Near infrared system coupled chemometric algorithms for the variable selection and prediction of baicalin in three different processes

Integrating progressive screening strategy-based continuous wavelet transform with EfficientNetV2 for enhanced near-infrared spectroscopy

Near-infrared (NIR) spectroscopy has gained wide acceptance across various fields as a result of advances in portable equipment that can record spectra on site or at production lines. Continuous wavelet transform (CWT) can transform traditional one-dimensional (1D) NIR spectra into more informative two-dimensional (2D) spectrograms, thus enhancing the analysis and interpretation of spectral information. This study introduces a high-efficiency 2D CWT-EfficientNetV2 regression model to optimize NIR spectroscopy applications. A novel progressive screening strategy is employed to select the optimal wavelet functions and scales for CWT, which are then used to transform the features into wavelet coefficient matrices. Direct digital mapping (DDM) with Gray colormap generates 2D spectrograms from matrices, significantly preserving the representation of wavelet coefficients. The 2D CWT-EfficientNetV2 model was used to predict the content of five polyphenols in tobacco leaf samples with superior performance compared to partial least squares regression (PLSR) and other high-efficiency models. Moreover, to further validate the robustness and reliability of the proposed method, two additional public NIR spectral datasets were included in this study. The model achieves lower root mean square error of prediction (RMSEP), as well as higher coefficient of determination of prediction (RP2) and the ratio of the standard error of prediction to the standard deviation of the reference values (RPD) on the test datasets. These results demonstrate that the 2D CWT-EfficientNetV2 model is a robust and efficient approach for the accurate quantification of various target compounds utilizing NIR spectroscopy.

FT-NIR combined with machine learning was used to rapidly detect the adulteration of pericarpium citri reticulatae (chenpi) and predict the adulteration concentration

Pericarpium citri reticulatae (PCR) has been used as a food and spice for many years and is known for its rich nutritional content and unique aroma. However, price increases are often accompanied by adulteration. In this study, two kinds of adulterants (Orange peel-OP and Mandarin Rind-MR) were identified by chromaticity analysis, FT-NIR and machine learning algorithm, and the doping concentration was predicted quantitatively. The results show that colorimetric analysis cannot completely differentiate between PCR and adulterants. Using spectral preprocessing combined with machine learning algorithms, PCR and two adulterants were successfully distinguished, with classification accuracy reaching 99.30 % and 98.64 % respectively. After selecting characteristic wavelengths, the R2 P of the adulterated quantitative model is greater than 0.99. Generally, this study proposes to use FT-NIR to study the adulteration of PCR for the first time, which fills the technical gap in the adulteration research of PCR, and provides an important method to solve the increasingly serious adulteration problem of PCR.

Rapid and accurate quality evaluation of Angelicae Sinensis Radix based on near-infrared spectroscopy and Bayesian optimized LSTM network

The authentic traditional Chinese medicines (TCMs) including Angelicae Sinensis Radix (ASR) are the representative of high-quality herbals in China. However, ASR from authentic region being adulterated or counterfeited is frequently occurring, and there is still a lack of rapid quality evaluation methods for identifying the authentic ASR. In this study, the color features of ASR were firstly characterized. The results showed that the authentic ASR cannot be fully identified by color characteristics. Then near-infrared (NIR) spectroscopy combined with Bayesian optimized long short-term memory (BO-LSTM) was used to evaluate the quality of ASR, and the performance of BO-LSTM with common classification and regression algorithms was compared. The results revealed that following the pretreatment of NIR spectra, the optimal NIR spectra combined with BO-LSTM not only successfully distinguished authentic, non-authentic, and adulterated ASR with 100 % accuracy, but also accurately predicted the adulteration concentration of authentic ASR (R2 > 0.99). Moreover, BO-LSTM demonstrated excellent performance in classification and regression compared with common algorithms (ANN, SVM, PLSR, etc.). Overall, the proposed strategy could quickly and accurately evaluate the quality of ASR, which provided a reference for other TCMs.

Application of flash GC e-nose and FT-NIR combined with deep learning algorithm in preventing age fraud and quality evaluation of pericarpium citri reticulatae

Pericarpium citri reticulatae (PCR) is the dried mature fruit peel of Citrus reticulata Blanco and its cultivated varieties in the Brassicaceae family. It can be used as both food and medicine, and has the effect of relieving cough and phlegm, and promoting digestion. The smell and medicinal properties of PCR are aged over the years; only varieties with aging value can be called "Chenpi". That is to say, the storage year of PCR has a great influence on its quality. As the color and smell of PCR of different storage years are similar, some unscrupulous merchants often use PCRs of low years to pretend to be PCRs of high years, and make huge profits. Therefore, we did this study with the aim of establishing a rapid and nondestructive method to identify the counterfeiting of PCR storage year, so as to protect the legitimate rights and interests of consumers. In this study, a classification model of PCR was established by e-eye, flash GC e-nose, and Fourier transform near-infrared (FT-NIR) combined with machine learning algorithms, which can quickly and accurately distinguish PCRs of different storage years. DFA and PLS-DA models were established by flash GC e-nose to distinguish PCRs of different ages, and 8 odor components were identified, among which (+)-limonene and γ-terpinene were the key components to distinguish PCRs of different ages. In addition, the classification and calibration model of PCRs were established by the combination of FT-NIR and machine learning algorithms. The classification models included SVM, KNN, LSTM, and CNN-LSTM, while the calibration models included PLSR, LSTM, and CNN-LSTM. Among them, the CNN-LSTM model built by internal capsule had significantly better classification and calibration performance than the other models. The accuracy of the classification model was 98.21 %. The R2P of age, (+)-limonene and γ-terpinene was 0.9912, 0.9875 and 0.9891, respectively. These results showed that the combination of flash GC e-nose and FT-NIR combined with deep learning algorithm could quickly and accurately distinguish PCRs of different ages. It also provided an effective and reliable method to monitor the quality of PCR in the market.

Classification and rapid non-destructive quality evaluation of different processed products of Cyperus rotundus based on near-infrared spectroscopy combined with deep learning

The quality of traditional Chinese medicine is very important for human health, but the traditional quality control method is very tedious, which leads to the substandard quality of many traditional Chinese medicine. In order to solve the problem of time-consuming and laborious traditional quality control methods, this study takes traditional Chinese medicine Cyperus rotundus as an example, a comprehensive strategy of near-infrared (NIR) spectroscopy combined with One-dimensional convolutional neural network (1D-CNN) and chaotic map dung beetle optimization (CDBO) algorithm combined with BP neural network (BPNN) is proposed. This strategy has the advantages of fast and non-destructive. It can not only qualitatively distinguish Cyperus rotundus and various processed products, but also quantitatively predict two bioactive components. In classification, 1D-CNN successfully distinguished four kinds of processed products of Cyperus rotundus with 100 % accuracy. Quantitatively, a CDBO algorithm is proposed to optimize the performance of the BPNN quantitative model of two terpenoids, and compared with the BP, whale optimization algorithm (WOA)-BP, sparrow optimization algorithm (SSA)-BP, grey wolf optimization (GWO)-BP and particle swarm optimization (PSO)-BP models. The results show that the CDBO-BPNN model has the smallest error and has a significant advantage in predicting the content of active components in different processed products. To sum up, it is feasible to use near infrared spectroscopy to quickly evaluate the effect of processing methods on the quality of Cyperus rotundus, which provides a meaningful reference for the quality control of traditional Chinese medicine with many other processing methods.

Rapid evaluation of Ziziphi Spinosae Semen and its adulterants based on the combination of FT-NIR and multivariate algorithms

Ziziphi Spinosae Semen (ZSS) is a valued seed renowned for its sedative and sleep-enhancing properties. However, the price increase has been accompanied by adulteration. In this study, chromaticity analysis and Fourier transform near-infrared (FT-NIR) combined with multivariate algorithms were employed to identify the adulteration and quantitatively predict the adulteration ratio. The findings suggested that the utilization of chromaticity extractor was insufficient for identification of adulteration ratio. The raw spectrum of ZMS and HAS adulterants extracted by FT-NIR was processed by SNV + CARS and 1d + SG + ICO respectively, the average accuracy of machine learning classification model was improved from 77.06 % to 97.58 %. Furthermore, the R2 values of the calibration and prediction set of the two quantitative prediction regression models of adulteration ratio are greater than 0.99, demonstrating excellent linearity and predictive accuracy. Overall, this study demonstrated that FT-NIR combined with multivariate algorithms provided a significant approach to addressing the growing issue of ZSS adulteration.

Rapid evaluation of Radix Paeoniae Alba and its processed products by near-infrared spectroscopy combined with multivariate algorithms

It is well known that the processing method of herbal medicine has a complex impact on the active components and clinical efficacy, which is difficult to measure. As a representative herb medicine with diverse processing methods, Radix Paeoniae Alba (RPA) and its processed products differ greatly in clinical efficacy. However, in some cases, different processed products are confused for use in clinical practice. Therefore, it is necessary to strictly control the quality of RPA and its processed products. Giving that the time-consuming and laborious operation of traditional quality control methods, a comprehensive strategy of near-infrared (NIR) spectroscopy combined with multivariate algorithms was proposed. This strategy has the advantages of being rapid and non-destructive, not only qualitatively distinguishing RPA and various processed products but also enabling quantitative prediction of five bioactive components. Qualitatively, the subspace clustering algorithm successfully differentiated RPA and three processed products, with an accuracy rate of 97.1%; quantitatively, interval combination optimization (ICO), competitive adaptive reweighted sampling (CARS), and competitive adaptive reweighted sampling combined with successive projections algorithm (CARS-SPA) were used to optimize the PLS model, and satisfactory results were obtained in terms of wavelength selection. In conclusion, it is feasible to use NIR spectroscopy to rapidly evaluate the effect of processing methods on the quality of RPA, which provides a meaningful reference for quality control of other herbal medicines with numerous processing methods.

Raman spectroscopy for on-line monitoring of botanical extraction process using convolutional neural network with background subtraction

Aqueous extraction is the most common and cost-effective means of obtaining active ingredients from medicinal plants. However, botanical extracts generally contain high pigment content and complex chemical composition posing a challenge for the process analysis of aqueous extraction. Here, we employed Raman spectroscopy to monitor the physical and chemical properties during the extraction process using convolution neural network (CNN) with background subtraction. Real-time spectra were first preprocessed to eliminate fluorescence background interference. Next, two types of CNN models, the one-dimensional CNN (1D-CNN) based on one preprocessing method, and two-dimensional CNN (2D-CNN) based on a concatenation of differentially pretreated data blocks, were used to receive the preprocessed spectra data. Two case studies were conducted for 1D- and 2D-CNN: the extraction of Aurantii fructus, and the co-extraction of Radix Salvia miltiorrhiza and Rhizoma Ligusticum chuanxiong. Furthermore, partial least squares (PLS) models and sequential preprocessing through orthogonalization (SPORT) models were developed and compared with 1D-CNN and 2D-CNN, respectively. CNN-based methods were superior to other models in terms of prediction accuracy, with 2D-CNN yielding the best results. These results indicated that preprocessing and CNN methods were highly complementary, and could effectively remove the fluorescence effect and artefacts introduced by pretreatment in spectral profile. To the best of our knowledge, this is the first study to demonstrate that a combination of preprocessing and CNN leads to improved prediction performance of analytes when using Raman spectroscopy for online monitoring high-pigmented samples.

Rapid detection of cellulose and hemicellulose contents of corn stover based on near-infrared spectroscopy combined with chemometrics

The feasibility of near-infrared spectroscopy (NIRS) combined with chemometrics for the rapid detection of the cellulose and hemicellulose contents in corn stover is discussed. Competitive adaptive reweighted sampling (CARS) and genetic simulated annealing algorithm (GSA) were combined (CARS-GSA) to select the characteristic wavelengths of cellulose and hemicellulose and to reduce the dimensionality and multicollinearity of the NIRS data. The whole spectra contained 1845 wavelength variables. After CARS-GSA optimization, the number of characteristic wavelengths of cellulose (hemicellulose) was reduced to 152 (260), accounting for 8.24% (14.09%) of all wavelengths. The coefficients of determination of the regression models for predicting the cellulose and hemicellulose contents were 0.968 and 0.996, the root mean square errors of prediction (RMSEPs) were 0.683 and 0.648, and the residual predictive deviations (RPDs) were 5.213 and 16.499, respectively. The RMSEP of the cellulose and hemicellulose regression models was 0.152 and 0.190 lower for CARS-GSA than for the full-spectrum, and the RPD was increased by 0.949 and 3.47, respectively. The results showed that the CARS-GSA model substantially reduced the number of characteristic wavelengths and significantly improved the predictive ability of the regression model.

Nondestructive qualitative and quantitative analysis of Yaobitong capsule using near-infrared spectroscopy in tandem with chemometrics

The purpose of the study is to present a nondestructive qualitative and quantitative approach of hard-shell capsule using near-infrared (NIR) spectroscopy combined with chemometrics. The Yaobitong capsule (YBTC) was used for demonstration of the proposed approach and the NIR spectra were collected using a handheld fiber probe (FP) without the damage of capsule shell. By comparing the differences and similarities of the NIR spectra of capsule shells, contents and intact capsules, a preliminary conclusion can be drawn that the NIR spectra contained the information of the contents. Characteristic variables were selected by competitive adaptive weighted resampling (CARS) method, and least squares support vector machine (LSSVM) method based on particle swarm optimization (PSO) algorithm was applied to the construction of quantitative models. The relative standard error of prediction (RSEP) values of five saponins including notoginsenoside R1, ginsenoside Rg1, Re, Rb1, and Rd were 3.240%, 5.468%, 5.303%, 5.043%, and 3.745%, respectively. In addition, for qualitative model, three different types of adulterated capsules were designed. The model established by data driven version of soft independent modeling of class analogy (DD-SIMCA) demonstrated a satisfactory result that all adulterated capsules were identified accurately after an appropriate number of principal components (PCs) were chosen. The results indicated that although the NIR spectra collection was affected by capsule shell, sufficient content information can be obtained for quantitative and qualitative analysis after combining with chemometrics. It further proved that acquired NIR spectra do contain the effective component information of the capsule. This study provided a reference for the rapid nondestructive quality analysis of traditional Chinese medicine (TCM) capsule without damaging capsule shell.

Application of Fourier transform near-infrared spectroscopy combined with GC in rapid and simultaneous determination of essential components in Amomum villosum

A method is described using rapid and sensitive Fourier transform near-infrared spectroscopy combined with Gas Chromatograpy internal standard method detection for the simultaneous identification and determination of three bioactive compounds in Amomum villosum samples. Partial least squares regression is selected as the analysis type and multiplicative scatter correction, second derivative, and SNV were adopted for the spectral pretreatment. The correlation coefficients (R) of the calibration models were above 0.95 and the root mean square error of predictions were under 0.8. The developed models were applied to unknown samples with satisfantory results. The established method was validated and can be applied to the intrinsic quality control of Amomum villosum.

Rapid monitoring approaches for concentration process of lanqin oral solution by near-infrared spectroscopy and chemometric models

Qualitative and quantitative detection methods based on near-infrared spectroscopy (NIRs) have been proposed in the process analysis of traditional Chinese medicine in recent years. In this study, rapid monitoring methods were developed for quality control of concentration process of lanqin oral solution (LOS). Partial least squares regression (PLSR) method was adopted to construct quantitative models for epigoitrin, geniposide, baicalin, berberine hydrochloride and density. Simultaneously, the genetic algorithm joint extreme learning machine (GA-ELM) was first applied in qualitative analysis of NIRs to distinguish end point of concentration process. Results of PLSR models were satisfactory with the relative standard error of calibration valued at 3.80%, 3.75%, 3.79%, 11.5% and 1.22% for epigoitrin, geniposide, baicalin, berberine hydrochloride and density respectively, and the residual predictive deviation values were higher than 3. For qualitative analysis, the GA-ELM model obtained 100% prediction accuracy. The PLSR quantitative models and the end point discrimination model constructed by GA-ELM correspond with the requirements of practical applications. The results indicate that NIRs in combination with chemometrics has great potential in improving the efficiency in production.

A Raman spectroscopy analysis method for rapidly determining saccharides and its application to monitoring the extraction process of Wenxin granule manufacturing procedure

Saccharides are the major constituents of many herbs, and they are often utilized as quality indicators of many botanical drugs, such as Chinese medicines. A method for the rapid determination of saccharides in the in-process extract solutions is beneficial for process monitoring and ensuring consistency in the quality of the end-products during the manufacturing of Chinese medicines. In this work, a method based on Raman spectroscopy and a competitive adaptive reweighted sampling-partial least squares (CARS-PLS) model was established for the rapid quantification of saccharides. The accuracy and precision of this method were confirmed by employing one monosaccharide (glucose), one oligosaccharide (maltotriose), and two polysaccharides (Codonopsis radix polysaccharides and Polygonati rhizome polysaccharides) as reference substances. The determined results correlated well with the reference values of the four substances with the coefficient of determination of prediction (R_p²) ≥ 0.9939 and the root-mean-square error of prediction (RMSEP) ≤ 1.1052 mg/mL. Then, the method was applied to monitoring the simulated extraction process for Wenxin granule manufacture using total saccharides as a quality indicator. The CARS-PLS model exhibited satisfactory fitting and predictive capability, with R_p² and RMSEP values of 0.9743 and 1.4931 mg/mL, respectively. Our work demonstrated that Raman spectroscopy coupled with chemometrics can offer a reliable and nondestructive alternative for the determination of different types of saccharides, in addition to being useful for real-time monitoring of the extraction process during the manufacturing of Wenxin granules. The presented approach is expected to be applicable to other Chinese medicines.

Near-infrared spectroscopy coupled with chemometrics algorithms for the quantitative determination of the germinability of Clostridium perfringens in four different matrices

Clostridium perfringens (C. perfringens) has the ability to form metabolically-dormant spores that can survive food preservation processes and cause food spoilage and foodborne safety risks upon germination outgrowth. This study was conducted to investigate the effects of different AGFK concentrations (0, 50, 100, 200 mM/mL) on the spore germination of C. perfringens in four matrices, including Tris-HCl, FTG, milk, and chicken soup. C. perfringens spore germinability was investigated using near infrared spectroscopy (NIRS) combined with chemometrics. The spore germination rate (S), the OD₆₀₀%, and the Ca²⁺-DPA% were measured using traditional spore germination methods. The results of spore germination assays showed that the optimum germination rate was obtained using 100 mM/L concentrations of AGFK in the FTG medium, and the S, OD₆₀₀% and Ca²⁺-DPA% were 98.6%, 59.3% and 95%, respectively. The best prediction models for the S, OD₆₀₀% and Ca²⁺-DPA% were obtained using SNV as the preprocessing method for the original spectra, with the competitive adaptive weighted resampling method (CARS) as the characteristic variables related to the selected spore germination methods from NIRS data. The results of the S showed that the optimum model was built by CARS-PLSR (RMSEV = 0.745, R_c = 0.897, RMSEP = 0.769, R_p = 0.883). For the OD₆₀₀%, interval partial least squares regression (CARS-siPLS) was performed to optimize the models. The calibration yielded acceptable results (RMSEV = 0.218, R_c = 0.879, RMSEP = 0.257, R_p = 0.845). For the Ca²⁺-DPA%, the optimum model with CARS-siPLS yielded acceptable results (RMSEV = 44.7, R_c = 0.883, RMSEP = 50.2, R_p = 0.872). This indicated that quantitative determinations of the germinability of C. perfringens spores using NIR technology is feasible. A new method based on NIR was provided for rapid, automatic, and non-destructive determination of the germinability of C. perfringens spores.

Development of a comprehensive quality control method for the quantitative analysis of volatiles and lignans in Magnolia biondii Pamp. by near infrared spectroscopy

The quality of drug is vital to its curative effect, thus it is important to develop a comprehensive quality control method for commonly used drugs. In this study, we developed a Gas chromatography-mass spectrometry separation method for the qualitative and quantitative analysis of volatiles, together with a High-performance liquid chromatography-mass spectrometry separation method for lignans in Magnolia biondii Pamp.. 79 volatiles and 11 lignans were identified via comparing their chromatographic behavior and mass spectra data with those in the literature. The methods were then used to determine the contents of volatiles (1, 8-cineole, d-Limonene, α-terpineol, linalool, L-camphor brain and bornyl acetate) and lignans (epieudesmin, magnolin, epi-magnolin A and fargesin) in Magnolia biondii Pamp.. Subsequently, 13 qualitative models including volatiles (1, 8-cineole, d-Limonene, α-terpineol, linalool, L-camphor brain and bornyl acetate), water-soluble extractive, lignans (pinoresinol dimethyl ether, magnolin, epi-magnolin A and fargesin) and moisture were developed by Near-Infrared Spectroscopy based on partial least square regression herein. The reference values were obtained by High-performance liquid chromatography, Gas chromatography and etc., while the predicted values were attained from the NIR spectrum. Compared with the traditional detection methods, NIR technique methodology significantly improved the ability to evaluate the quality of Magnolia biondii Pamp., which had the advantages of convenience, celerity, highly efficiency, low cost, no harm to samples, no reagent consumption, and no pollution to the environment. Moreover, the systematic analysis method combined pharmaceutical analysis with pharmacochemistry was proposed to prepare volatiles, water-soluble extractive and lignans parts from the same sample. This way could extract more index components to be beneficial in the quality control of Magnolia biondii Pamp. roundly.