[Objectives]This study was conducted to realize the rapid and nondestructive identification of blueberry producing areas and protect benefits of high-quality blueberry brands.[Methods]Five types of blueberries from di...[Objectives]This study was conducted to realize the rapid and nondestructive identification of blueberry producing areas and protect benefits of high-quality blueberry brands.[Methods]Five types of blueberries from different regions were selected as experimental subjects,and spectral analysis techniques were combined with deep learning.Firstly,standard normal variable transform(SNV)and convolutional smoothing(SG)were used to deal with scattering noise and other issues in original spectral data.Secondly,due to a large amount of redundant information and high correlation between adjacent wavelengths in the collected spectra,continuous projection algorithm(SPA)and partial least squares regression(PLS)were combined for screening of features with RMSE as the indicator,and 40 feature variables were obtained.Finally,a convolutional network model CNN-SE integrating a Squeeze and Excitation(SE)attention mechanism module was constructed and compared with convolutional neural network(CNN),support vector machine(SVM),and BP neural network.[Results]The CNN-SE model had the best effect,with the accuracy and precision of the test set reaching 95%and 94.56%,respectively,and the recall and F 1 score reaching 93.94%and 94.24%,respectively.[Conclusions]The CNN-SE convolution network model can realize rapid,nondestructive and high-throughout identification of blueberry producing areas.展开更多
[Objective] To explore a rapid determination method for fiber content in grains of quinoa. [Method] Near infrared spectra of 100 quinoa samples were collected. The predicted models for quantitative analysis of fiber c...[Objective] To explore a rapid determination method for fiber content in grains of quinoa. [Method] Near infrared spectra of 100 quinoa samples were collected. The predicted models for quantitative analysis of fiber contents in the grains were built using near infrared transmittance spectroscopy （NITS）. [Result] In the wavelength range of 10 000-4 000 cm-1, the near infrared quantitative model of quinoa crude fiber was set up via first derivative ＋ vector normalization preprocessing and combining with the data from chemical methods. The calibration and prediction effect were best, and then the cross validation determination coefficient （FFcv） and external validation determination coefficient （FFval） of fiber by near in- frared quantitative model were 0.884 8 and 0.876 1, respectively. [Conclusion] the model of NITS about complete grains quinoa fiber can be available for fast detecting quinoa fiber content.展开更多
We have developed a set of chemometric methods to address two critical issues in quality control of a precious traditional Chinese medicine （TCM）, Dong＇e Ejiao （DEE J）. Based on near infrared （NIR） spectra of m...We have developed a set of chemometric methods to address two critical issues in quality control of a precious traditional Chinese medicine （TCM）, Dong＇e Ejiao （DEE J）. Based on near infrared （NIR） spectra of multiple samples, the genuine manufacturer of DEE J, e.g. Dong＇e Ejiao Co., Ltd., was accurately identified among 21 suppliers by the fingerprint method using Hotelling T2, distance to Model X （DModX）, and similarity match value （SMV） as dis- criminate criteria. Soft independent modeling of the class analogy algorithm led to a misjudgment ratio of 6.2%, suggesting that the fingerprint method is more suitable for manufacturer identification. For another important feature related to clinical efficacy of DEE J, storage time, the partial least squares-discriminant analysis （PLS-DA） method was applied with a satisfactory misjudgment ratio （15.6%） and individual prediction error around 1 year. Our results demonstrate that NIR spectra comprehensively reflect the essential quality information of DEE J, and with the aid of proper chemometric algorithms, it is able to identify genuine manufacturer and determine accurate storage time. The overall results indicate the promising potential of NIR spectroscopy as an effective quality control tool for DEEJ and other precious TCM products.展开更多
Near infrared（NIR） spectroscopy technique has shown great power and gained wide acceptance for analyzing complicated samples.The present work is to distinguish different brands of tobacco products by using on-line N...Near infrared（NIR） spectroscopy technique has shown great power and gained wide acceptance for analyzing complicated samples.The present work is to distinguish different brands of tobacco products by using on-line NIR spectroscopy and pattern recognition techniques.Moreover,since each brand contains a large number of samples,an improved dendrogram was proposed to show the classification of different brands.The results suggest that NIR spectroscopy combined with principal component analysis （PCA） and hierarchical cluster analysis（HCA） performs well in discrimination of the different brands,and the improved dendrogram could provide more information about the difference of the brands.展开更多
With the technique of Fourier transform near infrared (FT-NIR) spectroscopy, the calibration models for quantitative analysis of sucrose and polarization in sugarcane juice were developed by using transmission mode an...With the technique of Fourier transform near infrared (FT-NIR) spectroscopy, the calibration models for quantitative analysis of sucrose and polarization in sugarcane juice were developed by using transmission mode and calibrating with partial least square (PLS) algorithm. The determination coefficients (R2) of the predicted models for sucrose and polarization in juice were 0. 9980 and 0. 9979 respectively; the root mean square errors of cross validation (RMSECV) were 0. 143 and 0. 155% for sucrose and polarization in juice respectively. The predictive errors measured by FT-NIR were close to those by routine laboratory methods. The results demonstrated that the FT-NIR methods had high accuracy and they were able to replace the routine laboratory analysis. It was also demonstrated that as a rapid and accurate measurement, the FT-NIR technique had potential applications in quality control of mill sugarcane, establishment of payment system based on sugarcane quality, and selection of clones in sugarcane breeding.展开更多
Near infrared spectrometer technology under a wavelength range of 918-1045 nm was used to rapidly detect paddy rice that was stored at 5℃, 15℃ and 25℃. A total of 121 paddy rice samples were collected from artifici...Near infrared spectrometer technology under a wavelength range of 918-1045 nm was used to rapidly detect paddy rice that was stored at 5℃, 15℃ and 25℃. A total of 121 paddy rice samples were collected from artificial infection with moulds to build the calibration models to calculate the total number colony of moulds based on the principal component regression method and multiple linear regression method. The results of statistical analysis indicated that multiple linear regression method was applicable to the detection of the total number colony of moulds. The correlation of calibration data set was 0.943. The correlation of prediction data set was 0.897. Therefore, the result showed that near infrared spectroscopy could be a useful instrumental method for determining the total number colony of moulds in paddy rice. The near infrared spectroscopy methodology could be applied for monitoring mould contamination in postharvest paddy rice during storage and might become a powerful tool for monitoring the safety of the grain.展开更多
Near infrared spectroscopy(NIRS)analysis technology,combined with chemometrics,can be effectively used in quick and nondestructive analysis of quality and category.In this paper,an effective drug identification method...Near infrared spectroscopy(NIRS)analysis technology,combined with chemometrics,can be effectively used in quick and nondestructive analysis of quality and category.In this paper,an effective drug identification method by using deep belief network(DBN)with dropout mecha-nism(dropout-DBN)to model NIRS is introduced,in which dropout is employed to overcome the overfitting problem coming from the small sample.This paper tests proposed method under datasets of different sizes with the example of near infrared diffuse refectance spectroscopy of erythromycin ethylsuccinate drugs and other drugs,aluminum and nonaluminum packaged.Meanwhile,it gives experiments to compare the proposed method's performance with back propagation(BP)neural network,support vector machines(SVMs)and sparse denoising auto-encoder(SDAE).The results show that for both binary classification and multi-classification,dropout mechanism can improve the classification accuracy,and dropout-DBN can achieve best classification accuracy in almost all cases.SDAE is similar to dropout-DBN in the aspects of classification accuracy and algorithm stability,which are higher than that of BP neural network and SVM methods.In terms of training time,dropout-DBN model is superior to SDAE model,but inferior to BP neural network and SVM methods.Therefore,dropout-DBN can be used as a modeling tool with effective binary and multi-class classification performance on a spectrum sample set of small size.展开更多
To clarify the quality characters,understand the genetic diversity and screen elite lines among different oilseed sunflowers,the contents of crude fat,oleic acid,linoleic acid,palmitic acid and stearic acid of 525 oil...To clarify the quality characters,understand the genetic diversity and screen elite lines among different oilseed sunflowers,the contents of crude fat,oleic acid,linoleic acid,palmitic acid and stearic acid of 525 oil sunflowers(including 375 germplasm accessions and 150 inbred lines)were detected by near-infrared spectroscopy(NIRS);the genetic variation and correlation analysis of quality traits were also performed.The results showed that oleic acid and linoleic acid had rich diversities with large variation ranges for each material type.Similar to the relation between crude fat content and palmitic acid content,significantly negative relation with high estimated value existed between oleic acid and linoleic acid content,while stearic acid content positively associated with oleic acid and palmitic acid content.Principal component analysis indicated that 5 quality traits were integrated into 2principal component factors(linoleic acid negative factor and palmitic acid factor)with the contribution rate of 88.191%,which could be used for evaluating sunflower quality.525 oilseed sunflowers were clustered into 3groups with obvious differences of quality characters,materials in Group I had high contents of oleic acid and low crude fat,but the opposite was found in GroupⅢ.59 superior quality accessions were obtained using large-scale and rapid near-infrared spectroscopy,and these excellent materials were verified by the traditional national chemical standard method.This research provided materials and significant reference for sunflower genetic research and quality breeding.展开更多
A near infrared spectroscopy（NIRS） approach was established for quality control of the alcohol precipitation liquid in the manufacture of Codonopsis Radix. By applying NIRS with multivariate analysis, it was possibl...A near infrared spectroscopy（NIRS） approach was established for quality control of the alcohol precipitation liquid in the manufacture of Codonopsis Radix. By applying NIRS with multivariate analysis, it was possible to build variation into the calibration sample set, and the Plackett-Burman design, Box-Behnken design, and a concentrating-diluting method were used to obtain the sample set covered with sufficient fluctuation of process parameters and extended concentration information. NIR data were calibrated to predict the four quality indicators using partial least squares regression（PLSR）. In the four calibration models, the root mean squares errors of prediction（RMSEPs） were 1.22 μg/ml, 10.5 μg/ml, 1.43 μg/ml, and 0.433% for lobetyolin, total flavonoids, pigments, and total solid contents, respectively. The results indicated that multi-components quantification of the alcohol precipitation liquid of Codonopsis Radix could be achieved with an NIRS-based method, which offers a useful tool for real-time release testing（RTRT） of intermediates in the manufacture of Codonopsis Radix.展开更多
A discriminant analysis technique using wavelet transformation(WT)and influence matrixanalysis(CAIMAN)method is proposed for the near infrared(NIR)spectroscopy classifi-cation.In the proposed methodology,NIR spectra a...A discriminant analysis technique using wavelet transformation(WT)and influence matrixanalysis(CAIMAN)method is proposed for the near infrared(NIR)spectroscopy classifi-cation.In the proposed methodology,NIR spectra are decomposed by WT for data com-pression and a forward feature selection is further employed to extract the relevant informationfrom the wavelet coefficients,reducing both classification errors and model complexity.Adiscriminant-CAIMAN(D-CAIMAN)method is utilized to build the classification model inwavelet domain on the basis of reduced wavelet coefficients of spectral variables.NIR spectradata set of 265 salviae miltiorrhizae radia samples from 9 different geographical origins is usedas an example to test the classification performance of the algorithm.For a comparison,k-nearest neighbor(KNN),linear discriminant analysis(LDA)and quadratic discriminant analysis(QDA)methods are also employed.D-CAIMAN with wavelet-based feature selection(WD-CAIMAN)method shows the best performance,achieving the total classification rate of ioo%in both cross-validation set and prediction set.It is worth noting that the WD-CAIMANclassifier also shows improved sensitivity,selectivity and model interpretability in thecla.ssifications.展开更多
As one of the important indicators of spectrometer,signal-to-noise ratio(SNR)reflects the ability of spectrometer to detect weak signals.To investigate the influence of SNR on the prediction accuracy of spectral analy...As one of the important indicators of spectrometer,signal-to-noise ratio(SNR)reflects the ability of spectrometer to detect weak signals.To investigate the influence of SNR on the prediction accuracy of spectral analysis,we first introduce the major factors affecting the spectral SNR.Taking green tea as an example,the influence of spectral SNR on the prediction accuracy of the origin identification model is analyzed by experiments.At the same time,the relationship between the spectral SNR and prediction accuracy of spectral analysis model is fitted.Based on this,the common methods for improving the spectral SNR are discussed.The results show that the accuracy of the prediction set model first decreases slowly,then decreases linearly,and finally tends to be flat as the spectral SNR decreases.Through calculation,in order to achieve the prediction accuracy of prediction model reaching 90%and 85%,the spectral SNR is required to be higher than 23.42 dB and 21.16 dB,respectively.The overall results provide certain parameters support for the development of new online analytical spectroscopic instruments,especially for the technical indicators of SNR.展开更多
As an important process analysis tool,near infrared spectroscopy(NIRS)has been widely used in process monitoring.In the present work,the feasibility of NIRS for monitoring the moisture content of human coagulation fac...As an important process analysis tool,near infrared spectroscopy(NIRS)has been widely used in process monitoring.In the present work,the feasibility of NIRS for monitoring the moisture content of human coagulation factor VIII(FVIII)in freeze-drying process was investigated.A partial least squares regression(PLS-R)model for moisture content determination was built with 88 samples.Different pre-processing methods were explored,and the best method found was standard normal variate(SNV)transformation combined with 1st derivation with Savitzky–Golay(SG)15 point smoothing.Then,four different variable selection methods,including uninformative variable elimination(UVE),interval partial least squares regression(iPLS),competitive adaptive reweighted sampling(CARS)and manual method,were compared for eliminating irrelevant variables,and iPLS was chosen as the best variable selection method.The correlation coe±cient(R),correlation coe±cient of calibration set(Rcal),correlation coefficient of validation set(Rval),root mean square errors of cross-validation(RMSECV)and root mean square errors of prediction(RMSEP)of PLS model were 0.9284,0.9463,0.8890,0.4986% and 0.4514%,respectively.The results showed that the model for moisture content determination has a wide range,good linearity,accuracy and precision.The developed approach was demonstrated to be a potential for monitoring the moisture content of FVIII in freeze-drying process.展开更多
Germinated brown rice(GBR)is rich in gamma oryzanol which increase its consumption popularity,particularly in the health food market.The objective of this research was to apply the near infraredspectroscopy(NIRS)for e...Germinated brown rice(GBR)is rich in gamma oryzanol which increase its consumption popularity,particularly in the health food market.The objective of this research was to apply the near infraredspectroscopy(NIRS)for evaluation of gamma oryzanol of the germinated brown rice.The germinated brown rice samples were prepared from germinated rough rice(soaked for 24 and 48 h,incubated for 0,6,12,18,24,30 and 36 h)and purchased from local supermar kets.The germinated brown rice sampleswere subjected to NIR scanning before the evaluation of gamma oryzanol by using partial extractionmet hodology.The prediction model was established by partial least square regression(PLSR)andvalidated by full cross validation method.The NIRS model established from various varieties of germinated brown rice bought from diferent markets by first derivatives+vector normalizationpretreated spectra showed the optimal prediction with the correlation of determination(R?),root mean squared error of cross validation(RMSECV),and bias of 0.934,8.84×10^(-5) mg/100 g drymatter and 1.06×10^(-5) mg/100 g dry matter,respectively.This is the first report on the application of NIRS in the evaluation of gamma oryzanol of the germinated brown rice.This information is veryuseful to the germinated brown rice production factory and consumers.展开更多
Although near infrared (NIR) spectroscopy has been evaluated for numerous applications, the number of actual on-line or even on-site industrial applications seems to be very limited. In the present paper, the attempts...Although near infrared (NIR) spectroscopy has been evaluated for numerous applications, the number of actual on-line or even on-site industrial applications seems to be very limited. In the present paper, the attempts to produce online predictions of the chemical oxygen demand (COD) in wastewater from a pulp and paper mill using NIR spectroscopy are described. The task was perceived as very challenging, but with a root mean square error of prediction of 149 mg/l, roughly corresponding to 1/10 of the studied concentration interval, this attempt was deemed as successful. This result was obtained by using partial least squares model regression, interpolated reference values for calibration purposes, and by evenly distributing the calibration data in the concentration space. This work may also represent the first industrial application of online COD measurements in wastewater using NIR spectroscopy.展开更多
To date, the cortical effect of exercise has not been fully elucidated. Using the functional near infrared spectroscopy, we attempted to compare the cortical effect between shoulder vibration exercise and shoulder sim...To date, the cortical effect of exercise has not been fully elucidated. Using the functional near infrared spectroscopy, we attempted to compare the cortical effect between shoulder vibration exercise and shoulder simple exercise. Eight healthy subjects were recruited for this study. Two different exercise tasks（shoulder vibration exercise using the flexible pole and shoulder simple exercise） were performed using a block paradigm. We measured the values of oxygenated hemoglobin in the four regions of interest： the primary sensory-motor cortex（SM1 total, arm somatotopy, and leg and trunk somatotopy）, the premotor cortex, the supplementary motor area, and the prefrontal cortex. During shoulder vibration exercise and shoulder simple exercise, cortical activation was observed in SM1（total, arm somatotopy, and leg and trunk somatotopy）, premotor cortex, supplementary motor area, and prefrontal cortex. Higher oxygenated hemoglobin values were also observed in the areas of arm somatotopy of SM1 compared with those of other regions of interest. However, no significant difference in the arm somatotopy of SM1 was observed between the two exercises. By contrast, in the leg and trunk somatotopy of SM1, shoulder vibration exercise led to a significantly higher oxy-hemoglobin value than shoulder simple exercise. These two exercises may result in cortical activation effects for the motor areas relevant to the shoulder exercise, especially in the arm somatotopy of SM1. However, shoulder vibration exercise has an additional cortical activation effect for the leg and trunk somatotopy of SM1.展开更多
Human albumin(HA)is a very important blood product which requires strict quality controlstrategy.Acid precipitation is a key step which has a great effect on the quality of final product.Therefore,a new method based o...Human albumin(HA)is a very important blood product which requires strict quality controlstrategy.Acid precipitation is a key step which has a great effect on the quality of final product.Therefore,a new method based on quality by design(QbD)was proposed to investigate thefeasibility of realizing online quality control with the help of near infrared spectroscopy(NIRS)and chemometrics.The pH value is the critical process parameter(CPP)in acid precipitationprocess,which is used as the end-point indicator.Six batches,a total of 74 samples of acidprecipitation process,were simulated in our lab.Four batches were selected randomly as cali-bration set and remaining two batches as validation set.Then,the analysis based on materialinformation and three dfferent variable selection methods,including interval partial least squaresregression(iPLS),competitive adaptive reweighted sampling(CARS)and correlation coeficient(CC)were compared for eliminating irrelevant variables,Fimally,iPLS was used for variablesselection.The quantitative model was built up by partial least squares regression(PLSR).Thevalues of determination coeficients(R^(2)_(C) and R^(2)_(P)),root mean squares error of prediction(RMSEP),root mean squares error of calibration(RMSEC)and root mean squared error of crossvalidation(RMSECV)were 0.969,0.953,0.0496,0.0695 and 0.0826,respectively.The paired t test and repeatability test showed that the model had good prediction ability and stability.The results indicated that PLSR model could give accurate measurement of the pH value.展开更多
The composition of cement raw materials was detected by near-infrared spectroscopy.It was found that the BiPLS-SiPLS method selected the NIR spectral band of cement raw materials,and the partial least squares regressi...The composition of cement raw materials was detected by near-infrared spectroscopy.It was found that the BiPLS-SiPLS method selected the NIR spectral band of cement raw materials,and the partial least squares regression algorithm was adopted to establish a quantitative correction model of cement raw materials with good prediction effect.The root-mean-square errors of SiO_(2),Al_(2)O_(3),Fe_(2)O_(3) and CaO calibration were 0.142,0.072,0.034 and 0.188 correspondingly.The results show that the NIR spectroscopy method can detect the composition of cement raw meal rapidly and accurately,which provides a new perspective for the composition detection of cement raw meal.展开更多
Two universal spectral ranges(4550-4100 cm^(-1) and 6190-5510 cm^(-1))for construction of quantitative models of homologous analogs of cephalosporins were proposed by evaluating theperformance of five spectral ranges ...Two universal spectral ranges(4550-4100 cm^(-1) and 6190-5510 cm^(-1))for construction of quantitative models of homologous analogs of cephalosporins were proposed by evaluating theperformance of five spectral ranges and their combinations,using three data sets of cephalos-porins for injection,ie.,cefuroxime sodium,cetriaxone sodium and cefoperazone sodium.Subsequently,the proposed ranges were validated by using eight calibration sets of otherhomologous analogs of cephalosporins for injection,namely cefmenoxime hydrochloride,ceftezole sodium,cefmetazole,cefoxitin sodium,cefotaxime sodium,cefradine,cephazolin sodium and ceftizoxime sodium.All the constructed quantitative models for the eight kinds of cephalosporinsusing these universal ranges could fulill the requirements for quick quantification.After that,competitive adaptive reweighted sampling(CARS)algorithm and infrared(IR)-near infrared(NIR)two-dimensional(2D)correlation spectral analysis were used to determine the scientific basis of these two spectral ranges as the universal regions for the construction of quantitativemodels of cephalosporins.The CAR.S algorithm demonstrated that the ranges of 4550-4100 cm^(-1) and 6190-5510 cm^(-1) included some key wavenumbers which could be attributed to content changes of cephalosporins.The IR-NIR 2D spectral analysis showed that certain wavenumbersin these two regions have strong correlations to the structures of those cephalosporins that wereeasy to degrade.展开更多
Near infrared spectroscopy(NIRS)is based on molecular overtone and combination vibrations.It is difficult to assign specific features under complicated system.So it is necessary to find the relevance between NIRS and ...Near infrared spectroscopy(NIRS)is based on molecular overtone and combination vibrations.It is difficult to assign specific features under complicated system.So it is necessary to find the relevance between NIRS and target compound.For this purpose,the chondroitin sulfate(CS)ethanol precipitation process was selected as the research model,and 90 samples of 5 different batches were collected and the content of CS was determined by modifed carbazole method.The relevance between NIRS and CS was studied throughout optical pathlength,pretreat ment methods and variables selection methods.In conclusion,the first derivative with Savitzky--Golay(SG)smoothing was selected as the best pretreatment,and the best spectral region was selected using interval partial least squares(iPLS)method under 1 mm optical cell.A multivariate cali-bration model was established using PLS algorithm for determining the content of CS,and the root mean square error of prediction(RMSEP)is 3.934gL-1.This method will have great potential in process analytical technology in the future.展开更多
Near Infrared spectroscopy(NIRS)has been widely used in the discrimination(classification)of pharmaceutical drugs.In real applications,however,the class imbalance of the drug samples,i.e.,the number of one drug sample...Near Infrared spectroscopy(NIRS)has been widely used in the discrimination(classification)of pharmaceutical drugs.In real applications,however,the class imbalance of the drug samples,i.e.,the number of one drug sample may be much larger than the number of the other drugs,deceasesdrastically the discrimination performance of the classification models.To address this classimbalance problem,a new computational method--the scaled convex hull(SCH)-basedmaximum margin classifier is proposed in this paper.By a suitable selection of the reductionfactor of the SCHs generated by the two classes of drug samples,respectively,the maximalmargin classifier bet ween SCHs can be constructed which can obtain good classification per-formance.With an optimization of the parameters involved in the modeling by Cuckoo Search,a satisfied model is achieved for the classification of the drug.The experiments on spectra samplesproduced by a pharmaceutical company show that the proposed method is more effective androbust than the existing ones.展开更多
基金Supported by Natural Science Foundation of Heilongjiang Province(LH2022E099)Daqing Guidance Fund for Science and Technology Planning Project(zd-2023-63)San Heng San Zong Support Program of Heilongjiang Bayi Agricultural University(ZRCPY202216).
文摘[Objectives]This study was conducted to realize the rapid and nondestructive identification of blueberry producing areas and protect benefits of high-quality blueberry brands.[Methods]Five types of blueberries from different regions were selected as experimental subjects,and spectral analysis techniques were combined with deep learning.Firstly,standard normal variable transform(SNV)and convolutional smoothing(SG)were used to deal with scattering noise and other issues in original spectral data.Secondly,due to a large amount of redundant information and high correlation between adjacent wavelengths in the collected spectra,continuous projection algorithm(SPA)and partial least squares regression(PLS)were combined for screening of features with RMSE as the indicator,and 40 feature variables were obtained.Finally,a convolutional network model CNN-SE integrating a Squeeze and Excitation(SE)attention mechanism module was constructed and compared with convolutional neural network(CNN),support vector machine(SVM),and BP neural network.[Results]The CNN-SE model had the best effect,with the accuracy and precision of the test set reaching 95%and 94.56%,respectively,and the recall and F 1 score reaching 93.94%and 94.24%,respectively.[Conclusions]The CNN-SE convolution network model can realize rapid,nondestructive and high-throughout identification of blueberry producing areas.
基金Supported by the Collection and Arrangement of Crop Germplasm Resources in Shanxi Province(2016zzcx-17)the Special Fund for the Protection and Utilization of Crop Germplasm Resources of the Ministry of Agriculture(2015NWB030-07)+1 种基金the Project of the National Science and Technology Infrastructure of the Ministry of Science and Technology and the Ministry of Finance(NICGR2015-026)the Special Fund for Seed Industry of Shanxi Province(2016zyzx41)~~
文摘[Objective] To explore a rapid determination method for fiber content in grains of quinoa. [Method] Near infrared spectra of 100 quinoa samples were collected. The predicted models for quantitative analysis of fiber contents in the grains were built using near infrared transmittance spectroscopy （NITS）. [Result] In the wavelength range of 10 000-4 000 cm-1, the near infrared quantitative model of quinoa crude fiber was set up via first derivative ＋ vector normalization preprocessing and combining with the data from chemical methods. The calibration and prediction effect were best, and then the cross validation determination coefficient （FFcv） and external validation determination coefficient （FFval） of fiber by near in- frared quantitative model were 0.884 8 and 0.876 1, respectively. [Conclusion] the model of NITS about complete grains quinoa fiber can be available for fast detecting quinoa fiber content.
基金Project supported by the National Science and Technology Major Project(No.2011ZX09201-201-10),China
文摘We have developed a set of chemometric methods to address two critical issues in quality control of a precious traditional Chinese medicine （TCM）, Dong＇e Ejiao （DEE J）. Based on near infrared （NIR） spectra of multiple samples, the genuine manufacturer of DEE J, e.g. Dong＇e Ejiao Co., Ltd., was accurately identified among 21 suppliers by the fingerprint method using Hotelling T2, distance to Model X （DModX）, and similarity match value （SMV） as dis- criminate criteria. Soft independent modeling of the class analogy algorithm led to a misjudgment ratio of 6.2%, suggesting that the fingerprint method is more suitable for manufacturer identification. For another important feature related to clinical efficacy of DEE J, storage time, the partial least squares-discriminant analysis （PLS-DA） method was applied with a satisfactory misjudgment ratio （15.6%） and individual prediction error around 1 year. Our results demonstrate that NIR spectra comprehensively reflect the essential quality information of DEE J, and with the aid of proper chemometric algorithms, it is able to identify genuine manufacturer and determine accurate storage time. The overall results indicate the promising potential of NIR spectroscopy as an effective quality control tool for DEEJ and other precious TCM products.
基金supported by National Natural Science Foundation of China(No.20835002)
文摘Near infrared（NIR） spectroscopy technique has shown great power and gained wide acceptance for analyzing complicated samples.The present work is to distinguish different brands of tobacco products by using on-line NIR spectroscopy and pattern recognition techniques.Moreover,since each brand contains a large number of samples,an improved dendrogram was proposed to show the classification of different brands.The results suggest that NIR spectroscopy combined with principal component analysis （PCA） and hierarchical cluster analysis（HCA） performs well in discrimination of the different brands,and the improved dendrogram could provide more information about the difference of the brands.
文摘With the technique of Fourier transform near infrared (FT-NIR) spectroscopy, the calibration models for quantitative analysis of sucrose and polarization in sugarcane juice were developed by using transmission mode and calibrating with partial least square (PLS) algorithm. The determination coefficients (R2) of the predicted models for sucrose and polarization in juice were 0. 9980 and 0. 9979 respectively; the root mean square errors of cross validation (RMSECV) were 0. 143 and 0. 155% for sucrose and polarization in juice respectively. The predictive errors measured by FT-NIR were close to those by routine laboratory methods. The results demonstrated that the FT-NIR methods had high accuracy and they were able to replace the routine laboratory analysis. It was also demonstrated that as a rapid and accurate measurement, the FT-NIR technique had potential applications in quality control of mill sugarcane, establishment of payment system based on sugarcane quality, and selection of clones in sugarcane breeding.
基金Supported by the National 12th Five-year Plan for Science&Technology Support Fund(2012BAK08B04-02)the Heilongjiang Science and Technology Plan(GC12B404)
文摘Near infrared spectrometer technology under a wavelength range of 918-1045 nm was used to rapidly detect paddy rice that was stored at 5℃, 15℃ and 25℃. A total of 121 paddy rice samples were collected from artificial infection with moulds to build the calibration models to calculate the total number colony of moulds based on the principal component regression method and multiple linear regression method. The results of statistical analysis indicated that multiple linear regression method was applicable to the detection of the total number colony of moulds. The correlation of calibration data set was 0.943. The correlation of prediction data set was 0.897. Therefore, the result showed that near infrared spectroscopy could be a useful instrumental method for determining the total number colony of moulds in paddy rice. The near infrared spectroscopy methodology could be applied for monitoring mould contamination in postharvest paddy rice during storage and might become a powerful tool for monitoring the safety of the grain.
基金the National Natural Science Foundation of China(Grant Nos.21365008 and 61562013)Natural Science.Foundation of Guangxi(Grant No.2013GXNSFBA019279)Innovation Project of GUET Graduate.Education(Grant Nos.GDYCSZ201474 and GDYCSZ201478).
文摘Near infrared spectroscopy(NIRS)analysis technology,combined with chemometrics,can be effectively used in quick and nondestructive analysis of quality and category.In this paper,an effective drug identification method by using deep belief network(DBN)with dropout mecha-nism(dropout-DBN)to model NIRS is introduced,in which dropout is employed to overcome the overfitting problem coming from the small sample.This paper tests proposed method under datasets of different sizes with the example of near infrared diffuse refectance spectroscopy of erythromycin ethylsuccinate drugs and other drugs,aluminum and nonaluminum packaged.Meanwhile,it gives experiments to compare the proposed method's performance with back propagation(BP)neural network,support vector machines(SVMs)and sparse denoising auto-encoder(SDAE).The results show that for both binary classification and multi-classification,dropout mechanism can improve the classification accuracy,and dropout-DBN can achieve best classification accuracy in almost all cases.SDAE is similar to dropout-DBN in the aspects of classification accuracy and algorithm stability,which are higher than that of BP neural network and SVM methods.In terms of training time,dropout-DBN model is superior to SDAE model,but inferior to BP neural network and SVM methods.Therefore,dropout-DBN can be used as a modeling tool with effective binary and multi-class classification performance on a spectrum sample set of small size.
基金the Project of“Accurate Identification of Sunflower Germplasm Resources(19221985)”the earmarked fund of“CARS—Specific Oilseed Crops(CARS-14)”+2 种基金the Project of“Exploration,Identification and Innovative Utilization of Excellent Germplasm Resources of Oil Crops(CAAS-OCRI-ZDRW-202101)”the Project of“Oil Crop Germplasm Resource Protection(19221888-4)”the Project of“National Science and Technology Resource Sharing Service Platform(NCGRC-2022-Special Oil Crop)”。
文摘To clarify the quality characters,understand the genetic diversity and screen elite lines among different oilseed sunflowers,the contents of crude fat,oleic acid,linoleic acid,palmitic acid and stearic acid of 525 oil sunflowers(including 375 germplasm accessions and 150 inbred lines)were detected by near-infrared spectroscopy(NIRS);the genetic variation and correlation analysis of quality traits were also performed.The results showed that oleic acid and linoleic acid had rich diversities with large variation ranges for each material type.Similar to the relation between crude fat content and palmitic acid content,significantly negative relation with high estimated value existed between oleic acid and linoleic acid content,while stearic acid content positively associated with oleic acid and palmitic acid content.Principal component analysis indicated that 5 quality traits were integrated into 2principal component factors(linoleic acid negative factor and palmitic acid factor)with the contribution rate of 88.191%,which could be used for evaluating sunflower quality.525 oilseed sunflowers were clustered into 3groups with obvious differences of quality characters,materials in Group I had high contents of oleic acid and low crude fat,but the opposite was found in GroupⅢ.59 superior quality accessions were obtained using large-scale and rapid near-infrared spectroscopy,and these excellent materials were verified by the traditional national chemical standard method.This research provided materials and significant reference for sunflower genetic research and quality breeding.
基金supported by the National Basic Research Program(973)of China(No.2012CB518405)the Zhejiang Traditional Medical Science and Technology Projects(No.2015ZB023),China
文摘A near infrared spectroscopy（NIRS） approach was established for quality control of the alcohol precipitation liquid in the manufacture of Codonopsis Radix. By applying NIRS with multivariate analysis, it was possible to build variation into the calibration sample set, and the Plackett-Burman design, Box-Behnken design, and a concentrating-diluting method were used to obtain the sample set covered with sufficient fluctuation of process parameters and extended concentration information. NIR data were calibrated to predict the four quality indicators using partial least squares regression（PLSR）. In the four calibration models, the root mean squares errors of prediction（RMSEPs） were 1.22 μg/ml, 10.5 μg/ml, 1.43 μg/ml, and 0.433% for lobetyolin, total flavonoids, pigments, and total solid contents, respectively. The results indicated that multi-components quantification of the alcohol precipitation liquid of Codonopsis Radix could be achieved with an NIRS-based method, which offers a useful tool for real-time release testing（RTRT） of intermediates in the manufacture of Codonopsis Radix.
基金Financial support from China Postdoctoral Science Foundation Special Funded Project(2013T60604)Zhejang Provincial Public Welfare Application Project of China(2012C21102)are gratefully acknowledged.
文摘A discriminant analysis technique using wavelet transformation(WT)and influence matrixanalysis(CAIMAN)method is proposed for the near infrared(NIR)spectroscopy classifi-cation.In the proposed methodology,NIR spectra are decomposed by WT for data com-pression and a forward feature selection is further employed to extract the relevant informationfrom the wavelet coefficients,reducing both classification errors and model complexity.Adiscriminant-CAIMAN(D-CAIMAN)method is utilized to build the classification model inwavelet domain on the basis of reduced wavelet coefficients of spectral variables.NIR spectradata set of 265 salviae miltiorrhizae radia samples from 9 different geographical origins is usedas an example to test the classification performance of the algorithm.For a comparison,k-nearest neighbor(KNN),linear discriminant analysis(LDA)and quadratic discriminant analysis(QDA)methods are also employed.D-CAIMAN with wavelet-based feature selection(WD-CAIMAN)method shows the best performance,achieving the total classification rate of ioo%in both cross-validation set and prediction set.It is worth noting that the WD-CAIMANclassifier also shows improved sensitivity,selectivity and model interpretability in thecla.ssifications.
基金Key Research and Development Program of Anhui Province(No.201904a07020073)Science and Technology Foundation of Electronic Test&Measurement Laboratory(No.6142001180307)National Basic Research Program(No.JSJL2018210C003)。
文摘As one of the important indicators of spectrometer,signal-to-noise ratio(SNR)reflects the ability of spectrometer to detect weak signals.To investigate the influence of SNR on the prediction accuracy of spectral analysis,we first introduce the major factors affecting the spectral SNR.Taking green tea as an example,the influence of spectral SNR on the prediction accuracy of the origin identification model is analyzed by experiments.At the same time,the relationship between the spectral SNR and prediction accuracy of spectral analysis model is fitted.Based on this,the common methods for improving the spectral SNR are discussed.The results show that the accuracy of the prediction set model first decreases slowly,then decreases linearly,and finally tends to be flat as the spectral SNR decreases.Through calculation,in order to achieve the prediction accuracy of prediction model reaching 90%and 85%,the spectral SNR is required to be higher than 23.42 dB and 21.16 dB,respectively.The overall results provide certain parameters support for the development of new online analytical spectroscopic instruments,especially for the technical indicators of SNR.
基金We are grateful for the financial support of the Major Special Project of National Science and Technology (No.2014ZX09508003).
文摘As an important process analysis tool,near infrared spectroscopy(NIRS)has been widely used in process monitoring.In the present work,the feasibility of NIRS for monitoring the moisture content of human coagulation factor VIII(FVIII)in freeze-drying process was investigated.A partial least squares regression(PLS-R)model for moisture content determination was built with 88 samples.Different pre-processing methods were explored,and the best method found was standard normal variate(SNV)transformation combined with 1st derivation with Savitzky–Golay(SG)15 point smoothing.Then,four different variable selection methods,including uninformative variable elimination(UVE),interval partial least squares regression(iPLS),competitive adaptive reweighted sampling(CARS)and manual method,were compared for eliminating irrelevant variables,and iPLS was chosen as the best variable selection method.The correlation coe±cient(R),correlation coe±cient of calibration set(Rcal),correlation coefficient of validation set(Rval),root mean square errors of cross-validation(RMSECV)and root mean square errors of prediction(RMSEP)of PLS model were 0.9284,0.9463,0.8890,0.4986% and 0.4514%,respectively.The results showed that the model for moisture content determination has a wide range,good linearity,accuracy and precision.The developed approach was demonstrated to be a potential for monitoring the moisture content of FVIII in freeze-drying process.
文摘Germinated brown rice(GBR)is rich in gamma oryzanol which increase its consumption popularity,particularly in the health food market.The objective of this research was to apply the near infraredspectroscopy(NIRS)for evaluation of gamma oryzanol of the germinated brown rice.The germinated brown rice samples were prepared from germinated rough rice(soaked for 24 and 48 h,incubated for 0,6,12,18,24,30 and 36 h)and purchased from local supermar kets.The germinated brown rice sampleswere subjected to NIR scanning before the evaluation of gamma oryzanol by using partial extractionmet hodology.The prediction model was established by partial least square regression(PLSR)andvalidated by full cross validation method.The NIRS model established from various varieties of germinated brown rice bought from diferent markets by first derivatives+vector normalizationpretreated spectra showed the optimal prediction with the correlation of determination(R?),root mean squared error of cross validation(RMSECV),and bias of 0.934,8.84×10^(-5) mg/100 g drymatter and 1.06×10^(-5) mg/100 g dry matter,respectively.This is the first report on the application of NIRS in the evaluation of gamma oryzanol of the germinated brown rice.This information is veryuseful to the germinated brown rice production factory and consumers.
文摘Although near infrared (NIR) spectroscopy has been evaluated for numerous applications, the number of actual on-line or even on-site industrial applications seems to be very limited. In the present paper, the attempts to produce online predictions of the chemical oxygen demand (COD) in wastewater from a pulp and paper mill using NIR spectroscopy are described. The task was perceived as very challenging, but with a root mean square error of prediction of 149 mg/l, roughly corresponding to 1/10 of the studied concentration interval, this attempt was deemed as successful. This result was obtained by using partial least squares model regression, interpolated reference values for calibration purposes, and by evenly distributing the calibration data in the concentration space. This work may also represent the first industrial application of online COD measurements in wastewater using NIR spectroscopy.
基金supported by the DGIST R&D Program of the Ministry of Science,ICT and Future Planning(16-BD-0401)
文摘To date, the cortical effect of exercise has not been fully elucidated. Using the functional near infrared spectroscopy, we attempted to compare the cortical effect between shoulder vibration exercise and shoulder simple exercise. Eight healthy subjects were recruited for this study. Two different exercise tasks（shoulder vibration exercise using the flexible pole and shoulder simple exercise） were performed using a block paradigm. We measured the values of oxygenated hemoglobin in the four regions of interest： the primary sensory-motor cortex（SM1 total, arm somatotopy, and leg and trunk somatotopy）, the premotor cortex, the supplementary motor area, and the prefrontal cortex. During shoulder vibration exercise and shoulder simple exercise, cortical activation was observed in SM1（total, arm somatotopy, and leg and trunk somatotopy）, premotor cortex, supplementary motor area, and prefrontal cortex. Higher oxygenated hemoglobin values were also observed in the areas of arm somatotopy of SM1 compared with those of other regions of interest. However, no significant difference in the arm somatotopy of SM1 was observed between the two exercises. By contrast, in the leg and trunk somatotopy of SM1, shoulder vibration exercise led to a significantly higher oxy-hemoglobin value than shoulder simple exercise. These two exercises may result in cortical activation effects for the motor areas relevant to the shoulder exercise, especially in the arm somatotopy of SM1. However, shoulder vibration exercise has an additional cortical activation effect for the leg and trunk somatotopy of SM1.
基金support of the Major Special Project of National Science and Technology(No.2014ZX09508003-001-003)the supply of Supernatant FIV of Shandong Taibang Biological Products Limited Company.
文摘Human albumin(HA)is a very important blood product which requires strict quality controlstrategy.Acid precipitation is a key step which has a great effect on the quality of final product.Therefore,a new method based on quality by design(QbD)was proposed to investigate thefeasibility of realizing online quality control with the help of near infrared spectroscopy(NIRS)and chemometrics.The pH value is the critical process parameter(CPP)in acid precipitationprocess,which is used as the end-point indicator.Six batches,a total of 74 samples of acidprecipitation process,were simulated in our lab.Four batches were selected randomly as cali-bration set and remaining two batches as validation set.Then,the analysis based on materialinformation and three dfferent variable selection methods,including interval partial least squaresregression(iPLS),competitive adaptive reweighted sampling(CARS)and correlation coeficient(CC)were compared for eliminating irrelevant variables,Fimally,iPLS was used for variablesselection.The quantitative model was built up by partial least squares regression(PLSR).Thevalues of determination coeficients(R^(2)_(C) and R^(2)_(P)),root mean squares error of prediction(RMSEP),root mean squares error of calibration(RMSEC)and root mean squared error of crossvalidation(RMSECV)were 0.969,0.953,0.0496,0.0695 and 0.0826,respectively.The paired t test and repeatability test showed that the model had good prediction ability and stability.The results indicated that PLSR model could give accurate measurement of the pH value.
基金Funded by the National Natural Science Foundation of China (No. 62073153)The Major Scientific and Technological Innovation Projects in Shandong Province (No.2019JZZY010448)The Key Research and Development Plan of Shandong Province of China (No.2019GSF109018)。
文摘The composition of cement raw materials was detected by near-infrared spectroscopy.It was found that the BiPLS-SiPLS method selected the NIR spectral band of cement raw materials,and the partial least squares regression algorithm was adopted to establish a quantitative correction model of cement raw materials with good prediction effect.The root-mean-square errors of SiO_(2),Al_(2)O_(3),Fe_(2)O_(3) and CaO calibration were 0.142,0.072,0.034 and 0.188 correspondingly.The results show that the NIR spectroscopy method can detect the composition of cement raw meal rapidly and accurately,which provides a new perspective for the composition detection of cement raw meal.
基金supported by grant from the National Department Public Benefit Research Foundation(General Administration of Quality Supervision,inspection and Quarantine of the People's Republicof China)(Grant No.2012104008)At the sametime,the authors would like to thank Prof Yi zeng Liang(Central South University,PR China)for freely providing us with CARS program。
文摘Two universal spectral ranges(4550-4100 cm^(-1) and 6190-5510 cm^(-1))for construction of quantitative models of homologous analogs of cephalosporins were proposed by evaluating theperformance of five spectral ranges and their combinations,using three data sets of cephalos-porins for injection,ie.,cefuroxime sodium,cetriaxone sodium and cefoperazone sodium.Subsequently,the proposed ranges were validated by using eight calibration sets of otherhomologous analogs of cephalosporins for injection,namely cefmenoxime hydrochloride,ceftezole sodium,cefmetazole,cefoxitin sodium,cefotaxime sodium,cefradine,cephazolin sodium and ceftizoxime sodium.All the constructed quantitative models for the eight kinds of cephalosporinsusing these universal ranges could fulill the requirements for quick quantification.After that,competitive adaptive reweighted sampling(CARS)algorithm and infrared(IR)-near infrared(NIR)two-dimensional(2D)correlation spectral analysis were used to determine the scientific basis of these two spectral ranges as the universal regions for the construction of quantitativemodels of cephalosporins.The CAR.S algorithm demonstrated that the ranges of 4550-4100 cm^(-1) and 6190-5510 cm^(-1) included some key wavenumbers which could be attributed to content changes of cephalosporins.The IR-NIR 2D spectral analysis showed that certain wavenumbersin these two regions have strong correlations to the structures of those cephalosporins that wereeasy to degrade.
基金the Chinese National Level College Student Innovation Project (No.1110422080)the 863 program (Hi-tech research and development program of China)under contract NO.2012AA021505the National Training Programs of Innovation and Entrepreneurship for Undergraduates (No.201210422079).
文摘Near infrared spectroscopy(NIRS)is based on molecular overtone and combination vibrations.It is difficult to assign specific features under complicated system.So it is necessary to find the relevance between NIRS and target compound.For this purpose,the chondroitin sulfate(CS)ethanol precipitation process was selected as the research model,and 90 samples of 5 different batches were collected and the content of CS was determined by modifed carbazole method.The relevance between NIRS and CS was studied throughout optical pathlength,pretreat ment methods and variables selection methods.In conclusion,the first derivative with Savitzky--Golay(SG)smoothing was selected as the best pretreatment,and the best spectral region was selected using interval partial least squares(iPLS)method under 1 mm optical cell.A multivariate cali-bration model was established using PLS algorithm for determining the content of CS,and the root mean square error of prediction(RMSEP)is 3.934gL-1.This method will have great potential in process analytical technology in the future.
基金funded by the National Nat ural Science Foundation of China(Grant Nos.61105004,61071136and 21365008)Natural Science Foundation of Guangxi(Grant No.2013GXNSFBA019279)Innovation Project of GUET Graduate Education(No.ZYC0725).
文摘Near Infrared spectroscopy(NIRS)has been widely used in the discrimination(classification)of pharmaceutical drugs.In real applications,however,the class imbalance of the drug samples,i.e.,the number of one drug sample may be much larger than the number of the other drugs,deceasesdrastically the discrimination performance of the classification models.To address this classimbalance problem,a new computational method--the scaled convex hull(SCH)-basedmaximum margin classifier is proposed in this paper.By a suitable selection of the reductionfactor of the SCHs generated by the two classes of drug samples,respectively,the maximalmargin classifier bet ween SCHs can be constructed which can obtain good classification per-formance.With an optimization of the parameters involved in the modeling by Cuckoo Search,a satisfied model is achieved for the classification of the drug.The experiments on spectra samplesproduced by a pharmaceutical company show that the proposed method is more effective androbust than the existing ones.
