Multilayer Perceptron Neural Network Research Articles

Design of a novel intelligent adaptive fractional-order proportional-integral-derivative controller for mitigation of seismic vibrations of a building equipped with an active tuned mass damper

The primary objective of this study is to introduce a novel adaptive fractional order proportional–integral–derivative (FOPID) controller. The adaptive FOPID controller’s parameters are dynamically adjusted in real-time using five distinct multilayer perceptron neural networks. The extended Kalman filter (EKF) is employed to facilitate the parameter-tuning process. A multilayer perceptron neural network, trained using the error Backpropagation algorithm, is employed to identify the structural system and estimate the plant. The real-time estimated Jacobian is applied to the controller to control the model. The stability and robustness of the adaptive interval type-2 fuzzy neural networks controller are enhanced by utilizing the EKF and the feedback error learning strategy for compensator tuning. This improvement increases resilience against estimation errors, seismic disturbances, and unknown nonlinear functions. The primary objective is to address the challenges posed by maximum displacement, acceleration, and drift, as well as the uncertainties arising from variations in stiffness and mass. In order to validate the reliability of the proposed controller, the performance investigation is carried out on an 11-story building equipped with an active tuned mass damper under far and near-field earthquakes. Numerical findings show the remarkable effectiveness of the proposed controllers compared to their predecessors. In addition, it is revealed that the inclusion of the adaptive interval type-2 fuzzy neural networks compensator has increased the performance of the proposed controller and shows significant capabilities in reducing the seismic responses of structures during severe earthquake events.

Intelligent mitigation of GPS spoofing using the Kalman filter in the tracking loop based on multi-correlator

In the last decade, spoofing attack has been known as the most dangerous intentional interference in Global Positioning System (GPS). This work suggested an algorithm that performs spoofing mitigation by utilising the Kalman filter. In particular, first, in the tracking stage multi-correlator structure is established and correlators output are investigated by using a Multi-Layer Perceptron Neural Network (MLP NN) in other to detect the spoofing attack, after that, the Kalman filter estimates the DLL discriminator output. The proposed method was verified using three different spoofing in which, the mitigation rate was 84.25%, 93.20% and 97.24%, respectively.

Ensuring Toplogical Data-Structure Preservation under Autoencoder Compression Due to Latent Space Regularization in Gauss–Legendre Nodes

We formulate a data-independent latent space regularization constraint for general unsupervised autoencoders. The regularization relies on sampling the autoencoder Jacobian at Legendre nodes, which are the centers of the Gauss–Legendre quadrature. Revisiting this classic allows us to prove that regularized autoencoders ensure a one-to-one re-embedding of the initial data manifold into its latent representation. Demonstrations show that previously proposed regularization strategies, such as contractive autoencoding, cause topological defects even in simple examples, as do convolutional-based (variational) autoencoders. In contrast, topological preservation is ensured by standard multilayer perceptron neural networks when regularized using our approach. This observation extends from the classic FashionMNIST dataset to (low-resolution) MRI brain scans, suggesting that reliable low-dimensional representations of complex high-dimensional datasets can be achieved using this regularization technique.

Optimizing pervious concrete with machine learning: Predicting permeability and compressive strength using artificial neural networks

This study makes a significant contribution to the field of pervious concrete by using machine learning to innovatively predict both mechanical and hydraulic performance. Unlike existing methods that rely on labor-intensive trial-and-error experiments, our proposed approach leverages a multilayer perceptron network. To develop this approach, we compiled a comprehensive dataset comprising 271 sets and 3,252 experimental data points. Our methodology involved evaluating 22,246 network configurations, employing Monte Carlo cross-validation over 20 iterations, and using 4 training algorithms, resulting in a total of 1,779,680 training iterations. This results in an optimized model that integrates diverse mix design parameters, enabling accurate predictions of permeability and compressive strength even in the absence of experimental data, achieving R² values of 0.97 and 0.98, respectively. Sensitivity analyses validate the model's alignment with established principles of pervious concrete behavior. By demonstrating the efficacy of machine learning as a complementary tool for optimizing pervious concrete mix designs, this research not only addresses current methodological limitations but also lays the groundwork for more efficient and effective approaches in the field.

A Deep Learning Approach to Investigating Clandestine Laboratories Using a GC-QEPAS Sensor

Illicit drug production in clandestine laboratories involves the use of large quantities of different chemicals that can be obtained for legitimate purposes. The identification of these chemicals, including reagents, catalyzers and solvents, is crucial for forensic investigations. From a legal point of view, a drug precursor is a material that is specific and critical to the production of a finished chemical and that constitutes a significant portion of the final molecular structure of the drug. In this study, a gas chromatography quartz-enhanced photoacoustic spectroscopy (GC-QEPAS) sensor—in conjunction with a deep learning model—was evaluated for its effectiveness in the detection and identification of interesting compounds for the production of amphetamine, methamphetamine, 3,4-methylenedioxymethamphetamine (MDMA), phenylcyclohexyl piperidine (PCP), and cocaine. The GC-QEPAS sensor includes a gas sampler, a fast GC for separation, and a QEPAS detector, which excites molecules exiting the GC column using a quantum cascade laser to provide the infra-red (IR) spectrum. The on-site capability of the GC-QEPAS system offers significant advantages over the current instruments employed in this field, including rapid analysis, which is crucial in field operations. This allows law enforcement to quickly identify specimens of interest on site. The system’s performance was validated by taking into account the limit of detection, repeatability, and within-laboratory reproducibility. The results showed excellent repeatability and reproducibility for both the GC and QEPAS modules. The deep learning model, a multilayer perceptron neural network, was trained using IR spectra and retention times, achieving very high classification accuracy in the testing conditions. This study demonstrated the efficacy of the GC-QEPAS sensor combined with a deep learning model for the reliable identification of drug precursors, providing a robust tool for law enforcement during criminal investigations in clandestine laboratories.

Artificial neural network hyperparameters optimization for predicting the thermal conductivity of MXene/graphene nanofluids

BackgroundThe critical role of thermal conductivity (TC) as a significant thermo-physical property in MXene/graphene-based nanofluids for photovoltaic/thermal systems has motivated recent research into developing precision predictive models. The multilayer perceptron neural network (MLPNN) has emerged as an eminent AI algorithm for this task. MethodsThis study employs Bayesian optimization, random search (RS), and grid search (GS) to fine-tune MLPNN hyperparameters—hidden layers, neurons, activation functions, standardization, and regularization—to elevate TC modeling efficiency. The proposed methodology unfolds in sequential phases: data analysis, data pre-processing, and introduction of MLPNN, GS, RS, Bayesian approach, and their integration algorithm. The next phase entails developing predictive models and presenting optimal cases. Lastly, the final models undergo statistical evaluation and graphical comparison for a thorough analysis. FindingsResults manifest that the GS-MLPNN model excels, achieving the lowest testing data error (MAPE = 0.5261%) and high conformity with empirical data (R = 0.99941). Meanwhile, the RS method adjusts hyperparameters with negligible precision loss (MAPE = 0.6046%, R = 0.99887). Contrarily, Bayesian optimization lags, increasing errors (MAPE = 3.1981%) and lower correlation (R = 0.98099), suggesting its relative inefficacy for this specific application. The optimized models provide efficient predictions, significantly reducing the financial/computing costs associated with experimental/numerical analysis.

Comparison of enhanced neural network and response surface models in predicting bio-dissolution of aluminum and vanadium from bauxite residue by isolated Aspergillus niger strains

Background: Recovery of Al and V from red mud, a hazardous residue of the Bayer process, using bioleaching is a nature-based waste management solution that simultaneously improves environment protection and metallurgical recoveries.Methods: For the first time, a novel hybrid multilayer Perceptron (MLP) network enhanced by an Imperialist Competitive Algorithm (ICA), and a response surface developed based on a factorial experiment design methodology (RSM) were employed and compared for, prediction optimization and optimization prediction of Al and V bioleaching by strains of A. Niger microorganisms isolated from pistachio shells and grape skins. The controlling variables were fungi source (A), adoption strategy (B), solid activation (C), solid percent (D), and bioleaching time. Considering the stochastic nature of ICA, a multi-criteria-ranking system based on accuracy and error indices was developed to select the best MLP. Probability value at 95% confidence interval, lack-of-fit, analysis of variance, R2, Adj. R2, and predicted R2 were the judges for the determination of the developed model's statistical significance.Significant Findings: Based on ANOVA, between A, B, C, and D, the effectiveness orders of A > D > C>AC>AD on Al, and A>AD>C>AC>D on V bioleaching were obtained. The superiority of the developed hybrid ICA-MLP model over the developed RSM model in predicting Al and V dissolution was determined by NSE, RSME, MAE, and MEDAE. Parameters optimization and consequently evaluating optimum condition repeatability through three repeating experiments resulted in maximum dissolution recoveries of RSM: 96.5% for Al and 91.2% for V, and ICA-MLP: 97.1% for Al and 90.3% for V. Considering the lower relative errors of repeating validation tests, it can be concluded that, although both models provide reasonable results, but the ICA-MLP methodology is more reliable (relative error <1.8%).

Fast radiance field reconstruction from sparse inputs

Neural Radiance Field (NeRF) has emerged as a powerful method in data-driven 3D reconstruction because of its simplicity and state-of-the-art performance. However, NeRF requires densely captured calibrated images and lengthy training and rendering time to realize high-resolution reconstruction. Thus, we propose a fast radiance field reconstruction method from a sparse set of images with silhouettes. Our approach integrates NeRF with Shape from Silhouette, a traditional 3D reconstruction method that uses silhouette information to fit the shape of an object. To combine NeRF’s implicit representation with Shape from Silhouette’s explicit representation, we propose a novel explicit–implicit radiance field representation consisting of voxel grids with confidence and feature embedding for geometry and a multilayer perceptron network to decode view-dependent color emission for appearance. We propose to make the reconstructed geometry compact by taking advantage of silhouette images, which can avoid the majority of artifacts in sparse input scenarios and speed up training and rendering. We also apply voxel dilating and pruning to refine the geometry prediction. In addition, we impose a total variation regularization on our model to encourage a smooth radiance field. Experiments on the DTU and the NeRF-Synthetic datasets show that our algorithm surpasses the existing baselines in terms of efficiency and accuracy.

Predicting axial-bearing capacity of fully grouted rock bolting systems by applying an ensemble system

In this paper, the potential of the five latest artificial intelligence (AI) predictive techniques, namely multiple linear regression (MLR), multi-layer perceptron neural network (MLPNN), Bayesian regularized neural network (BRNN), generalized feed-forward neural networks (GFFNN), extreme gradient boosting (XGBoost), and their ensemble soft computing models were evaluated to predict of the maximum peak load (PL) and displacement (DP) values resulting from pull-out tests. For this, 34 samples of the fully cementitious grouted rock bolts were prepared and cast. After conducting pull-out tests and building a dataset, twenty-four tests were randomly considered as a training dataset, and the remaining measurements were chosen to test the models’ performance. The input parameters were water-to-grout ratio (%) and curing time (day), while peak loads and displacement values were the outputs. The results revealed that the ensemble XGBoost model was superior to the other models. It was because having higher values of R2 (0.989, 0.979) and VAF (99.473, 98.658) and lower values of RMSE (0.0201, 0.0435) were achieved for testing the dataset of PL and DP’ values, respectively. Besides, sensitivity analysis proved that curing time was the most influential parameter in estimating values of peak loads and displacements. Also, the results confirmed that the ensemble XGBoost method was positioned to predict the axial-bearing capacity of the fully cementitious grouted rock bolting system with extreme performance and accuracy. Eventually, the results of the ensemble XGBoost modeling technique suggested that this novel model was more economical, less time-consuming, and less complicated than laboratory activities.

An Ensemble Spectral Prediction (ESP) model for metabolite annotation.

A key challenge in metabolomics is annotating measured spectra from a biological sample with chemical identities. Currently, only a small fraction of measurements can be assigned identities. Two complementary computational approaches have emerged to address the annotation problem: mapping candidate molecules to spectra, and mapping query spectra to molecular candidates. In essence, the candidate molecule with the spectrum that best explains the query spectrum is recommended as the target molecule. Despite candidate ranking being fundamental in both approaches, limited prior works incorporated rank learning tasks in determining the target molecule. We propose a novel machine learning model, Ensemble Spectral Prediction (ESP), for metabolite annotation. ESP takes advantage of prior neural network-based annotation models that utilize multilayer perceptron (MLP) networks and Graph Neural Networks (GNNs). Based on the ranking results of the MLP- and GNN-based models, ESP learns a weighting for the outputs of MLP and GNN spectral predictors to generate a spectral prediction for a query molecule. Importantly, training data is stratified by molecular formula to provide candidate sets during model training. Further, baseline MLP and GNN models are enhanced by considering peak dependencies through label mixing and multi-tasking on spectral topic distributions. When trained on the NIST 2020 dataset and evaluated on the relevant candidate sets from PubChem, ESP improves average rank by 23.7% and 37.2% over the MLP and GNN baselines, respectively, demonstrating performance gain over state-of-the-art neural network approaches. However, MLP approaches remain strong contenders when considering top five ranks. Importantly, we show that annotation performance is dependent on the training dataset, the number of molecules in the candidate set and candidate similarity to the target molecule. The ESP code, a trained model, and a Jupyter notebook that guide users on using the ESP tool is available at https://github.com/HassounLab/ESP.

Enhancing Customer Satisfaction Analysis Using Advanced Machine Learning Techniques in Fintech Industry

Customer satisfaction (CSAT) is vital in service and marketing, indicating how well products or services meet customer expectations. Traditional CSAT methods like the American Customer Satisfaction Index (ACSI) and Net Promoter Score (NPS) face challenges such as survey fatigue and low response rates. This study introduces a novel framework using advanced machine learning (ML) and deep learning (DL) techniques, specifically Bidirectional Encoder Representations from Transformers (BERT), to classify customer feedback into distinct CSAT drivers. Integrating term frequency-inverse document frequency (TF-IDF) methods with BERT-based embeddings, the framework significantly improves prediction accuracy. Using a proprietary dataset of 5,943 customer feedback responses from 39 companies across 13 industries, the fine-tuned BERT model achieved an F1 score of 0.84, surpassing traditional methods like TF-IDF and support vector machine (SVM) with an F1 score of 0.47, and TF-IDF with multi-layer perceptron (MLP) networks at 0.50. A hybrid approach combining BERT and TF-IDF embeddings with MLP networks yielded an F1 score of 0.71. The results show the transformative potential of DL techniques, particularly fine-tuned BERT models, in enhancing CSAT prediction accuracy. This research bridges the gap between traditional and advanced text mining methods, setting a new standard for CSAT modeling and offering a robust framework for extracting actionable insights from customer feedback. It highlights the importance of adopting advanced ML and DL models for strategic decision-making and improving customer satisfaction measurement.

Prediction of saturation exponent for subsurface oil and gas reservoirs using soft computing methods

The most widely used equation to calculate water saturation or suitable shaly water saturation in clean or shaly formation, respectively, is the modified Archie formula. The quality of Archie parameters including saturation exponent affects the preciseness of water saturation, and thus estimated oil and gas in place. Therefore, estimating the saturation exponent by the soft computation methods deems to be necessary. In this study, intelligent models such as multilayer perceptron neural network, least squares support vector machine, radial basis function neural network, and adaptive neuro-fuzzy inference system are developed to predict saturation exponent in terms of petrophysical data including porosity, absolute permeability, water saturation, true resistivity, and resistivity index by utilizing a databank for middle east oil and gas reservoirs. The introduced models are optimized using particle swarm optimization, genetic algorithm, and levenberg marquardt techniques. Graphical and statistical methods are used to demonstrate the capability of the constructed models. Based on the statistical indexes obtained for each model, it is found that radial basis function neural network, multilayer perceptron neural network, and least squares support vector machine are the most robust models as they possess the smallest mean squared error, root mean squared error and average absolute relative error as well as highest coefficient of determination. Moreover, the sensitivity analysis indicates that water saturation has the most effect and porosity has the least effect on the saturation exponent. The developed models are simple-to-use and time-consuming tools to predict saturation exponent without needing laboratory methods which are tedious and arduous.

Prediction of free chloride concentration in fly ash concrete by machine learning methods

Free chloride concentration distribution is important for assessing the corrosion risk of steel bars in reinforced concrete structures under chloride environment. In this study, a group of 3150 free chloride concentration data sets were obtained. Afterwards, three machine learning methods, namely support vector regression (SVR), multilayer perceptron (MLP) and one-dimensional convolutional neural network (1D-CNN) were adopted to construct models to predict chloride concentration distribution. The results show that 1D-CNN and MLP models are better at predicting the chloride concentration in fly ash concrete, whereas the prediction capability of SVR is relatively poor. Moreover, free chloride concentration prediction based on unmeasured parameters was conducted. The results show that the 1D-CNN and MLP models both have high prediction abilities – that is, predicted results are consistent with experimental measurements, performing generally better than the time-varying model constructed based on Fick's second law. When the free chloride concentrations were higher than 0.1%, the SVR model had a better prediction effect, but had unsatisfactory results and differed significantly from the actual chloride concentration when at a lower concentration. Overall, the 1D-CNN model performs the best in predicting free chloride concentration of concrete at different penetration depths, exposure time and with different fly ash content.

Data‐driven quality prediction in injection molding: An autoencoder and machine learning approach

AbstractIn the injection molding process, the pressure within the mold cavity is crucial to the quality of the final product. Due to the inability to directly observe the process, sensor technology is required to acquire data. Traditionally, experts interpret and encode pressure curves, but this method has limitations. This study proposes an innovative pressure curve encoding technique to overcome these limitations and achieve automation to obtain more comprehensive pressure information. The study employs mold flow analysis software and autoencoders to capture and encode pressure data, classifying pressure curves into global pressure and local pressure values. Subsequently, a multilayer perceptron (MLP) neural network is used for machine learning to predict multiple qualities. Results indicate that local pressure features perform better in predicting multiple‐quality targets than global pressure features, exhibiting smaller prediction ranges and higher prediction stability. Although domain knowledge‐based indicator features slightly outperform in terms of predictive capability, the low error results of the local pressure feature method validate the effectiveness of the autoencoder approach, demonstrating its potential for digital information extraction and practical quality prediction in the injection molding process.Highlights Develops a product quality prediction system for efficient injection molding. Autoencoders extract key features from pressure data without domain knowledge. ML models predict quality indicators, optimizing injection molding processes. Compares pressure features, showing data‐driven methods' prediction accuracy.

Prediction of Sea Level Using Double Data Decomposition and Hybrid Deep Learning Model for Northern Territory, Australia

Sea level rise (SLR) attributed to the melting of ice caps and thermal expansion of seawater is of great global significance to vast populations of people residing along the world’s coastlines. The extent of SLR’s impact on physical coastal areas is determined by multiple factors such as geographical location, coastal structure, wetland vegetation and related oceanic changes. For coastal communities at risk of inundation and coastal erosion due to SLR, the modelling and projection of future sea levels can provide the information necessary to prepare and adapt to gradual sea level rise over several years. In the following study, a new model for predicting future sea levels is presented, which focusses on two tide gauge locations (Darwin and Milner Bay) in the Northern Territory (NT), Australia. Historical data from the Australian Bureau of Meteorology (BOM) from 1990 to 2022 are used for data training and prediction using artificial intelligence models and computation of mean sea level (MSL) linear projection. The study employs a new double data decomposition approach using Multivariate Variational Mode Decomposition (MVMD) and Successive Variational Mode Decomposition (SVMD) with dimensionality reduction techniques of Principal Component Analysis (PCA) for data modelling using four artificial intelligence models (Support Vector Regression (SVR), Adaptive Boosting Regressor (AdaBoost), Multilayer Perceptron (MLP), and Convolutional Neural Network–Bidirectional Gated Recurrent Unit (CNN-BiGRU). It proposes a deep learning hybrid CNN-BiGRU model for sea level prediction, which is benchmarked by SVR, AdaBoost, and MLP. MVMD-SVMD-CNN-BiGRU hybrid models achieved the highest performance values of 0.9979 (d), 0.996 (NS), 0.9409 (L); and 0.998 (d), 0.9959 (NS), 0.9413 (L) for Milner Bay and Darwin, respectively. It also attained the lowest error values of 0.1016 (RMSE), 0.0782 (MABE), 2.3699 (RRMSE), and 2.4123 (MAPE) for Darwin and 0.0248 (RMSE), 0.0189 (MABE), 1.9901 (RRMSE), and 1.7486 (MAPE) for Milner Bay. The mean sea level (MSL) trend analysis showed a rise of 6.1 ± 1.1 mm and 5.6 ± 1.5 mm for Darwin and Milner Bay, respectively, from 1990 to 2022.

Machine learning-based prediction of construction and demolition waste generation in developing countries: a case study.

Data is needed for making informed decisions regarding managing waste in the time of construction and demolition phases of buildings. However, data availability is very limited in most developing countries in the area of waste generation. The objective of this study is to employ an artificial intelligence (AI)-based approach to develop a reliable model for forecasting monthly construction and demolition waste (C&DW) generation in the case study of Tehran, Iran. We have trained different prediction models using various AI algorithms, including multilayer perceptron neural network, radial basis function neural network, support vector machines, and adaptive neuro-fuzzy inference system (ANFIS). According to the findings, all employed AI algorithms demonstrated high prediction performance for C&DW forecasting models. The ANFIS model, with R2 = 0.96 and RMSE = 0.04209, was identified as the model that better represented the observed values of C&DW generation. The better efficiency of the ANFIS model could be due to its effective enhancement of neural networks to model subjective variables based on fuzzy logic capabilities. The developed prediction model can be employed as an efficient tool for policy and decision-making for C&DW management by predicting waste quantities in the future.

Effect of applying serpentine channels and hybrid nanofluid for thermal management of photovoltaic cell: Numerical simulation, ANN and sensitivity analysis

Regarding the importance of thermal management of solar PV cells to achieve higher efficiency and electricity output, a novel configuration by use of serpentine channels for cooling is proposed and numerically investigated in the present article. Moreover, a hybrid nanofluid, (MWCNT)-Fe3O4/water, is employed as the coolant to investigate its potential in further improvement of thermal management. Computational Fluid Dynamics (CFD) is applied to numerically simulate the systems and investigate the impacts of different factors. Performance of the proposed configuration is compared with cooling channels with simple structure without nanofluids. Simulations results revealed that the employment of serpentine channels leads to modification in the thermal management of the cell compared with the simple channel. The maximum improvement rate in this condition compared with simple channels is around 9.63 % that is obtained in case of maximum mass flow rate of coolant and solar radiation intensity. Despite increment in pressure loss by using the serpentine channel compared with the simple channel, 2.6 ×10−3 W and 9.3 ×10−4 W, respectively, in mass flow rate of 0.003 kg/s for water, increase in the generated electricity is much more in this case. Furthermore, numerical results show that applying the hybrid nanofluid with 0.1 % concentration can cause slight reduction in the temperature compared with using water. Moreover, Group Method of Data Handling (GMDH) and Multilayer Perceptron (MLP) neural network as intelligent methods used for estimation of the cell temperature and the maximum error for the developed model is approximately 1.1 % and 0.098 % for the GMDH- and MLP-based models, respectively. Finally, sensitivity analysis is implemented and it is shown that solar radiation intensity is the most influential factor on the cell temperature in condition of using serpentine channels while mass flow rate of the coolant has the minimum relevancy factor and consequently effect on the temperature of the solar cell.

Time series imaging-based deep learning method for inventory control

ABSTRACT Data-driven newsvendor methods offer promising solutions for estimating replenishment quantity within complex markets by leveraging demand-related features. However, most features utilized by these methods rely on manual selection, and some important unobservable features cannot be thoroughly utilized. These issues might result in the loss of some crucial information, thus incurring considerable cost in these decision-making results, meaning that there is still much room for improvement. To remedy this, we propose a time series imaging-based deep learning method, which automatically extracts crucial features alongside those selected manually. This method maximizes the advantages of time series imaging, convolutional neural networks, bidirectional long short-term memory networks, and multilayer perceptron networks. Experiments with four diverse product time series and real-world data show that our approach reduces the average newsvendor problem cost by 16.33% to 33.43% compared to the best benchmark, highlighting its robustness. Additionally, each component within our method significantly contributes to decision-making.

Citizen profiles based on social capital in the Spanish fiscal context: Profile development and multivariate consistency analysis

Previous studies have established that social capital plays a significant role in individual tax-related behaviors, including inclinations toward tax evasion and compliance. This study seeks to extend the understanding of tax morale in Spain using data from the Public Opinion and Fiscal Policy Survey (CIS, Study 3332). We use factor analysis with maximum likelihood extraction and Varimax rotation to identify key social capital variables and tax attitudes. We identify profiles based on their social capital and tax compliance using cluster analysis. We will apply hierarchical clustering with Ward's chaining and k-means clustering. The robustness of the resulting profiles will be confirmed by discriminant analysis and a multilayer perceptron neural network, which will look for higher rates of correct classification as an indicator of improved profile consistency. Our findings suggest that identifying Spanish tax citizens' profiles helps analyze social capital in tax policy. After our analysis, we have determined that enhancing the accumulation of social capital variables leads to better tax adherence.

Developing an innovative corrosion and scaling index for industrial cooling water using artificial intelligence

The present study developed an intelligent model to predict the corrosion and scaling potential (CSP) of industrial cooling water circuits using artificial intelligence (AI) techniques. AI techniques have attracted a lot of attention due to the high accuracy and speed of calculations, as well as possible analysis of large datasets. The study analyzed nine years of data on cooling water quality parameters, including pH, alkalinity, hardness, dissolved solids, chloride, turbidity, suspended solids, and iron, from electric arc furnaces at the Khuzestan Steel Company. Multiple linear regression (MLR), multiple nonlinear regression (MNLR), and multi-layer perceptron neural network (ANN-MLP) models were applied to predict CSP. The ANN-MLP model achieved the best performance with an R2 of 0.75, Mean Absolute Error of 0.34, and Mean Squared Error of 0.35, demonstrating that neural networks can effectively predict CSP in industrial cooling water. The results also showed that total hardness and chloride have the greatest impact on CSP in the circulating water circuits.