Artificial neural network modelling of the antioxidant activity and phenolic compounds of bananas submitted to different drying treatmentsby Raquel P.F. Guiné, Maria João Barroca, Fernando J. Gonçalves, Mariana Alves, Solange Oliveira, Mateus Mendes

Food Chemistry


Analytical Chemistry / Food Science


Declaration of Intent

Feminist Network of Hungary

Conservation and land management

The Viscount of Arbuthnott

Strategies of social research in Mozambique

by Members of the Centre of African


e m


Alag 199

University of Coimbra, Pinhal de Marrocos – Polo II, 3030 Coimbra, Portugal reproduction of plants, besides being responsible for the colour, astringency and aroma in several foods (Sharma, 2014). These compounds, being antioxidants, fight free radicals (Rodrigo &

Gil-Becerra, 2014), prevent heart diseases (Jiang, 2014; Khoo & ing may destroy unds, thus reducdız, & Akdemir ngles, & C family Mu and are one of the most popular fruits worldwide. They strong ability to protect themselves from the oxidative caused by intense sunshine and high temperature by increasing their antioxidant levels. Bananas contain vitamins (A, B, C and E), b-carotene and phenolic compounds, such as catechin, epicatechin, lignin, tannins and anthocyanins (Huang et al., 2014; Sulaiman et al., 2011), and are notably perishable, as they ripen rapidly causing significant changes of physicochemical, biochemical and sensory attributes (Huang et al., 2014). Hence drying represents ⇑ Corresponding author. Tel.: +351 232446641; fax: +351 232426536.

E-mail addresses: (R.P.F. Guiné), (M.J. Barroca), (F.J. Gonçalves), (M. Alves), (S. Oliveira), (M. Mendes).

Food Chemistry 168 (2015) 454–459

Contents lists availab

Food Che lseing chain reactions. These natural chemical compounds are generally aromatic and contain at least one hydroxyl group and are called bioactive substances, including, among others, phenolic compounds that are part of the constitution of various foods.

Phenolic compounds are widely present in the plant kingdom, have simple or complex structures, and are essential for growth and (Maqsood & Benjakul, 2010). Thermal process the amount or the bioavailability of these compo ing beneficial health effects (Agcam, Akyıl

Evrendilek, 2014; Al Bittar, Périno-Issartier, Da 2013).

Bananas belong to the genus Musa from the 0308-8146/ 2014 Elsevier Ltd. All rights reserved.hemat, saceae have a stressPhenolic compounds  2014 Elsevier Ltd. All rights reserved. 1. Introduction

The antioxidant compounds can be defined as substances that in small concentrations, compared to the oxidizable substrate, significantly delay or prevent the initiation or propagation of oxidisFalk, 2014), neurodegenerative disorders (Hamaguchi, Ono,

Murase, & Yamada, 2009), circulatory problems (Medina-Remón,

Tresserra-Rimbau, Valderas-Martinez, Estruch, & LamuelaRaventos, 2014), cancer (Fernández-Arroyo et al., 2012), inflammation (Wen, Chen, & Yang, 2012), and inhibit lipid oxidationa r t i c l e i n f o

Article history:

Received 3 April 2014

Received in revised form 17 June 2014

Accepted 17 July 2014

Available online 24 July 2014


Antioxidant activity



Neural networka b s t r a c t

Bananas (cv.Musa nana andMusa 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.cPolytechnic Institute of Viseu, Dep. Food Industry, Quinta da Alagoa, Estrada de Nelas, Ranhados, 3500-606 Viseu, Portugal d Polytechnic Institute of Coimbra – ESTGOH/Institute of Systems and Robotics of the University of Coimbra, Department of Electrical and Computer Engineering,Artificial neural network modelling of th and phenolic compounds of bananas sub drying treatments

Raquel P.F. Guiné a,⇑, Maria João Barroca b, Fernando

Solange Oliveira c, Mateus Mendes d a Polytechnic Institute of Viseu, Research Centre CI&DETS/Dep. Food Industry, Quinta da b Polytechnic Institute of Coimbra, ISEC, DEQB, Rua Pedro Nunes, Quinta da Nora, 3030journal homepage: www.eantioxidant activity itted to different

Gonçalves a, Mariana Alves c, oa, Estrada de Nelas, Ranhados, 3500-606 Viseu, Portugal

Coimbra, Portugal le at ScienceDirect mistry vier .com/locate / foodchem

Tavakoli, Ghassemian, Khoshtaghaza, and Banakar (2013) used emistry 168 (2015) 454–459 4552. Materials and methods 2.1. Sampling

In this work samples from two varieties of banana, Musa nana (MN) and Musa cavendishii (MC) were used. The bananas were obtained from a local supermarket and then were peeled and cut into slices 8 mm thick before submitting them to the drying process. The initial moisture content of the bananas was calculated as an average of three tests made with a halogen Moisture Analyser (Operating parameters: temperature = 130 C, rate = 3). For M. nana the initial moisture content was 67.37 ± 2.65% (wet basis), and for M. cavendishii it was 72.32 ± 2.36% (wet basis). 2.2. Processing

The convective drying was undertaken in an electrical FD 155

Binder drying chamber with an air flow of 0.2 m/s and over perforated trays. The samples were dried until a final moisture content lower than 10% (wet basis) was reached, in order to ensure good preservation characteristics as well as good final physical and chemical properties. The drying experiments were conducted at a constant temperature, having been tested two different temperatures: 50 and 70 C. The drying of the bananas of cv. M. nana at 50 C lasted 525 min and the obtained final moisture content (wet basis) was 9.36%, whereas the drying a 70 C was faster, lasting only 270 min and the final moisture obtained was 4.71%. ForM. cavendishii dried at 50 C the process lasted 450 min and the final moisture content (wet basis) was 6.37%, while at 70 C the process lasted 300 min and the final moisture was 8.83%.neural networks to model and control the drying process of grapes.