Computational intelligence applied to discriminate bee pollen quality and botanical origin

Abstract

a b s t r a c tThe 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%.

Influence of the storage conditions on the quality of bee pollen

“…The mean values observed for reducing sugar content of bee pollen are similar to those reported by Anjos et al (2017) and Gonçalves et al (2017).…”

“…Polyphenols namely, phenolic acids and flavonoids are key bee pollen compounds in the bee pollen that have been reported to be powerful antioxidants and the most essential non-nutrient components (Rice-Evans et al, 1996). Bee pollen is rich in polyphenols, which determines its biological activity (Leja et al, 2007;Gonçalves et al, 2017). Several studies in pure or mixed pollen have reported an important antioxidant activity related to the polyphenols, such as flavones, flavonols, isoflavones, flavonones, anthocyanins, catechin and isocatechin (Almaraz-Abarca et al, 2007; Morais et al, 2011).…”

“…Bee pollen is another product of the beehive, which over the decades has been studied and consumed by the population, due to its chemical composition (Feás et al, 2012;Komosinska-Vassev et al, 2015;Campos et al, 2016). From a nutritional point of view, bee pollen is very rich in protein, fatty-acids, free sugars, carbohydrates, and it contains trace amounts of minerals, phenolic acids, flavonoids and a range of vitamins (Campos et al, 2016;Anjos et al, 2017; Gonçalves et al, 2017). Interestingly, bee pollen possesses all the essential amino acids in concentrations that are five to seven times higher than those found in most protein-rich products.…”

Carbohydrate composition of Slovenian bee pollens

“…The sugars in bee pollen have sometimes been ignored in previous studies or have been included in the total carbohydrate, which also contains the dietary fibre and starch (Carpes et al ., ; Estevinho et al ., ; Feas et al ., ; Yang et al ., ; Kostić et al ., ; Lilek et al ., ). Some studies have reported on the sugars in bee pollen, with their content determined as the reducing sugars (Villanueva et al ., ; Estevinho et al ., ; Nogueira et al ., ; Gonçalves et al ., ) or as the individual sugars, as determined using HPLC (Szczêsna, ; Qian et al ., ; Bobiş et al ., ; Martins et al ., ; Sattler et al ., ), gas chromatography (Serra‐Bonvehi & Escolà‐Jordà, ; Szczesna et al ., ) and capillary electrophoresis (Kalaycıoglu et al ., ).…”

Influence of the Storage Conditions (Frozen vs. Dried) in Health‐Related Lipid Indexes and Antioxidants of Bee Pollen

“…[35,36] The AI and TI indexes consider the different effects that each fatty acid has on human health, particularly on the probability of increasing atherosclerosis and/or promoting thrombus formation. [35,36] The AI and TI indexes consider the different effects that each fatty acid has on human health, particularly on the probability of increasing atherosclerosis and/or promoting thrombus formation.…”