Independent Component Analysis and Neural Network applied on Electronic Nose System
Electronic noses are being developed as systems for the automated detection and classification of odors, vapors, and gases. Based on the study of the theory and constitutes of the electronic nose system, a set of independent component analysis (ICA) algorithms with BP neural network, for detection of gas mixture is designed and constructed, and the data processing which is measured by an electronic nose system consisting of five gas sensors is carried out. The results show that ICA algorithm can make a good classification for the data and reduce the data correlation. As the input of the BP network, it can predigest the structure and improve the convergence speed of the network.
electronic nose BP neural network independent component analysis(ICA)
Xiaochuan He Shoushui Wei Ruiqing Wang
School of Control Science and Engineering Shandong University Jinan, P. R. China
国际会议
上海
英文
490-493
2008-05-16（万方平台首次上网日期，不代表论文的发表时间）