A Projection Pursuit Based Risk Assessment Method in Mobile Ad hoc Networks

Establishing high performance cooperation and estimating nodes’ risk level in mobile ad hoc networks (MANETs) are currently fundamental and challenging due to the inherent characteristics of MANETs, such as the highly dynamic topology and the absence of an effective security mechanism. Trust based assessment methods were recently put forward but presumed restrictions to the data samples or presumed weights for node’s attributes are required. In this paper, Projection Pursuit based Risk Assessment (PPRA), is proposed to analyze node’s creditability. As projection pursuit turns high-dimensional node properties to low-dimension space, all nodes’ risk levels could be clustered effectively and accurately. Projection index, the same as judgment index of clustering consequence, is utilized to reveal the behavior of different nodes. By maximizing projection index through Genetic Algorithm (GA), optimal projection direction is obtained, and then the projection values of each node could be calculated. Finally, the results in one-dimension or two-dimension projection space show that our method is more efficient and practical than traditional methods.