RESUMEN
Chemometrics is a new cross discipline based on computer and modern technology. It has been widely used in the research of Chinese materia medica (CMM) identification, qualitative characterization, quality control, and group-effect relationship, especially in quality control and evaluation of CMM. In this paper, the application and progress of chemical pattern recognition methods in chemometrics for quality control of CMM in recent years are reviewed. Two unsupervised pattern recognition methods (cluster analysis and principal component analysis) and four supervised pattern recognition methods (soft independent modeling of class analogy, partial least-squares discriminant analysis, support vector machine, and artificial neural network) are described. This paper reviews application of chemical pattern recognition in quality control of CMM from different aspects, including growing areas, herbal origin, processing, identification of the authenticity, etc.
RESUMEN
SIMCA(self independent modeling of class analogy) is a classical class modeling method for chemical) pattern recognition. Although widely used, SIMCA suffers difficulties in selecting a proper number of principal components and determining the decision region. A new class modeling technique based on partial least squares regression, partial least squares class model(PLSCM) is proposed, where the number of latent variables) and decision region can be readily estimated by the routine methods in multivariate calibration, e.g. Monte Carlo cross validation. PLSCM is successfully applied to identify trueborn bezoar samples from artificial and adulterated bezoar samples based on infrared spectra measured in the range of 4000-9000 cm~(-1). It is demonstrated that PLSCM outperforms SIMCA in terms of both maneuverability and identification accuracy. For the raw spectra, both the training and prediction accuracy of PLSCM are 100%. For the standard normal variate-processed data, the training and prediction accuracy of PLSCM is 99% and 100%, respectively.