期刊名称：International Journal of Computer Science and Management Studies
电子版ISSN：2231-5268
出版年度：2013
卷号：13
期号：2
出版社：Imperial Foundation
摘要：This paper presents an application of a neural network in wireless sensor network to enhance the security. A multilayer perceptron (MLP) based media access control protocol (MAC) can be used in wireless sensor network (WSN) against the denial-of-service (DOS) attacks. The MLP enhances the security of a WSN by constantly monitoring the parameters that exhibit unusual variations in case of DOS attack. The MLP shuts down the MAC layer and the physical layer of the sensor node when the suspicion factor appears or the output of the MLP exceeds a threshold level. Back propagation and Hopfield are used for training the MLP. Hopfield network (HN) uses associative memory to store the pattern. The HN itself is robust since it performs pattern completion in case of missing data and pattern correction in case of corrupted data due to the association ability.
