Title :
The Research on Data-Fusion Methods Based on Wavelet Neural Network
Author :
Hong, Song ; Lianjun, Hu ; Xiaohui, Zeng ; Hui, Xiao
Author_Institution :
Sch. of Autom. & Electron. Inf. Eng., Sichuan Univ. of Sci. & Eng., Zigong, China
Abstract :
The wavelet transform is introduced into pretreatments and feature extractions in the paper. The threshold value is determined according to the change of wavelet coefficients which can reduce noises and extract effective characteristic parameters. The neural net is used for fusion calculations, realizing the data fusion of multi-sensor. The simulation results show the feasibility and validity of the method.
Keywords :
feature extraction; radial basis function networks; sensor fusion; wavelet transforms; feature extraction; multisensor data fusion; noises reduction; wavelet neural network; Data acquisition; Data engineering; Data mining; Feature extraction; Neural networks; Sampling methods; Sensor fusion; Sensor phenomena and characterization; Wavelet analysis; Wavelet transforms; Neutral net; Wavelet transform; data-fusion;
Conference_Titel :
Natural Computation, 2009. ICNC '09. Fifth International Conference on
Conference_Location :
Tianjin
Print_ISBN :
978-0-7695-3736-8
DOI :
10.1109/ICNC.2009.82
