Adaptive Neuro-fuzzy Inference System Model Research Articles

Efficiency increment of CFD modeling by using ANFIS artificial intelligence for thermal-based separation modeling

This study presents a comprehensive analysis of predicting the temperature in a vacuum membrane distillation (VMD) process. The simulation was carried out via computational fluid dynamics (CFD) as well as machine learning. CFD was performed for obtaining temperature distribution in the feed solution, and the calculated temperature was used for training several machine learning models. The dataset comprises over 13,000 observations, which provide a rich source for modeling complex relationships. Three sophisticated regression models were employed: Adaptive Neuro-Fuzzy Inference System (ANFIS), Kernel Ridge Regression (KRR), and Multi-Layer Perceptron (MLP). ANFIS was chosen for its hybrid nature, combining neural networks and fuzzy logic, effectively capturing intricate non-linear relationships in data. ANFIS performance in fitting the data was compared with the other models. Hyper-parameter optimization for these models was conducted using the Tabu Search algorithm to ensure optimal performance. The ANFIS model demonstrated superior performance with an R2 score of 0.9964513 on the training set and 0.9964507 on the test set, alongside a MSE of 0.037655 and a MAE of 0.168272. The robustness of ANFIS was further confirmed by a 3-fold cross-validation mean R2 score of 0.9964579 and a standard deviation of 3.3619616e−05.

Method for Predicting Internal Defect Areas of Timber Components Based on an Adaptive Neuro-Fuzzy Inference System

ABSTRACT Internal defects in the timber components of ancient architecture can reduce their effective cross-sectional areas, deteriorate their mechanical performance, and increase the risk of structural failure. To accurately and rapidly determine the extent of internal damage in components of ancient architecture, this study performed damage detection tests on Larix gmelinii (Larch) column specimens using stress wave nondestructive testing technology. An adaptive neuro-fuzzy inference system (ANFIS) model was developed using the cross-sectional wave velocity ratio after investigating the laws of defect identification through stress-wave testing. Stress-wave detection could identify the relative positional correlation of defect areas. However, the accuracy of the defect area detection was inconsistent (8%–98%). The accuracy of the ANFIS model exhibits a diminishing trend as both parameters rejection rate and influence range increase. However, the ANFIS outperformed the stress-wave detection technique and linear regression model with correlation coefficient and prediction accuracy of 0.99 and 88%, respectively. The root mean square error for the ANFIS was reduced by 79% and 70% compared to the stress wave detection method and linear regression model, respectively. Thus, the ANFIS model can precisely forecast areas of internal damage in timber components of historical edifices and can be used to evaluate the safety of ancient timber buildings.

Artificial intelligence‐based modeling of novel non‐thermal milk pasteurization to achieve desirable color and predict quality parameters during storage

AbstractThis study proposed using color components as artificial intelligence (AI) input to predict milk moisture and fat contents. In this sense, an adaptive neuro‐fuzzy inference system (ANFIS) was applied to milk processed by moderate electrical field‐based non‐thermal (NP) and conventional pasteurization (CP). The differences between predicted and experimental data were not significant (p > 0.05) for lightness (L*), redness‐greenness (a*), yellowness‐blueness (b*), total color differences (∆E), hue angle (h), chroma (C), whiteness (WI), yellowness (YI), and browning index (BI). ANFIS well‐predicted milk fat and moisture content using quadratic and two‐factor interaction models with mean errors of .00858–.01260 and correlation coefficient of .8051–.8205. Stability tests showed L* and WI reduced while a*, b*, ΔE, h, C, YI, and BI increased during the storage. NP milk had 77.21% higher half‐life than CP, as predicted by ANFIS modeling. Findings indicated milk quality characteristics could be estimated based on physical parameters (e.g., color components), contributing to sustainable food production.Practical applicationsThe findings offer practical applications of artificial intelligence (AI) as an innovative monitoring and prediction technique to enhance food quality and sustainability. The proposed methodology makes the real‐time prediction of milk quality feasible by leveraging AI and physical parameters. An adaptive neuro‐fuzzy inference system (ANFIS) accurately predicts moisture and fat contents according to color values, facilitating quality assessment. Stability tests during cold storage provide insights into milk quality changes over time, aiding in determining key parameters in predictive modeling. The proposed approach was found to be applicable to both conventional and non‐thermal pasteurized milk. This study also provides a step‐by‐step protocol, facilitating the implementation of emerging technologies in the food industry.

A hybrid model of artificial intelligence integrated into GIS for predicting accidents in water supply networks

The search for an effective and reliable model for predicting accidents on water supply networks by determining their exact locations has always been important for effectively managing water distribution systems. This study, based on the adaptive neuro-fuzzy logical inference system (ANFIS) model, was developed to predict accidents in the city of Kyiv (Ukraine) water supply network. The ANFIS model was combined with genetic algorithms and swarm optimization (ACO) methods and integrated into a GIS to visualize results and determine locations. Forecasts were evaluated according to the following criteria: mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2). Depending on the amount and type of input data, ANFIS optimization with genetic algorithms and swarm optimization (ACO) can, on average, increase the accuracy of ANFIS predictions by 10.1% to 11%. The obtained results indicate that the developed hybrid model may be successfully applied to predict accidents on water supply networks.

Exploring AI approaches for predicting groundwater levels in coastal agro-climatic zones: a case study in Cuttack District, Odisha

Groundwater level (GWL) prediction across various time scales is essential for efficient management and governance of water resources especially in regions characterized by arid and semi-arid climates, and it holds great significance. Within certain coastal regions, agro-climatic zones give rise to challenges like water scarcity in summer and waterlogging during the rainy season, resulting in reduced GWL during scarcity periods and saltwater intrusion that contaminates groundwater. This study emphasizes on application of diverse AI methodologies, encompassing Artificial Neural Networks (ANN), Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Support Vector Regression (SVR), Long Short-Term Memory (LSTM), and Wavelet Transform-based ANN (W-ANN), ANFIS (W-ANFIS), SVR (W-SVR), and LSTM (W-LSTM) models for quantitative assessment of groundwater in Odisha's Cuttack District, aiming to comprehend GWL fluctuations across the region. The investigation leverages historical groundwater data from monitoring wells, incorporating monthly datasets of rainfall, temperature, relative humidity, and GWLs. Through comparative assessment using statistical methods namely Pearson’s R (R), co-efficient of determination (R2), Root Mean Squared Error (RMSE), and Sum of Squared Error (SSE), the most precise and robust AI approach for groundwater estimation in the area is identified. The W-LSTM (R2-0.78196, RMSE- 0.09254, R-0.88428 and SSE-2.66357) and W-ANFIS (R2-0.74068, RMSE-0.08229, R-0.86063 and SSE-2.10596) hybrid algorithms consistently achieved the most accurate predictions for GWLs followed by W-SVR, W-ANN hybrid models and LSTM and ANN for all stations. Overall, this study demonstrated promising outcomes, offering a dependable foundation for water resources planners to guide future investigations into groundwater resources.

A neuro-fuzzy security risk assessment system for software development life cycle

This study aims to protect software development by creating a Software Risk Assessment (SRA) model for each phase of the Software Development Life Cycle (SDLC) using an Adaptive Neuro-Fuzzy Inference System (ANFIS) model. Software developers discovered and validated the risk variables affecting each SDLC phase, following which relevant data about risk factors and associated SRA for each SDLC phase were collected. To create the SRA model for SDLC phases, risk factors were used as inputs, and SRA was used as an output. The formulated model was simulated using 70 % and 80 % of the data for training, while 30 % and 20 % were used for testing the model. The performance of the SRA models using the test datasets was evaluated based on accuracy. According to the study findings, many risk variables were discovered and confirmed for the requirement, design, implementation, integration, and operation phases of SDLC 11, 8, 9, 4, and 6, respectively. The SRA model was formulated using the risk factors using 2048, 256, 512, 16, and 64 inference rules for the requirement, design, implementation, integration, and operation phases, respectively. The study concluded that using the SRA model to assess security risk at each SDLC phase provided a secured software development process.

Indirect prediction of graphene nanoplatelets-reinforced cementitious composites compressive strength by using machine learning approaches

Graphene nanoplatelets (GrNs) emerge as promising conductive fillers to significantly enhance the electrical conductivity and strength of cementitious composites, contributing to the development of highly efficient composites and the advancement of non-destructive structural health monitoring techniques. However, the complexities involved in these nanoscale cementitious composites are markedly intricate. Conventional regression models encounter limitations in fully understanding these intricate compositions. Thus, the current study employed four machine learning (ML) methods such as decision tree (DT), categorical boosting machine (CatBoost), adaptive neuro-fuzzy inference system (ANFIS), and light gradient boosting machine (LightGBM) to establish strong prediction models for compressive strength (CS) of graphene nanoplatelets-based materials. An extensive dataset containing 172 data points was gathered from published literature for model development. The majority portion (70%) of the database was utilized for training the model while 30% was used for validating the model efficacy on unseen data. Different metrics were employed to assess the performance of the established ML models. In addition, SHapley Additve explanation (SHAP) for model interpretability. The DT, CatBoost, LightGBM, and ANFIS models exhibited excellent prediction efficacy with R-values of 0.8708, 0.9999, 0.9043, and 0.8662, respectively. While all the suggested models demonstrated acceptable accuracy in predicting compressive strength, the CatBoost model exhibited exceptional prediction efficiency. Furthermore, the SHAP analysis provided that the thickness of GrN plays a pivotal role in GrNCC, significantly influencing CS and consequently exhibiting the highest SHAP value of + 9.39. The diameter of GrN, curing age, and w/c ratio are also prominent features in estimating the strength of graphene nanoplatelets-based cementitious materials. This research underscores the efficacy of ML methods in accurately forecasting the characteristics of concrete reinforced with graphene nanoplatelets, providing a swift and economical substitute for laborious experimental procedures. It is suggested that to improve the generalization of the study, more inputs with increased datasets should be considered in future studies.

Hybrid ANFIS-ant colony optimization model for prediction of carbamazepine degradation using electro-Fenton process catalyzed by Fe@Fe2O3 nanowire from aqueous solution

Pharmaceutical compounds, such as carbamazepine, have become a concern in aquatic environments due to their wide usage, resistance to degradation, and inefficiency of wastewater treatment processes. Therefore, it is important to find methods to remove these compounds from aqueous solutions. This study focuses on using Fe@Fe2O3 nanowires combined with electro Fenton process in an electrochemical reactor to decompose carbamazepine (CBZ). Various parameters were considered in 81 experiments, such as pH, current density, concentrations of FeSO4·7H2O, carbamazepine, Fe@Fe2O3, and reaction time. The removal efficiency ranged from 30.4 % to 88.6 %. This study utilized a hybrid adaptive neuro fuzzy inference system (ANFIS) combined with the ant colony optimization algorithm (ACO). The ACO is integrated with the ANFIS models to determine the optimum values for the studied parameters. The implementation of optimization through ACO enhances the ANFIS models' ability. A total of 65 data points were used for training the model, and 16 data points were used to test it. The model's performance was assessed using the coefficient of determination (R2 = 0.9988), the root-mean-squared error (RMSE = 4.54E-03), and the average absolute relative deviation (AARD% = 0.7153). The optimal input parameters for CBZ removal were determined as follows: concentrations of CBZ, FeSO4·7H2O and Fe@Fe2O3 nanowire dose of 9.0 mg/L, 4.5 mg/L, and 1050.0 mg/L; contact time of 45.0 min; pH of 4.0; and current of 0.18 A, resulting in a removal efficiency of 91.2 %. Additionally, the extended Fourier amplitude sensitivity test (EFAST) sensitivity analysis was applied to assess the influence of individual input parameters or their interactions on the model's output.

Advanced Prognostic Models for Bearing Health: A Comparative Analysis of BiLSTM and ANFIS

Bearings play a critical role in the operation of rotary machines, serving as essential components. Their failure often leads to unexpected shutdowns, posing a significant risk to the entire system. To mitigate these risks, it is imperative to implement proactive maintenance measures and strategic planning to prevent system breakdowns. This article introduces a comparative analysis between two predictive modelling approaches: Bidirectional Long Short-Term Memory (Bi-LSTM) and Adaptive Neuro Fuzzy Inference System (ANFIS) networks, aiming to enhance bearing prognostics. The proposed methodology involves a two-step process. Firstly, data undergoes pre-processing through wavelet packet decomposition (WPD). Subsequently, a degradation model is employed for predicting the remaining useful life (RUL). To validate the accuracy of the proposed approach, extensive testing is conducted using a bearing's life dataset obtained from a run-to-failure experiment. The results demonstrate that the ANFIS model exhibits remarkable capabilities in learning and accurately estimating the system's RUL, achieving this with minimal computation time compared to alternative methods, thus presenting a more efficient and precise solution.

Comparative assessment of deep belief network and hybrid adaptive neuro-fuzzy inference system model based on a meta-heuristic optimization algorithm for precise predictions of the potential evapotranspiration

Accurately predicting potential evapotranspiration (PET) is crucial in water resource management, agricultural planning, and climate change studies. This research aims to investigate the performance of two machine learning methods, the adaptive network-based fuzzy inference system (ANFIS) and the deep belief network (DBN), in forecasting PET, as well as to explore the potential of hybridizing the ANFIS approach with the Snake Optimizer (ANFIS-SO) algorithm. The study utilized a comprehensive dataset spanning the period from 1983 to 2020. The ANFIS, ANFIS-SO, and DBN models were developed, and their performances were evaluated using statistical metrics, including R2, Radj2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}_{adj}^2$$\\end{document}, NSE, WI, STD, and RMSE. The results showcase the exceptional performance of the DBN model, which achieved R2 and Radj2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}_{adj}^2$$\\end{document} values of 0.99 and NSE and WI scores of 0.99 across the nine stations analyzed. In contrast, the standard ANFIS method exhibited relatively weaker performance, with R2 and Radj2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}_{adj}^2$$\\end{document} values ranging from 0.52 to 0.88. However, the ANFIS-SO approach demonstrated a substantial improvement, with R2 and Radj2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$${R}_{adj}^2$$\\end{document} values ranging from 0.94 to 0.99, suggesting the value of optimization techniques in enhancing the model’s capabilities. The Taylor diagram and violin plots with box plots further corroborated the comparative analysis, highlighting the DBN model’s superior ability to closely match the observed standard deviation and correlation and its consistent and low-variance predictions. The ANFIS-SO method also exhibited enhanced performance in these visual representations, with an RMSE of 0.86, compared to 0.95 for the standard ANFIS. The insights gained from this study can inform the selection of the most appropriate modeling technique, whether it be the high-precision DBN, the flexible ANFIS, or the optimized ANFIS-SO approach, based on the specific requirements and constraints of the application.

Investigating the effects of surface water recharge on groundwater quality using hydrochemistry and ANFIS model: A case study Minia Governorate, Egypt

Monitoring and assessing groundwater quality and quantity lays the basis for sustainable management. Therefore, this research aims to investigate various factors that affect groundwater quality, emphasizing its distance to the primary source of recharge, the Nile River. To this end, two separate study areas have been considered, including the West and West-West of Minia, Egypt, located around 30 and 80 km from the Nile River. The chosen areas rely on the same aquifer as groundwater source (Eocene aquifer). Groundwater quality has been assessed in the two studied regions to investigate the difference in quality parameters due to the river's distance. The power of machine learning to associate different variables and generate beneficial relationships has been utilized to mitigate the cost consumed in chemical analysis and alleviate the calculation complexity. Two adaptive neuro-fuzzy inference system (ANFIS) models were developed to predict the water quality index (WQI) and the irrigation water quality index (IWQI) using EC and the distance to the river. The findings of the assessment of groundwater quality revealed that the groundwater in the west of Minia exhibits suitability for agricultural utilization and partially meets the criteria for potable drinking water. Conversely, the findings strongly recommend the implementation of treatment processes for groundwater sourced from the West-West of Minia before its usage for various purposes. These outcomes underscore the significant influence of surface water recharge on the overall quality of groundwater. Also, the results revealed the uncertainty of using sodium adsorption ratio (SAR), Sodium Percentage (Na%), and Permeability Index (PI) techniques in assessing groundwater for irrigation and recommended using IWQI. The developed ANFIS models depicted perfect accuracy during the training and validation stages, reporting a coefficient of correlation (R) equal to 0.97 and 0.99 in the case of WQI and 0.96 and 0.98 in the case of IWQI. The research findings could incentivize decision-makers to monitor, manage, and sustain groundwater.

A hybrid long-term industrial electrical load forecasting model using optimized ANFIS with gene expression programming

Electric energy demand forecasting is vital in contemporary power systems, especially amidst market deregulation trends and the increasing influence of industrial customers on power dynamics. However, existing forecasting models encounter challenges such as slow convergence and high complexity. Addressing these issues, this study proposes a hybrid forecasting model that combines the Adaptive Neuro-Fuzzy Inference System (ANFIS) with Gene Expression Programming (GEP) to enhance predictions of electrical energy consumption. Validated using real-time monthly electrical load data from an industrial user in Uganda, the hybrid model outperforms individual ANFIS and GEP models, demonstrating reduced errors and minimal computation time. The application of this hybrid model presents promising results, showcasing exceptional predictive capabilities and offering potential improvements in efficiency and precision for electrical energy consumption forecasting amidst market deregulation and evolving industrial dynamics.

Vital health indicator based state of health estimation of lithium-ion battery by adaptive neuro-fuzzy inference system

ABSTRACT The battery management system (BMS) in electric vehicles (EVs) relies on State of Health (SOH) assessment to monitor battery health and ensure performance. BMS can detect and prevent cell balance, thermal runaway, and extend its lifespan. Methodical charging and discharging under different circumstances reduce battery degradation. Grid Partitioning (GP), Subtractive Clustering (SC), and Fuzzy C-Means (FCM) from the Adaptive Neuro-Fuzzy Inference System (ANFIS) have been employed to predict battery SOH in this work. This study examines charge-discharge cycles of 8 lithium-ion pouch cells from the Oxford Battery Degradation Dataset. Charging cycle data extracts the five vital health indicators (VHIs), whereas discharging cycle data calculates cell capacity. For analyzing the effects of VHIs on SOH, a correlation matrix is formed. Three instances are defined depending on the individual VHIs impacts. Instance 1 utilizes VHI 1, VHI 2, and VHI 5, instance 2 utilizes VHI 3 and VHI 4, and instance 3 uses all VHIs as inputs. Due to enormous data points, only even-numbered cell data is utilized for training the ANFIS model, while odd-numbered cell data is used for validation and testing. In the best-case scenario, instance 1 gives the lowest root mean square error (RMSE) from all the methods.

A neuro-fuzzy based prediction modeling and mechanical characterization of multiwalled-carbon nanotubes filled Luffa cylindrica hybrid core and isotropic skin-based sandwich plate

The study focuses on mechanical characterization and adaptive neuro-fuzzy inference system (ANFIS)-based prediction modeling of MWCNT-filled Luffa cylindrica hybrid core-based sandwich plates. Experiments determine natural frequencies using modal impact hammer tests with a Fast Fourier Transform (FFT) analyzer. Elastic properties from tensile tests utilized for numerical simulations of natural frequencies in ABAQUS, showing high consistency with experimental results. SEM analysis characterizes the fiber-matrix bond in the hybrid core. ANFIS modeling establishes input–output relationships for unseen data sets. Comparisons of numerical simulations with ANFIS predictions demonstrate an accuracy within a 5% margin of error, providing insights into dynamic behavior and potential applications.

Effects on quality characteristics of ultrasound-treated gilaburu juice using RSM and ANFIS modeling with machine learning algorithm

Gilaburu (Viburnum opulus L.) is a red-colored fruit with a sour taste that grows in Anatolia. It is rich in various antioxidant and bioactive compounds. In this study, bioactive compounds and ultrasound parameters of ultrasound-treated gilaburu water were optimized by response surface methodology (RSM) and adaptive neuro-fuzzy inference system (ANFIS). As a result of RSM optimization, the independent ultrasound parameters were determined as an ultrasound duration of 10.7 min and an ultrasound amplitude of 53.3, respectively. The R2 values of the RSM modeling level were 99.93%, 98.54%, and 99.80%, respectively, and the R2 values of the ANFIS modeling level were 99.99%, 98.89%, and 99.87%, respectively. Some quality parameters of gilaburu juice were compared between ultrasound-treated gilaburu juice (UT-GJ), thermal pasteurized gilaburu juice (TP-GJ), and control group (C-GJ). The quality parameters include bioactive compounds, phenolic compounds, minerals, and sensory evaluation. Bioactive compounds in the samples increased after ultrasound application compared to C-GJ and TP-GJ samples. The content of 15 different phenolic compounds was determined in Gilaburu juice samples, and the phenolic compound of UT-GJ samples increased compared to TP-GJ and C-GJ samples, except for gentisic acid. Ultrasound treatment applied to gilaburu juice enabled its bioactive compounds to hold more in the juice.

Predicting the scouring depth around a rectangular pier with a round nose by artificial intelligence methods

Local scour around bridge piers constitutes a significant phenomenon in river engineering. The development of artificial intelligence models and their capabilities has resulted in the widespread adoption of these models. In the experiments, various factors were considered, encompassing three different pier angles (0, 5, and 10°), six submerged vanes with two angles (20 and 30°) aligned with the flow direction, three vane heights (0, 1.25, and 2.5 cm) on the bed, and a collar. The study evaluated the performance of distinct machine learning models, namely, the multi-linear regression (MLR) model, radial basis function neural network (RBF), multilayer perceptron neural network (MLP), support vector machine (SVM), and adaptive neuro-fuzzy inference system (ANFIS) in predicting the scouring depth. Application of these models (RBF, MLP, ANFIS, SVM, and MLR) yielded positive outcomes, with corresponding R2 values of 0.99, 0.98, 0.97, 0.96, and 0.90 for scour depth assessment. The results demonstrated that the RBF artificial neural network model exhibited excellent generalizability in comparison to the other models. It consistently provided accurate predictions with minimal errors across varying training set sizes. Conversely, the ANFIS model exhibited limited generalizability compared to the other models, as reducing the training set size resulted in a significant increase in prediction errors during testing. Furthermore, although the MLR model demonstrated good generalizability, its prediction error was relatively high compared to the alternative models.

Feasibility of integrated numerical and Adaptive Neuro-Fuzzy Inference System models in predicting the thermophysical properties of unsteady coupled micropolar–Casson hybrid nanofluids

This article aims to probe postulated phenomena using a paired micropolar and Casson hybrid fluid over a rotating disk. The intension to design a numerical technique (Runge–Kutta fourth-order along with shooting technique) integrated Adaptive Neuro-Fuzzy Inference System (ANFIS) envisioned with a thermal and exponentially space-dependent heat source, nonlinear thermal radiation and entropy production is developed in this phase of work. To ensure that, a nonlinear partial differential equation set of equations has been transformed into an ordinary differential equation by using the proper self-similarity variables. The model's research results, with a few notable outliers, are mostly consistent with those from prior research that was merged into the dataset used to train the ANFIS model. With the impact of active factors, the results are esthetically exhibited for numerous profiles. This displays that with the rise in magnetic field and radiation, the velocity and temperature profiles increase sharply, resulting in a contradiction phenomenon with the decreasing electric field inputs. Also, tilting of vortex viscosity, spin gradient viscosity and microinertia density on the various microrotation components displays inclination. Moreover, ANFIS training was exploited to analyze the approximate solutions for specific scenarios, and the developed ANFIS was evaluated against a testing dataset to emphasize its performance. Due to their longer render, the nanoparticles exploited here are deemed suitable for use in bone implants, iodinated agents for blood imaging and red blood cell stimulation. Thus, the results of this study may be applied to therapeutic anemia therapies.

Investigating the influence of clustering techniques and parameters on a hybrid PSO-driven ANFIS model for electricity prediction

The availability of reliable electrical power, which is essential for a comfortable lifestyle worldwide, requires realistic power usage projections for electric utilities and policymakers, leading to the adoption of machine learning-based modelling tools due to the limitations of traditional power usage projection approaches. However, successful modeling of power usage in neuro-fuzzy models depends on the optimal selection of hyper-parameters. Consequently, this research looked at the major impact clustering methods and hyper-parameter modifications on a particle swarm optimization (PSO)-based adaptive neuro-fuzzy inference system (ANFIS) model. The study examined two distinct clustering methods and other key hyperparameters such as the number of clusters and cluster radius, resulting in a total of 10 sub-models. The performance of the developed models was assessed using four widely recognized performance indicators: root mean square error, mean absolute percentage error (MAPE), mean absolute error (MAE), and coefficient of variation of the root mean square error (CVRMSE). Additionally, the robustness of the optimal sub-model was evaluated by comparing it with other hybrid models based on three different PSO variants. The results revealed that the combination of the ANFIS approach and PSO, specifically with two clusters, yielded the most accurate forecasting scheme with the optimal values for MAPE (7.7778%), MAE (712.6094), CVRMSE (9.5464), and RMSE (909.4998).

Prediction and optimization kerf width in laser beam machining of titanium alloy using genetic algorithm tuned adaptive neuro-fuzzy inference system

In the power diode laser beam machining (DLBM) process, the kerf width (KW) and surface roughness (SR) are important factors in evaluating the cutting quality of the machined specimens. Apart from determining the influence of process parameters on these factors, it is also very important to adopt multi-response optimization approaches for them, in order to achieve better processing of specimens, especially for hard-to-cut materials. In this investigation, adaptive neuro-fuzzy inference system (ANFIS) and genetic algorithm tuned ANFIS (GA-ANFIS) were used to predict the KW on a titanium alloy workpiece during DLBM. Five machining process factors, namely power diode, standoff distance, feed rate, duty cycle, and frequency, were used for the development of the model due to their correlation with KW. As in some cases, traditional soft computing methods cannot achieve high accuracy; in this investigation, an endeavor was made to introduce the GA-assisted ANFIS technique to predict kerf width while machining grooves in a titanium alloy workpiece using the DLBM process based on experimental results of a total of 50 combinations of the process parameters. It was observed that FIS was tuned well using the ANN in the ANFIS model with an R2 value of 0.99 for the training data but only 0.94 value for the testing dataset. The predicting performance of the GA-ANFIS model was better with less value for error parameters (MSE, RMSE, MAE) and a higher R2 value of 0.98 across different folds. Comparison with other state-of-the-art models further indicated the superiority of the GA-ANFIS predictive model, as its performance was superior in terms of all metrics. Finally, the optimal process parameters for minimum KW and SR, from gray relational–based (GRB) multi-response optimization (MRO) approach, were found as 20 W (level 2) for laser power, 22 mm (level 5) for standoff distance, 300 mm/min (level 5) for feed rate, 85% (level 5) for duty cycle, and 18 kHz (level 3) for frequency.

Precision in Insurance Forecasting: Enhancing Potential with Ensemble and Combination Models based on the Adaptive Neuro-Fuzzy Inference System in the Egyptian Insurance Industry

ABSTRACT Enhancing the precision of retention ratio predictions holds profound significance for insurance industry decision-makers and those vested in advancing insurance services. Precision helps insurance companies navigate inflationary pressures and evaluate underwriting profitability, enabling reliable prognoses of future underwriting gains. As far as we know, although there have been multiple attempts to construct a predictive model for retention ratio, none of these attempts have used combining models or studied the Egyptian market. Therefore, this study contributes significantly to this developing field by providing combining models, which combined statistical time series models such as Exponential Smoothing (ES), and Autoregressive Integrated Moving Average (ARIMA), with Adaptive Neuro-Fuzzy Inference System (ANFIS). Two different types of combinations are employed with these models. Furthermore, the study introduces three ensemble models designed for the purpose of predicting the retention ratio within the Egyptian insurance market. Dataset was carefully gathered from the EFSA’s annual reports, focused on the property-liability insurance sector within the Egyptian insurance market and covers the time period from 1989 to 2021. Next, the proposed models are assessed employing well-established statistical assessment metrics, namely, Mean Absolute Error (MAE), Mean Absolute Percent Error (MAPE), R Square (R2), and Root Mean Square Error (RMSE). The results show that combining and ensemble methods improve predicted accuracy. A multi-linear regression-based ensemble model that combines ARIMA, ES, and ANFIS models outperforms both single and combined models in robustness. The article concludes that the insurance industry can greatly benefit from modern predictive methods to make sound decisions.