Detection-of-Communities-based-on-Modularity-Factor

Analyzing optimization based Community detection algorithms

Breif Description :

EHO

Community structures in complicated networks are quite useful because they can help us uncover misinterpreted node relationships by providing more information about unknown nodes.Using computer approaches, however, it is still difficult to forecast community structures with precision.The current study presents a high-accuracy multi-swarm EHO algorithm for detecting significant community structures.The elephant population is divided into equal interacting sub swarms known as clans, and the evolution of these clans is dependent on two major procedures: clan updating and clan separation.The update technique uses a local search function to discover a better spot for the clan's worried folks, and a multi-swarm Ring strategy for separating individuals to keep only the most important ones.

DMFO

A discrete moth–flame optimization technique for community detection (DMFO-CD) for complex networks was proposed in this study. The MFO algorithm's solution vectors representation, distance computation, and spiral flight movement were adapted for community detection. This was accomplished by introducing a single ten�point crossover to mimic distance computation, a two-point crossover to change movement strategy, and a single ten-point neighbor-based mutation to improve exploration ability.

Tools Used

• Programming language : Python
• Visualization : NetworkX
• Version control system : GitHub

References

1. An efficient multi-swarm elephant herding optimization for solving community detection problem in complex environment. Youcef Belkhiri, Nadjet Kamel, Habiba Drias.

2. Nadimi-Shahraki, M.H.; Moeini, E.; Taghian, S.; Mirjalili, S. DMFO-CD: A Discrete Moth-Flame Optimization Algorithm for Community Detection. Algorithms 2021, 14, 314