Chem. J. Chinese Universities ›› 1993, Vol. 14 ›› Issue (6): 775.

• Articles • Previous Articles     Next Articles

Pattern Recognition Application to 13C NMR Spectra of Flavone Compounds

ZHANG Liang, ZHANG Zheng-Xing, SHENG Long-Sheng, AN Deng-Kui   

  1. Department of Pharmaceutical Analysis, China Pharmaceutical University, Nanjing, 210009
  • Received:1992-07-07 Revised:1992-11-10 Online:1993-06-24 Published:1993-06-24

Abstract: Aset of 6413C NMRspectra of flavone compounds were examined for information concerning chemical classes by pattern recognition.The Shannon information content for each chemical shift channel was calculated, the 14 channels with the highest information content were retained as a compressed basis set for SIMCA, LDAand KNNpattern recognition.The inherent class structure of the data showed two classes by NLM.Classification accuracy was 90.91%, 96.97% and 90.91% for two classes for SIMCA, LDAand KNN, respectively.

Key words: Pattern recognition, Shannon information theory, 13C NMR spectra, Flavone, Flavonol

TrendMD: