Using FTIR spectra and pattern recognition for discrimination of tea varieties

Abstract

In order to classify typical Chinese tea varieties, Fourier transform infrared spectroscopy (FTIR) of tea polysaccharides (TPS) was used as an accurate and economical method. Partial least squares (PLS) modeling method along with a self-organizing map (SOM) neural network method was utilized due to the diversity and heterozygosis between teas. FTIR spectra results of tea extracts after spectra preprocessing were used as input data for PLS and SOM multivariate statistical analyses respectively. The predicted correlation coefficient of optimization PLS model was 0.9994, and root mean square error of calibration and cross-validation (RMSECV) was 0.03285. The features of PLS can be visualized in principal component (PC) space, contributing to discover correlation between different classes of spectra samples. After that, a data matrix consisted of the scores on the selected 3PCs computed by principle component analysis (PCA) and the characteristic spectrum data was used as inputs for training of SOM neural network. Compared with the PLS linear technique's recognition rate of 67% only, the correct recognition rate of the PLS-SOM as a non-linear classification algorithm to differentiate types of tea reaches up to 100%. And the models become reliable and provide a reasonable clustering of tea varieties.

Discrimination of six tea categories coming from different origins depending on polyphenols, caffeine, and theanine combined with different discriminant analysis

“…In one study, Fourier transform infrared spectra and pattern recognition were combined with modern chemometrics to classify and provide a reasonable clustering of typical Chinese tea varieties. [5] Elsewhere, black teas from several plantation estates in Sri Lanka were all well discriminated through fluorescence spectroscopy and linear discriminant analysis. [6] Electronic nose technique has been used to classify tea aroma and evaluate tea quality, [7][8][9] and to categorize tea varieties.…”

Optimization of a Novel Kinetic-Assisted Infundation for Rich-Egcg and Polyphenols of White Tea (Camellia Sinensis) Using Central Composite Design

“…High polyphenols content (especially EGCG) in white tea extract powder will be easily analyzed using FTIR instruments [29]. In general, hydroxyl and carbonyl groups provide vibration bands that are easily detected [30][31][32]. Analysis using FTIR has been done to characterize extracts and medicinal raw materials.…”

Robust Classification of Tea Based on Multi-Channel LED-Induced Fluorescence and a Convolutional Neural Network

“…The optical method has been widely applied in the field of food classification due to its non-destructive and rapid response characteristics. Absorption spectroscopy is an important method for food quality control, classification and authentication; it mainly includes UV-Vis absorption spectroscopy [1,2], near-infrared (NIR) spectroscopy [3] and mid-infrared spectroscopy [4,5] accompanied with chemometrics including partial least square (PLS) and linear discriminant analysis (LDA). Laser-induced breakdown spectroscopy (LIBS) can excite the trace elements contained in samples, and classify the species according to the trace…”