Artificial Neural Network Network Research Articles

Optimizing reverse osmosis desalination from brackish waters: Predictive approach employing response surface methodology and artificial neural network models

A mathematical model frame has been developed to optimize the performance of reverse osmosis (RO) desalination in brackish waters with medium to high salt concentrations using response surface methodology (RSM) and artificial neural network (ANN), specifically catered towards efficiently operating RO desalination systems. The RSM model aims at predicting RO performance with second-order polynomials based on 15 experimental datasets. Inputs for RSM model include feed TDS concentration, feed water flow rate, and concentration-to-desalination ratio, while the outputs consider rejection, membrane flux, performance index, and specific energy consumption. The Genetic Algorithm optimized back-propagation Neural Network was employed to update network weights and biases, leading to an optimal ANN network structure of 3–10-4. A ratio of 70 % training, 15 % validation, and 15 % test data was chosen to establish an ANN model that predicts the performance of RO desalination. The ANN model demonstrated significantly higher prediction accuracy than the RSM model, with impressive correlation coefficients of 0.9936 for the performance index and 0.9932 for SEC prediction, and low RMSE of 0.85 for rejection. To maximize the performance index and minimize specific energy consumption, a two-step optimization method was further set up by applying the RSM model to initially determine optimal process conditions followed by the ANN model to enhance the accuracy of performance forecasts. Optimal process conditions were proposed for specific feed TDS scenarios, which involved setting a feed TDS concentration limit to meet drinking water standards.

Fault Detection Method based on Artificial Neural Network for 330kV Nigerian Transmission Line

This research focused on identifying various types of faults occurring on 330kV transmission lines through the use of artificial neural networks (ANN). A MATLAB model for the Gwagwalada-Katampe 330kV transmission line in Nigeria was implemented to generate fault datasets. Voltage and current fault parameters were utilized to train and simulate the ANN network architecture selected for each stage of fault detection. Four types of faults were considered, along with a fifth condition representing no fault. The results illustrated the success of the developed model in identifying various fault conditions and system parameters on the Gwagwalada-Katampe 330kV transmission line, modelled using MATLAB Simulink.

Mitigating Peak Sidelobe Levels in Pulse Compression Radar using Artificial Neural Networks

In this paper, Artificial Neural Networks (ANNs) are being considered to obtain low sidelobe pattern for binary codes and thereby to improve the performance of pulse compression radar. Pulse compression is a popular technique used for improving range resolution in the radar systems. This paper proposes a new approach for Pulse Compression using various types of ANN networks like Multi-Layer Perception (MLP), Recursive Neural Networks (RNN), Radial Basis Function (RBF) and Recurrent Radial Basis Function (RRBF) and a special class of Feed-Forward Wavelet Neural Network (WNN) with one input layer, one output layer and one hidden layer are being considered. Networks of 13-bit Barker code and extended binary Barker codes of 35, 55 and 75 length codes were used for the implementation and thereby to improve the performance of pulse compression radar. WNN-based networks using Morlet and Sigmoid activation function in hidden and output layers respectively, a special class of Artificial Neural Network is considered in this paper. The performance metrics used are Peak Sidelobe Ratio (PSLR), Integrated Sidelobe Ratio (ISLR) and Signal-to-Sidelobe Ratio (SSR). Further the performance in terms of range and Doppler resolution is also presented in this paper. Better performance in terms of sidelobe reduction can be achieved with ANNs compared to Autocorrelation Function (ACF) called as matched filter. If the sidelobe values are high there is possibility of masking weaker return signals and there by detection becomes difficult. From this paper it can be established that RRBF gives better result than other ANN networks. Further, WNN gives the best performance even compared with RRBF in terms of sidelobe reduction in pulse compression radar.

A diagnostic model based on bioinformatics and machine learning to differentiate bipolar disorder from schizophrenia and major depressive disorder

Bipolar disorder (BD) showed the highest suicide rate of all psychiatric disorders, and its underlying causative genes and effective treatments remain unclear. During diagnosis, BD is often confused with schizophrenia (SC) and major depressive disorder (MDD), due to which patients may receive inadequate or inappropriate treatment, which is detrimental to their prognosis. This study aims to establish a diagnostic model to distinguish BD from SC and MDD in multiple public datasets through bioinformatics and machine learning and to provide new ideas for diagnosing BD in the future. Three brain tissue datasets containing BD, SC, and MDD were chosen from the Gene Expression Omnibus database (GEO), and two peripheral blood datasets were selected for validation. Linear Models for Microarray Data (Limma) analysis was carried out to identify differentially expressed genes (DEGs). Functional enrichment analysis and machine learning were utilized to identify. Least absolute shrinkage and selection operator (LASSO) regression was employed for identifying candidate immune-associated central genes, constructing protein-protein interaction networks (PPI), building artificial neural networks (ANN) for validation, and plotting receiver operating characteristic curve (ROC curve) for differentiating BD from SC and MDD and creating immune cell infiltration to study immune cell dysregulation in the three diseases. RBM10 was obtained as a candidate gene to distinguish BD from SC. Five candidate genes (LYPD1, HMBS, HEBP2, SETD3, and ECM2) were obtained to distinguish BD from MDD. The validation was performed by ANN, and ROC curves were plotted for diagnostic value assessment. The outcomes exhibited the prediction model to have a promising diagnostic value. In the immune infiltration analysis, Naive B, Resting NK, and Activated Mast Cells were found to be substantially different between BD and SC. Naive B and Memory B cells were prominently variant between BD and MDD. In this study, RBM10 was found as a candidate gene to distinguish BD from SC; LYPD1, HMBS, HEBP2, SETD3, and ECM2 serve as five candidate genes to distinguish BD from MDD. The results obtained from the ANN network showed that these candidate genes could perfectly distinguish BD from SC and MDD (76.923% and 81.538%, respectively).

Experimentally and numerically verified behaviour of splice joints under multiple loading conditions and their capacity predictions using artificial neural networks

Splicing steel beams is a widely adopted practice, necessitated by span constraints that arise from challenges in transporting and handling longer beams, which may jeopardize the safety of the onsite workforce. The spliced joint must possess adequate strength and stiffness while effectively distributing the design loads without compromising the structural stability of the system. In this paper, an experimental study was carried out on various spliced joints, followed by finite element-based simulations on the validated girders. Extensive finite element analyses were conducted to investigate the influence of the width and thickness parameters of the splice plates under both three-point and four-point loading. Under both these loading conditions, superior performance was attained when a thicker flange splice and a thinner web splice were adopted. Strength improvements of 10% and 4% were achieved when the width of the flange splice (WFS) was dropped from 140 mm to 50 mm while maintaining a constant width of the web splice (WWS) at 270 mm, under three-point and four-point loading conditions respectively. Capacity enhancements of 16% and 23% were noted when WWS was raised from 60 mm to 270 mm while maintaining a constant WFS at 140 mm, under the above mentioned loading conditions, respectively. Lastly, the feasibility of artificial neural networks (ANNs) to predict the ultimate capacity of the splice joints was assessed, and it was verified that they could predict the ultimate load capacity with reasonable accuracy. The predicted load capacity of the splice joint outside the training set revealed that an appropriately trained and optimized ANN network could reliably estimate the strengths with a mean absolute error of less than 2%.

RNN-based pavement moduli prediction for flexible pavement design enhancement

In order to facilitate the effective implementation of the MEPDG, researchers concentrate on quantifying local material properties, with a particular emphasis on pavement layer moduli. The layer modulus is a critical parameter necessary for calculating pavement responses (stress, strain, and deflections) resulting from traffic loading. Accurately determining the layer modulus is crucial for enhancing pavement design as it directly impacts the required pavement layer thicknesses and associated costs. Backcalculation is a commonly used method for analyzing Falling Weight Deflectometer (FWD) data to determine pavement layer moduli, with Artificial Neural Networks (ANNs) being the traditional choice. However, ANNs have limitations in terms of convergence accuracy and generalization capability. The aim of this study is to improve the backcalculation of layer moduli to enhance pavement design. By utilizing FWD data, Recurrent Neural Network (RNN) was employed to address the limitations of conventional ANN. Both ANN and RNN networks were developed and trained using identical properties. The findings demonstrate that RNN achieved faster convergence and higher convergence accuracy compared to ANN. The RNN network generated reasonable and precise layer moduli values, exhibiting a determination coefficient (R) of 0.95 in comparison to the measured values, while the ANN network had an R-value of 0.79. The results indicate that the RNN network can learn the continuity pattern between deflection basin points, thereby enhancing the accuracy of FWD backcalculation.

Modelling of chemical processes using artificial neural network

ABSTRACT In this paper, a methodical strategy is put forth for the development of models for chemical processes by using an Artificial Neural Network (ANN). To show the effectiveness of the proposed methodology, three industrial chemical processes were considered. The intended work is to introduce the guideline for designing any ANN model by identifying the optimum number of neurons and hidden layers and coming up with the most suitable architecture for the neural network. The effect of viable parameters on predicting the specified parameter was evaluated using an ANN model. A systematic procedure adopted, ANN networks were designed to predict the boiler efficiency, frost thermal conductivity, and gas holdup under different operating conditions. At last, a comparative study on the experimental output and ANN approximated output for the three chemical processes was done. For developing the ANN model for boiler and frost conductivity, it was found that employing two layers provided a superior fit. The R² values for these fits were found to be 0.98877 and 0.9891, respectively. On the other hand, when configuring the column flotation model, a single layer with nine nodes was identified as the optimal ANN structure, yielding an excellent R² fit value of 0.99337.

Application of Deep Neural Network-Artificial Neural Network Model for Prediction Of Dew Point Pressure in Gas Condensate Reservoirs from Field-X in the Niger Delta Region Nigeria

Reservoirs of natural gas and gas condensate have been proposed as a potential for providing affordable and cleaner energy sources to the global population growth and industrialization expansion simultaneously. This work evaluates reservoir simulation for production optimization using Deep Neural network - artificial neural network (DNN-ANN) model to predict the dew point pressure in gas condensate reservoirs from Field-X in the Niger Delta Region of Nigeria. The dew-point pressure (DPP) of gas condensate reservoirs was estimated as a function of gas composition, reservoir temperature, molecular weight and specific gravity of heptane plus percentage. Results obtained show that the mean relative error (MRE) and R-squared (R2) are 0.99965 and 3.35%, respectively, indicating that the model is excellent in predicting DPP values. The Deep Neural Network - Artificial Neural Network (DNN-ANN) model is also evaluated in comparison to earlier models created by previous authors. It was recommended that the DNN - ANN model developed in this study could be applied to reservoir simulation and modeling well performance analysis, reservoir engineering problems and production optimization.

Application of Artificial Neural Network Base Enhanced MLP Model for Scattering Parameter Prediction of Dual-band Helical Antenna

Many design optimization problems have problems that seek fast, efficient and reliable based solutions. In such cases, artificial intelligence-based modeling is used to solve costly and complex problems. This study is based on the modeling of a multiband helical antenna using the Latin hypercube sampling (LHS) method using a reduced data enhanced multilayer perceptron (eMLP). The proposed helical antenna is dual-band and has resonance frequencies of 2.4 GHz and 2.75 GHz. The enhanced structure of the artificial neural network (ANN) was tested using 4 different training algorithms and a maximum of 10 different MLP architectures to determine the most suitable model in a simple and quick way. Then, performance comparison with other ANN networks was made to confirm the success of the model. Considering the high cost of antenna simulations, it is clear that the proposed model will save a lot of time. In addition, thanks to the selected sampling model, a wide range of modeling can be done with minimum data. When the target and prediction data are compared, it is seen that these data overlap to a large extent. As a result of the study, it was seen that the ANN modeling and the 125 samples used, were as accurate as an electromagnetic (EM) simulator for other input parameters in a wide range selected.

Sales rate forecasting of single-detached houses using artificial neural network technique

Although the predicted number of sold units per month is one of the most necessary information to study the feasibility of detached-housing estate projects, traditional forecasting methods are limited. The research objective was to apply the Artificial Neural Network (ANN) technique to develop a sales rate forecasting model by compiling factors from an appropriate literature review. Then, 100 housing project data were collected from market research reports and the projects' websites and analyzed using the ANN technique. The results showed the ANN network with 16 input nodes from 10 factors: Selling price, Number of bathrooms, Number of bedrooms, Distance from the main road, Distance from the bus stop, Distance from the expressway, Distance from the metro station, Distance from the gas station, Distance from the shopping mall, and Project location zone. The acquired model had a Root Mean Square Error (RMSE) of ±6.296, and the slope and R2 values of the linear regression analysis between the forecasted rate and the actual rate were 0.620 and 0.571, respectively. The findings guide real estate developers and academia on the factors affecting the sales rate and provide a decision support model for investment and design of projects and confirm the potential of ANN in solving the problem with limited numbers of data.

Prediction of characteristic points of single-peak flow curve through statistical technique and artificial neural network

ABSTRACT Artificial neural network (ANN) is an input–output modeling technique that has been successfully implemented in the field of material science to predict material behavior in terms of constitutive models. The material behavior considered here is the stress–strain behavior of the material at elevated temperatures that is characterized by a single-peak flow curve consisting of characteristic points viz. critical stress, peak stress and steady-state stress. The present work focuses on predicting these stress values along with the corresponding strain values through statistical regression analysis (SRA), ANN, and multi-layer complex neural network (MLCNN) with reasonable accuracy. The flow curves obtained from the axisymmetric compression test of 304LN austenitic stainless steel, performed at constant temperatures and constant strain rates, are used to train the models. The MLCNN has performed best while SRA has performed relatively worst with the current dataset due to rigorous and thorough computation. Both MLCNN and ANN are observed to perform better than SRA because of their non-parametric nature of handling data.

An artificial neural network and a combined capacitive sensor for measuring the void fraction independent of temperature and pressure changes for a two-phase homogeneous fluid

Void fraction plays a vital role in diverse industries like oil, petrochemical, etc., which involve a wide range of fluids, including two-phase and three-phase fluids. Various procedures are used for the measurement of the void fraction, with one of the most popular being capacitance-based sensors. The characteristics of the fluid inside the pipe affect the output of this type of sensor, and every property, such as temperature, pressure, and density, plays a role. This paper presents the use of an Artificial Neural Network (ANN) and a combined capacitance-based sensor to measure the void fraction of a two-phase air-water homogeneous fluid. The aim is to develop a system that can predict void fraction independent of temperature and pressure changes. To achieve this, the COMSOL Multiphysics software was used to design and simulate two widely used sensors, concave and ring, to create a combined capacitance sensor. Simulations were conducted for the implemented sensor in different temperature ranges (275–370 K) and pressure ranges (1–500 Bar). After a large number of simulations and producing 3780 data from the combined sensor, they were used as inputs to train the proposed MLP ANN network. The presented model provides a new metering system that can accurately estimate the amount of the void fraction of a two-phase air-water homogeneous fluid independent of temperature and pressure changes and had a low error which means the MAE is equal to 4.868.

Spectral purification improves monitoring accuracy of the comprehensive growth evaluation index for film-mulched winter wheat

In order to further improve the utility of unmanned aerial vehicle (UAV) remote-sensing for quickly and accurately monitoring the growth of winter wheat under film mulching, this study examined the treatments of ridge mulching, ridge–furrow full mulching, and flat cropping full mulching in winter wheat. Based on the fuzzy comprehensive evaluation (FCE) method, four agronomic parameters (leaf area index, above-ground biomass, plant height, and leaf chlorophyll content) were used to calculate the comprehensive growth evaluation index (CGEI) of the winter wheat, and 14 visible and near-infrared spectral indices were calculated using spectral purification technology to process the remote-sensing image data of winter wheat obtained by multispectral UAV. Four machine learning algorithms, partial least squares, support vector machines, random forests, and artificial neural network networks (ANN), were used to build the winter wheat growth monitoring model under film mulching, and accuracy evaluation and mapping of the spatial and temporal distribution of winter wheat growth status were carried out. The results showed that the CGEI of winter wheat under film mulching constructed using the FCE method could objectively and comprehensively evaluate the crop growth status. The accuracy of remote-sensing inversion of the CGEI based on the ANN model was higher than for the individual agronomic parameters, with a coefficient of determination of 0.75, a root mean square error of 8.40, and a mean absolute value error of 6.53. Spectral purification could eliminate the interference of background effects caused by mulching and soil, effectively improving the accuracy of the remote-sensing inversion of winter wheat under film mulching, with the best inversion effect achieved on the ridge–furrow full mulching area after spectral purification. The results of this study provide a theoretical reference for the use of UAV remote-sensing to monitor the growth status of winter wheat with film mulching.

Estimation of the Daily Production Levels of a Run-of-River Hydropower Plant Using the Artificial Neural Network

Renewable energy sources, as well as the studies being conducted regarding these energy sources, are becoming increasingly important for our world. In this manuscript, the daily energy production level of a small (15 MW) run-of-river hydropower plant (RRHPP) was estimated using the artificial neural network (ANN) model. In this context, the model utilized both meteorological data and HPP-related data. The input parameters of the artificial neural network included the daily total precipitation, daily mean temperature, daily mean water vapour pressure, daily mean relative humidity, and the daily mean river water elevation at the hydropower plant, while the only output parameter consisted of the total daily energy production. For the ANN, data from the four years between 2017 and 2020 were used for training purposes, while data from the first eight months of 2021 were used for testing purposes. Ten different ANN networks were tested. A comparison of the ANN data with the real data indicated that the model provided satisfying results. The minimum error rate was 0.13%, the maximum error rate was 9.13%, and the mean error rate was 3.13%. Furthermore, six different algorithms were compared with each other. It was observed that the best results were obtained from the Levenberg-Marquardt algorithm.This study demonstrated that the ANN can estimate the daily energy production of a run-of-river HPP with high accuracy and that this model can potentially contribute to studies investigating the potential of renewable energies.

Prediction of failure load in flat-joggle-flat co-cured composite joints using artificial neural networks

The current research examines the impact of bonding angle, bonding width, and adherend thickness on the failure load of flat-joggle-flat (FJF) co-cured composite joints. The primary goal of this work is to use an artificial neural network (ANN) to predict the failure load at the FJF joint. The experimental data was fed into the network, and the Colab tool was used to design and train the ANN network using a back-propagation algorithm. Experimental results revealed that, 8 mm to 12 mm adherend thickness, 25 mm adherend width, and a 10° to 15° bonding angle, gave maximum failure load. The ANN model estimated the predictive failure load with acceptable error. The results obtained from ANN, R2= 0.9803 for training andR2 = 0.9242 for testing the data, are within the acceptable error, so the experimental and ANN results are consistent and in good agreement.

Application of Artificial Neural Networks for Modelling and Control of Flux Decline in Cross-Flow Whey Ultrafiltration

This study is part of the re-valorisation of the dairy waste industry through the use of membrane ultrafiltration (UF), in order to recover whey proteins and remove as much water as possible from the permeate. This study aimed to predict and control the permeate flux decline in cross-flow whey UF through a step procedure, and to compare different Artificial Neural Networks (ANNs), followed by a genetic algorithm (GA), as the optimization strategy. Models were developed in Matlab® Neural Network Toolbox. ANNs of one or two hidden layers were trained and simulated. A trial-and-error procedure identified the best network based on its performance values. The networks were trained through a selected set of experimental data obtained for lab-scale hollow-fibre membrane modules used to re-value scotta, the final waste of the dairy industry. The operating conditions considered as the input of the ANN were: operating time (top), sampling time (tsample), cross-flow velocity (CFV) and transmembrane pressure (TMP), while the output of the network was exclusively the normalized permeate flux (Jn). GA optimization was carried out to the following range of operating conditions to reach the best performances and to manage the fouling effect: 225 < top < 300 min, 8.33 < tsample < 15.9 min, 6.25 < CFV < 8.33 L/min, and TMP equal to 1.33 bar, otherwise it can be ignored. In fact, it has been noted that the networks with only three inputs, without TMP, predict and control Jn output better. Moreover, considering the normalized flux, it was possible to ignore some other important operating conditions, such as the membrane geometry. Consequently, the proposed general solution could also be used for other kinds of membrane applications. Finally, a hybrid approach among the ANN networks and a theoretical model was also used to better predict the resistance trend. It also returned more evident correspondence results than the ANN simulation alone, especially in the initial drop of Jn. The use of the theoretical part in the hybrid approach acts as a filter and returned the following order of significance of the operational input conditions on the resistance: top, tsample, CFV and TMP.

Hybrid Techniques for Diagnosing Endoscopy Images for Early Detection of Gastrointestinal Disease Based on Fusion Features

Gastrointestinal (GI) diseases, particularly tumours, are considered one of the most widespread and dangerous diseases and thus need timely health care for early detection to reduce deaths. Endoscopy technology is an effective technique for diagnosing GI diseases, thus producing a video containing thousands of frames. However, it is difficult to analyse all the images by a gastroenterologist, and it takes a long time to keep track of all the frames. Thus, artificial intelligence systems provide solutions to this challenge by analysing thousands of images with high speed and effective accuracy. Hence, systems with different methodologies are developed in this work. The first methodology for diagnosing endoscopy images of GI diseases is by using VGG-16 + SVM and DenseNet-121 + SVM. The second methodology for diagnosing endoscopy images of gastrointestinal diseases by artificial neural network (ANN) is based on fused features between VGG-16 and DenseNet-121 before and after high-dimensionality reduction by the principal component analysis (PCA). The third methodology is by ANN and is based on the fused features between VGG-16 and handcrafted features and features fused between DenseNet-121 and the handcrafted features. Herein, handcrafted features combine the features of gray level cooccurrence matrix (GLCM), discrete wavelet transform (DWT), fuzzy colour histogram (FCH), and local binary pattern (LBP) methods. All systems achieved promising results for diagnosing endoscopy images of the gastroenterology data set. The ANN network reached an accuracy, sensitivity, precision, specificity, and an AUC of 98.9%, 98.70%, 98.94%, 99.69%, and 99.51%, respectively, based on fused features of the VGG-16 and the handcrafted.

AI Techniques of Dermoscopy Image Analysis for the Early Detection of Skin Lesions Based on Combined CNN Features.

Melanoma is one of the deadliest types of skin cancer that leads to death if not diagnosed early. Many skin lesions are similar in the early stages, which causes an inaccurate diagnosis. Accurate diagnosis of the types of skin lesions helps dermatologists save patients' lives. In this paper, we propose hybrid systems based on the advantages of fused CNN models. CNN models receive dermoscopy images of the ISIC 2019 dataset after segmenting the area of lesions and isolating them from healthy skin through the Geometric Active Contour (GAC) algorithm. Artificial neural network (ANN) and Random Forest (Rf) receive fused CNN features and classify them with high accuracy. The first methodology involved analyzing the area of skin lesions and diagnosing their type early using the hybrid models CNN-ANN and CNN-RF. CNN models (AlexNet, GoogLeNet and VGG16) receive lesions area only and produce high depth feature maps. Thus, the deep feature maps were reduced by the PCA and then classified by ANN and RF networks. The second methodology involved analyzing the area of skin lesions and diagnosing their type early using the hybrid CNN-ANN and CNN-RF models based on the features of the fused CNN models. It is worth noting that the features of the CNN models were serially integrated after reducing their high dimensions by Principal Component Analysis (PCA). Hybrid models based on fused CNN features achieved promising results for diagnosing dermatoscopic images of the ISIC 2019 data set and distinguishing skin cancer from other skin lesions. The AlexNet-GoogLeNet-VGG16-ANN hybrid model achieved an AUC of 94.41%, sensitivity of 88.90%, accuracy of 96.10%, precision of 88.69%, and specificity of 99.44%.

L-proline enrichment of bread enhances its KFO: Assessment of freshness by electronic nose technology and an ANN prediction model

Freshness-aroma or sweet “popcorn”- like aroma of white bread was enhanced by increasing the formation of 2-acetyl-1-pyrroline (2-AP), a key food odorant by addition of its precursor molecule, viz. L-proline (1.2% w/w) to the bread-dough. Overall sensorial acceptability scores, physico-chemical properties, aroma and freshness-stability were all significantly (p < 0.05) enhanced in bread; while the acrylamide content was concomitantly reduced consequent to this amino acid enrichment. Employment of hurdle technology resulted in a 4-fold enhanced freshness-stability of bread (E-7 with 1.2% L-proline added) vis-à-vis the experimental control and commercially available bread samples. In this investigation, electronic nose along with artificial neural network (ANN) was employed to effectively discriminate the test sample (E-7) from the experimental control ones with respect to freshness-stability, for a large number of sample sets. The optimum topology (ANN network) of 8-15-5 rapidly and accurately predicted the shelf-life of E-7, with high correlation (R2 = 0.9785) between the predicted and experimental values. Mahalanobis distance method was adopted to determine ‘freshness index’ of bread by correlating it with its 2-AP content (quantified by gas chromatography) which allowed unambiguous-cum-rapid prediction of this freshness molecular marker in the bread samples during storage. We envisage that ANN coupled with e-nose technology would allow rapid-cum-accurate detection of freshness status of bread for bakery industries forgoing invasive, time-intensive, conventional biochemical analysis.

Applying regression techniques to determine mathematical equations of exergy, electricity, and energy values of photovoltaic thermal collector

The highlight of this study is to produce mathematical equations that can calculate the electricity, energy, and exergy efficiency values of an air-type photovoltaic-thermal (PV-T) solar collector with the help of a regression-based artificial intelligence method. Contrary to classical predictive artificial intelligence models, the Elastic.Net regression method, which can produce a linear equation for the modeled parameter, was used. Six different data sets were obtained, with the trials carried out in two months for the PV-T efficiency values. The Elastic Net algorithm produced energy, electrical, and exergy efficiency equations with the first, third, and fifth datasets. Comparisons were made between experimental thermal efficiency ratings and the output of efficiency formulas. The other three data sets were then subjected to efficiency equations, and the results were contrasted with the experimental values. The thermal efficiency equations predicted the experimental data in the data sets 1, 3, 5 and, 2, 4, 6 with mean MAPEs of 2.9% and 4.16%, respectively. The experimental values in both group data sets have been said to be comparable to the efficiency values discovered using the equations. As a result, it is anticipated that the efficiency equations developed can be used in various experimental configurations or flat solar collectors. Additionally, prediction models were created utilizing datasets 1, 3, and 5 using the artificial neural network (ANN) technique. The best ANN network structure was obtained using different network types, training algorithms, transfer functions, and layer-neuron numbers in ANN models.