Title: A variant of EAM to uncover community structure in complex networks
Authors: Tribhuvan Singh; Krishn Kumar Mishra; Ranvijay
Addresses: Department of Computer Science and Engineering, MNNIT Allahabad, Prayagraj, India ' Department of Computer Science and Engineering, MNNIT Allahabad, Prayagraj, India ' Department of Computer Science and Engineering, MNNIT Allahabad, Prayagraj, India
Abstract: Environmental adaptation method (EAM) was developed to solve single-objective optimisation problems. After the first proposal, other variants have been suggested to speed up the convergence rate and to maintain the diversity of the solutions. Among those variants, IEAM-RP works with real numbers. In this paper, a variant of IEAM-RP has been suggested with major changes in adaptation operator to improve the overall performance of the algorithm. In the proposed method, significant attention has been given for balancing exploration and exploitation of individuals in the population. The performance of the proposed algorithm is compared against 14 state-of-the-art algorithms using standard benchmark functions of the comparing continuous optimisers (COCO) framework. Further, to check the effectiveness of the proposed approach, it has been applied to a real-world problem of community detection in complex networks. Again, the experimental results are found very promising and competitive compared to other algorithms.
Keywords: single-objective optimisation; evolutionary algorithms; environmental adaptation method; EAM; community detection problem.
DOI: 10.1504/IJBIC.2020.109713
International Journal of Bio-Inspired Computation, 2020 Vol.16 No.2, pp.102 - 110
Accepted: 02 Feb 2020
Published online: 21 Sep 2020 *