Modeling of wheat soaking using two artificial neural networks (MLP and RBF)

Building a Kokumi Database and Machine Learning-Based Prediction: A Systematic Computational Study on Kokumi Analysis

Kokumi is a subtle sensation characterized by a sense of fullness, continuity, and thickness. Traditional methods of taste discovery and analysis, including those of kokumi, have been labor-intensive and costly, thus necessitating the emergence of computational methods as critical strategies in molecular taste analysis and prediction. In this study, we undertook a comprehensive analysis, prediction, and screening of the kokumi compounds. We categorized 285 kokumi compounds from a previously unreleased kokumi database into five groups based on their molecular characteristics. Moreover, we predicted kokumi/non-kokumi and multi-flavor compositions using six structure-taste relationship models: MLP-E3FP, MLP-PLIF, MLP-RDKFP, SVM-RDKFP, RF-RDKFP, and WeaveGNN feature of Atoms and Bonds. These six predictors exhibited diverse performance levels across two different models. For kokumi/non-kokumi prediction, the WeaveGNN model showed an exceptional predictive AUC value (0.94), outperforming the other models (0.87, 0.90, 0.89, 0.92, and 0.78). For multi-flavor prediction, the MLP-E3FP model demonstrated a higher predictive AUC and MCC value (0.94 and 0.74) than the others (0.73 and 0.33; 0.92 and 0.70; 0.95 and 0.73; 0.94 and 0.64; and 0.88 and 0.69). This data highlights the model's proficiency in accurately predicting kokumi molecules. As a result, we sourced kokumi active compounds through a high-throughput screening of over 100 million molecules, further refined by toxicity and similarity screening. Lastly, we launched a web platform, KokumiPD (https://www.kokumipd.com/), offering a comprehensive kokumi database and online prediction services for users.

Modeling liquid rate through wellhead chokes using machine learning techniques

Precise measurement and prediction of the fluid flow rates in production wells are crucial for anticipating the production volume and hydrocarbon recovery and creating a steady and controllable flow regime in such wells. This study suggests two approaches to predict the flow rate through wellhead chokes. The first is a data-driven approach using different methods, namely: Adaptive boosting support vector regression (Adaboost-SVR), multivariate adaptive regression spline (MARS), radial basis function (RBF), and multilayer perceptron (MLP) with three algorithms: Levenberg-Marquardt (LM), bayesian-regularization (BR), and scaled conjugate gradient (SCG). The second is a developed correlation that depends on wellhead pressure (Pwh), gas-to-liquid ratio (GLR), and choke size (Dc). A dataset of 565 data points is available for model development. The performance of the two suggested approaches is compared with earlier correlations. Results revealed that the proposed models outperform the existing ones, with the Adaboost-SVR model showing the best performance with an average absolute percent relative error (AAPRE) of 5.15% and a correlation coefficient of 0.9784. Additionally, the results indicated that the developed correlation resulted in better predictions compared to the earlier ones. Furthermore, a sensitivity analysis of the input variable was also investigated in this study and revealed that the choke size variable had the most significant effect, while the Pwh and GLR showed a slight effect on the liquid rate. Eventually, the leverage approach showed that only 2.1% of the data points were in the suspicious range.

Modeling based on machine learning to investigate flue gas desulfurization performance by calcium silicate absorbent in a sand bed reactor

Flue gas desulfurization (FGD) is a critical process for reducing sulfur dioxide (SO2) emissions from industrial sources, particularly power plants. This research uses calcium silicate absorbent in combination with machine learning (ML) to predict SO2 concentration within an FGD process. The collected dataset encompasses four input parameters, specifically relative humidity, absorbent weight, temperature, and time, and incorporates one output parameter, which pertains to the concentration of SO2. Six ML models were developed to estimate the output parameters. Statistical metrics such as the coefficient of determination (R2) and mean squared error (MSE) were employed to identify the most suitable model and assess its fitting effectiveness. The random forest (RF) model emerged as the top-performing model, boasting an R2 of 0.9902 and an MSE of 0.0008. The model's predictions aligned closely with experimental results, confirming its high accuracy. The most suitable hyperparameter values for RF model were found to be 74 for n_estimators, 41 for max_depth, false for bootstrap, sqrt for max_features, 1 for min_samples_leaf, absolute_error for criterion, and 3 for min_samples_split. Three-dimensional surface plots were generated to explore the impact of input variables on SO2 concentration. Global sensitivity analysis (GSA) revealed absorbent weight and time significantly influence SO2 concentration. The integration of ML into FGD modeling offers a novel approach to optimizing the efficiency and effectiveness of this environmentally crucial process.

Spectral-Based Classification of Genetically Differentiated Groups in Spring Wheat Grown under Contrasting Environments

The global concern about the gap between food production and consumption has intensified the research on the genetics, ecophysiology, and breeding of cereal crops. In this sense, several genetic studies have been conducted to assess the effectiveness and sustainability of collections of germplasm accessions of major crops. In this study, a spectral-based classification approach for the assignment of wheat cultivars to genetically differentiated subpopulations (genetic structure) was carried out using a panel of 316 spring bread cultivars grown in two environments with different water regimes (rainfed and fully irrigated). For that, different machine-learning models were trained with foliar spectral and genetic information to assign the wheat cultivars to subpopulations. The results revealed that, in general, the hyperparameters ReLU (as the activation function), adam (as the optimizer), and a size batch of 10 give neural network models better accuracy. Genetically differentiated groups showed smaller differences in mean wavelengths under rainfed than under full irrigation, which coincided with a reduction in clustering accuracy in neural network models. The comparison of models indicated that the Convolutional Neural Network (CNN) was significantly more accurate in classifying individuals into their respective subpopulations, with 92 and 93% of correct individual assignments in water-limited and fully irrigated environments, respectively, whereas 92% (full irrigation) and 78% (rainfed) of cultivars were correctly assigned to their respective classes by the multilayer perceptron method and partial least squares discriminant analysis, respectively. Notably, CNN did not show significant differences between both environments, which indicates stability in the prediction independent of the different water regimes. It is concluded that foliar spectral variation can be used to accurately infer the belonging of a cultivar to its respective genetically differentiated group, even considering radically different environments, which is highly desirable in the context of crop genetic resources management.

Customer decision-making analysis based on big social data using machine learning: a case study of hotels in Mecca

Big social data and user-generated content have emerged as important sources of timely and rich knowledge to detect customers' behavioral patterns. Revealing customer satisfaction through the use of user-generated content has been a significant issue in business, especially in the tourism and hospitality context. There have been many studies on customer satisfaction that take quantitative survey approaches. However, revealing customer satisfaction using big social data in the form of eWOM (electronic word of mouth) can be an effective way to better understand customers' demands. In this study, we aim to develop a hybrid methodology based on supervised learning, text mining, and segmentation machine learning approaches to analyze big social data on travelers' decision-making regarding hotels in Mecca, Saudi Arabia. To do so, we use support vector regression with sequential minimal optimization (SMO), latent Dirichlet allocation (LDA), and k-means approaches to develop the hybrid method. We collect data from travelers' online reviews of Mecca hotels on TripAdvisor. The data are segmented, and travelers' satisfaction is revealed for each segment based on their online reviews of hotels. The results show that the method is effective for big social data analysis and traveler segmentation in Mecca hotels. The results are discussed, and several recommendations and strategies for hotel managers are provided to enhance their service quality and improve customer satisfaction.

Investigation of rice performance characteristics: A comparative study of LR, ANN, and RSM

Parboiling is a type of heat pretreatment used in rice processing to reach higher head rice yield and improve the nutrition properties of raw rice. In this research, the goals were prediction and determination of optimum conditions for parboiled rice processing using the response surface method (RSM) as well as modeling the output values by linear regression (LR) and artificial neural networks (ANN). The parameters including steaming time (0, 5, 10, and 15 min), dryer type (solar and continuous dryers), and drying air temperature (35, 40, and 45°C) were employed as input values. In addition, the breakage resistance (BR) and head rice yield (HRY) were selected as output values. The ANN-based nonlinear regression, the multi-layer perceptron (MLP), and the radial basis function (RBF) have been developed to model the process parameters, as well as the central composite design (CCD) was conducted for optimization of BR and HRY values. The outputs of RBF network have been successfully applied to predict higher coefficient of determination of BR and HRY as 0.989 and 0.986, respectively, indicating the appropriateness of the model equation in predicting head rice yield and breakage resistance when the three processing variables (steaming time, dryer type, and drying air temperature) are mathematically combined. Also, the lower root mean square error (RMSE) was obtained for each one as 0.043 and 0.041. The optimum values of BR and HRY were obtained as 12.80 N and 67.3%, respectively, at 9.62 min and 36.9°C for a solar dryer with a desirability of 0.941. In addition, the same values were obtained as 14.50 N and 72.1%, respectively, at 8.77 min and 37.0°C for a continuous dryer with a desirability of 0.971.

Behavioral Investigation of Single Wall and Double Wall CNT Mixed Asphalt Adhesion Force Using Chemical Force Microscopy and Artificial Neural Networks

Flexible pavement deterioration due to moisture intrusion and aging is the key concern worldwide for highway engineers. However, this damage has not been properly investigated in detail due to lack of appropriate experimental and modeling techniques. Such lacking hinders the design of long-lasting pavements, as the effects of environmental damages are unknown, especially for modified asphalt. Therefore, the current study aims at determining a better approach for modeling asphalt adhesion damage using Artificial Neural Networks (ANNs). The Atomic Force Microscopy (AFM) test was deployed to determine the adhesion and cohesion forces of asphalt samples with varying contents of polymer and Antistripping Agents (ASAs). Two types of ANN models, namely multilayer perceptions (MLPs) and radial basis function neural network (RBFNN), were used in this effort. Two popular modifications, namely ensemble learning and hierarchical modeling, were also engaged to achieve convenient and accurate damage models. The analysis found that RBFNN was better suited for hierarchical models than MLP. RBFNN is preferred for aged and moisture-damaged samples which have less variation in their datasets. Hierarchical models are convenient to apply as they can be applied to any type of asphalt sample. However, they produced a small reduction in accuracy (less than 10%) as compared to other models. The accuracy of the hierarchical model was found to be satisfactory. The ensemble learning approach showed slight improvement in accuracy for all models ranging between 1–3%, i.e., 6–8 nN. This study recommends the use of hierarchical models, developed with ensemble learning, for prediction of asphalt damage. The results of the study will be helpful for researchers and practitioners working on pavement materials for developing prediction models to prepare a better mix design of polymer modified asphalt.

Comprehensive study on applications of artificial neural network in food process modeling

Artificial neural network (ANN) is a simplified model of the biological nervous system consisting of nerve cells or neurons. The application of ANN to food process engineering is relatively novel. ANN had been employed in diverse applications like food safety and quality analyses, food image analysis, and modeling of various thermal and non-thermal food-processing operations. ANN has the ability to map nonlinear relationships without any prior knowledge and predicts responses even with incomplete information. Every neural network possesses data in the form of connection weights interconnecting lines between the input to hidden layer neurons and weights of hidden to output layer neurons, which has a significant role in predicting the output data. The applications of ANN in different unit operations in food processing were described that includes theoretical developments using intelligent characteristics for adaptability, automatic learning, classification, and prediction. The parallel architecture of ANN resulted in a fast response and low computational time making it suitable for application in real-time systems of different food process operations. The predicted responses obtained by the ANN model exhibited high accuracy due to lower relative deviation and root mean squared error and higher correlation coefficient. This paper presented the various applications of ANN for modeling nonlinear food engineering problems. The application of ANN in the modeling of the processes such as extraction, extrusion, drying, filtration, canning, fermentation, baking, dairy processing, and quality evaluation was reviewed.HIGHLIGHTS1. This paper discusses application of ANN in different emerging trends in food process.2. Application of ANN to develop non-linear multivariate modeling is illustrated.3. ANNs have been shown to be useful tool for prediction of outcomes with high accuracy.4. ANN resulted in fast response making it suitable for application in real time systems.

Towards optimized drum composting: evaluation of the radial mixing performance of a model substrate on the laboratory scale

The rotating drum composter (RDC) is one of the most widespread reactor systems for biowaste treatment, worldwide. Nevertheless, knowledge on optimum operating conditions including, e.g. fill level, turning frequency, and mixing tool configuration is sparse. This study investigated the effect of static mixing tools (SMTs) on mixing in a rotating drum at high fill levels (60-80%). The methodological approach encompassed mixing experiments in a laboratory RDC using soaked wheat grains as a model material. The temporal course of material blending was quantified in terms of the entropy of mixing using digital image analysis. Experiments without SMTs showed the evolution of unmixed cores. With a single SMT, mixing was superior even at fill levels >70% while peripheral unmixed zones persisted when overly long SMTs were used. The results of this study may help to derive optimal process conditions for RDCs operated at high fill levels.

Optimization of microfluidic gallotannic acid extraction using artificial neural network and genetic algorithm

The current study presents the outcomes of modeling and optimizing extraction of gallotannic acid from Quercus leaves using a microfluidic system. In this study, the effects of various experimental parameters were investigated using the method of design expert. Number of experiments suggested is 31 by central composite design of Design Expert. The experimental results of design expert were analyzed by artificial neural network (ANN). Based on the results of ANN, independent variables experiment: temperature (T), flow rate ratio (FR) and pH have shown a negative effect on extraction yield (dependent variable), while the residence time (RT) has shown a positive effect. In trained network, ${R^2} = 0.9805$ and RMSE = 0.0166 shows good agreement between the predicted values of ANN and experimental results. Optimum extraction conditions, to reach maximum yield by genetic algorithms (GA), were FR = 0.53, RT = 26.4, pH = 2.06 and T = 21.44 ${R^2} = 0.9805$ . The extraction yield under the optimum predicated conditions was 96.4 %, which was well matched with the experimental value 95.01 % $\pm 0.63$ . Based on the obtained results, it was found that the ANN model could be employed successfully in estimating the gallotannic acid extraction efficiency using microfluidic extraction method.

Application of radial basis function neural network to predict soil sorption partition coefficient using topological descriptors

The soil sorption partition coefficient logK_oc is an indispensable parameter that can be used in assessing the environmental risk of organic chemicals. In order to predict soil sorption partition coefficient for different and even unknown compounds in a fast and accurate manner, a radial basis function neural network (RBFNN) model was developed. Eight topological descriptors of 800 organic compounds were used as inputs of the model. These 800 organic compounds were chosen from a large and very diverse data set. Generalized Regression Neural Network (GRNN) was utilized as the function in this neural network model due to its capability to adapt very quickly. Hence, it can be used to predict logK_oc for new chemicals, as well. Out of total data set, 560 organic compounds were used for training and 240 to test efficiency of the model. The obtained results indicate that the model performance is very well. The correlation coefficients (R2) for training and test sets were 0.995 and 0.933, respectively. The root-mean square errors (RMSE) were 0.2321 for training set and 0.413 for test set. As the results for both training and test set are extremely satisfactory, the proposed neural network model can be employed not only to predict logK_oc of known compounds, but also to be adaptive for prediction of this value precisely for new products that enter the market each year.

Emerging adsorptive removal of azo dye by metal-organic frameworks

Adsorptive removal of toxic compounds using advanced porous materials is one of the most attractive approaches. In recent years, the metal-organic frameworks (MOFs), a subset of advanced porous nano-structured materials, due to their unique characteristics are showing great promise for better adsorption/separation of various water contaminants. Given the importance of azo dye removal, as an important class of pollutants, this paper aims to review and summarize the recently published research on the effectiveness of various MOFs adsorbents under different physico-chemical process parameters in dyes adsorption. The effect of pH, the adsorption mechanism and the applicability of various adsorption kinetic and thermodynamic models are briefly discussed. Most of the results observed showed that the adsorption kinetic and isotherm of azo dyes onto the MOFs mostly followed the pseudo-second order and Langmuir models respectively. Also, the optimum pH value for the removal of majority of azo dyes by MOFs was observed to be in the range of ∼5-7.

Modeling of the lycopene extraction from tomato pulps

The inputs of this network were the concentration of pectinase and time of incubation, and the outputs were extracted lycopene and the activity of radical scavenging activity. Two different networks were designed for the process under the sonication and without it. For optimal network, networks' transfer functions and different learning algorithms were evaluated and the validity of each one was determined. Consequently, the feedforward neural network with function of logarithmic transfer, Levenberg Marquardt algorithm and 4 neurons in the hidden layer with the correlation coefficient of 0.96 and 0.99 were respectively observed for the treatments under sonication and without it, furthermore, root mean squared error and standard error values were obtained 0.46 and 0.22 respectively for the treatments under sonication and 0.77 and 0.38 without it as respectively optimal networks. The selected networks could determine the chosen responses, individually and in combined effect of both inputs as well (R(2) > 0.98).

Performance evaluation and modeling of a submerged membrane bioreactor treating combined municipal and industrial wastewater using radial basis function artificial neural networks

Treatment process models are efficient tools to assure proper operation and better control of wastewater treatment systems. The current research was an effort to evaluate performance of a submerged membrane bioreactor (SMBR) treating combined municipal and industrial wastewater and to simulate effluent quality parameters of the SMBR using a radial basis function artificial neural network (RBFANN). The results showed that the treatment efficiencies increase and hydraulic retention time (HRT) decreases for combined wastewater compared with municipal and industrial wastewaters. The BOD, COD, [Formula: see text] and total phosphorous (TP) removal efficiencies for combined wastewater at HRT of 7 hours were 96.9%, 96%, 96.7% and 92%, respectively. As desirable criteria for treating wastewater, the TBOD/TP ratio increased, the BOD and COD concentrations decreased to 700 and 1000 mg/L, respectively and the BOD/COD ratio was about 0.5 for combined wastewater. The training procedures of the RBFANN models were successful for all predicted components. The train and test models showed an almost perfect match between the experimental and predicted values of effluent BOD, COD, [Formula: see text] and TP. The coefficient of determination (R(2)) values were higher than 0.98 and root mean squared error (RMSE) values did not exceed 7% for train and test models.

Comparison of spectral and image morphological analysis for egg early hatching property detection based on hyperspectral imaging

The use of non-destructive methods to detect egg hatching properties could increase efficiency in commercial hatcheries by saving space, reducing costs, and ensuring hatching quality. For this purpose, a hyperspectral imaging system was built to detect embryo development and vitality using spectral and morphological information of hatching eggs. A total of 150 green shell eggs were used, and hyperspectral images were collected for every egg on day 0, 1, 2, 3 and 4 of incubation. After imaging, two analysis methods were developed to extract egg hatching characteristic. Firstly, hyperspectral images of samples were evaluated using Principal Component Analysis (PCA) and only one optimal band with 822 nm was selected for extracting spectral characteristics of hatching egg. Secondly, an image segmentation algorithm was applied to isolate the image morphologic characteristics of hatching egg. To investigate the applicability of spectral and image morphological analysis for detecting egg early hatching properties, Learning Vector Quantization neural network (LVQNN) was employed. The experimental results demonstrated that model using image morphological characteristics could achieve better accuracy and generalization than using spectral characteristic parameters, and the discrimination accuracy for eggs with embryo development were 97% at day 3, 100% at day 4. In addition, the recognition results for eggs with weak embryo development reached 81% at day 3, and 92% at day 4. This study suggested that image morphological analysis was a novel application of hyperspectral imaging technology to detect egg early hatching properties.

Estimativa da produtividade de trigo em função da adubação nitrogenada utilizando modelagem neuro fuzzy

Atualmente, novas técnicas de processamento de dados, tais como redes neurais, lógica nebulosa (fuzzy) e sistemas híbridos, são utilizadas para elaborar modelos de predição em sistemas complexos e estimar parâmetros desejados. Neste artigo investigou-se a habilidade de se desenvolver um modelo de inferência adaptativo neuro fuzzy para estimação da produtividade de trigo utilizando-se uma base de dados da combinação dos seguintes tratamentos: cinco doses de N (0, 50, 100, 150 e 200 kg ha-1); três fontes (Entec, sulfato de amônio e ureia); duas épocas de aplicação de N (na semeadura ou em cobertura) e dois cultivares de trigo (E21 e IAC 370), avaliados durante dois anos, em Selvíria, MS. Através dos dados de entrada e saída o sistema de inferência neuro fuzzy adaptativo apreende e posteriormente pode estimar um novo valor de produção de trigo com base em doses diferenciadas de N. O erro de predição da produtividade de trigo em função das cinco doses de N, obtido com o sistema neuro fuzzy, foi menor que o valor obtido utilizando-se uma aproximação quadrática. Os resultados mostraram que o sistema neuro fuzzy é viável para desenvolver um modelo de predição visando estimar a produtividade de trigo em função da dose de N.