Classification of Tea Quality Levels Using Near-Infrared Spectroscopy Based on CLPSO-SVM

Rapid quality evaluation of moutan cortex (Paeonia suffruticosa Andrews) by near-infrared spectroscopy and bionic swarm intelligent optimization algorithm

Moutan Cortex (MC), recognized as a traditional Chinese medicinal herb, possesses significant therapeutic properties. The existing quality assessment method only measures the content of one component in MC, which is obviously not comprehensive enough. Besides, the determination process is time-consuming and laborious.Thus, this article presents a novel approach for the rapid, precise, and efficient quality assessment of MC based on near-infrared spectroscopy (NIR) technology in combination with the bionic swarm intelligent optimization algorithms. First, MC samples were collected and acquired with the NIR spectra in diffuse reflectance mode. Second, the content of paeonol, paeoniflorin, and gallic acid in MC was determined by high-performance liquid chromatography, and the content of total flavonoids and phenols was determined by UV-visible spectrophotometry. Afterward, all the measured content was analyzed in correlation with the NIR spectra of MC, and the partial least squares regression method was utilized to build the models. Especially, to improve the models' performance, five famous bionic swarm intelligent optimization algorithms were investigated to perform the wavelength selection. As a result, the models' performance was significantly enhanced. The coefficient of determination (R2) > 0.9 and residual prediction deviation (RPD) > 3 were observed on the calibration set and the prediction set. Thus, we believe that bionic swarm intelligent optimization algorithms have the potential to enhance the performance of quantitative models considerably, which offers substantial support for the quality assessment of MC and shows promising applications in the domain of NIR analysis.

Fluorescence hyperspectral imaging for detection of selenium content in lettuce leaves under cadmium-free and cadmium environments

This study aimed to investigate the feasibility of detecting selenium content in lettuce leaves under complex environments (cadmium-free and cadmium environments) using fluorescence hyperspectral imaging (FHSI). Accordingly, multimodal difference-aware competitive adaptive reweighted sampling (MDCARS) was proposed to select cadmium-related features in complex environments and was integrated with a ResNet-convolutional neural network (RCNN) for the quantitative prediction of selenium content. MDCARS selected features with superior interpretability and model verification outcomes compared with common methods, thereby highlighting its advantages for complex data sources. Additionally, the RCNN performed better than the other models, and it was combined with MDCARS to achieve the optimal prediction of selenium content in lettuce leaves under complex environments, with the R2p, RMSEP and RPD values of 0.8975, 0.0487 mg•kg-1 and 3.1240 respectively. Therefore, FHSI combined with MDCARS and RCNN offers a viable approach for predicting the selenium content in lettuce leaves under complex environments.

Geographical Origin Traceability of Navel Oranges Based on Near-Infrared Spectroscopy Combined with Deep Learning

The quality and price of navel oranges vary depending on their geographical origin, thus providing a financial incentive for origin fraud. To prevent this phenomenon, it is necessary to explore a fast, non-destructive, and precise method for tracing the origin of navel oranges. In this study, a total of 490 Newhall navel oranges were selected from five major production regions in China, and the diffuse reflectance near-infrared spectrum in 4000-10,000 cm-1 were non-invasively collected. We examined seven preprocessing techniques for the spectra, including Savitzky-Golay (SG) smoothing, first derivative (FD), multiplicative scattering correction (MSC), combinations of SG with MSC (SG+MSC), SG with FD (SG+FD), MSC with FD (MSC+FD), and three combined (SG+MSC+FD). A one-dimensional convolutional neural network (1DCNN) deep learning model for geographical origin tracing of navel orange was established, and five machine learning algorithms, i.e., partial least squares discriminant analysis (PLS-DA), linear discriminant analysis (LDA), support vector machine (SVM), random forest (RF), and back-propagation neural network (BPNN), were compared with 1DCNN. The results show that the 1DCNN model based on the SG+FD preprocessing method achieved the optimal performance for the testing set, with prediction accuracy, precision, recall, and F1-score of 97.92%, 98%, 97.95%, and 97.90%, respectively. Therefore, NIRS combined with deep learning has a significant research and application value in the rapid, nondestructive, and accurate geographical origin traceability of agricultural products.

Fusion of convolutional neural network with XGBoost feature extraction for predicting multi-constituents in corn using near infrared spectroscopy

Near-infrared (NIR) spectroscopy has been widely utilized to predict multi-constituents of corn in agriculture. However, directly extracting constituent information from the NIR spectra is challenging due to many issues such as broad absorption band, overlapping and non-specific nature. To solve these problems and extract implicit features from the raw data of NIR spectra to improve performance of quantitative models, a one-dimensional shallow convolutional neural network (CNN) model based on an eXtreme Gradient Boosting (XGBoost) feature extraction method was proposed in this paper. The leaf node feature information in the XGBoost was encoded and reconstructed to obtain the implicit features of raw data in the NIR spectra. A two-parametric Swish (TSwish or TS) activation function was proposed to improve the performance of CNN, and the elastic net (EN) was also applied to avoid the overfitting problem of the CNN model. Performance of the developed XGBoost-CNN-TS-EN model was evaluated using two public NIR spectroscopy datasets of corn and soil, and the obtained determination coefficients (R2) for moisture, oil, protein, and starch of the corn on test set were 0.993, 0.991, 0.998, and 0.992, respectively, with that of the soil organic matter being 0.992. The XGBoost-CNN-TS-EN model exhibits superior stability, good prediction accuracy, and generalization ability, demonstrating its great potentials for quantitative analysis of multi-constituents in spectroscopic applications.

Handheld NIR Spectroscopy Combined with a Hybrid LDA-SVM Model for Fast Classification of Retail Milk

The EU market offers different types of milk, distinguished by origin, production method, processing technology, fat content, and other characteristics, which are often detailed on product labels. In this context, ensuring the authenticity of milk is crucial for maintaining standards and preventing fraud. Various food authenticity techniques have been employed to achieve this. Among them, near-infrared (NIR) spectroscopy is valued for its non-destructive and rapid analysis capabilities. This study evaluates the effectiveness of a miniaturized NIR device combined with support vector machine (SVM) algorithms and LDA feature selection to discriminate between four commercial milk types: high-quality fresh milk, milk labeled as mountain product, extended shelf-life milk, and TSG hay milk. The results indicate that NIR spectroscopy can effectively classify milk based on the type of milk, relying on different production systems and heat treatments (pasteurization). This capability was greater in distinguishing high-quality mountain and hay milk from the other types, while resulting in less successful class assignment for extended shelf-life milk. This study demonstrated the potential of portable NIR spectroscopy for real-time and cost-effective milk authentication at the retail level.

Rapid Classification of Milk Using a Cost-Effective Near Infrared Spectroscopy Device and Variable Cluster-Support Vector Machine (VC-SVM) Hybrid Models

Removing fat from whole milk and adding water to milk to increase its volume are among the most common food fraud practices that alter the characteristics of milk. Usually, deviations from the expected fat content can indicate adulteration. Infrared spectroscopy is a commonly used technique for distinguishing pure milk from adulterated milk, even when it comes from different animal species. More recently, portable spectrometers have enabled in situ analysis with analytical performance comparable to that of benchtop instruments. Partial Least Square (PLS) analysis is the most popular tool for developing calibration models, although the increasing availability of portable near infrared spectroscopy (NIRS) has led to the use of alternative supervised techniques, including support vector machine (SVM). The aim of this study was to develop and implement a method based on the combination of a compact and low-cost Fourier Transform near infrared (FT-NIR) spectrometer and variable cluster-support vector machine (VC-SVM) hybrid model for the rapid classification of milk in accordance with EU Regulation EC No. 1308/2013 without any pre-treatment. The results obtained from the external validation of the VC-SVM hybrid model showed a perfect classification capacity (100% sensitivity, 100% specificity, MCC = 1) for the radial basis function (RBF) kernel when used to classify whole vs. not-whole and skimmed vs. not-skimmed milk samples. A strong classification capacity (94.4% sensitivity, 100% specificity, MCC = 0.95) was also achieved in discriminating semi-skimmed vs. not-semi-skimmed milk samples. This approach provides the dairy industry with a practical, simple and efficient solution to quickly identify skimmed, semi-skimmed and whole milk and detect potential fraud.

Geographical origin identification of Khao Dawk Mali 105 rice using combination of FT-NIR spectroscopy and machine learning algorithms

The mislabelled Khao Dawk Mali 105 rice coming from other geographical region outside the Thung Kula Rong Hai region is extremely profitable and difficult to detect; to prevent retail fraud (that adversely affects both the food industry and consumers), it is vital to identify geographical origin. Near infrared spectroscopy can be used to detect the specific content of organic moieties in agricultural and food products. The present study implemented the combinatorial method of FT-NIR spectroscopy with chemometrics to identify geographical origin of Khao Dawk Mali 105 rice. Rice samples were collected from 2 different region including the north and northeast of Thailand. NIR spectra data were collected in range of 12,500 - 4,000 cm-1 (800-2,500 nm). Five machine learning algorithms including linear discriminant analysis (LDA), partial least squares discriminant analysis (PLS-DA), C-support vector classification (C-SVC), backpropagation neural networks (BPNN), hybrid principal component analysis-neural network (PC-NN) and K-nearest neighbors (KNN) were employed to classify NIR data of rice samples with full wavelength and selected wavelength by Extremely Randomized Trees (Extra trees) algorithm. Based on the findings, geographical origin of rice could be specified quickly, cheaply, and reliably using combination of NIRS and machine learning. All models creating by full wavelength and selected wavelength exhibited accuracy between 65 and 100 % for identifying geographical region of rice. It was proven that NIR spectroscopy may be used for the quick and non-destructive identification of geographical origin of Khao Dawk Mali 105 rice.

A novel near infrared spectroscopy analytical strategy for soil nutrients detection based on the DBO-SVR method

Soil is the basis of agricultural production and accessing accurate information on soil nutrients is essential. Traditional methods of soil composition detection, which are based on chemical analysis, are characterized by being costly and polluting. Spectroscopic analysis has proven to be a rapid, non-destructive and effective technique for predicting soil properties in general and potassium, phosphorus and organic matter in particular. However, previous research on soils has rarely combined optimization algorithms with machine learning techniques, which has led to suboptimal model accuracy and convergence speed. In this study, a total of 184 soil samples were collected from three cities of Linhai, Yueqing and Longyou County, Zhejiang Province, China. After measuring pH values, alkali-hydrolyzable nitrogen (SAN), available phosphorus (SAP), available potassium (SAK) and soil organic matter (SOM) contents, along with their corresponding spectroscopic measurements, nine pretreatment methods and their combinations are adopted. A novel assessment model, integrating support vector machine and dung beetle optimization algorithm (DBO-SVR), is proposed to predict pH values and SAN, SAP, SAK, SOM content. Meanwhile, the DBO algorithm is compared with three mainstream optimization algorithms (particle swarm optimization (PSO), whale optimization algorithm (WOA) and grey wolf optimizer (GWO)). Results showed that the DBO-SVR model was shown best performance with Rp, RMSEP and RPD of 0.9842, 0.1306, 5.6485 respectively for prediction of pH value, with Rp, RMSEP and RPD of 0.8802, 15.0574 mg/kg and 2.0508, respectively for assessment of SAN content, with Rp, RMSEP and RPD of 0.9790, 12.8298 mg/kg, and 4.5132, respectively for assessment of SAP content, with Rp, RMSEP and RPD of 0.8677, 22.5107 mg/kg, and 1.9546, respectively for assessment of SAK content, and with Rp, RMSEP and RPD of 0.9273, 2.6427g/kg , and 2.1821, respectively for assessment of SOM content. This study demonstrates that the combination of near-infrared (NIR) spectroscopy and the DBO-SVR algorithm is capable of predicting soil nutrient composition with greater accuracy and efficiency.

Study on the quality of Corydalis Rhizoma in Zhejiang based on multidimensional evaluation method

ETHNOPHARMACOLOGICAL RELEVANCE

The quality requirements of Corydalis Rhizoma (CR) in different producing areas are uniform, resulting in uneven efficacy. As a genuine producing area, the effective quality control of CR in Zhejiang Province (ZJ) could provide a theoretical basis for the rational application of medicinal materials.

AIM OF THE STUDY

The purpose of this study was to effectively distinguish the CR inside and outside ZJ, and provided a theoretical basis for the quality control and material basis research of ZJ CR.

MATERIALS AND METHODS

The core components of ZJ CR could be identified by HPLC combined with chemometrics screening, and the quality of CR from different producing areas was evaluated by a genetic algorithm-back propagation (GA-BP) neural network. Chromaticity and near-infrared (NIR) spectroscopy were used to identify CR inside and outside ZJ, and rapid content prediction was realized. The analgesic effect of CR in different regions was compared by a zebrafish analgesic experiment. Analgesic experiments in rats and analysis of the research status of quality components were used to screen the quality control components of ZJ CR.

RESULTS

The contents of palmatine hydrochloride (YSBMT), dehydrocorydaline (TQZJJ), tetrahydropalmatine (YHSYS), tetrahydroberberine (SQXBJ), corydaline (YHSJS), stylopine (SQHLJ), and isoimperatorin (YOQHS) in ZJ CR were higher than those in CR from outside ZJ, but the content of protopine (YAPJ) and berberine hydrochloride (YSXBJ) was lower than that in CR from outside ZJ. YHSJS and SQHLJ could be used as the core components to identify ZJ CR. The GA-BP neural network showed that the relative importance of ZJ CR was the strongest. Chroma-content correlation analysis and the NIR qualitative model could effectively distinguish CR from inside and outside of ZJ, and the NIR quantitative model could quickly predict the content of CR from inside and outside of ZJ. Zebrafish experiments showed that ZJ, Shaanxi (SX), Henan (HN), and Sichuan (SC) CR had significant analgesic effects, while Hebei (HB) CR had no significant analgesic effect. Overall comparison, the analgesic effect of ZJ CR was better than that of CR outside ZJ. The comprehensive score of the grey correlation degree between YAPJ, YSBMT, YSXBJ, TQZJJ, YHSYS, YHSJS, SQXBJ, and SQHLJ were higher than 0.9, and the research frequency were extremely high.

CONCLUSIONS

The relative importance of the content and origin of most components of ZJ CR was higher than that of CR outside ZJ. The holistic analgesic effect of ZJ CR was better than that of CR outside ZJ, but slightly lower than that of SX CR. YHSJS and SQHLJ could be used as the core components to identify ZJ CR. YAPJ, YSBMT, YSXBJ, TQZJJ, YHSYS, SQXBJ, YHSJS, and SQHLJ could be used as the quality control components of ZJ CR. The multidimensional evaluation method used in this study provided a reference for the quality control and material basis research of ZJ CR.

Predictive models for sensory score and physicochemical composition of Yuezhou Longjing tea using near-infrared spectroscopy and data fusion

In this study, NIR quantitative prediction model was established for sensory score and physicochemical components of different varieties and quality grades of Yuezhou Longjing tea. Firstly, L, a, b color factors and diffuse reflection spectral data are collected for each sample. Subsequently, the original spectrum is preprocessed. Three techniques for selecting variables, CARS, BOSS, and SPA, were utilized to extract optimal feature bands. Finally, the spectral data extracted from feature bands were fused with L, a and b color factors to build SVR and PLSR prediction models. enabling the rapid non-destructive discrimination of different varieties and grades of Yuezhou Longjing tea. The outcomes demonstrated that BOSS was the best variable selection technique for sensory score and the distinctive caffeine wavelengths, CARS, however, was the best variable selection technique for catechins distinctive wavelengths. Additionally, the middle-level data fusion-based non-linear prediction models greatly outperformed the linear prediction models. For the prediction models of sensory score, catechins, and caffeine, the relative percent deviation (RPD) values were 2.8, 1.6, and 2.6, respectively, suggesting the good predictive ability of the models. In conclusion, evaluating the quality of the five Yuezhou Longjing tea varieties using near-infrared spectroscopy and data fusion have proved as feasible.

Simultaneous Determination of Four Catechins in Black Tea via NIR Spectroscopy and Feature Wavelength Selection: A Novel Approach

As a non-destructive, fast, and cost-effective technique, near-infrared (NIR) spectroscopy has been widely used to determine the content of bioactive components in tea. However, due to the similar chemical structures of various catechins in black tea, the NIR spectra of black tea severely overlap in certain bands, causing nonlinear relationships and reducing analytical accuracy. In addition, the number of NIR spectral wavelengths is much larger than that of the modeled samples, and the small-sample learning problem is rather typical. These issues make the use of NIRS to simultaneously determine black tea catechins challenging. To address the above problems, this study innovatively proposed a wavelength selection algorithm based on feature interval combination sensitivity segmentation (FIC-SS). This algorithm extracts wavelengths at both coarse-grained and fine-grained levels, achieving higher accuracy and stability in feature wavelength extraction. On this basis, the study built four simultaneous prediction models for catechins based on extreme learning machines (ELMs), utilizing their powerful nonlinear learning ability and simple model structure to achieve simultaneous and accurate prediction of catechins. The experimental results showed that for the full spectrum, the ELM model has better prediction performance than the partial least squares model for epicatechin (EC), epicatechin gallate (ECG), epigallocatechin (EGC), and epigallocatechin gallate (EGCG). For the feature wavelengths, our proposed FIC-SS-ELM model enjoys higher prediction performance than ELM models based on other wavelength selection algorithms; it can simultaneously and accurately predict the content of EC (Rp2 = 0.91, RMSEP = 0.019), ECG (Rp2 = 0.96, RMSEP = 0.11), EGC (Rp2 = 0.97, RMSEP = 0.15), and EGCG (Rp2 = 0.97, RMSEP = 0.35) in black tea. The results of this study provide a new method for the quantitative determination of the bioactive components of black tea.

Garlic Origin Traceability and Identification Based on Fusion of Multi-Source Heterogeneous Spectral Information

The chemical composition and nutritional content of garlic are greatly impacted by its production location, leading to distinct flavor profiles and functional properties among garlic varieties from diverse origins. Consequently, these variations determine the preference and acceptance among diverse consumer groups. In this study, purple-skinned garlic samples were collected from five regions in China: Yunnan, Shandong, Henan, Anhui, and Jiangsu Provinces. Mid-infrared spectroscopy and ultraviolet spectroscopy were utilized to analyze the components of garlic cells. Three preprocessing methods, including Multiple Scattering Correction (MSC), Savitzky-Golay Smoothing (SG Smoothing), and Standard Normalized Variate (SNV), were applied to reduce the background noise of spectroscopy data. Following variable feature extraction by Genetic Algorithm (GA), a variety of machine learning algorithms, including XGboost, Support Vector Classification (SVC), Random Forest (RF), and Artificial Neural Network (ANN), were used according to the fusion of spectral data to obtain the best processing results. The results showed that the best-performing model for ultraviolet spectroscopy data was SNV-GA-ANN, with an accuracy of 99.73%. The best-performing model for mid-infrared spectroscopy data was SNV-GA-RF, with an accuracy of 97.34%. After the fusion of ultraviolet and mid-infrared spectroscopy data, the SNV-GA-SVC, SNV-GA-RF, SNV-GA-ANN, and SNV-GA-XGboost models achieved 100% accuracy in both training and test sets. Although there were some differences in the accuracy of the four models under different preprocessing methods, the fusion of ultraviolet and mid-infrared spectroscopy data yielded the best outcomes, with an accuracy of 100%. Overall, the combination of ultraviolet and mid-infrared spectroscopy data fusion and chemometrics established in this study provides a theoretical foundation for identifying the origin of garlic, as well as that of other agricultural products.

Quantitative Analysis of Bioactive Compounds in Commercial Teas: Profiling Catechin Alkaloids, Phenolic Acids, and Flavonols Using Targeted Statistical Approaches

Tea, an extensively consumed and globally popular beverage, has diverse chemical compositions that ascertain its quality and categorization. In this investigation, we formulated an analytical and quantification approach employing reversed-phase ultra-high-performance liquid chromatography (UHPLC) methodology coupled with diode-array detection (DAD) to precisely quantify 20 principal constituents within 121 tea samples spanning 6 distinct variants. The constituents include alkaloids, catechins, flavonols, and phenolic acids. Our findings delineate that the variances in chemical constitution across dissimilar tea types predominantly hinge upon the intricacies of their processing protocols. Notably, green and yellow teas evinced elevated concentrations of total chemical moieties vis à vis other tea classifications. Remarkably divergent levels of alkaloids, catechins, flavonols, and phenolic acids were ascertained among the disparate tea classifications. By leveraging random forest analysis, we ascertained gallocatechin, epigallocatechin gallate, and epicatechin gallate as pivotal biomarkers for effective tea classification within the principal cadre of tea catechins. Our outcomes distinctly underscore substantial dissimilarities in the specific compounds inherent to varying tea categories, as ascertained via the devised and duly validated approach. The implications of this compositional elucidation serve as a pertinent benchmark for the comprehensive assessment and classification of tea specimens.

CNN-LSTM Neural Network for Identification of Pre-Cooked Pasta Products in Different Physical States Using Infrared Spectroscopy

Infrared (IR) spectroscopy is nondestructive, fast, and straightforward. Recently, a growing number of pasta companies have been using IR spectroscopy combined with chemometrics to quickly determine sample parameters. However, fewer models have used deep learning models to classify cooked wheat food products and even fewer have used deep learning models to classify Italian pasta. To solve these problems, an improved CNN-LSTM neural network is proposed to identify pasta in different physical states (frozen vs. thawed) using IR spectroscopy. A one-dimensional convolutional neural network (1D-CNN) and long short-term memory (LSTM) were constructed to extract the local abstraction and sequence position information from the spectra, respectively. The results showed that the accuracy of the CNN-LSTM model reached 100% after using principal component analysis (PCA) on the Italian pasta spectral data in the thawed state and 99.44% after using PCA on the Italian pasta spectral data in the frozen form, verifying that the method has high analytical accuracy and generalization. Therefore, the CNN-LSTM neural network combined with IR spectroscopy helps to identify different pasta products.

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.

Classification of Tea Leaves Based on Fluorescence Imaging and Convolutional Neural Networks

The development of the smartphone and computer vision technique provides customers with a convenient approach to identify tea species, as well as qualities. However, the prediction model may not behave robustly due to changes in illumination conditions. Fluorescence imaging can induce the fluorescence signal from typical components, and thus may improve the prediction accuracy. In this paper, a tea classification method based on fluorescence imaging and convolutional neural networks (CNN) is proposed. Ultra-violet (UV) LEDs with a central wavelength of 370 nm were utilized to induce the fluorescence of tea samples so that the fluorescence images could be captured. Five kinds of tea were included and pre-processed. Two CNN-based classification models, e.g., the VGG16 and ResNet-34, were utilized for model training. Images captured under the conventional fluorescent lamp were also tested for comparison. The results show that the accuracy of the classification model based on fluorescence images is better than those based on the white-light illumination images, and the performance of the VGG16 model is better than the ResNet-34 model in our case. The classification accuracy of fluorescence images reached 97.5%, which proves that the LED-induced fluorescence imaging technique is promising to use in our daily life.

A Rapid Prediction Method of Moisture Content for Green Tea Fixation Based on WOA-Elman

Fixation is the most critical step in the green tea process. Hence, this study developed a rapid and accurate moisture content detection for the green tea fixation process based on near-infrared spectroscopy and computer vision. Specifically, we created a quantitative moisture content prediction model appropriate for the processing of green tea fixation. First, we collected spectrum and image information of green tea fixation leaves, utilizing near-infrared spectroscopy and computer vision. Then, we applied the partial least squares regression (PLSR), support vector regression (SVR), Elman neural network (ENN), and Elman neural network based on whale optimization algorithm (WOA-ENN) methods to build the prediction models for single data (data from a single sensor) and mid-level data fusion, respectively. The results revealed that the mid-level data fusion strategy combined with the WOA-ENN model attained the best effect. Namely, the prediction set correlation coefficient (Rp) was 0.9984, the root mean square error of prediction (RMSEP) was 0.0090, and the relative percent deviation (RPD) was 17.9294, highlighting the model’s excellent predictive performance. Thus, this study identified the feasibility of predicting the moisture content in the process of green tea fixation by miniaturized near-infrared spectroscopy. Moreover, in establishing the model, the whale optimization algorithm was used to overcome the defect whereby the Elman neural network falls into the local optimum. In general, this study provides technical support for rapid and accurate moisture content detection in green tea fixation.

Detecting Starch-Head and Mildewed Fruit in Dried Hami Jujubes Using Visible/Near-Infrared Spectroscopy Combined with MRSA-SVM and Oversampling

Dried Hami jujube has great commercial and nutritional value. Starch-head and mildewed fruit are defective jujubes that pose a threat to consumer health. A novel method for detecting starch-head and mildewed fruit in dried Hami jujubes with visible/near-infrared spectroscopy was proposed. For this, the diffuse reflectance spectra in the range of 400–1100 nm of dried Hami jujubes were obtained. Borderline synthetic minority oversampling technology (BL-SMOTE) was applied to solve the problem of imbalanced sample distribution, and its effectiveness was demonstrated compared to other methods. Then, the feature variables selected by competitive adaptive reweighted sampling (CARS) were used as the input to establish the support vector machine (SVM) classification model. The parameters of SVM were optimized by the modified reptile search algorithm (MRSA). In MRSA, Tent chaotic mapping and the Gaussian random walk strategy were used to improve the optimization ability of the original reptile search algorithm (RSA). The final results showed that the MRSA-SVM method combined with BL-SMOTE had the best classification performance, and the detection accuracy reached 97.22%. In addition, the recall, precision, F₁ and kappa coefficient outperform other models. Furthermore, this study provided a valuable reference for the detection of defective fruit in other fruits.