scholarly journals Development of calibration models for rapid determination of moisture content in rubber sheets using portable near-infrared spectrometers

2020 ◽  
Vol 13 (02) ◽  
pp. 2050009
Author(s):  
Amorndej Puttipipatkajorn ◽  
Amornrit Puttipipatkajorn
Keyword(s):  
Moisture Content ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared ◽  
Least Square ◽  
Mean Square ◽  
Ann Model ◽  
Rubber Sheet ◽  
Calibration Models

Rubber sheets are one of the primary products of natural rubber and are the main raw material in various rubber industries. The quality of a rubber sheet can be visually examined by holding it against clear light to inspect for any specks and impurities inside, but its moisture content is difficult to evaluate based on a visual inspection and this might lead to unfair trading. Herein, we developed a rapid, robust and nondestructive near-infrared spectroscopy (NIRS)-based method for moisture content determination in rubber sheets. A set of 300 rubber sheets were divided into a calibration (200 samples) and prediction groups (100 samples). The calibration set was used to develop NIRS calibration equation using different calibration models, Partial Least Square Regression (PLSR), Least Square Support Vector Machine (LS-SVM) and Artificial Neural Network (ANN). Among the models investigated, the ANN model with the first derivative of spectral preprocessing presented the best prediction with a coefficient of determination ([Formula: see text] of 0.993, root mean square error of calibration (RMSEC) of 0.126% and root mean square error of prediction (RMSEP) of 0.179%. The results indicated that the proposed NIRS-ANN model will be able to reduce human error and provide a highly accurate estimate of the moisture content in a rubber sheet compared to traditional wet chemistry estimation methods according to AOAC standards.

The Actoside Content Analysis in Radix Rehmanniae Using Near-Infrared Technology

2014 ◽  
Vol 912-914 ◽  
pp. 374-377
Author(s):  
Hai Yan Gong ◽  
Cai Xia Xie ◽  
Yong Xia Cui ◽  
Zhi Hong Chen ◽  
Yan Bai ◽  
...  
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Partial Least Square ◽  
Least Square ◽  
Mean Square ◽  
Calibration Models ◽  
Average Recovery Rate

In this paper, near-infrared diffuse reflectance spectroscopy was used to analysis the acteoside content of Radix Rehmanniae. The quantitative calibration models of acteoside content were established by the partial least square (PLS). The results showed that the correlation coefficient of calibration (R2) was 0.98102, the root-mean-square error of calibration (RMSEC) was 0.00464, the root-mean-square error of prediction (RMSEP) was 0.00163, and the average recovery rate was 104.837%. So the recovery of prediction set was available. The results indicated that it was available to determine the content of actoside in Radix Rehmanniae by near-infrared spectroscopy.

Nondestructive Method for Analysis of the Soybean Quality

2012 ◽  
Vol 8 (4) ◽  
Author(s):  
Yan Dong ◽  
Shi You Qu
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Crude Protein ◽  
Near Infrared ◽  
Nondestructive Method ◽  
Partial Least Square ◽  
Least Square ◽  
Mean Square ◽  
Pre Treatment

Abstract Fourier transform near infrared (NIR) spectra combined with chemometric methods was proposed to the analysis of the crude protein and fat contents in whole-kernel soybean. The calibration models were established by partial least square. After optimizing spectral pre-treatment, the determination coefficient (R2) of the crude protein and fat were 0.971, 0.970, and root mean square error of calibration (RMSEC) were 0.610, 0.365，respectively. For the prediction samples of the crude protein and fat, root mean square error of prediction (RMSEP) were 0.766, 0.420, respectively. The analytical results showed that NIR spectra had significant potential as a rapid and nondestructive method for the crude protein and fat contents in soybean.

scholarly journals Rapid and Simultaneous Measurement of Praeruptorin A, Praeruptorin B, Praeruptorin E, and Moisture Contents in Peucedani Radix Using Near-Infrared Spectroscopy and Chemometrics

2020 ◽  
Vol 103 (2) ◽  
pp. 504-512
Author(s):  
Yijuan Hu ◽  
Hongjian Zhang ◽  
Weiqing Liang ◽  
Pan Xu ◽  
Kelang Lou ◽  
...  
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Mean Square ◽  
Determination Coefficient ◽  
Moisture Contents ◽  
Calibration Models

Abstract Background: Peucedani Radix is a popular traditional Chinese medicine herb with a long history in China. Praeruptorin A (PA), praeruptorin B (PB), and praeruptorin E (PE) are usually taken as important quality indexes of Peucedani Radix. Objective: To establish a rapid method for simultaneous determination of PA, PB, PE, and moisture contents in Peucedani Radix using near-infrared (NIR) spectroscopy and chemometrics. Methods: One hundred twenty Peucedani Radix samples were analyzed with HPLC as a reference method. The NIR spectral scanning range was from 12000 cm−1 to 4000 cm−1. Partial least squares (PLS) regression algorithm was used to establish calibration models. Three variable selection methods were investigated, including variable importance in projection (VIP), competitive adaptive reweighted sampling (CARS), and Monte Carlo uninformative variable elimination (MCUVE). The performances of the established models were evaluated by root-mean-square error (RMSEC) and determination coefficient (Rc2) of calibration set, root-mean-square error (RMSEP) and determination coefficient (Rp2) of prediction set, and residual predictive deviation (RPD). Results: A clear ranking of the performance of the calibration models could be as follows: CARS-PLS > MCUVE-PLS > VIP-PLS > Full-PLS. For CARS-PLS, Rp2, RMSEP, and RPD of the prediction set are as follows: 0.9204, 0.0860%, and 3.5850 for PA; 0.8011, 0.0431%, and 2.0868 for PB; 0.8043, 0.0367%, and 2.1569 for PE; and 0.9249, 0.3350%, and 3.6551 for moisture, respectively. Conclusions: The NIR spectroscopy combined with CARS-PLS calibration models could be used for rapid and accurate determination of PA, PB, PE, and moisture contents in Peucedani Radix samples.

Rapid Determination of Paeoniflorin and Moisture in Xiaoyao Pills (Concentrated) by Near-Infrared Spectroscopy

2013 ◽  
Vol 807-809 ◽  
pp. 1972-1977
Author(s):  
Yan Bai ◽  
Hai Yan Gong ◽  
Xiao Qing Li ◽  
Cai Xia Xie ◽  
Xiao Yan Duan ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Least Square ◽  
Calibration Model ◽  
Mean Square

The objective of the present research was to establish a rapid analytical method for paeoniflorin and moisture in Xiaoyao Pills (condensed) by near-infrared spectroscopy. The near-infrared spectral data of 97 samples was collected by Nicolet 6700 NIR spectrograph,and the reference value of index component content were obtained by HPLC and oven-drying method. Then the multivariate calibration model of paeoniflorin and moisture were established by patrical least square (PLS) and predicting the content of unknow samples. The results showed that the correlation coefficients (R2) of the quantitative calibration model for paeoniflorin and moisture were 0.99774,0.95352, the root-mean-square error of calibration (RMSEC) were 0.00489,0.132,the root-mean-square error of prediction (RMSEP) were 0.00827,0.177. The results indicated that NIRS can provide a simple and accurate way for the fast determination of index component in large numbers of Xiaoyao Pills (concentrated).

Detection of wet-pockets on the surface of Tsuga heterophylla (Raf.) Sarg. by near infrared (NIR) spectroscopy

Holzforschung ◽  
2010 ◽  
Vol 64 (1) ◽  
Author(s):  
Ken Watanabe ◽  
Foster Hart ◽  
Shawn D. Mansfield ◽  
Stavros Avramidis
Keyword(s):  
Moisture Content ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared ◽  
Tsuga Heterophylla ◽  
Moisture Distribution ◽  
Mean Square ◽  
Surface Moisture ◽  
Line Speed

Abstract Multivariate statistical models capable of rapidly and accurately predicting the surface moisture content in Tsuga heterophylla were developed based on near infrared (NIR) spectra of small specimens precisely conditioned within the hygroscopic range. In an initial research phase, the applicability of NIR as predictor of surface moisture was investigated. The first derivative spectra in the range of 1300–2100 nm yielded the best results. The partial least squares regression (PLS-1) model had coefficient of determination (R2) of 0.98, root mean square error of cross validation (RMSECV) of 0.97%, root mean square error of prediction (RMSEP) of 1.05%, and ratio of performance to deviation (RPD) of 7.25. In a subsequent phase, an inline pilot-plant NIR system combined with this PLS-1 model was constructed. The prediction ability of the NIR system was tested with line speeds of 0, 100, 200, and 400 mm s-1 on kiln-dried full-length lamination boards classified as “wets” after conventional kiln drying. In a calibrated range of moisture content (0–25.4%), the NIR system demonstrated R2 values of 0.79 and 0.74, RMSEP values of 3.13 and 3.28, and RPD values of 2.18 and 1.67 at a line speed of 0 and 100 mm s-1, respectively, regardless of the presence of knots and surface roughness. These results demonstrate that the NIR system at a line speed of 0–100 mm s-1 could be used to provide entire surface moisture distribution and to detect local moisture peaks that indicate surface wet-pockets in kiln-dried lumber destined for lamination.

Quantitative Analysis of Forsythiae fructus by Near Infrared Spectroscopy

2013 ◽  
Vol 807-809 ◽  
pp. 1967-1971
Author(s):  
Yan Bai ◽  
Xiao Yan Duan ◽  
Hai Yan Gong ◽  
Cai Xia Xie ◽  
Zhi Hong Chen ◽  
...  
Keyword(s):  
Infrared Spectroscopy ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Cross Validation ◽  
Ethanol Extract ◽  
Mean Square ◽  
Validation Set

In this paper, the content of forsythoside A and ethanol-extract were rapidly determinated by near-infrared reflectance spectroscopy (NIRS). 85 samples of Forsythiae Fructus harvested in Luoyang from July to September in 2012 were divided into a calibration set (75 samples) and a validation set (10 samples). In combination with the partical least square (PLS), the quantitative calibration models of forsythoside A and ethanol-extract were established. The correlation coefficient of cross-validation (R2) was 0.98247 and 0.97214 for forsythoside A and ethanol-extract, the root-mean-square error of calibration (RMSEC) was 0.184 and 0.570, the root-mean-square error of cross-validation (RMSECV) was 0.81736 and 0.36656. The validation set were used to evaluate the performance of the models, the root-mean-square error of prediction (RMSEP) was 0.221 and 0.518. The results indicated that it was feasible to determine the content of forsythoside A and ethanol-extract in Forsythiae Fructus by near-infrared spectroscopy.

scholarly journals Authentication of Patin Fish Oil (Pangasius micronemus) using FTIR Spectroscopy Combined with Chemometrics

2020 ◽  
pp. 23
Author(s):  
Anggita Rosiana Putri ◽  
Abdul Rohman ◽  
Sugeng Riyanto ◽  
Widiastuti Setyaningsih
Keyword(s):  
Root Mean Square Error ◽  
Fish Oil ◽  
Ftir Spectroscopy ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Partial Least Square ◽  
Least Square ◽  
Partial Least Square Regression ◽  
Coefficient Of Determination ◽  
Mean Square

Authentication of Patin fish oil (MIP) is essential to prevent adulteration practice, to ensure quality, nutritional value, and product safety. The purpose of this study is to apply the FTIR spectroscopy combined with chemometrics for MIP authentication. The chemometrics method consists of principal component regression (PCR) and partial least square regression (PLSR). PCR and PLSR were used for multivariate calibration, while for grouping the samples using discriminant analysis (DA) method. In this study, corn oil (MJ) was used as an adulterate. Twenty-one mixed samples of MIP and MJ were prepared with the adulterate concentration range of 0-50%. The best authentication model was obtained using the PLSR technique using the first derivative of FTIR spectra at a wavelength of 650-3432 cm-1. The coefficient of determination (R2) for calibration and validation was obtained 0.9995 and 1.0000, respectively. The value of root mean square error of calibration (RMSEC) and root mean square error of prediction (RMSEP) were 0.397 and 0.189. This study found that the DA method can group the samples with an accuracy of 99.92%.

Multivariate analysis of three chemometric algorithms on rapid prediction of some important quality parameters of crude shea butter using Fourier transform-near infrared spectroscopy

2019 ◽  
Vol 27 (3) ◽  
pp. 220-231
Author(s):  
Emmanuel Amomba Seweh ◽  
Zou Xiaobo ◽  
Feng Tao ◽  
Shi Jiachen ◽  
Haroon Elrasheid Tahir ◽  
...  
Keyword(s):  
Genetic Algorithm ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Cross Validation ◽  
Partial Least Square ◽  
Least Square ◽  
Mean Square ◽  
Saponification Value ◽  
Peroxide Values

A comparative study of three chemometric algorithms combined with NIR spectroscopy with the aim of determining the best performing algorithm for quantitative prediction of iodine value, saponification value, free fatty acids content, and peroxide values of unrefined shea butter. Multivariate calibrations were developed for each parameter using supervised partial least squares, interval partial least squares, and genetic-algorithm partial least square regression methods to establish a linear relationship between standard reference and the Fourier transformed-near infrared predicted. Results showed that genetic-algorithm partial least square models were superior in predicting iodine value and saponification value while partial least squares was excellent in predicting free fatty acids content and peroxide values. The nine-factor genetic-algorithm partial least square iodine value calibration model for predicting iodine value yielded excellent ( R2 cal = 0.97), ( R2 val = 0.97), low (root mean square error of cross-validation = 0.26), low (root mean square error of Prediction = 0.23), and (ratio of performance to deviation = 6.41); for saponification value, the nine-factor genetic-algorithm partial least square saponification value calibration model had excellent R2 cal (0.97), R2 val (0.99); low root mean square error of cross-validation (0.73), low root mean square error of Prediction (0.53), and (ratio of performance to deviation = 8.27); while for free fatty acids, the 11-factor partial least square free fatty acids produced very high R2 cal (0.97) and R2 val (0.97) with very low root mean square error of cross-validation (0.03), low root mean square error of Prediction (0.04) and (ratio of performance to deviation = 5.30) and finally for peroxide values, the 11-factor partial least square peroxide values calibration model obtained excellent R2 cal (0.96) and R2val (0.98) with low root mean square error of cross-validation (0.05), low root mean square error of Prediction (0.04), and (ratio of performance to deviation = 5.86). The built models were accurate and robust and can be reliably applied in developing a handheld quality detection device for screening, quality control checks, and prediction of shea butter quality on-site.

Determination of Magnesium Oxide Content in Mineral Medicine Talcum Using Near-Infrared Spectroscopy Integrated with Support Vector Machine

2017 ◽  
Vol 71 (11) ◽  
pp. 2427-2436 ◽  
Author(s):  
Mi Lei ◽  
Long Chen ◽  
Bisheng Huang ◽  
Keli Chen
Keyword(s):  
Root Mean Square Error ◽  
Least Squares ◽  
Partial Least Squares ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Support Vector ◽  
Mean Square ◽  
Characteristic Spectrum

In this research paper, a fast, quantitative, analytical model for magnesium oxide (MgO) content in medicinal mineral talcum was explored based on near-infrared (NIR) spectroscopy. MgO content in each sample was determined by ethylenediaminetetraacetic acid (EDTA) titration and taken as reference value of NIR spectroscopy, and then a variety of processing methods of spectra data were compared to establish a good NIR spectroscopy model. To start, 50 batches of talcum samples were categorized into training set and test set using the Kennard–Stone (K-S) algorithm. In a partial least squares regression (PLSR) model, both leave-one-out cross-validation (LOOCV) and training set validation (TSV) were used to screen spectrum preprocessing methods from multiplicative scatter correction (MSC), and finally the standard normal variate transformation (SNV) was chosen as the optimal pretreatment method. The modeling spectrum bands and ranks were optimized using PLSR method, and the characteristic spectrum ranges were determined as 11995–10664, 7991–6661, and 4326–3999 cm−1, with four optimal ranks. In the support vector machine (SVM) model, the radical basis function (RBF) kernel function was used. Moreover, the full spectrum data of samples pretreated with SNV, the characteristic spectrum data screened using synergy interval partial least squares (SiPLS), and the scoring data of the first four ranks obtained by a partial least squares (PLS) dimension reduction of characteristic spectrum were taken as input variables of SVM, and the MgO content reference values of various sample were taken as output values. In addition, the SVM model internal parameters were optimized using the grid optimization method (GRID), particle swarm optimization (PSO), and genetic algorithm (GA) so that the optimal C and g-values were determined and the validation model was established. By comprehensively comparing the validation effects of different models, it can be concluded that the scoring data of the first four ranks obtained by PLS dimension reduction of characteristic spectrum were taken as input variables of SVM, and the PLS-SVM regression model established using GRID was the optimal NIR spectroscopy quantitative model of talc. This PLS-SVM regression model (rank = 4) measured that the MgO content of talcum was in the range of 17.42–33.22%, with root mean square error of cross validation (RMSECV) of 2.2127%, root mean square error of calibration (RMSEC) of 0.6057%, and root mean square error of prediction (RMSEP) of 1.2901%. This model showed high accuracy and strong prediction capacity, which can be used for rapid prediction of MgO content in talcum.

Determination of Loganin in Qiju Dihuang Pills by Near-Infrared Spectroscopy Technique

2013 ◽  
Vol 807-809 ◽  
pp. 1978-1983 ◽  
Author(s):  
Cai Xia Xie ◽  
Hai Yan Gong ◽  
Jian Ying Liu ◽  
Jing Wei Lei ◽  
Xiao Yan Duan ◽  
...  
Keyword(s):  
Root Mean Square Error ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Diffuse Reflectance ◽  
Near Infrared ◽  
Diffuse Reflectance Spectroscopy ◽  
Partial Least Square ◽  
Calibration Model ◽  
Mean Square

To establish a rapid analytical method for Loganin in Qiju Dihuang Pills (condensed) by Near-infrared Diffuse Reflectance Technique. Collecting NIR spectra by NIR Diffuse Reflectance Spectroscopy, the partial least square calibration model was built. The correlation coefficients (R2) and the root-mean-square error of cross-validation (RMSECV) were 0.99764 and 0.09340, respectively. In the external validation,coefficients of determination (r2) between NIRS and HPLC values was 0.97348,the root-mean-square error of prediction (RMSEP) was 0.08491. The results showed that the method was rapid, accurate, and could be applied to the fast determination of Loganin in Qiju Dihuang Pills (condensed).

Sign in / Sign up

Export Citation Format

Share Document