Prediction of the geographical origin of butters by partial least square discriminant analysis (PLS-DA) applied to infrared spectroscopy (FTIR) data

Bassbasi, M.; Luca, Michele De; Ioele, Giuseppina; Abdelkhalek, Othmane; Ragno, Gaetano

doi:10.1016/j.jfca.2013.11.010

Cited by 93 publications

(32 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, as for all other legislations with regard to geographic designations set down by other countries, there is only a very generic description of the discriminant characteristics that the product must present, and no statement on how checking the expected typicality. To overcome these limitations, over the last few years, some analytical approaches have been developed and proposed for the geographical discrimination of Moroccan foodstuffs , being some of them successfully applied to the geographical discrimination of Moroccan VOOs .…”

Section: Introductionmentioning

confidence: 99%

A first approach towards the development of geographical origin tracing models for North Moroccan olive oils based on triacylglycerols profiles

Bajoub

Medina‐Rodríguez

Hurtado‐Fernández

et al. 2015

Euro J Lipid Sci & Tech

View full text Add to dashboard Cite

The triacylglycerols composition of monovarietal Picholine Marocaine olive oils, produced in seven of the most productive areas in northern Morocco, has been established for the first time, starting a register of typicality and geographical identity of Moroccan olive oils. Two hundred seventy-nine olive samples were collected over two consecutive crop seasons (2011/2012 (n ¼ 140) and 2012/2013 (n ¼ 139)), the analysis of the triacylglycerol profiles of the obtained oils was performed using high performance liquid chromatography, the influence of the region of provenance was investigated, and chemometric data analysis (including principal components analysis, linear discriminant analysis, partial least squares-discriminant analysis, and soft independent modeling of class analogies) was used to differentiate the studied samples according to their geographical origin. Twenty-one triacylglycerols were characterized and the variability observed among the studied samples could be related to the production area. The combination of triacylglycerols composition with chemometrics provided a powerful tool to verify the geographical origin of north Moroccan olive oils.Practical applications: Moroccan legislations established Geographic Indication labels for adding value to typical products. However, the general procedure to control the geographical authenticity of these protected products remains based on the traceability of their production and there is a lack of appropriate and reliable tools for their geographical unambiguous authentication and control. In this work, geographical authentication models for classifying olive oil samples (based on triacylglycerols composition) have been developed and evaluated, achieving adequate classification and prediction rates for oils coming from the main north Moroccan olive growing areas. The results obtained herein, could represent a significant contribution to the control of the geographical authenticity of Moroccan olive oils.

show abstract

Section: Introductionmentioning

confidence: 99%

A first approach towards the development of geographical origin tracing models for North Moroccan olive oils based on triacylglycerols profiles

Bajoub

Medina‐Rodríguez

Hurtado‐Fernández

et al. 2015

Euro J Lipid Sci & Tech

View full text Add to dashboard Cite

show abstract

“…Partial least‐squares discriminant analysis (PLS‐DA) is widely applied as a simple, fast, relative good performance, and linear discrimination method for qualitative analysis (Costa, Uchida, Miguel, Duarte, & Lima, 2017). The methodology was implemented to explore what were the components or latent variables which better discriminate between different grades of samples from their NIR spectra (X matrix: 900–1,700 nm) according to their maximum covariance with a target class defined in a class pertinence variable (Y matrix: grades) (Bassbasi, De Luca, Ioele, Oussama, & Ragno, 2014; Genisheva et al, 2018). The performance of the PLS‐DA model was assessed in terms of the correlation coefficients of calibration ( R c ) and prediction ( R p ), the root mean square error of cross‐validation (RMSECV), and the root mean squared error of prediction (RMSEP).…”

Section: Methodsmentioning

confidence: 99%

Qualitative discrimination of Chinese dianhong black tea grades based on a handheld spectroscopy system coupled with chemometrics

Huang

Ren

Sun

et al. 2020

Food Science & Nutrition

View full text Add to dashboard Cite

The evaluation of Chinese dianhong black tea (CDBT) grades was an important indicator to ensure its quality. A handheld spectroscopy system combined with chemometrics was utilized to assess CDBT from eight grades. Both variables selection methods, namely genetic algorithm (GA) and successive projections algorithm (SPA), were employed to acquire the feature variables of each sample spectrum. A partial least‐squares discriminant analysis (PLS‐DA) and support vector machine (SVM) algorithms were applied for the establishment of the grading discrimination models based on near‐infrared spectroscopy (NIRS). Comparisons of the portable and benchtop NIRS systems were implemented to obtain the optimal discriminant models. Experimental results showed that GA‐SVM models by the handheld sensors yielded the best predictive performance with the correct discriminant rate (CDR) of 98.75% and 100% in the training set and prediction set, respectively. This study demonstrated that the handheld system combined with a suitable chemometric and feature information selection method could successfully be used for the rapid and efficient discrimination of CDBT rankings. It was promising to establish a specific economical portable NIRS sensor for in situ quality assurance of CDBT grades.

show abstract

“…The results have demonstrated that stable isotope ratios of C, N, O, S and Sr of milk and cheese were linked to their territories of origin, as a result of variations in the type of vegetation and the environment . Additionally, the product origin of dairy products has been studied using metabolite fingerprinting techniques involving NMR and FTIR . Accurate determination of geographical origin for dairy products seems feasible when multi‐analytical approaches, such as metabolomics combined with chemometrics, are studied.…”

Section: Authentication and Adulteration By Food Categorymentioning

confidence: 99%

Modern analytical methods for the detection of food fraud and adulteration by food category

et al. 2017

View full text Add to dashboard Cite

This review provides current information on the analytical methods used to identify food adulteration in the six most adulterated food categories: animal origin and seafood, oils and fats, beverages, spices and sweet foods (e.g. honey), grain-based food, and others (organic food and dietary supplements). The analytical techniques (both conventional and emerging) used to identify adulteration in these six food categories involve sensory, physicochemical, DNA-based, chromatographic and spectroscopic methods, and have been combined with chemometrics, making these techniques more convenient and effective for the analysis of a broad variety of food products. Despite recent advances, the need remains for suitably sensitive and widely applicable methodologies that encompass all the various aspects of food adulteration. © 2017 Society of Chemical Industry.

show abstract

Prediction of the geographical origin of butters by partial least square discriminant analysis (PLS-DA) applied to infrared spectroscopy (FTIR) data

Cited by 93 publications

References 16 publications

A first approach towards the development of geographical origin tracing models for North Moroccan olive oils based on triacylglycerols profiles

A first approach towards the development of geographical origin tracing models for North Moroccan olive oils based on triacylglycerols profiles

Qualitative discrimination of Chinese dianhong black tea grades based on a handheld spectroscopy system coupled with chemometrics

Modern analytical methods for the detection of food fraud and adulteration by food category

Contact Info

Product

Resources

About