A discrete modified fireworks algorithm for community detection in complex networks

详细信息    查看全文

• 作者：Mohamed Guendouz ; Abdelmalek Amine ; Reda Mohamed Hamou
• 关键词：Community detection ; Evolutionary algorithms ; Swam intelligence ; Fireworks algorithm
• 刊名：Applied Intelligence
• 出版年：2017
• 出版时间：March 2017
• 年：2017
• 卷：46
• 期：2
• 页码：373-385
• 全文大小：
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence (incl. Robotics); Mechanical Engineering; Manufacturing, Machines, Tools;
• 出版者：Springer US
• ISSN：1573-7497
• 卷排序：46

文摘

In the last decade, several algorithms have been proposed to solve the problem of community detection in complex networks. Many of them are based on swarm intelligence and evolutionary algorithms. Most of these algorithms use the modularity density as a fitness function to maximize. However, these algorithms attempt to find the best solution without taking into consideration the structure of the network. In this paper, a new discrete modified Fireworks Algorithm (FWA) has been developed to solve the problem of community detection. A new initialization strategy and new mutation strategies are proposed, based on the label propagation strategy to enhance the algorithm and to speed up its convergence. The proposed algorithm has been evaluated on real-world and synthetic networks. Experimental results compared with three other known algorithms show the effectiveness of using our proposed algorithm for solving the problem of detecting communities in complex networks.