AN EFFICIENT DATA FUSION METHOD BASED ON EXTREME LEARNING MACHINE OPTIMIZED BY PSO ALGORITHM
The extreme learning machine is used for cellular heterogeneous wifi sensor networks in order to properly eliminate the extra information being broadcasted in the network. The machine is optimized by PSO algorithm. The Analysis of cellular hetrogeneous wifi sensor network's information is performed along with the wifi sensor networks acting as the neuron in the neutral community of gaining knowledge of machines. The neural community of the excessive getting to know laptop takes the sensory information composed with the aid of cellular heterogeneous wi-fi sensor community and merges the composed sensor facts along with the collective route to a exquisite extent in order to bring down the extent of community facts transmitted to the sink joint. ELM is based on the principle of empiric risk minimisation, and the learning cycle involves just one repetition. The method prevents several iterations and spatial minimisation. It has been used in a variety of fields and applications due to improved generalization skills, robustness, controllability and rapid learning. A latest method of records that fusions for cellular heterogeneous Wi-fi sensors network is mainly based on intense mastering laptop which is efficiently optimized via PSO algorithm is suggested. The simulation consequences proves that the recommended PSO ELM based records fusion algorithm can efficaciously bring down community visitors and extensively extends network’s life duration.