Multivariate Calibration and Chemometrics for near Infrared Spectroscopy: Which Method?

2000 ◽  
Vol 8 (4) ◽  
pp. 229-237 ◽  
Author(s):  
Pierre Dardenne ◽  
George Sinnaeve ◽  
Vincent Baeten
Keyword(s):  
Near Infrared ◽  
Multivariate Calibration ◽  
Scatter Correction ◽  
Large Data ◽  
Data Sets ◽  
Agricultural Commodity ◽  
Regression Methods ◽  
Standard Normal Variate ◽  
Pre Treatment ◽  
Artificial Neural Network Ann

The four most important regression methods are evaluated on very large data sets: Multiple Linear Regression (MLR), Partial Least Squares (PLS), Artificial Neural Network (ANN) and a new concept called “LOCAL” (PLS with selection of a calibration sample subset of the closest neighbours for each sample to predict). The Standard Errors of Prediction ( SEPs) are statistically tested and the results show that the regression methods are almost equal and that the data matrices are more important than the fitting methods themselves. The types of pre-treatments (Multiplicative Scatter Correction, Detrend, Standard Normal Variate, derivative etc.) of the spectra are too numerous to be able to test all the combinations. For each test, the pre-treatment found as the best with the PLS method is fixed for the other ones. The second part of the paper emphasises the importance of the number of samples. If any agricultural commodity, and probably any kind of product measured by an NIR instrument, can be considered as a mixture of several constituents, the databases built by collecting actual samples bringing new information can reach hundreds, if not thousands, of samples.

The Effect of Multiplicative Scatter Correction (MSC) and Linearity Improvement in NIR Spectroscopy

1988 ◽  
Vol 42 (7) ◽  
pp. 1273-1284 ◽  
Author(s):  
Tomas Isaksson ◽  
Tormod Næs
Keyword(s):  
Near Infrared ◽  
Scatter Correction ◽  
Principal Component Regression ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Data Sets ◽  
Prediction Errors ◽  
Regression Methods ◽  
Multiplicative Scatter Correction ◽  
Linearity Improvement

Near-infrared (NIR) reflectance spectra of five different food products were measured. The spectra were transformed by multiplicative scatter correction (MSC). Principal component regression (PCR) was performed, on both scatter-corrected and uncorrected spectra. Calibration and prediction were performed for four food constituents: protein, fat, water, and carbohydrates. All regressions gave lower prediction errors (7–68% improvement) by the use of MSC spectra than by the use of uncorrected absorbance spectra. One of these data sets was studied in more detail to clarify the effects of the MSC, by using PCR score, residual, and leverage plots. The improvement by using nonlinear regression methods is indicated.

Optimised Scaling (OS-2) Regression Applied to near Infrared Diffuse Spectroscopy Data from Food Products

1993 ◽  
Vol 1 (2) ◽  
pp. 85-97 ◽  
Author(s):  
Tomas Isaksson ◽  
Ziyi Wang ◽  
Bruce Kowalski
Keyword(s):  
Near Infrared ◽  
Scatter Correction ◽  
Principal Component Regression ◽  
Predictive Ability ◽  
Principal Component ◽  
Calibration Method ◽  
Meat Sample ◽  
Data Sets ◽  
Regression Methods ◽  
Calibration Models

A recently presented calibration method, called optimised scaling (OS-2) was tested and compared to multiplicative scatter correction (MSC) and principal component regression (PCR). The predictive ability of these regression methods was tested on eight data sets consisting of diffuse near infrared (NIR) reflectance and transmittance continuous spectra of meat, sausages, soya bean and designed sample sets. Calibration was performed for constituents such as fat, protein, water, carbohydrate, temperature, lactate and glucose. A total of 21 calibration models were validated and compared. OS-2 gave good or promising prediction results for the major constituents with large variation, such as prediction of fat in two of the studied meat sample sets. OS-2 gave poorer prediction results of minor constituents compared to MSC or first derivatives of the data and PCR.

scholarly journals Applicability of Fuzzy Logic and Artificial Neural Network for Unpaved Airfield Surface Bearing Strength Prediction

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3373
Author(s):  
Ludek Cicmanec
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuzzy Logic ◽  
Regression Function ◽  
Large Data ◽  
Soil Strength ◽  
Data Sets ◽  
Bearing Strength ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

The main objective of this paper is to describe a building process of a model predicting the soil strength at unpaved airport surfaces (unpaved runways, safety areas in runway proximity, runway strips, and runway end safety areas). The reason for building this model is to partially substitute frequent and meticulous inspections of an airport movement area comprising the bearing strength evaluation and provide an efficient tool to organize surface maintenance. Since the process of building such a model is complex for a physical model, it is anticipated that it might be addressed by a statistical model instead. Therefore, fuzzy logic (FL) and artificial neural network (ANN) capabilities are investigated and compared with linear regression function (LRF). Large data sets comprising the bearing strength and meteorological characteristics are applied to train the likely model variations to be subsequently compared with the application of standard statistical quantitative parameters. All the models prove that the inclusion of antecedent soil strength as an additional model input has an immense impact on the increase in model accuracy. Although the M7 model out of the ANN group displays the best performance, the M3 model is considered for practical implications being less complicated and having fewer inputs. In general, both the ANN and FL models outperform the LRF models well in all the categories. The FL models perform almost equally as well as the ANN but with slightly decreased accuracy.

On the Scales Associated with Near-Infrared Reflectance Difference Spectra

1995 ◽  
Vol 49 (6) ◽  
pp. 765-772 ◽  
Author(s):  
M. S. Dhanoa ◽  
S. J. Lister ◽  
R. J. Barnes
Keyword(s):  
Near Infrared ◽  
Scatter Correction ◽  
The Other ◽  
Difference Spectra ◽  
Near Infrared Reflectance ◽  
Standard Normal Variate ◽  
Near Infrared Spectra ◽  
Standard Normal ◽  
Relationship Of ◽  
The Relationship

Scale differences of individual near-infrared spectra are identified when set-independent standard normal variate (SNV) and de-trend (DT) transformations are applied in either SNV followed by DT or DT then SNV order. The relationship of set-dependent multiplicative scatter correction (MSC) to SNV is also referred to. A simple correction factor is proposed to convert derived spectra from one order to the other. It is suggested that the suitable order for the study of changes using difference spectra (when removing baselines) should be DT followed by SNV, which leads to all derived spectra on the scale of mean zero and variance equal to one. If baselines are identical, then SNV scale spectra can be used to calculate differences.

Comparison of Multivariate Calibration Techniques Applied to Experimental NIR Data Sets

2000 ◽  
Vol 54 (4) ◽  
pp. 608-623 ◽  
Author(s):  
Vítézslav Centner ◽  
Jorge Verdú-Andrés ◽  
Beata Walczak ◽  
Delphine Jouan-Rimbaud ◽  
Frédéric Despagne ◽  
...  
Keyword(s):  
Near Infrared ◽  
Multivariate Calibration ◽  
Calibration Method ◽  
Heterogeneous Data ◽  
Data Sets ◽  
Calibration Data ◽  
Calibration Problem ◽  
Calibration Techniques ◽  
Selection Of ◽  
Infrared Data

The present study compares the performance of different multivariate calibration techniques applied to four near-infrared data sets when test samples are well within the calibration domain. Three types of problems are discussed: the nonlinear calibration, the calibration using heterogeneous data sets, and the calibration in the presence of irrelevant information in the set of predictors. Recommendations are derived from the comparison, which should help to guide a nonchemometrician through the selection of an appropriate calibration method for a particular type of calibration data. A flexible methodology is proposed to allow selection of an appropriate calibration technique for a given calibration problem.

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 Model Prediksi Kadar Air Buah Cabai Rawit Domba (Capsicum frutescens L.) Menggunakan Spektroskopi Ultraviolet Visible Near Infrared

2021 ◽  
Vol 4 (1) ◽  
pp. 15-22
Author(s):  
Kusumiyati Kusumiyati ◽  
Ine Elisa Putri ◽  
Agus Arip Munawar
Keyword(s):  
Partial Least Squares Regression ◽  
Near Infrared ◽  
Scatter Correction ◽  
Capsicum Frutescens ◽  
Least Squares Regression ◽  
Orthogonal Signal ◽  
Standard Normal Variate ◽  
Orthogonal Signal Correction ◽  
Signal Correction ◽  
Standard Normal

Penelitian ini bertujuan untuk menduga kadar air buah cabai rawit domba (Capsicum frutescens L.) menggunakan spektroskopi UV-Vis-NIR. Total sampel yang digunakan yaitu 45 buah. Analisis dilakukan di Laboratorium Hortikultura, Fakultas Pertanian, Universitas Padjadjaran. Akuisisi data spektra dengan rentang panjang gelombang 300 – 1050 nm (Nirvana AG410). Spektra diperbaiki dengan metode multiplicative scatter correction (MSC), standard normal variate transformation (SNV), orthogonal signal correction (OSC), first derivative (dg1) dan second derivative (dg2). Analisis data dilakukan dengan menggunakan partial least squares regression (PLSR). Berdasarkan penelitian ini menunjukkan bahwa metode koreksi OSC menghasilkan model kalibrasi tertinggi dengan Rkal, RMSEC, Rval, RMSECV, RPD dan faktornya masing-masing yaitu 0.99, 0.31, 0.98, 0.68, 6.62 dan 4. Hal ini menunjukkan bahwa spektroskopi UV-Vis-NIR dapat digunakan untuk memprediksi kadar air pada buah cabai rawit domba.

scholarly journals NIR model development and robustness in prediction of melon fruit total soluble solids

2006 ◽  
Vol 57 (4) ◽  
pp. 411 ◽  
Author(s):  
J. A. Guthrie ◽  
C. J. Liebenberg ◽  
K. B. Walsh
Keyword(s):  
Near Infrared ◽  
Multivariate Calibration ◽  
Mean Squared Error ◽  
Scatter Correction ◽  
Model Development ◽  
Equatorial Region ◽  
Soluble Solids ◽  
Eating Quality ◽  
Spectral Window ◽  
Total Soluble Solids

Near infrared spectroscopy (NIRS) can be used for the on-line, non-invasive assessment of fruit for eating quality attributes such as total soluble solids (TSS). The robustness of multivariate calibration models, based on NIRS in a partial transmittance optical geometry, for the assessment of TSS of intact rockmelons (Cucumis melo) was assessed. The mesocarp TSS was highest around the fruit equator and increased towards the seed cavity. Inner mesocarp TSS levels decreased towards both the proximal and distal ends of the fruit, but more so towards the proximal end. The equatorial region of the fruit was chosen as representative of the fruit for near infrared assessment of TSS. The spectral window for model development was optimised at 695–1045 nm, and the data pre-treatment procedure was optimised to second-derivative absorbance without scatter correction. The ‘global’ modified partial least squares (MPLS) regression modelling procedure of WINISI (ver. 1.04) was found to be superior with respect to root mean squared error of prediction (RMSEP) and bias for model predictions of TSS across seasons, compared with the ‘local’ MPLS regression procedure. Updating of the model with samples selected randomly from the independent validation population demonstrated improvement in both RMSEP and bias with addition of approximately 15 samples.

Application of neural networks for classifying softwood species using near infrared spectroscopy

2020 ◽  
Vol 28 (5-6) ◽  
pp. 298-307
Author(s):  
Sang-Yun Yang ◽  
Ohkyung Kwon ◽  
Yonggun Park ◽  
Hyunwoo Chung ◽  
Hyunbin Kim ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Training Procedure ◽  
Softwood Lumber ◽  
Standard Normal Variate ◽  
Artificial Neural Network Ann ◽  
The Stability ◽  
Second Derivative Spectra

Lumber species identification is an important issue for the wood industry. In this study, three types of neural networks (artificial neural network (ANN), deep neural network (DNN), and convolutional neural network (CNN)) were employed for classifying softwood lumber species using NIR spectroscopy. The results show that CNN, which is based on deep learning, was more stable than the other neural networks. In particular, the stability of the training process was remarkably improved in CNN models. During the training procedure, the validation accuracy of the CNN model was 99.3% for the raw spectra, 99.9% for the standard normal variate (SNV) spectra and 100.0% for the Savitzky-Golay second derivative spectra. Interestingly, there was little difference in the validation accuracies among the CNN models depending on mathematical preprocessing. The results showed that CNN is sufficiently adequate to classify the softwood lumber species.

Sign in / Sign up

Export Citation Format

Share Document