Adaptive Fuzzy Inference System Research Articles

Stacking Ensemble Technique Using Optimized Machine Learning Models with Boruta–XGBoost Feature Selection for Landslide Susceptibility Mapping: A Case of Kermanshah Province, Iran

Landslides cause significant human and financial losses in different regions of the world. A high-accuracy landslide susceptibility map (LSM) is required to reduce the adverse effects of landslides. Machine learning (ML) is a robust tool for LSM creation. ML models require large amounts of data to predict landslides accurately. This study has developed a stacking ensemble technique based on ML and optimization to enhance the accuracy of an LSM while considering small datasets. The Boruta–XGBoost feature selection was used to determine the optimal combination of features. Then, an intelligent and accurate analysis was performed to prepare the LSM using a dynamic and hybrid approach based on the Adaptive Fuzzy Inference System (ANFIS), Extreme Learning Machine (ELM), Support Vector Regression (SVR), and new optimization algorithms (Ladybug Beetle Optimization [LBO] and Electric Eel Foraging Optimization [EEFO]). After model optimization, a stacking ensemble learning technique was used to weight the models and combine the model outputs to increase the accuracy and reliability of the LSM. The weight combinations of the models were optimized using LBO and EEFO. The Root Mean Square Error (RMSE) and Area Under the Receiver Operating Characteristic Curve (AUC-ROC) parameters were used to assess the performance of these models. A landslide dataset from Kermanshah province, Iran, and 17 influencing factors were used to evaluate the proposed approach. Landslide inventory was 116 points, and the combined Voronoi and entropy method was applied for non-landslide point sampling. The results showed higher accuracy from the stacking ensemble technique with EEFO and LBO algorithms with AUC-ROC values of 94.81% and 94.84% and RMSE values of 0.3146 and 0.3142, respectively. The proposed approach can help managers and planners prepare accurate and reliable LSMs and, as a result, reduce the human and financial losses associated with landslide events.

A Comprehensive Evaluation Model for Sustainable Supply Chain Capabilities in the Energy Sector

This study introduces a comprehensive model to evaluate multiple capabilities within the sustainable supply chain evaluation framework. The primary aim is to determine the significance of various capabilities in the context of sustainable supply chains. The research involved a sample of sixteen companies operating in Iran’s energy sector. The findings indicate that the majority of these companies are at level two in terms of capability. Therefore, it is recommended that these companies employ this model to assess their capability levels and identify any existing gaps. Methodologically, a checklist tool was used to refine the criteria using the fuzzy Delphi method. Subsequently, an appropriate model was chosen and developed by reviewing existing evaluation models. The criteria were compared and finalized using the Analytic Hierarchy Process. Finally, the criteria were further refined and validated through a fuzzy expert system, incorporating Adaptive Neuro-Fuzzy Inference System and Fuzzy Inference System. The developed model was then simulated and validated using MATLAB Simulink software (R2017b).

Hybrid Power Generating System Sources and Load Synchronization Using Adaptive-Neural-Fuzzy-Inference-System and Pelican Optimization Algorithm Technique

The integration of renewable energy sources (RESs) into current power networks addresses rising global energy demand and mitigates greenhouse gas emissions. This transition shifts the role of frequency regulation from synchronous generators to power converters, serving as interfaces between the grid and RESs. This paper proposes a hybrid method for optimizing power flow in hybrid power-generating systems. The proposed hybrid technique is the combined execution of an Adaptive-Neural-Fuzzy-Inference-System (ANFIS) and Pelican Optimization Algorithm. Hence it is named as ANFIS-POA technique. POA optimizes current and voltage controllers, while ANFIS predicts optimal system parameters. Implemented in MATLAB, the proposed strategy achieves an impressive efficiency of 96%, outperforming existing strategies like genetic algorithm (GA) and particle swarm optimization (PSO). With a faster settling time (0.56 s), a shorter rising time (1.32 s), and a reduced peak time (5.78 s), the proposed approach performs better than existing methods. Additionally, it significantly lessens system costs (Rs. 99,450) and demonstrates superior statistical performance in terms of lower error rates and improved key metrics like accuracy, precision, and recall compared to existing methods.

A Novel Hybrid ANFIS-NARX and NARX- ANN models to Predict the profitability of Egyptian Insurance Companies

The use of fuzzy logic models with machine learning (ML) models have become common in many areas, especially insurance field. This study aims to compare between non-hybrid models such as artificial neural network (ANN) model, adaptive neural fuzzy inference system (ANFIS) model, nonlinear auto-regressive external input (NARX) model, and the following hybrid models (ANFIS-NARX) and (NARX-ANN) to predict the profits of the insurance activity which represent the important indicator of the good performance of Egypt's 39 insurance companies in the period from 1st January 2009 to 31 December 2022 , monthly .This prediction based on the following factors (net premiums, reinsurance commissions, net income from earmarked investments, other direct income, net compensation, production cost commissions and general and administrative expenses) that help decision makers to make appropriate decisions . The results found that the (ANN) model is given good results compared with the following models (ANFIS), (NARX), hybrid (ANFIS-NARX) and (NARX-ANN) models according to the following prediction accuracy measures (RMSE, MAPE, MAE and Theil inequality). The explanatory ability (R2) was appeared (0.79, 0.61) respectively for training and testing phases in persons insurance companies. The explanatory ability also was appeared (0.83, 0.68) respectively in property insurance companies.

Optimizing Fish Feeding with FFAUNet Segmentation and Adaptive Fuzzy Inference System

Efficient and optimized fish-feeding practices are crucial for enhancing productivity and sustainability in aquaculture. While many studies have focused on classifying fish-feeding intensity, there is a lack of research on optimizing feeding, necessitating a precise and automated model. This study fills this gap with a hybrid solution for precision aquaculture feeding management involving segmentation and optimization phases. In the segmentation phase, we used the novel feature fusion attention U-Net (FFAUNet) to accurately segment fish-feeding intensity areas. The FFAUNet achieved impressive metrics: a mean intersection over union (mIoU) of 89.39%, a mean precision of 95.07%, a mean recall of 95.08%, a mean pixel accuracy of 95.12%, and an overall accuracy of 95.61%. In the optimization phase, we employed an adaptive neuro-fuzzy inference system (ANFIS) with a particle swarm optimizer (PSO) to optimize feeding. Extracting feeding intensity percentages from the segmented output, the ANFIS with PSO achieved an accuracy of 98.57%, a sensitivity of 99.41%, and a specificity of 99.53%. This model offers fish farmers a robust, automated tool for precise feeding management, reducing feed wastage and improving overall productivity and sustainability in aquaculture.

Implementing fuzzy SMRGT, ANN, and ANFIS for flow coefficient estimation in Antalya River Basin

The estimation of the flow coefficient is a vital hydrological procedure that holds considerable importance in flood prediction, water resource management, and flood mitigation. The precise estimation of the flow coefficient is imperative in mitigating flood-related damages, administering flood alert mechanisms, and regulating water discharge. It is hard to accurately determine the flow coefficient without a good understanding of the river basin’s hydrology, climate, topography, and soil characteristics. A range of methodologies have been documented in the most recent body of literaturefor flow coefficient modeling. The majority of these methods, however, depend on opaque techniques that lack generalizability. Therefore, this research employed three distinct methodologies—specifically, the Adaptive Neural Fuzzy Inference System (ANFIS), the Simple Membership Function, and the Fuzzy Rules Generation Technique (SMRGT) are all examples of fuzzy inference systems, and Artificial Neural Network (ANN), to achieve its objectives. The Aksu River Basin in Antalya, Turkey, was chosen as the study area. The models underwent multiple permutations of precipitation (P), temperature (T), relative humidity (Rh), wind speed (Ws), land use (LU), and soil properties (Sp) data that were tailored to the particular study region. The study analyzed the results using various performance metrics of the model such as mean absolute error (MAE), Nash–Sutcliffe efficiency coefficient (NSE), root mean square error (RMSE), and correlation coefficient (R2). The results indicate that the SMRGT method resulted in a remarkable degree of accuracy in forecasting the flow coefficient, as demonstrated with the minimal RMSE and MAE values and high correlation coefficient values. The study’s findings suggest that the SMRGT method was applied effectively in hydrological analysis to estimate the flow coefficient, contributing to more accurate flood prediction, water resource management, and flood mitigation strategies.

EFFICIENT DSP-BASED REAL-TIME IMPLEMENTATION OF ANFIS REGULATOR FOR SINGLE-PHASE POWER FACTOR CORRECTOR

As a widely used technology, active power factor corrector (A-PFC) circuits face many control challenges, such as nonlinearity and uncertainties. With more and more power electrical appliances that are connected to the utility grid, the A-PFC is for the task of improving the power quality (PQ) to meet the requirement of the international standards, and this results in great challenges for keeping the total harmonic distortion (THD) as long as a power factor in the desired ranges. To this end, this paper focuses on the simulation and real-time implementation of a combined adaptive neural-fuzzy inference system (ANFIS) and predictive current controller for a single-phase PFC rectifier. The proposed control method has a simple, low-cost structure for better response and robustness. The performance of the proposed control approach was evaluated in real-time based on the dSPACE 1104 digital signal processor for different reference and load conditions. The results obtained from simulation and experimental tests validate the superiority of the proposed approach by evidencing a unity power factor, lower THD, fast dynamic response, and robustness against fast load and output voltage variations.

Employing Adaptive Neural Fuzzy Inference System Model Via Meta-heuristic Algorithms for Predicting Maximum Dry Density

Employing Adaptive Neural Fuzzy Inference System Model Via Meta-heuristic Algorithms for Predicting Maximum Dry Density

AI-assisted prediction of St14 steel sheets formability: Neural-fuzzy systems and crystal plasticity assessments

We've introduced a new technique leveraging artificial intelligence to determine in-plane forming limit strains in St14 sheet metals. A neural-fuzzy AI system was devised to predict safe points on forming limit diagrams, considering aspects like crystal texture, metal sheet thickness, and spherical punch diameter. Neural-fuzzy systems could be utilized in prediction of forming limit curves using linguistic data description. To obtain the data required for training the AI network, in-depth tests, including XRD, metallography, tensile testing, and Nakazima's hemisphere evaluations, were carried out to detail the metallurgical and mechanical properties of St14 sheet metal. Data on texture, the tensile curves, and grain morphology were then incorporated in crystal plasticity models to find hardening constants for St14's single crystals. Using these determined values, Nakazima's tests were replicated through multi-crystal aggregate configurations. We then undertook a comprehensive parameter investigation via 324 crystal plasticity simulations to shed light on the effects of texture, sheet depth, and punch dimensions on St14's formability. This rich dataset paved the way for training an adaptive neural fuzzy inference system (ANFIS), leading to substantial reductions in time and computational needs. The results validate that the ANFIS model offers accurate and reliable predictions, highlighting its viability for wider use in determining forming limit diagrams.

Modeling and prediction of flame retardant performance of alkyl phosphinate using artificial neural network and adaptive neural fuzzy inference system

AbstractThe flame retardancy of polymer materials is closely linked to the types and compositions of flame retardants used. However, due to the complex relationships involved, it is difficult to quantify and predict flame retardancy using linear equations and models. Alkyl phosphinate flame retardants have emerged as promising candidates for their environmentally friendly, low toxicity, and excellent flame retardant properties. In this study, we aimed to develop a novel, low‐cost alkyl phosphinate flame retardant by predicting the quantitative impact of flame retardant composition on flame retardancy. To establish prediction models for the limiting oxygen index (LOI) value of alkyl phosphinate flame retardants, we utilized artificial neural network (ANN) and adaptive neural fuzzy inference system (ANFIS) programs, namely ANN, ANFIS‐grid partition (GP), and ANFIS‐subtractive clustering (SC). The prediction models were trained and validated, and their reliability was assessed based on the root mean square error (RMSE), coefficient of determination (R2), and mean absolute percentage error (MAPE) criteria. Our results indicate that the ANFIS‐SC prediction model exhibits the highest reliability, with high accuracy and ideal prediction results.

Performance evaluation of BLDC motor drive mounted in aerial vehicle (drone) using adaptive neuro-fuzzy

The development of autonomous drones equipped with cameras and various sensors has paved the way for their application in agriculture and perimeter security. These aerial drones require specific power, acceleration, high torque, and efficiency to meet the demands of agricultural tasks, utilizing built-in brushless DC (BLDC) motors. However, a common challenge drone’s face is maintaining the desired speed for extended periods. Enhancing the performance of BLDC motors through advanced controllers is crucial to address this issue. This research paper proposes optimizing the size and speed of brushless DC motors for aerial vehicles using an adaptive fuzzy inference system and supervised learning techniques. When these drones carry loads, the BLDC motors must dynamically adjust the drone's speed. During this phase, the motors must control their speed and torque using artificial intelligence controllers like adaptive neuro-fuzzy inference systems (ANFIS) to enhance the drone's functionality, resilience, and safety. This research has conducted analyses focused on improving the performance of BLDC motors explicitly personalized for unmanned aerial vehicle (UAVs). The proposed method will be implemented using MATLAB/Simulink, expecting to significantly enhance the BLDC motor's performance compared to conventional controllers. Comparative analyses will be conducted between traditional and ANFIS controllers to validate the effectiveness of the proposed approach.

Estimation of optimal process parameters for minimum wear in the application of SiC/RHA reinforced Al7075 hybrid composites using ANN, ANFIS, and GA

Increasing demand for high-performance materials has led to the exploration of composite materials for enhanced mechanical properties. In this study, a composite of silicon carbide particulate and rice husk ash (RHA) in varying proportions was utilized to reinforce an aluminum alloy (Al7075) hybrid composite fabricated through the stir casting technique. Microstructure examination via an optical microscope ensured the homogeneous distribution of reinforced particles. Wear was evaluated using a pin-on-disc apparatus, considering material factors (% of SiC and % of RHA) and mechanical wear factors (load applied, speed of rotation, and sliding distance). Experimental data were used to develop artificial neural network and adaptive neural fuzzy inference system models, which demonstrated high predictive accuracy. An objective function, formulated to minimize wear via regression analysis, guided the application of a genetic algorithm to determine optimal process parameters. The optimal combination, resulting in a minimum wear of 34.5 µm, comprised 12% SiC, 7% RHA, a sliding speed of 1.9 m/s, an applied load of 11.5 N, and a sliding distance of 715 mm. This study concludes with recommendations for further research and implications for composite material design and optimization.

Comparative study for the performance of pure artificial intelligence software sensor and self-organizing map assisted software sensor in predicting 5-day biochemical oxygen demand for Kauma Sewage Treatment Plant effluent in Malawi

Introduction: Modeling plays a crucial role in understanding wastewater treatment processes, yet conventional deterministic models face challenges due to complexity and uncertainty. Artificial intelligence offers an alternative, requiring no prior system knowledge. This study tested the reliability of the Adaptive Fuzzy Inference System (ANFIS), an artificial intelligence algorithm that integrates both neural networks and fuzzy logic principles, to predict effluent Biochemical Oxygen Demand. An important indicator of organic pollution in wastewater.Materials and Methods: The ANFIS models were developed and validated with historical wastewater quality data for the Kauma Sewage Treatment Plant located in Lilongwe City, Malawi. A Self Organizing Map (SOM) was applied to extract features of the raw data to enhance the performance of ANFIS. Cost-effective, quicker, and easier-to-measure variables were selected as possible predictors while using their respective correlations with effluent. Influents’ temperature, pH, dissolved oxygen, and effluent chemical oxygen demand were among the model predictors.Results and Discussions: The comparative results demonstrated that for the same model structure, the ANFIS model achieved correlation coefficients (R) of 0.92, 0.90, and 0.81 during training, testing, and validation respectively, whereas the SOM-assisted ANFIS Model achieved R Values of 0.99, 0.87 and 0.94. Overall, despite the slight decrease in R-value during the testing stage, the SOM- assisted ANFIS model outperformed the traditional ANFIS model in terms of predictive capability. A graphic user interface was developed to improve user interaction and friendliness of the developed model. Integration of the developed model with supervisory control and data acquisition system is recommended. The study also recommends widening the application of the developed model, by retraining it with data from other wastewater treatment facilities and rivers in Malawi.

Fault Detection and Localization in Transmission Lines Using Adaptive Neural Fuzzy Inference System

Fault Detection and Localization in Transmission Lines Using Adaptive Neural Fuzzy Inference System

ЭФФЕКТИВНОСТЬ АЛГОРИТМА ДЕРЕВА ПРИНЯТИЯ РЕШЕНИЙ В МОДЕЛИ ANFIS НА ПРИМЕРЕ ВОССТАНОВЛЕНИЯ НЕДОСТАЮЩИХ ДАННЫХ

Missing data in water resources studies prevent planning. For this reason, data estimation studies are carried out. In this study, ANFIS (Adaptive Neural Fuzzy Inference System) was used to complete the missing data. At the study area, the Yesilirmak Basin located in the north of Turkey, input variables from seven stations and output variable from one station were determined. In the research, 80% (378 months of data) of 504 months of the flow data between 1969 and 2011 was used in the training phase and 20% (126 months of data) was employed in the testing one. The decision tree was used instead of the trial and error method in the selection of input variables and determining the number of membership functions in ANFIS models. It was concluded that the ANFIS model established with the information obtained from the decision tree is successful compared to the randomly established ANFIS models. Using the decision tree before ANFIS models are created will not only minimize the time spent on the model development, but also prevent the best of the possible models from being overlooked.

A fuzzy model for generalized transportation problems in China

SummaryThis study underscores the growing significance of multimodal transportation within the cargo sector and its consequential environmental impacts. We present a novel mathematical model for operation scheduling, incorporating variables such as resource availability, customer service benchmarks, and environmental considerations. Our objective is to mitigate transportation expenses and reduce delivery delays. The proposed approach advocates LU decomposition with a pivot strategy for rapid model resolution, adherence to convergence criteria, optimization of cost strategies, and efficient resource utilization. Leveraging the adaptive neural fuzzy inference system (ANFIS) and genetic algorithm (GA), our methodology facilitates learning from past decisions to enhance solutions, aligning supply, and demand efficiently. We evaluate financial and environmental implications across four scenarios, offering insights into the economic and environmental advantages of various transportation modes—trains, ships, airplanes—compared to truck transportation, with a specific focus on CO2 emission impacts. Implementing the ANFIS+GA model in multimodal scenarios yield impressive results: minimal MAPE transportation cost of 0.17%, R2 transportation cost of 0.996, MAPE CO2 emissions of 0.13%, and R2 CO2 emissions of 0.996. By identifying cost‐efficient routes and optimizing resource allocations, our approach enables informed decisions regarding vehicle distribution, supplier selection, and contract negotiations. Additionally, we use LU decomposition to establish the supplier risk threshold, crucial for comparing emission trade variances. Multimodal scenarios typically yield lower emissions, favoring buying emission allowances low and selling them high. Notably, the risk threshold affects low‐emission provider utilization, impacting transportation emissions. With a risk threshold of 0.12 and an emission price of 1.2, our ANFIS+GA‐based multimodal approach achieves a significant −20% deviation in CO2 emissions.

Study on the use of different machine learning techniques for prediction of concrete properties from their mixture proportions with their deterministic and robust optimisation

The construction industry relies so heavily on concrete that it's crucial to precisely forecast and optimize the strength and workability of concrete mixtures, while reducing costs as much as possible. For this objective, this study tries to predict and optimize the compressive strength and workability (slump) of concrete by using deterministic and robust optimization approaches, so as to determine the optimum concrete mixture proportions, while minimizing cost. Specifically, strength and slump were predicted based on concrete mixture proportions with five different machine learning techniques—support vector machine (SVM), artificial neural network (ANN), fuzzy inference system (FIS), adaptive fuzzy inference system (ANIS), and genetic expression programming (GEP), based on a dataset comprising two hundred concrete mixtures, which has various levels of key ingredients, including cement, water, fine aggregate, coarse aggregate, and size of coarse aggregate, along with their associated measures of strength and workability. These ingredients were used as input parameters, while compressive strength and slump (representing workability) served as output parameters for each mix proportion. Experimental investigations were conducted on fifteen distinct concrete mixes to validate the performance of the five networks, finding that ANFIS can yield the best results both for training and validation. This study provides valuable insights for predicting concrete properties and optimizing concrete mixture proportions, thus helping to maximize strength and workability while minimizing costs.

SVD-based adaptive fuzzy for generalized transportation

This research stems from the urgent need to address the complex challenges faced in multimodal transportation within the cargo sector, particularly concerning the reduction of transportation costs and CO2 emissions. Existing transportation systems often struggle to efficiently balance economic and environmental concerns, necessitating innovative solutions. In this paper, we have introduced a novel mathematical model that integrates Singular Value Decomposition (SVD), Genetic Algorithms (GA), and the Adaptive Neural Fuzzy Inference System (ANFIS). The synergy of GA and the ANFIS forms a dynamic learning system that continually refines solutions by adapting to historical decisions and aligning with supply-demand dynamics. This integrated approach aims to optimize cost allocation and resource utilization while simultaneously minimizing CO2 emissions. Deploying the ANFIS+GA+SVD model in multimodal scenarios yields impressive results, with a minimal average percentage error (MAPE) of 0.28% for transportation costs and a remarkable coefficient of determination R2 of 0.992 for the Truck + Ship scenario. Similarly, a MAPE of 0.11% for CO2 emissions, supported by an impressive R2 of 0.989, underscores the model's accuracy. Observations of people's transportation choices in response to emission price changes reveal a significant decrease in truck usage, plummeting from 84% to below 50%. Alternative transportation methods, especially in the 3S-3 M-3 C scenario, show a substantial surge, with railways leading at a remarkable 30% increase in utilization. The combined quantity and cost comparison, utilizing the ANFIS+GA+SVD model, emphasizes the suitability of the Truck + Ship scenario for Iraq's transportation network, reinforcing the case for sustainable and efficient multimodal transportation systems.

Adaptive Particle Swarm Optimization of a Photovoltaic System under Partial Shading

The solar photovoltaic (PV) energy is the most prevalent and popular source of energy. But the PV output characteristics are mainly depending on temperature and irradiance and are nonlinear in nature. Therefore, PV array characteristics greatly vary with change in the atmospheric condition. Under partial shading condition (PSC), PV modules will not receive the same level of incident solar irradiance throughout the system due to some obstructions such as: dust, cloudy weather, shadows of nearby objects: buildings, trees, mountains, birds etc… which causes mismatch in PV module characteristics of the PV array and losses arise in the entire PV configuration. Consequently, power extraction from the PV system is reduced and the PSC on the PV array can be minimized by the proper selection of PV configurations, physical relocation of the PV modules and maximum power point tracking techniques (MPPT) to overcome this problem. The present article studies and compares the MPPT based on the Adaptive particle swarm optimization (APSO) algorithm under partial and completely shaded. The perturbation and observation (P&O) method is widely due to its simplicity and easy implementation but the Intelligent and hybrid control such as: fuzzy logic control (FLC) and adaptive neural fuzzy inference system (ANFIS) can track the MPP with better efficiency but in a long time compared to conventional approaches. In addition, these methods need big data for good results and the data problem is regulated with the evolutionary algorithms and searching the duty cycle (d) in a shorter time than FLC and ANFIS. The principle of PSO, grey wolf optimization (GWO), and APSO techniques is the search for a global solution, and it have good behaviour under PSC but APSO can be classified as best solution between the studied approaches. The simulation results, which are presented in MATLAB/Simulink software, show the effectiveness of the proposed APSO technique.

A Dynamic Collision Risk Assessment Model for the Traffic Flow on Expressways in Urban Agglomerations in North China

Expressways in urban agglomerations are important in connecting cities, thus attracting great attention from researchers in the expressways risk assessment. However, there is a lack of safety assessment models suitable for the characteristics of expressways in Chinese urban agglomerations, and the nature and mode of dynamic risks on Chinese highways are still unclear. Therefore, this study adopts the Adaptive Neural Fuzzy Inference System (ANFIS) and the method of decision tree, combined with data from the Beijing section of the Beijing Harbin Expressway, to model the risk of accident-prone highways in urban agglomerations. To determine the optimal model, we evaluated the model’s bias at different time intervals. In addition, key factors affecting highway safety were analyzed, providing scientific support for the risk prevention of highways in urban agglomerations in China.