Browsing by Author "Mendes, Mateus"
Now showing 1 - 10 of 14
Results Per Page
Sort Options
- Analysis and Modeling of Phenolic Compounds and Antioxidant Activity of Two Banana Varieties Using Machine LearningPublication . Carvalho, Filipe; Couceiro, Paula; Guiné, Raquel; Silva, Pascola; Mendes, Mateus
- Aplicação da modelização por redes neuronais ao teor de compostos fenólicos e atividade antioxidante em bananas de diferentes cultivares secadas sob condições distintasPublication . Guiné, Raquel; Barroca, Maria João; Gonçalves, Fernando; Alves, Mariana; Oliveira, Solange; Mendes, MateusOs compostos fenólicos estão amplamente presentes no reino vegetal, sendo essenciais para o crescimento e reprodução das plantas, além de serem responsáveis pela cor, adstringência e aroma em vários alimentos [1]. Estes compostos, sendo antioxidantes, combatem os radicais livres, previnem doenças cardíacas, doenças neurodegenerativas, problemas do aparelho circulatório, cancro, inflamação e inibem a oxidação lipídica [1-2]. Porém, o processamento térmico pode destruir a quantidade ou a biodisponibilidade destes compostos, reduzindo assim os efeitos benéficos para a saúde [3]. As redes neurais artificiais (ANN: Artificial Neural Networks) têm sido utilizadas nos últimos anos para a modelização de muitos processos em engenharia de alimentos, como por exemplo: modelização e controlo do processo de secagem das uvas, previsão do desempenho energético do processo de secagem por atomização para óleo de peixe e leite em pó desnatado, previsão do encolhimento e reidratação de cenouras desidratadas [4-5]. O presente estudo foi realizado com o objetivo de investigar o impacto das condições de secagem sobre o teor em compostos fenólicos totais e atividade antioxidante em bananas de duas cultivares, bem como modelizar as variáveis do processo por meio de redes neurais artificiais. Bananas (cv. Musa nana e Musa cavendishii) em fresco, secadas por ar a 50 e 70 ºC e liofilizadas foram analisados quanto ao seu conteúdo em compostos fenólicos (FT) utilizando o reagente de Folin-Ciocalteu e atividade antioxidante (AA) utilizando o radical ABTS. Todas as amostras foram sujeitas a seis extrações sucessivas (três com metanol e três com uma solução de acetona). Os dados experimentais serviram para treinar uma rede neural usada para análise de dados e previsão das variáveis de saída (FT e AA). Os resultados indicam que as bananas das duas cultivares apresentam resultados semelhantes e que a secagem ao ar provocou um decréscimo do conteúdo de fenóis e na atividade antioxidante para ambas as temperaturas. A liofilização também diminuiu o teor de compostos fenólicos, porém em menor grau. Os testes feitos com as redes neurais mostraram que as variáveis FT e AA podem ser previstas com uma precisão elevada a partir das variáveis de entrada (Figura 1): variedade, estado de secagem, tipo de extrato e ordem do extracto, sendo que de entre estas as que assumem maior importância são o estado de secagem e a ordem do extrato.
- Artificial neural network modelling of the antioxidant activity and phenolic compounds of bananas submitted to different drying treatmentsPublication . Guiné, Raquel; Barroca, Maria João; Gonçalves, Fernando; Alves, Mariana; Oliveira, Solange; Mendes, MateusBananas (cv. Musa nana and Musa cavendishii) fresh and dried by hot air at 50 and 70 C and lyophilisation were analysed for phenolic contents and antioxidant activity. All samples were subject to six extractions (three with methanol followed by three with acetone/water solution). The experimental data served to train a neural network adequate to describe the experimental observations for both output variables studied: total phenols and antioxidant activity. The results show that both bananas are similar and air drying decreased total phenols and antioxidant activity for both temperatures, whereas lyophilisation decreased the phenolic content in a lesser extent. Neural network experiments showed that antioxidant activity and phenolic compounds can be pre- dicted accurately from the input variables: banana variety, dryness state and type and order of extract. Drying state and extract order were found to have larger impact in the values of antioxidant activity and phenolic compounds.
- Artificial neural network modelling of the chemical composition of carrots submitted to different pre-drying treatmentsPublication . Barroca, Maria João; Guiné, Raquel; Calado, Ana Rita P.; Correia, Paula; Mendes, MateusThe effect of various pre-drying treatments on the quality of dried carrots was evaluated by assessing the values of moisture, ash, protein, fibre, sugars and col- our. The pre-drying treatments under investigation were dipping, either in ascorbic acid or sodium metabisulphite at different concentrations and pre-treatment times, as well as blanching. The experimental data was analysed using neural networks, so that relevant patterns in the data were found and conclusions drawn about each variable. The results showed that the type of pre-drying treatment (chemical or physical) had variable impact on the nutri- tional composition of the dried carrots but not on the colour parameters, which were found to be mostly unaffected by the pre-treatment procedure. Pre-treatment with chemical agents such as ascorbic acid or metabisulphite seem to have the least impact on the parameters studied. The results of the analysis by artificial neural networks confirmed these findings.
- Convective drying of apples: kinetic study, evaluation of mass transfer properties and data analysis using artificial neural networksPublication . Guiné, Raquel; Cruz, Ana; Mendes, MateusIn the present work the effect of drying was evaluated on some chemical and physical properties of apples, and the functions were modelled using feed-forward artificial neural networks. The drying kinetics and the mass transfer properties were also studied. The results indicated that acidity and sugars were significantly reduced by drying. Regarding colour lightness decreases whereas redness and yellowness increased. As for texture, the dried samples were softer and less cohesive as compared to the fresh ones. Mass diffusivity increased with temperature, from 4.4x10-10 m2/s at 30 ºC to 1.4x10-9 m2/s at 60 ºC, and so did the mass transfer coefficient, increasing from 3.7x10-10 m/s at 30 ºC to 7.4x10-9 m/s at 60 ºC. As to the activation energy, it was found to be 34 kJ/mol. Neural network modelling showed that all properties can be correctly predicted by feed-forward neural networks. The analysis of the networks’ behaviours input layer weight values also show which properties are more affected by dehydration or more dependent on variety.
- Evaluation of phenolic compounds and antioxidant activity of blueberries and modelization by artificial neural networksPublication . Guiné, Raquel; Matos, Susana; Gonçalves, Fernando J.; Costa, Daniela; Mendes, MateusThe study aimed at evaluating the influence of different production conditions, conservation and extraction procedures on the total phenolic compounds and antioxidant activity of blueberries by DPPH and ABTS methods. The production factors considered were origin, altitude of the farm location and age of the bushes. The conservation conditions considered were freezing as opposed to the fresh product. The extraction procedures included two different solvents and two orders of extraction. The data analysis was carried out by training artificial neural networks to model the data and extract information from the model. The results obtained revealed that the type of extract and the order of extraction influenced the concentrations of phenolic compounds as well as the antioxidant activity of the different samples studied. Also the origin of the farms from where the blueberries were harvested significantly influence those properties, showing that the blueberries from Oliveira do Hospital had less phenolic compounds and lower antioxidant activity. Also older bushes at higher altitudes seem to produce berries richer in these properties. Regarding conservation, no influence was observed for phenols but a slight influence could be detected for antioxidant activity.
- Evalution through artificial neural networks of the sociodemographic Influences on food choicesPublication . Guiné, Raquel; Ferrão, Ana Cristina; Correia, Paula; Ferreira, Manuela; Mendes, Mateus; Leal, Marcela; Ferreira, Vanessa; Rumbak, Ivana; El-Said, Ayman; Papageorgiou, Maria; Szucs, Viktória; Vittadini, Elena; Klava, Dace; Bartkiene, Elena; Munoz, Lucia; Korzeniowska, Małgorzata; Tarcea, Monica; Djekic, Ilija; Bizjak, Maša; Isoldi, KathyIntroduction: The EATMOT Project is a multinational study that is being carried out in 16 countries about different eating motivations, given their recognized importance in the definition of people’s dietary patterns. Objective: This study investigated the influence of sociodemographic factors on some types of eating motivations, specifically: health related factors; economic and availability aspects; emotional determinants; social, cultural and religious influences; marketing and advertising campaigns and finally environmental concerns. Methods: This is a longitudinal observational study carried out on a non-probabilistic sample with 11960 participants. For the analysis of the data were used the T-test for independent samples or ANOVA with Post-Hoc Tukey HSD, depending on the case. The modelling through artificial neural networks included 7 input variables (sociodemographic characteristics) and 6 output variables (the eating motivations’ groups). Results: Variables like age, marital status, country, living environment, level of education or professional area significantly influenced all the types of eating motivations analysed. However, regarding gender, no significant differences were observed for two of the six types of motivations analysed: economic & availability and marketing & commercial. The results of the ANN modelling showed that the strongest positive factors determining the eating motivations were age for health, country for emotional motivations, gender for economic & availability, country for social & cultural, country for environmental & political, and finally country also for the marketing & commercial motivations. Conclusions: These results highlight the importance of the sociodemographic characteristics as determinants for eating patterns around the globe, and particularly the geographic location.
- Influence of sociodemographic factors on eating motivations – modelling through artificial neural networks (ANN)Publication . Guiné, Raquel; Ferrão, Ana Cristina; Ferreira, Manuela; Correia, Paula; Mendes, Mateus; Bartkiene, Elena; Szűcs, Viktória; Tarcea, Monica; Sarić, Marijana Matek; Černelič-Bizjak, Maša; Isoldi, Kathy; EL-Kenawy, Ayman; Ferreira, Vanessa; Klava, Dace; Korzeniowska, Małgorzata; Vittadini, Elena; Leal, Marcela; Frez-Muñoz, Lucia; Papageorgiou, Maria; Djekić, IlijaThis study aimed at investigating the influence of some sociodemographic factors on the eating motivations. A longitudinal study was carried conducted with 11960 participants from 16 countries. Data analysis included t-test for independent samples or ANOVA, and neural network models were also created, to relate the input and output variables. Results showed that factors like age, marital status, country, living environment, level of education or professional area significantly influenced all of the studied types of eating motivations. Neural networks modelling indicated variability in the food choices, but identifying some trends, for example the strongest positive factor determining health motivations was age, while for emotional motivations was living environment, and for economic and availability motivations was gender. On the other hand, country revealed a high positive influence for the social and cultural as well as for environmental and political and also for marketing and commercial motivations.
- Modeling of the phenolic compounds and antioxidant activity of blueberries by artificial neural networks for data miningPublication . Guiné, Raquel; Matos, Susana; Costa, Daniela; Mendes, MateusThe present work’s goal was to evaluate the effect of different production and conservation conditions, as well as extraction procedures on the phenolic compounds and antioxidant activity of blueberries from cultivar Bluecrop. The production factors considered were origin, altitude of the farm location and age of the bushes, and the conservation was under freezing as opposed to the fresh product. The extraction procedures included two different solvents and different orders of the extraction. Data analysis was performed by training artificial neural networks to model the data and extract information from the model. The results showed that the type of extract and the order of extraction influence the concentrations of phenolic compounds as well as the antioxidant activity of the different samples studied. As to the origin of the farms from where the blueberries were collected, it was found to significantly influence these properties, so that the blueberries from Oliveira do Hospital showed less phenolic compounds and lower antioxidant activity. Older bushes at higher altitudes seem to produce richer berries. Regarding conservation, no influence was observed for phenols but a slight influence could be detected for antioxidant activity.
- Modeling the influence of production and storage conditions on the blueberry qualityPublication . Guiné, Raquel; Matos, Susana; Gonçalves, Christophe; Costa, Daniela Vasconcelos Teixeira da; Mendes, Mateus; Gonçalves, FernandoBlueberry is a widely consumed fruit with major economic value, appreciated due to its characteristic flavor as well as health benefits. The present work aimed to evaluate the effect of several production factors and storage conditions on some chemical and physical properties of blueberries. Some physical and chemical characteristics (moisture, acidity, sugars, color and texture) of blueberries from three cultivars, originating from five different locations and conventional or organic farming, were evaluated. The variation of the properties along time was also evaluated for storage at room temperature and refrigeration. Moreover, artificial neural network models were developed to estimate the physical-chemical characteristics of the blueberries, as influenced by the production and conservation factors considered. The results showed that all the characteristics considered varied according to cultivar, place of cultivation and production mode. The storage conditions also induced changes in the chemical components as well as in color and texture. The changes were dependent on type and duration of storage, cultivar and production mode. Weight analysis of the artificial neural network models highlighted the patterns and trends observed experimentally.