Assessment of matcha sensory quality using hyperspectral microscope imaging technology

Identification and Classification of Coix seed Storage Years Based on Hyperspectral Imaging Technology Combined with Deep Learning

Developing a fast and non-destructive methodology to identify the storage years of Coix seed is important in safeguarding consumer well-being. This study employed the utilization of hyperspectral imaging (HSI) in conjunction with conventional machine learning techniques such as support vector machines (SVM), k-nearest neighbors (KNN), random forest (RF), extreme gradient boosting (XGBoost), as well as the deep learning method of residual neural network (ResNet), to establish identification models for Coix seed samples from different storage years. Under the fusion-based modeling approach, the model's classification accuracy surpasses that of visible to near infrared (VNIR) and short-wave infrared (SWIR) spectral modeling individually. The classification accuracy of the ResNet model and SVM exceeds that of other conventional machine learning models (KNN, RF, and XGBoost). Redundant variables were further diminished through competitive adaptive reweighted sampling feature wavelength screening, which had less impact on the model's accuracy. Upon validating the model's performance using an external validation set, the ResNet model yielded more satisfactory outcomes, exhibiting recognition accuracy exceeding 85%. In conclusion, the comprehensive results demonstrate that the integration of deep learning with HSI techniques effectively distinguishes Coix seed samples from different storage years.

Identifying the Producer and Grade of Matcha Tea through Three-Dimensional Fluorescence Spectroscopy Analysis and Distance Discrimination

The three-dimensional fluorescence spectroscopy features the advantage of obtaining emission spectra at different excitation wavelengths and providing more detailed information. This study established a simple method to discriminate both the producer and grade of matcha tea by coupling three-dimensional fluorescence spectroscopy analysis and distance discrimination. The matcha tea was extracted three times and three-dimensional fluorescence spectroscopies of these tea infusions were scanned; then, the dimension of three-dimensional fluorescence spectroscopies was reduced by the integration at three specific areas showing local peaks of fluorescence intensity, and a series of vectors were constructed based on a combination of integrated vectors of the three tea infusions; finally, four distances were used to discriminate the producer and grade of matcha tea, and two discriminative patterns were compared. The results indicated that proper vector construction, appropriate discriminative distance, and correct steps are three key factors to ensure the high accuracy of the discrimination. The vector based on the three-dimensional fluorescence spectroscopy of all three tea infusions resulted in a higher accuracy than those only based on spectroscopy of one or two tea infusions, and the first tea infusion was more sensitive than the other tea infusion. The Mahalanobis distance had a higher accuracy that was up to 100% when the vector is appropriate, while the other three distances were about 60-90%. The two-step discriminative pattern, identifying the producer first and the grade second, showed a higher accuracy and a smaller uncertainty than the one-step pattern of identifying both directly. These key conclusions above help discriminate the producer and grade of matcha in a quick, accurate, and green method through three-dimensional fluorescence spectroscopy, as well as in quality inspections and identifying the critical parameters of the producing process.

Non-destructive assessment of equivalent umami concentrations in salmon using hyperspectral imaging technology combined with multivariate algorithms

This study utilized equivalent umami concentrations (EUC) to characterize umami intensity in salmon with different freeze-thaw times. A rapid and non-destructive method was established to determine EUC values in salmon which is based on hyperspectral imaging (HSI) system combined with multiple characteristic variable screening methods. The established CARS-PLS model showed greater advantages in correlating the reference values of spectral data with EUC in salmon with Rc of 0.9012, Rp of 0.9009, RMSECV of 0.82, and RMSEP of 0.88. The model was employed pixel-wise to visualize the distribution of EUC with different freeze-thaw times, which demonstrated the reduction of EUC value with the increasing of freeze-thaw times. Therefore, this reseearch showed hyperspectral imaging (HSI) system combined with chemometrics possesses a substantial capability to predict and visualize the EUC of salmon, which would provide an intuitive understanding of salmon quality prediction and detection.

Effect of three milling processes (cyclone-, bead- and stone-millings) on the quality of matcha: Physical properties, taste and aroma

Analysis of three matcha (cyclone-, bead- and stone-milled) revealed differences in their sizes and surface morphologies. Using liquid chromatography, 4 sugars, 6 organic acids, 18 amino acids and 9 polyphenols were detected in all matcha samples and shown to present in different amount. Moreover, 108 volatile compounds were detected and 30 potential flavour-contributing compounds were quantified by gas chromatography time-of-flight mass spectrometry using headspace-stir bar sorptive extraction-thin-film solid-phase microextraction (HS-SBSE-TFSPME). Sensory evaluation by a trained panel found that the matcha samples possess different notes (cyclone-milled: leafy; bead-milled: fishy; and stone-milled: roasty) which is supported by the volatile compound analysis. Finally, the three matcha were differentiated based on non-volatile and volatile components using principal component analysis, and the correlation between chemical composition and sensory evaluation data was carried out using partial least square regression. In conclusion, milling processes clearly affected the physical, chemical and sensory qualities of matcha.

Physicochemical indicators coupled with multivariate analysis for comprehensive evaluation of matcha sensory quality

The sensory quality of matcha is a pivotal factor in determining consumer acceptance. However, the human sensory panel test is difficult to popularize by virtue of professional requirements and inability to evaluate large samples. The analysis showed that physicochemical indicators of matcha were significantly related to sensory quality. Hence, principal component analysis (PCA) based on selected key physicochemical indicators was proposed to evaluate the sensory quality of matcha in this research. The eight key indicators were selected from twenty-four physicochemical indicators based on least absolute shrinkage and selection operator (LASSO) for the establishment of the PCA comprehensive evaluation model. The results demonstrated that the PCA comprehensive evaluation model achieved superior performance, with -0.895 r_c (correlation coefficient in calibration set) and -0.883 r_p (correlation coefficient in prediction set) for overall sensory quality. This work demonstrated that LASSO-PCA comprehensive evaluation as an objective protocol has great potential in predicting matcha sensory quality.

Effects of stem removal on physicochemical properties and sensory quality of tencha beverages (Camellia sinensis; Chuanxiaoye)

Fresh tea leaves (Camellia sinensis; Chuanxiaoye) used to make tencha tea are a combination of the stem and leaf. Tencha made from the leaf alone is considered a high-quality tencha beverage with a seaweed-like aroma, mellow taste, and a green appearance. However, no study has investigated the differences between these two variants. In this study, the effects of stem removal on physicochemical properties and sensory quality of tencha beverage were investigated. The appearance feature, taste, and aroma were evaluated, and the results indicated that stem removal improved the quality of tencha beverages. The water extract, total free amino acids, total catechin, epigallocatechin gallate, caffeine, and chlorophyll were higher in leaf-only tencha (LOT) than in leaf and stem tencha (LST), whereas the crude fiber and phenol ammonia ratios were lower in LOT than in LST. Principal component analysis and hierarchical clustering analysis further discriminated between the tencha beverages with different stem contents. This study provided a theoretical basis for quality control by adopting a stem-leaf separation process in tencha manufacturing. PRACTICAL APPLICATION: This research provides theoretical guidance for improving tencha quality during manufacturing.