Institute of Food Technology

Permanent URI for this community

http://oa.fins.uns.ac.rs/handle/123456789/1
FINS Repository of the Institute of Food Technology in Novi Sad has been established to provide open, online access to the wide range of Institute's research and to offer these data to the community helping in better promotion of the science results.

Browse

Browsing Institute of Food Technology by Author "Ačanski, Marijana"

Now showing 1 - 5 of 5
  • No Thumbnail Available
    Item
    Auto-ML GC/MS fingerprinting strategy for cereal flour authentication
    (2022) Pastor, Kristian; Ilić, Nebojša; Kojić, Jovana; Nastić, Nataša; Krulj, Jelena; Ačanski, Marijana
    Despite food authentication being a global challenge since decades, not much work has been done in developing authentication methodologies of cereal flours and bakery products. This research represents an innovative and rapid method for classifying types of non-gluten and gluten-containing cereal flours: 10 corn, 5 wheat, and 5 barley samples. To achieve this aim, a gas chromatography – mass spectrometry (GC/MS) instrument was coupled to an automated machine learning algorithm (AutoML). Grains were sampled from the experimental fields of the Institute of Field and Vegetable Crops in Novi Sad, Serbia. Cereals were milled into flour, after which liposoluble matter was extracted with n-hexane, and derivatized into corresponding volatile compounds using a 0.2 M trimethylsulfonium hydroxide solution. Total ion current chromatograms consisting of 1666 datapoints/scans were used as raw signals, each of them representing a unique fingerprint of a cereal class. However, the aim of this work was to apply the Weka open-source software in automated mode, as a single, highly parametric machine learning framework for classifying types of flour into classes defined by botanical origin and gluten content. This was achieved using an Auto-Weka package with a state-of-the-art Bayesian optimization method, thus solving the combined algorithm selection and hyperparameter optimization (CASH) problem. The Weka’s learning algorithm took into account all classifiers provided by the software: 27 base learners, 10 meta-methods, and 2 ensemble methods. Both 60 and 120 min time-budgets were carried out by the computer unattended. In each case, a Support Vector classifier (SMO) using normalized polynomial kernel was recommended as the most optimal, using a 10-fold cross-validation to exploit the performance gains on a given dataset. Cereal flour samples were adequately classified in 3 groups: non-gluten corn, and gluten wheat and barley. The presented approach directly supports the application of artificial intelligence on processing chemical information, in order to develop methods for food authentication.
  • No Thumbnail Available
    Item
    Classification of cereal flour by gas ghromatography – mass spectrometry (GC-MS) liposoluble fingerprints and automated machine learning
    (Taylor & Francis, 2022) Pastor, Kristian; Ilić, Marko; Kojić, Jovana; Ačanski, Marijana; Vujić, Đura
    An innovative and rapid approach is described for classifying common types of gluten and non-gluten cereal flour (wheat, rye, triticale, barley, oats, and corn) into the groups defined by their botanical origin. Liposoluble compounds were extracted from flour samples, derivatized, and analyzed using gas chromatography – mass spectrometry (GC-MS). Raw signals used for data processing consisted of mass spectra scans of full chromatograms. These represented unique fingerprints for each class. An automated machine learning framework was applied for classification. The algorithm automatically explored each of the 39 classifiers provided by the software. Using 10-fold cross-validation, a simple logistic classifier was recommended to be optimal. The constructed model resulted in 85.71% correctly classification according to the botanical origin. Furthermore, it unequivocally discriminated samples of non-gluten corn flour. This non-targeted strategy supports the use of artificial intelligence in developing methods for flour authentication.
  • No Thumbnail Available
    Item
    Postupak utvđivanja udela heljdinog brašna u hlebu proizvedenom od mešavine pšeničnog i heljdinog brašna
    (2022-09-23) Pastor, Kristian; Kojić, Jovana; Filipčev, Bojana; Nastić, Nataša; Krulj, Jelena; Vujić, Đura; Ačanski, Marijana
  • No Thumbnail Available
    Item
    Practical method for the confirmation of authentic flours of different types of cereals and pseudocereals
    (Elsevier, 2015-04-01) Ačanski, Marijana; Vujić, Đura N.; Psodorov, Đorđe;
    Gas chromatography with mass spectrometry was used to perform a qualitative analysis of the liposoluble flour extract of different types of cereals (bread wheat and spelt) and pseudocereals (amaranth and buckwheat). In addition to major fatty acids, the liposoluble extract also contained minor fatty acids with more than 20 carbon atoms, higher hydrocarbons and phytosterols. TMSH (trimethylsulfonium hydroxide, 0.2 mol/l in methanol) was used as a trans-esterification reagent. In a trans-esterification reaction, triglycerides esterified from acilglycerols to methyl-esters. SIM (selected ion monitoring) was applied to isolate fatty acid methyl esters on TIC (total ion current) chromatograms, using the 74 Da fragment ion, which originated from McLafferty rearrangement, and is typical for methyl-esters. GC–MS system was used for the trans-esterification of triglycerides to fatty acid methyl esters in the gas chromatographic injector. This eliminated laboratory preparation for fatty acid methyl esters. Cluster analysis was applied to compare the liposoluble flour extract from different types of cereals and pseudocereals. Statistical data showed the liposoluble extract analysis enabled determination of flour origin and, because the results were unambiguous, this approach could be used for quality control.
  • No Thumbnail Available
    Item
    Rapid method for small grain and corn flour authentication using GC/EIMS and multivariate analysis
    (Springer, 2016-02) Pastor, Kristian; Ačanski, Marijana; Vujić, Đura; Bekavac, Goran; Milovac, Snežana; Kravić, Snežana
    The aim of this study was the application of the gas chromatography–mass spectrometry system (GC/EI–MS) system and multivariate data analysis to investigate the possibility of chemical differentiation between small grain flour (wheat, barley, oat, triticale, rye) and corn flour samples. All cereal flour samples were first defatted with hexane, after which the extraction with ethanol was performed. Extracted simple sugars (monosaccharides, disaccharides, trisaccharides, and sugar alcohols) were analyzed in the form of their corresponding trimethylsilyl oximes. Peaks of simple sugar derivatives were selected in total ion current (TIC) chromatograms by monitoring exclusively the following characteristic abundant ions: 204, 217, and 361 m/z. The total surface areas under the selected peaks were subjected to multivariate analysis. Applying principal coordinate analysis and hierarchical cluster analysis to obtained data, samples of corn flour could be very clearly distinguished from all samples of small grain flour, which presented a weaker separation among each other. This method circumvents common analytical procedures by excluding simple sugar identifications, quantitative analysis, the use of analytical standards, and calibration curves. Results are applicable in the quality assurance of mixed flour on the market, considering the increased popularity of their consumption in human nutrition.