https://scholars.lib.ntu.edu.tw/handle/123456789/573131
標題: | Prediction of tea theanine content using near-infrared spectroscopy and flower pollination algorithm | 作者: | Ong P Chen S Tsai C.-Y Chuang Y.-K. SUMING CHEN |
關鍵字: | Calibration; Forecasting; Gaussian distribution; Gaussian noise (electronic); Infrared devices; Least squares approximations; Mean square error; Support vector machines; Support vector regression; Flower pollination algorithm; Gaussian process regression; Infrared: spectroscopy; Near Infrared; Near-infrared; Partial least square regression; Selection methods; Support vector machine regressions; Theanine; Wavelength selection; Near infrared spectroscopy; glutamic acid derivative; theanine; algorithm; flower; least square analysis; near infrared spectroscopy; pollination; tea; Algorithms; Flowers; Glutamates; Least-Squares Analysis; Pollination; Spectroscopy, Near-Infrared; Tea | 公開日期: | 2021 | 卷: | 255 | 來源出版物: | Spectrochimica Acta - Part A: Molecular and Biomolecular Spectroscopy | 摘要: | In this study, near-infrared (NIR) spectroscopy was exploited for non-destructive determination of theanine content of oolong tea. The NIR spectral data (400–2500 nm) were correlated with the theanine level of 161 tea samples using partial least squares regression (PLSR) with different wavelengths selection methods, including the regression coefficient-based selection, uninformative variable elimination, variable importance in projection, selectivity ratio and flower pollination algorithm (FPA). The potential of using the FPA to select the discriminative wavelengths for PLSR was examined for the first time. The analysis showed that the PLSR with FPA method achieved better predictive results than the PLSR with full spectrum (PLSR-full). The developed simplified model using on FPA based on 12 latent variables and 89 selected wavelengths produced R-squared (R2) value and root mean squared error (RMSE) of 0.9542, 0.8794 and 0.2045, 0.3219 for calibration and prediction, respectively. For PLSR-full, the R2 values of 0.9068, 0.8412 and RMSEs of 0.2916, 0.3693, were achieved for calibration and prediction. Also, the optimized model using FPA outperformed other wavelengths selection methods considered in this study. The obtained results indicated the feasibility of FPA to improve the predictability of the PLSR and reduce the model complexity. The nonlinear regression models of support vector machine regression and Gaussian process regression (GPR) were further utilized to evaluate the superiority of using the FPA in the wavelength selection. The results demonstrated that utilizing the wavelength selection method of FPA and nonlinear regression model of GPR could improve the predictive performance. ? 2021 Elsevier B.V. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85102654352&doi=10.1016%2fj.saa.2021.119657&partnerID=40&md5=1e3cad1975fa93969b8fee160b3d5a6f https://scholars.lib.ntu.edu.tw/handle/123456789/573131 |
ISSN: | 13861425 | DOI: | 10.1016/j.saa.2021.119657 |
顯示於: | 生物機電工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。