Identification of curcumin content in raw and vinegar-processed rhizomes of Curcuma kwangsiensis based on electronic nose combined with back propagation neural network

LAN Zhen-wei1 JI De2 WANG Shu-mei1 LU Tu-lin2 MENG Jiang1

(1.Engineering Technology Research Center for Chinese Materia Medica Quality of Universities in Guangdong Province, Key Laboratory of Digital Quality Evaluation of Chinese Materia Medica, State Administration of Traditional Chinese Medicine, School of Traditional Chinese Medicine, Guangdong Pharmaceutical University, Guangzhou, Guangdong province, China 510006)
(2.School of Pharmacy, Nanjing University of Chinese Medicine, Nanjing, Jiangsu province, China 210023)

【Abstract】This study established a rapid and accurate method for the identification of raw and vinegar-processed rhizomes of Curcuma kwangsiensis to predict the curcumin content for scientific evaluation. A complete set of bionics recognition mode was adopted. The digital odor signal of raw and vinegar-processed rhizomes of C. kwangsiensis was obtained by the electronic nose (E-nose) and analyzed by back propagation (BP) neural network algorithm, with the accuracy, the sensitivity, and specificity in the discriminant model, correlation coefficient as well as the mean square error in the regression model as the evaluation indexes. The experimental results showed that the three indexes of the E-nose signal discrimination model established by the neural network algorithm were 100% in training set, correction set and prediction set, which were obviously superior to the traditional decision tree model, naive bayes model, support vector machine, K-nearest neighbor, and boost model, and could accurately differentiate the raw and vinegar-processed products. Correlation coefficient and mean square error of the regression model in prediction set were 0.974 8 and 0.117 5 respectively, which could well predict curcumin content in C. kwangsiensis, and demonstrate the superiority of the simulation biometrics model in the analysis of Chinese medicine. By BP neural network algorithm, E-nose odor fingerprint could quickly, conveniently and accurately realize the discrimination and regression, which suggested that more bionics information acquisition and identification patterns could be combined in the field of Chinese medicine to provide ideas and methods for the rapid evaluation and standardization of the quality of Chinese medicine.

【Keywords】 Curcuma kwangsiensis; vinegar-processed rhizomes of Curcuma kwangsiensis; electronic nose; BP neural network; curcumin; content prediction;

【DOI】

【Funds】 Traditional Chinese Medicine Standardization Project of Emerging Industry Major Project in 2016 (ZYBZH-Y-SC-40) Innovation and Strong University Project of Guangdong Pharmaceutical University, Department of Education of Guangdong Province (2016KTSCX064, 2018KZDXM040) Project of Guangzhou Municipal Science and Technology Bureau (201707010170)

Download this article

    References

    [1] Chinese Pharmacopoeia Commission. Pharmacopoeia of the People’s Republic of China. Vol. One [S]. Beijing: China Medical Science Press, 2015: 208 (in Chinese).

    [2] LIN L Y, CHEN S H, LV G Y. Pharmacological study on the function of “qi-promoting, blood-breaking, stagnation-removing and pain-relieving” of Zedoray Rhizome [J]. International Journal of Traditional Chinese Medicine, 2008, 30 (2): 114 (in Chinese).

    [3] GAN Y X, ZHAO S L, LUO N N, et al. Comparative research on efficacy of promoting the flow of qi and eliminate blood stasis of Curcuma Rhizoma before and after processing with vinegar [J]. Research and Practice on Chinese Medicines, 2015, 29 (2): 29 (in Chinese).

    [4] CUI G J, LIN Y C. 莪术的鉴别与炮制 [J]. Capital Medicine, 2010, 17 (19): 50 (in Chinese).

    [5] SHEN Y, LI Y, LIU T T, et al. Microscopical and physicochemical identification of 3 sources of Curcumae Rhizoma [J]. Chemical Research and Application, 2014, 26 (2): 267 (in Chinese).

    [6] YE Y H, HAO H, CAI Y Y, et al. 广西莪术的栽培繁殖及分子鉴定研究进展 [J]. Journal of Chinese Medicinal Materials, 2015, 38 (10): 2220 (in Chinese).

    [7] ZHAO C G, LIANG G, SHAO L L, et al. Advances in studies on structure-activity relationship of curcuminoids in anti-inflammation and cell-protection [J]. Chinese Traditional and Herbal Drugs, 2008, 39 (4): 619 (in Chinese).

    [8] WANG G Y, SHENG L, WANG X H. 应用电子鼻研究中医药 [J]. Journal of Medical Information, 2013 (18): 243 (in Chinese).

    [9] GONG J T, WANG J Y, LI L, et al. Identification of Curcuma herbs using XGBoost algorithm in electronic nose odor fingerprint [J]. China Journal of Chinese Materia Medica, 2019, 44 (24): 5375 (in Chinese).

    [10] GONG J T, ZHAO L Y, XU D, et al. Discrimination of Armeniacae Semen Amarum from different processed products and various rancidness degrees by electronic nose and support vector machine [J]. China Journal of Chinese Materia Medica, 2020, 45 (10): 2389 (in Chinese).

    [11] FEI C H, DAI H, SU H, et al. Advances of electronic nose technology and its application in Chinese medicine industry [J]. World Chinese Medicine, 2019, 14 (2): 257 (in Chinese).

    [12] HUANG D D, HE W W, JIN L, et al. Distinguish Schisandrae Sphenantherae Fructus from different producing areas based on electronic nose technology [J]. Chinese Journal of Experimental Traditional Medical Formulae, 2017, 23 (23): 22 (in Chinese).

    [13] CHEGN H Y. A study on application of GA-PSO-BP neural network in prediction of air pollutants concentration [D]. Wuhan: Huazhong University of Science and Technology, 2014 (in Chinese).

    [14] SHI Z B, ZUO C C, YANG C M. Experimental study on a bionic nose system [J]. Transactions of The Chinese Society of Agricultural Machinery, 2005, 36 (2): 70 (in Chinese).

    [15] DAI J M. Galaxy morphology classification with deep convolutional neural networks [D]. Beijing: University of Chinese Academy of Sciences, 2018 (in Chinese).

    [16] YUSUF S, ISMAIL H. Quality evaluation of chickpeas using an artificial neural network integrated computer vision system [J]. Int J Food Sci Technol, 2011, 46 (1): 194.

    [17] AMMA N G B. Cardiovascular disease prediction system using genetic algorithm and neural network [C]. Dindigul:International Conference on Computing, IEEE, 2012.

    [18] HECHT N. Theory of the backpropagation neural network [C]. Washington: International 1989 Joint Conference on Neural Networks, IEEE, 2002.

    [19] WANG X Y, MENG J, TAN G L, et al. Research on the relation of EEG signal chaos characteristics with high-level intelligence activity of human brain [J]. Nonlinear Biomed Phys, 2010, 4 (1): 2.

    [20] ZHANG J, WANG K.Research about the cooperation fuzzy chaos neural network [C]. Dalian: World Congress on Intelligent Control & Automation, IEEE, 2006.

This Article

ISSN:1001-5302

CN:11-2272/R

Vol 45, No. 16, Pages 3863-3870

August 2020

Downloads:2

Share
Article Outline

Abstract

  • 1 Materials
  • 2 Methods and results
  • 3 Discussion
  • References