Comparison of Ensemble Strategies in Online NIR for Monitoring the Extraction Process of Pericarpium Citri Reticulatae Based on Different Variable Selections

Abstract

Different ensemble strategies were compared in online near-infrared models for monitoring active pharmaceutical ingredients of Traditional Chinese Medicine. Bagging partial least square regression and boosting partial least square regression were adopted to near-infrared models, to determine hesperidin and nobiletin content during the extraction process of Pericarpium Citri Reticulatae in a pilot scale system. Different pretreatment methods were investigated, including Savitzky-Golay smoothing, derivatives, multiplicative scatter correction, standard normal variate, normalize, and combinations of them. Two different variable selection methods, including synergy interval partial least squares and backward interval partial least squares algorithms, were performed. Based on the result of the synergy interval partial least squares algorithm, bagging partial least square regression and boosting partial least square regression were adopted into the quantitative analysis. The results demonstrated that the established approach could be applied for rapid determination and real-time monitoring of hesperidin and nobiletin in Pericarpium Citri Reticulatae (Citrus reticulata) during the extraction process. Comparing the results, the boosting partial least square regression provided a slightly better accuracy than the bagging partial least square regression. Finally, this paper provides a promising ensemble strategy on online near-infrared models in Chinese medicine.

Key words

Citrus reticulata - Rutaceae - Pericarpium Citri Reticulatae - on-line near-infrared - partial least square regression - bagging-PLS - boosting-PLS

• References

• 1 Wu ZS, Sui CL, Xu B, Ai L, Ma Q, Shi XY, Qiao YJ. Multivariate detection limits of on-line NIR model for extraction process of chlorogenic acid from Lonicera japonica . J Pharm Biomed Anal 2013; 77: 16-20
• 2 McClure WF. 204 years of near infrared technology: 1800–2003. J Near Infrared Spec 2003; 11: 487-518
• 3 Li YK, Shao XG, Cai WS. A consensus least squares support vector regression (LS-SVR) for analysis of near-infrared spectra of plant samples. Talanta 2007; 72: 217-222
• 4 Tsymbal A, Pechenizkiy M, Cunningham P. Diversity in search strategies for ensemble feature selection. Inf Fusion 2005; 6: 83-98
• 5 Breiman L. Bagging predictors. Mach Learn 1996; 24: 123-140
• 6 Galar M, Fernandez A, Barrenechea E, Bustince H, Herrera F. A review on ensembles for the class imbalance problem: bagging-, boosting-, and hybrid-based approaches. IEEE T Syst Man Cy C 2012; 42: 463-484
• 7 Viscarra Rossel RA. Robust modelling of soil diffuse reflectance spectra by “bagging-partial least squares regression”. J Near Infrared Spec 2007; 15: 39
• 8 Schapire RE. The strength of weak learnability. Mach Learn 1990; 5: 197-227
• 9 Webb GI. Multiboosting: A technique for combining boosting and wagging. Mach Learn 2000; 40: 159-196
• 10 Tan C, Wang J, Wu T, Qin X, Li M. Determination of nicotine in tobacco samples by near-infrared spectroscopy and boosting partial least squares. Vib Spectrosc 2010; 54: 35-41
• 11 Zhang MH, Xu QS, Massart DL. Boosting partial least squares. Anal Chem 2005; 77: 1423-1431
• 12 Chinese Pharmacopoeia Commission. Pharmacopeia of Peopleʼs Republic of China. Beijing: China Medical Science Press; 2010: 176-177
• 13 Yi LZ, Yuan DL, Liang YZ, Xie PS, Zhao Y. Quality control and discrimination of Pericarpium Citri Reticulatae and Pericarpium Citri Reticulatae Viride based on high-performance liquid chromatographic fingerprints and multivariate statistical analysis. Anal Chim Acta 2007; 588: 207-215
• 14 Food and Drug Administration. Guidance for industry PAT–a framework for innovative pharmaceutical development, manufacturing, and quality assurance. Rockville, MD: DHHS; 2004
• 15 Li Y, Shi XY, Wu ZS, Guo MY, Xu B, Pan XN, Ma Q, Qiao YJ. Near-infrared for on-line determination of quality parameter of Sophora japonica L. (formula particles): From lab investigation to pilot-scale extraction process. Pharmacogn Mag 2015; 11: 8
• 16 Wu ZS, Xu B, Du M, Sui CL, Shi XY, Qiao YJ. Validation of a NIR quantification method for the determination of chlorogenic acid in Lonicera japonica solution in ethanol precipitation process. J Pharm Biomed Anal 2012; 62: 1-6
• 17 Wang P, Zhang H, Yang HL, Nie L, Zang HC. Rapid determination of major bioactive isoflavonoid compounds during the extraction process of kudzu (Pueraria lobata) by near-infrared transmission spectroscopy. Spectrochim Acta A Mol Biomol Spectrosc 2015; 137: 1403-1408
• 18 Büning PH. Analysis of water in food by near infrared spectroscopy. Food Chem 2003; 82: 107-115
• 19 Tan C, Wu T, Xu ZH, Li WY, Zhang KS. A simple ensemble strategy of uninformative variable elimination and partial least-squares for near-infrared spectroscopic calibration of pharmaceutical products. Vib Spectrosc 2012; 58: 44-49
• 20 Zhang QH, Li QB, Zhang GJ. A strategy of small sample modeling for multivariate regression based on improved Boosting PLS. Anal Methods – UK 2012; 4: 2039-2047
• 21 Williams P. Tutorial: The RPD statistic: a tutorial note. NIR news 2010; 21: 22
• 22 Esbensen K, Geladi P, Larsen A. The RPD myth…. NIR news 2014; 25: 24
• 23 Bauer E, Kohavi R. An empirical comparison of voting classification algorithms: Bagging, boosting, and variants. Mach Learn 1999; 36: 105-139
• 24 Lu WZ, Yuan HF, Xu GT. Modern near infrared spectroscopy analytical technology. Beijing: China Petrochemical Press; 2007
• 25 Liu EH, Zhao P, Duan L, Zheng GD, Guo L, Yang H, Li P. Simultaneous determination of six bioactive flavonoids in Citri Reticulatae Pericarpium by rapid resolution liquid chromatography coupled with triple quadrupole electrospray tandem mass spectrometry. Food Chem 2013; 141: 3977-3983
• 26 Zheng GD, Yang DP, Wang DM, Zhou F, Yang X, Jiang L. Simultaneous determination of five bioactive flavonoids in pericarpium Citri reticulatae from china by high-performance liquid chromatography with dual wavelength detection. J Agric Food Chem 2009; 57: 6552-6557