基于双人工神经网络的中药秦皮紫外吸收光谱分析

Analysis of ultraviolet absorption spectrum of Chinese herbal medicine-Cortex Fraxini by double ANN.

作者信息

Bai Lifei, Zhang Haitao, Wang Hongxia, Li Junfeng, Lu Lei, Zhang Hanqi, Wang Hongyan

机构信息

College of Chemistry, Jilin University, Changchun 130012, China.

出版信息

Spectrochim Acta A Mol Biomol Spectrosc. 2006 Nov;65(3-4):863-8. doi: 10.1016/j.saa.2006.01.014. Epub 2006 Aug 17.

DOI:10.1016/j.saa.2006.01.014

PMID:16914366

Abstract

A fast, accurate and convenient method for the simultaneous determination of multi-component in the Chinese herbal medicine was proposed by using ultraviolet absorption spectrum. In this method, dummy components were added to training sample, and a double artificial neural network (DANN) that has the function of high self-revision and self-simulation was used. Effect of other interference components could be eliminated by adjusting concentration of dummy components. Therefore, the accuracy of concentration prediction for multi-component in the complicated Chinese herbal medicine was improved. It has been realized that two effective components of Cortex Fraxini, aesculin and aesculetin, were simultaneously determined, without any separation. The predicted accuracy was 92% within the permitted relative errors. The measurement precisions of the aesculin and aesculetin were 0.37% and 1.5%, respectively.

摘要

提出了一种利用紫外吸收光谱同时测定中草药中多组分的快速、准确且便捷的方法。在该方法中，向训练样本中加入虚拟组分，并使用具有高度自我修正和自我模拟功能的双人工神经网络（DANN）。通过调整虚拟组分的浓度可以消除其他干扰组分的影响。因此，提高了复杂中草药中多组分浓度预测的准确性。现已实现了在无需任何分离的情况下同时测定秦皮中的两种有效成分七叶苷和七叶内酯。在允许的相对误差范围内，预测准确率为92%。七叶苷和七叶内酯的测量精密度分别为0.37%和1.5%。