MutatedSocioAgentSim (MSAS): semisupervised modelling of multiagent simulation to predict and detect the mutation in a camouflaged social network

A social network is a networked structure formed by a set of agents/actors. It describes their interrelationshipsthat facilitate the exchange and flow of resources and information. A camouflaged social network is one such communitythat influences the underlying structure and the profile of the agents, to cause mutation. The proposed MSAM is anovel system that simulates a multiagent network whose community structure is analyzed to identify the critical agentsby studying the mutations caused due to attachment and detachment of agents. The isolation of the tagged agents willdemonstrate disruption of information flow, which leads to the dismantling of the camouflaged community and givingscope for a predictive study about near future reconciliation. The proposed system simulates the 9/11 covert networkbased on the belief matrix and uses the novel density-based link prediction and suite of fragmentation algorithms forpredictive community analysis. MSAM is claimed to be an intelligent system as agents perceive the knowledge fromthe dynamic environment through the belief matrix and further co-evolve as a community upon which semisupervisedmethodologies are used to predict the critical agents causing serious mutation.

PDF

___

[1] Gazendam HW, Jorna RJ. Theories about Architecture and Performance of Multi-agent Systems. University of Groningen. SOM Research Report 98 A02; 1998.
[2] Ghanem AG, Vedanarayanan S, Minai AA. Agents of influence in social networks. In Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems Volume 1 Jun 4 2012; 551-558.
[3] Luck M, McBurney P, Shehory O, Willmott S. Agent technology: computing as interaction (a roadmap for agent based computing). University of Southampton, 2005.
[4] Jiang Y, Jiang JC. Diffusion in social networks: A multiagent perspective. IEEE T Syst Man Cyb 2015; 45: 198-213.
[5] Li W, Bai Q, Zhang M. Agent-based influence propagation in social networks. InAgents (ICA), IEEE International Conference 2016; 51-56.
[6] Such JM, Espinosa A, Garc´ıa-Fornes A. A survey of privacy in multi-agent systems. Knowl Eng Rev 2014; 29: 314-44.
[7] Clauset A, Moore C, Newman ME. Hierarchical structure and the prediction of missing links in networks. Nature 2008; 453: 98-101.
[8] Fortunato S, Castellano C. Community structure in graphs. Comput Complex 2012; 490-512.
[9] Newman ME, Girvan M. Finding and evaluating community structure in networks. Phys Rev E 2004; 69: 026113.
[10] Xu X, Yuruk N, Feng Z, Schweiger TA. Scan: a structural clustering algorithm for networks. In Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; Aug 12 2007; pp. 824-833.
[11] Falkowski T, Barth A, Spiliopoulou M. Dengraph: A density-based community detection algorithm. In Web Intelligence, IEEE/WIC/ACM International Conference Nov 2 2007; pp. 112-115.
[12] Huang J, Sun H, Han J, Deng H, Sun Y, Liu Y. SHRINK: a structural clustering algorithm for detecting hierarchical communities in networks. In Proceedings of the 19th ACM international conference on Information and Knowledge Management Oct 26 2010; pp. 219-228.
[13] Weinstein C, Campbell W, Delaney B, O’Leary G. Modeling and detection techniques for counter-terror social network analysis and intent recognition. In Aerospace conference; Mar 7 2009; pp. 1-16.
[14] Borgatti SP. Identifying sets of key players in a social network. Comput Mqth Organ Th 2006; 12: 21-34.