期刊名称：International Journal of Distributed Sensor Networks
印刷版ISSN：1550-1329
电子版ISSN：1550-1477
出版年度：2014
卷号：2014
DOI：10.1155/2014/703625
出版社：Hindawi Publishing Corporation
摘要：The node importance evaluation based on removal of nodes and their incident links cannot accurately reflect
the importance of the nodes, because such approach may change the topology of the network, and even split the
network into several disconnected parts. To solve this problem, we propose a novel node importance evaluation
method based on agglomeration contraction principle. This method does not require the node being evaluated to be
removed from the network; thus, it may not cause network fracture. With this method, aided by spectral analysis,
the vital gateway nodes can be identified by using the nontrivial eigenvectors of the Laplace matrix of the network
diagram. Then, a formula to estimate the importance of particular individuals within the network is proposed;
moreover, the betweenness centrality and the positions of nodes are taken into consideration. At last, using some
superenergy nodes to provide targeted protection for the vital gateway nodes in the network, the life of the
network can be prolonged and the robustness of the system improved effectively. Above all, with this method, the
number of nodes to be evaluated in a network can be reduced, and the computation decreased accordingly. Final
experiments verify the efficiency of the proposed method and the result is consistent with our intuitive judgments.
