Review: The evolution of chemometrics coupled with near infrared spectroscopy for fruit quality evaluation

2022 ◽  
pp. 096703352110572
Author(s):  
Nicholas T Anderson ◽  
Kerry B Walsh
Keyword(s):  
Near Infrared ◽  
Nir Spectroscopy ◽  
Short Wave ◽  
Least Squares Regression ◽  
Machine Learning Methods ◽  
Transmission Geometry ◽  
Modelling Techniques ◽  
Test Sets ◽  
Model Robustness

Short wave near infrared (NIR) spectroscopy operated in a partial or full transmission geometry and a point spectroscopy mode has been increasingly adopted for evaluation of quality of intact fruit, both on-tree and on-packing lines. The evolution in hardware has been paralleled by an evolution in the modelling techniques employed. This review documents the range of spectral pre-treatments and modelling techniques employed for this application. Over the last three decades, there has been a shift from use of multiple linear regression to partial least squares regression. Attention to model robustness across seasons and instruments has driven a shift to machine learning methods such as artificial neural networks and deep learning in recent years, with this shift enabled by the availability of large and diverse training and test sets.

scholarly journals Application of VIS/NIR Spectroscopy and SDAE-NN Algorithm for Predicting the Cold Storage Time of Salmon

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Ting Wu ◽  
Nan Zhong ◽  
Ling Yang
Keyword(s):  
Neural Network ◽  
Cold Storage ◽  
Storage Time ◽  
Near Infrared ◽  
High Efficiency ◽  
Back Propagation ◽  
Nir Spectroscopy ◽  
Back Propagation Neural Network ◽  
Least Squares Regression ◽  
Test Sets

The cold storage time of salmon has a significant impact on its freshness, which is an important factor for consumers to evaluate the quality of salmon. The efficient, accurate, and convenient protocol is urgent to appraise the freshness for quality checking. In this paper, the ability of visible/near-infrared (VIS/NIR) spectroscopy was evaluated to predict the cold storage time of salmon meat and skin, which were stored at low-temperature box for 0~12 days. Meanwhile, a double-layer stacked denoising autoencoder neural network (SDAE-NN) algorithm was introduced to establish the prediction model without spectral pre-preprocessing. The results showed that, compared with the common methods such as partial least squares regression (PLSR) and back propagation neural network (BP-NN), the SDAE-NN method had a better performance due to its high efficiency in decreasing noise and optimizing the initial weights. The determination coefficient of test sets (R2test) and root mean square error of test sets (RMSEP) have been calculated based on SDAE-NN, for the salmon meat (skin), the R2test can reach 0.98 (0.92), and the RMSEP can reach 0.93 (1.75), respectively. It is highlighted that the algorithm is efficient and accurate and that the salmon meat would be more suitable for predicting freshness than the salmon skin. VIS/NIR spectroscopy combined with the SDAE-NN algorithm can be widely used to predict the freshness of various agricultural products.

scholarly journals Evaluation of the physicochemical content and solid-state fermentation stage of Zhenjiang aromatic vinegar using near-infrared spectroscopy

2020 ◽  
Vol 16 (12) ◽  
Author(s):  
Suwan Fan ◽  
Tianhong Pan ◽  
Guoquan Li
Keyword(s):  
Solid State ◽  
Solid State Fermentation ◽  
Near Infrared ◽  
Evaluation Method ◽  
Nir Spectroscopy ◽  
Least Squares Regression ◽  
Total Acid ◽  
Fermentation Products ◽  
Fermentation Stage

AbstractAs one of the most famous traditional Chinese vinegars, the grains physicochemical content of Zhenjiang aromatic vinegar during solid-state fermentation (SSF) reflects the growth status of microorganisms and the quality of fermentation products. In addition, the time for grain-turning has a significant effect on the quality of fermentation products. In this study, a new evaluation method combined near-infrared (NIR) spectroscopy with partial least squares regression (PLSR) was proposed to predict the physicochemical content of grains and the fermentation stage. The performance of the PLSR models for the total acid and the nonvolatile acid were RMSEP = 0.0371, Rp2 = 0.9760, and RMSEP = 0.0216, Rp2 = 0.9646, respectively. The accuracy ratio of SSF stage judgment was 100%. Experimental results indicate that the proposed method can be used to guide on-site grain-turning and improve the quality of fermentation products.

scholarly journals Applying NIR spectroscopy to evaluate quality of whey protein supplements available on the Polish market

2018 ◽  
Vol 115 (2) ◽  
pp. 59-70
Author(s):  
Krzysztof Wójcicki
Keyword(s):  
Near Infrared ◽  
Protein Hydrolysate ◽  
Scatter Correction ◽  
Protein A ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Protein Isolate ◽  
Least Squares Regression ◽  
Protein Supplements

The objective of the research study was to apply near infrared (NIR) spectroscopy to evaluate the quality of protein supplements available in the Polish shops and gyms. The evaluation was performed on the basis of the determination of the protein quantity contained in the individual samples by a Kjeldahl method and then the evaluation results were correlated with the measured NIR spectra using an appropriate chemometric method. The research material consisted of fifteen protein supplement samples for athletes, which included the following types: WPI (protein isolate), WPC (protein concentrate), WPH (protein hydrolysate), and mixtures thereof. The obtained NIR spectra of protein supplements were characterized by a similar shape of the bands. Depending on the type of protein, a different intensity of absorption of individual bands could be observed. A Principal Component Analysis (PCA) was used to distinguish the samples based on the spectra measured. Unfortunately, owing to the varying composition of the protein mixtures, it was not possible to find characteristic arrangement of the samples depending on their types. The spectra were correlated with the protein contents determined in the samples using a Partial Least Squares regression method (PLS regression) and various mathematic transformations of the NIR spectral data. The obtained regression models were analysed and the analysis results confirmed that it was possible to apply NIR spectra to estimate the content of proteins in protein supplements. The best result was obtained in a spectrum region between 9401 and 5448 cm-1 and after the first derivative was applied with Multiplicate Scatter Correction (MSC) as a mathematical pre-treatment. On the basis of the results obtained, it was proved that the NIR spectra applied together with the chemometric analysis could be used to quickly evaluate the products studied.

Monitoring the Quality of Oils for Biodiesel Production Using Multivariate near Infrared Spectroscopy Models

2008 ◽  
Vol 16 (5) ◽  
pp. 445-454 ◽  
Author(s):  
Patrícia Baptista ◽  
Pedro Felizardo ◽  
José C. Menezes ◽  
M. Joana Neiva Correia
Keyword(s):  
Quality Control ◽  
Water Content ◽  
Vegetable Oils ◽  
Iodine Value ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Acid Number ◽  
Biodiesel Production ◽  
Least Squares Regression

Biodiesel is a mixture of fatty acid methyl esters, derived from vegetable oils or animal fats, which is usually produced by a transesterification reaction, where the oils or fats react with an alcohol in the presence of a catalyst. The quality of the oils used for biodiesel production strongly influences the final properties of biodiesel, namely its compliance to the European Standard. This work reports the use of near infrared (NIR) spectroscopy in the quality control of several oil properties, such as the iodine value, the water content and the acid number but, more importantly, the weight–weight percentages (wt%) of soybean, palm and rapeseed oil in mixtures. Principal component analysis was used to perform a qualitative analysis of the spectra, whereas partial least squares regression allowed the development of calibration models between analytical reference data and NIR spectra. The calibration ranges were 60–126 g I2 100 g−1 for the iodine value, 478–2500 mg kg−1 for the water content and 0.13-6.56 mg KOH g−1 for the acid number, whereas the validation errors were around 3.1 g I2 100 g−1, 111 mg kg−1 and 0.22 mg KOH g−1, respectively. The results obtained show that NIR spectroscopy is a promising technique to carry out the quality control of the commonly used vegetable oils for biodiesel production, namely the quality assurance and authenticity. Furthermore, it is of great value to have a simple, fast and reliable method to identify the composition of an oil mixture and/or some of its quality parameters, prior to storage or upon admission of a new lot of oil.

scholarly journals Eating quality of cooked rice determination using Fourier transform near infrared spectroscopy

2014 ◽  
Vol 07 (06) ◽  
pp. 1450003 ◽  
Author(s):  
Ravipat Lapcharoensuk ◽  
Panmanas Sirisomboon
Keyword(s):  
Fourier Transform ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Eating Quality ◽  
Least Squares Regression ◽  
Prediction Ability ◽  
Cooked Rice ◽  
Near Infrared Spectra ◽  
Jasmine Rice

The goal of this research was to study the relationship between the eating quality of cooked rice and near infrared spectra measured by a Fourier Transform near infrared (FT–NIR) Spectrometer. Samples of milled: parboiled rice, white rice, new Jasmine rice (harvested in 2012) and aged Jasmine rice (harvested in 2006 or during the period 2007–2011) were used in this study. The eating quality of the cooked rice, i.e., adhesiveness, hardness, dryness, whiteness and aroma, were evaluated by trained sensory panelists. FT–NIR spectroscopy models for predicting the eating quality of cooked rice were established using the partial least squares regression. Among the eating quality, the stickiness model indicated its highest prediction ability (i.e., [Formula: see text]; RMSEP = 0.65; Bias = 0.00; RPD = 1.87) and SEP/SD of 2. In addition, it was clear that the water content did not affect the eating quality of cooked rice, rather the main chemical component implicated was starch.

scholarly journals Textile Recognition and Sorting for Recycling at an Automated Line Using Near Infrared Spectroscopy

Recycling ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 11
Author(s):  
Kirsti Cura ◽  
Niko Rintala ◽  
Taina Kamppuri ◽  
Eetta Saarimäki ◽  
Pirjo Heikkilä
Keyword(s):  
Infrared Spectroscopy ◽  
Near Infrared Spectroscopy ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Automated Recognition ◽  
Textile Materials ◽  
Input Material ◽  
Adequate Quality ◽  
Automated Line

In order to add value to recycled textile material and to guarantee that the input material for recycling processes is of adequate quality, it is essential to be able to accurately recognise and sort items according to their material content. Therefore, there is a need for an economically viable and effective way to recognise and sort textile materials. Automated recognition and sorting lines provide a method for ensuring better quality of the fractions being recycled and thus enhance the availability of such fractions for recycling. The aim of this study was to deepen the understanding of NIR spectroscopy technology in the recognition of textile materials by studying the effects of structural fabric properties on the recognition. The identified properties of fabrics that led non-matching recognition were coating and finishing that lead different recognition of the material depending on the side facing the NIR analyser. In addition, very thin fabrics allowed NIRS to penetrate through the fabric and resulted in the non-matching recognition. Additionally, ageing was found to cause such chemical changes, especially in the spectra of cotton, that hampered the recognition.

Water absorption thermodynamics in single wood pellets modelled by multivariate near-infrared spectroscopy

Holzforschung ◽  
2008 ◽  
Vol 62 (4) ◽  
Author(s):  
Torbjörn A. Lestander
Keyword(s):  
Water Content ◽  
Near Infrared ◽  
Calorific Value ◽  
Least Squares Regression ◽  
Wood Pellets ◽  
Differential Heat ◽  
On Line ◽  
Explained Variation ◽  
Test Sets ◽  
Content Range

Abstract Samples of wood pellets were adjusted into six water content classes from 0% to 12%. The water content in single pellets varied between 0.1% and 14.2%. Three equations were constructed to estimate the differential heat of sorption (-ΔH) values from (1) fractal-geometry, (2) isosteric, and (3) calorimetric data. The ranges in calculated -ΔH of single pellets were (1) 133–1475, (2) 315–881, and (3) 195–1188 J g-1 water, respectively, across the studied moisture content range. Partial least squares regression was used to model near-infrared (NIR) spectra from single pellets and to predict -ΔH values and water content. The explained variation in test sets for the different models ranged from 97.1% to 99.9%. The shifts in peak absorbance for two water bands indicated that frequency in overtone vibration of O-H stretching and bending decreased, when water content was raised. Simulations of mixes between pellets of differential heat values showed that released heat was up to 0.03% of the gross calorific value of wood pellets. This heat may be a major contributor to initial temperature increases in pellet stacks during storage. The results indicate that on-line NIR based predictions of differential heat in wood pellets is possible to apply in the pellet industry.

Estimation of soil organic matter using proximal and satellite sensors after a wildfire in Mediterranean Croatia

2021 ◽  
Author(s):  
Iva Hrelja ◽  
Ivana Šestak ◽  
Igor Bogunović
Keyword(s):  
Organic Matter ◽  
Soil Organic Matter ◽  
Spectral Data ◽  
Near Infrared ◽  
Mean Squared Error ◽  
Nir Spectroscopy ◽  
Soil Samples ◽  
Least Squares Regression ◽  
Macro Scale ◽  
Sentinel 2

<p>Spectral data obtained from optical spaceborne sensors are being recognized as a valuable source of data that show promising results in assessing soil properties on medium and macro scale. Combining this technique with laboratory Visible-Near Infrared (VIS-NIR) spectroscopy methods can be an effective approach to perform robust research on plot scale to determine wildfire impact on soil organic matter (SOM) immediately after the fire. Therefore, the objective of this study was to assess the ability of Sentinel-2 superspectral data in estimating post-fire SOM content and comparison with the results acquired with laboratory VIS-NIR spectroscopy.</p><p>The study is performed in Mediterranean Croatia (44° 05’ N; 15° 22’ E; 72 m a.s.l.), on approximately 15 ha of fire affected mixed <em>Quercus ssp.</em> and <em>Juniperus ssp.</em> forest on Cambisols. A total of 80 soil samples (0-5 cm depth) were collected and geolocated on August 22<sup>nd</sup> 2019, two days after a medium to high severity wildfire. The samples were taken to the laboratory where soil organic carbon (SOC) content was determined via dry combustion method with a CHNS analyzer. SOM was subsequently calculated by using a conversion factor of 1.724. Laboratory soil spectral measurements were carried out using a portable spectroradiometer (350-1050 nm) on all collected soil samples. Two Sentinel-2 images were downloaded from ESAs Scientific Open Access Hub according to the closest dates of field sampling, namely August 31<sup>st</sup> and September 5<sup>th </sup>2019, each containing eight VIS-NIR and two SWIR (Short-Wave Infrared) bands which were extracted from bare soil pixels using SNAP software. Partial least squares regression (PLSR) model based on the pre-processed spectral data was used for SOM estimation on both datasets. Spectral reflectance data were used as predictors and SOM content was used as a response variable. The accuracy of the models was determined via Root Mean Squared Error of Prediction (RMSE<sub>p</sub>) and Ratio of Performance to Deviation (RPD) after full cross-validation of the calibration datasets.</p><p>The average post-fire SOM content was 9.63%, ranging from 5.46% minimum to 23.89% maximum. Models obtained from both datasets showed low RMSE<sub>p </sub>(Spectroscopy dataset RMSE<sub>p</sub> = 1.91; Sentinel-2 dataset RMSE<sub>p</sub> = 0.99). RPD values indicated very good predictions for both datasets (Spectrospcopy dataset RPD = 2.72; Sentinel-2 dataset RPD = 2.22). Laboratory spectroscopy method with higher spectral resolution provided more accurate results. Nonetheless, spaceborne method also showed promising results in the analysis and monitoring of SOM in post-burn period.</p><p><strong>Keywords:</strong> remote sensing, soil spectroscopy, wildfires, soil organic matter</p><p><strong>Acknowledgment: </strong>This work was supported by the Croatian Science Foundation through the project "Soil erosion and degradation in Croatia" (UIP-2017-05-7834) (SEDCRO). Aleksandra Perčin is acknowledged for her cooperation during the laboratory work.</p>

Non-Invasive Blood Glucose Monitoring by Means of near Infrared Spectroscopy: Methods for Improving the Reliability of the Calibration Models

1997 ◽  
Vol 20 (5) ◽  
pp. 285-290 ◽  
Author(s):  
U.A. Müller ◽  
B. Mertes ◽  
C. Fischbacher ◽  
K.U. Jageman ◽  
K. Danzer
Keyword(s):  
Blood Glucose ◽  
Near Infrared ◽  
Glucose Monitoring ◽  
Blood Glucose Monitoring ◽  
Least Squares Regression ◽  
Non Invasive ◽  
Infrared Reflection ◽  
Calibration Models ◽  
Infrared Reflection Spectroscopy

The feasibility of using near infrared reflection spectroscopy for non-invasive blood glucose monitoring is discussed. Spectra were obtained using a diode-array spectrometer with a fiberoptic measuring head with a wavelength ranging from 800 nm to 1350 nm. Calibration was performed using partial least-squares regression and radial basis function networks. The results of different methods used to evaluate the quality of the recorded spectra in order to improve the reliability of the calibration models, are presented.

Ability of Vis-PIR spectroscopy to monitor changes in organic carbon of loamy soils at two depths

2021 ◽  
Author(s):  
Hayfa Zayani ◽  
Youssef Fouad ◽  
Didier Michot ◽  
Zeineb Kassouk ◽  
Zohra Lili-Chabaane ◽  
...  
Keyword(s):  
Organic Carbon ◽  
Near Infrared ◽  
Full Range ◽  
Nir Spectroscopy ◽  
Soil Samples ◽  
Calibration Data ◽  
Least Squares Regression ◽  
Data Set ◽  
Soil Carbon Stocks ◽  
The Mean

<p>Visible-Near Infrared (Vis-NIR) spectroscopy has proven its efficiency in predicting several soil properties such as soil organic carbon (SOC) content. In this preliminary study, we explored the ability of Vis-NIR to assess the temporal evolution of SOC content. Soil samples were collected in a watershed (ORE AgrHys), located in Brittany (Western France). Two sampling campaigns were carried out 5 years apart: in 2013, 198 soil samples were collected respectively at two depths (0-15 and 15-25 cm) over an area of 1200 ha including different land use and land cover; in 2018, 111 sampling points out of 198 of 2013 were selected and soil samples were collected from the same two depths. Whole samples were analyzed for their SOC content and were scanned for their reflectance spectrum. Spectral information was acquired from samples sieved at 2 mm fraction and oven dried at 40°C, 24h prior to spectra acquisition, with a full range Vis-NIR spectroradiometer ASD Fieldspec®3. Data set of 2013 was used to calibrate the SOC content prediction model by the mean of Partial Least Squares Regression (PLSR). Data set of 2018 was therefore used as test set. Our results showed that the variation ∆SOC<sub>obs</sub><sub></sub>obtained from observed values in 2013 and 2018 (∆SOC<sub>obs</sub> = Observed SOC (2018) - Observed SOC (2013)) is ranging from 0.1 to 25.9 g/kg. Moreover, our results showed that the prediction performance of the calibrated model was improved by including 11 spectra of 2018 in the 2013 calibration data set (R²= 0.87, RMSE = 5.1 g/kg and RPD = 1.92). Furthermore, the comparison of predicted and observed ∆SOC between 2018 and 2013 showed that 69% of the variations were of the same sign, either positive or negative. For the remaining 31%, the variations were of opposite signs but concerned mainly samples for which ∆SOCobs is less than 1,5 g/kg. These results reveal that Vis-NIR spectroscopy was potentially appropriate to detect variations of SOC content and are encouraging to further explore Vis-NIR spectroscopy to detect changes in soil carbon stocks.</p>

Sign in / Sign up

Export Citation Format

Share Document