论文部分内容阅读
化学计量学是以计算机和近代计算技术为基础的一门新兴交叉学科,在中药鉴别、定性表征、质量控制、组效关系等研究中均具有广泛应用,尤其在中药的质量控制与评价研究中具有重要意义。综述近年来化学计量学中化学模式识别方法,包括2种无监督模式识别方法(聚类分析、主成分分析)和4种有监督模式识别方法(簇类独立软模式法、偏最小二乘法判别分析、支持向量机、人工神经网络),并从产地、基原、炮制、真伪等多个方面总结了化学模式识别方法在中药质量控制研究中的应用。
Chemometrics is a newly emerging interdisciplinary subject based on computer and modern computing technology. It has been widely used in the research of traditional Chinese medicine (TCM) identification, qualitative characterization, quality control and group-effect relationship, especially in the quality control and evaluation of traditional Chinese medicine It is of great significance. In this paper, the methods of chemical pattern recognition in stoichiometry are summarized, including two unsupervised pattern recognition methods (cluster analysis, principal component analysis) and four supervised pattern recognition methods (clustering independent soft pattern method and partial least squares method Analysis, support vector machine, artificial neural network), and summarizes the application of chemical pattern recognition methods in the quality control of traditional Chinese medicine from the aspects of origin, primitive, processing, authenticity and so on.