Application of Neural Network in the Analysis of Near-Infrared Spectra
The main problem in the spectrum analysis technology is the difficulty in locating the target which will affect the predication and the analysis. How to choose the right mathematic model becomes the key point in the spectrum analysis. This paper designs the practical manual neural network model to locate the target and predicate. This paper uses error backward direction propagation calculation method and establishes three-layer neural network to solve the problems such as the spectrum peaks overlap seriously and noise is big in the spectrum analysis. When the quantity of samples to be located the target is significant, employ manual neural network method to analyze and discuss the corns protein content and near-infrared spectrum. By analyzing the experimental result this paper concludes that manual neural network method performs better than linear regression method and partial least-squares method and obtains ideal result.
spectrum analysis location and predication manual neural network method.
Ping Zuo Shichun Pang Xue Feng Yanchao Gao Dandan Qin
Foundational Department of Aviation University of Air Force,Changchun, China Business School ,JiLin Foundational Department of Aviation University of Air Force,Changchun, China
国际会议
南昌
英文
155-158
2012-08-26（万方平台首次上网日期，不代表论文的发表时间）