Search

In this study freeze-drying and oven-drying (at 50 and 65 °C) were applied for the preparation of dried pumpkin waste. The effect of drying methods on physical properties (moisture content, water activity, hygroscopicity, water solubility, bulk and tapped density, flowability and colour), content of bioactive compounds (carotenoids and phenolics) and antioxidant activity were investigated. Also, the influence of one-year storage at –20 °C on the bioactive compounds content and the antioxidant activity of dried pumpkin waste was examined. Results indicated that drying method showed a significant impact on the investigated characteristics. Bioactive compounds content and antioxidant activity by DPPH test of freeze-dried were higher than of oven-dried pumpkin waste, while higher antioxidant activity in reducing power assay was determined by oven-dried pumpkin waste. An artificial neural network model was developed, for the anticipation of antioxidant activity according to bioactive compounds content (phenolics and carotenoids), in oven-dried (at 50 and 65 °C) and in freeze-dried pumpkin waste after one-year storage. These models showed good prediction properties (the r2 value during training cycle for output variables was 0.999). It was demonstrated that pumpkin waste is potentially an important source of bioactive compounds, which can be used after extraction in suitable forms in the development of functional food products.

Supramolecular solvent-based extraction (SUPRAS) stands out as a promising approach, particularly due to its environmentally friendly and efficient characteristics. This research explores the optimization of SUPRAS extraction for sango radish and kale microgreens, focusing on enhancing the extraction efficiency. The Taguchi experimental design and artificial neural network (ANN) modeling were utilized to systematically optimize extraction parameters (ethanol content, SUPRAS: equilibrium ratio, centrifugation rate, centrifugation time, and solid-liquid ratio). The extraction efficiency was evaluated by measuring the antioxidant activity (DPPH assay) and contents of chlorophylls, carotenoids, phenolics, and anthocyanidins. The obtained results demonstrated variability in phytochemical contents and antioxidant activities across microgreen samples, with the possibility of achieving high extraction yields using the prediction of optimized parameters. The optimal result for sango radish can be achieved at an ethanol content of 35.7%; SUPRAS: equilibrium ratio of 1 v/v, centrifugation rate of 4020 rpm, centrifugation time of 19.84 min, and solid-liquid ratio of 30.2 mg/mL. The following parameters are predicted for maximal extraction efficiency for kale: ethanol content of 35.64%; SUPRAS: equilibrium ratio of 1 v/v; centrifugation rate of 3927 rpm; centrifugation time of 19.83 min; and solid-liquid ratio of 30.4 mg/mL. Additionally, laboratory verification of predicted SUPRAS parameters showed very low divergency degrees for both microgreens (–3.09 to 2.36% for sango radish, and −2.57 to 3.58% for kale). This potential of SUPRAS extraction, coupled with statistical and computational optimization techniques, can enhance the recovery of valuable bioactive compounds from microgreens and contribute to green extraction applications. [ABSTRACT FROM AUTHOR]

The aim of the study was to investigate the changes in ultimate, proximate analysis, and calorific properties of Miscanthus x giganteus with three types of planting materials (two rhizomes - R1 and R2 - and one seedling - S) and three ash fertiliser treatments (P0, P2, and P5) were included in the study. The research further examined their effects on crop yield, stem height and various chemical properties. The results showed that the maximum yield was obtained with the R1 x P2 plant type, while the minimum yield was recorded with the R2 x P2 plant type. In addition, the greatest average stem height (3.34 m) was recorded for the R2 x P5 plant type. Significant differences were also found in the chemical components between the plant types and treatments. For example, the highest ash content of 2.25% was found in plant type 'S' x P5, while the highest coke content of 14.48 % was found in plant type R1 x P5. The statistical analysis confirmed that planting material and ash fertilisation had significant influence on the physicochemical properties of Miscanthus x giganteus. This consequently affects the calorific value, with the average higher and lower heating value being 18.32 and 17.04 MJ/kg, respectively. The neural regression network models showed robust predictive performance for the higher heating value and lower heating value, with low chi-square values, X², and high coefficients of determination, R². [ABSTRACT FROM AUTHOR]

This study focuses on predicting and optimizing the quality parameters of cookies enriched with dehydrated peach through the application of Support Vector Machine (SVM) and Artificial Neural Network (ANN) models. The purpose of the study is to employ advanced machine learning techniques to understand the intricate relationships between input parameters, such as the presence of dehydrated peach and treatment methods (lyophilization and lyophilization with osmotic pretreatment), and output variables representing various quality aspects of cookies. For each of the 32 outputs, including the parameters of the basic chemical compositions of the cookie samples, selected mineral contents, moisture contents, baking characteristics, color properties, sensorial attributes, and antioxidant properties, separate models were constructed using SVMs and ANNs. Results showcase the efficiency of ANN models in predicting a diverse set of quality parameters with r2 up to 1.000, with SVM models exhibiting slightly higher coefficients of determination for specific variables with r2 reaching 0.981. The sensitivity analysis underscores the pivotal role of dehydrated peach and the positive influence of osmotic pretreatment on specific compositional attributes. Utilizing established Artificial Neural Network models, multi-objective optimization was conducted, revealing optimal formulation and factor values in cookie quality optimization. The optimal quantity of lyophilized peach with osmotic pretreatment for the cookie formulation was identified as 15%. [ABSTRACT FROM AUTHOR]

Agricultural production is a Serbian main economic sector, presenting a base for the food industry. By analysing the public available data of the agriculture sector, applying a newly developed business model it is possible to assess the current situation and to realize the relation between variables, which can also be used for prediction of future trends in agricultural production and food industry. Within this paper an attempt was made to develop a novel artificial neural network model for better understanding the relation between the observed parameters and to estimate the efficiency in sustainability achievement and sector potential the well-known Cobb-Douglas production model was compared to the newly developed model. The presented models could be used to achieve the transformation towards a circular bioeconomy, by developing the national strategies for sustainable agricultural production, with the aim of better utilization of resources and reduction of wastes.

For many years, linseed has been attracted a great attention in animal nutrition because of its exceptionally favourable fatty acid composition and high content of essential α-linolenic acid. However, the presence of antinutritive components, cyanogenic glycosides, limits its inclusion in the animal's diet. Several ways of linseed detoxification were observed in literature, emphasizing extrusion as one of the most effective processes. In the presented study, the application of Artificial Neural Network (ANN) has been observed, as a tool for prediction of process influence on the deterioration of cyanogenic glycosides during the extrusion process of linseed-sunflower meal co-extrudate. The content of hydrogen cyanide (HCN) was determined according to the AOAC method as an indicator of cyanogenic glycosides in the produced co-extrudate. Extrusion of the material was performed on a laboratory single screw extruder. The performance of ANN model was compared with experimental data in order to develop rapid and accurate method for prediction of HCN content in co-extrudate. According to the experimental results, the highest HCN content (126 mg/kg) was determined at the lowest moisture content (7%) and the lowest screw speed (240 rpm). With the increase of moisture content and temperature during extrusion, the content of HCN drastically decreased. The ANN model showed high prediction accuracy (r2> 0.999), which indicates that the model could be easily and reliably applied in practice.

The aim of this study was to investigate the potential of using structural analysis parameters for estimating the higher heating value (HHV) of biomass by obtaining information on the composition of cellulose, lignin, and hemicellulose. To achieve this goal, several nonlinear mathematical models were developed, including polynomials, support vector machines (SVMs), random forest regression (RFR) and artificial neural networks (ANN) for predicting HHV. The performed statistical analysis "goodness of fit" showed that the ANN model has the best performance in terms of coefficient of determination (R2 = 0.90) and the lowest level of model error for the parameters X2 (0.25), RMSE (0.50), and MPE (2.22). Thus, the ANN model was identified as the most appropriate model for determining the HHV of different biomasses based on the specified input parameters. In conclusion, the results of this study demonstrate the potential of using structural analysis parameters as input for HHV modeling, which is a promising approach for the field of biomass energy production. The development of the model ANN and the comparative analysis of the different models provide important insights for future research in this field. [ABSTRACT FROM AUTHOR]

The problem of microbial biofilms has come to the fore alongside food, pharmaceutical, and healthcare industrialization. The development of new antibiofilm products has become urgent, but it includes bioprospecting and is time and money-consuming. Contemporary efforts are directed at the pursuit of effective compounds of natural origin, also known as "green" agents. Mushrooms appear to be a possible new source of antibiofilm compounds, as has been demonstrated recently. The existing modeling methods are directed toward predicting bacterial biofilm formation, not in the presence of antibiofilm materials. Moreover, the modeling is almost exclusively targeted at biofilms in healthcare, while modeling related to the food industry remains under-researched. The present study applied an Artificial Neural Network (ANN) model to analyze the anti-adhesion and anti-biofilm-forming effects of 40 extracts from 20 mushroom species against two very important food-borne bacterial species for food and food-related industries—Listeria monocytogenes and Salmonella enteritidis. The models developed in this study exhibited high prediction quality, as indicated by high r2 values during the training cycle. The best fit between the modeled and measured values was observed for the inhibition of adhesion. This study provides a valuable contribution to the field, supporting industrial settings during the initial stage of biofilm formation, when these communities are the most vulnerable, and promoting innovative and improved safety management. [ABSTRACT FROM AUTHOR]

One of the essential factors for the selection of the drying process is energy consumption. This study intended to optimize the drying treatment of capers using convection (CD), refractive window (RWD), and vacuum drying (VD) combined with ultrasonic pretreatment by a comparative approach among artificial neural networks (ANN) and response surface methodology (RSM) focusing on the specific energy consumption (SEC). For this purpose, the effects of drying temperature (50, 60, 70 °C), ultrasonication time (0, 20, 40 min), and drying method (RWD, CD, VD) on the SEC value (MJ/g) were tested using a face-centered central composite design (FCCD). RSM (R2: 0.938) determined the optimum drying-temperature–ultrasonication-time values that minimize SEC as; 50 °C-35.5 min, 70 °C-40 min and 70 °C-24 min for RWD, CD and VD, respectively. The conduct of the ANN model is evidenced by the correlation coefficient for training (0.976), testing (0.971) and validation (0.972), which shows the high suitability of the model for optimising specific energy consumption (SEC). [ABSTRACT FROM AUTHOR]

This study aimed to investigate the drying kinetics of capers at different temperatures and to examine the morphological changes of capers during the drying and rehydration processes. Computer‐aided image processing and Artificial Neural Network models (ANN) were used to analyze the shrinkage and moisture ratio of capers (drying) and the expansion of capers (rehydration). Lewis, Page, Fick's law, and logarithmic models were investigated to describe the conventional drying kinetics of capers at 50, 60, and 70°C; the logarithmic model was shown to be the best describing model (r2: 0.9996, 0.9996 and 0.9981, respectively). Effective diffusivities varied between 1.91 × 10−10 and 2.62 × 10−10 m2/s for the temperature range. The activation energy was 14.572 kJ/mol. Image processing revealed that diameter reduction rates were 1 × 10−4 mm/s for 50 and 70°C and 7 × 10−5 mm/s for 60°C. ANN was applied using multilayer perceptron models with three layers (input: ANN1, hidden: ANN2, and output: ANN3) which were sufficiently valid for predicting the experimental parameters (r2: 0.9992, 0.9915, and 0.8484, respectively). All morphological properties were reduced with drying, and shrinkage of capers was increased proportionally with the moisture content. The Global Sensitivity Analysis recognized treatment time as the most influential parameter affecting the moisture ratio and the caper diameter changes. Practical applications: One of the major problems for humans has been to improve food preservation techniques for long‐term storage. The major scope of industry is the drying of fruits and/or vegetables to produce dried foods with high quality and a long shelf life. To the best of our knowledge, drying of capers regarding the drying kinetics, modeling and quality changes has not been published to date. In this study, goal was to better understand drying kinetics and geometric changes that occur to capers during the dehydration and rehydration processes at various drying temperatures. Quantitative information regarding geometrical changes to capers was supplied by the image processing of the acquired pictures, which enabled rapid monitoring of physical changes during dehydration and rehydration. The remarked kinetic model, ANN model, and Quantitative information regarding geometrical changes are valuable information for researchers studying on drying of food and large‐scale dryer designers. [ABSTRACT FROM AUTHOR]

Agricultural Parameters and Essential Oil Content Composition Prediction of Aniseed, Based on Growing Year, Locality and Fertilization Type - An Artificial Neural Network Approach Keywords: aniseed; essential oil; growing year; locality; fertilization; artificial neural network EN aniseed essential oil growing year locality fertilization artificial neural network 1722 16 11/17/22 20221101 NES 221101 1. [Extracted from the article]

Maize is the most widespread and, along with wheat, the most important staple crop in the Republic of Serbia, which is of great significance for ensuring national food security. With the increasing demand for food and forage, intensive agricultural practices have been adopted in the maize production systems. In this direction, considerable research efforts have been made to examine the effects of different types of cover crops as a green manure on maize productivity; however, no consistent conclusions have been reached so far. Therefore, the objective of the present study is to examine the possibility of predicting the effects of winter cover crops (CC) integrated with different management practices on the morphological traits, yield, and yield components of maize. The experiment was carried out on chernozem soil from 2016 to 2020 as a randomized complete block design arranged as a split-split-plot with three replicates. The pea as a sole crop (P) and the mixture of pea and triticale (PT) are sown as winter CC with the following subplots: (i) CC used as green manure, and (ii) CC used as forage and removed before maize sowing. The artificial neural network is used for exploring nonlinear functions of the tested parameters and 13 categorical input variables for modeling according to the following factors: CC, way of using CC, N fertilization, and year. The computed maximums of plant height, number of leaves, number of internodes, plant density, number of ears, grain yield, 1000-grain weight, hectolitre weight, dry matter harvest residue, harvest index, leaves percentage, stems percentage, and ears percentage are as follows: 232.3 cm; 9.7; 10.2; 54,340 plants ha−1; 0.9; 9.8 t ha−1; 272.4 g; 67.0 kg HL−1; 9.2 t ha−1; 0.52; 18.9%; 36.0%, and 45.1%, respectively. The optimal result is obtained with peas used as green manure, with 50 kg N ha−1 and in the climatic conditions of 2018. Consequently, maize production under subsequent sowing periods can be successfully optimized by adapting selected management options for higher yield accomplishment. [ABSTRACT FROM AUTHOR]

Miscanthus is a perennial energy crop that produces high yields and has the potential to be converted into energy. The ultimate analysis determines the composition of the biomass and the energy value in terms of the higher heating value (HHV), which is the most important parameter in determining the quality of the fuel. In this study, an artificial neural network (ANN) model based on the principle of supervised learning was developed to predict the HHV of miscanthus biomass. The developed ANN model was compared with the models of predictive regression models (suggested from the literature) and the accuracy of the developed model was determined by the coefficient of determination. The paper presents data from 192 miscanthus biomass samples based on ultimate analysis and HHV. The developed model showed good properties and the possibility of prediction with high accuracy (R2 = 0.77). The paper proves the possibility of using ANN models in practical application in determining fuel properties of biomass energy crops and greater accuracy in predicting HHV than the regression models offered in the literature. [ABSTRACT FROM AUTHOR]

Yeasts are considered an extraordinary alternative source of natural carotenoids and pigmented terpenoids with multiple applications. Production of carotenoids by yeast fermentation technology has many benefits; it is cost-effective, easily scalable, and safe. The aim of this research is the isolation of yeasts from natural resources and selection of the most potent bioagent for carotenoid production. Additionally, an upgraded carotenoid extraction protocol we established, which implies the testing of four methods for cell lysis (hydrochloric acid treatment, ultrasound treatment, milling treatment, and osmotic pressure treatment), three extraction methods (conventional extraction, ultrasound extraction, and conventional + ultrasound extraction), and three extraction solvents (acetone, isopropanol/methanol (50:50), and ethanol). For the first time, the obtained results were further modeled by an artificial neural network (ANN). Based on the obtained maximal carotenoid yield (253.74 ± 9.74 mg/100 g d.w) for the best-performing Rhodotorula mucilaginosa, the optimized extraction procedure involving milling treatment (for cell lysis) and conventional extraction with acetone (for carotenoid extraction) convincingly stood out compared to the other 35 tested protocols. Therefore, the selected carotenoid extraction protocol was verified with respect to its universality for all other yeast isolates, demonstrating its simplicity and effectiveness. [ABSTRACT FROM AUTHOR]

A novel rice-based snack enriched with chicory root flour (CRF) was developed by twin-screw extrusion. Chicory (Cichorium intybus L.) is one of the promising medicinal plants for the development of innovative food and may be considered a functional food ingredient. Central composite design (CCD) was employed to generate snack formulations by varying feed moisture (M, 16.3–22.5%), screw speed (SS, 500–900 rpm) and CRF content (20–40%). The optimization according to artificial neural network modeling and a genetic algorithm was applied to define optimal process conditions (17.6% moisture, 820 rpm and 24.1% of CRF) for obtaining the product with the highest expansion (3.34), crispiness (3.22 × 10−3), volume (2040 m3), degree of gelatinization (69.70%) and good color properties. Bulk density (110.33 g/L), density (250 kg/m3), and hardness (98.74 N) resulted in low values for the optimal sample. The descriptive sensory analysis evaluated low hardness and bitterness, with high crispiness for the optimal extrudate. This study points to the possibility of a novel chicory enriched extrudate production with desirable physicochemical and sensory properties. [ABSTRACT FROM AUTHOR]

Given that global amounts of waste are growing rapidly, it is extremely important to determine what amount of waste will be generated in the near future. Accurate waste forecasting is also important for planning and designing a sustainable municipal solid waste (MSW) management system. For that reason, there is a need to build a model to predict the amount of MSW generated in the near future. Based on previous research, artificial neural networks (ANN) show better results in predicting waste generation compared to other mathematical models. In this research, an ANN model using the iterative algorithm Broyden–Fletcher–Goldfarb–Shanno (BFGS) for the prediction of MSW fractions, based on the socio-demographic characteristics, economic and industrial data obtained in Croatia and summarized data of the member states of EU (EU-27 from 2020), showed good predictive capabilities. The coefficient of determination during the training cycle for the output variables; household and similar waste (HHS), paper and cardboard waste (PCW), wood waste (WW), textile waste (TW), plastic waste (PW) and glass waste (GW) were 0.993; 0.997; 0.999; 0.997; 0.998; and 0.998, respectively, while reduced chi-square, mean bias error, root mean square error, mean percentage error, average absolute relative deviation and sum of squared errors were found low. In this paper, Yoon′s method of interpretation shows the relationships between socio-demographic data and the amount of generated waste. The results indicate that the lowest level of education shows a negative impact on observed waste-types calculations, with a relative impact between −9.889 and −4.467%. The most pronounced positive impact on the calculation of HHS, PCW, WW, TW, PW and GW was observed for year variable, gross domestic product, exports of goods and services, imports of goods and services, wages and salaries, secondary income, arrivals in collective accommodation establishments, overnight stays in collective accommodation establishments and exports of petroleum and petroleum products to partner countries, with a relative influence of 4.063–7.028; 2828–4851; 5240–6197; 5.308–6.341; 4290–4810; 4533–5805; and 4.345–4.493, respectively. The obtained results indicate that the amount of HHS waste at the EU-27 level in 2025 will decrease by approximately 18% compared to the data from 2018. The quantities of other observed recyclable types of waste will increase by 34% for PCW, 310% for WW, 40% for TW, 276% for PW and about 67% for GW. The amount of waste generated provides the basic information needed to plan, operate and optimize the waste management system. It could also help in the transition to an environmentally friendly and economically profitable circular economy. The model created in this research could also help with the system of separate waste collection, which would lead to more efficient recycling and the achievement of the set goals for recycling 55% of municipal waste by 2025. [ABSTRACT FROM AUTHOR]

The present study investigated the effect of incorporating 10, 20, and 30% apple powder obtained by freeze-drying, and apple powder produced with osmotic pre-treatment in sugar beet molasses solution, into muffins. The powder was freeze-dried and introduced as a whole spelt wheat flour replacement in muffins. The obtained products were investigated for their chemical composition and technological properties, and were subjected to a sensory analysis as well as a consumer acceptance test. Increasing the substitution level from 0 to 30% apple powder lowered the protein, starch, and fat content, while moisture content, sugar, and cellulose showed the opposite trend. The sensory analysis results indicated that the addition of apple powder or apple powder with osmotic pre-treatment (apple OT+Lyo powder) to the ingredients of muffins positively affected the taste, smell, mastication, and appearance of the final product. Consumers rated the muffins with 30% apple OT+Lyo powder as the most acceptable. Principal component analysis, an artificial neural network, and global sensitivity analysis were utilized to differentiate among muffin samples, and to estimate the corresponding influence of the substitution of spelt flour with apple powder or apple OT powder on the observed quality and nutritional parameters of the muffins. [ABSTRACT FROM AUTHOR]

Artificial neural intelligence was established for the estimation, prediction, and optimization of many agricultural and food processes to enable enhanced and balanced utilization of fresh and processed fruits. The predictive capabilities of artificial neural networks (ANNs) are evaluated to estimate the phytochemical composition and the antioxidant and antimicrobial activity of horned melon (Cucumis metuliferus) pulp, peel, and seed. Using multiobjective optimization, the main goals were successively achieved through analysis of antimicrobial potential against sensitive microorganisms for peel (Bacillus cereus, Pseudomonas aeruginosa, Aspergillus brasiliensis, and Penicillium aurantiogriseum), pulp (Salmonella enterica subsp. enterica serotype Typhimurium), and seed samples (Saccharomyces cerevisiae and Candida albicans), and its connection with phytochemical and nutritional composition and antioxidant activity. The highly potent extracts were obtained from peels which represent a waste part with strong antioxidant and antifungal capacity. Briefly, the calculated inhibition zone minimums for sensitive microorganisms were 25.3–30.7 mm, while the optimal results achieved with carotenoids, phenolics, vitamin C, proteins, lipids, DPPH, ABTS, and RP were: 332.01 mg β-car/100 g, 1923.52 mg GAE/100 g, 928.15 mg/100 g, 5.73 g/100 g, 2.3 g/100 g, 226.56 μmol TE/100 g, 8042.55 μmol TE/100 g, and 7526.36 μmol TE/100 g, respectively. These results imply the possibility of using horned melon peel extract as an antioxidant and antifungal agent for food safety and quality. [ABSTRACT FROM AUTHOR]

Salvia sclarea L. or clary sage is cultivated worldwide in temperate and sub‐tropical climates, as an ornamental and essential oil (EO) bearing plant. EO is obtained from fresh spikes in full flowering stage and is recognized as an important commercial product for food, beverage and cosmetic industries. This study investigated the EO composition of S. sclarea grown in Serbia (Southeast Europe) obtained by two different methods, steam (SD) and hydrodistillation (HD). GC‐MS analysis identified oxygenated monoterpenes as the main class of compounds for all EOs (between 81.8% and 88.2% depending on the distillation process). The most abundant oxygenated monoterpenes were linalyl acetate and linalool. In addition, in vitro antimicrobial (modified resazurin microtitre‐plate assay) and antioxidant activities (DPPH· assay) and total polyphenol content of obtained EOs were also evaluated. According to the assay used for the evaluation of the antibacterial activity, Gram‐negative bacteria were more sensitive to S. sclarea EO in comparison to Gram‐positive bacteria. EOs exhibited low antioxidant capacity, below 3% neutralized DPPH· radicals, reaching up to approximately 400 µg AAE mL‐1. This study also investigated a possibility for predicting retention indices (RIs) of compounds isolated from EOs. In total, 78 experimentally obtained RIs were applied to construct the prediction model. The quantitative structure‐chromatographic retention relationship (QSRR) model was used to anticipate the experimentally obtained RIs. Five molecular descriptors were selected by factor analysis and genetic algorithm to predict RIs. The obtained accuracy of the QSRR model reached r2 =.912, which showed that these models might be applied for predicting retention indices. [ABSTRACT FROM AUTHOR]

BACKGROUND: Sunflower seeds are in the top five most abundant oilseeds in the world, as well as sunflower oil in the edible oils group. Recently, increasing attention has been paid to cold‐pressed sunflower oil because less processing is involved and no solvent is used. The present study was carried out to investigate dimensions (length, width, thickness), firmness, general (moisture content and hull content, mass of 1000 seeds), gravimetric (true and bulk density, porosity) and geometric characteristics (equivalent diameter, surface area, seed volume, sphericity) of 20 new sunflower hybrid seeds. Steps to determine most of these parameters are quite simple and easy since the process does not require long time or special equipment. RESULTS: Principal component analysis and cluster analysis confirmed differences in the mentioned characteristics between oily and confectionary sunflower hybrid seeds. One of the major differences between two groups of samples was in extraction oil yield. Mechanical extraction oil yield of the oily hybrid seeds was significantly (P ˂ 0.05) higher (from 68.72 ± 4.21% to 75.61 ± 1.99%) compared to confectionary hybrids (from 20.10 ± 2.82% to 39.91 ± 6.23%). Extraction oil yield values are known only after oil extraction. CONCLUSION: Knowledge of the extraction oil yield value before the mechanical extraction enables better management of the process. By application of the artificial neural network approach, an optimal neural network model was developed. The developed model showed a good generalization capability to predict the mechanical extraction oil yield of new sunflower hybrids based on the experimental data, which was a main goal of this paper. © 2021 Society of Chemical Industry. [ABSTRACT FROM AUTHOR]

Rapeseed losses during storage can lead to undesirable difficulties in oil and biodiesel production. In this paper, three artificial neural networks were created to anticipate the main quality parameters of thirteen rapeseed varieties - cultivars and hybrids (Brassica napus L.) - during drying and storage. The varieties, drying temperature, air velocity and drying time were used as inputs to the artificial neural network model to predict the changes in seed weight and moisture during the drying process. The moisture diffusivity and activation energy of the investigated rapeseed varieties were determined under convective drying. For the experiment, an on-site drying system was used at 40, 60 and 80 °C drying air temperature. The effective diffusivity ranged from: 7.947.10−10 to 1.459.10−8 m2/s (first drying period) and 4.716.10−10 to 8.611.10−9 m2/s (second drying period). The predicted Arrhenius constant and activation energy ranged from 17.169 to 42.546 kJ/mol (first drying period) and from 31.261 to 50.474 kJ/mol (second drying period). Seed oil content, free fatty acids and thousand seed weight were determined after drying at different temperatures and after 12 months of storage under the three different storage conditions. To predict these parameters after storage time, a multilayer perceptron model with three layers (input, hidden and output) for three artificial neural networks (ANNs) was used for modelling using the implemented drying parameters (such as: variety, drying temperature, air velocity and drying time, along with initial oil and free fatty acid content and storage type) were used. The prediction of the developed model was accurate enough for the prediction of the output parameters. The coefficients of determination ranged from 0.965 to 0.998 when predicting the weight and moisture of the rapeseed during the drying process and the oil and free fatty acid content and thousand grain weights after the 12 months storage period. • 13 rapeseed hybrids quality parameters were anticipated during drying and storage. • prediction of drying and storage parameters was performed using neural network model. • rapeseed varieties, drying temperature, air velocity and drying time were ANN inputs. • optimization of drying parameters was achieved through multi-object optimization. [ABSTRACT FROM AUTHOR]

The aim of this work was to investigate the changes in osmotically treated pork meat during rehydration process, using artificial neural network approach, compared to second order polynomial model (obtained using response surface methodology). Meat samples were osmotically treated in two different solutions: (1) sugar beet molasses and (2) saccharose-NaCl solution, at temperature of (23 ± 2) °C for 5 h. After being osmotically treated, meat samples were rehydrated at three constant temperatures (20 °C, 40 °C and 60 °C) during four different immersion durations (15 min, 30 min, 45 min and 60 min), and afterwards examined for mass and volume gain (dV), and for rehydration percentage (R). The maximum R was observed for 20 °C and 60 min (24.1% and 26.2% for solution 1 and 2, respectively), while the maximum dV was observed at 40 °C and 30 min (16.1% and 22.6% for solution 1 and 2, respectively). Second order polynomials used for prediction of R and dV showed good accuracy compared to experimental results (coefficient of determination, r², ranged between 99.171-93.665), while the best of five artificial neural network models gained r² in the range of 0.992-0.995 for R, and in the range of 0.976-0.988 for dV, for samples treated in solution 1 and 2. [ABSTRACT FROM AUTHOR]

As one of the greatest agricultural challenges, yield prediction is an important issue for producers, stakeholders, and the global trade market. Most of the variation in yield is attributed to environmental factors such as climate conditions, soil type and cultivation practices. Artificial neural networks (ANNs) and random forest regression (RFR) are machine learning tools that are used unambiguously for crop yield prediction. There is limited research regarding the application of these mathematical models for the prediction of rapeseed yield and quality. A four-year study (2015–2018) was carried out in the Republic of Serbia with 40 winter rapeseed genotypes. The field trial was designed as a randomized complete block design in three replications. ANN, based on the Broyden–Fletcher–Goldfarb–Shanno iterative algorithm, and RFR models were used for prediction of seed yield, oil and protein yield, oil and protein content, and 1000 seed weight, based on the year of production and genotype. The best production year for rapeseed cultivation was 2016, when the highest seed and oil yield were achieved, 2994 kg/ha and 1402 kg/ha, respectively. The RFR model showed better prediction capabilities compared to the ANN model (the r2 values for prediction of output variables were 0.944, 0.935, 0.912, 0.886, 0.936 and 0.900, for oil and protein content, seed yield, 1000 seed weight, oil and protein yield, respectively). [ABSTRACT FROM AUTHOR]

This study was primarily focused on the supercritical fluid extraction (SFE) of cherry seed oil and the optimization of the process using sequential extraction kinetics modeling and artificial neural networks (ANN). The SFE study was organized according to Box-Behnken design of experiment, with additional runs. Pressure, temperature and flow rate were chosen as independent variables. Five well known empirical kinetic models and three mass-transfer kinetics models based on the Sovová's solution of SFE equations were successfully applied for kinetics modeling. The developed mass-transfer models exhibited better fit of experimental data, according to the calculated statistical tests (R2, SSE and AARD). The initial slope of the SFE curve was evaluated as an output variable in the ANN optimization. The obtained results suggested that it is advisable to lead SFE process at an increased pressure and CO2 flow rate with lower temperature and particle size values to reach a maximal initial slope. [ABSTRACT FROM AUTHOR]

• 5 corn hybrids types were grown during 3 vegetation periods. • the corn was dried at 4 temperatures, using 2 different pre-treatments. • prediction of drying parameters was performed using neural network model. • optimization of drying parameters was achieved through multi-object optimization. Two artificial neural network (ANN) models were developed to predict the main quality parameters of the corn used for ethanol production. Five Croatian corn hybrids were evaluated in this study (introducing the hybrid type as the first input categorical variable for ANN modelling), grown during three vegetation periods (the second categorical variable), under two levels of agrotechnology (the third categorical variable), dried at four temperatures (the fourth input variable), using two different heating and pressure pre-treatments of corn kernels (the fifth variable for ANN calculation) in order to improve the properties of corn for ethanol production. The first model (ANN1) was used to predict the hectolitre weight, 1000-kernels weight, the gelatinisation rate, and the contents of: glucose, reducing sugars and ethanol during the drying process, according to the type of the corn hybrid and the drying temperature. The ANN2 model was developed to predict the corn weight and moisture during the process, based on the input parameters. The artificial neural network models gave a good fit to experimental data and were able to predict the output variables successfully, showing a reasonably good predictive capability (overall r2 for the corn kernel weight and moisture was 0.989, while r2 for other outputs was 0.856). On the basis of a developed ANN models, multi-objective optimization was performed showing the possible practical use in the corn kernel drying process. [ABSTRACT FROM AUTHOR]

• Oil extraction kinetics was fitted by empirical and mass-transfer models. • Kinetics of the process was highly affected by the process parameters. • Constant extraction rate period was described by initial mass-transfer rate. • ANN optimization was applied to achieve the highest initial mass-transfer rate. The aim of this study was the optimization of supercritical fluid extraction (SFE) of raspberry seed oil. Sequential extraction kinetic modelling and artificial neural networks (ANN) were used for this purpose. SFE was performed according to the broaden Box-Behnken experimental design with pressure, temperature and CO 2 flow rate as independent variables, while the influence of particle size on extraction kinetics and adjustable model parameters was additionally evaluated. Five empirical kinetic equations and mass-transfer model proposed by Sovová were utilized for extraction kinetics modelling. According to appropriate statistical parameters (R2 , SSE and AARD), the mass-transfer model exhibited the best fit of experimental data. The initial mass-transfer rate of extraction curve was used as a response variable in ANN optimization. SFE should be performed at elevated pressure and CO 2 flow rate, while temperature and particle size should be held at a lower level in order to achieve a maximal initial mass-transfer rate. [ABSTRACT FROM AUTHOR]

Screens of antioxidant activity (AA) of various natural products have been a focus of the research community worldwide. This work aimed to differentiate selected samples of Merlot wines originated from Montenegro, with regard to phenolic profile and antioxidant capacity studied by survival rate, total sulfhydryl groups and activities of glutathione peroxidase (GPx), glutathione reductase and catalase in H2O2–stressed Saccharomyces cerevisiae cells. In this study, DPPH assay was also performed. Higher total phenolic content leads to an enhanced AA under both conditions. The same trend was observed for catechin and gallic acid, the most abundant phenolics in the examined wine samples. Finally, the findings of an Artificial Neural Network (ANN) model were in a good agreement (r2 = 0.978) with the experimental data. All tested samples exhibited a protective effect in H2O2–stressed yeast cells. Pre-treatment with examined wines increased survival in H2O2–stressed cells and shifted antioxidative defense towards GPx–mediated defense. Finally, sensitivity analysis of obtained ANN model highlights the complexity of the impact that variations in the concentrations of specific phenolic components have on the antioxidant defense system. [ABSTRACT FROM AUTHOR]

• Precise prediction of mechano-chemically activated pyrophyllite quality via Artificial Neural Network. • Novel application of pyrophyllite in composite building materials. • Pyrophyllite as additional pozzolana in the Portland cement hydration. • Micronized pyrophyllite crystalline foila as micro-reinforcement in cement structure. The optimal outputs of pyrophyllite mechano-chemical activation in an ultra-centrifugal mill performing under different technological conditions were determined by analytical modeling and verified via Artificial Neural Network in order to be employed in the production of cement-based binders. Cluster Analysis and Principal Component Analysis were utilized in assessment of the effect of activation process parameters on the activated pyrophyllite quality. Artificial Neural Network which performed with high prediction accuracy, i.e. 0.914 during the training period, was sufficient for precise prediction of activated pyrophyllite quality in a wide range of processing parameters. The probability of utilization of observed activation products was estimated through interrelation of technological parameters (mesh size sieve, activation period, specific energy consumption) and acquired characteristics of pyrophyllite (grain diameter, specific surface area). The optimal products singled out from each activation sequence were used as mineral additives in the mix-designs of four cement binders (cement replacement portion was 30%). Influence of activated pyrophyllite additions on the cement chemistry, mineral phase compositions and microstructures of the cement binders were monitored by instrumental techniques (DTA/TGA, XRD, SEM). Activated pyrophyllite showed characteristics of pozzolana as it slightly accelerated early stages of hydration, decreased cement hydration energy and increased the quantity of cement mineral alite at later hydration stages. Micron-sized crystalline foila characteristic for mechanically activated pyrophyllite formed micro-reinforcement within cement binder microstructure. [ABSTRACT FROM AUTHOR]