Sugeno-type Fuzzy Inference System Research Articles

Comparative Analysis of Fuzzy Expert Systems for Diabetic Diagnosis

Diabetes is a situation when a body is not capable to produce insulin, which is needed to control glucose. Diabetes will also develop heart disease, kidney disease, blindness, nerve damage, and blood vessel damage. This paper uses Mamdanitype and Sugeno-type fuzzy expert systems for a diabetes diagnosis. Fuzzy expert system is a group of membership functions and rules. Fuzzy expert systems are tilting toward numerical processing. This paper recapitulates the essential distinction between the Mamdani-type and Sugeno-type fuzzy expert systems by using the input parameters such as age, obesity, RBS(Random Blood Sugar), family history and diet. The MATLAB fuzzy logic toolbox is used for the imitation of both the models. The accuracy, sensitivity, specificity and precision of the Mamdani-type fuzzy expert system is 95.48%, 96.36%, 93.33% and 97.24%, respectively, and the accuracy, sensitivity, specificity and precision of the Sugenotype fuzzy inference system is 96.77% , 97.27%, 95.55% and 98.16%, respectively. General Terms Expert system, fuzzy logic, membership function

An Online Learning Control Strategy for Hybrid Electric Vehicle Based on Fuzzy Q-Learning

In order to realize the online learning of a hybrid electric vehicle (HEV) control strategy, a fuzzy Q-learning (FQL) method is proposed in this paper. FQL control strategies consists of two parts: The optimal action-value function Q*(x,u) estimator network (QEN) and the fuzzy parameters tuning (FPT). A back propagation (BP) neural network is applied to estimate Q*(x,u) as QEN. For the fuzzy controller, we choose a Sugeno-type fuzzy inference system (FIS) and the parameters of the FIS are tuned online based on Q*(x,u). The action exploration modifier (AEM) is introduced to guarantee all actions are tried. The main advantage of a FQL control strategy is that it does not rely on prior information related to future driving conditions and can self-tune the parameters of the fuzzy controller online. The FQL control strategy has been applied to a HEV and simulation tests have been done. Simulation results indicate that the parameters of the fuzzy controller are tuned online and that a FQL control strategy achieves good performance in fuel economy.

Adaptive neuro-fuzzy inference-based modeling of a full-scale expanded granular sludge bed reactor treating corn processing wastewater

In this study, an adaptive neuro-fuzzy inference system ANFIS including five process variables, such as influent chemical oxygen demand, influent flow rate, influent total Kjeldahl nitrogen, effluent volatile fatty acids and effluent bicarbonate, was described to predict the effluent chemical oxygen demand load from a full-scale expanded granular sludge bed reactor EGSBR treating corn processing wastewater. The proposed ANFIS model was conducted by applying hybrid learning algorithm and the model performance was tested by the means of distinct test data set randomly selected from the experimental domain. The ANFIS-based predictions were also validated using various descriptive statistical indicators, such as root mean-square error, index of agreement, the factor of two, fractional variance, proportion of systematic error, etc. The lowest root mean square error RMSE = 0.03655 and the highest determination coefficient R2 = 0.958 were achieved with the subtractive clustering of a first-order Sugeno type fuzzy inference system. ANFIS predicted results were compared with the outputs of multiple nonlinear regression analysis-based models derived in the scope of the present work. Statistical performance indices computed for the testing data set proved that the developed ANFIS-based model exhibited a very good precision in predicting the effluent chemical oxygen demand, load for the EGSBR system. Due to high capability of the ANFIS model in capturing the dynamic behavior and non-linear interactions, it was demonstrated that a complex system, such as anaerobic digestion, could be easily modeled.

Prediction of inverse kinematics of a 5-DOF pioneer robotic arm having 6-DOF end-effector using ANFIS

In this paper, a method for forward and inverse kinematics analysis of a 5-DOF pioneer robotic arm PArm having 6-DOF end-effector is proposed. Obtaining the trajectory and computing the required joint angles for a higher DOF robot manipulator is one of the important concerns in robot kinematics and control. The difficulties in solving the inverse kinematics equations of higher DOF robot manipulator arises due to the presence of uncertain, time varying and nonlinear nature of equations having transcendental functions. In this paper, the ability of adaptive neuro-fuzzy inference system ANFIS is used to the generated data for solving inverse kinematics problem. The proposed hybrid neuro-fuzzy system combines the learning capabilities of neural networks with fuzzy inference system for nonlinear function approximation. A single-output Sugeno-type fuzzy inference system FIS using grid partitioning has been modelled in this work. The Denavit-Hartenberg D-H representation is used to model robot links and solve the transformation matrices of each joint. The forward kinematics and inverse kinematics for a 5-DOF manipulator are analysed systemically.

Exploration feature selection applied to hybrid data integration modeling: Targeting copper-gold potential in central Iran

A Sugeno-type fuzzy inference system is implemented in the framework of an adaptive neural network to map Cu–Au prospectivity of the Urumieh–Dokhtar magmatic arc (UDMA) in central Iran. We use the hybrid “Adaptive Neuro Fuzzy Inference System” (ANFIS; Jang, 1993) algorithm to optimize the fuzzy membership values of input predictor maps and the parameters of the output consequent functions using the spatial distribution of known mineral deposits. Generic genetic models of porphyry copper–gold and iron oxide copper–gold (IOCG) deposits are used in conjunction with deposit models of the Dalli porphyry copper–gold deposit, Aftabru IOCG prospect and other less important Cu–Au deposits within the study area to identify recognition criteria for exploration targeting of Cu–Au deposits. The recognition criteria are represented in the form of GIS predictor layers (spatial proxies) by processing available exploration data sets, which include geology, stream sediment geochemistry, airborne magnetics and multi-spectral remote sensing data. An ANFIS is trained using 30% of the 61 known Cu–Au deposits, prospects and occurrences in the area. In a parallel analysis, an exclusively expert-knowledge-driven fuzzy model was implemented using the same input predictor maps. Although the neuro-fuzzy analysis maps the high potential areas slightly better than the fuzzy model, the well-known mineralized areas and several unknown potential areas are mapped by both models. In the fuzzy analysis, the moderate and high favorable areas cover about 16% of the study area, which predict 77% of the known copper–gold occurrences. By comparison, in the neuro-fuzzy approach the moderate and high favorable areas cover about 17% of the study area, which predict 82% of the copper–gold occurrences.

Control of Z-Source Inverter Based PV System with MPPT Using ANFIS

This paper presents an artificial intelligence based MPPT technique to deliver maximum power from a photo-voltaic (PV) system for three phase resistive load. Z-source inverter (ZSI) is employed in the system to boost PV module output voltage as well as inversion of voltage simultaneously in a single-stage. Here PV cell and PV module model are developed from mathematical equations. The ZSI eliminates the limitations of conventional boost converter interfaced with voltage source inverter (VSI). Simple boost control technique with sinusoidal pulse width modulation is used here for ZSI. Inductor and capacitor values are calculated for Z-source network. In the proposed system duty ratio control of ZSI is developed to control the output power of PV panel. Maximum power point tracking (MPPT) technique using Adaptive Neuro-Fuzzy Inference System (ANFIS) is developed and trained with hybrid learning algorithm to identify parameters of Sugeno-type fuzzy inference systems using Matlab/Simulink tool box for PV module.ANFIS based MPPT is trained with various membership functions like trapezoidal, gauss and bell membership function .Comparative study is done for the complete system using both the artificial neural network (ANN) based MPPT technique and ANFIS based MPPT technique, based on their performance parameters and simulated results in MATLAB/Simulink.

Sugeno-Type Fuzzy Inference Model for Stock Price Prediction

operations of the prediction of stock price are complex and risky due to fluctuation in the stock market because of the vagueness, incompleteness, and uncertainty of the information used. However, it is therefore as a matter of necessity to seek to foresee stock prices because traders need to know when to invest in order to get the maximum return of the investment. This paper proposes a Sugeno-type fuzzy inference system for stock price prediction using technical indicators as its input values. Knowledge Base, Fuzzification, Inference Engine and Defuzzification are the essential components of our model. We explore Sugeno-type fuzzy inference engine to optimize the estimated result. We evaluate the degree of participation of each input parameter with Trapezoidal membership function. Center of Gravity technique is employed for defuzzification. We employ object oriented design tool to model our database. MATLAB and fuzzy relational database are used in the implementation of our study. The development of this system is based on the selection of stock data history which are studied and used for training the system. This system provides vital support to stock traders, researchers and other financial experts in making decisions as regards stock trading.

Quantification of sand fraction from seismic attributes using Neuro-Fuzzy approach

In this paper, we illustrate the modeling of a reservoir property (sand fraction) from seismic attributes namely seismic impedance, seismic amplitude, and instantaneous frequency using Neuro-Fuzzy (NF) approach. Input dataset includes 3D post-stacked seismic attributes and six well logs acquired from a hydrocarbon field located in the western coast of India. Presence of thin sand and shale layers in the basin area makes the modeling of reservoir characteristic a challenging task. Though seismic data is helpful in extrapolation of reservoir properties away from boreholes; yet, it could be challenging to delineate thin sand and shale reservoirs using seismic data due to its limited resolvability. Therefore, it is important to develop state-of-art intelligent methods for calibrating a nonlinear mapping between seismic data and target reservoir variables. Neural networks have shown its potential to model such nonlinear mappings; however, uncertainties associated with the model and datasets are still a concern. Hence, introduction of Fuzzy Logic (FL) is beneficial for handling these uncertainties. More specifically, hybrid variants of Artificial Neural Network (ANN) and fuzzy logic, i.e., NF methods, are capable for the modeling reservoir characteristics by integrating the explicit knowledge representation power of FL with the learning ability of neural networks. In this paper, we opt for ANN and three different categories of Adaptive Neuro-Fuzzy Inference System (ANFIS) based on clustering of the available datasets. A comparative analysis of these three different NF models (i.e., Sugeno-type fuzzy inference systems using a grid partition on the data (Model 1), using subtractive clustering (Model 2), and using Fuzzy c-means (FCM) clustering (Model 3)) and ANN suggests that Model 3 has outperformed its counterparts in terms of performance evaluators on the present dataset. Performance of the selected algorithms is evaluated in terms of correlation coefficients (CC), root mean square error (RMSE), absolute error mean (AEM) and scatter index (SI) between target and predicted sand fraction values. The achieved estimation accuracy may diverge minutely depending on geological characteristics of a particular study area. The documented results in this study demonstrate acceptable resemblance between target and predicted variables, and hence, encourage the application of integrated machine learning approaches such as Neuro-Fuzzy in reservoir characterization domain. Furthermore, visualization of the variation of sand probability in the study area would assist in identifying placement of potential wells for future drilling operations.

Intelligent Modeling and Analysis of Moisture Sorption Isotherms in Milk and Pearl Millet–Based Weaning Food “Fortified Nutrimix”

Soft computing–based intelligent models have been proposed to predict moisture sorption isotherms in milk and pearl millet–based weaning food, “fortified Nutrimix,” at four temperatures, 15, 25, 35, and 45°C over the water activity range 0.11–0.97. Connectionist and adaptive neuro-fuzzy inference system (ANFIS) models were investigated. A back-propagation algorithm with Bayesian regularization/Levenberg-Marquardt optimization mechanisms was employed to develop connectionist models. The ANFIS model was based on the Sugeno-type fuzzy inference system. In addition, several empirical models were explored for fitting the sorption data. The soft computing models, in particular, ANFIS, outperformed the conventional sorption models for predicting isotherms in Nutrimix.

Neuro-Fuzzy for Sensor Fault Detection and Isolation

This paper presents the sensor fault configuration through Neuro-Fuzzy. As we know that sensor faults have been observed in may domain. Various sensors faults are present such as bias, scaling, drift so to remove this kind of fault which is present we make the sensor to reconfigure to normal condition and this reconfiguration is done through Neuro-Fuzzy which uses the expert knowledge stored in them while training. This technique is implemented through ANFIS tool. Sugeno-Type fuzzy inference system is used, which is adaptive in nature and also Gaussian membership function is used. This technique uses the hybrid optimization which consists of combination of backpropagation and least square method algorithm. Simulation result is shown.

Generating fuzzy rule base classifier for highly imbalanced datasets using a hybrid of evolutionary algorithms and subtractive clustering

In this paper, a design methodology is proposed for generating a fuzzy rule-based classifier for highly imbalanced datasets (only binary classification problems). The classifier is based on sugeno-type fuzzy inference system (FIS) and is generated using subtractive clustering, differential evolution (DE) and multi-gene genetic programming (MGGP) to obtain fuzzy rules. Subtractive clustering and DE are utilized for producing antecedents of rules and MGGP is employed for generating the functions in the consequence parts of rules. Feature selection is utilized as an important pre-processing step for dimension reduction. Performance of the proposed method is compared with some fuzzy rule-based classification approaches taken from the literature. The experiments are performed over 22 highly imbalanced datasets from KEEL dataset repository; the classification results are evaluated using AUC as a performance measure. Some statistical non-parametric tests are used to compare classification performance of different methods in different datasets. The obtained results reveal that the proposed classifier outperforms other methods in terms of AUC values.

Study of fuzzy systems with Sugeno and Mamdani-type fuzzy inference systems for determination of heartbeat cases on Electrocardiogram (ECG) signals

This paper discusses the suitability of implementing Sugeno- and Mamdani-type FISs for heartbeat case determination based on the Electrocardiogram (ECG) signals. The heartbeat cases are Normal Sinus Rhythm (NORM), Left Bundle Branch Block (LBBB), Right Bundle Branch Block (RBBB), Ventricular Premature Contractions (VPC) and Atrial Premature Contractions (APC). Overall, fuzzy system with Sugeno-type FIS was developed based on the FL method used in a paper. System modifications were carried out to create an alternative system for the application, implemented using Mamdani-type FIS. Both systems were verified with 3000 sets of random data for systems’ performance comparison. Sugeno’s system sensitivities in determining each heartbeat case are 100%, which leads to a TCA value of 100%, whereas in Mamdani’s system, the sensitivities are all 100%, except for NORM heartbeat case which is 99.8% and thus TCA value is 99.9667%. It is also found that the Sugeno’s system processing time is always less compared to Mamd...

Prediction of Pyrite Oxidation in a Coal Washing Waste Pile Applying Artificial Neural Networks (ANNs) and Adaptive Neuro-fuzzy Inference Systems (ANFIS)

Two models were evaluated as alternative methods for predicting pyrite oxidation in the Alborz Sharghi coal washing waste pile (in northeastern Iran). The first model applies a ‘feed-forward artificial neural network (ANN) with 4-7-1 structure’. The model uses depth, initial remaining pyrite fraction, mole fraction of oxygen, and annual precipitation as input parameters and returns the remaining pyrite fraction in the related depth of the pile as its output. In the second model, an adaptive neuro-fuzzy inference system (ANFIS), which uses generalised bell membership functions and the Takagi–Sugeno-type fuzzy inference system, was applied with the same input–output parameters. The correlation coefficient, root mean squared error, and average absolute relative error for the training stage of the ANNs were 0.81, 0.169, and 0.12, respectively, while the values for ANFIS were 0.91, 0.091, and 0.078, respectively. Comparison of the correlation coefficients and the error parameters revealed that both models successfully predicted remaining pyrite fraction from various depths of the pile. However, ANFIS was found to be more reliable and more accurate.

A neuro-fuzzy network based impulse noise filtering for gray scale images

A neuro-fuzzy network based impulse noise filtering for gray scale images is presented. The proposed filter is constructed by combining two neuro-fuzzy filters with a postprocessor, which generates the final output. Each neuro-fuzzy filter is a first order Sugeno type fuzzy inference system with 4-inputs and 1-output. The proposed impulse noise filter consists of two modes of operation, namely, training and testing (filtering). As demonstrated by the experimental results, the proposed filter not only has the ability of noise attenuation but also possesses desirable capability of detail preservation. It significantly outperforms other conventional filters.

ADAPTIVE NOISE SUPPRESSION IN VOICE COMMUNICATION USING ASSNFIS SYSTEM

The paper proposed the adaptive noise suppression technique for suppression of noise in voice communication. There are different techniques earlier used for adaptive filteration like least mean square, kalman’s filter etc.In the paper we used “fuzzy logic” technique for adaptive filteration. We know about the theory of adptive filteration of noise and application of fuzzy logic. We are using the fuzzy logic functions anfis and genfis1 by matlab for simulation. Anfis is the adaptive neuro-fuzzy training of sugeno-type fuzzy inference systems. In this paper we uses anfis system to suppress different types of noise from voice signal.

Using GA for Optimization of the Fuzzy C-Means Clustering Algorithm

Fuzzy C-Means Clustering algorithm (FCM) is a method that is frequently used in pattern recognition. It has the advantage of giving good modeling results in many cases, although, it is not capable of specifying the number of clusters by itself. In FCM algorithm most researchers fix weighting exponent (m) to a conventional value of 2 which might not be the appropriate for all applications. Consequently, the main objective of this paper is to use the subtractive clustering algorithm to provide the optimal number of clusters needed by FCM algorithm by optimizing the parameters of the subtractive clustering algorithm by an iterative search approach and then to find an optimal weighting exponent (m) for the FCM algorithm. In order to get an optimal number of clusters, the iterative search approach is used to find the optimal single-output Sugeno-type Fuzzy Inference System (FIS) model by optimizing the parameters of the subtractive clustering algorithm that give minimum least square error between the actual data and the Sugeno fuzzy model. Once the number of clusters is optimized, then two approaches are proposed to optimize the weighting exponent (m) in the FCM algorithm, namely, the iterative search approach and the genetic algorithms. The above mentioned approach is tested on the generated data from the original function and optimal fuzzy models are obtained with minimum error between the real data and the obtained fuzzy models.

Performance Evaluation of Mamdani-type and Sugeno-type Fuzzy Inference System Based Controllers for Computer Fan

Nowadays, there are several models of computer systems finding their ways into various offices, houses, organizations as well as remote locations. Any slight malfunction of the computer system's components could lead to loss of vital data and information. One of the sources of computer system malfunction is overheating of the electronic components. A common method of cooling a computer system is the use of cooling fan(s). Therefore, it is essential to have an appropriate control mechanism for the operation of computer system's cooling fan in order to save energy, and prevent overheating. Failure to adopt a well designed and efficient performance controller could lead to the malfunction of a computer system. Presently, most controllers in computer systems are pulse width modulation based. That is, they make use of pulses in form of digits, 0 and 1. It was observed that inherent noise is still prevalent in the operation of computer system. Also, eventual breakdown of components is common. A new approach is therefore investigated through the use of fuzzy logic to serve as a base or platform to build an intelligent controller using a set of well defined rules to guide its operational performance. Mamdani-type fuzzy inference system and Sugeno-type fuzzy inference system were used with two input sets each and a single output function each. Simulation was carried out in MATLAB R2007a platform and operational performances of the two approaches were compared. Simulated results of the performances of the Mamdani-type fuzzy inference system based controller and the Sugeno-type fuzzy inference system based controller are presented accordingly.

A new human comfort model onboard a vessel based on Sugeno type fuzzy inference system

The objective of this research is to develop a human (passenger/crew) comfort model to establish the relationship between the indoor living conditions and the motions of a vessel, with the main objective of being able to provide better insight and understanding of the factors that can make a human more comfortable onboard a vessel during her operation. In order to do this, a new passenger comfort index (PCI) is developed by using a Sugeno type fuzzy inference system which takes into account seven variables which are motion sickness, air temperature, mean radiant temperature, relative humidity, air velocity, activity level of passengers and their clothing insulation. The PCI is calculated implicitly as the outcome of linguistic rules which are expressed as in the form of if-then clauses. Validation and operational scenarios are performed and discussed to show the applicability of the proposed index. The proposed methodology can be used as a human comfort assessment tool during ship design stage as well as a real-time comfort evaluation of human/passengers to help ship personnel onboard a passenger vessel during her voyage.

Fuzzy model for predicting project performance based on procurement experiences

Abstract This paper presents a data-clustering-based fuzzy model for predicting the performance of construction projects delivered through different procurement methods. To illustrate the model, a sample of 96 substation projects of an electric power company, delivered through the design–bid–build (DBB), design–build (DB), and turnkey (TK) methods, were used as training and testing data for model development and verification. Through a factor analysis, an initial set of 48 variables was reduced to nine inputs to the model for predicting eight performance metrics as outputs of the model. To establish the input–output relationships for each metric, Sugeno-type fuzzy inference systems were built, wherein the fuzzy rules were derived from selected projects as the estimated cluster centers in the training data. For the limited sample, zeroth-order systems built with hybrid training were found to outperform both first-order systems and stepwise regression models in prediction accuracy, while sensitivity analyses confirmed their robustness. As the data represents the company's procurement experiences of substation projects, the model may be regarded as a way of implementing organizational learning to improve procurement decision.

Fuzzy Controller Design of TCSC with ANFIS to Improve the Dynamic Stability of Power System

In this paper, a new variable fuzzy control algorithm is proposed for thyristor-controlled series capacitor (TCSC) to improve power system dynamic performance. Rules of adaptive neuron fuzzy inference system (ANFIS) devise this fuzzy controller for TCSC in power system. ANFIS uses a hybrid learning algorithm to identify the membership function parameters of Sugeno-type fuzzy inference system. Consequences of this control trend are compared with PI controller and it is shown by using fuzzy controller the system has more stable power flow and less power oscillations. Simulation results signify power stability improvement of two-area power system by using fuzzy controller in TCSC than traditional PI controller.