Neural Network Based Classification Techniques For Wireless Sensor Network with Cooperative Routing

Wireless Sensor Networks(WSN) are battery powered. Hence every aspect of WSN is to be designed with energy constrain. Communication is the largest consumer of energy in WSN. Hence energy consumption during communication must be reduced to the minimum possible. This paper focuses on reduced energy consumption on communication. Classification techniques are used to classify sensor data to reduce communication cost. Cooperative routing is used to communicate data. The co-operative routing protocol is designed for communication in a distributed environment. In a distributed environment, the data routing takes place in multiple hops and all the nodes take part in communication. This protocol has been designed for wireless sensor networks. The main objective is to achieve a uniform dissipation of energy for all the nodes in the whole network. The paper discusses classification technique using ART1 and Fuzzy ART neural network models. The classified sensor data is communicated further using cooperative routing. Ptolemy-II is used for modeling and simulation of the sensor network. Lifetime improvement of the WSN is compared amongst diffusion routing and cooperative routing with and without classification. KeywordsWSN; Neural Network; Clustering; Ptolemy-II; Visual sence, Life Time Modelling