Multivariate Classification of Sound and Insect-Infested Seeds of a Tropical Multipurpose Tree, Cordia Africana, with near Infrared Reflectance Spectroscopy

2002 ◽  
Vol 10 (1) ◽  
pp. 45-51 ◽  
Author(s):  
Mulualem Tigabu ◽  
Per Christer Odén
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Calibration Model ◽  
Least Squares Regression ◽  
Near Infrared Reflectance ◽  
Classification Rate ◽  
Multipurpose Tree ◽  
Cordia Africana

Near infrared (NIR) spectroscopy was used to classify insect-infested and sound seeds of a tropical multipurpose tree, Cordia africana Lam. A calibration model derived by partial least squares regression of orthogonal signal corrected spectra resulted in a 100% classification rate. Difference spectrum and partial least squares weight indicated that absorbance differences between insect-infested and sound seeds might have been due to differences in composition of chitin and cuticular lipid components as well as moisture content. The result shows the possibility of using NIR spectroscopy in the seed cleaning process in the future provided that appropriate sorting instruments are developed.

scholarly journals The application of NIR spectroscopy in moisture determining of vegetable seeds

2020 ◽  
Vol 38 (No. 2) ◽  
pp. 131-136
Author(s):  
Wojciech Poćwiardowski ◽  
Joanna Szulc ◽  
Grażyna Gozdecka
Keyword(s):  
Experimental Data ◽  
Least Squares ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Calibration Model ◽  
Least Squares Regression ◽  
Moisture Analysis ◽  
Non Destructive

The aim of the study was to elaborate a universal calibration for the near infrared (NIR) spectrophotometer to determine the moisture of various kinds of vegetable seeds. The research was conducted on the seeds of 5 types of vegetables – carrot, parsley, lettuce, radish and beetroot. For the spectra correlation with moisture values, the method of partial least squares regression (PLS) was used. The resulting qualitative indicators of a calibration model (R = 0.9968, Q = 0.8904) confirmed an excellent fit of the obtained calibration to the experimental data. As a result of the study, the possibilities of creating a calibration model for NIR spectrophotometer for non-destructive moisture analysis of various kinds of vegetable seeds was confirmed.<br /><br />

scholarly journals Analysis of amino acid composition of sheep colostrum by near-infrared spectroscopy

2011 ◽  
Vol 49 (No. 5) ◽  
pp. 177-182 ◽  
Author(s):  
S. Kráčmar ◽  
R. Jankovská ◽  
K. Šustová ◽  
J. Kuchtík ◽  
L. Zeman
Keyword(s):  
Infrared Spectroscopy ◽  
Amino Acid ◽  
Least Squares ◽  
Partial Least Squares ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Correlation Coefficients ◽  
Nir Spectroscopy ◽  
Least Squares Regression ◽  
Near Infrared Reflectance

This paper deals with changes in the basic composition of sheep colostrum within the first 72 hours after parturition on the one hand and with the possibility of determining the major components of sheep colostrum by near-infrared spectroscopy on the other. Levels of essential, nonessential and total amino acids in sheep colostrum were determined by near-infrared reflectance spectroscopy (NIRS). ). For each component, sets of 90 samples were used to calibrate the instrument by means of a modified partial least-squares regression. The values of correlation coefficients (r) were as follows: 0.979 for Thr; 0.954 for Val; 0.968 for Leu; 0.918 for Ile; 0.946 for Lys; 0.908 for Arg; 0.845 for His; 0.999 for Trp; 0.915 for Phe; 0.909 for Met; 0.939 for Cys; 0.911 for &Sigma;met + Cys; 0.933 for Tyr; 0.945 for Asp; 0.935 for Glu; 0.986 for Ser; 0.985 for Pro; 0.957 for Gly; 0.949 for Ala; 0.940 for &Sigma;EAA; 0.958 for &Sigma;NEAA and 0.977 for &Sigma;AA. Partial least-squares (PLS) regression was used to develop calibration models for examined samples of sheep colostrum. When using the NIRS method, the following correlation coefficients were calculated: Thr (0.959), Val (0.912), Leu (0.936), Ile (0.855), Lys (0.903), Arg (0.853), His (0.717), Trp (0.667), Phe (0.854), Met (0.867), Cys (0.895), &Sigma;met + Cys (0.868), Tyr (0.886), Asp (0.910), Glu (0.882), Ser (0.968), Pro (0.968), Gly (0.923), Ala (0.916), &Sigma;EAA (0.901), &Sigma;NEAA (0.923) and &Sigma;AA (0.943). Calibration was tested using the same set of samples.NIRS results were compared with reference data and no significant differences between them were found (P = 0.05). Calibration and validation models were constructed in the same way.Results of this study indicate that NIR spectroscopy can be used for a rapid analysis of amino acid contents in sheep colostrum. &nbsp;

NIR Spectroscopy and Partial Least Squares Regression for the Determination of Phosphate Content and Viscosity Behaviour of Potato Starch

2001 ◽  
Vol 9 (2) ◽  
pp. 133-139 ◽  
Author(s):  
L.G. Thygesen ◽  
S.B. Engelsen ◽  
M.H. Madsen ◽  
O.B. Sørensen
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Potato Starch ◽  
Nir Spectroscopy ◽  
Peak Time ◽  
Phosphate Content ◽  
Least Squares Regression ◽  
Data Prediction

A set of 97 potato starch samples with a phosphate content corresponding to a phosphorus content between 0.029 and 0.11 g per 100 g dry matter was analysed using a Rapid Visco Analyzer (RVA) and near infrared (NIR) spectroscopy, (700–2498 nm). NIR-based prediction of phosphate content was possible with a root mean square error of cross-validation ( RMSECV) of 0.006% using PLSR (partial least squares regression). However, the NIR/PLSR model relied on weak spectral signals, and was highly sensitive to sample preparation. The best prediction of phosphate content from the RVA viscograms was a linear regression model based on the RVA variable Breakdown, which gave a RMSECV of 0.008%. NIR/PLSR prediction of the RVA variables Peak viscosity and Breakdown was successful, probably because they were highly related to phosphate content in the present data. Prediction of the other RVA variables from NIR/PLSR was mediocre (Through, Final Viscosity) or not possible (Setback, Peak time, Pasting temperature).

scholarly journals Prediction of the Leaf Primordia of Potato Tubers Using Sensor Fusion and Wavelength Selection

2019 ◽  
Vol 5 (1) ◽  
pp. 10 ◽  
Author(s):  
Ahmed Rady ◽  
Daniel Guyer ◽  
William Kirk ◽  
Irwin R Donis-González
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Prediction Models ◽  
Calibration Model ◽  
Data Sets ◽  
Least Squares Regression ◽  
Potato Tubers ◽  
Russet Norkotah ◽  
Systems Models

The sprouting of potato tubers during storage is a significant problem that suppresses obtaining high quality seeds or fried products. In this study, the potential of fusing data obtained from visible (VIS)/near-infrared (NIR) spectroscopic and hyperspectral imaging systems was investigated, to improve the prediction of primordial leaf count as a significant sign for tubers sprouting. Electronic and lab measurements were conducted on whole tubers of Frito Lay 1879 (FL1879) and Russet Norkotah (R.Norkotah) potato cultivars. The interval partial least squares (IPLS) technique was adopted to extract the most effective wavelengths for both systems. Linear regression was utilized using partial least squares regression (PLSR), and the best calibration model was chosen using four-fold cross-validation. Then the prediction models were obtained using separate test data sets. Prediction results were enhanced compared with those obtained from individual systems’ models. The values of the correlation coefficient (the ratio between performance to deviation, or r(RPD)) were 0.95(3.01) and 0.9s6(3.55) for FL1879 and R.Norkotah, respectively, which represented a feasible improvement by 6.7%(35.6%) and 24.7%(136.7%) for FL1879 and R.Norkotah, respectively. The proposed study shows the possibility of building a rapid, noninvasive, and accurate system or device that requires minimal or no sample preparation to track the sprouting activity of stored potato tubers.

Investigation of Noninvasive in vivo Blood Hematocrit Measurement Using NIR Reflectance Spectroscopy and Partial Least-Squares Regression

2000 ◽  
Vol 54 (2) ◽  
pp. 294-299 ◽  
Author(s):  
Songbiao Zhang ◽  
Babs R. Soller ◽  
Shubjeet Kaur ◽  
Kristen Perras ◽  
Thomas J. Vander Salm
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Near Infrared ◽  
Multivariate Calibration ◽  
Nir Spectroscopy ◽  
Study Groups ◽  
Patient Specific ◽  
Least Squares Regression ◽  
Fiber Optic Probe

Hematocrit (Hct), the volume percent of red cells in blood, is monitored routinely for blood donors, surgical patients, and trauma victims and requires blood to be removed from the patient. An accurate, noninvasive method for directly measuring hematocrit on patients is desired for these applications. The feasibility of noninvasive hematocrit measurement by using near-infrared (NIR) spectroscopy and partial least-squares (PLS) techniques was investigated, and methods of in vivo calibration were examined. Twenty Caucasian patients undergoing cardiac surgery on cardiopulmonary bypass were randomly selected to form two study groups. A fiber-optic probe was attached to the patient's forearm, and NIR spectra were continuously collected during surgery. Blood samples were simultaneously collected and reference Hct measurements were made with the spun capillary method. PLS multivariate calibration techniques were applied to investigate the relationship between spectral and Hct changes. Single patient calibration models were developed with good cross-validated estimation of accuracy (∼ 1 Hct%) and trending capability for most patients. Time-dependent system drift, patient temperature, and venous oxygen saturation were not correlated with the hematocrit measurements. Multi-subject models were developed for prediction of independent subjects. These models demonstrated a significant patient-specific offset that was shown to be partially related to spectrometer drift. The remaining offset is attributed to the large spectral variability of patient tissue, and a significantly larger set of patients would be required to adequately model this variability. After the removal of the offset, the cross-validated estimation of accuracy is 2 Hct%.

Variable Screening for Near Infrared (NIR) Spectroscopy Data Based on Ridge Partial Least Squares Regression

2020 ◽  
Vol 23 (8) ◽  
pp. 740-756
Author(s):  
Naifei Zhao ◽  
Qingsong Xu ◽  
Man-lai Tang ◽  
Hong Wang
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Screening Methods ◽  
Spectroscopy Data ◽  
Least Squares Regression ◽  
Variable Screening ◽  
Highly Correlated

Aim and Objective: Near Infrared (NIR) spectroscopy data are featured by few dozen to many thousands of samples and highly correlated variables. Quantitative analysis of such data usually requires a combination of analytical methods with variable selection or screening methods. Commonly-used variable screening methods fail to recover the true model when (i) some of the variables are highly correlated, and (ii) the sample size is less than the number of relevant variables. In these cases, Partial Least Squares (PLS) regression based approaches can be useful alternatives. Materials and Methods : In this research, a fast variable screening strategy, namely the preconditioned screening for ridge partial least squares regression (PSRPLS), is proposed for modelling NIR spectroscopy data with high-dimensional and highly correlated covariates. Under rather mild assumptions, we prove that using Puffer transformation, the proposed approach successfully transforms the problem of variable screening with highly correlated predictor variables to that of weakly correlated covariates with less extra computational effort. Results: We show that our proposed method leads to theoretically consistent model selection results. Four simulation studies and two real examples are then analyzed to illustrate the effectiveness of the proposed approach. Conclusion: By introducing Puffer transformation, high correlation problem can be mitigated using the PSRPLS procedure we construct. By employing RPLS regression to our approach, it can be made more simple and computational efficient to cope with the situation where model size is larger than the sample size while maintaining a high precision prediction.

Determination of carbon fraction and nitrogen concentration in tree foliage by near infrared reflectances: a comparison of statistical methods

1996 ◽  
Vol 26 (4) ◽  
pp. 590-600 ◽  
Author(s):  
Katherine L. Bolster ◽  
Mary E. Martin ◽  
John D. Aber
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Data Sets ◽  
Independent Data ◽  
Least Squares Regression ◽  
Near Infrared Reflectance ◽  
Regression Methods

Further evaluation of near infrared reflectance spectroscopy as a method for the determination of nitrogen, lignin, and cellulose concentrations in dry, ground, temperate forest woody foliage is presented. A comparison is made between two regression methods, stepwise multiple linear regression and partial least squares regression. The partial least squares method showed consistently lower standard error of calibration and higher R2 values with first and second difference equations. The first difference partial least squares regression equation resulted in standard errors of calibration of 0.106%, with an R2 of 0.97 for nitrogen, 1.613% with an R2 of 0.88 for lignin, and 2.103% with an R2 of 0.89 for cellulose. The four most highly correlated wavelengths in the near infrared region, and the chemical bonds represented, are shown for each constituent and both regression methods. Generalizability of both methods for prediction of protein, lignin, and cellulose concentrations on independent data sets is discussed. Prediction accuracy for independent data sets and species from other sites was increased using partial least squares regression, but was poor for sample sets containing tissue types or laboratory-measured concentration ranges beyond those of the calibration set.

scholarly journals Sensitive Wavelengths Selection in Identification of Ophiopogon japonicus Based on Near-Infrared Hyperspectral Imaging Technology

2017 ◽  
Vol 2017 ◽  
pp. 1-11 ◽  
Author(s):  
Zhengyan Xia ◽  
Chu Zhang ◽  
Haiyong Weng ◽  
Pengcheng Nie ◽  
Yong He
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Hyperspectral Imaging ◽  
Near Infrared ◽  
Support Vector ◽  
Calibration Model ◽  
Least Squares Regression ◽  
Selection Methods ◽  
Wavelength Selection ◽  
Ophiopogon Japonicus

Hyperspectral imaging (HSI) technology has increasingly been applied as an analytical tool in fields of agricultural, food, and Traditional Chinese Medicine over the past few years. The HSI spectrum of a sample is typically achieved by a spectroradiometer at hundreds of wavelengths. In recent years, considerable effort has been made towards identifying wavelengths (variables) that contribute useful information. Wavelengths selection is a critical step in data analysis for Raman, NIRS, or HSI spectroscopy. In this study, the performances of 10 different wavelength selection methods for the discrimination of Ophiopogon japonicus of different origin were compared. The wavelength selection algorithms tested include successive projections algorithm (SPA), loading weights (LW), regression coefficients (RC), uninformative variable elimination (UVE), UVE-SPA, competitive adaptive reweighted sampling (CARS), interval partial least squares regression (iPLS), backward iPLS (BiPLS), forward iPLS (FiPLS), and genetic algorithms (GA-PLS). One linear technique (partial least squares-discriminant analysis) was established for the evaluation of identification. And a nonlinear calibration model, support vector machine (SVM), was also provided for comparison. The results indicate that wavelengths selection methods are tools to identify more concise and effective spectral data and play important roles in the multivariate analysis, which can be used for subsequent modeling analysis.

Developing near infrared spectroscopy models for predicting chemistry and responses to stress in Pinus radiata (D. Don)

2021 ◽  
pp. 096703352110065
Author(s):  
Judith S Nantongo ◽  
BM Potts ◽  
T Rodemann ◽  
H Fitzgerald ◽  
NW Davies ◽  
...  
Keyword(s):  
Least Squares ◽  
Partial Least Squares ◽  
Pinus Radiata ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Coefficient Of Determination ◽  
Individual Plant ◽  
Least Squares Regression ◽  
Plant Parts ◽  
Quantitative Genetic

Incorporating chemical traits in breeding requires the estimation of quantitative genetic parameters, especially the levels of additive genetic variation. This requires large numbers of samples from pedigreed populations. Conventional wet chemistry procedures for chemotyping are slow, expensive and not a practical option. This study focuses on the chemical variation in Pinus radiata, where the near infrared (NIR) spectral properties of the needles, bark and roots before and after exposure to methyl jasmonate (MJ) and artificial bark stripping (strip) treatments were investigated as an alternative approach. The aim was to test the capability of NIR spectroscopy to (i) discriminate samples exposed to MJ and strip assessed 7, 14, 21 and 28 days after treatment from untreated samples, and (ii) quantitatively predict individual chemical compounds in the three plant parts. Using principal components analysis (PCA) on the spectral data, we differentiated between treated and untreated samples for the individual plant parts. Based on partial least squares–discriminant analysis (PLS-DA) models, the best discrimination of treated from non-treated samples with the smallest root mean square error cross-validation (RMSECV) and highest coefficient of determination (r2) was achieved in the fresh needles (r2 = 0.81, RMSECV= 0.24) and fresh inner bark (r2 = 0.79, RMSECV = 0.25) for MJ-treated samples 14 days and 21 days after treatment, respectively. Using partial least squares regression, models for individual compounds gave high (r2), residual predictive deviation (RPD), lab to NIR error (PRL) or range error ratio (RER) for fructose (r2 = 0.84, RPD = 1.5, PRL = 0.71, RER = 7.25) and glucose (r2 = 0.83, RPD = 1.9, PRL = 1.14, RER = 8.50) and several diterpenoids. This provides an optimistic outlook for the use of NIR spectroscopy-based models for the larger-scale prediction of the P. radiata chemistry needed for quantitative genetic studies.

Application of Partial Least-Squares Regression to Near-Infrared Reflectance Spectroscopic Determination of Shive Content in Flax

2003 ◽  
Vol 57 (5) ◽  
pp. 551-556 ◽  
Author(s):  
Miryeong Sohn ◽  
Franklin E. Barton ◽  
Wiley H. Morrison ◽  
Douglas D. Archibald
Keyword(s):  
Least Squares ◽  
Spectral Data ◽  
Partial Least Squares ◽  
Standard Error ◽  
Near Infrared ◽  
Single Sample ◽  
Calibration Model ◽  
Infrared Reflectance ◽  
Near Infrared Reflectance ◽  
Sample Set

Shive, the nonfiberous core portion of the stem, in flax fiber after retting is related to fiber quality. The objective of this study is to develop a standard calibration model for determining shive content in retted flax by using near-infrared reflectance spectroscopy. Calibration samples were prepared by manually mixing pure, ground shive and pure, ground fiber from flax retted by three different methods (water, dew, and enzyme retting) to provide a wide range of shive content from 0 to 100%. Partial least-squares (PLS) regression was used to generate a calibration model, and spectral data were processed using various pretreatments such as a multiplicative scatter correction (MSC), normalization, derivatives, and Martens' Uncertainty option to improve the calibration model. The calibration model developed with a single sample set resulted in a standard error of 1.8% with one factor. The best algorithm was produced from first-derivative processing of the spectral data. MSC was not effective processing for this model. However, a big bias was observed when independent sample sets were applied to this calibration model to predict shive content in flax fiber. The calibration model developed using a combination sample set showed a slightly higher standard error and number of factors compared to the model for a single sample set, but this model was sufficiently accurate to apply to each sample set. The best algorithm for the combination sample set was generated from second derivatives followed by MSC processing of spectral data and from Martens' Uncertainty option; it resulted in a standard error of 2.3% with 2 factors. The value of the digital second derivative centered at 1674 nm for these spectral data was highly correlated to shive content of flax and could form the basis for a simple, low-cost sensor for the shive or fiber content in retted flax.

Sign in / Sign up

Export Citation Format

Share Document