Artificial neural network modelling of the antioxidant activity and phenolic compounds of bananas submitted to different drying treatments

• Published in: Food chemistry Vol. 168; pp. 454 - 459
• Main Authors: Guiné, Raquel P.F., Barroca, Maria João, Gonçalves, Fernando J., Alves, Mariana, Oliveira, Solange, Mendes, Mateus
• Format: Journal Article
• Language: English
• Published: Kidlington Elsevier Ltd 01.02.2015; Elsevier
• Subjects: acetone; air; air drying; Antioxidant activity; Antioxidants - pharmacology; Banana; bananas; Biological and medical sciences; Desiccation - methods; Drying; Food toxicology; freeze drying; Medical sciences; methanol; Musa - chemistry; Musa acuminata; Neural network; neural networks; Neural Networks (Computer); Phenolic compounds; phenols; Phenols - analysis; Plant Extracts - pharmacology; temperature; Toxicology; Neural network; Phenolic compounds; Antioxidant activity; Banana; Drying; Treatment; Fruit; Plant origin; Phenols; Antioxidant
• ISSN: 0308-8146; 1873-7072; 1873-7072
• DOI: 10.1016/j.foodchem.2014.07.094

•Bananas fresh and dried were analysed for phenols (TP) and antioxidant activity (AA).•Different consecutive extraction solutions were used.•The data trained a neural network (ANN) for data analysis and variable prediction.•Phenols and antioxidant activity decreased with drying for al treatments.•ANN showed that TP and AA can be predicted from the input variables tested. Bananas (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 predicted 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.