Article
Computer Science, Information Systems
Tirana Noor Fatyanosa, Masayoshi Aritsugi
Summary: The study proposes a diversity-guided genetic algorithm-convolutional neural network (DGGA-CNN) that facilitates the search process by exploration and exploitation while preserving population diversity, guided by the average pairwise Hamming distance. The DGGA fully handles the architecture of the CNN and demonstrates its capability and efficiency in comparison with other methods in tests on suggestion mining and Twitter airline datasets.
Article
Green & Sustainable Science & Technology
Monirahmad Rasoolizadeh, Mashallah Salarpour, Mahmoud Ahmadpour Borazjani, Amin Nikkhah, Hamid Mohamadi, Valiollah Sarani
Summary: This study applied a hybrid method to optimize five tropical crop production systems and found that managing input consumption can improve the exergy efficiency of the systems.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2022)
Article
Green & Sustainable Science & Technology
Monirahmad Rasoolizadeh, Mashallah Salarpour, Mahmoud Ahmadpour Borazjani, Amin Nikkhah, Hamid Mohamadi, Valiollah Sarani
Summary: In this study, a hybrid exergy analysis approach was used to optimize five tropical crop production systems. The evaluation using Cumulative Degree of Perfection and Renewability Index showed that banana had the highest exergy efficiency. Optimization results revealed a noticeable enhancement in exergy efficiency for all tropical crop production systems in the optimized mode.
SUSTAINABLE ENERGY TECHNOLOGIES AND ASSESSMENTS
(2022)
Article
Astronomy & Astrophysics
Isidro Gomez-Vargas, Joshua Briones Andrade, J. Alberto Vazquez
Summary: The applications of artificial neural networks in cosmology have been successful due to their ability to model large datasets and nonlinear functions. However, their use can be controversial due to the potential for inaccurate results when hyperparameters are not carefully selected. In this paper, the use of genetic algorithms to find optimal hyperparameter combinations for neural networks is proposed and tested on three different cosmological cases, showing improved performance compared to a standard grid method.
Article
Computer Science, Artificial Intelligence
Zhenyu Fang, Jinchang Ren, Stephen Marshall, Huimin Zhao, Song Wang, Xuelong Li
Summary: This paper optimizes the topology of DenseNet using a genetic algorithm to reduce unnecessary convolutional kernels, and also introduces a pretrained weight inheritance method to significantly reduce the time consumption of the genetic process. Experimental results show that the proposed model achieves comparable accuracy to state-of-the-art models while reducing the number of parameters.
PATTERN RECOGNITION
(2021)
Article
Mathematics
Costel Anton, Florin Leon, Marius Gavrilescu, Elena-Niculina Dragoi, Sabina-Adriana Floria, Silvia Curteanu, Catalin Lisa
Summary: In the brick manufacturing industry, researchers are concerned about reducing energy consumption. This study modified the manufacturing mix by introducing sunflower seed husks and sawdust, and used artificial intelligence tools along with optimization algorithms inspired by human and virus behaviors. The results showed that by adding a certain amount of sunflower seed husks and sawdust, the emissions of CH4 and CO can be minimized.
Article
Chemistry, Physical
Bartosz Miller, Leonard Ziemianski
Summary: This study investigates the application of surrogate models in multi-objective optimization of composite shells. By using deep neural networks to approximate the relationships between input parameters and key metrics, incorporating mode shape identification, and employing network ensembles, the efficiency and accuracy of the optimization process are enhanced.
Article
Chemistry, Multidisciplinary
Carlos Guzman Martinez, Fabricio Napoles Rivera, Agustin Castro-Montoya
Summary: The study presents a multi-objective optimization of different ethanol dehydration processes with objectives of maximizing ethanol purity and net profit, while minimizing CO2 emissions. A method using MATLAB, Visual Basic, and Aspen Plus to solve the multi-objective design problem is proposed. It is found that reactive dehydration systems outperform conventional azeotropic distillation, and the inclusion of an organic Rankine cycle has potential benefits in utilizing the exothermic reactions for generating electricity.
SEPARATION SCIENCE AND TECHNOLOGY
(2021)
Article
Food Science & Technology
Izabela Staniszewska, Konrad W. Nowak, Danuta Zielinska, Iwona Konopka, Magdalena Zielinska
Summary: The aim of this study was to determine the optimal parameters of pulsed vacuum osmotic dehydration (PVOD) of fermented beetroot slices. The response surface methodology (RSM) was employed to optimize PVOD and improve the efficiency of the process. The optimum parameters were found to be a temperature of 20℃, sugar concentration of 60%, vacuum impregnation time of 10 minutes, and slice thickness of 6 mm.
FOOD AND BIOPROCESS TECHNOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Marco Vannucci, Valentina Colla
Summary: The paper presents an approach to designing the chemical composition of steel using neural networks and genetic algorithms to achieve desired hardenability behavior while considering other constraints. The proposed method utilizes a neural-network-based predictor of the Jominy hardenability profile and formulates an optimization problem to meet accuracy requirements and constraints. The results demonstrate the efficiency, flexibility, and customization of the approach for user demands and production objectives.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Juncheng Gao, Menad Nait Amar, Mohammad Reza Motahari, Mahdi Hasanipanah, Danial Jahed Armaghani
Summary: This paper introduces two new prediction tools for peak shear strength in rock slopes, utilizing neural networks and meta-heuristic algorithms. The RBFNN-GWO model demonstrated superior accuracy and convergence speed compared to other models, offering efficient support for rock engineers in slope design processes.
ENGINEERING WITH COMPUTERS
(2022)
Article
Chemistry, Multidisciplinary
Sabina-Adriana Floria, Marius Gavrilescu, Florin Leon, Silvia Curteanu
Summary: This paper utilizes various biologically inspired optimization algorithms to train multilayer perceptron neural networks and generate good regression models. By combining different optimization algorithms into a hybrid ensemble optimizer, the search capability is improved. Experimental results show that the neural networks generated by the hybrid multiple elite strategy are the most dependable regression models.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Artificial Intelligence
Mohammad Hassan Tayarani Najaran
Summary: This paper presents a genetic programming approach to optimize the structure of Convolutional Neural Networks (CNNs) for diagnosing COVID-19 cases through X-ray images. A graph representation is proposed for CNN architecture, and evolutionary operators such as crossover and mutation are designed for this representation. The algorithm optimizes both the skeleton and numerical parameters of the CNN architectures in a co-evolutionary scheme.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2023)
Article
Engineering, Chemical
Mariana Aguirre-Garcia, Orlenda Cortes-Zavaleta, Paola Hernandez-Carranza, Hector Ruiz-Espinosa, Carlos Enrique Ochoa-Velasco, Irving Israel Ruiz-Lopez
Summary: This study investigated the modeling of mass transfer and changes in antioxidant capacity of papaya cubes infused with a roselle extract/sucrose solution. A novel semi-analytical solution for the diffusion equation considering product shrinkage was proposed. The results showed that considering papaya shrinkage significantly affected the diffusivities of the migrating species.
JOURNAL OF FOOD ENGINEERING
(2023)
Article
Food Science & Technology
Mohamed Ghellam, Oscar Zannou, Hojjat Pashazadeh, Charis M. Galanakis, Turki M. S. Aldawoud, Salam A. Ibrahim, Ilkay Koca
Summary: Effects of syrup concentration and temperature variation are the most significant factors impacting the independent variables of berries during osmotic dehydration. Fruit-to-syrup ratio only appears to have a significant effect on water loss.
Article
Chemistry, Applied
Esmaeel Charpashlo, Behrouz Ghorani, Mohebbat Mohebbi
Summary: Electrospinning was used to design a multilayer sandwich structure to enhance the bioaccessibility of lycopene in the small intestine. The encapsulation efficiencies of lycopene in the sandwich samples were high and the release behavior exhibited Fickian diffusion characteristics.
FOOD HYDROCOLLOIDS
(2021)
Article
Food Science & Technology
Mohammad Ebrahim Goharjoo, Mohammad Reza Edalatian Dovom, Fakhri Shahidi, Farideh Tabatabaei Yazdi, Mohammad Javad Varidi
Summary: The study found that 4% ginger had a positive effect on the growth of lactic acid bacteria in fermented carrot. 27 isolates were identified belonging to three genera and six species. The application of ginger and yogurt serum could potentially enhance their industrial use for fermented carrot products.
JOURNAL OF FOOD PROCESSING AND PRESERVATION
(2021)
Article
Food Science & Technology
Mohammad Reza Salahi, Mohebbat Mohebbi
Summary: The aim of this study was to generate soy milk foam using whey protein concentrate and hydrocolloids, and investigate factors affecting foamability and foam stability. Results showed that foam stability was enhanced by the addition of guar gum and xanthan gum, while overrun was highest at 5 degrees C and stability was highest at 75 degrees C. Viscoelastic properties were observed in the soy milk foam, and foam stability was found to be directly related to rheological parameters.
LWT-FOOD SCIENCE AND TECHNOLOGY
(2021)
Article
Food Science & Technology
Arash Ghaitaranpour, Mohebbat Mohebbi, Arash Koocheki
Summary: The study utilized an agent-based model and Netlogo software to describe the oil penetration process during hot air frying, revealing that the penetration process consists of three main steps and the structure of the crust affects the oil absorption pattern.
FOOD RESEARCH INTERNATIONAL
(2021)
Article
Food Science & Technology
Shiva Ghaedrahmati, Fakhri Shahidi, Sahar Roshanak, Marzieh Nassiri Mahallati
Summary: Using Jaban watermelon environmental pollutants to produce economically and nutritionally valuable by-products. Investigating macro- and micro compounds in watermelon exocarp powder. Producing low calorie and high nutritional value ice cream by replacing cream with WEP.
JOURNAL OF FOOD PROCESSING AND PRESERVATION
(2021)
Article
Food Science & Technology
Meysam Komijani, Mohebbat Mohebbi, Behrouz Ghorani
Summary: In this study, tri-layered nanofibers were used to enhance the bioaccessibility of lycopene. The optimal nanofiber for trapping lycopene was obtained with a BSG to PVA ratio of 70:30. The encapsulation efficiency of lycopene was in the range of 81.7-92.26%. The thermal resistance of lycopene was improved in the tri-layered nanofibers.
LWT-FOOD SCIENCE AND TECHNOLOGY
(2022)
Article
Food Science & Technology
Amir Tavakoli Lahijani, Fakhri Shahidi, Mahmoud Habibian, Arash Koocheki, Behdad Shokrollahi Yancheshmeh
Summary: In this study, the effects of nonthermal plasma treatment on sunn pests-damaged wheat flour were investigated. The results showed that plasma treatment improved the physicochemical, rheological, functional, and microstructural properties of the flour, as well as the dough stability.
FOOD SCIENCE & NUTRITION
(2022)
Article
Food Science & Technology
Mohammad Tarahi, Fakhri Shahidi, Sara Hedayati
Summary: A novel starch was isolated from bitter vetch and compared with conventional starches. Bitter vetch starch showed higher levels of amylose, pasting temperature, and viscosity, making it a promising new source of starch.
INTERNATIONAL JOURNAL OF FOOD SCIENCE AND TECHNOLOGY
(2022)
Article
Polymer Science
Mohammad Tarahi, Sara Hedayati, Fakhri Shahidi
Summary: Understanding the interactions between starch and protein in food systems is crucial for obtaining products with desired functional properties. Adding mung bean protein isolate can enhance the rheological and textural properties of native corn starch.
Article
Chemistry, Applied
Afshin Faridi Esfanjani, Mohebbat Mohebbi
Summary: This study aimed to decrease the salt level in bread while maintaining its desirable properties by using the strategy of odor-taste-texture interactions. The findings showed that the interactions of gel emulsifier with taste in the bread matrix increased porosity and softness perception, which improved the sensory properties of low-salt bread.
Article
Food Science & Technology
Bahareh Saboori, Fakhri Shahidi, Sara Hedayati, Ali Javadmanesh
Summary: The present study isolated and identified bacteria from kashk samples in Iran, and evaluated their probiotic properties. The results showed that Pediococcus pentosaceus VNK-1 (KK4) and Pediococcus pentosaceus H11 (KF3) exhibited better probiotic properties compared to other isolates.
Article
Food Science & Technology
Mohammad Tarahi, Malihe Mohamadzade Fakhr-davood, Shiva Ghaedrahmati, Sahar Roshanak, Fakhri Shahidi
Summary: The study investigates the nutritional content and antioxidant activity of Jaban watermelon exocarp powder, and evaluates the physicochemical and sensory properties of gummy candies prepared with different concentrations of the powder. The results show that higher concentration of JWE powder improves the moisture content, acidity, brightness, viscosity, and hardness of the gummy candies. The gummy candy with 35% JWE powder, 0.75% citric acid, and 0.5% agar gum receives the highest score from panelists.
Article
Food Science & Technology
Jouhaina Hadree, Fakhri Shahidi, Mohebbat Mohebbi, Mohammadreza Abbaspour
Summary: This study investigated the effects of pomegranate peel extract concentration, drying temperature, and feed flow rate on the properties of pomegranate juice powder produced by spray drying. The optimal conditions for powder production were determined using response surface methodology. The results showed that the phenolic extract concentration, drying temperature, and feed flow rate significantly influenced various properties of the powder. The study concluded that the spray drying conditions did not negatively affect the phenolic compound content in pomegranate powder, making it suitable for use as a food additive or dietary supplement.
Article
Food Science & Technology
Ali Heydari, Mohebbat Mohebbi, Arash Ghaitaranpour
Summary: The objective of this research was to evaluate the effects of different fat types on a traditional gluten-free rice-based cookie. The data showed that the dough prepared with bakery and olive oil had different hardness values, and after baking, the samples prepared with olive oil had the highest hardness. The image processing results showed that the cookie prepared with bakery fat had the highest surface color uniformity.
INTERNATIONAL JOURNAL OF FOOD ENGINEERING
(2023)
Article
Polymer Science
Mohammad Tarahi, Fakhri Shahidi, Sara Hedayati
Summary: The aim of this study was to investigate the effect of mung bean protein isolate (MBPI) on the physicochemical, pasting, and thermal properties of native corn starch (NCS). The results showed that increasing MBPI concentration led to higher swelling power, water absorbance capacity, and solubility of NCS. Additionally, the addition of MBPI lowered the pasting temperature, final viscosity, and setback, while increasing the peak viscosity and breakdown. The thermal properties of NCS/MBPI gels exhibited higher onset, peak, and conclusion temperatures, but lower gelatinization enthalpy, with increasing MBPI concentration. Fourier transform infrared spectroscopy (FT-IR) analysis indicated a decrease in hydrogen bond content within starch upon addition of MBPI. Furthermore, the freeze-thaw shock test showed reduced syneresis in NCS-MBPI composites.