Discrimination and chemical composition quantitative model of Raw Moutan Cortex and Moutan Cortex Carbon based on electronic nose and machine learning

Sujuan Zhou; Huajian Lin; Jiang Meng; Sujuan Zhou; Huajian Lin; Jiang Meng

doi:10.3934/mbe.2022422

Mathematical Biosciences and Engineering

2022, Volume 19, Issue 9: 9079-9097. doi: 10.3934/mbe.2022422

Previous Article Next Article

Research article Special Issues

Discrimination and chemical composition quantitative model of Raw Moutan Cortex and Moutan Cortex Carbon based on electronic nose and machine learning

1.
College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou 510006, China
2.
Department of Automation, Guangdong University of Technology, China
3.
School of Traditional Chinese Medicine, Guangdong Pharmaceutical University /Key Laboratory of Digital Quality Evaluation of Chinese Materia Medica, State Administration of Traditional Chinese Medicine (TCM) /Engineering Technology Research Center for Chinese Materia Medica Quality of Universities in Guangdong Province, Guangdong 510006, China

† These authors contributed equally to this work
Academic Editor: Jose M. Rodriguez

Received: 07 March 2022 Revised: 09 June 2022 Accepted: 13 June 2022 Published: 22 June 2022

Raw Moutan Cortex (RMC) is a traditional medicinal material commonly used in China. Moutan Cortex Carbon (MCC) is a processed product of RMC by stir-frying. As raw and processed products of the same Chinese herb pieces, they have different effects. RMC has the effects of clearing heat and cooling blood, promoting blood circulation and removing blood stasis, but MCC has the contrary effect of cooling blood and hemostasis. Therefore, it is necessary to distinguish them effectively. The traditional quality evaluation method of RMC and MCC still adopts character identification, and mainly relies on the working experience and sensory judgment of employees with experience. This will lead to strong subjectivity and poor repeatability. And the final evaluation result may cause inevitable errors and the processed products with different processing degrees in actual production, which affects the clinical efficacy. In this study, the electronic nose technology was introduced to objectively digitize the odor of RMC and MCC. And the discrimination model of RMC and MCC was constructed in order to establish a rapid, objective and stable quality evaluation method of RMC and MCC. According to the correlation analysis, the experiment found the content of gallic acid, 5-hydroxymethylfurfural (5-HMF), paeoniflorin and paeonol determined by high performance liquid chromatography (HPLC) had a certain correlation with their odor characteristics. Thus, partial least squares regression (PLSR) and support vector machine regression (SVR) were compared and established the chemical composition quantitative model. Results showed that the quantitative data of RMC and MCC odor could be used to predict the contents of the chemical components. It can be used for quality control of RCM and MCC.
- Moutan Cortex,
- Moutan Cortex Carbon,
- discrimination model,
- composition quantitative model,
- electronic nose,
- support vector machine regression,
- HPLC
Citation: Sujuan Zhou, Huajian Lin, Jiang Meng. Discrimination and chemical composition quantitative model of Raw Moutan Cortex and Moutan Cortex Carbon based on electronic nose and machine learning[J]. Mathematical Biosciences and Engineering, 2022, 19(9): 9079-9097. doi: 10.3934/mbe.2022422

Related Papers:

Abstract

Raw Moutan Cortex (RMC) is a traditional medicinal material commonly used in China. Moutan Cortex Carbon (MCC) is a processed product of RMC by stir-frying. As raw and processed products of the same Chinese herb pieces, they have different effects. RMC has the effects of clearing heat and cooling blood, promoting blood circulation and removing blood stasis, but MCC has the contrary effect of cooling blood and hemostasis. Therefore, it is necessary to distinguish them effectively. The traditional quality evaluation method of RMC and MCC still adopts character identification, and mainly relies on the working experience and sensory judgment of employees with experience. This will lead to strong subjectivity and poor repeatability. And the final evaluation result may cause inevitable errors and the processed products with different processing degrees in actual production, which affects the clinical efficacy. In this study, the electronic nose technology was introduced to objectively digitize the odor of RMC and MCC. And the discrimination model of RMC and MCC was constructed in order to establish a rapid, objective and stable quality evaluation method of RMC and MCC. According to the correlation analysis, the experiment found the content of gallic acid, 5-hydroxymethylfurfural (5-HMF), paeoniflorin and paeonol determined by high performance liquid chromatography (HPLC) had a certain correlation with their odor characteristics. Thus, partial least squares regression (PLSR) and support vector machine regression (SVR) were compared and established the chemical composition quantitative model. Results showed that the quantitative data of RMC and MCC odor could be used to predict the contents of the chemical components. It can be used for quality control of RCM and MCC.

References

[1]	Q. L Ye, P. Cheng, D. H. Yan, Y. Sun, Y. Zhang, H. Cao, et al., Nine absorbed components pharmacokinetic of raw and processed Moutan Cortex in normal and blood‐heat and hemorrhage syndrome model rats, Biomed. Chromatogr., 34 (2020). https://doi.org/10.1002/bmc.4963 doi: 10.1002/bmc.4963
[2]	X. L. Zhao, A. W. Ding, L. Zhang, H. Zhang, A study on the historical changes of preparation of Cortex Moutan, Chin. Arch. Tradit. Chin. Med., 26 (2008), 1907-1910. https://doi.org/10.13193/j.archtcm.2008.09.68.zhaoxl.061 doi: 10.13193/j.archtcm.2008.09.68.zhaoxl.061
[3]	G. G. Gu, Shen Nong's Herbal Classic, Lanzhou University Press, (2009), 113.
[4]	S. J. Zhou, J. Meng, Z. P. Huang, S. Z. Jiang, Y. Q. Tu, A method for discrimination of processed ginger based on image color feature and a support vector machine model, Anal. Methods, 8 (2016), 2201-2206. https://doi.org/10.1039/C5AY03171K doi: 10.1039/C5AY03171K
[5]	Administration GfaD, Guangdong Standard for Processing Traditional Chinese Medicine, Guangdong Science and Technology Press, 1984.
[6]	Q. Y. Huang, S. J. Zhou, Q. F. Chen, J. Meng, S. M. Wang, Study on the content changes of multiple components in different processing levels of Peduncularum mout, Chin. Med. Mater., 39 (2016), 1024-1027. https://doi.org/10.13863/j.issn1001-4454.2016.05.017 doi: 10.13863/j.issn1001-4454.2016.05.017
[7]	X. Li, X. L. Wei, X. L. Zhao, A. W. Ding, Comparison of chemical composition changes of Mout bark before and after charcoal frying, Chin. J. Exp. Formulae, 17 (2011), 32-35. https://doi.org/10.3969/j.issn.1005-9903.2011.23.010 doi: 10.3969/j.issn.1005-9903.2011.23.010
[8]	H. Zhang. A. W. Ding, L. Zhang, Optimization of processing technology of Danpi charcoal by orthogonal method, China Pharm. Ind., 17 (2008), 25-26. https://doi.org/ 10.3969/j.issn.1006-4931.2008.03.019 doi: 10.3969/j.issn.1006-4931.2008.03.019
[9]	Y. Wang, X. Yang, P. F. Xia, X. Ma, R. J. Yang, J. R. Hu, et al., Research progress on chemical constituents, pharmacological effects and predictive analysis of quality markers of rhubarb, Chin. Herb. Med., 50 (2019), 4821-4837. https://doi.org/10.7501/j.issn.0253-2670.2019.19.033 doi: 10.7501/j.issn.0253-2670.2019.19.033
[10]	Q. L. Ye, P. Cheng, D. H. Yan, Y. Sun, Y. Zhang, H. Cao, et al., Nine absorbed components pharmacokinetic of raw and processed Moutan Cortex in normal and blood‐heat and hemorrhage syndrome model rats, Biomed. Chromatogr., 34 (2020), 49-63. https://doi.org/10.1002/bmc.4963 doi: 10.1002/bmc.4963
[11]	X. Li, L. Zhang, A. W. Ding, Study on the effective site and mechanism of hemostatic action of Paederma charcoal, Chin. Herb. Med., 40 (2009), 1278-1280. https://doi.org/10.3321/j.issn:0253-2670.2009.08.033 doi: 10.3321/j.issn:0253-2670.2009.08.033
[12]	J. Y. Zhang, Y. K. Li, W. L. Wen, L. Zhao, Progress in Cardiovascular Activity of Paeonol, New Chin. Med. Clin. Pharm., 27 (2016), 148-150. https://doi.org/10.3969/j.issn.1003-9783.2016.01.032 doi: 10.3969/j.issn.1003-9783.2016.01.032
[13]	W. Li, Y. L. Wang, S. X. Cai, H. Y. Zhang, H. Y. Shi, F. L. Huang, et al., Comparison of the effects of paeonol and aspirin on hemorrheology in rats, Chin. Herb. Med., (2000), 31-33. https://doi.org/10.3321/j.issn:0253-2670.2000.01.017 doi: 10.3321/j.issn:0253-2670.2000.01.017
[14]	L. Zhang, L. L. Cao, X. L. Zhao, A. W. Ding, J. Chen, X. Li, Changes of 5-hydroxymethylfurfural content in Pedunculus mout charcoal with different processing levels, Chin. Pharm., 20 (2009), 2624-2626.
[15]	D. H. Yan, Study on Processing Mechanism of Moutan Bark Charcoal Based on Global Pharmacokinetics, Guangdong Pharmaceutical University, 2017.
[16]	J. Z. Tan, W. L Kerr, Determining degree of roasting in cocoa beans by artificial neural network (ANN)‐based electronic nose system and gas chromatography/mass spectrometry (GC/MS), J. Sci. Food Agric., 98 (2018), 3851-3859. https://doi.org/10.1002/jsfa.8901 doi: 10.1002/jsfa.8901
[17]	X. X. Chao, X. L. Ren, M. Wang, L. Z. Wang, Y. R. Deng, Research progress on specifications, grades and quality standards of traditional Chinese medicine and decoction pieces, Tradit. Chin. Med., 44 (2021), 494-498. https://doi.org/10.13863/j.issn1001-4454.2021.02.044 doi: 10.13863/j.issn1001-4454.2021.02.044
[18]	X. Y. Xie, X. Y. Zhen, H. Yu, Z. W. Zhang, S. W. Si, Y. Wang, et al., Advances in technology of pharmaceutical analysis in 2018, Chin. J. Pharm. Anal., 40 (2020), 18. https://doi.org/10.16155/j.0254-1793.2020.05.01 doi: 10.16155/j.0254-1793.2020.05.01
[19]	R. Q. Yang, Rapid Quality Evaluation Of Moldy Traditional Chinese Medicine Based On Electronic Nose, Beijing University of traditional Chinese Medicine, 2019.
[20]	J. Tan, J. Xu, Applications of electronic nose (e-nose) and electronic tongue (e-tongue) in food quality-related properties determination: A review, Artif. Intell. Agric., 4 (2020), 104-115. https://doi.org/10.1016/j.aiia.2020.06.003 doi: 10.1016/j.aiia.2020.06.003
[21]	S. T. Kim, I. H. Choi, H. Li, Identification of multi-concentration aromatic fragrances with electronic nose technology using a support vector machine, Anal. Methods, 13 (2021), 4710-4717. https://doi.org/10.1039/d1ay00788b. doi: 10.1039/d1ay00788b
[22]	A. Khorramifar, M. Rasekh, H. Karami, U. Malaga-Toboła, M. Gancarz, A machine learning method for classification and identification of potato cultivars based on the reaction of MOS type sensor-array, Sensors, 21 (2021), 5836. https://doi.org/10.3390/s21175836 doi: 10.3390/s21175836
[23]	M. Rasekh, H. Karami, A. D. Wilson, M. Gancarz, Performance analysis of mau-9 electronic-nose mos sensor array components and an classification methods for discrimination of herb and fruit essential oils, Chemosensors, 9 (2021), 243. https://doi.org/10.3390/chemosensors9090243 doi: 10.3390/chemosensors9090243
[24]	S. Slimani, E. Bultel, T. Cubizolle, C. Herrier, T. Rousselle, T. Livache, Opto-electronic nose coupled to a silicon micro pre-concentrator device for selective sensing of flavored waters, Chemosensors, 8(2020), 60. https://doi.org/10.3390/chemosensors8030060 doi: 10.3390/chemosensors8030060
[25]	Q. Tao, Study on odor detection of shellfish based on PEN3 type electronic nose sensor, Adv. J. Food Sci. Technol., 10 (2016), 796-800. https://doi.org/10.19026/ajfst.10.2264 doi: 10.19026/ajfst.10.2264
[26]	Q. Zhang, H. G. Li, M. Li, L. Ding, Feature extraction of face image based on LBP and 2-D Gabor wavelet transform, Math. Biosci. Eng., 17 (2020), 1578-1592. https://doi.org/10.3934/mbe.2020082 doi: 10.3934/mbe.2020082
[27]	P. Xanthopoulos, P. M. Pardalos, T. B. Trafalis, Linear Discriminant Analysis, in Robust Data Mining, Springer, New York, (2013), 27-33. https://doi.org/10.1007/978-1-4419-9878-1_4
[28]	M. Pérez-Enciso, M. Tenenhaus, Prediction of clinical outcome with microarray data: a partial least squares discriminant analysis (PLS-DA) approach, Hum. Genet., 112 (2003), 581-592. https://doi.org/10.1007/s00439-003-0921-9. doi: 10.1007/s00439-003-0921-9
[29]	D. Ballabio, V. Consonni, Classification tools in chemistry. Part 1: linear models. PLS-DA, Anal. Methods, 5 (2013), 3790-3798. https://doi.org/10.1039/c3ay40582f. doi: 10.1039/c3ay40582f
[30]	V. N. Vapnik, S. Mukherjee, Support vector method for multivariate density estimation, Adv. Neural Inf. Process. Syst., 76 (2000), 659-665. https://doi.org/10.1.1.899.1861
[31]	S. Mohapatra, K. Ganesh, M. Punniyamoorthy, R. Susmitha, Developing a classification model using SVM, in Service Quality in Indian Hospitals, (2018), 63-66. https://doi.org/10.1007/978-3-319-67888-7_8
[32]	A. D. Wilson, Rapid detection of urea fertilizer effects on voc emissions from cucumber fruits using a mos e-nose sensor array, Agronomy, 12 (2021). https://doi.org/10.3390/agronomy12010035 doi: 10.3390/agronomy12010035
[33]	R. Rusinek, M. Gawrysiak-Witulska, A. Siger, A. Oniszczuk, A. A. Ptaszyńska, J. Knaga, et al., Effect of supplementation of flour with fruit fiber on the volatile compound profile in bread, Sensors, 21 (2021), 2812. https://doi.org/10.3390/s21082812 doi: 10.3390/s21082812
[34]	F. Khodamoradi, E. Mirzaee-Ghaleh, M. J. Dalvand, R. Sharifi, Classification of basil plant based on the level of consumed nitrogen fertilizer using an olfactory machine, Food Anal. Methods, 14 (2021), 2617-2629. https://doi.org/10.1007/s12161-021-02089-y doi: 10.1007/s12161-021-02089-y

Reader Comments

Your name:*

Email:*
© 2022 the Author(s), licensee AIMS Press. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/4.0)