128 Proc. of The Sixth Intl. Conf. On Advances In Computing, Control And Networking - ACCN 2017 Copyright © Institute of Research Engineers and Doctors, USA .All rights reserved. ISBN: 978-1-63248-117-7 doi: 10.15224/ 978-1-63248-117-7-51 COMMUNITY DETECTION USING Central Force Optimization (CFO) Govind Agarwal 1 , Santosh Kumar Chourasia 1 , Anupam Biswas 1 , Siddhartha K Arjaria 2 , Bhaskar Biswas 1 Abstract— Community structure is believed to be one of the notable features of complex networks representing real complicated systems. Very often, uncovering community structures in networks can be regarded as an optimization problem, thus, many evolutionary algorithms based approaches have been put forward. . In this paper Central Force Optimization (CFO), physics based optimization, and its variants are used to detect communities. CFO is deterministic in nature, unlike the most widely used meta-heuristics. However, CFO is not free from the problem of premature convergence. Therefore the variants used Adaptive CFO (ACFO) and Multi-Start CFO (MCFO) are used in enhancing the convergence. Keywords—Community Detection, Physics Inspired Optimization, CF, Social Network Analysis. I. Introduction In recent times, Social networks became an important role in every aspect of modern life. Researchers, scientists and industry have shown interest in analysis of such networks. These Networks can be viewed as massive graphs that are composed of a set of vertices and edges, where nodes represent the objects and links represent the interactions amongst them, and then apply certain techniques to analyze the properties of the graph based network. One of such techniques for analyzing social networks is community detection. Communities are regarded as sub-graphs which have dense intra-links and sparse inter-links. Communities are also known as clusters or modules of graph. Mostly, the detection of community structures in networks can be considered either as a clustering problem or an optimization problem, thus, the choice of an appropriate optimization algorithm and evaluation function affects the ultima detection performance. Over the last decades, many nature-inspired heuristic optimization algorithms without requiring much information about the function became the most widely used optimization methods such as genetic algorithms (GA), particle swarm optimization (PSO), ant colony optimization (ACO), cuckoo search (CS) algorithm, group search optimizer (GSO), and glowworm swarm optimization (GSO1). 1. Department of Computer Science and Engineering, Indian Institute of Technology (BHU), Varanasi India. 2. Technocrats Institute of Technology, Bhopal, India These search methods all simulate biological phenomena. For the algorithms that are not bio-inspired, most have been developed by mimicking certain physical and/or chemical laws, including electrical charges, gravity, river systems, etc. As different natural systems are relevant to this category, we can even subdivide these into many subcategories which are not necessary. Since our work is based on physics inspired optimization techniques, we will not talk about chemistry or biology inspired algorithms. Some of the well-known physics optimization algorithms are as follows [5]: 1. Newton‟s gravitational law ➢ Pure physics ● CFO ● APO ● GSA ● GIO ➢ Semi physics ● IGOA 2. Quantum mechanics ➢ Pure physics ● QGA ● QEA ➢ Semi physics ● QPSO ● QSE ● QICA ● CQACO ● QBSO 3. Universe theory ➢ Pure physics ● BB-BC ● GBSA 4. Electromagnetism ➢ Pure physics ● EM 5. Electrostatics ➢ Pure physics ● ES Different from these algorithms, some heuristic optimization algorithms based on physical principles have been developed, for example, simulating annealing (SA) algorithm, electromagnetism-like mechanism (EM) algorithm, central force optimization (CFO) algorithm [1], gravitational search algorithm (GSA), and charged system search (CSS). SA simulates solid material in the annealing process. EM is based on Coulomb‟s force law associated with electrical charge process. GSA and CFO utilize Newtonian mechanics law. CSS is based on Coulomb‟s force and Newtonian mechanics laws. Unlike other algorithms, CFO is a deterministic method. In other words,