, a Chaotic Black Hole Optimization based Classification (CBHOC) is implemented to perform classification of huge quantity of data from numerous heterogeneous resources to increase the capability of data accessing in distributed atmosphere. The major intention of CBHOC is to gain a specified settlement of data distribution for heterogeneous devices in distributed atmosphere by exploiting little features of chaotic function for population assortment. The searching strength of black hole stars is getting better with the help of chaotic function and then the black hole optimization is applied to assort the best centroids and member of classes accurately. The CBHOC is developed in MATLAB 2021a platform for four huge datasets. The results depict the finer performance of CBHOC as examined against existing strategies K-Means, ALO, GA and BHO in terms of standard deviation, F-measure, purity index and intra-cluster distance.

Published
2021-10-23
How to Cite
Rajeev Pandey, Sanjay Silakari. (2021). A Chaotic Black Hole Optimization based Classification (CBHOC) for Large Dataset in Distributed Environment. Design Engineering, 6623 - 6634. Retrieved from http://thedesignengineering.com/index.php/DE/article/view/5637
Section
Articles