Abstract
With the traditional Chinese medicine herbsangelicae dahuricae radix (ADR or Baizhi) andsalviae miltiorrhizae radix (SMR or Danshen) as two examples, this work studies the automatic discrimination of the geographic origins of the herbs using near infrared (NIR) reflectance spectroscopy. Multi-class support vector machine (SVM) is utilized for the purpose, and recursive SVM is utilized to select the feature spectral segments that are decisive for the discrimination. With only 5 and 8 short spectral segments, discriminative accuracies of 92% are achieved on independent test sample sets. This work not only provides a prototype of accurate rapid discriminating systems for quality control of herbal medicines, but also opens new possibilities in studying subtle differences in the chemical compositions of herbs from different cultivation conditions and investigating their associations with the effectiveness of the herbs.
Similar content being viewed by others
References
Sun Suqin, Zhou Qun, Qin Zhu, Collection of 2D Correlation infrared Spectrums of Traditional Chinese Medicine (in Chinese), Beijing: Chemistry Industry Press, 2003.
Sun Suqin, Zhou Qun, Zhang Xuan et al., Undamaged determination of raw plant medicinal drugs with Fourier transform Raman spectroscopy, Chinese J. Analytical Chemistry (in Chinese), 2000, 28(2): 211–214.
Sun Suqin, Yuan Zimin, Bai Yan, Identify the genuine of Shanyao (Dioscorea opposita Thunb.) by FTIR combined with computer aided analysis, Computers and Applied Chemistry (in Chinese), 2002, 19(1): 77.
Woo, Y. -A., Kim, H. -J., Cho, J. et al., Discrimination of herbal medicines according to geographical origin with near infrared reflectance spectroscopy and pattern recognition techniques, Journal of Pharmaceutical and Biomedical Analysis, 1999, 21: 407–413.
Woo, Y. -A., Cho, C. -H., Kim, H. -J. et al., Classification of cultivation years of Ginseng using near-infrared (NIR) reflectance spectroscopy, Near Infrared Analysis, 2000, 1: 19–22.
Liu Shuhua, Zhang Xuegong, Zhou Qun et al., Use of FTIR and pattern recognition to determine geographical origins of Chinese medical herbs, Spectroscopy and Spectral Analysis (in Chinese), 2005, in press.
Liu Shuhua, Zhang Xuegong, Zhou Qun et al., Use of NIR and pattern recognition to determine geographical origins of Chinese medical herbs, Spectroscopy and Spectral Analysis (in Chinese), 2005, in press.
Zhang Xuegong, On statistical learning theory and support vector machines, Acta Automatic Sinica (in Chinese), 2000, 26(1): 32–42.
Vapnik, V., The Nature of Statistical Learning Theory, New York: Springer-Verlag, 1995.
Guyon, I., Weston, J., Barnhill, S. et al., Gene selection for cancer classification using support vector machines, Machine Learning, 2002, 46(1): 389–422.
Zhang, X., Ke, H., ALL/AML cancer classification by gene expression data using SVM and CSVM approach, Genome Informatics, 2000, 2: 237–239.
Ramaswamy, S., Tamayo, P., Riflin, R. et al., Multiclass cancer diagnosis using tumor gene expression signatures, PNAS, 2001, 98(26): 15149–15154.
Collobert, R., Bengio, S., SVMTorch: support vector machines for large-scale regression problems, Journal of Machine Learning Research, 2001, 1: 143–160 (http://www.idiap.ch/learning/SVMTorch. html).
Zhang, X., Wong, W. H., Sample classification and gene selection based on SVM: method and software description, Technical Report, Department of Biostatistics, Harvard School of Public Health, 2001 (http://www.biostat.harvard.edu/~xzhang/R-SVM/R-SVM.html).
Zhaoqi Bian, Xuegong Zhang, Pattern Recognition, 2nd ed. (in Chinese), Beijing: Tsinghua University Press, 2000.
Duda, R.O., Hart, P.E., Stork, D.G., Pattern Classification, 2nd eds. New York: John Wiley & Sons, 2001.
Author information
Authors and Affiliations
Corresponding author
About this article
Cite this article
Liu, S., Zhang, X. & Sun, S. Discrimination and feature selection of geographic origins of traditional Chinese medicine herbs with NIR spectroscopy. Chin.Sci.Bull. 50, 179–184 (2005). https://doi.org/10.1007/BF02897523
Received:
Issue Date:
DOI: https://doi.org/10.1007/BF02897523