Neuro-fuzzy System Research Articles

Retracted: Implementing the Hybrid Neuro-Fuzzy System to Model Specific Learning Disability in Special University Education Programs

Retracted: Implementing the Hybrid Neuro-Fuzzy System to Model Specific Learning Disability in Special University Education Programs

Analysis of Grid-tied Solar Photovoltaic Energy Generation under Uncertain Atmospheric Conditions Using Adaptive Neuro-fuzzy Control System

The grid-tied photovoltaic (PV) power system has remained the most practical and sustainable configuration among renewable energy generation systems. Although uncertainties persist in solar irradiance and temperature, the grid-tied system faces transient instability issues during maximum power point tracking, adversely affecting power quality and resulting in substantial costs. To overcome this issue, we proposed analyzing the grid-tied system under uncertain atmospheric conditions based on an adaptive neuro-fuzzy control system (ANCS). This control scheme incorporates a hybrid learning algorithm and undergoes evaluation across various operating conditions. The obtained results demonstrate the effectiveness of the learning algorithm in maintaining a fast convergence speed. Consequently, this capability ensures the consistent preservation of sufficient power quality in the power system without any discernible transient impact. Furthermore, the investigation reveals the significant impact of solar radiation and temperature on the performance of the solar grid-tied PV system. Specifically, temperature alone contributes to over 15% power reduction when reaching 45 °C. As the temperature decreases to 5 °C at 1000 W/m2 irradiance, the ANCS influences an increase in the system's power generation from 100.72 kW at 25 °C to 103.01 kW.

Gas turbine vibration monitoring based on real data using neuro-fuzzy system

Gas turbine vibration monitoring based on real data using neuro-fuzzy system

Optimal design of solar/wind/battery and EV fed UPQC for power quality and power flow management using enhanced most valuable player algorithm

The behavior and performance of distribution systems have been significantly impacted by the presence of solar and wind based renewable energy sources (RES) and battery energy storage systems (BESS) based electric vehicle (EV) charging stations. This work designs the Unified Power Quality Conditioner (UPQC) through optimal selection of the active filter and PID Controller (PIDC) parameters using the enhanced most valuable player algorithm (EMVPA). The prime objective is to effectively address the power quality (PQ) challenges such as voltage distortions and total harmonic distortions (THD) of a distribution system integrated with UPQC, solar, wind, BESS and EV (U-SWBEV). The study also aims to manage the power flow between the RES, grid, EV, BESS, and consumer loads by artificial neuro-fuzzy interface system (ANFIS). Besides, this integration helps to have a reliable supply of electricity, efficient utilization of generated power, and effective fulfillment of the demand. The proposed scheme results in a THD of 4.5%, 2.26%, 4.09% and 3.98% for selected four distinct case studies with power factor to almost unity with an appropriate power sharing. Therefore, the study and results indicate that the ANFIS based power flow management with optimal design of UPQC addresses the PQ challenges and achieves the appropriate and effective sharing of power.

Enhancing platoon performance: A novel approach to speed and direction control using V2X communication

Autonomous vehicle platoons have become an increasingly popular solution to enhance driving system performance and facilitate the safe integration of these vehicles on the roads. To ensure efficient platoon traffic, it is essential to effectively manage both speed and direction within this group of vehicles. It is in this context that this research is situated. Our primary objective is to enhance the performance of speed and direction controllers, as the ability of vehicles to adjust these parameters in a coordinated manner is crucial for the success of platoon traffic. To achieve this, we have developed a novel speed control approach based on neural networks and fuzzy logic, utilizing V2X communication. By incorporating environmental parameters through vehicle-to-vehicle communication and considering the specific goals of the platoon, our neuro-fuzzy system can accurately calculate optimal speeds and directions for the vehicles. Our experiments have demonstrated the effectiveness of this approach compared to traditional and advanced methods, improving both energy efficiency and temporal coordination of autonomous vehicles within the platoon.

Location of Faults in Six Phase Transmission Line using a Neuro Fuzzy System

Fault location plays an important role in power systems. It is frequently used in transmission lines to reduce the system damage for growing electrical energy demand. However, the location estimation method itself is easy to be disturbed by different parameters and gives estimation errors. To solve this problem, this paper introduces a scheme that uses neuro fuzzy system (NFS) to locate all types of faults such as shunt faults, transforming faults, series faults and simultaneous faults in six phase overhead line (SPOL). This scheme has been performed on a 68 km, 138 kV, 60Hz, SPOL for all fault types by employing MATLAB software Simulink. Here, Haar wavelet transforms (HWT) are used to extract the current signals in order to evaluate the behavior and characteristics of higher frequency components. Then, the obtained HWT currents data are employed to construct the fault location scheme in SPOL based on NFS. The obtained experimental results confirm that by using the NFS, the maximum fault location error (MFLE) can be reduced by more than 10%. It can further reduce the maximum response time (MRT) for the operator to address the faults and ensure the power system reliability in the future. The test result executed in this investigation indicates that the NFS is resilient to wide changes in fault conditions, and it shows good performance and huge potential for location of faults in SPOL.

A neuro-fuzzy modular system for modeling nonlinear systems

The real world is nonlinear and in the control application field, this aspect needs to be resolved to build models so we need to refer to nonlinear system modeling techniques. Neuro-fuzzy systems and modular neural networks (NNs) are among the best modeling approaches for nonlinear systems. The combined features of both approaches provide better models. Thus, we propose in this paper a neuro-fuzzy modular architecture for modeling nonlinear systems. The modular architecture consists of dividing a nonlinear problem into several simpler subproblems. We assigned to each subproblem an NN. Each NN provides individual solutions that will be combined to provide a general solution to the original problem. In this respect, the decomposition of the original problem is based on a fuzzy decision mechanism. This mechanism consists of a set of fuzzy rules for processing nonlinear problems using two different strategies. The first involves training only the network weights, and the second adds the fuzzy set parameters to the training step. A comparative study of both strategies reveals the competence of the second strategy in providing better accuracy and simplicity. Using the neuro-fuzzy combination among the modular NNs reduces the complexity of the original problem and achieves much better performance. The proposed architecture is evaluated by two second-order nonlinear systems, a numerical system and a real system called “the chemical reactor,” which is used to carry out a chemical reaction not only in chemical and biochemical engineering, but also in the petrochemical industry. For both systems, the proposed approach provides better performance in terms of the learning time, learning error, and number of neurons.

Total harmonic distortion analysis of inverter fed induction motor drive using neuro fuzzy type-1 and neuro fuzzy type-2 controllers

Introduction. When the working point of the indirect vector control is constant, the conventional speed and current controllers operate effectively. The operating point, however, is always shifting. In a closed-system situation, the inverter measured reference voltages show higher harmonics. As a result, the provided pulse is uneven and contains more harmonics, which enables the inverter to create an output voltage that is higher. Aim. A space vector modulation (SVM) technique is presented in this paper for type-2 neuro fuzzy systems. The inverter’s performance is compared to that of a neuro fuzzy type-1 system, a neuro fuzzy type-2 system, and classical SVM using MATLAB simulation and experimental validation. Methodology. It trains the input-output data pattern using a hybrid-learning algorithm that combines back-propagation and least squares techniques. Input and output data for the proposed technique include information on the rotation angle and change of rotation angle as input and output of produced duty ratios. A neuro fuzzy-controlled induction motor drive’s dynamic and steady-state performance is compared to that of the conventional SVM when using neuro fuzzy type-2 SVM the induction motor, performance metrics for current, torque, and speed are compared to those of neuro fuzzy type-1 and conventional SVM. Practical value. The performance of an induction motor created by simulation results are examined using the experimental validation of a dSPACE DS-1104. For various switching frequencies, the total harmonic distortion of line-line voltage using neuro fuzzy type-2, neuro fuzzy type-1, and conventional based SVMs are provided. The 3 hp induction motor in the lab is taken into consideration in the experimental validations.

Design of a neuro-fuzzy model for agricultural employment in Colombia using fuzzy clustering

<p>High levels of poverty in rural areas constitute one of the main challenges for developing countries. Since agricultural employment is the main source of income in these areas, the design of tools that simulate and help public policymakers will be remarkably useful. This work proposes the development of a model for agricultural employment in Colombia, considering input variables such as education, contract, and income, and the output is the amount of agricultural employment. Real data measured in Colombia are used for the design and adjustment of the model. To design the fuzzy system for an agricultural employment model, the methods employed are fuzzy C-means clustering and neuro-fuzzy systems. The systems were tested with different cluster configurations, and a fuzzy system was obtained with an adequate distribution of the fuzzy sets and the respective rules that relate the sets. It was observed that as the clusters increase, the adjustment function decreases. The implementation of neuro-fuzzy systems to model agricultural employment will allow public policymakers to generate guidelines that adjust to their political agendas with a lower degree of uncertainty.</p>

Metoda ANFIS za klasifikaciju EEG signala pri zamišljanju pokreta različitih zglobova istog ekstremiteta

Introduction: The experimental area of brain-computer interfaces (BCIs) is expanding to include movement actions, which play a crucial part in deciphering cognitive processes. Without the need for any kind of exterior stimulation, motor imagining (MI) can be used as a powerful model for braincomputer interfaces (BCIs). A natural method of operating exterior devices is to imagine moving various joints in the same arm. These envisioned motions have similar spatial images in the motor brain, making it difficult to differentiate MI of various joints of the same leg based on EEG data. Method: A pre-existing data collection of 25 participants was utilized in this study. The participants visualized using their right limbs to carry out three different activities: visualize yourself manipulating your right hand, visualize bending your right arm, and close your eyes while you relax. To assign categories to these impulses, we turned to the adaptive neuro-fuzzy reasoning system. Results: The average level of accuracy was 90%. Conclusion: The findings demonstrate that this technique is crucial for correctly categorizing EEG data. The data collection used in this investigation consists of EEG measurements of the same limb used in muscular imaging. The new categorization method will be applied to these signals to draw conclusions.

ИССЛЕДОВАНИЕ МЕТОДОВ И АЛГОРИТМОВ РЕДУКЦИИ НЕЧЕТКИХ ПРАВИЛ В МОДЕЛЯХ ОЦЕНКИ ДИСКРЕТНОГО СОСТОЯНИЯ ОБЪЕКТОВ

The article describes the stages and results of the study of methods and genetic algorithms used to reduce fuzzy rules in models for assessing the discrete state of objects. Such models are fuzzy knowledge bases and fuzzy logical inference algorithms. A study was conducted of the influence of the parameter values of genetic algorithms on the results of reduction of the initial and intermediate knowledge bases (on the reduction of the number of rules in the knowledge bases and on the values of classification quality metrics). The following stages of research were implemented: selection of data sets from publicly available sources, formation of research knowledge bases, study of the influence of genetic algorithm parameter values on the results of knowledge base reduction, analysis of research results and development of recommendations for choosing optimal values of genetic algorithm parameters to achieve the best reduction results. Data for analysis was obtained from the public source UCI Machine Learning Repository. The selected sets are: Iris, Banknote Authentication and User Knowledge Modeling. To create research knowledge bases, the software package “Neuro-fuzzy system for generating fuzzy models for assessing the discrete state of objects” was used. Based on the analysis of the Iris data set, 3 research knowledge bases were formed, including 269, 339 and 542 fuzzy rules. For the Banknote Authentication data set, corresponding knowledge bases with 335, 643 and 1038 fuzzy rules were generated. For the User Knowledge Modeling set - with 877, 2094 and 2797 rules. For each of the knowledge bases, the values of the classification quality metrics Accuracy, Precision, Recall and F1-Score were calculated on the training and test samples. The reduction of knowledge bases was carried out in two successive stages, at each of which the corresponding genetic algorithm was used. Based on the results of the research, recommendations were developed for choosing the optimal values of the parameters of each of the genetic algorithms. The reduction of research knowledge bases based on the developed methods and algorithms made it possible to significantly reduce the number of their fuzzy rules (by an average of 85%) and at the same time slightly increase the generalizing ability of fuzzy models (by an average of 1.5%). In general, this made it possible to reduce the complexity of fuzzy models and their constituent knowledge bases, increase the accuracy of estimating the discrete state of objects and improve the interpretability of the generated solutions.

АНАЛИЗ МОДЕЛЕЙ АДАПТИВНЫХ НЕЙРО-НЕЧЕТКИХ СИСТЕМ

The article deals with the study of basic methods for models of adaptive neuro-fuzzy systems. Based on the analysis, the strengths of neural networks and fuzzy logic were found, that became powerful tools for solving complex modeling and forecasting issues. There is studying and analyzing the adaptive neural network, which is a class of neural networks that have the ability to change their structure and parameters in the process of learning and adaptation to new data and conditions and besides the article studies the Gaussian membership function, also known as the normal membership function or the Gauss-type membership function, which is a valuable tool in the f ield of fuzzy logic and fuzzy systems. The paper provides as well an analysis of the generalized Bell membership function, also known as the Bell type membership function or Bell function, which plays an important role in the field of fuzzy logic and fuzzy systems. Furthermore it analyzes the Tsukamoto model, which is one of the main models of fuzzy logic. The author opted to choose the Co-Active Neuro-Fuzzy Inference System model, which is an adaptive neuro-fuzzy system that combines neural networks and fuzzy logic for processing data with uncertainty and fuzziness. With the further implementation of the combined model based on the abovelisted models based on the STL of the C++ language, thus the neural network model is obtained, the model with versatility, that is achieved by using a combination of those models. That will facilitate its easy modification and adaptation to various tasks.

Bioengineering, waste processing and fermentation process control for biogas production

The article discusses the analysis of the state of control of the processes of biogas production from animal waste by methane digestion. The article discusses the problems of synthesis of automated control systems of biotechnological processes under conditions of information uncertainty. The analysis of the current state of control of fermentation stage processes shows that insufficient attention is paid to the problem of synthesis of second-tier banks under conditions of information uncertainty. Construction of mathematical modeling of biosynthetic processes is a kinetic model, where experimental and analytical methods are used due to the difficulty of identifying patterns in microbiological processes. The article discusses the application of methods and algorithms for intellectualization of problem solving in ACS for the synthesis of complex biotechnological objects in conditions of lack of information, that they should be attributed to priority tasks. The results of research on the application of a neuro-fuzzy system for controlling fermentation processes under conditions of uncertainty and multimode of processes, as well as a forecasting algorithm using nonlinear sets and neural networks are presented.

AN ENSEMBLE NEURO FUZZY ALGORITHM FOR BREAST CANCER DETECTION AND CLASSIFICATION

Breast cancer remains a critical global health concern, necessitating advanced and accurate diagnostic tools. This study introduces an Ensemble Neuro-Fuzzy Algorithm (ENFA) designed for the detection and classification of breast cancer. In the background, we address the limitations of existing methods, emphasizing the need for enhanced accuracy and interpretability in diagnostic models. The methodology involves the fusion of neuro-fuzzy systems within an ensemble framework, leveraging the complementary strengths of both neural networks and fuzzy logic. The primary contribution lies in the development of a robust ENFA, which not only improves diagnostic accuracy but also provides interpretable insights into decision-making processes. The ensemble nature of the algorithm enhances resilience and generalization across diverse patient profiles. Experimental results demonstrate superior performance compared to existing methods, showcasing heightened sensitivity and specificity in breast cancer detection. The findings underscore the potential of ENFA as a reliable tool for early and accurate breast cancer diagnosis. This research signifies a significant step towards advancing the efficacy of computational models in medical diagnostics.

Fuzzy-ViT: A Deep Neuro-Fuzzy System for Cross-Domain Transfer Learning from Large-scale General Data to Medical Image

Fuzzy-ViT: A Deep Neuro-Fuzzy System for Cross-Domain Transfer Learning from Large-scale General Data to Medical Image

Boosting Robustness in Deep Neuro-Fuzzy Systems: Uncovering Vulnerabilities, Empirical Insights, and a Multi-Attack Defense Mechanism

Boosting Robustness in Deep Neuro-Fuzzy Systems: Uncovering Vulnerabilities, Empirical Insights, and a Multi-Attack Defense Mechanism

Intelligent Integration and Fusion of Multimodal Biometric Systems

The propagation and the frightening expansion of frauds due essentially to the easy access to high technologies make it difficult or sometimes impossible to detect these frauds and impostures. Therefore, it has become important, if not urgent, to develop identification techniques and tools that are more robust to attacks, more precise and more efficient. There are currently in Europe and some American countries very efficient biometric systems that combine two (2) modalities (photos and fingerprints in the case of biometric passports), but they remain very vulnerable, notably because of acquisition problems, data quality or the non-permanence of certain biometrics. Therefore, the systems based on biometric modality has been growing in the world for a decade. The processes of identification and identity verification of individuals have a very wide spectrum of applications in modern society and are becoming very relevant. However, the field of multi-biometrics is not new, many researchers have been working on this topic especially in the last 10 years. Scholar Google lists nearly 6000 publications on the subject, half of which since 2018. Real systems are in production, we can cite the UID program in India to enroll the 1.300 billion inhabitants with the 10 fingerprints and the two Iris. Most of the techniques consisted in generalizing classical biometric systems (with one modality) by attribute fusion (concatenation of data, statistical reduction...), by score fusion (often performed by summing up the comparison scores from each biometric system) or by decision fusion (majority vote most often). The objective of our work is to propose new techniques of fusion & multimodal biometric integration by using artificial intelligence tools and especially the application of fusion techniques such as: Brute Force Search, Support Vector Machines, neural networks, fuzzy systems, neuro-fuzzy systems, Genetic Algorithms, Particle Swarm Optimization.

МОДЕЛЬ ПРОГНОЗИРОВАНИЯ ЛЕСНЫХ ПОЖАРОВ НА ОСНОВЕ НЕЙРО-НЕЧЕТКОЙ СИСТЕМЫ ANFIS

The existing innovative approaches of both domestic and foreign scientists to intelligent forecasting, as well as forest fire management, are considered. The implementation of the application of the ANFIS neuro-fuzzy system for predicting forest fires in order to increase the reliability and reliability of the forecast data obtained is presented. The analysis of the feature space when considering forest fires is carried out, a correlation matrix is presented that characterizes the degree of influence of features on the predicted indicators. The structure of the neural network model with the corresponding linguistic variables and membership functions is constructed. The results of the ANFIS system training based on historical data in the Leningrad Region for the period from 2015 to 2023 are presented. The results obtained make it possible to increase the efficiency of operational forecasting of the dynamics of forest fires, to justify the adoption of management decisions on their elimination.

HETEROGENEOUS SERVER RETRIAL QUEUEING MODEL WITH FEEDBACK AND WORKING VACATION USING ARTIFICIAL BEE COLONY OPTIMIZATION ALGORITHM

This research delves into the dynamics of a retrial queueing system featuring heterogeneous servers with intermittent availability, incorporating feedback and working vacation mechanisms. Employing a matrix geometric approach, this study establishes the steady-state probability distribution for the queue size in this complex heterogeneous service model. Additionally, a range of system performance metrics is developed, alongside the formulation of a cost function to evaluate decision variable optimization within the service system. The Artificial Bee Colony (ABC) optimization algorithm is harnessed to determine service rates that minimize the overall cost. This work includes numerical examples and sensitivity analyses to validate the model's effectiveness. Also, a comparison between the numerical findings and the neuro-fuzzy results has been examined by the adaptive neuro fuzzy interface system (ANFIS).

Intelligent Decision Support for Identifying Chronic Kidney Disease Stages

The decision tree classification algorithm is becoming increasingly important in machine learning (ML) technology. It is being used in a variety of fields to solve extremely complicated issues. DTCA is also utilised in medical health data to identify chronic kidney disorders such as cancer and diabetes utilising computer-aided diagnosis. Deep learning is an intelligent area of machine learning in which neural networks are used to learn unsupervised from unstructured or unlabeled data. For CKD, the DL employed the deep stacked auto-encoder and soft-max classifier techniques. Kidney illness is another condition that can lead to a variety of health problems. Random forest, SVM, C5.0, decision tree classification algorithm, C4.5, ANN, neuro-fuzzy systems, classification and clustering, DSAE, DNN, FNC, MLP are used in this study to predict and identify an early diagnosis of CKD patients using various machine and deep learning algorithms using R Studio and Python Colab software. The many stages of chronic kidney disease are identified in this paper.