Neuro-fuzzy Inference System Research Articles

UNFIS: A Novel Neuro-Fuzzy Inference System with Unstructured fuzzy rules

An important constraint of Fuzzy Inference Systems (FIS) is their structured rules. Indeed, each rule should evaluate all input variables in its antecedent part. Thus, the length of all fuzzy rules and the number of input variables are equal. However, in many decision-making problems evaluating some conditions on a limited set of input variables is sufficient to decide properly (unstructured rules). Consequently, the FIS’s performance, generalizability, and interpretability are restricted by the aforementioned limitation. This study provides a neuro-fuzzy inference system that can create each fuzzy rule taking into account various sets of input variables in order to handle this problem. To realize this capability, a new fuzzy selector neuron with an adaptive parameter is proposed that can select input variables in the antecedent part of each fuzzy rule. Moreover, the consequent part of the Takagi–Sugeno–Kang FIS is properly changed to consider only the selected set of input variables. To learn the parameters of the proposed architecture, the Levenberg–Marquardt (LM) method is used for regression problems. For classification applications, a trust-region-based learning method (General quasi-Levenberg–Marquardt (GqLM)) is proposed to minimize cross-entropy in multiclass problems. The performance of the proposed method is compared with some related previous approaches in some real-world classification and regression problems. Based on these comparisons, the proposed method has better or very close performance with a parsimonious structure consisting of unstructured fuzzy rules.

Prediction of the Subgrade Soil California Bearing Ratio Using Machine Learning and Neuro-Fuzzy Inference System Techniques: A Sustainable Approach in Urban Infrastructure Development

In the realm of urban geotechnical infrastructure development, accurate estimation of the California Bearing Ratio (CBR), a key indicator of the strength of unbound granular material and subgrade soil, is paramount for pavement design. Traditional laboratory methods for obtaining CBR values are time-consuming and labor-intensive, prompting the exploration of novel computational strategies. This paper illustrates the development and application of machine learning techniques—multivariate linear regression (MLR), artificial neural networks (ANN), and the adaptive neuro-fuzzy inference system (ANFIS)—to indirectly predict the CBR based on the soil type, plasticity index (PI), and maximum dry density (MDD). Our study analyzed 2191 soil samples for parameters including PI, MDD, particle size distribution, and CBR, leveraging theoretical calculations and big data analysis. The ANFIS demonstrated superior performance in CBR prediction with an R2 value of 0.81, surpassing both MLR and ANN. Sensitivity analysis revealed the PI as the most significant parameter affecting the CBR, carrying a relative importance of 46%. The findings underscore the potent potential of machine learning and neuro-fuzzy inference systems in the sustainable management of non-renewable urban resources and provide crucial insights for urban planning, construction materials selection, and infrastructure development. This study bridges the gap between computational techniques and geotechnical engineering, heralding a new era of intelligent urban resource management.

Energy-efficient classification strategy for detecting interference and malicious sensor nodes in wireless body area Networks

Wireless Body Area Networks (WBANs) play a vital role in healthcare monitoring, using wireless sensors to track physiological parameters and predict illness onset. This study proposes a novel approach for detecting interference and malicious sensor nodes in WBANs, crucial for maintaining system integrity and performance. The method combines feature-based techniques with classification strategies to accurately identify anomalies. Features are taken from WBAN nodes and used to train Support Vector Machine (SVM) classifiers, which makes interference detection work well. A neurofuzzy inference system (ANFIS) classifier is also used to train the system on trusted and untrusted nodes at the start, which makes classification easier in real-world WBAN situations. Link failures due to rogue sensor nodes can severely impact WBAN performance, emphasizing the need for efficient detection and correction mechanisms. The proposed strategy introduces a weight metric to identify broken links, enhancing system reliability. Evaluation metrics, including LFD latency and packet delivery ratio, are analyzed to assess the efficacy of the approach. By improving interference detection and addressing link failures, this study contributes to enhancing the efficiency and reliability of WBAN networks, critical for advancing healthcare monitoring technologies.

ESTIMATING THE DIAMETER OF TREE USING THE NEURO-FUZZY INFERENCE SYSTEM AND ARTIFICIAL NEURAL NETWORKS FROM THE TOTAL HEIGHT VARIABLE

Studies that seek to identify potential techniques for obtaining diameter values at 1.30 m from the ground from tree height data are necessary, especially when considering the use of airborne Lidar in forest inventory activity. In this sense, this work aimed to evaluate two artificial intelligence tools for this purpose, namely the neuro-fuzzy inference systems and the artificial neural networks. Four models were tested to obtain estimates for the diameter variable, which were prepared by combining the independent variables useful area per plant, age and height. After processing, the statistics of bias, square root of the mean squared error in percentage, correlation and mean percentage error were calculated, in addition to the preparation of scatter plots and histogram of residues. It was observed that, for the estimation of the diameter in both techniques, the use of the model with all independent variables obtained the best values for the analysis statistics. It can be concluded that both tools can be used to estimate the diameter, with the neuro-fuzzy inference system being more suitable for its processing speed and small variability between the values obtained in different training sessions for the same database.

A Model for Determining Fuzzy Evaluations of Partial Indicators of Availability for High-Capacity Continuous Systems at Coal Open Pits Using a Neuro-Fuzzy Inference System

This paper presents a model for determining fuzzy evaluations of partial indicators of the availability of continuous systems at coal open pits using a neuro-fuzzy inference system. The system itself is a combination of fuzzy logic and artificial neural networks. The system availability is divided into partial indicators. By combining the fuzzy logic and artificial neural networks, a model is obtained that has the ability to learn and uses expert judgment for that learning. This paper deals with the ECC system (bucket wheel excavator-conveyor-crushing plant) of the open pit Drmno-Kostolac, which operates within the Electric Power Company of Serbia. The advantage of a model of this type is that it does not rely on the historical experiences of experts and usual predicted values for the fuzzy evaluation of partial indicators, which are based on the assumption that similar systems affect availability in a similar way. The fuzzy evaluation of partial indicators is based on historical data for the specific system for which the model was created. As such, it can more accurately predict continuous systems availability on the basis of expert evaluations in the appropriate time period. Another advantage of this model is that the availability is estimated on a quarterly basis, which gives a more accurate view because it uses a smaller time period with more similar characteristics and, thus, includes certain external influences which are related to the quarterly meteorological conditions.

Artificial intelligence in endodontics: relevant trends and practical perspectives

Background. Overall pool of studies regarding artificial intelligence (AI) implementation in dentistry is increasing every year, while possibilities for using AI methods within everyday endodontic practice is still quite confined and not always enough affirmed. 
 Objective. To systematize and depict principal data regarding use of virtual artificial intelligence for various endodontic-related clinical purposes.
 Materials and Methods. Targeted literature search was provided within National Center for Biotechnology Information databases using pre-specified Mesh-terms algorithm. The following information was extracted from each publication during content analysis: diagnostic and treatment planning aspects of endodontic practice for which AI methods could be applied; accuracy levels registered for AI models used for different endodontic-related purposes; limitations of using AI within endodontic practice.
 Results. AI features could be used in endodontic practice for the following reasons: analysis of root canal morphology, identification of root fractures, verification of periapical lesions, estimation of root canal working length, root canal treatment planning, prediction of pain development during post-treatment period, predication of endodontic interventions success. The most prevalently used artificial intelligence methods for different endodontic diagnostic and treatment planning objectives were the following: convolutional neural network, artificial neurons network, case-based reasoning, deep learning, machine learning, neuro-fuzzy inference system, probabilistic neural network.
 Conclusion. Main advantage of using AI models in endodontic practice associated with improvement of diagnostic accuracy within reduced amount of time needed for X-ray images and clinical data analysis. AI application for apical foramen detection and working length determination demonstrates the highest level of accuracy compared to AI performance for other clinically related objectives in endodontics.

Spurring sustainability commitment strategy of family-owned SMEs: A multi-analytical SEM & ANFIS perspective

The study seeks to understand the impact of leadership styles on the organizational strategy of sustainability commitment, utilizing the mediator role of employees' eco-friendly practices in family firms in Malaysia. To achieve this aim, dual-stage structural equation modeling (SEM) and neuro-fuzzy inference system (ANFIS) were employed to analyze the leadership style of Malaysian family firms. This study collects empirical data from 427 employees belonging to Malaysian family firms via a structured questionnaire. Results demonstrate supportive, authentic, and paternalistic leadership styles affect the sustainability commitment strategy of organizations. Moreover, employees' eco-friendly best practices fully mediate the link between leadership styles and the organizational strategy of sustainability commitment. Findings of non-compensatory relationships also indicated employees' eco-friendly best practices is the most determinant of the strategy of sustainability commitment, followed by authentic leadership, supportive leadership, and paternalistic leadership.

Pharmaceutical wastewater treatment using TiO2 nanosheets deposited by cobalt co-catalyst as hybrid photocatalysts: combined experimental study and artificial intelligence modeling

Abstract In this work, we developed a facile method for photocatalytic deposition of cobalt atoms as co-catalyst on TiO2 nanosheets (Co(x)/T) under visible light instead of UV irradiation for the first time. The deposition of cobalt atoms on TNs in the Co(x)/T samples was confirmed by DRS, Raman spectroscopy, photoluminescence, nitrogen physisorption, and TEM analyses. The size of cobalt nanoparticles/cluster dispersed on the TiO2 nanosheets were in the range of 5–20 nm according to TEM results. The PXRD patterns showed that the crystal structure and the anatase phase of TNs were preserved in the Co(x)/T samples after the visible light-assisted deposition process. The Co(x)/T samples showed higher activity compared to pure TiO2 nanosheets for the visible light degradation of tetracycline (TC) as pharmaceutical pollutant due to presence of cobalt co-catalyst. We studied the effect of several parameters on the degradation process and proposed the mechanism of degradation according to quenching experiments results. Due to time-consuming and costly of experimental works, we designed two strong artificial intelligence (AI) models (artificial neural networks (ANN) and neuro-fuzzy inference systems (ANFIS)) to estimate the removal process of TC, and predict the removal percent of TC for new values of inputs before performing experiment. The experimental and computational studies showed that the fabricated photocatalysts are as promising candidates for industrial wastewater treatment to meet environmental regulations and provide a new avenue for practical implications.

Comparative mathematical and data-driven models for simulating the performance of forward osmosis membrane under different draw solutions

Mathematical models have frequently been used to simulate system performance, including forward osmosis (FO)-related processes. More recently, Industry 4.0 has increased in importance, and artificial intelligence (AI) technology has proven to be effective at assisting decision-making across a range of industries, including membrane processes. This study, for the first time, proposes a comparison of the accuracy of predictions for water permeability under various types of draw solutions using conventional models and AI-based models. The results showed that the AI-based models, including artificial neural networks (NN) (2 layers; 10 neurons) and adaptive neuro-fuzzy inference system (NFIS) (with grid partition; membership functions = 5) performed significantly better than the conventional mathematical intermediate blocking (CIB) model, with the coefficient values (R) of 0.974, 0.994, and 0.963, respectively. The corresponding errors of these simulations were 0.04, 0.70, and 0.97 LMH, indicating that the AI technique was better suited than the mathematical CIB model for simulating FO-related system performance. Additionally, using AI to forecast system performance is timely (i.e., considerably quicker than developing a sophisticated mathematical model) and cost-effective (i.e., reducing the expense for analysis of environmental factors for CIB model construction). The authors also successfully constructed an application for end-users for better and simpler experiences with modeling and simulation, even for those with varying knowledge in the field.

AI-based ensemble modeling of landfill leakage employing a lysimeter, climatic data and transfer learning

Predicting leachate pollutants is of prime importance in detecting the amount of pollution in water resources adjacent to sources of leakage. In this study, Electrical Conductivity (EC) as a physicochemical water pollution parameter with the possibility of portable measurement was used as an indicator of leachate quality for the Tychy-Urbanowice operating and closed landfill complex. In order to simulate landfill conditions, two lysimeter experiments were conducted simultaneously. Using sensors mounted in the lysimeters, from the end of November 2018 to the end of December 2019, EC, waste temperature and waste moisture were measured for the open lysimeter and only waste moisture for the closed lysimeter. Additionally, meteorological data obtained from the nearest synoptic station and soil moisture and temperature acquired from the GLDAS satellite were employed as external data to analyze various conditions. Thereafter, Artificial Neural Network (ANN), Neuro-Fuzzy Inference System (ANFIS), and Emotional ANN (EANN) models were developed to determine the parameters affecting the EC value recorded for the open lysimeter and subsequently, predict the missing EC parameter of the closed lysimeter by employing the transfer learning method. Following that, in order to improve the precision of EC predictions, ensemble techniques were applied to the outputs of the models that were developed. The results showed that the moisture of the lysimeters made a significant contribution to the EC value prediction. It is worth mentioning that among ANN, ANFIS, and EANN, the EANN model yielded more precise results in EC estimation, with the average DC above 0.80 and 0.90 for individual and ensembled modeling in both the training and verification phases, respectively.

Comparison of ANFIS and FLC as Charging Battery Based on Zeta Converter

Solar energy is an unlimited source of energyand its availability will never run out. It can be converted into asupply of electrical energy. And saved into battery throughconverter. There are many people who convert solar energy intoelectrical energy. Unfortunately, when stored in the battery, it isstill necessary to adjust the output voltage of the converter. So, itis need a controller to do it. To solve the problem, we proposeFuzzy Logic Controller (FLC) and Adaptive Neuro FuzzyInference System (ANFIS) control to adjust output voltage whilethe input voltage is fluctuative. We will compare which twocontrollers are better. We used the constant voltage method, andafter we ran the simulation, we got ANFIZ better than FLC.Because we get setting point faster when using ANFIZ. Theresult, it need time 0,04s to get setting point on output voltage

An enhanced ANFIS based approach for estimating petrophysical properties of thinly laminated reservoirs in absence of core data

Obtaining reliable petrophysical estimation of the thinly laminated reservoirs is a major challenge due to the convoluting effect of laminations on the conventional logging tools that jeopardizes the accuracy of the interpretations and hence poses major risks to the resource evaluation and field development planning. Many existing parametric or non-parametric correlations fail to provide reliable estimations and therefore domain expert knowledge is critical in the studies pertaining to thinly laminated reservoirs. We present a two-step approach based on neuro-fuzzy inference system (FIS), and harnessing the available expert knowledge for proper depositional environment (DE) analogues that determine the ranges of the parameters for the estimation exercise. Application of the method to the data from different DEs shows satisfying outcome. The use of a FIS to mine for proper DE that represents the thinly laminated sand reservoir at hand, prior to use of ANFIS, sets the proposed approach apart from other available research based on conventional applications of non-parametric regression methods. The proposed approach provides a pragmatic tool for estimating the properties of thinly laminated sands when no core data is available. It, therefore, greatly improves the modeling of laminated reservoirs, and therefore helps mitigate the risks associated with the field development.

Enhanced adaptive code modulation for rainfall fade mitigation in Ethiopia

Rain attenuation is considerably noticed in a frequency spectrum above 7-GHz for tropical equatorial regions and in a frequency spectrum higher than 10-GHz for temperate climates. The attenuation prediction method provided by the International Telecommunication Union-Recommendation (ITU-R), through Recommendation P.530-16 and P.618-13 utilize data collected from temperate regions. Since the average raindrop size is bigger and the rainfall rate is high in magnitude in tropical regions than that of non-tropical areas, this prediction model is not suitable for the measured rain data. Unfortunately, a rain fade mitigation technique based on local rain data has not been adequately studied in tropical regions. This paper presents an enhanced adaptive code modulation (ACM) for rainfall fade mitigation in Ethiopia. In this research work, locally collected one-minute rain rate data is used to determine the rain attenuation. Then based on this result, the neuro-fuzzy inference system is employed to enhance the mitigation technique. Furthermore, a comparison of the performance of this proposed scheme is with the non-adaptive technique, and fuzzy-based adaptive modulation and coding technique is carried out. MATLAB simulation result showed that lower-order quadrature amplitude modulation (QAM) scheme with a lower convolutional coding rate is better in maintaining link availability in bad weather conditions. However, spectral efficiency is improved by utilizing a larger constellation size of quadrature amplitude modulation (QAM) scheme with a higher convolutional coding rate when the channel is not affected by rain.

Computational Intelligence for Modeling, Control, Optimization, Forecasting and Diagnostics in Photovoltaic Applications [Book News

This book describes describes applications of machine learning techniques to maximum power point tracking (MPPT), PV-cell design and sizing, and hybridmodule design and modeling. PV-cell parameter extraction and estimation are proposed using moth–flame and chaotic optimization or deterministic and metaheuristic global optimization algorithms. Neuro-fuzzy inference systems (ANFIS) and a particle swarm optimization-artificial neural network model are applied to PV power output forecasting, while a domain adaptation of deep neural networks is proposed for multistep solar irradiance forecasting. Machine learning approaches are also presented for PV power prediction based on available environmental parameters. Additionally, PV plant operation failure modes and module deterioration diagnosis are studied using complex network and image analysis. After a preface, the book includes 16 carefully selected articles to cover recent trends in machine learning applications to PV systems. The book is an open access tool for engineers and researchers in applying machine learning methods to PV systems. The book is also suited for students willing to further use machine learning skills on PV applications and is a valuable resource for practicing professionals in need of understanding and pursuing advanced trends in PV systems.

Crop Yield Prediction using Granular SVM

Agriculture is the backbone of the Indian economy. Farming is a major source of income for many people in developing countries. Prediction of yield of crops is desirable as it can predict the income and minimise losses for the farmersunder unfavorable conditions. But predicting crop yield is a challenging task in developing countries like India. Conventionally, crop yield prediction is done using farmer’s expertise. The sustainability and productivity of a crop growing area are dependent on suitable climatic, soil, and biological conditions. So, data mining techniques based on neural networks, Neuro-Fuzzy Inference Systems, Fuzzy Logic, SMO, and Multi Linear Regression can be used for prediction. Previous work has performed yield prediction based on crop models considering only some of the environmental factors. This work uses a Support Vector Machine (SVM) to predict the crop yield under different environmental conditions that include soil, climate, and biological factors. Applying granular computing enables dividing the problem space into a sequence of subtasks. So, the hyperplane construction of SVM can be parallelized by splitting the problem space. Testing can also be parallelized. The main advantage is that linear SVM can be used to handle higher dimension space. Time complexity is reduced. Prediction using granular SVM can be parallelized using appropriate techniques like MapReduce/GPGPU. IoT-based agriculture increases crop yield by accurate prediction, automation, remote monitoring, and reducing wastage of resources. IoT-based monitoring systems can be used by farmers, researchers, and government officials to analyze crop environments and statistical information to predict crop yield. This paper proposes an IoT-based system to predict crop yield based on climatic, soil, and biological factors using parallelized granular support vector machines.

Light hydrocarbons solvents solubility modeling in bitumen using learning approaches

In this paper, two types of machine learning, namely neuro-fuzzy inference system (ANFIS) and multilayer perceptron (MLP), have been studied to model light hydrocarbons’ solubility solvent in bitumen. The 268 number of experimental data is used in this work from different articles. The input parameters are Temperature (T), pressure (P), and molecular weight (MW) of hydrocarbons. The result shows the high performance of the MLP model with a two layers to predict the experimental values. The estimated values were investigated by statistical parameters such as R 2, MSE, and MARD%. According to, statistical parameters, the values of 0.99, 0.00081, and 0.68 for MLP, and 0.96, 0.0029, and 0.78 for ANFIS indicate the high performance of the MLP model. Comparison between established models and previous work indicates that the developed model can be a suitable technique for solubility modeling

An ANFIS based inverse modeling for pneumatic artificial muscles

Pneumatic Artificial Muscles (PAM) are soft actuators with advantages of high force to weight ratio, flexible structure and low cost. On the other hand, their inherent nonlinear characteristics yield difficulties in modeling and control actions, which is an important factor restricting use of PAM. In literature, there are various modeling approaches such as virtual work , empirical and phenomenological models. However, they appear as either much complicated or are approximate ones as a variable stiffness spring for model with nonlinear input-output relationship. In this work, the behaviour of PAM is interpreted as an integrated response to pressure input that results in a simultaneous force and muscle length change. The integrated response behaviour of PAM is not combined effectively in terms of simultaneous resultant force and muscle contraction in many existing models. In order to implement that response, standard identification methods , for instance NNARX, are not suitable for modeling this behaviour. Moreover, an inverse modeling with grey box approach is proposed in order to utilize the model in control applications. Since Neuro-Fuzzy inference systems are universal estimators, the modeling is implemented by an ANFIS structure using the experimental data collected from PAM test bed. According to implementation results, the ANFIS based inverse model has yielded satisfactory performance deducing that it could be a simple and effective solution for PAM modeling and control issue.

Recognizing of the best different artificial intelligence method for determination of local scour depth around group piers in equilibrium time

Unlike calculation of scour depth around of a single pier, estimation of scour depth around group piers is a complex problem. In this research, four types of artificial neural networks (ANNs) were applied multi layer perceptron (MLP), radial basis function (RBF), neuro fuzzy inference system (ANFIS), and support vector machine (SVM). The inputs of ANNs were coordinates of considered points in the channel (X, Y), size of pier, flow depth, flow discharge, flow velocity, and critical velocity for inception of sediment transport. The trained methods were momentum and Levenberg–Marquardt (LM) training methods. Also, genetic algorithm (GA) was applied for optimization of MLP and RBF. Two group piers were used (three circular piers and three square piers) in a channel with stable flow conditions, scouring of clear water, and uniform bed particles (with D50 = 1.31 mm). Outputs of different ANNs (scour depth) were compared with observed data using of performance criteria correlation coefficient (R), mean square error (MSE), and mean absolute error (MAE). For circular piers, between square piers and behind of gear square pier, the best ANN is RBF-GA, while in front of first square pier, the best ANN is MLP-GA. The best ANNs have two hidden layers, and their training method is the Levenberg–Marquardt (LM). The values of R, MSE, and MAE of RBF-GA are 0.997, 1.66 mm2, and 0.9 mm, and the values of R, MSE, and MAE of MLP-GA are 0.997, 2.55 mm2, and 1.16 mm. Also, the sensitive analysis shows that threshold velocity (Uc) is the most effective factor on scour depth

Dimension Reduction of Machine Learning-Based Forecasting Models Employing Principal Component Analysis

In this research, an attempt was made to reduce the dimension of wavelet-ANFIS/ANN (artificial neural network/adaptive neuro-fuzzy inference system) models toward reliable forecasts as well as to decrease computational cost. In this regard, the principal component analysis was performed on the input time series decomposed by a discrete wavelet transform to feed the ANN/ANFIS models. The models were applied for dissolved oxygen (DO) forecasting in rivers which is an important variable affecting aquatic life and water quality. The current values of DO, water surface temperature, salinity, and turbidity have been considered as the input variable to forecast DO in a three-time step further. The results of the study revealed that PCA can be employed as a powerful tool for dimension reduction of input variables and also to detect inter-correlation of input variables. Results of the PCA-wavelet-ANN models are compared with those obtained from wavelet-ANN models while the earlier one has the advantage of less computational time than the later models. Dealing with ANFIS models, PCA is more beneficial to avoid wavelet-ANFIS models creating too many rules which deteriorate the efficiency of the ANFIS models. Moreover, manipulating the wavelet-ANFIS models utilizing PCA leads to a significant decreasing in computational time. Finally, it was found that the PCA-wavelet-ANN/ANFIS models can provide reliable forecasts of dissolved oxygen as an important water quality indicator in rivers.

Basement Flood Control with Adaptive Neuro Fuzzy Inference System Using Ultrasonic Sensor

This paper proposes a basement flood management system based on Adaptive Neuro Fuzzy Inference System (ANFIS). Basement is one of the main parts of a building that has a high potential for flooding. Therefore, the existence of a flood control system in the basement can be a solution to this threat. Water level control is the key to solving the problem. Fuzzy Inference System (FIS) has proven to be a reliable method in the control system but this method has limitations, that is, it needs to have a basis or a reference when determining the fuzzy set. When there is no basis or reference, Adaptive Neuro FIS (ANFIS) can be a solution. The Neuron aspect in ANFIS determines fuzzy sets through training data. In terms of the Internet of Things (IoT), this system uses an ultrasonic sensor, Node Red IoT platform, and Matlab Server. Then the water pump will turn on to control the water level when there is rainfall. By undergoing a comparative test with the FIS method, ANFIS provides a lower Root Mean Square Error (RMSE) and is recommended for use in basement flood management systems.