Fuzzy Modeling Approach Research Articles

Identifying Key Factors of Reputational Risk in Finance Sector Using a Linguistic Fuzzy Modeling Approach

Management of reputational risk is crucial for financial institutions to establish a solid foundation for strategic decisions, gain customer trust, and enhance resilience against environmental adversities, as they largely operate on digital platforms. Since this becomes even more significant as online transactions and digital interactions amplify the visibility and potential impact of reputational issues in the context of electronic commerce, it is essential to thoroughly investigate environmental factors to achieve a comprehensive understanding of reputational risk. However, measuring and evaluating their influence on reputational risk is challenging due to their inherent connection to human perception. This study aims to explore the factors influencing reputational risk of financial organizations to mitigate potential reputational losses by addressing uncertainties associated with concepts such as vagueness. The employed methodology integrates the Decision-Making Trial and Evaluation Laboratory and Fuzzy Cognitive Map techniques using linguistic fuzzy terms. This approach focuses on both the direct effects of factors on reputational risk and the indirect effects arising from interdependencies between factors. Linguistic fuzzy variables enable us to consider the hesitation of the experts and the vagueness of human judgment. To validate the results, factors are also weighted using the fuzzy Stepwise Weight Assessment Ratio Analysis (SWARA) method. The most influential factors identified by both methods are market value, revenue, risk culture, shareholder value, firm performance, reputation awareness, and return on equity. Additionally, factors affecting other factors include firm performance, revenue, and growth opportunities.

Reliable Finite‐Time Control for Nonlinear Chaotic Semi‐Markov Jump Systems With Incomplete Transition Rates

ABSTRACTThis article studies the finite‐time control problem for a class of nonlinear chaotic semi‐Markov jump systems with incomplete transition rates described by the T‐S fuzzy model approach. As a means to depict the dynamical properties pertaining to the examined system, parametric uncertainties, faults, external disturbances and input saturation are taken into consideration. The foremost objective of this study is to come up with a composite control mechanism that effectively rejects and attenuates the repercussions of faults and disturbances. In particular, we primarily built a disturbance observer in order to obtain a precise estimation of the external disturbances. After which, the fault diagnosis observer is designated to effectively estimate the faults. Specifically, a composite reliable control mechanism is developed by fusing the output of the constructed observers with the mode‐dependent fuzzy‐rule based state feedback controller. By employing suitable Lyapunov functions in conjunction with the linear matrix inequality technique, a set of mode‐dependent conditions is derived to ensure the finite‐time stochastic boundedness of the underlying closed‐loop and estimation error systems. Following this, the anticipated controller and observer gain matrices are elicited by resolving the established linear matrix inequalities. Thereafter, intending to ascertain the efficacy and usefulness of accrued theoretical findings, simulation results performed on Chua's circuit system is endowed.

Unravelling poly(1-vinyl-1,2,4-triazole) hydrogels behaviors and enhancing 5-Fluorouracil delivery systems by utilizing a fuzzy modelling approach

In recent years, fuzzy-hybrid systems have been reported in biomedical applications due to their ability to handle uncertainties, provide flexibility, identify optimal production processes, and integrate experimental data sources to create reliable decision support mechanisms. This study focuses on introducing a fuzzy-hybrid methodology to model the swelling behavior of poly(1-vinyl-1,2,4-triazole) (PVTAz) hydrogels and the drug release profile of PVTAz hydrogels loaded with 5-Fluorouracil. The proposed fuzzy-hybrid approach was utilized in modelling swelling behavior of the PVTAz hydrogels as a fuzzy function of time, temperature, pH, and the drug release behavior as a fuzzy function of time only. All the obtained models were illustrated with respect to the experimental data, showing their effectiveness and applicability. Performance metrics (ARE, RMSE, R2) were calculated for the fuzzy-hybrid supported swelling behavior and drug release models: (ARE = 6.9492, RMSE = 150.59, R2 = 0.9529) and (ARE = 4.2956, RMSE = 2.2889, R2 = 0.9879), respectively. This study significantly advances our understanding of hydrogel behaviors in drug delivery systems, highlighting interdisciplinary synergy that enhances research outcomes.

Finite-Time Fault-Tolerant Control of Nonlinear Spacecrafts with Randomized Actuator Fault: Fuzzy Model Approach

The primary objective of this paper is to address the challenge of designing finite-time fault-tolerant control mechanisms for nonlinear flexible spacecraft systems, which are particularly vulnerable to randomized actuator faults. Diverging from traditional methodologies, our research harnesses the capabilities of the Takagi–Sugeno (T–S) fuzzy framework. A unique feature of our model is the representation of actuator failures as stochastic signals following a Markov process, thereby offering a robust solution for addressing timeliness concerns. In this paper, we introduce a generalized reciprocally convex inequality that includes adjustable parameters, broadening the scope of previous results by accommodating them as special cases. Through the amalgamation of this enhanced inequality and flexible independent parameters, we propose an innovative controller design strategy. This approach establishes a stability standard that guarantees mean-square H∞ performance. In order to validate the efficacy of the suggested strategy, we present a numerical illustration involving a nonlinear spacecraft system, showcasing the practical advantages and feasibility of our proposed technique.

Strategic Placement of Nuclear Power Plants in Pakistan: A Complex Polytopic Fuzzy Model Approach with Confidence Level Assessment

Strategic Placement of Nuclear Power Plants in Pakistan: A Complex Polytopic Fuzzy Model Approach with Confidence Level Assessment

Disturbance rejections of polynomial fuzzy systems under equivalent-input-disturbance estimator approach

This paper proposes an integrated robust stabilization and anti-disturbance control scheme for nonlinear systems using a polynomial fuzzy model approach. To estimate unknown disturbances, an equivalent-input-disturbance (EID) estimator is employed. The proposed approach incorporates a novel fuzzy model assisted by EID estimator into the sum-of-squares-based approach, utilizing a polynomial fuzzy model-based observer to estimate the disturbance effect. A suitable fuzzy rule-based control law is developed by utilizing the parallel distributed compensation approach and the output of the EID estimator. To ensure stability, fuzzy membership functions are converted into sum-of-square polynomials using a polynomial curve fitting approach, allowing their exact shape information to be used in the stability condition. The addressed system is transformed into an augmented system by incorporating the system, observer, and filter states, simplifying the analysis. Gain matrices for the controller and observer are obtained using Lyapunov stability theory and sum-of-squares methods to confirm asymptotic stabilization of the fuzzy system. Two numerical examples are presented to demonstrate the effectiveness of the proposed control design method.

Sustaining altitude pastures in mountain landscapes–a fuzzy cognitive model approach

Similarly to other European mountain areas, in Serra da Estrela the grazing pressure has been reducing due to social and economic drivers that have pushed shepherds and sheep to the foothill, or plainly out of the sector. Shrub encroachment on commons and other previously grazed land is one of the most tangible effects of pastoral abandonment in Serra de Estrela. The impacts of the resulting increase in landscape continuity and biomass availability were made clear in the severe fires of 2017 and 2022. As fire risk is likely to increase with climate change, it becomes urgent to understand what strategies can be deployed to keep fragmentation in these landscapes. Key actors such as shepherds should be involved in this discussion to understand their perceptions, points of view and reasons for abandoning upland pastures. In this study, we use fuzzy cognitive mapping to identify the key variables and mechanisms affecting the pastoral system according to local shepherds. In our study, we developed with local stakeholders a framework outlining the local pastoral system. Based on that, we carried out the fuzzy cognitive mapping collecting 14 questionnaires. We found that shepherds' income is a central issue, but that it is highly dependent on many factors. Increasing the Common Agricultural Policy payments alone is not enough to incentivise the use of upland pastures. More targeted strategies, such as more support for shrub clearing, and direct payments conditional to transhumance are more impactful. Despite a contentious discourse between conservation and shepherding values in Serra da Estrela, we find that shepherd's values are aligned with biodiversity conservation and a potential nature-based solution for minimizing fire risk through woody fuel management. This opens up possibilities for new governance strategies, that put Serra da Estrela's social, environmental and cultural values at its core.

Air pollution concentration fuzzy evaluation based on evidence theory and the K-nearest neighbor algorithm

Background: Air pollution, characterized by complex spatiotemporal dynamics and inherent uncertainty, poses significant challenges in accurate air quality prediction, and current methodologies often fail to adequately address these complexities.Objective: This study presents a novel fuzzy modeling approach for estimating air pollution concentrations.Methods: This fuzzy evaluation method integrates an improved evidence theory with comprehensive weighting and the K-nearest neighbor (KNN) interval distance within the framework of the matter-element extension model. This involves generating the basic probability assignment (BPA) based on interval similarity, performing sequential fusion using the Dempster–Shafer evidence theory, enhancing the fusion results via comprehensive weighting, and conducting fuzzy evaluation of air pollution concentrations using the matter-element extension KNN interval distance.Results: Our method achieved significant improvements in monitoring air pollution concentrations, incorporating spatiotemporal factors and pollutant concentrations more effectively than existing methods. Implementing sequential fusion and subjective–objective weighting reduced the error rate by 38% relative to alternative methods.Discussion: Fusion of multi-source air pollution data via this method effectively mitigates inherent uncertainty and enhances the accuracy of the KNN method. It produces more comprehensive air pollution concentration fusion results, improving accuracy by considering spatiotemporal correlation, toxicity, and pollution levels. Compared to traditional air-quality indices, our approach achieves greater accuracy and better interpretability, making it possible to develop more effective air quality management strategies. Future research should focus on expanding the dataset to include more diverse geographical and meteorological conditions, further refining the model to integrate external factors like meteorological data and regional industrial activity, and improving computational efficiency for real-time applications.

A multi-criteria model of supply chain sustainability assessment and improvement for sugarcane agroindustry

The sustainability of the sugarcane agro-industry supply chain plays a crucial role in providing economic benefits, minimizing social and environmental impacts, and optimizing resource utilization. This research aims to analyze the sustainability performance of the sugarcane agro-industry supply chain using multi-criteria assessment and formulate strategies for sustainability improvement. The study proposes a multi-criteria assessment model with twenty-eight indicators and four dimensions of sustainability: economic, social, environmental, and resources, which were developed based on previous research. The fuzzy inference system (FIS) and multi-dimensional scaling (MDS) methods were utilized to analyze the multi-criteria indicators of sustainability performance in each dimension and overall supply chain. The Adaptive Neuro Fuzzy Inference System (ANFIS) model was used to aggregate multi-dimension sustainability to achieve overall sustainability performance. A fuzzy cognitive map (FCM) framework was developed to formulate strategies for improving the sustainability performance of the supply chain. The research was verified at two sugar mill locations in Java Island, Indonesia. The FIS and MDS models successfully analyzed the sustainability performance of the two sugar agro-industries, showing an average value of “quite sustainable”. The overall sustainability performance using the ANFIS model for mill A and B were 57.2 and 61.9, respectively. Series of FGDs combined with the FCM model successfully formulated five clusters of strategies as initiatives in improving the sustainability performance, namely raw material provision, harvesting and post-harvest activities, production process optimization, IT-based technology implementation, and institutional aspects. This present work seeks to contributes to the development of multi-criteria of sustainability performance for the food industry's supply chain. It also proposes a comprehensive framework for analyzing and improving sustainable supply chain performance under uncertainty using a combination of conventional and fuzzy assessment modeling approach. A practical initiative strategy in sustainability improvement is revealed for the sugarcane agroindustry's supply chain.

Tracking control design for cyber‐physical systems with disturbances and input delays: An interval type‐2 fuzzy approach

SummaryThe underlying intention of this work is to devise a tracking control protocol for the nonlinear cyber‐physical systems that are prone to external disturbances, time‐varying input delays and deception attacks. To be more precise, the modified repetitive tracking controller is formulated for ensuring the asymptotic tracking outcomes of the assayed system with the aim of addressing the impacts caused by external disturbances as well as input time‐varying delays. First of all, the nonlinearities of the investigated cyber‐physical systems are efficaciously approximated by the interval type‐2 fuzzy model approach. Further, the predictor technique is utilized in this study to mitigate the influence of input delays and specifically, the extended Smith predictor approach is employed. That is, the transfer function is inserted into the conventional Smith predictor's main feedback channel. In parallel, the active disturbance rejection technique is executed to reject and estimate the external disturbance impacts on the assayed system. Notably, the improved equivalent‐input‐disturbance estimator approach is tied up and more precisely, the estimated disturbances obtained from the afore‐said estimator are incorporated into the proposed controller. Whilst the deception attacks are characterized as a stochastic distributed random variable that are governed by the Bernoulli distribution. With all of this as a backdrop, the appropriate delay‐dependent constraints are expressed in the context of linear matrix inequalities by employing the Lyapunov stability theory. In line with the predetermined criteria, the relations for computing the required gain matrices are also formulated. Ultimately, the simulation analysis is carried out using two distinct numerical examples to confirm the importance of the proposed control mechanism from the perspective of theory as well as practice.

Fuzzy membership-function-dependent design of aperiodic sample-data control scheme for nonlinear PMSG-based WECS with quantization measurements via refined looped Lyapunov functional

This manuscript investigates the fuzzy memory sampled-data control (MSDC) scheme for the nonlinear permanent magnet synchronous generator (PMSG)-based wind energy conversion system (WECS) with quantization measurements. First, due to the complex nonlinearity, a Takagi-Sugeno (T-S) fuzzy modeling approach is successfully applied to the dynamics of nonlinear PMSG-based WECS. Second, by using the information of both quantized aperiodic sampling pattern and signal transmission delay, an H∞-based fuzzy quantized controller is put forward to ensure the stable performance as well as disturbance suppression index of the considered PMSG model by utilizing the refined looped Lyapunov functional (RLLF) approach. This RLLF perfectly utilizes more realistic information about the time derivative of the fuzzy membership function and actual sampling pattern. Then, two new integral inequalities are introduced to approximate the quadratic integral terms arising from the derivative of RLLF. Next, we establish some less conservative stabilization results in terms of linear matrix inequalities (LMIs) using the constructed RLLF, along with the proposed integral inequalities and fuzzy membership function-dependent (MFD) switching ideas. Finally, the simulation studies of PMGS-based WECS are validated numerically, and then a comparative example is provided to emphasize the superiority and relevance of the suggested approach.

Fuzzy modelling approach and soft computing mechanism for predicting cognitive impairment in old people

Growing older is a phenomenon that is associated with increasingly complex health situations as a result of the coexistence of several chronic diseases. As a result, there is a downward tendency in both older people and their caretakers’ quality of life, which frequently results in frailty. There are numerous solutions available to treat the issue, which primarily affects older people. The basic and most popular imaging method for predicting cognitive impairment is magnetic resonance imaging. Furthermore, few of the earlier models had a definite level of accuracy when diagnosing the condition. Further, there is a critical need to put in place a stronger, more reliable approach to precise prediction. When compared to other procedures, using magnetic resonance images to predict cognitive decline is the safest and most straightforward. The advanced concept for a better optimized strategy to predict cognitive impairment at an early stage is presented in this research. The hybrid krill herd and grey wolf optimization method is offered as a solution to address the challenges in locating the impacted area. In a short amount of time, a significant number of MRI images are analyzed, and the results show a more precise or higher rate of recognition.

Dynamic Output Feedback-Based Tracking Control Design With Input Time-Varying Delay for Fuzzy Systems

The prime purpose of this study is to design an output tracking control law in the perspective of compensating the effects induced by time-varying input delays and disturbances. In particular, the control protocol is developed for nonlinear systems, where the nonlinearities are effectively represented as a convex summation of linear subsystems using membership functions, which is precisely referred by fuzzy model approach. Accordingly, with the aid of parallel distributed compensation strategy and extended Smith predictor approach, the fuzzy-dependent dynamic control law is formulated. Moreover, the improved-equivalent-input-disturbance estimator approach is implemented to estimate the disturbance signals, whose output are tied to the resultant dynamic output feedback controller. On such circumstances, the controller gain matrices that assures the asymptotic tracking performance of the addressed system is calculated by solving the derived set of sufficient conditions. Conclusively, the effectiveness of the developed theoretical outcomes is validated by virtue of numerical simulations.

Transitioning drivers from linear to circular economic models: evidence of entrepreneurship in emerging nations

PurposeVarious publications have extensively documented the advantages of a circular economy in ensuring sustainability and limiting climate change. Despite academic records emphasising the need to adopt this business strategy, entrepreneurs in developing countries prefer linear economies. This reluctance is attributable to several factors, including insufficient infrastructure and technology, limited financial access, inadequate education systems and the prevalence of informal enterprises. Therefore, a thorough analysis of the underlying economic, political and social conditions is required to identify the drivers of circular economies (CEs) and their contribution to entrepreneurship in developing countries.Design/methodology/approachIn this study, the authors first conducted a comprehensive quantitative literature review based on LangChain to identify the critical CE drivers from the social, technological and organisational perspectives. Based on the input from the expert panel of Iranian academic and industry professionals, the authors applied an integrated fuzzy interpretive structural modelling and cross-impact matrix multiplication approach to classification (Fuzzy-ISM-MICMAC) to investigate the chronology of entrepreneurial drivers.FindingsLevel-based model results reveal entrepreneurial drivers in developing nations and their interrelationships, specifically underlining the importance of supply chain factors and stakeholder preferences. Thus, the differences between the perception of the main drivers in developed and developing economies can be identified, with the former paying particular attention to legislative and financial factors. The study's findings contribute to conserving resources, reducing waste and adopting more sustainable corporate practices, thereby assisting developing countries in achieving development goals.Originality/valueThis study employs an innovative quantitative systematic literature review approach that relies on a large language model to identify the drivers of the CE. Furthermore, it adopts a systematic approach to examine the enablers of the CE rather than a narrow and individual perspective of the entrepreneurial drivers. The study employs the fuzzy ISM MICMAC technique to showcase the prioritisation of entrepreneurial prospects in emerging economies.

Analysing the Influence of Components of Entrepreneurial Ecosystem on the Entrepreneurial Process

The entrepreneurial ecosystem is a popular concept because of its systematic approach to analysing entrepreneurship and promoting entrepreneurial activity in the region. However, studies on EE have lacked a framework for indicating the influence that EE components have on entrepreneurship. The authors fill this gap in our research by investigating the influence of the components of the entrepreneurial environment on the entrepreneurial process. Entrepreneurial Intention Development, Entrepreneurial Exploration, and Entrepreneurial Exploitation are the three stages of the entrepreneurial process that were identified. To investigate complex systems and grasp the system's causal linkages, fuzzy cognitive modelling approach was employed. This study provides insights into the relationships between the components of the entrepreneurial ecosystem and the entrepreneurial process, which helps to support entrepreneurship during its different phases.

A fuzzy Interpretive Structural Modeling approach for implementing IoT and achieving the United Nations Sustainable Development Goals

The growing demand for data-driven decision-making and the emergence of new business models has led to a rise in digital technologies. As a result, businesses have become more aware of the impact of their activities on the environment, including the production of digital technologies. Sustainability has become a significant concern for businesses worldwide, pushing them to explore ways to integrate sustainable practices into their operations and address this issue. Digitization has emerged as an essential tool, with the Internet of Things (IoT) technology leading the way. Organizations can improve decision-making and enhance operational efficiency with IoT, but aligning its implementation with the United Nations’ Sustainable Development Goals is essential. Concepts like Industry 4.0 and Circular Economy principles have emerged to create sustainable business models, but their implementation faces various challenges. Businesses must adopt analytical methods and tools to support strategic planning. This study applies the Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) method to identify twelve key challenges businesses face in this IoT adoption. A survey was used for gathering expert opinion from industry specialists working in the field of IoT for conducting advanced analytical techniques like Fuzzy Interpretive Structural Modeling (F-ISM) and Matrice d’Impacts Croisés Multiplication Appliqués à un Classement (MICMAC) to highlight the most critical challenges, including loss of value appropriation, Low incentive to change, Less adoption of sustainable practices and Lack of interoperability. While IoT holds great promise for supporting sustainable development, the result highlights the urgent need for stakeholder collaboration to overcome these challenges and unlock its full potential. The findings of this study benefit organizations heavily dependent on digital services like IoT by providing them with a comprehensive framework for effectively implementing IoT towards sustainable development.

Networked fault detection for fuzzy systems using a quantizer with event-triggered strategy

This paper concerns with the problem of fault detection for networked fuzzy systems. Considering the digital communication channel, quantization is adopted to make the data transmission feasible and the induced data distortion is converted into a bounded uncertain term. For the purpose of saving network resources, a new quantizer with an event-triggered strategy is designed to reduce the length and the number of the transmitted data packets, simultaneously. In the process of stability analysis, the T-S fuzzy model approach is employed to approximate the nonlinear networked system, and a more flexible fuzzy design method is presented to get the fault detection filter which can detect the sensor fault in the presence of external disturbance. And sufficient conditions are constructed to guarantee the stability of the filter error system in terms of linear matrix inequalities. Finally, the simulation example is given to verify the feasibility of the method.

Exploring barriers in supply chain disaster management using fuzzy total interpretative structure modeling approach: Insight from Thai automotive industry

Supply chain disaster management (SCDM) has become a topic of interest for academicians and practitioners. Many businesses worldwide are experiencing disasters that disrupt their supply chains. This study attempts to identify the barriers to SCDM implementation and investigate their interrelationships. Fourteen barriers are identified through a broad literature review and certified by a panel of experts. The Fuzzy interpretative structural modeling (Fuzzy-ISM) approach is applied to construct a hierarchical model and identify the contextual relationships among SCDM barriers. Matrice d’ impacts croises-multiplication applique a classement (MICMAC) is deployed to categorize the 14 barriers into four actionable groups based on driving and dependence power. This study contributes to SCDM knowledge by identifying the main barriers to implementation and revealing their interrelationships. This empirical study uses an upstream supply chain in the Thai automotive industry. The results provide insight into the Thai automotive industry to alleviate barriers and efficiently and effectively manage resources while implementing SCDM. Finally, future research directions and theoretical and managerial implications are discussed.

Developing sustainable management strategies in construction and demolition wastes using a q-rung orthopair probabilistic hesitant fuzzy set-based decision modelling approach

Sustainable management of construction and demolition wastes (CDWs) has become a pressing global issue in social, environmental and economic contexts, and it involves complex technological, engineering, management and regulatory challenges. Recently, many CDW management strategies have been developed based on the barrier attributes of reuse distribution. However, no strategy can simultaneously address all barrier attributes of reuse distribution. Furthermore, no research has assessed and modelled the identified CDW management strategies to determine optimality. On this basis, the presence of multiple barrier attributes, varying attribute priority and a wide range of data allow for the modelling of CDW management strategies under complex multiple-attribute decision-making (MADM) problems. This study develops the fuzzy-weighted zero inconsistency (FWZIC) and fuzzy decision by opinion score method (FDOSM)-based multiplicative multiple objective optimisation by ratio analysis (MULTIMOORA) with the q-rung orthopair probabilistic hesitant fuzzy set (q-ROPHFS) to address this problem. The developed q-ROPHFS–FWZIC method prioritised and weighted the main and sub-barrier attributes of reuse distribution in CDW management strategies. The developed q-ROPHFS–FDOSM is used to score the CDW management strategies. Then, the MULTIMOORA method is used to model 51 CDW management strategies to determine the optimum one. Results showed that Strategy 46 modelled first in six q values because it had the most essential attributes (i.e. cost, market, value-for-money, experience, infrastructure, management, risk and trust). Strategy 17 and Strategy 20 are the least sustainable strategies because they had only one attribute (i.e. experience). Sensitivity analysis, systematic modelling and comparison analysis are conducted to validate and evaluate the stability and robustness of the proposed methods. The implications of this study would likely benefit various stakeholders involved in the construction industry, including construction companies, architects, engineers, policy-makers and members of the public.

Improving Automotive Air Conditioning System Performance Using Composite Nano-Lubricants and Fuzzy Modeling Optimization

This study aims to enhance the effectiveness of automobile air conditioning (AAC) systems through the use of composite nano-lubricants and fuzzy modeling optimization techniques. Composite nano-lubricants, which consist of varied metal oxide ingredients and content ratios, are projected to surpass single-component nano-lubricants in terms of improving the performance of AAC systems. Fuzzy modeling is used to simulate the AAC system based on experimental data using three input parameters: volume concentration of nano-lubricants (%), the refrigerant charge (g), and compressor speed (rpm). The output performance of the AAC system is measured using four parameters: cooling capacity (CC) in kW, compressor work (CW) in kJ/kg, coefficient of performance (COP), and power consumption (PC) in kW. Optimization is performed using the marine predators algorithm (MPA) to identify the best values for the input control parameters. The objective function is to minimize CW, COP, and PC while simultaneously maximizing CC and COP. Results showed that the performance of the AAC system improved from 85% to 88% compared to the experimental dataset, highlighting the potential benefits of using composite nano-lubricants and fuzzy modeling optimization for improving the energy efficiency of AAC systems. Furthermore, a comprehensive comparison with ANOVA was performed to demonstrate the superiority of the fuzzy modeling approach. The results indicate that the fuzzy model outperforms ANOVA, as evidenced by a reduced root mean square error (RMSE) for all data, from 0.412 using ANOVA to 0.0572 using fuzzy. Additionally, the coefficient of determination for training increased from 0.9207 with ANOVA to 1.0 with fuzzy, further substantiating the success of the fuzzy modeling phase.