参差比较和遗传算法的中药识别分类器

Chinese Traditional Medicine Identification Classifier Using Corresponding Relative Distance Computing and Genetic Algorithm

1.前言中医药学是中国人民的宝贵财富,但常有中药替代品甚至伪劣品出现.传统的中药形态鉴定法和理化鉴定法耗时,且受主观影响大.近几十年来,色谱学和光谱学等化学测量手段的发展和计算机模式识别的成熟,使得中药的化学模式识别成为中药识别领域的研究热点[1].

The identification of Chinese traditional medicine is a difficult subject in pharmacology. The development of chemical measurement and pattern recognition make the chemical pattern recognition possible. In this paper a new chemical pattern recognition method is proposed, in which a simple method named corresponding relative distance computing is used to compute the distance between samples for Nearest-Neighbor (NN) classifier, and the genetic algorithm is used to optimize the parameters of NN classifier. With the proposed method in this paper,experiments are carried out on chromatogram data of Panax. The results indicate that the method can identify the medicine of different harvest time or habitat, furthermore, this method which combines the pattern matching, genetic algorithm and NN classifier is robust, accurate and easy to be implemented.