Artificial neural network modelling of supercritical fluid CO2 extraction of polyunsaturated fatty acids from common carp (Cyprinus carpio L.) viscera

Quality of red tilapia viscera oil (Oreochromis sp.) as a function of extraction methods

This study aimed to propose a simple and efficient heating-freezing method for oil recovery from red tilapia (Oreochromis sp.) viscera, suitable for industrial application and that does not affect its composition. Three methodologies for oil extraction were studied: a) direct heating (69 °C and 29 min) of samples followed by separation of the oil by decantation, b) direct heating with subsequent freezing and c) solvent extraction assisted by ultrasound. For the oil obtained by each methodology, the following factors were determined: peroxide and iodine values, oxidative stability index, yield percentages and fatty acid profile and, to evaluate the changes thereof, a thermal analysis by differential scanning calorimetry was performed. An oil extracted by centrifugation from fresh viscera was used as control. Results showed yields of 92,126%, 60,99% and 55,36% for the oil obtained by heating and freezing, heating and decanting and solvent extraction, respectively, the other evaluated parameters were similar among each other. The content of PUFA was not affected by heating when compared to the control oil, although a decrease was observed in the solvent extracted oil. This behavior was corroborated with the thermal analysis, which showed that the higher PUFA content, the lower the melting temperatures of the oils and the energy required for phase change. A principal component analysis allowed determining that while there are no differences in the abundance of fatty acids C20:1, 14:0, 18:0, 16:1 and C16:0, there are differences for fatty acids C18:1 and C18:2 depending on the method of extraction used in the oil obtention. The results of this study show that the heating-freezing extraction method is a good alternative for acquiring value-added products and facilitates their implementation in rural areas. Furthermore, allows obtaining a product with high content of polyunsaturated fatty acids (at least a third of the total content).

Predictive Models of Phytosterol Degradation in Rapeseeds Stored in Bulk Based on Artificial Neural Networks and Response Surface Regression

The need to maintain the highest possible levels of bioactive components contained in raw materials requires the elaboration of tools supporting their processing operations, starting from the first stages of the food production chain. In this study, artificial neural networks (ANNs) and response surface regression (RSR) were used to develop models of phytosterol degradation in bulks of rapeseed stored under various temperatures and water activity conditions (T = 12–30 °C and a_w = 0.75–0.90). Among ANNs, networks based on a multilayer perceptron (MLP) and a radial basis function (RBF) were tested. The model input constituted a_w, temperature and storage time, whilst the model output was the phytosterol level in seeds. The ANN-based modeling turned out to be more effective in estimating phytosterol levels than the RSR, while MLP-ANNs proved to be more satisfactory than RBF-ANNs. The approximation quality of the ANNs models depended on the number of neurons and the type of activation functions in the hidden layer. The best model was provided by the MLP-ANN containing nine neurons in the hidden layer equipped with the logistic activation function. The model performance evaluation showed its high prediction accuracy and generalization capability (R² = 0.978; RMSE = 0.140). Its accuracy was also confirmed by the elliptical joint confidence region (EJCR) test. The results show the high usefulness of ANNs in predictive modeling of phytosterol degradation in rapeseeds. The elaborated MLP-ANN model may be used as a support tool in modern postharvest management systems.

High-Pressure Technologies for the Recovery of Bioactive Molecules from Agro-Industrial Waste

Large amounts of food waste are produced each year. These residues require appropriate management to reduce their environmental impact and, at the same time, economic loss. However, this waste is still rich in compounds (e.g., colorants, antioxidants, polyphenols, fatty acids, vitamins, and proteins) that can find potential applications in food, pharmaceutical, and cosmetic industries. Conventional extraction techniques suffer some drawbacks when applied to the exploitation of food residues, including large amounts of polluting solvents, increased time of extraction, possible degradation of the active molecules during extraction, low yields, and reduced extraction selectivity. For these reasons, advanced extraction techniques have emerged in order to obtain efficient residue exploitation using more sustainable processes. In particular, performing extraction under high-pressure conditions, such as supercritical fluids and pressurized liquid extraction, offers several advantages for the extraction of bioactive molecules. These include the reduced use of toxic solvents, reduced extraction time, high selectivity, and the possibility of being applied in combination in a cascade of progressive extractions. In this review, an overview of high-pressure extraction techniques related to the recovery of high added value compounds from waste generated in food industries is presented and a critical discussion of the advantages and disadvantages of each process is reported. Furthermore, the possibility of combined multi-stage extractions, as well as economic and environmental aspects, are discussed in order to provide a complete overview of the topic.

Establishment of the Predicting Models of the Dyeing Effect in Supercritical Carbon Dioxide Based on the Generalized Regression Neural Network and Back Propagation Neural Network

With the growing demand of supercritical carbon dioxide (SC-CO2) dyeing, it is important to precisely predict the dyeing effect of supercritical carbon dioxide. In this work, Generalized Regression Neural Network (GRNN) and Back Propagation Neural Network (BPNN) models have been employed to predict the dyeing effect of SC-CO2. These two models have been constructed based on published experimental data and calculated values. A total of 386 experimental data sets were used in the present work. In GRNN and BPNN models, two input parameters, such as temperature, pressure, dye stuff types, carrier types and dyeing time, were selected for the input layer and one variable, K/S value or dye-uptake, was used in the output layer. It was found that the values of mean-relative-error (MRE) for BPNN model and for GRNN model are 3.27–6.54% and 1.68–3.32%, respectively. The results demonstrate that both BPNN and GPNN models can accurately predict the effect of supercritical dyeing but the former is better than the latter.

Modeling and optimization of Newfoundland shrimp waste hydrolysis for microbial growth using response surface methodology and artificial neural networks

The hydrolyzed protein derived from seafood waste is regarded as a premium and low-cost nitrogen source for microbial growth. In this study, optimization of enzymatic shrimp waste hydrolyzing process was investigated. The degree of hydrolysis (DH) with four processing variables including enzyme/substrate ratio (E/S), hydrolysis time, initial pH value and temperature, were monitored. The DH values were used for response surface methodology (RSM) optimization through central composite design (CCD) and for training artificial neural network (ANN) to make a process prediction. Results indicated that the optimum levels of variables are: E/S ratio at 1.64%, hydrolysis time at 3.59h, initial pH at 9 and temperature at 52.57°C. Hydrocarbon-degrading bacteria Bacillus subtilis N3-1P was cultivated using different DHs of hydrolysate. The associated growth curves were generated. The research output facilitated effective shrimp waste utilization.

An Artificial Neural Network Based Analysis of Factors Controlling Particle Size in a Virgin Coconut Oil-Based Nanoemulsion System Containing Copper Peptide

A predictive model of a virgin coconut oil (VCO) nanoemulsion system for the topical delivery of copper peptide (an anti-aging compound) was developed using an artificial neural network (ANN) to investigate the factors that influence particle size. Four independent variables including the amount of VCO, Tween 80: Pluronic F68 (T80:PF68), xanthan gum and water were the inputs whereas particle size was taken as the response for the trained network. Genetic algorithms (GA) were used to model the data which were divided into training sets, testing sets and validation sets. The model obtained indicated the high quality performance of the neural network and its capability to identify the critical composition factors for the VCO nanoemulsion. The main factor controlling the particle size was found out to be xanthan gum (28.56%) followed by T80:PF68 (26.9%), VCO (22.8%) and water (21.74%). The formulation containing copper peptide was then successfully prepared using optimum conditions and particle sizes of 120.7 nm were obtained. The final formulation exhibited a zeta potential lower than -25 mV and showed good physical stability towards centrifugation test, freeze-thaw cycle test and storage at temperature 25°C and 45°C.