Search results
4 records were found.
The aim of this work was to develop computational intelligence models based on neural networks (NN), fuzzy models (FM), and support vector machines (SVM) to predict physicochemical composition of bee pollen mixture given their botanical origin. To obtain the predominant plant genus of pollen (was the output variable), based on physicochemical composition (were the input variables of the predictive model), prediction models were learned from data. For the inverse case study, input/output variables were swapped. The probabilistic NN prediction model obtained 98.4% of correct classification of the predominant plant genus of pollen. To obtain the secondary and tertiary plant genus of pollen, the results present a lower accuracy. To predict the physicochemical characteristic of a mixture of bee pollen, given their botanical origin, fuzzy models proven the best results with small prediction errors, and variability lower than 10%.
info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/publishedVersion
Mead, one of the oldest fermented drinks, is derived from the fermentation of diluted honey by yeasts. In the context of wine production, several procedures are applied to stabilize the beverage and to improve its organoleptic properties. This study aims to evaluate the impact of adding fining agents on the production of mead. In general, the best results were obtained for the samples containing just one fining agent instead of two combined. However, the best performance was obtained for the combined fining agents (bentonite + gelatine + egg albumin). Tannins decreased significantly the content of volatile compounds. On the other hand, silica appears to be the best fining agent, resulting in the lowest loss of volatile compounds. Thirty‐six volatile compounds were determined by gas chromatograph–flame ionization detector and gas chromatography–mass spectrometry, including alcohols (42.5%), carbonyl compounds (40.4%), acetates (14.4%) and esters (1.8%). Eleven volatile compounds had odour activity values >1, representing those with a major impact on the aroma of mead. Significant differences (p < 0.05) were found in 10 volatile compounds independently to the type of treatment used and no differences (p > 0.05) were observed for remaining compounds.
