Title :
A method of pattern classification for faint signals
Author :
Zuojin, Li ; Liukui, Chen ; Ying, Wu ; Yi, Xiang
Author_Institution :
Chongqing Univ. of Sci. & Technol., Chongqing, China
Abstract :
This paper proposes a faint signal processing approach combining AR model and BP neural network (NN), by which the faint signal is fitted with AR model, whose coefficient served as signal eigenvector, and then sent into a three-tier BP NN for training and recognition classification. Classification tests on human pulse signals between drug users and non-users show that this approach is characterized in high speed and high recognition rate.
Keywords :
backpropagation; eigenvalues and eigenfunctions; neural nets; pattern classification; signal classification; AR model; faint signal processing approach; human pulse signals; pattern classification; recognition classification; signal eigenvector; three-tier BP neural network; training classification; Artificial neural networks; Correlation; Data models; Drugs; Mathematical model; Time series analysis; Training; AR model; LM algorithm; orders; pulse faint signal;
Conference_Titel :
Business Management and Electronic Information (BMEI), 2011 International Conference on
Conference_Location :
Guangzhou
Print_ISBN :
978-1-61284-108-3
DOI :
10.1109/ICBMEI.2011.5920497
