Pattern recognition applied to the fingerprint of traditional Chinese medicine characterized by two-dimension information data.
- Author:
Lei NIE
1
;
Guo-an LUO
;
Jin CAO
;
Yi-ming WANG
Author Information
- Publication Type:Journal Article
- MeSH: Chromatography, High Pressure Liquid; methods; Cluster Analysis; Drugs, Chinese Herbal; chemistry; isolation & purification; Flavonoids; chemistry; isolation & purification; Ginkgo biloba; chemistry; Neural Networks (Computer); Pattern Recognition, Automated; Pharmacognosy; Plants, Medicinal; chemistry; classification; Species Specificity
- From: Acta Pharmaceutica Sinica 2004;39(2):136-139
- CountryChina
- Language:Chinese
-
Abstract:
AIMTo establish the two-dimension information fingerprints chromatograph of traditional Chinese medicine and investigate via pattern recognition.
METHODSHierarchical cluster was applied to fingerprints described by one-dimension information data and by two-dimension information data respectively and corresponding results was compared.
RESULTSThe gross classes, in which the samples denoted by two-dimension information data, classified by all kinds of hierarchical cluster methods had less differences and more robustness than the methods containing the samples expressed by one-dimension information data. The classes to which the unknown samples would be belonged were determined by hierarchical cluster analysis and artificial neural network (ANN), and the same results were obtained.
CONCLUSIONThe fingerprints characterized by two-dimension information data could provide more overall and special information as compared with the methods indicated by one-dimension information data.
