模式识别在白芍质量控制中的应用

Application of chemical pattern recognition to quality control of Radix Paeoniae Alba

目的旨在通过通用性强的中药色谱数据特征的抽取和神经网络识别,建立白芍的质量评价模式。方法首先通过实验获取同一品种不同质量29个白芍样本的高效液相色谱数据,然后依照非线性的核主成分分析(KP-CA)进行数学特征提取,将取得的压缩数据,输入BP神经网络进行学习,运用训练后的网络识别白芍的质量分类。并探讨了模式识别中人工神经网络的数据预处理、网络隐含层数、隐节点数、激励函数和过拟合现象等。结果通过改良后网络训练,已成功地识别白芍药材质量类别(识别率100%)。结论非线性特征提取KPCA法与人工神经网络结合适用于白芍整体质量分析。

Objective With generalization and steadiness, a new evaluation model by Integrating Non Linear Features extraction algorithm with artificial neural networks （ANN） used for pattern recognition of quality control of Radix Paeoniae Alba was proposed in this paper. Methods The HPLC data from 29 samples with different quality were proceeded with nonlinear kernel principal component analysis （KPCA） and an improved Back propagation algorithm of ANN. The extract characteristics was fed into BP neural networks as input elements for pattern recognition. In the meantime, the processing data, the optimal numbers of hidden layers, the numbers of hidden nodes, excitation functions, and over-fitting, etc. were discussed wholly so that standardization networks was designed without jamming. Results As recognition ratio was 100%, the pattern recognition of quality control of Radix Paeoniae Alba was established successfully by trained networks and predicted results. Conclusion Integrating KPCA algorithm with ANN for pattern recognition of quality control of Radix Paeoniae Alba has been proved to be available.