Identification of solid state fermentation degree with FT-NIR spectroscopy: Comparison of wavelength variable selection methods of CARS and SCARS

Rapid detection of fertilizer information based on Raman spectroscopy and machine learning

The rapid detection of fertilizer nutrient information is a crucial element in enabling intelligent and precise variable fertilizer application. However, traditional detection methods possess limitations, such as the difficulty in quantifying multiple components and cross-contamination. In this study, a rapid detection method was proposed, leveraging Raman spectroscopy combined with machine learning, to identify five types of fertilizers: K2SO4, (CO(NH2)2, KH2PO4, KNO3, and N:P:K (15-15-15), along with their concentrations. Qualitative and quantitative models of fertilizers were constructed using three machine learning algorithms combined with five spectral preprocessing methods. Two variable selection methods were used to optimize the quantitative model. The results showed that the classification accuracy of the five fertilizer solutions obtained by random forest (RF) was 100 %. Moreover, in terms of regression, partial least squares regression (PLSR) outperformed extreme learning machine (ELM) and least squares support vector machine (LSSVM), yielding prediction Rp2 within the range of 0.9843-0.9990 and a root mean square error in the range of 0.0486-0.1691. In addition, this study evaluated the impact of different water types (deionized water, well water, and industrial transition water) on the detection of fertilizer information via Raman spectroscopy. The results showed that while different water types did not notably affect the identification of fertilizer nutrients, they did exert a pronounced effect on the quantification of concentrations. This study highlights the efficacy of combining Raman spectroscopy with machine learning in detecting fertilizer nutrients and their concentration information effectively.

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.

Assessing Fermentation Broth Quality of Pineapple Vinegar Production with a Near-Infrared Fiber-Optic Probe Coupled with Stability Competitive Adaptive Reweighted Sampling

In this study, the performance of a near-infrared (NIR) fiber-optic probe coupled with stability competitive adaptive reweighted sampling (SCARS) was investigated for the analysis of acetic acid, ethanol, total soluble solids, caffeic acid, gallic acid, and tannic acid in the broth of pineapple vinegar during fermentation. The NIR spectra of the broth samples in the region of 11,536-3956 cm-1 were collected during vinegar fermentation promoted by Acetobacter aceti. This continuous biological process led to changes in the concentrations of all analytes studied. SCARS provided optimized and stabilized NIR spectral variables for the construction of a partial least squares (PLS) model for each analyte using a small number of optimal variables (under 88 variables). The SCARS-PLS model outperformed the conventional PLS model, and achieved excellent accuracy in accordance with ISO 12099:2017 for the four prediction models of acetic acid, ethanol, caffeic acid, and gallic acid, with root-mean-square error of prediction values of 0.137%, 0.178%, 0.637 μg/mL and 0.640 μg/mL, respectively. In contrast, only an acetic acid content prediction model constructed via the conventional PLS method and using the whole spectral region (949 variables) could pass with acceptable accuracy. These results indicate that the NIR optical probe coupled with SCARS is an appropriate method for the continuous monitoring of multianalytes during vinegar fermentation, particularly acetic acid and ethanol contents, which are indicators of the finished fermentation of pineapple vinegar.

Robustness of calibration model for prediction of lignin content in different batches of snow pears based on NIR spectroscopy

Snow pear is very popular in southwest China thanks to its fruit texture and potential medicinal value. Lignin content (LC) plays a direct and negative role (higher concentration and larger size of stone cells lead to thicker pulp and deterioration of the taste) in determining the fruit texture of snow pears as well as consumer purchasing decisions of fresh pears. In this study, we assessed the robustness of a calibration model for predicting LC in different batches of snow pears using a portable near-infrared (NIR) spectrometer, with the range of 1033-2300 nm. The average NIR spectra at nine different measurement positions of snow pear samples purchased at four different periods (batch A, B, C and D) were collected. We developed a standard normal variate transformation (SNV)-genetic algorithm (GA) -the partial least square regression (PLSR) model (master model A) - to predict LC in batch A of snow pear samples based on 80 selected effective wavelengths, with a higher correlation coefficient of prediction set (Rp) of 0.854 and a lower root mean square error of prediction set (RMSEP) of 0.624, which we used as the prediction model to detect LC in three other batches of snow pear samples. The performance of detecting the LC of batch B, C, and D samples by the master model A directly was poor, with lower Rp and higher RMSEP. The independent semi-supervision free parameter model enhancement (SS-FPME) method and the sequential SS-FPME method were used and compared to update master model A to predict the LC of snow pears. For the batch B samples, the predictive ability of the updated model (Ind-model AB) was improved, with an Rp of 0.837 and an RMSEP of 0.614. For the batch C samples, the performance of the Seq-model ABC was improved greatly, with an Rp of 0.952 and an RMSEP of 0.383. For the batch D samples, the performance of the Seq-model ABCD was also improved, with an Rp of 0.831 and an RMSEP of 0.309. Therefore, the updated model based on supervision and learning of new batch samples by the sequential SS-FPME method could improve the robustness and migration ability of the model used to detect the LC of snow pears and provide technical support for the development and practical application of portable detection device.

Early warning and diagnostic visualization of Sclerotinia infected tomato based on hyperspectral imaging

This research explored the feasibility of early warning and diagnostic visualization of Sclerotinia infected tomato by using hyperspectral imaging technology. Healthy tomato plants and tomato plants with Sclerotinia sclerotiorum were cultivated, and hyperspectral images at 400-1000 nm were collected from healthy and infected tomato leaves at 1, 3, 5, and 7 days of incubation. After preprocessing the spectra with first derivative (FD), second derivative (SD), standard normal variant (SNV), and multiplicative scatter correction (MSC) partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) were used to construct tomato sclerotinia identification model and select the best preprocessing method. On this basis, two band screening methods, competitive adaptive reweighted sampling (CARS) and successive projections algorithm (SPA), were introduced to reduce data redundancy and improve the model's prediction accuracy. The results showed that the accuracy of the validation sets and operation speed of the CARS-PLS and CARS-SVM models were 87.88% and 1.8 s, and 87.95% and 1.78 s, respectively. The experiment was based on the SNV-CARS-SVM prediction model combined with image processing, spectral extraction, and visualization analysis methods to create diagnostic visualization software, which opens a new avenue to the implementation of online monitoring and early warning system for sclerotinia infected tomato.

Quantitative determination of acacia honey adulteration by terahertz-frequency dielectric properties as an alternative technique

The dielectric characteristics in the terahertz region contribute to a revealing insight into the material components and provide intermolecular information. The dielectric properties of adulterated honey, described as the real and imaginary parts of the complex dielectric constant (Re[ε] and Im[ε]), were obtained from 0.3 to 1.5 THz. The relationship between invert syrup proportions and complex dielectric constants at different frequencies implied the possibility of using the dielectric property as an indicator of honey authenticity. The selected effective dielectric variables of Re[ε] and Im[ε] and their combination were chosen by stability competitive adaptive reweighted sampling (SCARS) algorithm and then used to establish PLS models. The accuracy and uncertainty result revealed SCARS-PLS model based on the combination of Re[ε] and Im[ε] is the best model relatively. These findings indicated the potential utility of this rapid, non-destructive, and on-site method for authenticity verification.

Rapid and nondestructive detection of marine fishmeal adulteration by hyperspectral imaging and machine learning

Pure fishmeal (PFM) from whole marine-origin fish is an expensive and indispensable protein ingredient in most aquaculture feeds. In China, the supply shortage of domestically produced PFM has caused frequent PFM adulteration with low-cost protein sources such as feather meal (FTM) and fishmeal from by-products (FBP). The aim of this study was to develop a rapid and nondestructive detection method using near-infrared hyperspectral imaging (NIR-HSI) combined with machine learning algorithms for the identification of PFM adulterated with FTM, FBP, and the binary adulterant (composed of FTM and FBP). A hierarchical modelling strategy was adopted to acquire a better classification accuracy. Partial least squares discriminant analysis (PLS-DA) and support vector machine (SVM) coupled with four spectral preprocessing methods were employed to construct classification models. The SVM with baseline offset (BO-SVM) model using 20 effective wavelengths selected by successive projections algorithm (SPA) and competitive adaptive reweighted sampling (CARS) achieved classification accuracy of 100% and 99.43% for discriminating PFM from the adulterants (FTM, FBP) and adulterated fishmeal (AFM), respectively. This study confirmed that NIR-HSI offered a promising technique for feed mills to identify AFM containing FTM, FBP, or binary adulterants.

A residual network with attention module for hyperspectral information of recognition to trace the origin of rice

In this work, a neural network framework for hyperspectral information recognition was proposed, combined with residual block and convolutional block attention module (CBAM) to enhance the detection performance of hyperspectral for tracing the rice quality. Firstly, the hyperspectral image system was used to obtain the hyperspectral information of the rice. Secondly, due to the small data set, the structure of the residual network was designed based on the characteristics of the hyperspectral information to prevent overfitting the model. Finally, the CBAM was introduced to calculate the channel and spatial attention to redistribute the weight parameter and enhance the classification performance of the model. The results showed that our (Res-CBAM) model had better classification performance than other classification methods. The classification accuracy of the rice was 96.33%. This study provided a strategy to enhance the detection performance of hyperspectral, and an intelligent technology to trace the rice quality.

Nondestructive Analysis of Internal Quality in Pears with a Self-Made Near-Infrared Spectrum Detector Combined with Multivariate Data Processing

The consumption of pears has increased, thanks not only to their delicious and juicy flavor, but also their rich nutritional value. Traditional methods of detecting internal qualities (e.g., soluble solid content (SSC), titratable acidity (TA), and taste index (TI)) of pears are reliable, but they are destructive, time-consuming, and polluting. It is necessary to detect internal qualities of pears rapidly and nondestructively by using near-infrared (NIR) spectroscopy. In this study, we used a self-made NIR spectrum detector with an improved variable selection algorithm, named the variable stability and cluster analysis algorithm (VSCAA), to establish a partial least squares regression (PLSR) model to detect SSC content in snow pears. VSCAA is a variable selection method based on the combination of variable stability and cluster analysis to select the infrared spectrum variables. To reflect the advantages of VSCAA, we compared the classical variable selection methods (synergy interval partial least squares (SiPLS), genetic algorithm (GA), successive projections algorithm (SPA), and bootstrapping soft shrinkage (BOSS)) to extract useful wavelengths. The PLSR model, based on the useful variables selected by SiPLS-VSCAA, was optimal for measuring SSC in pears, and the correlation coefficient of calibration (Rc), root mean square error of cross validation (RMSECV), correlation coefficient of prediction (Rp), root mean square error of prediction (RMSEP), and residual predictive deviation (RPD) were 0.942, 0.198%, 0.936, 0.222%, and 2.857, respectively. Then, we applied these variable selection methods to select the characteristic wavelengths for measuring the TA content and TI value in snow pears. The prediction PLSR models, based on the variables selected by GA-BOSS to measure TA and that by GA-VSCAA to detect TI, were the best models, and the Rc, RMSECV, Rp and RPD were 0.931, 0.124%, 0.912, 0.151%, and 2.434 and 0.968, 0.080%, 0.968, 0.089%, and 3.775, respectively. The results showed that the self-made NIR-spectrum detector based on a portable NIR spectrometer with multivariate data processing was a good tool for rapid and nondestructive analysis of internal quality in pears.

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.

Leaf area index estimation model for UAV image hyperspectral data based on wavelength variable selection and machine learning methods

BACKGROUND

To accurately estimate winter wheat leaf area index (LAI) using unmanned aerial vehicle (UAV) hyperspectral imagery is crucial for crop growth monitoring, fertilization management, and development of precision agriculture.

METHODS

The UAV hyperspectral imaging data, Analytical Spectral Devices (ASD) data, and LAI were simultaneously obtained at main growth stages (jointing stage, booting stage, and filling stage) of various winter wheat varieties under various nitrogen fertilizer treatments. The characteristic bands related to LAI were extracted from UAV hyperspectral data with different algorithms including first derivative (FD), successive projections algorithm (SPA), competitive adaptive reweighed sampling (CARS), and competitive adaptive reweighed sampling combined with successive projections algorithm (CARS_SPA). Furthermore, three modeling machine learning methods including partial least squares regression (PLSR), support vector machine regression (SVR), and extreme gradient boosting (Xgboost) were used to build LAI estimation models.

RESULTS

The results show that the correlation coefficient between UAV and ASD hyperspectral data is greater than 0.99, indicating the UAV data can be used for estimation of wheat growth information. The LAI bands selected by using different algorithms were slightly different among the 15 models built in this study. The Xgboost model using nine consecutive characteristic bands selected by CARS_SPA algorithm as input was proved to have the best performance. This model yielded identical results of coefficient of determination (0.89) for both calibration set and validation set, indicating a high accuracy of this model.

CONCLUSIONS

The Xgboost modeling method in combine with CARS_SPA algorithm can reduce input variables and improve the efficiency of model operation. The results provide reference and technical support for nondestructive and rapid estimation of winter wheat LAI by using UAV.

Simultaneous sex and species classification of silkworm pupae by NIR spectroscopy combined with chemometric analysis

BACKGROUND

Most studies only focus on the sex discrimination of silkworm pupae. However, species differentiation of silkworm pupae is also needed in sericulture. To classify the sex and species at the same time, the present study adopts near infrared (NIR) spectroscopy combined with multivariate analysis.

RESULTS

First, spectra samples were acquired using an NIR sensor, comprising female and male silkworm pupae from three species. Second, three different variables selection approaches were used, including a successive projections algorithm, competitive adaptive reweighted sampling (CARS) and interval partial least squares (iPLS). Third, identification models were built based on random forest and partial least squares discriminant analysis (PLSDA). The experimental results show that iPLS-PLSDA model (95.24%) gives a high performance when using the one of the three variable selection methods alone. To further increase the performance, the variable selection methods are optimized. The accuracy of the iPLS-CARS-PLSDA model is as high as 98.41%.

CONCLUSION

The present study demonstrates that the optimized variable selection method in combination with NIR spectroscopy represents a suitable strategy for sex and species identification of silkworm pupae. © 2020 Society of Chemical Industry.

Analysis of Chlorophyll Concentration in Potato Crop by Coupling Continuous Wavelet Transform and Spectral Variable Optimization

The analysis of chlorophyll concentration based on spectroscopy has great importance for monitoring the growth state and guiding the precision nitrogen management of potato crops in the field. A suitable data processing and modeling method could improve the stability and accuracy of chlorophyll analysis. To develop such a method, we collected the modelling data by conducting field experiments at the tillering, tuber-formation, tuber-bulking, and tuber-maturity stages in 2018. A chlorophyll analysis model was established using the partial least-square (PLS) algorithm based on original reflectance, standard normal variate reflectance, and wavelet features (WFs) under different decomposition scales (21–210, Scales 1–10), which were optimized by the competitive adaptive reweighted sampling (CARS) algorithm. The performances of various models were compared. The WFs under Scale 3 had the strongest correlation with chlorophyll concentration with a correlation coefficient of −0.82. In the model calibration process, the optimal model was the Scale3-CARS-PLS, which was established based on the sensitive WFs under Scale 3 selected by CARS, with the largest coefficient of determination of calibration set (Rc2) of 0.93 and the smallest Rc2−Rcv2 value of 0.14. In the model validation process, the Scale3-CARS-PLS model had the largest coefficient of determination of validation set (Rv2) of 0.85 and the smallest root–mean–square error of cross-validation (RMSEV) value of 2.77 mg/L, demonstrating good prediction capability of chlorophyll concentration. Finally, the analysis performance of the Scale3-CARS-PLS model was measured using the testing data collected in 2020; the R2 and RMSE values were 0.69 and 3.36 mg/L, showing excellent applicability. Therefore, the Scale3-CARS-PLS model could be used to analyze chlorophyll concentration. This study indicated the best decomposition scale of continuous wavelet transform and provided an important support method for chlorophyll analysis in the potato crops.

Rapid quality evaluation of Shenzhiling oral liquid by attenuated total reflectance-infrared spectroscopy with chemometrics

In this study, a useful method of Attenuated total reflectance-Fourier transform infrared spectroscopy (ATR-FTIR) combined with chemometrics was proposed for rapid quantification of two-indicator components as well as discrimination of Shenzhiling oral liquid in shelf life and over shelf life. Fifteen batches of samples were employed to construct quantitative and discriminant models. Two ingredients (paeoniflorin and cinnamic acid) for quality control were modeled by partial least square regression (PLSR). The discrimination of samples between in shelf life and over shelf life was carried out by using discriminant analysis (DA). The samples were divided into calibration set and validation set according to batches. Different data pre-processing algorithms such as standard-normal-variate (SNV), multiplicative scatter correction (MSC), Savitzkye-Golay (SG) smoothing with derivative methods were applied to reduce the influence of systematic disturbances. Variable selection methods including correlation coefficient (CC), competitive adaptive reweighted sampling (CARS) and interval partial least squares regression (iPLS) were all performed for optimizing the PLSR models and DA model. The results demonstrated that ATR-FTIR combined with chemometrics could be a rapid, convenient and nondestructive approach to evaluate the quality of Shenziling oral liquid.

Determination of 10-Hydroxy-2-Decenoic Acid of Royal Jelly Using Near-Infrared Spectroscopy Combined with Chemometrics

A rapid quantitative analysis model for determining the hydroxy-2-decenoic acid (10-HDA) content of royal jelly based on near-infrared spectroscopy combining with PLS has been developed. Firstly, near-infrared spectra of 232 royal jelly samples with different 10-HDA concentrations (0.35% to 2.44%) were be collected. Second-order derivative processing of the spectra was carried out to construct a full-spectrum PLS model. Secondly, GA-PLS, CARS-PLS, and Si-PLS were used to select characteristic wavelengths from the second-order derivative spectrum to construct a PLS calibration model. Finally, 58 samples were used to select the best predictive model for 10-HDA content. The result show that the PLS model constructed after wavelength selection was significantly more accurate than the full spectrum model. The Si-PLS algorithm performed best and the corresponding characteristic wavelength range were: 980 to 1038, 1220 to 1278, 1340 to 1398, and 1688 to 1746 nm. The prediction results were RMSEP = 0.1496% and R_P = 0.9380. Hence, it is feasible to employ near-infrared spectra to analyze 10-HDA in royal jelly.

Comparison of algorithms for wavelength variables selection from near-infrared (NIR) spectra for quantitative monitoring of yeast (Saccharomyces cerevisiae) cultivations

Rapid monitoring with near-infrared (NIR) spectroscopy of Saccharomyces cerevisiae cultivations was implemented to monitor yeast concentrations. The measurement of one spectrum by using of FT-NIR spectrometer can obtain 1557 wavelength variables. To distinguish which wavelength variables of the collected FT-NIR spectra carry important and relevant information regarding the yeast concentrations, there are three different variables selection approaches, namely genetic algorithm (GA), competitive adaptive reweighted sampling (CARS), and variable combination population analysis (VCPA), were compared in this study. The selected wavelength variables from each method were evaluated using partial least squares (PLS) models to seek the most significant variable combinations for predicting the yeast concentrations. Experimental results showed that the VCPA-PLS model with the best predictive performance was found when using ten principal components (PCs) based on selected eleven characteristic wavelength variables by VCPA algorithm. And the predictive performance indicators of the model were as follows: the root mean square error of prediction (RMSEP) was 0.0680, the coefficient of determination (R_p²) was 0.9924, and the ratio performance deviation (RPD) was 11.8625 in the validation process. Based on the results, it is promising to develop a specific inexpensive NIR sensor for the yeast cultivation process using several light-emitting diodes.

Development of a novel wavelength selection method for the trace determination of chlorpyrifos on Au@Ag NPs substrate coupled surface-enhanced Raman spectroscopy

A novel wavelength selection method named ICPA-mRMR coupled SERS was employed for the detection of CPS residues in tea samples.

Monitoring alcohol concentration and residual glucose in solid state fermentation of ethanol using FT-NIR spectroscopy and L1-PLS regression

This study aimed to investigate the potential of FT-NIR spectroscopy technique combined with chemometrics method, which employed to monitor time-related changes of alcohol concentration and residual glucose during solid state fermentation (SSF) of ethanol. Characteristic wavelength variables were firstly selected by use of L1-norm regularization approach. Then, the partial least squares (PLS) regression model was finally developed using the variables selected by L1-norm regularization method to quantitative determine alcohol concentration and residual glucose in SSF of ethanol. Compared with the best results of full-spectrum PLS, the L1-PLS model obtained better results as follows: RMSECV = 1.0392 g/L, R_c = 0.9911, RMSEP = 1.0910 g/L, R_p = 0.9917 for alcohol concentration; RMSECV = 1.7002 g/L, R_c = 0.9880, RMSEP = 2.1859 g/L, R_p = 0.9896 for residual glucose. The overall results sufficiently demonstrate that FT-NIR spectroscopy technique coupled with appropriate chemometrics method is a promising tool for monitoring the process of SSF of ethanol.

Study on feasibility of determination of glucosamine content of fermentation process using a micro NIR spectrometer

N-acetyl-d-glucosamine (GlcNAc) is a microbial fermentation product, and NIR spectroscopy is an effective process analytical technology (PAT) tool in detecting the key quality attribute: the GlcNAc content. Meanwhile, the design of NIR spectrometers is under the trend of miniaturization, portability and low-cost nowadays. The aim of this study was to explore a portable micro NIR spectrometer with the fermentation process. First, FT-NIR spectrometer and Micro-NIR 1700 spectrometer were compared with simulated fermentation process solutions. The R_c², R_p², RMSECV and RMSEP of the optimal FT-NIR and Micro-NIR 1700 models were 0.999, 0.999, 3.226 g/L, 1.388 g/L and 0.999, 0.999, 1.821 g/L, 0.967 g/L. Passing-Bablok regression method and paired t-test results showed there were no significant differences between the two instruments. Then the Micro-NIR 1700 was selected for the practical fermentation process, 135 samples from 10 batches were collected. Spectral pretreatment methods and variables selection methods (BiPLS, FiPLS, MWPLS and CARS-PLS) for PLS modeling were discussed. The R_c², R_p², RMSECV and RMSEP of the optimal GlcNAc content PLS model of the practical fermentation process were 0.994, 0.995, 2.792 g/L and 1.946 g/L. The results have a positive reference for application of the Micro-NIR spectrometer. To some extent, it could provide theoretical supports in guiding the microbial fermentation or the further assessment of bioprocess.

Simultaneous measurement of contents of liquirtin and glycyrrhizic acid in liquorice based on near infrared spectroscopy

OBJECTIVE

To establish calibration models for simultaneous determination of contents of liquirtin and glycyrrhizic acid, and to investigate the variable selection methods.

METHODS

The contents of liquirtin and glycyrrhizic acid determined by HPLC were as the reference values, which were associated with samples spectra by using near infrared spectrum (NIR) analysis technology. Calibration models were developed using partial least squares (PLS) regression algorithm, and evaluated by the independent dataset test with calculating the metrics of coefficients of determination of calibration and prediction (R²_c, R²_p), the root mean square errors of calibration and prediction (RMSEC, RMSEP), the mean absolute errors of calibration and prediction (MAEC, MAEP), and the residual prediction deviation (RPD). Five variable selection methods including variable importance in projection (VIP), competitive adaptive reweighted sampling (CARS), Monte Carlo uninformative variable elimination (MCUVE), particle swarm optimization (PSO) and genetic algorithm (GA), were investigated.

RESULTS

Compared to the original full spectra, both quantification models for liquirtin and glycyrrhizic acid performed better with a clear ranking of GA>PSO>CARS>MCUVE≅VIP>Full. Especially for GA-PLS models, RMSEC and RMSEP were <0.05%, R²_c and R²_p were >0.94, and RPD were both >4, indicating that both the models had good robustness and excellent prediction accuracy.

CONCLUSION

The present calibration models can be utilized to simultaneously determine the contents of liquirtin and glycyrrhizic acid in liquorice samples, and thus are of great help for rapid quality evaluation and control of liquorice.

Terahertz time-domain attenuated total reflection spectroscopy applied to the rapid discrimination of the botanical origin of honeys

A new technique to identify the floral resources of honeys is demanded. Terahertz time-domain attenuated total reflection spectroscopy combined with chemometrics methods was applied to discriminate different categorizes (Medlar honey, Vitex honey, and Acacia honey). Principal component analysis (PCA), cluster analysis (CA) and partial least squares-discriminant analysis (PLS-DA) have been used to find information of the botanical origins of honeys. Spectral range also was discussed to increase the precision of PLS-DA model. The accuracy of 88.46% for validation set was obtained, using PLS-DA model in 0.5-1.5THz. This work indicated terahertz time-domain attenuated total reflection spectroscopy was an available approach to evaluate the quality of honey rapidly.