Robust Wavelength Selection Using Filter-Wrapper Method and Input Scaling on Near Infrared Spectral Data

The extraction of relevant wavelengths from a large dataset of Near Infrared Spectroscopy (NIRS) is a significant challenge in vibrational spectroscopy research. Nonetheless, this process allows the improvement in the chemical interpretability by emphasizing the chemical entities related to the chemical parameters of samples. With the complexity in the dataset, it may be possible that irrelevant wavelengths are still included in the multivariate calibration. This yields the computational process to become unnecessary complex and decreases the accuracy and robustness of the model. In multivariate analysis, Partial Least Square Regression (PLSR) is a method commonly used to build a predictive model from NIR spectral data. However, in the PLSR method and common commercial chemometrics software, there is no standard wavelength selection procedure applied to screen the irrelevant wavelengths. In this study, a new robust wavelength selection procedure called the modified VIP-MCUVE (mod-VIP-MCUVE) using Filter-Wrapper method and input scaling strategy is introduced. The proposed method combines the modified Variable Importance in Projection (VIP) and modified Monte Carlo Uninformative Variable Elimination (MCUVE) to calculate the scale matrix of the input variable. The modified VIP uses the orthogonal components of Partial Least Square (PLS) in investigating the informative variable in the model by applying the amount of variation both in X and y{SSX,SSY}, simultaneously. The modified MCUVE uses a robust reliability coefficient and a robust tolerance interval in the selection procedure. To evaluate the superiority of the proposed method, the classical VIP, MCUVE, and autoscaling procedure in classical PLSR were also included in the evaluation. Using artificial data with Monte Carlo simulation and NIR spectral data of oil palm (Elaeis guineensis Jacq.) fruit mesocarp, the study shows that the proposed method offers advantages to improve model interpretability, to be computationally extensive, and to produce better model accuracy.

Download Full-text

Nondestructive Detection of Moisture Content in Walnut Kernel by Near-Infrared Diffuse Reflectance Spectroscopy

Journal of Spectroscopy ◽

10.1155/2021/9986940 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Dan Peng ◽

Yali Liu ◽

Jiasheng Yang ◽

Yanlan Bi ◽

Jingnan Chen

Keyword(s):

Moisture Content ◽

Spectral Data ◽

Diffuse Reflectance ◽

Near Infrared ◽

Diffuse Reflectance Spectroscopy ◽

Reflectance Spectroscopy ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Support Vector

The rapid and accurate detection of the moisture content is of great significance to the quality evaluation and oil extraction process of walnut kernel. Near-infrared (NIR) spectroscopy is an ideal method for measuring the moisture content in walnut kernel. In this study, a regression model for moisture content in walnut kernel was developed based on NIR diffuse reflectance spectroscopy using chemometric methods. The different spectral pretreatment methods were adopted to preprocess the original spectral data. The whole spectra band was divided into 5 subbands, 10 subbands, 15 subbands, and 20 subbands to screen specific wavelengths relevant to the walnut kernel moisture content. PLS (partial least square regression), MLR (multivariate linear regression), PCR (principle component regression), and SVR (support vector regression) were used to establish the relationship model between the spectral data and measurement values of the moisture content. In comparison, the optimized modeling conditions were determined as follows: detection wavelength 1349–1490 nm, SNV-FD (standard normal variate transformation and first derivative) preprocessing method, and PLS algorithm. Under these conditions, the square correlation coefficient (R2) and root mean square error of prediction (RMSEP) of the prediction model were 0.9865 and 0.0017, respectively. The results of this study provided a feasible method for the rapid detection of moisture content in walnut kernel. To improve the performance and applicability of the model, it is necessary to continuously expand the size of the sample set.

Download Full-text

Histamine Control in Raw and Processed Tuna: A Rapid Tool Based on NIR Spectroscopy

Foods ◽

10.3390/foods10040885 ◽

2021 ◽

Vol 10 (4) ◽

pp. 885

Author(s):

Sergio Ghidini ◽

Luca Maria Chiesa ◽

Sara Panseri ◽

Maria Olga Varrà ◽

Adriana Ianieri ◽

...

Keyword(s):

Root Mean Square ◽

Near Infrared ◽

Nir Spectroscopy ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Coefficient Of Determination ◽

Mean Square ◽

Tuna Fish ◽

Mean Square Errors

The present study was designed to investigate whether near infrared (NIR) spectroscopy with minimal sample processing could be a suitable technique to rapidly measure histamine levels in raw and processed tuna fish. Calibration models based on orthogonal partial least square regression (OPLSR) were built to predict histamine in the range 10–1000 mg kg−1 using the 1000–2500 nm NIR spectra of artificially-contaminated fish. The two models were then validated using a new set of naturally contaminated samples in which histamine content was determined by conventional high-performance liquid chromatography (HPLC) analysis. As for calibration results, coefficient of determination (r2) > 0.98, root mean square of estimation (RMSEE) ≤ 5 mg kg−1 and root mean square of cross-validation (RMSECV) ≤ 6 mg kg−1 were achieved. Both models were optimal also in the validation stage, showing r2 values > 0.97, root mean square errors of prediction (RMSEP) ≤ 10 mg kg−1 and relative range error (RER) ≥ 25, with better results showed by the model for processed fish. The promising results achieved suggest NIR spectroscopy as an implemental analytical solution in fish industries and markets to effectively determine histamine amounts.

Download Full-text

Measurement of the Irganox Content in Polypropylene Polymers during Extrusion

Journal of Near Infrared Spectroscopy ◽

10.1255/jnirs.467 ◽

2005 ◽

Vol 13 (3) ◽

pp. 147-154 ◽

Cited By ~ 6

Author(s):

Wolfgang Becker ◽

Norbert Eisenreich

Keyword(s):

Near Infrared ◽

Prediction Models ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Process Conditions ◽

Transmission Spectra ◽

Mean Square ◽

Score Plot ◽

Least Square Regression

Near infrared spectroscopy was used as an in-line control system for the measurement of polypropylene filled with different amounts of Irganox additives. For this purpose transmission probes were installed in an extruder. The probes can withstand temperatures up to 300°C and pressures up to 60 MPa. Transmission spectra of polypropylene mixed with an Irganox additive were recorded. PCA score plot was carried out revealing the influence of varying conditions for the mixing of the sample preparation. Prediction models were generated with partial least square regression which resulted in a model which estimated Irganox with a coefficient of detremination of 0.984 and a root mean square error of prediction of 0.098%. Furthermore the possibilities for controlling process conditions by measuring transmission at a specific wavelength were shown.

Download Full-text

Near-Infrared Spectroscopy for Discrimination of Charcoal from Eucalyptus and Native Cerrado Species—Contribution to a Database for Forestry Supervision

Forest Science ◽

10.1093/forsci/fxab015 ◽

2021 ◽

Author(s):

Silvana Nisgoski ◽

Thaís A P Gonçalves ◽

Júlia Sonsin-Oliveira ◽

Adriano W Ballarin ◽

Graciela I B Muñiz

Keyword(s):

Infrared Spectroscopy ◽

Discriminant Analysis ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

New Technologies ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Eucalyptus Species ◽

Linear Discriminant

Abstract The illegal charcoal trade is an internationally well-known forest crime. In Brazil, government agents try to control it using the document of forest origin (DOF). To confirm a load’s legality, the agents must compare it with the declared content of the DOF. However, to identify charcoal is difficult even for specialists in wood anatomy. Hence, new technologies would facilitate the agents’ work. Near-infrared spectroscopy (NIR) provides a rapid and precise response to differentiate carbonized species. Considering the rich Brazilian flora, NIR studies are still underdeveloped. Our work aimed to differentiate charcoals of seven eucalypts and 10 Cerrado species based on NIR analysis and to add information to a charcoal database. Data were collected with a spectrophotometer in reflectance mode. Partial least square regression with discriminant analysis (PLS-DA) and a linear discriminant analysis (LDA) was applied to confirm the performance and potential of NIR spectra to distinguish native Cerrado species from eucalyptus species. Wavenumbers from 4,000 to 6,000 cm−1 and transversal surface presented the best results. NIR had the potential to distinguish eucalypt charcoals from Cerrado species and in comparison to reference samples. NIR is a potential tool for forestry supervision to guarantee the sustainability of the charcoal supply in Brazil and countries with similar conditions. Study Implications It is a challenge to protect the Cerrado biome against deforestation for charcoal production. The application of new technologies such as near-infrared spectroscopy (NIR) for charcoal identification might improve the work of government agents. In this article, we studied the spectra of Cerrado and eucalypt species. Our results present good separation between the analyzed groups. The main goal is to develop a reliable NIR database that would be useful in the practical work of agents. The database will be available for all control agencies, and future training will be done for a rapid initial evaluation in the field.

Download Full-text

Determination of Fat, Protein, and Total Solids in Cheese by Near-Infrared Reflectance Spectroscopy

Journal of AOAC International ◽

10.1093/jaoac/78.3.802 ◽

1995 ◽

Vol 78 (3) ◽

pp. 802-806 ◽

Cited By ~ 46

Author(s):

José Louis Rodriguez-Otero ◽

Maria Hermida ◽

Alberto Cepeda

Keyword(s):

Near Infrared ◽

Independent Set ◽

Nir Spectroscopy ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Sample Treatment ◽

Infrared Reflectance ◽

Near Infrared Reflectance ◽

Total Solids

Abstract Near-infrared reflectance (NIR) spectroscopy was used to analyze fat, protein, and total solids in cheese without any sample treatment. A set of 92 samples of cow’s milk cheese was used for instrument calibration by principal components analysis and modified partial least-square regression. The following statistical values were obtained: standard error of calibration (SEC) = 0.388 and squared correlation coefficient (R2) = 0.99 for fat, SEC = 0.397 and R2 = 0.98 for protein, and SEC = 0.412 and R2 = 0.99 for total solids. To validate the calibration, an independent set of 25 cheese samples of the same type was used. Standard errors of validation were 0.47,0.50, and 0.61 for fat, protein, and total solids, respectively, and hf for the regression of measurements by reference methods versus measurements by NIR spectroscopy was 0.98 for the 3 components.

Download Full-text

Estimating Soil Organic Carbon in Agricultural Gypsiferous Soils by Diffuse Reflectance Spectroscopy

Water ◽

10.3390/w12010261 ◽

2020 ◽

Vol 12 (1) ◽

pp. 261 ◽

Cited By ~ 2

Author(s):

Maria Marques ◽

Ana Álvarez ◽

Pilar Carral ◽

Iris Esparza ◽

Blanca Sastre ◽

...

Keyword(s):

Organic Carbon ◽

Soil Organic Carbon ◽

Near Infrared ◽

Diffuse Reflectance Spectroscopy ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Prediction Ability ◽

Greenhouse Gas Inventories ◽

Starting Point

Contents of soil organic carbon (SOC), gypsum, CaCO3, and quartz, among others, were analyzed and related to reflectance features in visible and near-infrared (VIS/NIR) range, using partial least square regression (PLSR) in ParLes software. Soil samples come from a sloping olive grove managed by frequent tillage in a gypsiferous area of Central Spain. Samples were collected in three different layers, at 0–10, 10–20 and 20–30 cm depth (IPCC guidelines for Greenhouse Gas Inventories Programme in 2006). Analyses were performed by C Loss-On-Ignition, X-ray diffraction and water content by the Richards plates method. Significant differences for SOC, gypsum, and CaCO3 were found between layers; similarly, soil reflectance for 30 cm depth layers was higher. The resulting PLSR models (60 samples for calibration and 30 independent samples for validation) yielded good predictions for SOC (R2 = 0.74), moderate prediction ability for gypsum and were not accurate for the rest of rest of soil components. Importantly, SOC content was related to water available capacity. Soils with high reflectance features held c.a. 40% less water than soils with less reflectance. Therefore, higher reflectance can be related to degradation in gypsiferous soil. The starting point of soil degradation and further evolution could be established and mapped through remote sensing techniques for policy decision making.

Download Full-text

Rapid Determination of Intact Sardine Fat by NIRS Using Surface Interactance Fibre Probe

International Journal of Food Engineering ◽

10.2202/1556-3758.1248 ◽

2007 ◽

Vol 3 (6) ◽

Cited By ~ 3

Author(s):

Musleh Uddin ◽

Sandor Turza ◽

Emiko Okazaki

Keyword(s):

Near Infrared ◽

Rapid Determination ◽

Scatter Correction ◽

Screening Method ◽

Fat Content ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Infrared Spectrometer ◽

Near Infrared Spectrometer

A near-infrared spectrometer equipped with surface interactance optical fiber probe (400-1100 nm) was used to determine the fat content in intact sardine Sardinops melanostictus which is considered one of the important fish species of world aquaculture as well as human food source. The fat contents were 2.6425.52 % and fish weight ranges were between 45.23g and 133.76g. Partial least square regression was used to develop predictive equations for fat where two models (with and without multiplicative scatter correction known as MSC) showed relatively good performances with regression coefficients higher than 0.9 and errors below 1% on a fresh weight basis. Results showed that NIR interactance was a suitable non-destructive screening method for fat content in intact small pelagic fish like sardine.

Download Full-text

Method for predicting lignocellulose components in jute by transformed FT-NIR spectroscopic data and chemometrics

Nordic Pulp & Paper Research Journal ◽

10.1515/npprj-2018-0018 ◽

2019 ◽

Vol 34 (1) ◽

pp. 1-9 ◽

Cited By ~ 2

Author(s):

M. Nashir Uddin ◽

Sohan Ahmed ◽

Swapan Kumer Ray ◽

M. Saiful Islam ◽

Ariful Hai Quadery ◽

...

Keyword(s):

Chemical Composition ◽

Spectral Data ◽

Spectroscopic Data ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Chemical Compositions ◽

Nondestructive Technique ◽

Jute Fibers ◽

Calibration Techniques

Abstract In this investigation, a nondestructive technique has been developed for determining chemical composition of jute fiber by chemometric modeling with pretreated FT-NIR spectroscopic data. The chemical composition of jute fibers in wet chemical method were, 58 to 61.80 % α-cellulose, 13.0 to 21.90 % lignin, 9.89 to 16.8 % pentosan and 79.02 to 88.33 % holocellulose. FT-NIR spectral data from range 9000–4000 cm−1 of all jute samples were collected from the instrument. Spectral data of jute samples were pretreated with second order derivatives (SOD), standard normal variate (SNV) techniques and both together were used before calibration. Two chemometric calibration techniques: partial least square regression (PLSR) and artificial neural network (ANN) were assessed for predicting chemical compositions of Jute fibers. Result shows that prediction efficiency ({\text{R}^{2}}) of ANN varies from 72–99 % for calibration, validation and test datasets. However, by PLSR, {\text{R}^{2}} are much higher and consistent than those by earlier one. For α-cellulose, lignin, pentosan and holocellulose {\text{R}^{2}} values hover around 95–99 %. Thereby, a non-destructive, simple and cost effective novel method is being proposed to determine chemical compositions of jute with pretreated FT-NIR spectral data and chemometric calibration techniques.

Download Full-text

Visible and near infrared reflectance spectroscopy for field-scale assessment of Stagnosols properties

Plant Soil and Environment ◽

10.17221/220/2018-pse ◽

2018 ◽

Vol 64 (No. 6) ◽

pp. 276-282 ◽

Cited By ~ 1

Author(s):

Šestak Ivana ◽

Mesić Milan ◽

Zgorelec Željka ◽

Perčin Aleksandra ◽

Stupnišek Ivan

Keyword(s):

Soil Ph ◽

Near Infrared ◽

Soil Depth ◽

Partial Least Square ◽

Least Square ◽

Partial Least Square Regression ◽

Infrared Reflectance ◽

Field Scale ◽

Near Infrared Reflectance ◽

Vnir Spectroscopy

Spectral data contain information on soil organic and mineral composition, which can be useful for soil quality monitoring. The objective of research was to evaluate hyperspectral visible and near infrared reflectance (VNIR) spectroscopy for field-scale prediction of soil properties and assessment of factors affecting soil spectra. Two hundred soil samples taken from the experiment field (soil depth: 30 cm; sampling grid: 15 × 15 m) were scanned using portable spectroradiometer (350–1050 nm) to identify spectral differences of soil treated with ten different rates of mineral nitrogen (N) fertilizer (0–300 kg N/ha). Principal component analysis revealed distinction between higher- and lower-N level treatments conditioned by differences in soil pH, texture and soil organic matter (SOM) composition. Partial least square regression resulted in very strong correlation and low root mean square error (RMSE) between predicted and measured values for the calibration (C) and validation (V) dataset, respectively (SOM, %: RC2 = 0.75 and RV2 = 0.74; RMSEC = 0.334 and RMSEV = 0.346; soil pH: RC2 = 0.78 and RV2 = 0.62; RMSEC = 0.448 and RMSEV = 0.591). Results indicated that hyperspectral VNIR spectroscopy is an efficient method for measurement of soil functional attributes within precision farming framework.

Download Full-text