Abstract:The effects of optimization of network parameters, noise, and impurity on the network were investigated detailedly. To speed up the convergence of the network and enhance the resolution of the library search of UV spectra, the derivative spectra for BP-ANN library search was proposed. The method has a higher tolerance to noise and impurity levels than using ordinary UV spectra, especially to slop background levels. Finally, the resolutions of library search of UV spectra with ANN with optimized parameters were compared with conventional correlation coefficient method. Results showed that the ANN is superior to conventional correlation coefficient method and is an effective method for library search of UV spectra.
王凤霞,张卓勇*,王亚敏 . 有机环境污染物紫外光谱检索的神经网络方法[J]. 光谱学与光谱分析, 2006, 26(05): 908-912.
WANG Feng-xia, ZHANG Zhuo-yong*, WANG Ya-min . Library Search of UV Spectra of Organic Environmental Pollutants Based on Neural Network . SPECTROSCOPY AND SPECTRAL ANALYSIS, 2006, 26(05): 908-912.
[1] Gemperline P J, Long J R, Gregorious V G. Anal. Chem., 1991, 63: 2313. [2] Mittermayr C R, Drouen A C J, Otto M, et al. Anal. Chim. Acta, 1994, 294: 227. [3] Bruchmann A, Gotze H J, et al. Chemom. Intell. Lab. Syst., 1993, 18: 59. [4] Benjathapanun N, Boyle W J O, Grattan K T V. Measurement, 1998, 24: 1. [5] ZHANG Zhuo-yong, LIU Si-dong, DING Bao-jun, et al(张卓勇,刘思东,丁保军, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 1998, 18(6): 680. [6] LIU Si-dong, CUI Xiu-jun, ZHANG Zhuo-yong, et al(刘思东,崔秀君,张卓勇, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2003, 23(1): 119. [7] HAN Li-qun(韩力群). Artificial Neural Network Theory, Design and Application(人工神经网络理论, 设计及应用). Beijing: Chemical Industry Press(北京:化学工业出版社), 2001. 55. [8] Xu L, Ball J W, Dixon S L, et al. Environ. Sci. Biochem., 1994, 13: 841. [9] Andrea T A, Kalayeh H J. Med. Chem., 1991, 34: 2824. [10] XU Lu, SHAO Xue-guang(许 禄,邵学广). Methods of Chemometrics(化学计量学方法·第2版). Beijing: Science Press(北京:科学出版社), 2004. 564.