Random forest as one-class classifier and infrared spectroscopy for food adulteration detection

Santana, Felipe Bachion de; Neto, Waldomiro Borges; Poppi, Ronei J.

doi:10.1016/j.foodchem.2019.04.073

Cited by 137 publications

(41 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The Random forest algorithm has been applied as a one-class classifier in FTIR spectroscopy for food adulteration and showed superior performance comparing to PLS-DA and SIMCA, for classification and authentication in chemometrics [25]. The web-based software MetaboAnalyst 4.0 (https://www.…”

Section: Introductionmentioning

confidence: 99%

Attenuated Total Reflectance-Fourier Transform Infrared Spectroscopy (ATR-FTIR) Coupled with Chemometrics, to Control the Botanical Authenticity and Quality of Cold-Pressed Functional Oils Commercialized in Romania

et al. 2020

View full text Add to dashboard Cite

Attenuated total reflectance-Fourier transform infrared ppectroscopy (ATR-FTIR) proved to be a reliable, rapid, and easy-to-use technique to evaluate vegetable oils quality and authenticity. The spectral range of the middle infrared region (MIR) of FTIR spectra, from 4000 to 600 cm−1, has been commonly used to fingerprint specific functional groups of lipids and their modified forms induced by oxidation of thermal treatment. The applicability of FTIR-MIR spectroscopy in assessing oil fingerprinting and quality parameters is crucially dependent on the chemometric methods, including calibrations with authentic samples. We report here the evaluation of seven types of cold-pressed functional oils (sunflower, pumpkin, hempseed, soybean, walnut, linseed, sea buckthorn) produced in Romania, provided directly from small enterprises (as genuine, process-controlled authentic samples) comparative to commercialized samples. Concomitantly, olive oils of similar claimed quality were investigated. The ATR-FTIR-MIR data were complemented by UV–Vis spectral fingerprints and multivariate analysis using Unscrambler X.10.4 and Metaboanalyst 4.0 software (e.g., PCA, PLSDA, cluster analysis, heatmap, Random forest analysis) and ANOVA post-hoc analysis using Fischer’s least significant difference. The integration of spectral and chemometric analysis proved to offer valuable criteria for their botanical group recognition, individual authenticity, and quality, easy to be applied for large cohorts of commercialized oils.

show abstract

Section: Introductionmentioning

confidence: 99%

Attenuated Total Reflectance-Fourier Transform Infrared Spectroscopy (ATR-FTIR) Coupled with Chemometrics, to Control the Botanical Authenticity and Quality of Cold-Pressed Functional Oils Commercialized in Romania

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Third, each tree grows sufficiently without pruning, and is used to test the corresponding category from the test set X. The majority vote of T decision trees is used to make an ensemble classification decision of X 38 …”

Section: Methodsmentioning

confidence: 99%

Simultaneous sex and species classification of silkworm pupae by NIR spectroscopy combined with chemometric analysis

et al. 2020

View full text Add to dashboard Cite

BACKGROUND Most studies only focus on the sex discrimination of silkworm pupae. However, species differentiation of silkworm pupae is also needed in sericulture. To classify the sex and species at the same time, the present study adopts near infrared (NIR) spectroscopy combined with multivariate analysis. RESULTS First, spectra samples were acquired using an NIR sensor, comprising female and male silkworm pupae from three species. Second, three different variables selection approaches were used, including a successive projections algorithm, competitive adaptive reweighted sampling (CARS) and interval partial least squares (iPLS). Third, identification models were built based on random forest and partial least squares discriminant analysis (PLSDA). The experimental results show that iPLS‐PLSDA model (95.24%) gives a high performance when using the one of the three variable selection methods alone. To further increase the performance, the variable selection methods are optimized. The accuracy of the iPLS‐CARS‐PLSDA model is as high as 98.41%. CONCLUSION The present study demonstrates that the optimized variable selection method in combination with NIR spectroscopy represents a suitable strategy for sex and species identification of silkworm pupae. © 2020 Society of Chemical Industry

show abstract

“…For instance, [10] used Artificial Neural Networks (ANN) for classification of drug strength from NIR spectra. [11] compared the application of discriminant PLS and Random Forest (RF) on classification of adulterated oil and spice samples from Fourier Transform Infrared (FT-IR) and NIR spectra. They reported that RF delivers a superior performance.…”

Section: An Empirical Investigation Of Deviations From the Beer-lambementioning

confidence: 99%

An empirical investigation of deviations from the Beer-Lambert law in near-infrared spectroscopy: A case study of lactate in aqueous solutions, serum, blood and tissue

Mamouei

Budidha

Baishya

et al. 2021

Preprint

View full text Add to dashboard Cite

The linear relationship between optical absorbance and the concentration of analytes -as postulated by the Beer-Lambert law- is one of the fundamental assumptions that much of the optical spectroscopy literature is explicitly or implicitly based upon. The common use of linear regression models such as principal component regression and partial least squares exemplifies how the linearity assumption is upheld in practical applications. However, the literature also establishes that deviations from the Beer-Lambert law can be expected when a) the light source is far from monochromatic, b) the concentrations of analytes are very high and c) the medium is highly scattering. The lack of a quantitative understanding of when such nonlinearities can become predominant, along with the mainstream use of nonlinear machine learning models in different fields, have given rise to the use of methods such as random forests, support vector regression, and neural networks in spectroscopic applications. This raises the question that, given the small number of samples and the high number of variables in many spectroscopic datasets, are nonlinear effects significant enough to justify the additional model complexity? In the present study, we empirically investigate this question in relation to lactate, an important biomarker. Particularly, to analyze the effects of scattering matrices, three datasets were generated by varying the concentration of lactate in phosphate buffer solution, human serum, and sheep blood. Additionally, the fourth dataset pertained to invivo, transcutaneous spectra obtained from healthy volunteers in an exercise study. Linear and nonlinear models were fitted to each dataset and measures of model performance were compared to attest the assumption of linearity. To isolate the effects of high concentrations, the phosphate buffer solution dataset was augmented with six samples with very high concentrations of lactate between (100-600 mmol/L). Subsequently, three partly overlapping datasets were extracted with lactate concentrations varying between 0-11 mmol/L, 0-20 mmol/L and 0-600 mmol/L. Similarly, the performance of linear and nonlinear models were compared in each dataset. This analysis did not provide any evidence of substantial nonlinearities due high concentrations. However, the results suggest that nonlinearities in scattering media may be substantial, justifying the use of complex, nonlinear models.

show abstract

Random forest as one-class classifier and infrared spectroscopy for food adulteration detection

Cited by 137 publications

References 27 publications

Attenuated Total Reflectance-Fourier Transform Infrared Spectroscopy (ATR-FTIR) Coupled with Chemometrics, to Control the Botanical Authenticity and Quality of Cold-Pressed Functional Oils Commercialized in Romania

Attenuated Total Reflectance-Fourier Transform Infrared Spectroscopy (ATR-FTIR) Coupled with Chemometrics, to Control the Botanical Authenticity and Quality of Cold-Pressed Functional Oils Commercialized in Romania

Simultaneous sex and species classification of silkworm pupae by NIR spectroscopy combined with chemometric analysis

An empirical investigation of deviations from the Beer-Lambert law in near-infrared spectroscopy: A case study of lactate in aqueous solutions, serum, blood and tissue

Contact Info

Product

Resources

About