scholarly journals Near Infrared Hyperspectral Imaging in Transmission Mode: Assessing the Weathering of Thin Wood Samples

2016 ◽  
Vol 24 (6) ◽  
pp. 595-604 ◽  
Author(s):  
Knut Arne Smeland ◽  
Kristian Hovde Liland ◽  
Jakub Sandak ◽  
Anna Sandak ◽  
Lone Ross Gobakken ◽  
...  
Keyword(s):  
Solar Radiation ◽  
Near Infrared ◽  
Prediction Models ◽  
Hyperspectral Image ◽  
Principal Component Regression ◽  
Principal Component ◽  
Transmission Mode ◽  
Infrared Wavelength ◽  
Robust Prediction ◽  
Wooden Surface

Untreated wooden surfaces degrade when exposed to natural weathering. In this study thin wood samples were studied for weather degradation effects utilising a hyperspectral camera in the near infrared wavelength range in transmission mode. Several sets of samples were exposed outdoors for time intervals from 0 days to 21 days, and one set of samples was exposed to ultraviolet (UV) radiation in a laboratory chamber. Spectra of earlywood and latewood were extracted from the hyperspectral image cubes using a principal component analysis-based masking algorithm. The degradation was modelled as a function of UV solar radiation with four regression techniques, partial least squares, principal component regression, Ridge regression and Tikhonov regression. It was found that all the techniques yielded robust prediction models on this dataset. The result from the study is a first step towards a weather dose model determined by temperature and moisture content on the wooden surface in addition to the solar radiation.

scholarly journals Agricultural products quality determination by means of near infrared spectroscopy

2022 ◽  
Vol 951 (1) ◽  
pp. 012112
Author(s):  
A A Munawar ◽  
Z Zulfahrizal ◽  
R Hayati ◽  
Syahrul
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Prediction Models ◽  
Principal Component Regression ◽  
Principal Component ◽  
Agricultural Products ◽  
Cocoa Bean ◽  
Cocoa Beans ◽  
Non Destructive

Abstract Cocoa is one of main agricultural products cultivated in many tropical countries and processed onto several derivative products. To determine cocoa beans qualities, laboratory procedures based on solvent extractions were mainly used, however most of them are destructive and may cause environmental pollutions. The main purpose of this present study is to employ near infrared spectroscopy (NIRS) for rapid and non-destructive assessment of cocoa beans in form of fat content. Near infrared spectral data of cocoa bean samples were measured as diffuse reflectance in wavelength range from 1000 to 2500 nm. Reference fat contents were measured using standard laboratory methods. Prediction models were developed using principal component regression with raw and baseline corrected spectra data. The results showed that fat contents of cocoa beans can be predicted and determined with maximum correlation coefficient (r) of 0.89 and ratio prediction to deviation (RPD) index of 2.87 for raw spectra and r of 0.91, RPD of 3.18 for baseline spectra correction. It may conclude that NIRS was feasible to be applied as a rapid and non-destructive method for cocoa bean quality assessment.

scholarly journals Fast And Simultaneous Prediction Of Agricultural Soil Nutrients Content Using Infrared Spectroscopy

2019 ◽  
Vol 12 (1) ◽  
pp. 61-66
Author(s):  
Devianti Devianti ◽  
Zulfahrizal Zulfahrizal ◽  
Sufardi Sufardi ◽  
Agus Arip Munawar
Keyword(s):  
Agricultural Soil ◽  
Near Infrared ◽  
Prediction Models ◽  
Agricultural Soils ◽  
Principal Component Regression ◽  
Principal Component ◽  
Nutrient Content ◽  
Laboratory Method ◽  
Near Infrared Reflectance ◽  
Simultaneous Prediction

Abstract. The functions soil depends on the balances of its structure, nutrients composition as well as other chemical and physical properties. Conventional methods, used to determine nutrients content on agricultural soil were time consuming, complicated sample processing and destructive in nature. Near infrared reflectance spectroscopy (NIRS) has become one of the most promising and used non-destructive methods of analysis in many field areas including in soil science. The main aim of this present study is to apply NIRS in predicting nutrients content of soils in form of total nitrogen (N). Transmittance spectra data were obtained from a total of 18 soil samples from 8 different sites followed by N measurement using standard laboratory method. Principal component regression (PCR) with full cross validation were used to develop and validate N prediction models. The results showed that N content can be predicted very well even with raw spectra data with coefficient correlation (r) and residual predictive deviation index (RPD) were 0.95 and 3.35 respectively. Furthermore, spectra correction clearly enhances and improve prediction accuracy with r = 0.96 and RPD = 3.51. It may conclude that NIRS can be used as fast and simultaneous method in determining nutrient content of agricultural soils.

Nondestructive NIR and NIT Determination of Protein, Fat, and Water in Plastic-Wrapped, Homogenized Meat

1992 ◽  
Vol 46 (11) ◽  
pp. 1685-1694 ◽  
Author(s):  
Tomas Isaksson ◽  
Charles E. Miller ◽  
Tormod Næs
Keyword(s):  
Diffuse Reflectance ◽  
Near Infrared ◽  
Multivariate Calibration ◽  
Principal Component Regression ◽  
Principal Component ◽  
Prediction Errors ◽  
Optimal Test ◽  
Meat Samples ◽  
Water Contents

In this work, the abilities of near-infrared diffuse reflectance (NIR) and transmittance (NIT) spectroscopy to noninvasively determine the protein, fat, and water contents of plastic-wrapped homogenized meat are evaluated. One hundred homogenized beef samples, ranging from 1 to 23% fat, wrapped in polyamide/polyethylene laminates, were used. Results of multivariate calibration and prediction for protein, fat, and water contents are presented. The optimal test set prediction errors (root mean square error of prediction, RMSEP), obtained with the use of the principal component regression method with NIR data, were 0.45, 0.29 and 0.50 weight % for protein, fat, and water, respectively, for plastic-wrapped meat (compared to 0.40, 0.28 and 0.45 wt % for unwrapped meat). The optimal prediction errors for the NIT method were 0.31, 0.52 and 0.42 wt % for protein, fat, and water, respectively, for plastic-wrapped meat samples (compared to 0.27, 0.38, and 0.37 wt % for unwrapped meat). We can conclude that the addition of the laminate only slightly reduced the abilities of the NIR and NIT method to predict protein, fat, and water contents in homogenized meat.

scholarly journals Near-Infrared Spectroscopy Coupled Chemometric Algorithms for Rapid Origin Identification and Lipid Content Detection of Pinus Koraiensis Seeds

Sensors ◽  
2020 ◽  
Vol 20 (17) ◽  
pp. 4905
Author(s):  
Hongbo Li ◽  
Dapeng Jiang ◽  
Jun Cao ◽  
Dongyan Zhang
Keyword(s):  
Lipid Content ◽  
Near Infrared ◽  
Prediction Models ◽  
Principal Component ◽  
Two Dimensions ◽  
Breeding Value ◽  
Pinus Koraiensis ◽  
Small Scale ◽  
Important Indicator ◽  
Chemometric Algorithms

Lipid content is an important indicator of the edible and breeding value of Pinus koraiensis seeds. Difference in origin will affect the lipid content of the inner kernel, and neither can be judged by appearance or morphology. Traditional chemical methods are small-scale, time-consuming, labor-intensive, costly, and laboratory-dependent. In this study, near-infrared (NIR) spectroscopy combined with chemometrics was used to identify the origin and lipid content of P. koraiensis seeds. Principal component analysis (PCA), wavelet transformation (WT), Monte Carlo (MC), and uninformative variable elimination (UVE) methods were used to process spectral data and the prediction models were established with partial least-squares (PLS). Models were evaluated by R2 for calibration and prediction sets, root mean standard error of cross-validation (RMSECV), and root mean square error of prediction (RMSEP). Two dimensions of input data produced a faster and more accurate PLS model. The accuracy of the calibration and prediction sets was 98.75% and 97.50%, respectively. When the Donoho Thresholding wavelet filter ‘bior4.4’ was selected, the WT–MC–UVE–PLS regression model had the best predictions. The R2 for the calibration and prediction sets was 0.9485 and 0.9369, and the RMSECV and RMSEP were 0.0098 and 0.0390, respectively. NIR technology combined with chemometric algorithms can be used to characterize P. koraiensis seeds.

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.

Analisis Kandungan Nutrisi Kulit Kopi (Coffea sp.) dengan Menggunakan Metode Near Infrared Reflectance Spectroscopy (NIRS)

2017 ◽  
Vol 2 (4) ◽  
Author(s):  
Andika Boy Yuliansyah ◽  
Sitti Wajizah ◽  
Samadi Samadi
Keyword(s):  
Near Infrared ◽  
Principal Component Regression ◽  
Principal Component ◽  
Coffea Canephora ◽  
Reflectance Spectroscopy ◽  
Infrared Reflectance ◽  
Near Infrared Reflectance Spectroscopy ◽  
Near Infrared Reflectance ◽  
Coffee Pulp ◽  
Infrared Reflectance Spectroscopy

Abstrak.     Tujuan penelitian ini adalah untuk mengevaluasi akurasi metode analisis pakan dengan metode (Near Infrared Reflectance Sectroscopy) NIRS dalam memprediksi kandungan nutrisi limbah kulit kopi serta mengetahui panjang gelombangnya.  Penelitian ini dilakukan di Laboratorium Ilmu Nutrisi dan Teknologi Pakan, Univeritas Syiah Kuala, dari Agustus hingga September 2017.  Penelitian ini menggunakan 30 sampel limbah kulit kopi yang terdiri dari 2 varietas kopi yaitu kopi arabika (Coffea arabica) dan kopi robusta (Coffea canephora). Spektrum diukur dengan menggunakan yaitu FT-IR IPTEK T-1516 pada rentang wavelengrh 1000-2500 nm dan di kalibrasi dan validasi dengan menggunakan software The Unscrambler X version 10.4.  Pretreatment yang digunakan yaitu Multiplicative scatter analysis (MSC) dan DeTrending (DT) dengan metode regresi Principal Component Regression (PCR). Parameter nutrisi yang dianalisis yaitu bahan kering (BK), protein kasar (PK) dan serat kasar (SK).  Hasil penelitian memperlihatkan bahwa NIRS dengan model yang telah dibangun tidak dapat menprediksi bahan kering dengan baik. Hal ini ditunjukkan dengan nilai r, R2 dan RPD yang rendah (0.58, 0.34 dan 3.06) serta RMSEC yang tinggi (3.06). Metode NIRS dapat memprediksi kandungan PK dan SK dengan baik pada penggunaan pretreatment MSC (PK= r: 0.87, R2: 0.76, RMSEC: 0.45 dan RPD: 2.07; SK= r: 0.87, R2: 0.75, RMSEC: 2.83 dan RPD: 2.03). Prediksi kasar untuk PK dan SK didapatkan dengan menggunakan pretreatment DT (PK= r: 0.75, R2: 0.57, RMSEC: 0.60 dan RPD: 1.55; SK= r: 0.84, R2: 0.71, RMSEC: 3.06 dan RPD: 1.88). Analysis of Coffee Pulp (Coffea sp.) Nutrition Content Using Near Infrared Reflectance Spectroscopy (NIRS) Method Abstract.   The aim of present study was to evaluate the accuration of feed analysis method of Near infrared reflectance spectroscopy (NIRS) in predicting nutritional content of Coffee pulp and to know its wavelength.  The study was conducted in  nutrition science and feed technology Laboratory,   Department of Animal Husbandry,  Faculty of Agriculture,  Syiah Kuala University,  august until september, 2017.   As many as 30 coffee pulps  were used in this study and seperated to 2 specieses of coffee, arabica coffee (Coffea arabica) and robusta coffee (Coffea canephora).  The spectrum was scanned using. FT-IR IPTEK T-1516 at 1000 to 2500 nm wavelength and calibrated and validated using The Unscrambler X version 10.4 software. Pretreatment used in this study was Multiplicative scatter analysis (MSC) dan DeTrending (DT) with Principal component regression (PCR) calibration method. Nutrition parameters analyzed were dry matter (DM), crude protein (CP) and dietary fiber (DF). The results of study showed that NIRS with prediction models that have been build cannot predicted DM content in coffee pulp. This was shown with low value of r, R2 dan RPD (0.58, 0.34 dan 3.06) and high value of RMSEC (3.60). NIRS method can predicted CP and DF content quite well using MSC pretreatment (CP= r: 0.87, R2: 0.76, RMSEC: 0.45 dan RPD: 2.07; DF= r: 0.87, R2: 0.75, RMSEC: 2.83 dan RPD: 2.03). Rough prediction for CP and DM content was obtained by using DT pretreatment (CP= r: 0.75, R2: 0.57, RMSEC: 0.60 dan RPD: 1.55; DF= r: 0.84, R2: 0.71, RMSEC: 3.06 dan RPD: 1.88). 

Use of residual maximum likelihood to evaluate accuracy of two NIRS calibration procedures, relative to Kjeldahl, for determining nitrogen concentration of soybeans

1991 ◽  
Vol 71 (2) ◽  
pp. 385-392 ◽  
Author(s):  
G. B. Schaalje ◽  
H. -H. Mündel
Keyword(s):  
Maximum Likelihood ◽  
Near Infrared ◽  
Nitrogen Concentration ◽  
Principal Component Regression ◽  
Principal Component ◽  
Field Trials ◽  
Near Infrared Reflectance ◽  
Residual Maximum Likelihood ◽  
Maximum Likelihood Procedure ◽  
Calibration Methods

The accuracy of estimates of plant properties based on near-infrared reflectance spectroscopy (NIRS) varies with many factors including the biological material in question and the method used to calibrate the NIRS instrument. This study investigated the accuracy, relative to Kjeldahl analysis, of NIRS analysis based on two calibration methods in estimating nitrogen concentration of four stages and/or parts of soybean (Glycine max (L.) Merr.) plants. Samples of whole top growth at anthesis, whole top growth at maturity, whole top growth at maturity excluding seeds, and seeds were obtained from two field trials and one phytotron experiment. Two Kjeldahl determinations of nitrogen concentration were obtained for each sample, as well as reflectance values at each of 19 infrared wavelengths, using a Technicon InfraAlyser 400R. Different subsets of the sample data were used for calibration and assessment of accuracy. The instrument was calibrated using stepwise multiple linear regression (SMLR) and principal component regression (PCR). The residual maximum likelihood procedure was useful in showing that NIRS estimates based on either SMLR or PCR were at least as accurate as Kjeldahl estimates for all stages and/or parts except whole top growth at maturity excluding seeds. Key words: Calibration, principal component regression, stepwise regression

A Comparison of Techniques for Modelling Data with Non-Linear Structure

2003 ◽  
Vol 11 (1) ◽  
pp. 55-70 ◽  
Author(s):  
Laila Stordrange ◽  
Olav M. Kvalheim ◽  
Per A. Hassel ◽  
Dick Malthe-Sørenssen ◽  
Fred Olav Libnau
Keyword(s):  
Near Infrared ◽  
Principal Component Regression ◽  
Predictive Ability ◽  
Principal Component ◽  
Linear Structure ◽  
Data Set ◽  
Linear Pattern ◽  
Near Infrared Spectra ◽  
Non Linear ◽  
Regression Techniques

Partial least squares (PLS) is a powerful tool for multivariate linear regression. But what if the data show a non-linear structure? Near infrared spectra from a pharmaceutical process were used as a case study. An ANOVA test revealed that the data are well described by a 2nd order polynomial. This work investigates the application of regression techniques that account for slightly non-linear data. The regression techniques investigated are: linearising data by applying transformations, local PLS, i.e. splitting of data, and quadratic PLS. These models were compared with ordinary PLS and principal component regression (PCR). The predictive ability of the models was tested on an independent data set acquired a year later. Using the knowledge of non-linear pattern and important spectral regions, simpler models with better predictive ability can be obtained.

Sign in / Sign up

Export Citation Format

Share Document