摘要
介绍了用于信号识别的小波神经网络的结构和算法，并将其用于酪氨酸、二羟基苯丙氨酸和色氨酸的紫外光谱识别．在小波神经网络中，采用Morlet母小波和一维搜索变步长共轭梯度优化方法，结果表明，小波神经网络对于光谱间的细微结构差别具有很好的识别能力．
The wavelet neural network employed in signal recognltion is presented and ap-plied to recognltion of the UV spectra of tyrosine, 3, 4-dihydroxyphenylalanine and tryto-phane. In the network, Morlet mother wavelet and line search conjugate gradient optimiza-tion method are used- The convergence speed is fast and the error of learning sets drops to 0.000073 only through 8 iterations. The error of testing patterns is 0.0000 64- The recogni-tion results(shown in Table 1)show that the sets of spectra can be well recognized by using the wavelet neural network.
出处
《高等学校化学学报》
SCIE
EI
CAS
CSCD
北大核心
1997年第6期860-863,共4页
Chemical Journal of Chinese Universities
基金
国家自然科学基金
