DocumentCode :
2796619
Title :
A study on local sensor fusion of wireless sensor networks based on the neural network
Author :
Xu, Xiao-liang ; Qiu, Jun-na ; Chen, Chun
Author_Institution :
Sch. of Comput. Sci.&Software Eng., Hangzhou Dianzi Univ., Hangzhou
Volume :
7
fYear :
2008
fDate :
12-15 July 2008
Firstpage :
4045
Lastpage :
4050
Abstract :
Taken as the whole networkpsilas information fusion, local sensor fusion, integrating signals from different sources and processing locally, is the first step work. Due to the output of sensor nodes is vulnerable to the impact of around environmental factors, such as temperature, humidity, noise, etc., and in order to solve nonlinear problems between input and output, a sensor output compensation model based on the Neural Network is proposed. As the same time, the theory of the Neural Network is outlined, mainly an introduction is made to typical fusion algorithms, along with analyses and comparisons, in three Feed-Forward neural networks, BP, RBF and CMAC, respectively.
Keywords :
backpropagation; cerebellar model arithmetic computers; radial basis function networks; sensor fusion; telecommunication computing; wireless sensor networks; BP; CMAC; RBF; environmental factors; feedforward neural networks; local sensor fusion; neural network; sensor output compensation model; wireless sensor networks; Algorithm design and analysis; Environmental factors; Feedforward neural networks; Humidity; Neural networks; Sensor fusion; Signal processing; Temperature sensors; Wireless sensor networks; Working environment noise; BP; CMAC; Local sensor fusion; Neural network; RBF;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Machine Learning and Cybernetics, 2008 International Conference on
Conference_Location :
Kunming
Print_ISBN :
978-1-4244-2095-7
Electronic_ISBN :
978-1-4244-2096-4
Type :
conf
DOI :
10.1109/ICMLC.2008.4621110
Filename :
4621110
Link To Document :
بازگشت