Data Aggregation using Neural Network in WSN sing Neural Network in WSN sing Neural Network in WSN sing Neural Network in WSN
Usha Rani, Amita Dhankher, M. Tech · 2013
A sensor network is composed of a large number of s ensor nodes, which are densely deployed either inside the phenomenon or in its proximity. The sensor nodes may be randomly deployed in inaccessible terrains or disas ter relief operations hence sensor network protocols and algor ithms must possess self-organizing capabilities. Wireless sensor network is highly data centric. Data aggregation ar e very important in wireless sensor networks because sendi ng incorrect information by fault sensors make to wron g decision about environment and increasing defective sensor during the time incorrect data decries reliability of wireless sensor networks Data communication in WSN must be efficient one and must consume minimum power. Every sensor node consists of multiple sensors embedded i n the same node. Thus every sensor node is a source of da ta. This research applies the neural network within the sens ors, fault sensors and wrong data are discovered and eliminated. That is increased efficiency and reliability and longevi ty sensor networks. Simulation results show the better perfor mance than the existing algorithm. For making the system self learning for the particular area the SOM Neural Net work algorithm is implemented.