Bird flock effect-based dynamic community detection: Unravelling network patterns over time

Hairol Anuar, Siti Haryanti and Abal Abas, Zuraida and Waini, Iskandar and Mukhtar, Mohd Fariduddin and Sun, Zejun and Winanto, Eko Arip and Md Yunos, Norhazwani (2025) Bird flock effect-based dynamic community detection: Unravelling network patterns over time. Alexandria Engineering Journal, 112. pp. 177-208. ISSN 1110-0168

Text 02259231120241534441286.pdf Download (14MB)

Abstract

Community structure is essential for topological analysis, function study, and pattern detection in complex networks. As establishing community structure in a dynamic network is difficult, it gives a unique perspective in many interdisciplinary fields. Many researchers have explored the challenging technique that requires parameter specification and optimization for quality result. This study proposed an eco-system conceptual framework based on bird flock effect. Relying on the natural law of rule, we designed a dynamic community detection named DCDBFE. The design of algorithm was based on the three basic rules of bird flock: separation, alignment, and cohesion phase. Then, we provide an explanation of similarity measure used between vertices to identify the modules attraction. DCDBFE employs an incremental community detection approach to repeatedly detect communities in each network snapshot or time step. The contributions are obtained for high quality community detected, free-parameter and well stability. To test its performance, extensive experiments were conducted on both synthetic and real-world networks. The outcomes demonstrate that our approach can effectively find satisfaction from each time step by comparison with the other well-known algorithms.

Item Type:	Article
Uncontrolled Keywords:	Network structure, Dynamic community detection, Bird flock effect, Similarity measure
Divisions:	Faculty Of Electronics And Computer Technology And Engineering
Depositing User:	Norfaradilla Idayu Ab. Ghafar
Date Deposited:	28 Oct 2025 01:13
Last Modified:	28 Oct 2025 01:13
URI:	http://eprints.utem.edu.my/id/eprint/29089
Statistic Details:	View Download Statistic

Actions (login required)

View Item