Machine learning prediction of methane, nitrogen, and natural gas mixture viscosities under normal and harsh conditions.

The accurate estimation of gas viscosity remains a pivotal concern for petroleum engineers, exerting substantial influence on the modeling efficacy of natural gas operations. Due to their time-consuming and costly nature, experimental measurements of gas viscosity are challenging. Data-based machine learning (ML) techniques afford a resourceful and less exhausting substitution, aiding research and industry at gas modeling that is incredible to reach in the laboratory. Statistical approaches were used to analyze the experimental data before applying machine learning. Seven machine learning techniques specifically Linear Regression, random forest (RF), decision trees, gradient boosting, K-nearest neighbors, Nu support vector regression (NuSVR), and artificial neural network (ANN) were applied for the prediction of methane (CH4), nitrogen (N2), and natural gas mixture viscosities. More than 4304 datasets from real experimental data utilizing pressure, temperature, and gas density were employed for developing ML models. Furthermore, three novel correlations have developed for the viscosity of CH4, N2, and composite gas using ANN. Results revealed that models and anticipated correlations predicted methane, nitrogen, and natural gas mixture viscosities with high precision. Results designated that the ANN, RF, and gradient Boosting models have performed better with a coefficient of determination (R2) of 0.99 for testing data sets of methane, nitrogen, and natural gas mixture viscosities. However, linear regression and NuSVR have performed poorly with a coefficient of determination (R2) of 0.07 and - 0.01 respectively for testing data sets of nitrogen viscosity. Such machine learning models offer the industry and research a cost-effective and fast tool for accurately approximating the viscosities of methane, nitrogen, and gas mixture under normal and harsh conditions.

Evaluation of hydrogen production via steam reforming and partial oxidation of dimethyl ether using response surface methodology and artificial neural network.

This study aims to develop two models for thermodynamic data on hydrogen generation from the combined processes of dimethyl ether steam reforming and partial oxidation, applying artificial neural networks (ANN) and response surface methodology (RSM). Three factors are recognized as important determinants for the hydrogen and carbon monoxide mole fractions. The RSM used the quadratic model to formulate two correlations for the outcomes. The ANN modeling used two algorithms, namely multilayer perceptron (MLP) and radial basis function (RBF). The optimum configuration for the MLP, employing the Levenberg-Marquardt (trainlm) algorithm, consisted of three hidden layers with 15, 10, and 5 neurons, respectively. The ideal RBF configuration contained a total of 80 neurons. The optimum configuration of ANN achieved the best mean squared error (MSE) performance of 3.95e-05 for the hydrogen mole fraction and 4.88e-05 for the carbon monoxide mole fraction after nine epochs. Each of the ANN and RSM models produced accurate predictions of the actual data. The prediction performance of the ANN model was 0.9994, which is higher than the RSM model's 0.9771. The optimal condition was obtained at O/C of 0.4, S/C of 2.5, and temperature of 250 °C to achieve the highest H2 production with the lowest CO emission.

Application of Artificial Neural Network and Genetic Algorithm Modeling for In Vitro Regeneration of Seaweed Seedling Production.

Marine macro-algae, commonly known as "seaweed," are used in everyday commodity products worldwide for food, feed, and biostimulant for plants and animals and continue to be one of the conspicuous components of world aquaculture production. However, the application of ANN in seaweeds remains limited. Here, we described how to perform ANN-based machine learning modeling and GA-based optimization to enhance seedling production for implications on commercial farming. The critical steps from seaweed seedling explant preparation, selection of independent variables for laboratory culture, formulating experimental design, executing ANN Modelling, and implementing optimization algorithm are described.

Predicting projectile residual velocities using an advanced artificial neural network model.

In this research, we delve into the fascinating dynamics of projectiles and their interactions with materials, with a keen focus on residual velocity - the speed a projectile retains after striking a target. This parameter is pivotal, especially when considering the design of protective barriers in various environments. Traditional methods of gauging residual velocity have been cumbersome, resource-intensive, and occasionally inconsistent. To address these challenges, we introduce an innovative approach using an Artificial Neural Network (ANN) model through MATLAB R2021a. This computerized tool, trained on a rich dataset from prior research, can predict residual velocities by considering multiple factors, including the initial speed of the projectile, its material and shape, and the thickness of the target. This paper meticulously details the development, training, and validation of the ANN model, highlighting its superior accuracy when compared to traditional methods like the Recht-Ipson model. The developed ANN model demonstrated remarkable performance compared to the Recht-Ipson model. During training, it exhibited a Mean Absolute Percentage Error (MAPE) of 0.0259 and a Root Mean Squared Error (RMSE) of 1.5993. For validation, MAPE was 0.0295, and RMSE was 2.2056. In contrast, the Recht-Ipson model displayed higher errors, with MAPE and RMSE values of 0.2349 and 14.1791, respectively. Furthermore, we discuss the potential of the ANN model in predicting not just residual velocities but also absorbed energy, showcasing its versatility. The practical implications of our findings are vast. From designing safer infrastructures in urban settings to enhancing armour systems in military applications, the ANN model's predictions can be a cornerstone for innovation.

Exploring the recycled water acceptance based on the technological perspective of UTAUT2: a hybrid analytical approach.

Introduction: The development of advanced sewage technologies empowers the industry to produce high-quality recycled water, which greatly influences human's life and health. Thus, this study investigates the mechanism of individuals' adoption of recycled water from the technology adoption perspective. Methods: Employing the mixed method of structural equation modeling and artificial neural network analysis, we examined a research model developed from the extended Unified Theory of Acceptance and Use of Technology (UTAUT2) framework. To examine the research model, this study employs a leading web-survey company (Sojump) to collect 308 valid samples from the residents in mainland China. Results: The structural equation modeling results verified the associations between the six predictors (performance expectancy, effort expectancy, social influence, facilitating conditions, environmental motivation, and price value), individuals' cognitive and emotional attitudes, and acceptance intention. The artificial neural network analysis validates and complements the structural equation modeling results by unveiling the importance rank of the significant determinants of the acceptance decisions. Discussion: The study provides theoretical implications for recycled water research and useful insights for practitioners and policymakers to reduce the environmental hazards of water scarcity.

Modeling of scour hole characteristics under turbulent wall jets using machine learning.

The novelty of the present study is to investigate the parameters that depict the scour hole characteristics caused by turbulent wall jets and develop new mathematical relationships for them. Four significant parameters i.e., depth of scouring, location of scour depth, height of the dune and location of dune crest are identified to represent a complete phenomenon of scour hole formation. From the gamma test, densimetric Froude number, apron length, tailwater level, and median sediment size are found to be the key parameters that affect these four dependent parameters. Utilizing the previous data sets, Multi Regression Analysis (linear and non-linear) has been performed to establish the relationships between the dependent parameters and influencing independent parameters. Further, artificial neural network-particle swarm optimisation (ANN-PSO) and gene expression programming (GEP) based models are developed using the available data. In addition, results obtained from these models are compared with proposed regression equations and the best models are identified employing statistical performance parameters. The performance of the ANN-PSO model (RMSE = 1.512, R2 = 0.605), (RMSE = 6.644, R2 = 0.681), (RMSE = 6.386, R2 = 0.727) and (RMSE = 1.754, R2 = 0.636) for predicting four significant parameters are more satisfactory than that of regression and other soft computing techniques. Overall, by analysing all the statistical parameters, uncertainty analysis and reliability index, ANN-PSO model shows good accuracy and predicts well as compared to other presented models.

Optimization of process conditions for ionic liquid-based ultrasound-enzyme-assisted extraction of resveratrol from Polygonum Cuspidatum.

This work offered a productive technique for resveratrol extraction from Polygonum Cuspidatum (P. Cuspidatum) using ionic liquids in synergy with ultrasound-enzyme-assisted extraction (UEAE). Firstly, ionic liquids with different carbon chains and anions were evaluated. Subsequently, a comprehensive investigation was carried out to evaluate the effect of seven crucial parameters on the resveratrol yield: pH value, enzyme concentration, extraction temperature, extraction time, ultrasonic power, concentration of ionic liquid (IL concentration) and the liquid-solid ratio. Employing the Plackett-Burman Design (PBD), the critical factors were effectively identified. Building upon this foundation, the process was further optimized through the application of Response Surface Methodology (RSM) and an Artificial Neural Network-Genetic Algorithm (ANN-GA). The following criteria were determined to be the ideal extraction conditions: an enzyme concentration of 2.18%, extraction temperature of 58 °C, a liquid-solid ratio of 29 mL/g, pH value of 5.5, extraction time of 30 min, ultrasonic power of 250 W, and extraction solvent of 0.5 mol/L 1-butyl-3-methylimidazolium bromide. Under these conditions, the resveratrol yield was determined to be 2.90 ± 0.15 mg/g. Comparative analysis revealed that the ANN-GA model provided a better fit to the experimental data of resveratrol yield than the RSM model, suggesting superior predictive capabilities of the ANN-GA approach. The introduction of a novel green solvent system in this experiment not only simplifies the extraction process but also enhances safety and feasibility. This research paves the way for innovative approaches to extracting resveratrol from botanical sources, showcasing its significant potential for a wide range of applications.

Self-architectural knowledge distillation for spiking neural networks.

Spiking neural networks (SNNs) have attracted attention due to their biological plausibility and the potential for low-energy applications on neuromorphic hardware. Two mainstream approaches are commonly used to obtain SNNs, i.e., ANN-to-SNN conversion methods, and Directly-trained-SNN methods. However, the former achieve excellent performance at the cost of a large number of time steps (i.e., latency), while the latter exhibit lower latency but suffers from suboptimal performance. To tackle the performance-latency trade-off, we propose Self-Architectural Knowledge Distillation (SAKD), an intuitive and effective method for SNNs leveraging Knowledge Distillation (KD). We adopt a bilevel teacher-student training strategy in SAKD, i.e., level-1 involves directly transferring same-architectural pre-trained ANN weights to SNNs, and level-2 encourages the SNNs to mimic ANN's behavior, considering both final responses and intermediate features aspects. Learning with informative supervision signals fostered by labels and ANNs, our SAKD achieves new state-of-the-art (SOTA) performance with a few time steps on widely-used classification benchmark datasets. On ImageNet-1K, with only 4 time steps, our Spiking-ResNet34 model attains a Top-1 accuracy of 70.04%, outperforming the previous same-architectural SOTA methods. Notably, our SEW-ResNet152 model reaches a Top-1 accuracy of 77.30% on ImageNet-1K, setting a new SOTA benchmark for SNNs. Furthermore, we apply our SAKD to various dense prediction downstream tasks, such as object detection and semantic segmentation, demonstrating strong generalization ability and superior performance. In conclusion, our proposed SAKD framework presents a promising approach for achieving both high performance and low latency in SNNs, potentially paving the way for future advancements in the field.

Enhanced biosynthesis of coated silver nanoparticles using isolated bacteria from heavy metal soils and their photothermal-based antibacterial activity: integrating Response Surface Methodology (RSM) Hybrid Artificial Neural Network (ANN)-Genetic Algorithm (GA) strategies.

This study explores the biosynthesis of silver nanoparticles (AgNPs) using the Streptomyces tuirus S16 strain, presenting an eco-friendly alternative to mitigate the environmental and health risks of chemical synthesis methods. It focuses on optimizing medium culture conditions, understanding their physicochemical properties, and investigating their potential photothermal-based antibacterial application. The S16 strain was selected from soils contaminated with heavy metals to exploit its ability to produce diverse bioactive compounds. By employing the combination of Response Surface Methodology (RSM) and Artificial Neural Network (ANN)-Genetic Algorithm (GA) strategies, we optimized AgNPs synthesis, achieving an improvement of nearly 2.45 times the initial yield under specific conditions (Bennet's medium supplemented with glycerol [5 g/L] and casamino-acid [3 g/L] at 30 °C for 72 h). A detailed physicochemical characterization was conducted. Notably, the AgNPs were well dispersed, and a carbonaceous coating layer on their surface was confirmed using energy-dispersive X-ray spectroscopy. Furthermore, functional groups were identified using Fourier-transform infrared spectroscopy, which helped enhance the AgNPs' stability and biocompatibility. AgNPs also demonstrated efficient photothermal conversion under light irradiation (0.2 W/cm2), with temperatures increasing to 41.7 °C, after 30 min. In addition, treatment with light irradiation of E. coli K-12 model effectively reduced the concentration of AgNPs from 105 to 52.5 µg/mL, thereby enhancing the efficacy of silver nanoparticles in contact with the E. coli K-12.

Sensing Volatile Pollutants with Spin-Coated Films Made of Pillar[5]arene Derivatives and Data Validation via Artificial Neural Networks.

Different types of solvents, aromatic and aliphatic, are used in many industrial sectors, and long-term exposure to these solvents can lead to many occupational diseases. Therefore, it is of great importance to detect volatile organic compounds (VOCs) using economic and ergonomic techniques. In this study, two macromolecules based on pillar[5]arene, named P[5]-1 and P[5]-2, were synthesized and applied to the detection of six different environmentally volatile pollutants in industry and laboratories. The thin films of the synthesized macrocycles were coated by using the spin coating technique on a suitable substrate under optimum conditions. All compounds and the prepared thin film surfaces were characterized by NMR, Fourier transform infrared (FT-IR), elemental analysis, atomic force microscopy (AFM), scanning electron microscopy (SEM), and contact angle measurements. All vapor sensing measurements were performed via the surface plasmon resonance (SPR) optical technique, and the responses of the P[5]-1 and P[5]-2 thin-film sensors were calculated with ΔI/Io × 100. The responses of the P[5]-1 and P[5]-2 thin-film sensors to dichloromethane vapor were determined to be 7.17 and 4.11, respectively, while the responses to chloroform vapor were calculated to be 5.24 and 2.8, respectively. As a result, these thin-film sensors showed a higher response to dichloromethane and chloroform vapors than to other harmful vapors. The SPR kinetic data for vapors validated that a nonlinear autoregressive neural network was performed with exogenous input for the best molecular modeling by using normalized reflected light intensity values. It can be clearly seen from the correlation coefficient values that the nonlinear autoregressive with exogenous input artificial neural network (NARX-ANN) model for dichloromethane converged more successfully to the experimental data compared to other gases. The correlation coefficient values of the dichloromethane modeling results were approximately 0.99 and 0.98 for P[5]-1 and P[5]-2 thin-film sensors, respectively.

Prediction and reliability analysis of shear strength of RC deep beams.

This study explores machine learning (ML) capabilities for predicting the shear strength of reinforced concrete deep beams (RCDBs). For this purpose, eight typical machine-learning models, i.e., symbolic regression (SR), XGBoost (XGB), CatBoost (CATB), random forest (RF), LightGBM, support vector regression (SVR), artificial neural networks (ANN), and Gaussian process regression (GPR) models, are selected and compared based on a database of 840 samples with 14 input features. The hyperparameter tuning of the introduced ML models is performed using the Bayesian optimization (BO) technique. The comparison results show that the CatBoost model is the most reliable and accurate ML model (R2 = 0.997 and 0.947 in the training and testing sets, respectively). In addition, simple and practical design expressions for RCDBs have been proposed based on the SR model with a physical meaning and acceptable accuracy (an average prediction-to-test ratio of 0.935 and a standard deviation of 0.198). Meanwhile, the shear strength predicted by ML models was then compared with classical mechanics-driven shear models, including two prominent practice codes (i.e., ACI318, EC2) and two previous mechanical models, which indicated that the ML approach is highly reliable and accurate over conventional methods. In addition, a reliability-based design was conducted on two ML models, and their reliability results were compared with those of two code standards. The findings revealed that the ML models demonstrate higher reliability compared to code standards.

ANN-based swarm intelligence for predicting expansive soil swell pressure and compression strength.

This research suggests a robust integration of artificial neural networks (ANN) for predicting swell pressure and the unconfined compression strength of expansive soils (PsUCS-ES). Four novel ANN-based models, namely ANN-PSO (i.e., particle swarm optimization), ANN-GWO (i.e., grey wolf optimization), ANN-SMA (i.e., slime mould algorithm) alongside ANN-MPA (i.e., marine predators' algorithm) were deployed to assess the PsUCS-ES. The models were trained using the nine most influential parameters affecting PsUCS-ES, collected from a broader range of 145 published papers. The observed results were compared with the predictions made by the ANN-based metaheuristics models. The efficacy of all these formulated models was evaluated by utilizing mean absolute error (MAE), Nash-Sutcliffe (NS) efficiency, performance index ρ, regression coefficient (R2), root mean square error (RMSE), ratio of RMSE to standard deviation of actual observations (RSR), variance account for (VAF), Willmott's index of agreement (WI), and weighted mean absolute percentage error (WMAPE). All the developed models for Ps-ES had an R significantly > 0.8 for the overall dataset. However, ANN-MPA excelled in yielding high R values for training dataset (TrD), testing dataset (TsD), and validation dataset (VdD). This model also exhibited the lowest MAE of 5.63%, 5.68%, and 5.48% for TrD, TsD, and VdD, respectively. The results of the UCS model's performance revealed that R exceeded 0.9 in the TrD. However, R decreased for TsD and VdD. Also, the ANN-MPA model yielded higher R values (0.89, 0.93, and 0.94) and comparatively low MAE values (5.11%, 5.67, and 3.61%) in the case of PSO, GWO, and SMA, respectively. The UCS models witnessed an overfitting problem because the aforementioned R values of the metaheuristics were 0.62, 0.56, and 0.58 (TsD), respectively. On the contrary, no significant observation was recorded in the VdD of UCS models. All the ANN-base models were also tested using the a-20 index. For all the formulated models, maximum points were recorded to lie within ± 20% error. The results of sensitivity as well as monotonicity analyses depicted trending results that corroborate the existing literature. Therefore, it can be inferred that the recently built swarm-based ANN models, particularly ANN-MPA, can solve the complexities of tuning the hyperparameters of the ANN-predicted PsUCS-ES that can be replicated in practical scenarios of geoenvironmental engineering.

Using ANN for thermal neutron shield designing for BNCT treatment room.

Occupational radiation protection should be applied to the design of treatment rooms for various radiation therapy techniques, including BNCT, where escaping particles from the beam port of the beam shaping assembly (BSA) may reach the walls or penetrate through the entrance door. The focus of the present study is to design an alternative shielding material, other than the conventional material of lead, that can be considered as the material used in the door and be able to effectively absorb the BSA neutrons which have slowed down to the thermal energy range of < 1 eV after passing through the walls and the maze of the room. To this aim, a thermal neutron shield, composed of polymer composite and polyethylene, has been simulated using the Geant4 Monte Carlo code. The neutron flux and dose values were predicted using an artificial neural network (ANN), eliminating the need for time-consuming Monte Carlo simulations in all possible suggestions. Additionally, this technique enables simultaneous optimization of the parameters involved, which is more effective than the traditional sequential and separate optimization process. The results indicated that the optimized shielding material, chosen through ANN calculations that determined the appropriate thickness and weight percent of its compositions, can decrease the dose behind the door to lower than the allowable limit for occupational exposure. The stability of ANN was tested by considering uncertainties with the Gaussian distributions of random numbers to the testing data. The results are promising as they indicate that ANNs could be used as a reliable tool for accurately predicting the dosimetric results, providing a drastically powerful alternative approach to the time-consuming Monte Carlo simulations.

Prediction of CO2 solubility in Ionic liquids for CO2 capture using deep learning models.

Ionic liquids (ILs) are highly effective for capturing carbon dioxide (CO2). The prediction of CO2 solubility in ILs is crucial for optimizing CO2 capture processes. This study investigates the use of deep learning models for CO2 solubility prediction in ILs with a comprehensive dataset of 10,116 CO2 solubility data in 164 kinds of ILs under different temperature and pressure conditions. Deep neural network models, including Artificial Neural Network (ANN) and Long Short-Term Memory (LSTM), were developed to predict CO2 solubility in ILs. The ANN and LSTM models demonstrated robust test accuracy in predicting CO2 solubility, with coefficient of determination (R2) values of 0.986 and 0.985, respectively. Both model's computational efficiency and cost were investigated, and the ANN model achieved reliable accuracy with a significantly lower computational time (approximately 30 times faster) than the LSTM model. A global sensitivity analysis (GSA) was performed to assess the influence of process parameters and associated functional groups on CO2 solubility. The sensitivity analysis results provided insights into the relative importance of input attributes on output variables (CO2 solubility) in ILs. The findings highlight the significant potential of deep learning models for streamlining the screening process of ILs for CO2 capture applications.

The use of artificial neural network for modelling adsorption of Congo red onto activated hazelnut shell.

Activated hazelnut shell (HSAC), an organic waste, was utilized for the adsorptive removal of Congo red (CR) dye from aqueous solutions, and a modelling study was conducted using artificial neural networks (ANNs). The structure and characteristic functional groups of the material were examined by the FTIR method. The BET surface area of the synthesized material, named HSAC, was 812 m2/g. Conducted in a batch system, the adsorption experiments resulted in a notable removal efficiency of 87% under optimal conditions. The kinetic data for hazelnut shell activated carbon (HSAC) removal of CR were most accurately represented by the pseudo-second-order kinetic model (R2 = 0.998). Furthermore, the equilibrium data demonstrated a strong agreement with the Freundlich model. The maximum adsorption capacity of HSAC for CR was determined to be 34.8 mg/g. The optimum adsorption parameters were determined to be pH 6, contact time of 60 min, 10 g/L of HSAC, and a concentration of 400 mg/L for CR. Considering the various experimental parameters influencing CR adsorption, an artificial neural network (ANN) model was constructed. The analysis of the ANN model revealed a correlation of 98%, indicating that the output parameter could be reliably predicted. Thus, it was concluded that ANN could be employed for the removal of CR from water using HSAC.

Electrocardiography Classification with Leaky Integrate-and-Fire Neurons in an Artificial Neural Network-Inspired Spiking Neural Network Framework.

Monitoring heart conditions through electrocardiography (ECG) has been the cornerstone of identifying cardiac irregularities. Cardiologists often rely on a detailed analysis of ECG recordings to pinpoint deviations that are indicative of heart anomalies. This traditional method, while effective, demands significant expertise and is susceptible to inaccuracies due to its manual nature. In the realm of computational analysis, Artificial Neural Networks (ANNs) have gained prominence across various domains, which can be attributed to their superior analytical capabilities. Conversely, Spiking Neural Networks (SNNs), which mimic the neural activity of the brain more closely through impulse-based processing, have not seen widespread adoption. The challenge lies primarily in the complexity of their training methodologies. Despite this, SNNs offer a promising avenue for energy-efficient computational models capable of displaying a high-level performance. This paper introduces an innovative approach employing SNNs augmented with an attention mechanism to enhance feature recognition in ECG signals. By leveraging the inherent efficiency of SNNs, coupled with the precision of attention modules, this model aims to refine the analysis of cardiac signals. The novel aspect of our methodology involves adapting the learned parameters from ANNs to SNNs using leaky integrate-and-fire (LIF) neurons. This transfer learning strategy not only capitalizes on the strengths of both neural network models but also addresses the training challenges associated with SNNs. The proposed method is evaluated through extensive experiments on two publicly available benchmark ECG datasets. The results show that our model achieves an overall accuracy of 93.8% on the MIT-BIH Arrhythmia dataset and 85.8% on the 2017 PhysioNet Challenge dataset. This advancement underscores the potential of SNNs in the field of medical diagnostics, offering a path towards more accurate, efficient, and less resource-intensive analyses of heart diseases.

Linear and Non-Linear Modelling Methods for a Gas Sensor Array Developed for Process Control Applications.

New process developments linked to Power to X (energy storage or energy conversion to another form of energy) require tools to perform process monitoring. The main gases involved in these types of processes are H2, CO, CH4, and CO2. Because of the non-selectivity of the sensors, a multi-sensor matrix has been built in this work based on commercial sensors having very different transduction principles, and, therefore, providing richer information. To treat the data provided by the sensor array and extract gas mixture composition (nature and concentration), linear (Multi Linear Regression-Ordinary Least Square "MLR-OLS" and Multi Linear Regression-Partial Least Square "MLR-PLS") and non-linear (Artificial Neural Network "ANN") models have been built. The MLR-OLS model was disqualified during the training phase since it did not show good results even in the training phase, which could not lead to effective predictions during the validation phase. Then, the performances of MLR-PLS and ANN were evaluated with validation data. Good concentration predictions were obtained in both cases for all the involved analytes. However, in the case of methane, better prediction performances were obtained with ANN, which is consistent with the fact that the MOX sensor's response to CH4 is logarithmic, whereas only linear sensor responses were obtained for the other analytes. Finally, prediction tests performed on one-year aged sensor platforms revealed that PLS model predictions on aged platforms mainly suffered from concentration offsets and that ANN predictions mainly suffered from a drop of sensitivity.

A Novel Continuous Sleep State Artificial Neural Network Model Based on Multi-Feature Fusion of Polysomnographic Data.

Purpose: Sleep structure is crucial in sleep research, characterized by its dynamic nature and temporal progression. Traditional 30-second epochs falter in capturing the intricate subtleties of various micro-sleep states. This paper introduces an innovative artificial neural network model to generate continuous sleep depth value (SDV), utilizing a novel multi-feature fusion approach with EEG data, seamlessly integrating temporal consistency. Methods: The study involved 50 normal and 100 obstructive sleep apnea-hypopnea syndrome (OSAHS) participants. After segmenting the sleep data into 3-second intervals, a diverse array of 38 feature values were meticulously extracted, including power, spectrum entropy, frequency band duration and so on. The ensemble random forest model calculated the timing fitness value for all the features, from which the top 7 time-correlated features were selected to create detailed sleep sample values ranging from 0 to 1. Subsequently, an artificial neural network (ANN) model was trained to delineate sleep continuity details, unravel concealed patterns, and far surpassed the traditional 5-stage categorization (W, N1, N2, N3, and REM). Results: The SDV changes from wakeful stage (mean 0.7021, standard deviation 0.2702) to stage N3 (mean 0.0396, standard deviation 0.0969). During the arousal epochs, the SDV increases from the range (0.1 to 0.3) to the range around 0.7, and decreases below 0.3. When in the deep sleep (≤0.1), the probability of arousal of normal individuals is less than 10%, while the average arousal probability of OSA patients is close to 30%. Conclusion: A sleep continuity model is proposed based on multi-feature fusion, which generates SDV ranging from 0 to 1 (representing deep sleep to wakefulness). It can capture the nuances of the traditional five stages and subtle differences in microstates of sleep, considered as a complement or even an alternative to traditional sleep analysis.

Cefixime removal via WO3/Co-ZIF nanocomposite using machine learning methods.

In this research, an upgraded and environmentally friendly process involving WO3/Co-ZIF nanocomposite was used for the removal of Cefixime from the aqueous solutions. Intelligent decision-making was employed using various models including Support Vector Regression (SVR), Genetic Algorithm (GA), Artificial Neural Network (ANN), Simulation Optimization Language for Visualized Excel Results (SOLVER), and Response Surface Methodology (RSM). SVR, ANN, and RSM models were used for modeling and predicting results, while GA and SOLVER models were employed to achieve the optimal conditions for Cefixime degradation. The primary goal of applying different models was to achieve the best conditions with high accuracy in Cefixime degradation. Based on R analysis, the quadratic factorial model in RSM was selected as the best model, and the regression coefficients obtained from it were used to evaluate the performance of artificial intelligence models. According to the quadratic factorial model, interactions between pH and time, pH and catalyst amount, as well as reaction time and catalyst amount were identified as the most significant factors in predicting results. In a comparison between the different models based on Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and Coefficient of Determination (R2 Score) indices, the SVR model was selected as the best model for the prediction of the results, with a higher R2 Score (0.98), and lower MAE (1.54) and RMSE (3.91) compared to the ANN model. Both ANN and SVR models identified pH as the most important parameter in the prediction of the results. According to the Genetic Algorithm, interactions between the initial concentration of Cefixime with reaction time, as well as between the initial concentration of Cefixime and catalyst amount, had the greatest impact on selecting the optimal values. Using the Genetic Algorithm and SOLVER models, the optimum values for the initial concentration of Cefixime, pH, time, and catalyst amount were determined to be (6.14 mg L-1, 3.13, 117.65 min, and 0.19 g L-1) and (5 mg L-1, 3, 120 min, and 0.19 g L-1), respectively. Given the presented results, this research can contribute significantly to advancements in intelligent decision-making and optimization of the pollutant removal processes from the environment.

A proposed hybrid model of ANN and KNN for solar cell defects detection and temperature prediction using fuzzy image segmentation.

This paper presents a novel hybrid model employing Artificial Neural Networks (ANN) and Mathematical Morphology (MM) for the effective detection of defects in solar cells. Focusing on issues such as broken corners and black edges caused by environmental factors like broken glass cover, dust, and temperature variations. This study utilizes a hybrid model of ANN and K-Nearest Neighbor (KNN) for temperature prediction. This hybrid approach leverages the strengths of both models, potentially opening up new avenues for improved accuracy in temperature forecasting, which is critical for solar energy applications. The significance lies in the interconnectedness of temperature fluctuations and solar cell efficiency, leading to defects. The proposed model aims to predict temperatures accurately, providing insights into potential solar cell efficiency problems. Subsequently, this work studies the transitions to defect detection using Fuzzy C-Means (FCM) clustering and MM techniques. The hybrid model demonstrates accurate temperature prediction with Mean Absolute Percentage Error (MAPE) values of 0.92 %, 0.72 %, and 1.3 % for average, maximum, and minimum temperatures, respectively. The defect detection process yields a detection accuracy (CR) of 96 % and sensitivity of detection (SD) of 89 %. This work is validated compared to the literature work done and by using K-fold cross validation technique. The proposed work emphasizes the improvement in defect detection accuracy and the overall quality enhancement of solar cells.