A probabilistic class-modelling method based on prediction bands for functional spectral data: Methodological approach and application to near-infrared spectroscopy

AbstractNeutral detergent fiber (NDF) content was the critical indicator of fiber in corn stover. This study aimed to develop a prediction model to precisely measure NDF content in corn stover using near-infrared spectroscopy (NIRS) technique. Here, spectral data ranging from 400 to 2500 nm were obtained by scanning 530 samples, and Monte Carlo Cross Validation and the pretreatment were used to preprocess the original spectra. Moreover, the interval partial least square (iPLS) was employed to extract feature wavebands to reduce data computation. The PLSR model was built using two spectral regions, and it was evaluated with the coefficient of determination (R2) and root mean square error of cross validation (RMSECV) obtaining 0.97 and 0.65%, respectively. The overall results proved that the developed prediction model coupled with spectral data analysis provides a set of theoretical foundations for NIRS techniques application on measuring fiber content in corn stover.

Download Full-text

Detection of deltamethrin in cabbages using visible shortwave near-infrared spectroscopy

Food Research ◽

10.26656/fr.2017.5(3).742 ◽

2021 ◽

Vol 5 (3) ◽

pp. 273-280

Author(s):

C.D.M. Ishkandar ◽

N.M. Nawi ◽

R. Janius ◽

N. Mazlan ◽

T.T. Lin

Keyword(s):

Infrared Spectroscopy ◽

Root Mean Square Error ◽

Spectral Data ◽

Mean Square Error ◽

Root Mean Square ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Partial Least Square ◽

Calibration Model ◽

Mean Square

Pesticides have long been used in the cabbage industry to control pest infestation. This study investigated the potential application of low-cost and portable visible shortwave near-infrared spectroscopy for the detection of deltamethrin residue in cabbages. A total of sixty organic cabbage samples were used. The sample was divided into four batches, three batches were sprayed with deltamethrin pesticide whereas the remaining batch was not sprayed (control sample). The first three batches of the cabbages were sprayed with the pesticide at three different concentrations, namely low, medium and high with the values of 0.08, 0.11 and 0.14% volume/volume (v/v), respectively. Spectral data of the cabbage samples were collected using visible shortwave near-infrared (VSNIR) spectrometer with wavelengths range between 200 and 1100 nm. Gas chromatography-electron capture detector (GC-ECD) was used to determine the concentration of deltamethrin residues in the cabbages. Partial least square (PLS) regression method was adopted to investigate the relationship between the spectral data and deltamethrin concentration values. The calibration model produced the values of coefficient of determination (R2 ) and the root mean square error of calibration (RMSEC) of 0.98 and 0.02, respectively. For the prediction model, the values of R2 and the root mean square error of prediction (RMSEP) were 0.94 and 0.04, respectively. These results demonstrated that the proposed spectroscopic measurement is a promising technique for the detection of pesticide at different concentrations in cabbage samples.

Download Full-text

Structure of aqueous electrolyte solutions estimated by near infrared spectroscopy and chemometric analysis of spectral data

Russian Journal of General Chemistry ◽

10.1134/s1070363214100028 ◽

2014 ◽

Vol 84 (10) ◽

pp. 1877-1887 ◽

Cited By ~ 3

Author(s):

A. G. Davidian ◽

A. G. Kudrev ◽

L. A. Myund ◽

O. S. Khlynova ◽

M. K. Khripun

Keyword(s):

Infrared Spectroscopy ◽

Spectral Data ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Aqueous Electrolyte ◽

Electrolyte Solutions ◽

Chemometric Analysis ◽

Aqueous Electrolyte Solutions

Download Full-text

Use of near-infrared spectroscopy for prediction of chemical composition of Tifton 85 grass

Semina Ciências Agrárias ◽

10.5433/1679-0359.2021v42n3p1287 ◽

2021 ◽

Vol 42 (3) ◽

pp. 1287-1302

Author(s):

Camila Cano Serafim ◽

◽

Geisi Loures Guerra ◽

Ivone Yurika Mizubuti ◽

Filipe Alexandre Boscaro de Castro ◽

...

Keyword(s):

Infrared Spectroscopy ◽

Chemical Composition ◽

Spectral Data ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Prediction Models ◽

Neutral Detergent Fiber ◽

Mineral Matter ◽

Data Set

The reduction in the quality, consumption, and digestibility of forage can cause a decrease in animal performance, resulting in losses to the rural producer. Thus, it is important to monitor these characteristics in forage plants to devise strategies or practices that optimize production systems. The aim of this study was to develop and validate prediction models using near-infrared spectroscopy (NIRS) to determine the chemical composition of Tifton 85 grass. Samples of green grass, its morphological structures (whole plant, leaf blade, stem + sheath, and senescent material) and hay, totaling 105 samples were used. Conventional chemical analysis was performed to determine the content of oven-dried samples (ODS), mineral matter (MM), crude protein (CP), neutral detergent fiber (NDF), acid detergent fiber (ADF), acid detergent lignin (ADL), cellulose (CEL), hemicellulose (HEM), and in vitro dry matter digestibility (IVDMD). Subsequently, all the samples were scanned using a Vis-NIR spectrometer to collect spectral data. Principal component analysis (PCA) was applied to the data set, and modified partial least squares was used to correlate reference values to spectral data. The coefficients of determination (R2) were 0.74, 0.85, 0.98, 0.75, 0.85, 0.71, 0.82, 0.77, and 0.93, and the ratio of performance deviations (RPD) obtained were 1.99, 2.71, 6.46, 2.05, 2.58, 3.84, 1.86, 2.35, 2.09, and 3.84 for ODS, MM, CP, NDF, ADF, ADL, CEL, HEM, and IVDMD, respectively. The prediction models obtained, in general, were considered to be of excellent quality, and demonstrated that the determination of the chemical composition of Tifton 85 grass can be performed using NIRS technology, replacing conventional analysis.

Download Full-text

Effect of Sampling Frequency for Real-Time Tablet Coating Monitoring Using Near Infrared Spectroscopy

Applied Spectroscopy ◽

10.1177/0003702816662622 ◽

2016 ◽

Vol 70 (9) ◽

pp. 1476-1488 ◽

Cited By ~ 5

Author(s):

Benoît Igne ◽

Hiroaki Arai ◽

James K. Drennen ◽

Carl A. Anderson

Keyword(s):

Infrared Spectroscopy ◽

Spectral Data ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Process Development ◽

Film Coating ◽

Sampling Frequency ◽

Pharmaceutical Products ◽

Coating Weight

While the sampling of pharmaceutical products typically follows well-defined protocols, the parameterization of spectroscopic methods and their associated sampling frequency is not standard. Whereas, for blending, the sampling frequency is limited by the nature of the process, in other processes, such as tablet film coating, practitioners must determine the best approach to collecting spectral data. The present article studied how sampling practices affected the interpretation of the results provided by a near-infrared spectroscopy method for the monitoring of tablet moisture and coating weight gain during a pan-coating experiment. Several coating runs were monitored with different sampling frequencies (with or without co-adds (also known as sub-samples)) and with spectral averaging corresponding to processing cycles (1 to 15 pan rotations). Beyond integrating the sensor into the equipment, the present work demonstrated that it is necessary to have a good sense of the underlying phenomena that have the potential to affect the quality of the signal. The effects of co-adds and averaging was significant with respect to the quality of the spectral data. However, the type of output obtained from a sampling method dictated the type of information that one can gain on the dynamics of a process. Thus, different sampling frequencies may be needed at different stages of process development.

Download Full-text

Ability of near-infrared spectroscopy and chemometrics to predict the age of mosquitoes reared under different conditions

10.21203/rs.2.17981/v1 ◽

2019 ◽

Author(s):

Oselyne Ong ◽

Elise Kho ◽

Pedro Esperança ◽

Chris Freebairn ◽

Floyd Dowell ◽

...

Keyword(s):

Infrared Spectroscopy ◽

Spectral Data ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Age Groups ◽

Field Application ◽

Machine Learning Techniques ◽

Island Population ◽

Pls Regression ◽

The Impact

Abstract Background: Practical, field-ready age-grading tools for mosquito vectors of disease are urgently needed because of the impact that daily survival has on vectorial capacity. Previous studies have shown that near-infrared spectroscopy (NIRS), in combination with chemometrics and predictive modeling, can forecast the age of laboratory-reared mosquitoes with moderate to high accuracy. However, it remains it is unclear whether the technique has utility for identifying shifts in the age structure of wild-caught mosquitoes or whether models derived from the laboratory or semi-field mosquitoes can be applied to mosquitoes reared under different environments. Methods: NIRS spectral data from adult female Aedes albopictus mosquitoes reared in the laboratory (2, 5, 8, 12 and 15 days old) and in semi-field cages populated by wild-caught pupae (resulting in adults of 1, 7 and 14 days old). Spectral data collected from mosquitoes were used to determine if models derived from laboratory material using partial least squares (PLS) regression for the development of predictive models could be effectively applied to mosquitoes from more natural semi-field environments. Results: Models trained on spectra from laboratory-reared material were able to predict the age of other laboratory-reared mosquitoes with moderate accuracy and successfully differentiated all day 2 and 15 mosquitoes. Models derived with laboratory mosquitoes could not differentiate between semi-field age groups, with age predictions relatively indistinguishable for day 1-14. Pre-processing of spectral data and improving the PLS regression framework to avoid overfitting can increase accuracy, but predictions of mosquitoes reared in different environments remained poor. Principle component analysis confirms substantial spectral variations between laboratory and semi-field mosquitoes despite both being derived from the same island population. Conclusions: Model trained on laboratory mosquitoes were able to predict ages of laboratory mosquitoes with good sensitivity and specificity, however it was unable to predict age class of semi-field mosquitoes. This study suggests that laboratory-reared mosquitoes do not capture enough environmental variation to accurately predict the age of the same species reared under different conditions. Further research is needed to explore alternative pre-processing methods and machine learning techniques, and to understand factors that affect absorbance in mosquitoes before field application using NIRS.

Download Full-text

Near Infrared Spectroscopy: A Uniform Measuring Technology for a Sustainable Dairy Production System

Journal of Near Infrared Spectroscopy ◽

10.1255/jnirs.165 ◽

1998 ◽

Vol 6 (A) ◽

pp. A45-A51 ◽

Cited By ~ 3

Author(s):

R. Tsenkova

Keyword(s):

Infrared Spectroscopy ◽

Spectral Data ◽

Near Infrared Spectroscopy ◽

Production System ◽

Near Infrared ◽

System Analysis ◽

Dairy Production ◽

Biological Processes ◽

Biological Objects ◽

Dairy Management

The proposal presents an approach to define criteria for sustainable dairy management based on automated real time spectral data acquisition, monitoring and system analysis of spectral data acquired simultaneously from biological objects and biological processes in a dairy production system.

Download Full-text

Fault Isolation for Desalting Processes Using Near-Infrared Measurements

Mathematical Problems in Engineering ◽

10.1155/2021/9954172 ◽

2021 ◽

Vol 2021 ◽

pp. 1-9

Author(s):

Zhiguo Wang ◽

Yawen Gao ◽

Yuan Ge ◽

Fei Liu

Keyword(s):

Infrared Spectroscopy ◽

Crude Oil ◽

Spectral Data ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Fault Isolation ◽

Fault Detection And Isolation ◽

Molecular Vibration ◽

Infrared Measurements ◽

Selection Operator

Due to the important role of crude oil desalting for the whole petroleum refining process, the near-infrared spectroscopy resulting from molecular vibration is used to detect and isolate potential faults of the desalting process in this paper. With the molecular spectral data reflected by the near-infrared spectroscopy, the principal component analysis is adopted to monitor the process to see if it is in a normal operating condition or not. Considering the feature that the dimension of near-infrared spectroscopy is much larger than the sample size, the least absolute shrinkage and selection operator is employed to achieve an automatic variable selection procedure of the observed spectral data. Simultaneously, if some faults occur, the least absolute shrinkage and selection operator can be used to locate the spectral region affected by the failure. In such a way, the roots of faults can be tracked according to the change of the wavelength numbers. Performances of the proposed fault detection and isolation approaches are evaluated based on the near-infrared spectroscopy sampled for the crude oil desalting process to show the effectiveness.

Download Full-text

Three new Amazonian species of Myrcia sect. Myrcia (Myrtaceae) based on morphology and near-infrared spectroscopy

Phytotaxa ◽

10.11646/phytotaxa.451.4.2 ◽

2020 ◽

Vol 451 (4) ◽

pp. 267-282

Author(s):

PAULO HENRIQUE GAEM ◽

LEIDIANA LIMA DOS SANTOS ◽

ANA ANDRADE ◽

ALBERTO VICENTINI ◽

FIORELLA FERNANDA MAZINE

Keyword(s):

Infrared Spectroscopy ◽

New Species ◽

Spectral Data ◽

Geographical Distribution ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Conservation Status ◽

Habitat Conservation ◽

Flower Buds ◽

Different Shapes

Three new Amazonian species of the Myrcia splendens group from Brazil are proposed based on morphology and near-infrared spectroscopy of leaves and compared with similar taxa. Myrcia eveae resembles M. splendens and may be recognised mostly by large and oblong leaf blades that tapers abruptly at the apex and large bracts; Myrcia otocalyx also resembles M. splendens, being recognised mainly by pyriform flower buds, campanulate hypanthia that are longitudinally ridged, and sepals of different shapes that are patent on fruit; and Myrcia prismatica is similar to M. deflexa, being recognised essentially by chartaceous leaf blades, pedicels clustered at the tips of inflorescence axes, and oblong fruits with longitudinal edges. Spectral data revealed a unique pattern for each one of the new species and the putative related ones, reinforcing the morphological propositions. This is the first study to use morphology and spectroscopy of leaves combined to propose new species of Myrtaceae. Information on geographical distribution, habitat, conservation status, and an identification key are also provided.

Download Full-text

Application of near-Infrared Spectroscopy to Predict Paper Properties of Acacia

Advanced Materials Research ◽

10.4028/www.scientific.net/amr.236-238.1372 ◽

2011 ◽

Vol 236-238 ◽

pp. 1372-1378 ◽

Cited By ~ 1

Author(s):

Shu Ping Song ◽

Hao Zhang ◽

Qian Lang ◽

Jun Wen Pu

Keyword(s):

Mathematical Model ◽

Infrared Spectroscopy ◽

Physical Properties ◽

Mathematical Models ◽

Spectral Data ◽

Near Infrared Spectroscopy ◽

Near Infrared ◽

Paper Industry ◽

Paper Properties ◽

Kraft Paper

First attempt to predicting physical properties of paper by Near Infrared Spectroscopy (abbreviated as NIRS) mathematical model, Acacia is a kind of fast-growing tree which is a potential resource in pulp and paper industry. The mathematical models of physical properties of Acacia unbleached kraft paper were established by software OPUS6.5 of Near Infrared Spectroscopy. Spectral data of Acacia unbleached kraft paper were acquired by Near-Infrared. Physical properties, which include quality, whiteness, tensile index, burst index and tear index, of the paper were measured by GB methods. NIRS mathematical models between the spectral data and the laboratory reference values were established and optimized by software OPUS6.5 partial least squares (abbreviated as PLS). The NIRS mathematical models were evaluated by its parameters, and used to predict the physical properties of unknown samples rapidly and accurately. Compared with NIRS mathematical model of physical properties of Acacia unbleached kraft pulp, the NIRS mathematical models of paper have a better prediction on unknown samples; Compared with traditional laboratory methods, predicting properties of paper by the NIRS mathematical models of paper is rapid, accurate and non-destructive.

Download Full-text