Network Fuzzy Inference Research Articles

Correction to: Automated approach to predict cerebral stroke based on fuzzy inference and convolutional neural network

Correction to: Automated approach to predict cerebral stroke based on fuzzy inference and convolutional neural network

Automated approach to predict cerebral stroke based on fuzzy inference and convolutional neural network

Automated approach to predict cerebral stroke based on fuzzy inference and convolutional neural network

Improved adaptive neuro-fuzzy inference system with bacterial foraging optimization algorithm for suspended sediment concentration estimation

The accuracy of predicting river-suspended sediment concentration (SSC) is crucial for evaluating the functional lifespan of reservoirs, analyzing river geomorphological evolution, and assessing riverbed stability. In this study, we aim to develop new models for SSC prediction at two hydrological stations near Puerto Rico, USA, by integrating the bacterial foraging optimization algorithm and adaptive neural fuzzy inference network (ANFIS). The models comprise ANFIS with grid partition (ANFIS-GP), ANFIS with subtractive clustering (ANFIS-SC), and ANFIS with fuzzy c-means clustering (ANFIS-FCM). Additionally, we employ an artificial neural network (ANN) and the sediment rating curve (SRC) for predicting daily series data of flow discharge-suspended sediment concentration (SSC). Different scenarios are considered based on varying input and output variables, leading to predictions for four distinct scenarios. At the Rio Valenciano Station, the MRSE values for ANFIS-BFO, ANFIS-FCM, ANFIS-GP, ANFIS-SC, ANN, and SRC are 2.2172, 2.5389, 2.6627, 2.7549, 2.7994, and 3.7882, respectively. For the Quebrada Blanca Station, the MRSE values for ANFIS-BFO, ANFIS-FCM, ANFIS-SC, ANFIS-GP, ANN, and SRC are 0.8295, 0.8664, 0.8964, 0.9110, 0.9684, and 1.6742, respectively. It can be inferred that ANFIS-BFO exhibits superior prediction results compared to all other models. Furthermore, ANFIS-SC and ANFIS-FCM demonstrate slightly better prediction performance than ANFIS-GP. In comparison to ANN, ANFIS-GP, ANFIS-SC, and ANFIS-FCM exhibit slightly superior prediction performance.

Diagnosis and classification of disturbances in the power distribution network by phasor measurement unit based on fuzzy intelligent system

AbstractThe dynamic nature of distribution networks raises fresh issues with how such electrical systems function. These networks have some characteristics that indicate the need for better monitoring and control capabilities, including dispersed generation employing renewable resources, changing load profiles, and rising reliability requirements. Phasor measurement units (PMUs) offer simultaneous voltage and current phasor measurements at various places and offer a variety of options for gauging the condition and health of the power distribution network. In this regard, a cost‐optimized PMU with some unique features for distribution systems is presented in this work. These features include a fuzzy inference system to determine the root cause of potential electrical disturbances and methods to estimate electrical parameters through measured field data, which are necessities. This study takes into account the modelling of PMUs, utilizing a process for fault detection and classification with a fuzzy inference network. The 9‐bus distribution network's dependability model is built once the components and their functions are first outlined. The proposed model is then used to calculate the availability of the presented model, which has been examined to provide an analogous reliability model for PMUs. Depending on the specific manufacturer, the PMU's design and specs will change. To extract phase and size measurement features for the proposed model adaptive neural‐fuzzy inference system network's training, two PMU structures and associated reliability models are described here. When merging input data for fuzzy neural network prediction using MATLAB software, fuzzy sets are taken into account for error classification analysis.

Urban community governance and machine learning: practice and prospects for intelligent decision making

Abstract Urban community governance faces unprecedented challenges, but machine learning provides new ideas for it. The objective of this study is to examine the use of machine learning technology in urban community governance to enhance governance efficiency and decision-making quality. The study constructs an artificial neural network intelligent decision support model based on genetic algorithm optimization, which is based on the operational requirements of a smart decision support system. A weighted fuzzy inference network is further developed by the fusion of fuzzy logic and neural networks to enhance the system’s ability to deal with uncertainty and ambiguity. Next, prediction tests were conducted on the development levels of six communities to validate the model’s effectiveness. After 1686 training steps, the error squared SSE drops below 0.2%, according to the results. The composite index’s prediction error was 5.12%, while the minimum error was −1.79%. The predicted rankings of the communities did not change from the actual ones, which was in line with the normal trend, and the algorithmic model achieved better prediction results. This study not only provides a new intelligent decision support tool for community governance but also sets a theoretical and practical foundation for the intelligent development of urban community governance in the future.

RSFIN: A Rule Search-based Fuzzy Inference Network for performance prediction of configurable software systems

Many modern software systems provide numerous configuration options to users and different configurations often lead to different performances. Due to the complex impact of a configuration on the system performance, users have to experimentally evaluate the performance for different configurations. However, it is practically infeasible to exhaust the almost infinite configuration space. To address this issue, various approaches have been proposed for performance prediction based on a limited number of configurations and corresponding performance measurements. Many of such efforts attempt to achieve a reasonable trade-off between experiment effort and prediction accuracy. In this paper, we propose a novel performance prediction model using a Rule Search-based Fuzzy Inference Network (RSFIN) based on ANFIS and NAS. One intuition is that, in systems, similar configurations produce similar performance. We experimentally validate this intuition based on data and introduce a configuration space under entropy. This view suggests the use of RSFIN to capture hidden distributions in configuration space. We implement and evaluate RSFIN using eleven real-world configurable software systems. Experimental results show that RSFIN achieves a better trade-off between measurement effort and prediction accuracy compared to other algorithms. In addition, the results also confirm that the evaluation of configuration space complexity based on data entropy is beneficial.

Control of Oxygen Excess Ratio for a PEMFC Air Supply System by Intelligent PID Methods

The hydrogen fuel cell is a quite promising green device, which could be applied in extensive fields. However, as a complex nonlinear system involving a number of subsystems, the fuel cell system requires multiple variables to be effectively controlled. Oxygen excess ratio (OER) is the key indicator to be controlled to avoid oxygen starvation, which may result in severe performance degradation and life shortage of the fuel cell stack. In this paper, a nonlinear air supply system model integrated with the fuel cell stack voltage model is first built, based on physical laws and empirical data; then, conventional proportional-integral-derivative (PID) controls for the oxygen excess ratio are implemented. On this basis, fuzzy logic inference and neural network algorithm are integrated into the conventional PID controller to tune the gain coefficients, respectively. The simulation results verify that the fuzzy PID controller with seven subsets could clearly improve the dynamic responses of the fuel cells in both constant and variable OER controls, with small overshoots and the fastest settling times of less than 0.2 s.

Mackey–Glass Chaotic Time Series Forecasting by Using Self-Organizing Fuzzy Inference Network

Mackey–Glass Chaotic Time Series Forecasting by Using Self-Organizing Fuzzy Inference Network

Data Analytics on Unpredictable Pregnancy Data Records Using Ensemble Neuro-Fuzzy Techniques

The immune system goes through a profound transformation during pregnancy, and certain unexpected maternal complications have been correlated to this transition. The ability to correctly examine, diagnoses, and predict pregnancy-hastened diseases via the available big data is a delicate problem since the range of information continuously increases and is scalable. Many approaches for disease diagnosis/classification have been established with the use of data mining concepts. However, such methods do not provide an appropriate classification/diagnosis model. Furthermore, single learning approaches are used to create the bulk of these systems. Classification issues may be made more accurate by combining predictions from many different techniques. As a result, we used the Ensembling of Neuro-Fuzzy (E-NF) method to perform a high-level classification of medical diseases. E-NF is a layered computational model with self-learning and self-adaptive capabilities to deal with specific problems, such as the handling of imprecise and ambiguous data that may lead to uncertainty concerns that specifically emerge during the classification stage. Preprocessing data, Training phase, Ensemble phase, and Testing phase make up the complete procedure for the suggested task. Data preprocessing includes feature extraction and dimensionality reduction. Besides such processes, the training phase includes the fuzzification process of medical data. Moreover, training of input data was done using four types of NF techniques: Fuzzy Adaptive Learning Control Network (FALCON), Adaptive Network-based Fuzzy Inference System (ANFIS), Self Constructing Neural Fuzzy Inference Network (SONFIN) and/Evolving Fuzzy Neural Network (EFuNN). Later, in the ensemble phase, all the NF methods’ predicted outcomes are integrated, and finally, the test results are evaluated in the testing phase. The outcomes indicate that the method could predict impaired glucose tolerance, preeclampsia, gestational hypertensive abnormalities, bacteriuria, and iron deficiency anaemia better than the others. In addition, the model exposed the capability to be utilized as an autonomous learning strategy, specifically in the early stages of pregnancy, examinations, and clinical guidelines for disease interventions.

Greenhouse Climate Modeling Using Fuzzy Neural Network Machine Learning Technique

The greenhouse climate is a non-linear system that contains multiple inputs (predictors) and multiple outputs (responses). This project aimed to provide a solution, aided by artificial intelligence, to the issue of variations in time, input and output factors in a greenhouse internal climate that can adversely affect tomato seedlings. Machine learning Methodologies such as fuzzy inference and neural networks have been applied to mimic idealistic behavior. This paper proposes an adaptive system based on artificial neural networks technique embedded with fuzzy logic technique calls Adaptive Neuro Fuzzy Inference System (ANFIS) to predict air humidity, air temperature, internal radiation, and CO2 concentration while the seeds grow, in order to produce favorable greenhouse climate conditions. The input parameters include ten meteorological and control actuators that majorly influence tomato plants during their growth process in the greenhouse climate. This discussion revolves around a linguistic ANFIS model that will operate during the 48 days that it takes for the seedlings to grow. It will provide estimates of the greenhouse climate using meteorological data along with control actuators rooted in trained neural networks with back propagation optimization algorithm, and 500 iterations of the least square algorithm. Simulations have revealed the efficiency of this model.

Model-Free Adaptive Control Based on Fractional Input-Output Data Model

Memory properties of fractional-order operators are considered for an input-output data model for highly uncertain nonlinear systems. The model arises by relating the fractional-order variation of the output to the fractional-order variation of the input; the instantaneous gain is computed through a fuzzy inference network, whose output consequences are adapted online on a gradient descent rule. The fractional-order nature of the proposed model relaxes the stringent conditions on data-driven schemes, allowing instantaneous changes in the output signal with a null variation in the controller. The main contribution consists of taking advantage of the memory properties of fractional-order operators and the flexibility of fuzzy logic rules to construct a data-driven model for highly uncertain discrete-time nonlinear systems. The relevance of the proposed method is assessed through experiments in a real-world scenario.

Estimation of Left Ventricular Ejection Fraction Using Cardiovascular Hemodynamic Parameters and Pulse Morphological Characteristics with Machine Learning Algorithms.

It is estimated that 360,000 patients have suffered from heart failure (HF) in Taiwan, mostly those over the age of 65 years, who need long-term medication and daily healthcare to reduce the risk of mortality. The left ventricular ejection fraction (LVEF) is an important index to diagnose the HF. The goal of this study is to estimate the LVEF using the cardiovascular hemodynamic parameters, morphological characteristics of pulse, and bodily information with two machine learning algorithms. Twenty patients with HF who have been treated for at least six to nine months participated in this study. The self-constructing neural fuzzy inference network (SoNFIN) and XGBoost regression models were used to estimate their LVEF. A total of 193 training samples and 118 test samples were obtained. The recursive feature elimination algorithm is used to choose the optimal parameter set. The results show that the estimating root-mean-square errors (ERMS) of SoNFIN and XGBoost are 6.9 ± 2.3% and 6.4 ± 2.4%, by comparing with echocardiography as the ground truth, respectively. The benefit of this study is that the LVEF could be measured by the non-medical image method conveniently. Thus, the proposed method may arrive at an application level for clinical practice in the future.

Модель нейронной сети для прогнозирования предэвакуационного поведения людей при пожаре

This article discusses a comprehensive study of pre-evacuation behavior of people in the event of an emergency. In this regard, it is advisable to use machine learning approaches, in particular neural networks, for data mining in the field of security. Statistical data obtained in emergency situations may be limited and generally uncertain, for this reason it is recommended to choose a neural network architecture - adaptive fuzzy inference Network System (ANFIS) based on the Takagi–Sugeno fuzzy inference system. The neural network architecture considered in the article in the form of an adaptive fuzzy inference network system architecture consists of five layers, where each layer performs a well-defined function. Data on the behavioral reaction of people before the evacuation to train an artificial neural network were obtained using such approaches as interviewing, questionnaire, survey.

IoT Smart Agriculture and Agricultural Product Income Insurance Participant Behavior Based on Fuzzy Neural Network

With the continuous development of modern science, more and more attention is paid to the application of science and technology for agricultural production. First of all, this article analyzes the development trend of modern agriculture, and designs the system through an overall plan of four parts: automatic acquisition, terminal control, network transmission, and cloud platform and terminal application. Taking automatic irrigation system and temperature automatic control system as examples, design an automatic control algorithm based on fuzzy neural network, and obtain the best control strategy through fuzzy inference and neural network training. Then, this paper studies the reliability of “price setting” in agricultural income insurance. This article takes the main crops of a certain province as an example to verify and analyze the risks of farmers' income levels from the viewpoint of corn yield risks and price risks, and advocate the necessity and feasibility of agricultural income insurance. Finally, from the perspective of different participants, this article analyzes the impact of insurance premium subsidies on the enthusiasm of agricultural producers to participate in insurance, the impact of insurance companies on the improvement of insurance operation efficiency in the planting industry, and the stability of the government's promotion of agricultural production. It also influences to design a set of IoT automatic control system for intelligent agriculture. The system realizes the acquisition and remote control of agricultural data by establishing an Internet of Things cloud platform, and uses automatic control algorithms based on fuzzy neural networks to realize automatic water-saving irrigation, automatic temperature control, and other functions. Based on this research, the main actions of joining agricultural income insurance and the participation model based on the perspective of tripartite participants.

Neural Fuzzy Inference Network Based on Differential Evolution for Nonlinear System Control

Neural Fuzzy Inference Network Based on Differential Evolution for Nonlinear System Control

Hierarchically Reorganized Multi-Layer Fuzzy Neural Networks Architecture Driven With the Aid of Node Selection Strategies and Structural Network Optimization

In this study, a design methodology based on fuzzy sets inference and polynomial neural network(PNN) for hierarchically reorganized self-organizing network architecture is introduced to cope with over-fitting as well as multi-collinearity problems which generally appear in a conventional fuzzy neural network. The design method of the proposed self-organizing network structure provides an efficient solution to construct the hierarchically reorganized multi-layer fuzzy neural networks (HRmFNN) architecture through a synergy of multi-techniques such as L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> -norm regularization, probability theory, and multi-optimization. The overall network structure is realized with the aid of parallel network structure with newly added inputs as well as effective neuron selection method through the exponential-based roulette selection technique for each layer in HRmFNN, and the least square error estimation (LSE)-based learning method with L2-norm regularization is used for constructing the stabilized network architecture, and their ensuring design methodologies result in alleviating the overfitting phenomenon and also enhancing the generalization ability. For the performance enhancement of HRmFNN directly affected by some parameters such as the number of input variables, collocation of the specific subset of input variables, the number of membership functions per each variable, and the order of polynomial in the consequent parts of the fuzzy rules, multi-particle swarm optimization (MPSO) is exploited for the effectively structural as well as parametric optimization of the proposed network. That is, the multi-optimization helps achieve a compromise between the better generation performance and the alleviated over-fitting leading to the stabilization of the proposed multi-layered self-organizing network structure with the aid of synergistic multi-techniques such as a) L <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> -norm regularization-based LSE learning, b) probability theory for effective neuron selection, and c) novel parallel network structure including newly added inputs and neuron selection method. The performance of the proposed network structure is quantified by comprehensive experiments and comparative analysis. It is also demonstrated through the application to cement compressive strength.

Novel Adaptive Fuzzy Feedback Neural Network Controller for Narrowband Active Noise Control System

With the development of science and technology in recent years, many operating machines have become sources of noise affecting quality of life. Hence, the topic of noise diminution using an active noise control (ANC) system has attracted many researchers. This paper develops a new adaptive fuzzy feedback neural network controller (AFFNNC) to improve the performance for narrowband active noise control (NANC) systems. The proposed controller combines fuzzy inference and adaptive feedback neural network controllers that are based on the filtered-s least mean square (FSLMS) algorithm. The AFFNNC comprises five network layers, in which the output layer of the controller uses an adaptive algorithm to tune directly the parameters of filters without prior training. The computational complexity, convergence and stability of the AFFNNC are analyzed. Evaluations are performed on both linear and nonlinear NANC systems with a recorded noise signal that was obtained from a transformer. Numerical simulations confirm the efficiency of the proposed controller compared with other ANC controllers.

A Team Formation Approach to Supplier Network Design, Considering Multi-Objective Modeling, Fuzzy Inference, and Social Network Analysis

A Team Formation Approach to Supplier Network Design, Considering Multi-Objective Modeling, Fuzzy Inference, and Social Network Analysis

A Team Formation Approach to Supplier Network Design, Considering Multi-Objective Modeling, Fuzzy Inference, and Social Network Analysis

A Team Formation Approach to Supplier Network Design, Considering Multi-Objective Modeling, Fuzzy Inference, and Social Network Analysis

Hierarchical Fuzzy Signature and Neuro-Fuzzy Hybrid System for QMS Control

Recently, the Quality Management System (QMS) control supports organizations managers identifying the best practices to upgrade the efficiency and effectiveness. This control has become a successful tool to improve the organization decision-making process. However, QMS encloses several performance indicators inputs that necessitate to be managed. In fact, it may include as inputs, customers requirements, quality policies, standard procedures and many other criteria. Hence, to provide the control of QMS problem insurance, two approaches are investigated which are Hierarchical Fuzzy Signature (HFS) and NeuroFuzzy Hierarchical Hybrid system (NFHH), respectively. These approaches are applied in the case of an industrial company operating in the electromechanical sector. This company has to be creative, agile, responsive and especially ready for fierce competition. Then, the obtained results are compared to Adaptive Neural Fuzzy Inference and Neural Network Systems, regarding the learning phase. Consequently, all of them help the company to assess its overall performance. However, NFHH reaches the best accuracy, reduces the number of neurons and uses the parameters that keep the universal approximated property of neural networks and fuzzy systems. Keywords—Quality management system, Fuzzy logic, Neuro-Fuzzy, hierarchical structure, fuzzy signature