Grades Of Tea Research Articles

Machine learning technique combined with data fusion strategies: A tea grade discrimination platform

It is desirable to give a full-scaled evaluation of vine tea by incorporating both the quality related compounds in high content and the volatile compounds in trace level. The NIR and GC-MS technologies were performed for vine tea grade discrimination through data fusion approaches. Two machine learning methods of random forest (RF) and partial least squares-discrimination analysis (PLS-DA) were carried out to construct the tea grade discrimination platform with eight data driven models. Besides, the Monte-Carlo technology was implemented to acquire more representative results from thirty sub-models. As a result, the mid-level fusion combined with RF (92.38% ± 0.0446%) gave more impressive performance owing to the overall analysis with more balanced matrix, efficient features, and remarkable discriminant ability. The results revealed that the mid-level fusion coupled with RF is a promising method for tea grade identification and have great potential to guarantee the food quality.

Characterization of different grades of Jiuqu hongmei tea based on flavor profiles using HS-SPME-GC-MS combined with E-nose and E-tongue

In order to distinguish different grades of Jiuqu hongmei tea (black tea), four different grades of Jiuqu hongmei tea were used as materials in this study: Super Grade (SuG), First Grade (FG), Second Grade (SG), and Third Grade (TG). HS-SPME-GC-MS combined with electronic nose (E-nose) and electronic tongue (E-tongue) technology was used to detect and analyze tea samples. The results showed that 162 volatile substances were identified, mainly alcohols, followed by hydrocarbons, aldehydes, ketones and esters. Twenty-nine volatile compounds were found in all grades of tea samples. The results of heat map analysis showed that the relative contents of five volatile compounds in different grades of Jiuqu hongmei tea were positively correlated with the grades of Jiuqu hongmei tea. By orthogonal partial least squares discriminant analysis (OPLS-DA), 35 different compounds of SuG and FG, 30 different compounds of SG and TG, 34 different compounds of FG and SG were found. Overall, the results indicated that there were significant differences in volatile compounds among different grades of Jiuqu hongmei tea, and the use of HS-SPME-GC-MS combined with E-nose and E-tongue could provide a scientific reference method as an effective tool for detecting flavor characteristics of other types of black tea grades.

Multiple-Sensor Detection System Design for Tea Identification Based on Mutual Information Array Optimization Scheme

In this paper, a multi-metal oxide sensor (MOS) detection system is developed for the identification of different grades of tea leaves. To cope with the interference brought by redundant information and further improve the detection capability of the system and reduce the number of sensors, sensor array optimization algorithms are further implemented. The main idea of sensor array optimization is to select sensors according to evaluation index which ranks the importance of sensors. This paper optimizes the sensor array based on information theory. Specifically, a weighted modified mutual information optimization algorithm that simultaneously considers relevancy, redundancy, and complementarity is developed. The experimental results show that the weighted modified mutual information optimization method can obtain the best system performance with the minimum number of sensors.

Investigating partial least squares discriminant analysis and hierarchical modelling of short wave infrared hyperspectral imaging data to distinguish production area and quality of rooibos (Aspalathus linearis)

Short wave infrared hyperspectral imaging was tested for its ability to distinguish rooibos tea ( Aspalathus linearis) based on production area and quality grade, with the aim to replace time-consuming sensory analysis in the industry. The number of latent variables and model parameters of the calibration model were optimised by cross-validation. Classification error rates were used to evaluate the performance of the models in classifying rooibos based on production area and quality grade. The production area of rooibos was distinguished by applying a partial least square-discriminant analysis model with second derivative pre-processing, followed by mean centering and inclusion of nine LVs. The model could successfully distinguish between the two production areas and had a classification accuracy of 100% for the prediction set. To distinguish between different quality grades, a hierarchical model with second derivative pre-processing was developed. Grade A could be distinguished successfully from grades B, C and D (class BCD) with 100% accuracy and grade D could be distinguished from grades B and C (class BC) with 96% accuracy. However, the model was less accurate to distinguish between grade B and C samples, with prediction accuracies of 82 and 66% for B and C, respectively. Application of near infrared hyperspectral imaging therefore offers the potential to replace the use of sensory analysis in the rooibos tea industry to predict production area and quality grade of this herbal tea.

Sorting of Fresh Tea Leaf Using Deep Learning and Air Blowing

The sorting of machine-picked fresh tea leaves after mechanized harvesting remains a challenge because of the complex morphological characteristics and physicochemical properties of fresh tea leaves. First, the recognition results of four types of models, namely, YOLOv5, YOLOv3, Fast RCNN, and SSD, were compared. It was found that YOLOv5, with guaranteed recognition accuracy, had a recognition speed of 4.7 ms/frame (about four times that of the second ranked YOLOv3). Therefore, this study presents a novel fresh tea leaf sorting system that provides rapid and high-precision multi-channel sorting for four grades of tea leaves using a tea leaf recognition model based on the You Only Look Once (YOLOv5) deep learning model. Subsequently, a raw dataset, consisting of 6400 target images of different grades and different moisture contents, was used to evaluate three different optimization methods. Among these, the Stochastic Gradient Descent (SGD) optimization method was found to provide the best model training results with an average recognition accuracy of 98.2%. In addition, the recognition efficacy of the recognition model was found to be positively correlated with the gradient coverage of tea’s moisture content in the training set. Theoretical analysis was then conducted, along with the experimental investigation of the air-blowing force on the fresh tea leaves in the sorting process, with 30° determined to be the optimal air-blowing angle. Finally, the overall results showed that the construction of the full moisture content training set enabled a model recognition accuracy of up to 88.8%, a recall of 88.4%, a recognition speed of 4.7 ms/frame, and an overall sorting accuracy of 85.4%. This result is promising for multi-channel sorting of fresh tea leaf grades in complex situations, and as such provides a strong basis for the application of tea leaf sorting equipment.

Automated tea quality identification based on deep convolutional neural networks and transfer learning

AbstractDifferent quality grades of tea tend to have a high degree of similarity in appearance. Traditional image‐based identification methods have limited effects, while complex deep learning architectures require much data and long‐term training. In this paper, two tea quality identification methods based on deep convolutional neural networks and transfer learning are proposed. Different types and quality of tea images are collected by a self‐designed computer vision system to form a data set, which is small‐scale and of high inter‐ and intraclass similarity. The first method uses three simplified convolutional neural network (CNN) models with different image input sizes to identify the quality of tea. The second method performs transfer learning to identify the tea quality by fine‐tuning the mature AlexNet and ResNet50 architecture. Classification performance and model complexity are measured and compared. The related application software is also developed. The results show that the performance of the CNN models and the transfer learning models are close, and both can achieve high identification accuracy. However, the complexity of the CNN models is two to three orders of magnitude lower than that of the transfer learning models. The study shows that deep CNNs and transfer learning have great potential to be rapid and effective methods for automated tea quality identification tasks with high inter‐ and intrasimilarity.

Accurate Classification of Chunmee Tea Grade Using NIR Spectroscopy and Fuzzy Maximum Uncertainty Linear Discriminant Analysis.

The grade of tea is closely related to tea quality, so the identification of tea grade is an important task. In order to improve the identification capability of the tea grade system, a fuzzy maximum uncertainty linear discriminant analysis (FMLDA) methodology was proposed based on maximum uncertainty linear discriminant analysis (MLDA). Based on FMLDA, a tea grade recognition system was established for the grade recognition of Chunmee tea. The process of this system is as follows: firstly, the near-infrared (NIR) spectra of Chunmee tea were collected using a Fourier transform NIR spectrometer. Next, the spectra were preprocessed using standard normal variables (SNV). Then, direct linear discriminant analysis (DLDA), maximum uncertainty linear discriminant analysis (MLDA), and FMLDA were used for feature extraction of the spectra, respectively. Finally, the k-nearest neighbor (KNN) classifier was applied to classify the spectra. The k in KNN and the fuzzy coefficient, m, were discussed in the experiment. The experimental results showed that when k = 1 and m = 2.7 or 2.8, the accuracy of the FMLDA could reach 98.15%, which was better than the other two feature extraction methods. Therefore, FMLDA combined with NIR technology is an effective method in the identification of tea grade.

Determination of Tibetan tea quality by hyperspectral imaging technology and multivariate analysis

Tibetan tea is a dark tea native to Ya'an, and its taste and quality are closely related to the contents of tea polyphenols (TPs) and free amino acids (FAAs). In this study, TPs and FAAs were determined by chemometrics and the grades of Tibetan tea were distinguished. Then, hyperspectral data were collected, a variety of preprocessing methods were used to preprocess the spectral data, and principal component analysis (PCA) was used for feature dimensionality reduction. Results showed that the combination of the preprocessing method and machine learning (ML) could achieve a higher prediction effect. Savitzky Golay (SG)-Standard Normal Variable (SNV)-PCA-Extratree had the best predictive ability for TPs (Rp2=0.9248, RMSEP=0.4842, and RPD=3.646). For detecting FAAs, SG-Multiplicative Scatter Correction (MSC)-PCA-Extratree had the best predictive ability (Rp2=0.8736, RMSEP=0.159, and RPD=2.813). In addition, tea grade can be determined by SG-MSC-PCA-Support Vector Machine (SVM) with 100% accuracy, recall, and precision. In sum, hyperspectral imaging technology (HSI) can be used as an alternative method for rapid, non-destructive testing of tea quality.

Rapid Characterization of Black Tea Taste Quality Using Miniature NIR Spectroscopy and Electronic Tongue Sensors.

The taste of tea is one of the key indicators in the evaluation of its quality and is a key factor in its grading and market pricing. To objectively and digitally evaluate the taste quality of tea leaves, miniature near-infrared (NIR) spectroscopy and electronic tongue (ET) sensors are considered effective sensor signals for the characterization of the taste quality of tea leaves. This study used micro-NIR spectroscopy and ET sensors in combination with data fusion strategies and chemometric tools for the taste quality assessment and prediction of multiple grades of black tea. Using NIR features and ET sensor signals as fused information, the data optimization based on grey wolf optimization, ant colony optimization (ACO), particle swarm optimization, and non-dominated sorting genetic algorithm II were employed as modeling features, combined with support vector machine (SVM), extreme learning machine and K-nearest neighbor algorithm to build the classification models. The results obtained showed that the ACO-SVM model had the highest classification accuracy with a discriminant rate of 93.56%. The overall results reveal that it is feasible to qualitatively distinguish black tea grades and categories by NIR spectroscopy and ET techniques.

Comparative analysis of different grades of Tieguanyin oolong tea based on metabolomics and sensory evaluation

To develop objective methods of oolong tea grading for importers and customs, metabolomics and sensory evaluation were applied to screen the characteristic compounds associated with Tieguanyin (TGY) tea grades T, 1, 2, and 3, and types (fresh scent flavor and high fragrance). With decreasing TGY grade/quality, the astringency and content of most flavonoid glycosides increased (especially catechin and epicatechin). The floral aroma of fresh scent flavor TGY decreased, and the roasted aroma of high-fragrance TGY increased with decreasing TGY grade. Five non-volatile compounds (epicatechin gallate, quercetin-3-O-galactoside, quercetin-3-O-rutinoside, epicatechin, and gallocatechin) and five volatile compounds (benzyl benzoate, β-phenylethyl acetate, 6-methyl-5-hepten-2-one, heptanal, and (E)-2-hexenal) were identified, which could readily distinguish different grades of fresh scent flavor and high fragrance TGY by quantitative chemical analysis. Lower grades of TGY had inferior flavor, but higher antioxidant capacity.

Implementasi Jaringan Syaraf Tiruan Backpropagation Pada Klasifikasi Grade Teh Hitam

Black tea is the most widely produced type of tea in Indonesia, where Indonesia itself is the 5th largest black tea exporter in the world. According to the provisions of SNI-1902-2016, the quality requirements of black tea through appearance include the shape, size and weight (density), and the color of the black tea particles themselves. This study aims to determine the workings of the backpropagation method and the implementation of python on black tea grade classification, and to determine the level MSE of accuracy in the results of black tea grade classification using backpropagation. The model used in this study uses 4 input layers, 5 hidden layers, and 3 output layers. In the input layer, 4 input variables are used, namely shape, size, density, and color. The results of the classification using backpropagation with a number of iterations of 1000 iterations on the training data obtained an error of 0.096.

Characterization of Congou Black Tea by an Electronic Nose with Grey Wolf Optimization (GWO) and Chemometrics

The aroma indicator is an important factor in evaluating the quality and grade of black tea and is vital in preventing fraud and reducing financial losses. A rapid method for the characterization of Congou black tea is described using an electronic nose (EN) with grey wolf optimization (GWO) and chemometrics. First, the aroma qualities of the tea were determined by the EN for 700 samples of seven grades and converted into 10 characteristic values. The GWO algorithm was used to optimize the aroma indicators of the EN sensors. Discrimination models based upon the optimized odor sensor features and partial least squares discriminant analysis, k-nearest neighbor (KNN), extreme learning machine, and support vector machine were created to assess the quality of the samples. The results showed that the KNN model constructed with the five odor sensor response values optimized by the GWO algorithm performed best with an accuracy of 97.85%. The results demonstrate that the EN is suitable for the rapid assessment of the quality and grades of Congou black tea products.

Rapid authentication of green tea grade by excitation-emission matrix fluorescence spectroscopy coupled with multi-way chemometric methods

Rapid authentication of green tea grade by excitation-emission matrix fluorescence spectroscopy coupled with multi-way chemometric methods

GC-MS-based untargeted metabolomics reveals the key volatile organic compounds for discriminating grades of Yichang big-leaf green tea

In this work, headspace gas chromatography coupled to mass spectrometry (HS-GC-MS) combined with multivariate statistical analysis was applied to reveal volatile markers from different grades of Yichang big-leaf green tea (YBGT). A total of 94 volatile organic compounds (VOCs) were detected and identified, which can be categorized as alkanes, terpene, aromatics, ketone, ester, alcohol, heterocyclic compounds, aldehyde, olefin, acid, amine, and nitrogen compounds. The differences between low-grade and high-grade YBGT were demonstrated by principal component analysis (PCA) and hierarchical cluster analysis (HCA). Based on orthogonal partial least squares discriminant analysis (OPLS-DA), 19 VOCs were screened as markers for the discrimination of first-grade and second-grade YBGT, and 25 VOCs were screened as markers to distinguish first-grade from third-grade YBGT. Among them, 16 VOCs are common, which can be used as characteristic markers to distinguish low-grade from high-grade YBGT. Overall, our findings indicated that there are significant differences in VOCs among different grades of YBGT, and HS-GC-MS in combination with chemometric multivariate statistical analysis can be extended as a reliable strategy for discriminating grades of other Chinese green teas.

Applications of Electronic Nose Coupled with Statistical and Intelligent Pattern Recognition Techniques for Monitoring Tea Quality: A Review

Tea is the most widely consumed non-alcoholic beverage worldwide. In the tea sector, the high demand for tea has led to an increase in the adulteration of superior tea grades. The procedure of evaluating tea quality is difficult to assure the highest degree of tea safety in the context of consumer preferences. In recent years, the advancement in sensor technology has replaced the human olfaction system with an artificial olfaction system, i.e., electronic noses (E-noses) for quality control of teas to differentiate the distinct aromas. Therefore, in this review, the potential applications of E-nose as a monitoring device for different teas have been investigated. The instrumentation, working principles, and different gas sensor types employed for E-nose applications have been introduced. The widely used statistical and intelligent pattern recognition methods, namely, PCA, LDA, PLS-DA, KNN, ANN, CNN, SVM, etc., have been discussed in detail. The challenges and the future trends for E-nose devices have also been highlighted. Overall, this review provides the insight that E-nose combined with an appropriate pattern recognition method is a powerful non-destructive tool for monitoring tea quality. In future, E-noses will undoubtedly reduce their shortcomings with improved detection accuracy and consistency by employing food quality testing.

Relationship between the turbidity difference and the grade of green tea under Ca2+ acceleration: A preliminary study.

The grade of green tea indicates its intrinsic quality and guides consumers when purchasing. Simple, accessible, and on-site determination of green tea grades is essential for consumers and regulators. In this study, we assumed that the turbidity difference in green tea might indicate its grade, and our results confirmed this hypothesis. The turbidity difference was measured in green tea infusions before and after the Ca2+ acceleration. For the same kind of green tea, it was found that higher grades of green tea had larger turbidity differences. Effects of brewing temperature, brewing time, Ca2+ concentration, and Ca2+ treatment time on the turbidity of green tea infusions were analyzed, and their optimal values were obtained. This study demonstrates that applying the turbidity difference and Ca2+ acceleration could be an accessible method for the on-site determination of green tea grades.

Tea Category Identification Using Wavelet Signal Reconstruction of Hyperspectral Imagery and Machine Learning

Accurately distinguishing the types of tea is of great significance to the pricing, production, and processing of tea. The similarity of the internal spectral characteristics and appearance characteristics of different types of tea greatly limits further research on tea identification. However, wavelet transform can simultaneously extract time domain and frequency domain features, which is a powerful tool in the field of image signal processing. To address this gap, a method for tea recognition based on a lightweight convolutional neural network and support vector machine (L-CNN-SVM) was proposed, aiming to realize tea recognition using wavelet feature figures generated by wavelet time-frequency signal decomposition and reconstruction. Firstly, the redundant discrete wavelet transform was used to decompose the wavelet components of the hyperspectral images of the three teas (black tea, green tea, and yellow tea), which were used to construct the datasets. Secondly, improve the lightweight CNN model to generate a tea recognition model. Finally, compare and evaluate the recognition results of different models. The results demonstrated that the results of tea recognition based on the L-CNN-SVM method outperformed MobileNet v2+RF, MobileNet v2+KNN, MobileNet v2+AdaBoost, AlexNet, and MobileNet v2. For the recognition results of the three teas using reconstruction of wavelet components LL + HL + LH, the overall accuracy rate reached 98.7%, which was 4.7%, 3.4%, 1.4%, and 2.0% higher than that of LH + HL + HH, LL + HH + HH, LL + LL + HH, and LL + LL + LL. This research can provide new inspiration and technical support for grade and quality assessment of cross-category tea.

Green tea grades identification via Fourier transform near‐infrared spectroscopy and weighted global fuzzy uncorrelated discriminant transform

AbstractThe extraction of near‐infrared (NIR) spectral discrimination information is important for the NIR spectral classification task. Some discriminant information extraction algorithms such as linear discriminant analysis (LDA), uncorrelated discriminant transform (UDT), and fuzzy uncorrelated discriminant transform (FUDT) use the sample mean to calculate the total scattering matrix. However, the calculation of the sample mean will be affected by abnormal samples, which will affect the extraction of discriminant information. To solve this problem, this article proposes an improved discriminant information extraction algorithm called weighted global fuzzy uncorrelated discriminant transform (WGFUDT). The algorithm uses the Euclidean distance between the training samples to weight the training samples and assigns a smaller weight to the abnormal data to reduce its effect on the sample mean. The algorithm was used for the grade identification of two green teas (Huangshan Maofeng tea and Mee tea). The results show that the classification accuracies of WGFUDT on Mee tea and Huangshan Maofeng tea are 97.22% and 99.07%, respectively. Compared with LDA, UDT and FUDT, WGFUDT can obtain more spectral discriminant information and has higher accuracy in grade identification of Huangshan Maofeng tea and Mee tea.Practical ApplicationsSome traditional discriminant information extraction algorithms sometimes cannot extract enough discriminant information, which will affect the recognition rate of tea grades. WGFUDT can extract more discriminant information in the face of green tea spectral information and achieve higher accuracy. WGFUDT for green tea grade identification is fast and effective.

Establishment of a rapid detection model for the sensory quality and components of Yuezhou Longjing tea using near-infrared spectroscopy

Quantitative prediction models for sensory quality scores, total catechins, and caffeine based on near-infrared spectroscopy were established for different quality grades of Yuezhou Longjing tea. One-way ANOVA and multiple comparison test analyses were first conducted on the obtained sensory quality scores and physical and chemical quality indices to check the accuracy and reliability of the experimental data. There were significant differences in the sensory quality, total catechins, and caffeine of different grades of tea. Secondly, the obtained near-infrared spectrum data were preprocessed, and then the competitive adaptive reweighted sampling (CARS) and variables combination population analysis combined with iterative retained information variable algorithm (VCPA-IRIV) were used to screen the optimal characteristic wavenumbers of each quality index. Along with principal component analysis (PCA) to establish prediction models for the partial least squares regression (PLSR), support vector regression (SVR), and random forest algorithm (RF). The results showed that the best predictive models for sensory scores, total catechins, and caffeine were VCPA-IRIV + SVR, VCPA-IRIV + RF, and CARS + SVR, and the relative percent deviation (RPD) were 2.485, 2.584, and 2.873, respectively. Indicates that the model has good predictive performance. In conclusion, it is feasible to evaluate the quality of Yuezhou Longjing tea with near-infrared spectroscopy.

Study on the establishment of quality discrimination model of Longjing 43 green tea (Camellia sinensis(L.) Kuntze)

Traditionally, the quality grade of green tea depends on the results of sensory evaluation. However, there are some problems, such as the strong subjectivity, the susceptibility to environmental interference and the need for standard samples. In this paper, Longjing green tea in Qiantang producing region is taken as the research object. The traditional sensory evaluation, chemical analysis and intelligent sensory technology are combined. We obtain a quality discrimination model of which the sensory scores are represented by physical and chemical data. The results indicate the relationship between chemical components and sensory evaluation which is established by non-linear models such as partial least squares and partial least squares discriminant analysis has a better performance of prediction accuracy. Both of the PLS and PLS-DA methods achieve better discrimination for the tea grades based on the green tea. The analysis results of the two methods are accordance for calibration set and validation set.