In:
Modern Physics Letters B, World Scientific Pub Co Pte Ltd, Vol. 31, No. 29 ( 2017-10-20), p. 1750262-
Abstract:
Currently, community detection is a hot topic. This paper, based on the self-organizing map (SOM) algorithm, introduced the idea of self-adaptation (SA) that the number of communities can be identified automatically, a novel algorithm SA-SOM of detecting communities in complex networks is proposed. Several representative real-world networks and a set of computer-generated networks by LFR-benchmark are utilized to verify the accuracy and the efficiency of this algorithm. The experimental findings demonstrate that this algorithm can identify the communities automatically, accurately and efficiently. Furthermore, this algorithm can also acquire higher values of modularity, NMI and density than the SOM algorithm does.
Type of Medium:
Online Resource
ISSN:
0217-9849
,
1793-6640
DOI:
10.1142/S0217984917502621
Language:
English
Publisher:
World Scientific Pub Co Pte Ltd
Publication Date:
2017
Permalink