scholarly journals Reflectance Spectroscopy with Multivariate Methods for Non-Destructive Discrimination of Edible Oil Adulteration

Biosensors ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 492
Author(s):  
Ning Su ◽  
Shizhuang Weng ◽  
Liusan Wang ◽  
Taosheng Xu
Keyword(s):  
Soybean Oil ◽  
Rapeseed Oil ◽  
Edible Oils ◽  
Reflectance Spectroscopy ◽  
Edible Oil ◽  
Sesame Oil ◽  
Identification Accuracy ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Nir Reflectance Spectroscopy

The visible and near-infrared (Vis-NIR) reflectance spectroscopy was utilized for the rapid and nondestructive discrimination of edible oil adulteration. In total, 110 samples of sesame oil and rapeseed oil adulterated with soybean oil in different levels were produced to obtain the reflectance spectra of 350–2500 nm. A set of multivariant methods was applied to identify adulteration types and adulteration rates. In the qualitative analysis of adulteration type, the support vector machine (SVM) method yielded high overall accuracy with multiple spectra pretreatments. In the quantitative analysis of adulteration rate, the random forest (RF) combined with multivariate scattering correction (MSC) achieved the highest identification accuracy of adulteration rate with the full wavelengths of Vis-NIR spectra. The effective wavelengths of the Vis-NIR spectra were screened to improve the robustness of the multivariant methods. The analysis results suggested that the competitive adaptive reweighted sampling (CARS) was helpful for removing the redundant information from the spectral data and improving the prediction accuracy. The PLSR + MSC + CARS model achieved the best prediction performance in the two adulteration cases of sesame oil and rapeseed oil. The coefficient of determination (RPcv2) and the root mean square error (RMSEPcv) of the prediction set were 0.99656 and 0.01832 in sesame oil adulterated with soybean oil, and the RPcv2 and RMSEPcv were 0.99675 and 0.01685 in rapeseed oil adulterated with soybean oil, respectively. The Vis-NIR reflectance spectroscopy with the assistance of multivariant analysis can effectively discriminate the different adulteration rates of edible oils.

Use of near Infrared Reflectance Spectroscopy to Analyse Bovine Faecal Samples

2002 ◽  
Vol 10 (4) ◽  
pp. 309-314 ◽  
Author(s):  
D. Cozzolino ◽  
A. La Manna ◽  
D. Vaz Martins
Keyword(s):  
Near Infrared ◽  
Cross Validation ◽  
Dry Weight ◽  
Reflectance Spectroscopy ◽  
Coefficient Of Determination ◽  
Near Infrared Reflectance ◽  
Faecal Samples ◽  
Acid Detergent Fibre ◽  
Nir Reflectance Spectroscopy ◽  
Calibration Equations

Near infrared (NIR) reflectance spectroscopy was used to predict nitrogen (N), acid detergent fibre (ADF), neutral detergent fibre (NDF) and chromium (Cr) in beef faecal samples. One hundred and twenty faecal samples were scanned in a NIRSystems 6500 monochromator instrument over the wavelength range of 400–2500 nm in reflectance. Calibration equations were developed using modified partial least squares (MPLS) with internal cross validation to avoid overfitting. The coefficient of determination in calibration ( R2cal) and the standard error in cross validation ( SECV) were 0.80 (0.74) for N, 0.92 (12.04) for ADF, 0.86 (13.5) for NDF and 0.56 (0.07) for Cr in g kg−1 dry weight, respectively. Results for validation were 0.78 ( SEP: 0.1) for N, 0.74 ( SEP: 7.5) for ADF, 0.85 ( SEP: 8.5) for NDF and 0.10 (0.09) for Cr in g kg−1 dry weight, respectively.

The use of visible (VIS) and near infrared (NIR) reflectance spectroscopy to predict fibre diameter in both clean and greasy wool samples

2005 ◽  
Vol 80 (3) ◽  
pp. 333-337 ◽  
Author(s):  
D. Cozzolino ◽  
F. Montossi ◽  
R. San Julian
Keyword(s):  
Near Infrared ◽  
Cross Validation ◽  
Model Development ◽  
Fibre Diameter ◽  
Reflectance Spectroscopy ◽  
Partial Least Square ◽  
Least Square ◽  
Coefficient Of Determination ◽  
Calibration Models ◽  
Nir Reflectance Spectroscopy

AbstractAbstract Visible (VIS) and near infrared (NIR) reflectance spectroscopy combined with multivariate data analysis were explored to predict fibre diameter in both clean and greasy Merino wool samples. Fifty clean and 400 greasy wool samples were analysed. Samples were scanned in a large cuvette using a NIRSystems 6500 monochromator instrument by reflectance in the VIS and NIR regions (400 to 2500 nm). Partial least square (PLS) regression was used to develop a number of calibration models between the spectral and reference data. Different mathematical treatments were used during model development. Cross validation was used to assess the performance and avoid overfitting of the models. The NIR calibration models gave a coefficient of determination in calibration (R2) > 0·90 for clean wool samples and a R2 < 0·50 for greasy wool samples. The values for the residual predictive value, RPD (ratio of standard deviation (s. d.) to the root mean square of the standard error of cross validation (RMSECV)) were 3 for clean and 0·6 for greasy wool samples, respectively. The results indicated that fibre diameter in greasy wool samples was poorly predicted with NIR, while clean wool showed good relationships.More research is required to improve the calibration on greasy wool samples if the technology is to be used for rapid analysis to assist in the selection of animals in breeding programmes.

scholarly journals Examining the Performance of PARACUDA-II Data-Mining Engine versus Selected Techniques to Model Soil Carbon from Reflectance Spectra

2018 ◽  
Vol 10 (8) ◽  
pp. 1172 ◽  
Author(s):  
Asa Gholizadeh ◽  
Mohammadmehdi Saberioon ◽  
Nimrod Carmon ◽  
Lubos Boruvka ◽  
Eyal Ben-Dor
Keyword(s):  
Data Mining ◽  
Soil Carbon ◽  
Near Infrared ◽  
Reflectance Spectroscopy ◽  
The Other ◽  
Boosted Regression Trees ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Data Mining Algorithm ◽  
Least Squares Regression

The monitoring and quantification of soil carbon provide a better understanding of soil and atmosphere dynamics. Visible-near-infrared-short-wave infrared (VIS-NIR-SWIR) reflectance spectroscopy can quantitatively estimate soil carbon content more rapidly and cost-effectively compared to traditional laboratory analysis. However, effective estimation of soil carbon using reflectance spectroscopy to a great extent depends on the selection of a suitable preprocessing sequence and data-mining algorithm. Many efforts have been dedicated to the comparison of conventional chemometric techniques and their optimization for soil properties prediction. Instead, the current study focuses on the potential of the new data-mining engine PARACUDA-II®, recently developed at Tel-Aviv University (TAU), by comparing its performance in predicting soil oxidizable carbon (Cox) against common data-mining algorithms including partial least squares regression (PLSR), random forests (RF), boosted regression trees (BRT), support vector machine regression (SVMR), and memory based learning (MBL). To this end, 103 soil samples from the Pokrok dumpsite in the Czech Republic were scanned with an ASD FieldSpec III Pro FR spectroradiometer in the laboratory under a strict protocol. Spectra preprocessing for conventional data-mining techniques was conducted using Savitzky-Golay smoothing and the first derivative method. PARACUDA-II®, on the other hand, operates based on the all possibilities approach (APA) concept, a conditional Latin hypercube sampling (cLHs) algorithm and parallel programming, to evaluate all of the potential combinations of eight different spectral preprocessing techniques against the original reflectance and chemical data prior to the model development. The comparison of results was made in terms of the coefficient of determination (R2) and root-mean-square error of prediction (RMSEp). Results showed that the PARACUDA-II® engine performed better than the other selected regular schemes with R2 value of 0.80 and RMSEp of 0.12; the PLSR was less predictive compared to other techniques with R2 = 0.63 and RMSEp = 0.29. This can be attributed to its capability to assess all the available options in an automatic way, which enables the hidden models to rise up and yield the best available model.

Exploring the Use of near Infrared Reflectance Spectroscopy to Study Physical Properties and Microelements in Soils

2003 ◽  
Vol 11 (2) ◽  
pp. 145-154 ◽  
Author(s):  
A. Moron ◽  
D. Cozzolino
Keyword(s):  
Standard Error ◽  
Near Infrared ◽  
Agricultural Soils ◽  
Low Cost ◽  
Scatter Correction ◽  
Reflectance Spectroscopy ◽  
Coefficient Of Determination ◽  
Second Derivative ◽  
Near Infrared Reflectance ◽  
Nir Reflectance Spectroscopy

Near infrared (NIR) reflectance spectroscopy was used to predict the content of silt, sand, clay, iron (Fe), copper (Cu), manganese (Mn) and zinc (Zn) in soil. A total of 332 samples from agricultural soils (0–15 cm depth) in Uruguay (South America) were used. The samples were scanned in a monochromator instrument (NIRSystems 6500, Silver Spring, MD, USA). Two mathematical treatments (first and second derivative) with SNVD (scatter normal variate and detrend) and without scatter correction were studied. Modified partial least squares (mPLS) was used to develop the calibration models. The coefficient of determination in calibration ( R2cal) and the standard error in calibration ( SEC) using the second derivative were 0.81 ( SEC: 5.1), 0.83 ( SEC: 5.3), 0.92 ( SEC: 2.6) for percent sand, silt and clay, respectively. The R2cal and standard error of cross-validation ( SECV) were for Cu 0.87 ( SEC: 0.7), for Fe 0.92 ( SEC: 21.7), for Mn 0.72 ( SEC: 83.0) and for Zn 0.72 ( SEC: 1.2) on mg kg−1 dry matter. It was concluded that NIR reflectance spectroscopy has a great potential as an analytical method for routine analysis of soil texture, Fe, Zn and Cu due the speed and low cost of analysis.

Prediction of the Neuro-Toxin Beta-N-Oxalyl-Amino-L-Alanine in Lathyrus Species, Using near Infrared Reflectance Spectroscopy

1998 ◽  
Vol 6 (A) ◽  
pp. A93-A96 ◽  
Author(s):  
F. Jaby El-Haramein ◽  
A. Abd-El Moneim ◽  
H. Nakkoul ◽  
P.C. Williams
Keyword(s):  
Near Infrared ◽  
Reflectance Spectroscopy ◽  
Lower Limbs ◽  
Coefficient Of Determination ◽  
Near Infrared Reflectance ◽  
Northern India ◽  
Drought Tolerant ◽  
Large Numbers ◽  
Analysis Application ◽  
Nir Reflectance Spectroscopy

Grasspea or chickling vetch ( Lathyrus spp.) is a common food legume, widely grown and eaten in northern India, Bangladesh, Pakistan, Nepal and Ethiopia. It contains the neurotoxin beta-N-oxalyl-amino-L-alanine (BOAA), which can cause the disease known as “neuro-lathyrism”, an irreversible paralysis of the lower limbs, if BOAA-rich seeds form a large proportion of the diet. Lathyrus is a drought-tolerant crop, and ICARDA seeks to breed high-yielding lines that are low in BOAA. Conventional methods for determination of BOAA are time-consuming, expensive, and not practicable for screening large numbers of genotypes. Near infrared (NIR) reflectance spectroscopy offers a rapid, inexpensive method of analysis. Application of NIR reflectance spectroscopy to the prediction of BOAA in Lathyrus has been achieved by developing NIR reflectance spectroscopy equations involving 88 samples, which represented three species: L. sativus, L. cicera and L. ochrus. Both intact and ground seeds were studied. Content of BOAA ranged from 0.09 to 0.83%. Seeds of L. cicera were significantly lower than those of the other two species. The best results were obtained from whole seeds, using multiple linear regression. The standard error of prediction of 0.05% and coefficient of determination ( r2) of 0.94 are considered quite adequate for use in the Lathyrus breeding programme.

scholarly journals Present status of edible oil consumption and household demand projection for Tamil Nadu (India)

2012 ◽  
Vol 57 (1) ◽  
pp. 41-56
Author(s):  
Gurrappanaidu Govindaraj ◽  
Satrasala Suryaprakash ◽  
Nilakantan Sivaramane
Keyword(s):  
Palm Oil ◽  
Sunflower Oil ◽  
Tamil Nadu ◽  
Edible Oils ◽  
Edible Oil ◽  
Sesame Oil ◽  
Sample Survey ◽  
Household Demand ◽  
Oil Demand ◽  
Traditional Crops

Until the 1990s the major edible oil consumed in Tamil Nadu state was peanut and sesame oil. The technological, economic and policy changes thereafter induced dynamism in consumer demand for food, including edible oils. In this study, the household demand for individual edible oils based on present consumption was assessed and forecasted for 2015 and 2020 for Tamil Nadu. Due to constraints in the secondary data published by National Sample Survey Organisation (NSSO), the primary data was used. The Almost Ideal Demand System (AIDS) model was employed to estimate the income (expenditure) elasticities and in turn used to project the demand for edible oils and associated products like ghee and butter. The overall edible oil demand is expected to grow at 7.0% per annum in Tamil Nadu, with the highest growth of sunflower oil (8.7%) followed by other oils (7.8%), sesame oil (6.6%), peanut oil (6.6%) and palm oil (3.1%). The demand for total edible oil in rural Tamil Nadu increases from 3.14 lakh tonnes (2009-10) to 5.3 lakh tonnes (2020), whereas, in urban areas, it increases from 3.24 lakh tonnes to 5.45 lakh tonnes. The non-traditional oil like sunflower oil and other oils (soybean, corn, rice bran, palm oil) has made inroads in the consumption basket and will continue to dominate in the future. Hence, concerted efforts like increasing seed replacement rate, increasing the intensity of adoption of improved technology and appropriate price policy are required to increase productivity of non-traditional crops besides promoting traditional crops (peanut and sesame) to meet the growing edible oil demand in the state.

scholarly journals Predicting Ink Transfer Rate of 3D Additive Printing Using EGBO Optimized Least Squares Support Vector Machine Model

2020 ◽  
Vol 2020 ◽  
pp. 1-12
Author(s):  
Shengpu Li ◽  
Yize Sun
Keyword(s):  
Support Vector Machine ◽  
Prediction Model ◽  
Least Squares ◽  
Transfer Rate ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Experimental Sample ◽  
Machine Model ◽  
Ink Transfer

Ink transfer rate (ITR) is a reference index to measure the quality of 3D additive printing. In this study, an ink transfer rate prediction model is proposed by applying the least squares support vector machine (LSSVM). In addition, enhanced garden balsam optimization (EGBO) is used for selection and optimization of hyperparameters that are embedded in the LSSVM model. 102 sets of experimental sample data have been collected from the production line to train and test the hybrid prediction model. Experimental results show that the coefficient of determination (R2) for the introduced model is equal to 0.8476, the root-mean-square error (RMSE) is 6.6 × 10 (−3), and the mean absolute percentage error (MAPE) is 1.6502 × 10 (−3) for the ink transfer rate of 3D additive printing.

scholarly journals Correlation between the structure and skin permeability of compounds

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Ruolan Zeng ◽  
Jiyong Deng ◽  
Limin Dang ◽  
Xinliang Yu
Keyword(s):  
Large Data ◽  
Qsar Model ◽  
Coefficient Of Determination ◽  
Support Vector ◽  
Skin Permeability ◽  
Data Set ◽  
Test Set ◽  
Svm Algorithm ◽  
Svm Model ◽  
Toxicity Relationship

AbstractA three-descriptor quantitative structure–activity/toxicity relationship (QSAR/QSTR) model was developed for the skin permeability of a sufficiently large data set consisting of 274 compounds, by applying support vector machine (SVM) together with genetic algorithm. The optimal SVM model possesses the coefficient of determination R2 of 0.946 and root mean square (rms) error of 0.253 for the training set of 139 compounds; and a R2 of 0.872 and rms of 0.302 for the test set of 135 compounds. Compared with other models reported in the literature, our SVM model shows better statistical performance in a model that deals with more samples in the test set. Therefore, applying a SVM algorithm to develop a nonlinear QSAR model for skin permeability was achieved.

scholarly journals Optimized Method for Mapping Inorganic Pigments by Means of Multispectral Imaging Combined with Hyperspectral Spectroscopy for the Study of Vincenzo Pasqualoni’s Wall Painting at the Basilica of S. Nicola in Carcere in Rome

Minerals ◽  
2021 ◽  
Vol 11 (8) ◽  
pp. 839
Author(s):  
Lucilla Pronti ◽  
Giuseppe Capobianco ◽  
Margherita Vendittelli ◽  
Anna Candida Felici ◽  
Silvia Serranti ◽  
...  
Keyword(s):  
Multispectral Imaging ◽  
Imaging System ◽  
Principal Component ◽  
Reflectance Spectroscopy ◽  
Wall Painting ◽  
High Spectral Resolution ◽  
Spectral Difference ◽  
Color Palette ◽  
A Minor ◽  
Nir Reflectance Spectroscopy

Multispectral imaging is a preliminary screening technique for the study of paintings. Although it permits the identification of several mineral pigments by their spectral behavior, it is considered less performing concerning hyperspectral imaging, since a limited number of wavelengths are selected. In this work, we propose an optimized method to map the distribution of the mineral pigments used by Vincenzo Pasqualoni for his wall painting placed at the Basilica of S. Nicola in Carcere in Rome, combining UV/VIS/NIR reflectance spectroscopy and multispectral imaging. The first method (UV/VIS/NIR reflectance spectroscopy) allowed us to characterize pigment layers with a high spectral resolution; the second method (UV/VIS/NIR multispectral imaging) permitted the evaluation of the pigment distribution by utilizing a restricted number of wavelengths. Combining the results obtained from both devices was possible to obtain a distribution map of a pictorial layer with a high accuracy level of pigment recognition. The method involved the joint use of point-by-point hyperspectral spectroscopy and Principal Component Analysis (PCA) to identify the pigments in the color palette and evaluate the possibility to discriminate all the pigments recognized, using a minor number of wavelengths acquired through the multispectral imaging system. Finally, the distribution and the spectral difference of the different pigments recognized in the multispectral images, (in this case: red ochre, yellow ochre, orpiment, cobalt blue-based pigments, ultramarine and chrome green) were shown through PCA false-color images.

scholarly journals Machine Learning for Sensorless Temperature Estimation of a BLDC Motor

Sensors ◽  
2021 ◽  
Vol 21 (14) ◽  
pp. 4655
Author(s):  
Dariusz Czerwinski ◽  
Jakub Gęca ◽  
Krzysztof Kolano
Keyword(s):  
Machine Learning ◽  
Temperature Measurement ◽  
Stochastic Gradient Descent ◽  
Estimation Accuracy ◽  
Coefficient Of Determination ◽  
Percentage Error ◽  
Support Vector ◽  
Bldc Motor ◽  
Temperature Estimation ◽  
Motor Operation

In this article, the authors propose two models for BLDC motor winding temperature estimation using machine learning methods. For the purposes of the research, measurements were made for over 160 h of motor operation, and then, they were preprocessed. The algorithms of linear regression, ElasticNet, stochastic gradient descent regressor, support vector machines, decision trees, and AdaBoost were used for predictive modeling. The ability of the models to generalize was achieved by hyperparameter tuning with the use of cross-validation. The conducted research led to promising results of the winding temperature estimation accuracy. In the case of sensorless temperature prediction (model 1), the mean absolute percentage error MAPE was below 4.5% and the coefficient of determination R2 was above 0.909. In addition, the extension of the model with the temperature measurement on the casing (model 2) allowed reducing the error value to about 1% and increasing R2 to 0.990. The results obtained for the first proposed model show that the overheating protection of the motor can be ensured without direct temperature measurement. In addition, the introduction of a simple casing temperature measurement system allows for an estimation with accuracy suitable for compensating the motor output torque changes related to temperature.

Sign in / Sign up

Export Citation Format

Share Document