Optimized Fuzzy Logic Controller and Neural Network Controller- a comparative study
|
|
- Emory Russell
- 5 years ago
- Views:
Transcription
1 Optimized Fuzzy Logic Controller and Neural Network Controller- a comparative study JOSÉ B. MENEZES FILHO, J. BOAVENTURA-CUNHA 2, NUNO MIGUEL FERREIRA 3 () Instituto Federal de Educação, Ciência e Tecnologia da Paraíba Av. Primeiro de Maio, 72, Jaguaribe - João Pessoa-PB BRAZIL jbmenezesf@hotmail.com (2) University of Trás-os-Montes and Alto Douro; INESC TEC - INESC Technology and Science Engenharias I, 5-8 Vila Real PORTUGAL jboavent@utad.pt; jose.boaventura@inesctec.pt (3) Instituto Superior de Engenharia de Coimbra Rua Pedro Nunes, Quinta da Nora, Coimbra PORTUGAL nunomig@isec.pt Abstract: - This work presents the use of a Mamdani Fuzzy controller and a Neural Network controller to detect and catch an object on a 2 axes (X,Y) workspace with a robot arm. The controllers use two inputs and one output for each of two controlled axes of the robot. The inputs are defined as the position errors and the derivative of the position errors regarding the setpoint position (X REF, Y REF ) of the object to catch. The outputs of the controllers drive the X and Y axes motors. The two axes motors are actuated with the objective of capturing an object on a workspace, being the object position, i.e. the setpoint position, computed by processing an image acquired with a video camera placed over the workspace. A genetic algorithm, developed in a previous work, was used to compute the characteristics of the membership functions of the Mamdani Fuzzy Controller. The robot positioning system, using the two axes transfer functions, the Fuzzy controller and the Neural Network controller were simulated in MATLAB environment being the results presented. Also, the performances of the controllers are compared regarding the setpoint tracking accuracy, the evolution of the (x,y) trajectories over time and the control effort. Key-Words: - Fuzzy control, Neural Network, Modeling, Optimization, Position control, Robot claw Introduction Positioning systems such as robotic manipulators are widely used in a wide variety of industrial processes. Particularly, systems that have motion control provides a continuous improvement of product quality associated with the minimization of manufacturing costs, which are possible through the use of high-precision equipment that combine flexibility with security and high-speed time response, such as robotic systems. Therefore, the modeling and control studies for robotic systems play an important role in the industrial development. This paper presents and compares two strategies to control a robot of two degrees of freedom with the goal of locate and catch an object over a workspace. A video camera is used to acquire an image of the object, the claw and the workspace. Afterwards, the image is processed to compute the object position, i.e. the setpoint position to be reached by the robot claw (X REF, Y REF ), and the actual claw position (x, y). A Mamdani fuzzy logic controller and a Neural Network controller were designed and tested to drive the X and Y robot motors with the goal of positioning the robotic claw on the object. Systems based on fuzzy logic and neural networks have great potential to solve several problems in the control engineering fields. Also, there are growing interests in the development of fuzzy logic and neural networks controllers, among other intelligent control techniques, since they are generally well ISBN:
2 suited to solve nonlinear control problems [, 2, 3, 4, 2, 3]. The fuzzy and neural controllers can efficiently regulate several variables of nonlinear processes, but the first one works in a way that mimics the reasoning of human operators while the neural network control exhibits a black-box nature. If both controllers are properly designed, they can cope with complex nonlinear input-output relationships, being robust for real time operation under noise environments. However, a neural network controller is more difficult to design since it must be determined the optimal number of nodes, hidden layers, activation functions, etc., being the computation load high. The pioneering work in application of fuzzy logic in process control is due to [], whose theoretical supports are described in the works of [3, 5, 6]. Although different methods are available in the literature, they can be classified into two major groups: The Mamdani and the Sugeno Fuzzy systems [2, 3]. In this work is shown the results obtained using an optimized Mamdani Controller and a neural network controller to drive a two axes robot. The methods are validated with the presentation of simulation results. Each axis is represented with a transfer function obtained by solving a previous identification problem using experimental data. The simulations use the same setpoints to evaluate and compare the performances of both controllers. This work is organized in the following way: In this first section is presented the overall view of the subject treated. In section two is presented the problem formulation, where is shown the complete system to be controlled. Section three describes the design and the implementation of the Fuzzy Controller. Section four presents the design and implementation of the Neural Network Controller. These two previous sections also present the simulation results obtained with both control strategies. Section five presents a comparative evaluation of the performances of the two controllers. Finally, in the sixth section, are drawn the conclusions and perspectives for future work. (G) and the ultimate array correspond to the blue color (B). Figure shows a detail of the original image acquired of the object in the workspace (a), and the images obtained by decomposition in the Red color (.b), Green color (.c) and Blue color (.d). a b c d Fig. - Image acquired with the video camera (.a) and its decompositions in the Red color (.b) Green color (.c) and Blue color (.d). To Process the camera video signal, the Green color array is used since it provides a better contrast. In this array, each element with values ranging from to 255 corresponds to one pixel. The value corresponds to white color and the value 255 to the black color. A binarization of the image is afterwards performed using a threshold value of. The values of the pixels with values greater than are transformed to 255, while the values of pixels with values less or equal than are transformed to. In this way, the values of all elements of the matrix have only two possibilities: to a white color and 255 to a black color. After transforming the values of all elements to the binary format, the computational program checks all elements of the array starting the first row and column up to the last. As in the beginning of process all elements are, corresponding to a background of the workspace, search continues until to the first time that the process find an element equal to 255. It is considered that the object on the workspace is detected when the first transition between and 255 is found. The following sequence is performed by the computational program: 2 Problem Formulation The image of the object in the workspace, which is the target to reach by the robot claw is acquired with a video camera in the format of array with dimensions (567,24,3). Afterwards the image is decomposed in three arrays, the first corresponding to the red color (R), the second is the Green color. Read the array of color that is sent by the web camera. 2. Extract the three arrays that contain the basic colors: Red, Green and Blue. 3. Reduce the values of each element of the array Green to two values: or 255, dependent upon of its original value compared to the previous defined threshold. 4. Identification of the object position ISBN:
3 The complete Robot system controller architecture is shown in Fig. 2. In the blocks called Controller and Controller is located either the Optimized Fuzzy Logic Controller or the Neural Network controller. The overall objective for both controllers, is that the claw must follow a computed trajectory to catch the object in the workspace according to defined project specifications regarding time responses and control effort. Image of target object obtained by web camera Image signal processing Calculating of speed Calculating of speed Computer Locating of object error(k) error(k-) error(k) error(k-) Controller Controller Locating of robot hand z - ex z - ^ R ey Robot + - V^ e^ Determining ex and ey Ux Uy Driving of Driving of Fig. 2. Complete Robot Hand Controller In Fig. 2 the signals Rˆ, Vˆ and ê represent the reference position of the target object, the position of the robotic hand, and the error, respectively, in the Cartesian coordinates (x,y). The signals e x and e y are the position errors and U x and U y the control signals driving the motors regarding the X and Y axes. In order to perform the simulations it were used two identical third order Transfer Functions for both X and in terms of Z transform. These functions have one sample time delay and their parameters were previously obtained with the use of identification techniques. Eq. () shows the Transfer functions used for the X and Y axes. The sample time in which the Transfer Functions were computed was ms. ( Z Z 2 ) KZ G, y ( z) = 69374Z Z Z 3 x () With the gain K= Fuzzy Controller The Mamdani Fuzzy Controller uses two input variables: The distance between the object and the robotic hand for both axes called Error and the variation of this error, which is called derror. The memberships functions used for the Error variable were formed by four membership functions with triangular shapes called Ze (Zero), Sp (Small positive), Mp (Medium positive) and Gp (Great positive). The Figures 3 and 4 show the Memberships Functions regarding the x and y axes of the controller for the Error and derror variables. Note that it is only necessary the use of the positive side of the universe of discourse owing to the fact that it is assumed the symmetry of the control. If the error is negative, the control signal is multiplied by - and applied to the Transfer Function. Fig. 3. Membership Functions of error variable Fig. 4. Membership Functions of derror variable In the preceding Figures are shown the points xsp and xmp. The determination of these points plays an important role in the construction of the membership functions. By means of shifting these points it is possible to modify the shape of the triangle of the membership functions Sp and Mp. It was performed an optimization of the membership functions using a genetic algorithm using a population of 8 chromosomes, wich of them with 8 genes, according to [7, 8]. The optimization procedure was performed to minimize a cost function given by the quadratic of the actuating signals multiplied by time. In this way it was founded the optimal values xsp=9 and xmp=8. ISBN:
4 3. Mamdani Fuzzy Controller Inference In the inference step of Mamdani Fuzzy Controller, the composition of each rule and the relationship between them is accomplished in accordance to Table (). In this step whenever the rule if then is activated the consequences are obtained with the minimum value between the Error and Derror. It was utilized the inference technique MAX-MIN. In this step the control variables, which drive the axes motors of the robot, are determined. The variables have four membership functions and are applied in the universe of discourse that range from to. In the defuzzification process it was utilized de Centerof-Area method. This method was successfully applied in [9]. Table. Fuzzy Rules Table of Fuzzy Mamdani controller Error Derror DZe DSp DMp DGp Ze Ze Sp Sp Mp Sp Sp Mp Mp Gp Mp Mp Gp Gp Gp Gp Gp Gp Gp Gp 3.2 Mamdani Fuzzy Controller Results The manipulator was driven from an initial point in the planar space given by the coordinates (.,) to a final position (.,.), being these values normalized. Both axis are driven by an individual Mamdani Fuzzy Controller. The trajectory performed by the and the are shown in Figures 5 and 6 and the planar trajectory, composed by two axis is shown in Fig. 7. trajectory Fig. 5. trajectory- Fuzzy Controller Y Axis Y Axis Y Axis trajectory Fig. 6. trajectory- Fuzzy Controller Initial position Final position ) Fig. 7. Planar trajectory- Fuzzy Controller Note that all the simulation results are presented as per unit value. In practical experimentation, the true measures may be in any units. In per unit values the results are not affected by the measurement units. So, the universe of discourse ranges between zero to one in accordance with the use of per unit value. 4. Neural Network Controller A Neural Network controller implemented in Matlab environment is used to perform the simulations using the same response specifications specified for the Fuzzy controller. The Neural Network has two layers. The input layer contains two neurons which receives the error and the derivative of the error of the position signals. The second layer, called the hiden layer, has 5 neurons. The Neural Network is trainned by the well known backpropagation scheme. The complete structure is shown by Fig. 8. The output layer of the Neural Network Controller have a single neuron. The output layers of each network provide the control signals to the axes motors. ISBN:
5 coordinates (.,) to the point (.,.). Both axis are driven by an individual Neural Network Control. The trajectory performed by the and the Y axis are shown in the Figures 9 and and the planar trajectory, composed by two axis is shown in Fig.. Fig. 8. Neural Network Controller Architecture The number of the neurons used in the hidden layer was specified after performing several tests. The Neural Network was tested with 4, 8, 2 and 5 neurons in this layer. The tests with 5 neurons showed better results. In this structure, the input layer serves only to connect the input signals to the hidden neural network. The connections between each input terminal and the hidden layer neurons occur through 3 synaptic weights called "win", forming an array of 2 rows and 5 columns. The connections between the neurons of the hidden layer and the output layer of neurons occur through synaptic weights called "whid". These synaptic weights form a matrix with 5 columns and row. All the activation functions of the hidden layer are hyperbolic tangents. The type of these functions was the same used in a previous work [9]. The neural controller is adaptive, since for each sampling time the synaptic weights and win whid are adjusted to provide a better control. For each sampling period, the processes occurring in the forward direction, or straight through processing (Feedforward) and backpropagation (Backpropagation) which starts at the output layer and propagates toward the input layer aims to update the synaptic weights [, ]. The synaptic weights were chosen initially randomly. The algorithm was executed several times until the signal output of the plant reach the reference signal without overshoot and whit a smaller time settling. 4.. Neural Network Controller Results In the same way as the simulation performed with the Fuzzy Controller, the manipulator was driven from an initial point in the planar space given by the X Axis Trajetory reference Fig. 9. trajectory- NN Controller Y trajectory Fig.. trajectory- NN Controller Initial position Final position.2 Fig.. Planar trajectory- NN Controller 5. Comparative study In order to compare the results of the two strategies the trajectories of both obtained outputs are shown in Fig. 2 for the and Fig. 3 for the. The planar trajectory obtained by the two strategies is shown in Fig. 4. Also, it were computed, for both controllers, the performance indexes expressed by Eq. 2 to 5. ISBN:
6 X Axis Fuzzy Logic result neural network result E ey = e y (t) 2.t (5) The values for each of these indexes are show in the Table 2. Table 2. Performance indexes of the Fuzzy Mamdani and the Neural Network controllers.2 Fig. 2. trajectories Performance indexes Controller E ux E uy E ex E ey Fuzzy Logic Neural Network X Axis Y Axis.2 Fuzzy logic result Neural Network result Initial point Fig. 3. trajectories Final point Fuzzy Controller trajectory Neural Network trajectory ) 6 Conclusions According to the results presented, we can conclude that the Fuzzy Logic Control, with the membership functions optimized using a genetic algorithm, showed better performances when compared to the Neural Network Controller. Also, it must be pointed that despite the settling times achieved are very similar for both controllers, the trajectories obtained with the Fuzzy Logic Controller were more close to the reference signals at each sample time. Acknowledgments The author José B. Menezes Filho thanks CAPES Foundation, Ministry of Education of Brazil, the financial supporting to this research trough the Project number Fig. 4. Planar trajectory- Comparative trajectory The E ux and E uy indexes express the energy consumption plus time used to drive the axes motors. The E ex and E ey indexes are the sum of the quadratic errors plus time. Moreover, it was performed the determination of the settling times, T sx and T sy, respectively for the and trajectories obtained with the 2 controllers. The settling time was specified as the time instant where the error follows below 2% of the defined setpoint. E ux = u x (t) 2.t (2) E uy = u y (t) 2.t (3) E ex = e x (t) 2.t (4) s [] Zadeh, L.A., Fuzzy Sets, Information and Control, Vol. 8, 965, pp [2] Mamdani, E.H., Assilan, S., An experiment in linguistic synthesis with a fuzzy logic controller, International Journal of Man- Machine Studies, Vol. 7(), 975, pp. 3. [3] Driankov, D., Rainer, P., Advances in Fuzzy Control, Physica-Verlag, 23. [4] Reel, S., Goel, A.K., Artificial Neural Networks and Fuzzy Logic in Process Modeling and Control, Springer, 2. ISBN:
7 [5] Passino, K. M., Yurkovich, S., Fuzzy Control, Addison Wesley Longman, Menlo Park, CA, 998. [6] Kazuo Tanaka, K., Wang, H., (2). Fuzzy control systems design and analysis: a linear matrix inequality approach, John Wiley and Sons, 2. [7] Menezes Filho, J.B., Ferreira, N.M.F., Boaventura-Cunha, J., Use of a Genetic Algorithm to Tune a Mamdani Fuzzy Controller Applied to a Robot Manipulator, Lecture Notes in Electrical Engineering, Vol. 32, 24, pp [8] Koza, J.R., Genetic Programming, MIT Press, 992. [9] Menezes Filho, J., Silva, S., Araujo, C., Filho, A., Controlador Vetorial Neural para Mesa de Coordenadas XY. Revista Controle & Automação, Vol. 2(4), 2, pp [] Douratsos I., Gomm J.B., Neural Network Based Model Adaptive Control for process with time delay. International Journal of Information and Systems Sciences, vol. 3 (), 27, pp [] Yang, C., Li, Z., Jing Li, Smith, A., Adaptive Neural Network Control of Robot with Passive Last Joint, Lecture Notes in Computer Science, Vol. 758, 22, pp 3-22, pp [2] J. Lin, F.L. Lewis, Two-time scale fuzzy logic controller of flexible link robot arm, Fuzzy sets and systems, vol. 39(), 23, pp [3] M.A. Ahmad, M.Z.M. Tumari, A.N.K. Nasir, Composite Fuzzy Logic Control Approach to a Flexible Joint Manipulator, International Journal Advanced Robotic Systems, vol.(58), 23, pp.-9. ISBN:
Reference Variables Generation Using a Fuzzy Trajectory Controller for PM Tubular Linear Synchronous Motor Drive
Reference Variables Generation Using a Fuzzy Trajectory Controller for PM Tubular Linear Synchronous Motor Drive R. LUÍS J.C. QUADRADO ISEL, R. Conselheiro Emídio Navarro, 1950-072 LISBOA CAUTL, R. Rovisco
More informationIntelligent Control. 4^ Springer. A Hybrid Approach Based on Fuzzy Logic, Neural Networks and Genetic Algorithms. Nazmul Siddique.
Nazmul Siddique Intelligent Control A Hybrid Approach Based on Fuzzy Logic, Neural Networks and Genetic Algorithms Foreword by Bernard Widrow 4^ Springer Contents 1 Introduction 1 1.1 Intelligent Control
More informationTracking of Human Body using Multiple Predictors
Tracking of Human Body using Multiple Predictors Rui M Jesus 1, Arnaldo J Abrantes 1, and Jorge S Marques 2 1 Instituto Superior de Engenharia de Lisboa, Postfach 351-218317001, Rua Conselheiro Emído Navarro,
More informationCHAPTER 4 FREQUENCY STABILIZATION USING FUZZY LOGIC CONTROLLER
60 CHAPTER 4 FREQUENCY STABILIZATION USING FUZZY LOGIC CONTROLLER 4.1 INTRODUCTION Problems in the real world quite often turn out to be complex owing to an element of uncertainty either in the parameters
More informationAPPLICATIONS OF INTELLIGENT HYBRID SYSTEMS IN MATLAB
APPLICATIONS OF INTELLIGENT HYBRID SYSTEMS IN MATLAB Z. Dideková, S. Kajan Institute of Control and Industrial Informatics, Faculty of Electrical Engineering and Information Technology, Slovak University
More informationTakagi-Sugeno Fuzzy System Accuracy Improvement with A Two Stage Tuning
International Journal of Computing and Digital Systems ISSN (2210-142X) Int. J. Com. Dig. Sys. 4, No.4 (Oct-2015) Takagi-Sugeno Fuzzy System Accuracy Improvement with A Two Stage Tuning Hassan M. Elragal
More informationCHAPTER 5 FUZZY LOGIC CONTROL
64 CHAPTER 5 FUZZY LOGIC CONTROL 5.1 Introduction Fuzzy logic is a soft computing tool for embedding structured human knowledge into workable algorithms. The idea of fuzzy logic was introduced by Dr. Lofti
More informationThe Design of Pole Placement With Integral Controllers for Gryphon Robot Using Three Evolutionary Algorithms
The Design of Pole Placement With Integral Controllers for Gryphon Robot Using Three Evolutionary Algorithms Somayyeh Nalan-Ahmadabad and Sehraneh Ghaemi Abstract In this paper, pole placement with integral
More informationA Comparative Study of Prediction of Inverse Kinematics Solution of 2-DOF, 3-DOF and 5-DOF Redundant Manipulators by ANFIS
IJCS International Journal of Computer Science and etwork, Volume 3, Issue 5, October 2014 ISS (Online) : 2277-5420 www.ijcs.org 304 A Comparative Study of Prediction of Inverse Kinematics Solution of
More informationSCREW-BASED RELATIVE JACOBIAN FOR MANIPULATORS COOPERATING IN A TASK
ABCM Symposium Series in Mechatronics - Vol. 3 - pp.276-285 Copyright c 2008 by ABCM SCREW-BASED RELATIVE JACOBIAN FOR MANIPULATORS COOPERATING IN A TASK Luiz Ribeiro, ribeiro@ime.eb.br Raul Guenther,
More informationHALOGEN AUTOMATIC DAYLIGHT CONTROL SYSTEM BASED ON CMAC CONTROLLER WITH TRIANGULAR BASIS FUNCTIONS
HALOGEN AUTOMATIC DAYLIGHT CONTROL SYSTEM BASED ON CMAC CONTROLLER WITH TRIANGULAR BASIS FUNCTIONS Horatiu Stefan Grif, Mircea Dulău Petru Maior University of Târgu Mureş, Romania hgrif@emgineering.upm.ro,
More informationGenetic Tuning for Improving Wang and Mendel s Fuzzy Database
Proceedings of the 2009 IEEE International Conference on Systems, Man, and Cybernetics San Antonio, TX, USA - October 2009 Genetic Tuning for Improving Wang and Mendel s Fuzzy Database E. R. R. Kato, O.
More informationRenu Dhir C.S.E department NIT Jalandhar India
Volume 2, Issue 5, May 202 ISSN: 2277 28X International Journal of Advanced Research in Computer Science and Software Engineering Research Paper Available online at: Novel Edge Detection Using Adaptive
More informationBackground Fuzzy control enables noncontrol-specialists. A fuzzy controller works with verbal rules rather than mathematical relationships.
Introduction to Fuzzy Control Background Fuzzy control enables noncontrol-specialists to design control system. A fuzzy controller works with verbal rules rather than mathematical relationships. knowledge
More informationFUZZY INFERENCE SYSTEMS
CHAPTER-IV FUZZY INFERENCE SYSTEMS Fuzzy inference is the process of formulating the mapping from a given input to an output using fuzzy logic. The mapping then provides a basis from which decisions can
More informationA NOUVELLE MOTION STATE-FEEDBACK CONTROL SCHEME FOR RIGID ROBOTIC MANIPULATORS
A NOUVELLE MOTION STATE-FEEDBACK CONTROL SCHEME FOR RIGID ROBOTIC MANIPULATORS Ahmad Manasra, 135037@ppu.edu.ps Department of Mechanical Engineering, Palestine Polytechnic University, Hebron, Palestine
More informationSolving A Nonlinear Side Constrained Transportation Problem. by Using Spanning Tree-based Genetic Algorithm. with Fuzzy Logic Controller
Solving A Nonlinear Side Constrained Transportation Problem by Using Spanning Tree-based Genetic Algorithm with Fuzzy Logic Controller Yasuhiro Tsujimura *, Mitsuo Gen ** and Admi Syarif **,*** * Department
More informationTuning Fuzzy Control Rules via Genetic Algorithms: An Experimental Evaluation
Research Journal of Recent Sciences ISSN 77-50 Res.J.Recent Sci. Tuning Fuzzy Control Rules via Genetic Algorithms: An Experimental Evaluation Pitalúa Díaz N. 1, Lagunas Jiménez R. and González Angelesa
More informationRobustness of Selective Desensitization Perceptron Against Irrelevant and Partially Relevant Features in Pattern Classification
Robustness of Selective Desensitization Perceptron Against Irrelevant and Partially Relevant Features in Pattern Classification Tomohiro Tanno, Kazumasa Horie, Jun Izawa, and Masahiko Morita University
More informationDefect Depth Estimation Using Neuro-Fuzzy System in TNDE by Akbar Darabi and Xavier Maldague
Defect Depth Estimation Using Neuro-Fuzzy System in TNDE by Akbar Darabi and Xavier Maldague Electrical Engineering Dept., Université Laval, Quebec City (Quebec) Canada G1K 7P4, E-mail: darab@gel.ulaval.ca
More informationA New Fuzzy Neural System with Applications
A New Fuzzy Neural System with Applications Yuanyuan Chai 1, Jun Chen 1 and Wei Luo 1 1-China Defense Science and Technology Information Center -Network Center Fucheng Road 26#, Haidian district, Beijing
More informationThe analysis of inverted pendulum control and its other applications
Journal of Applied Mathematics & Bioinformatics, vol.3, no.3, 2013, 113-122 ISSN: 1792-6602 (print), 1792-6939 (online) Scienpress Ltd, 2013 The analysis of inverted pendulum control and its other applications
More informationImproving Trajectory Tracking Performance of Robotic Manipulator Using Neural Online Torque Compensator
JOURNAL OF ENGINEERING RESEARCH AND TECHNOLOGY, VOLUME 1, ISSUE 2, JUNE 2014 Improving Trajectory Tracking Performance of Robotic Manipulator Using Neural Online Torque Compensator Mahmoud M. Al Ashi 1,
More informationOn Evolving Fuzzy Modeling for Visual Control of Robotic Manipulators
On Evolving Fuzzy Modeling for Visual Control of Robotic Manipulators P.J.S. Gonçalves 1,2, P.M.B. Torres 2, J.R. Caldas Pinto 1, J.M.C. Sousa 1 1. Instituto Politécnico de Castelo Branco, Escola Superior
More informationA Matlab Tool for Analyzing and Improving Fault Tolerance of Artificial Neural Networks
A Matlab Tool for Analyzing and Improving Fault Tolerance of Artificial Neural Networks Rui Borralho*. Pedro Fontes*. Ana Antunes*. Fernando Morgado Dias**. *Escola Superior de Tecnologia de Setúbal do
More informationLecture notes. Com Page 1
Lecture notes Com Page 1 Contents Lectures 1. Introduction to Computational Intelligence 2. Traditional computation 2.1. Sorting algorithms 2.2. Graph search algorithms 3. Supervised neural computation
More informationImproving interpretability in approximative fuzzy models via multi-objective evolutionary algorithms.
Improving interpretability in approximative fuzzy models via multi-objective evolutionary algorithms. Gómez-Skarmeta, A.F. University of Murcia skarmeta@dif.um.es Jiménez, F. University of Murcia fernan@dif.um.es
More informationIdentification of Vehicle Class and Speed for Mixed Sensor Technology using Fuzzy- Neural & Genetic Algorithm : A Design Approach
Identification of Vehicle Class and Speed for Mixed Sensor Technology using Fuzzy- Neural & Genetic Algorithm : A Design Approach Prashant Sharma, Research Scholar, GHRCE, Nagpur, India, Dr. Preeti Bajaj,
More informationClassification with Diffuse or Incomplete Information
Classification with Diffuse or Incomplete Information AMAURY CABALLERO, KANG YEN Florida International University Abstract. In many different fields like finance, business, pattern recognition, communication
More informationJo-Car2 Autonomous Mode. Path Planning (Cost Matrix Algorithm)
Chapter 8.2 Jo-Car2 Autonomous Mode Path Planning (Cost Matrix Algorithm) Introduction: In order to achieve its mission and reach the GPS goal safely; without crashing into obstacles or leaving the lane,
More informationCHAPTER 8 ANFIS MODELING OF FLANK WEAR 8.1 AISI M2 HSS TOOLS
CHAPTER 8 ANFIS MODELING OF FLANK WEAR 8.1 AISI M2 HSS TOOLS Control surface as shown in Figs. 8.1 8.3 gives the interdependency of input, and output parameters guided by the various rules in the given
More informationDesign of Different Fuzzy Controllers for Delayed Systems
Design of Different Fuzzy Controllers for Delayed Systems Kapil Dev Sharma 1, Shailika Sharma 2, M.Ayyub 3 1, 3 Electrical Engg. Dept., Aligarh Muslim University, Aligarh, 2 Electronics& Com. Engg. Dept.,
More informationEuropean Journal of Science and Engineering Vol. 1, Issue 1, 2013 ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM IDENTIFICATION OF AN INDUCTION MOTOR
ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM IDENTIFICATION OF AN INDUCTION MOTOR Ahmed A. M. Emam College of Engineering Karrary University SUDAN ahmedimam1965@yahoo.co.in Eisa Bashier M. Tayeb College of Engineering
More information2. Neural network basics
2. Neural network basics Next commonalities among different neural networks are discussed in order to get started and show which structural parts or concepts appear in almost all networks. It is presented
More informationManipulability Analysis of Two-Arm Robotic Systems
Manipulability Analysis of Two-Arm Robotic Systems N. M. Fonseca Ferreira Institute of Engineering of Coimbra Dept. of Electrical Engineering Quinta da Nora 3031-601 Coimbra Codex, Portugal tel: 351 239790200,
More informationNeuro-Fuzzy Inverse Forward Models
CS9 Autumn Neuro-Fuzzy Inverse Forward Models Brian Highfill Stanford University Department of Computer Science Abstract- Internal cognitive models are useful methods for the implementation of motor control
More informationOptimization of Robotic Arm Trajectory Using Genetic Algorithm
Preprints of the 19th World Congress The International Federation of Automatic Control Optimization of Robotic Arm Trajectory Using Genetic Algorithm Stanislav Števo. Ivan Sekaj. Martin Dekan. Institute
More informationDETERMINING PARETO OPTIMAL CONTROLLER PARAMETER SETS OF AIRCRAFT CONTROL SYSTEMS USING GENETIC ALGORITHM
DETERMINING PARETO OPTIMAL CONTROLLER PARAMETER SETS OF AIRCRAFT CONTROL SYSTEMS USING GENETIC ALGORITHM Can ÖZDEMİR and Ayşe KAHVECİOĞLU School of Civil Aviation Anadolu University 2647 Eskişehir TURKEY
More informationFUZZY LOGIC TECHNIQUES. on random processes. In such situations, fuzzy logic exhibits immense potential for
FUZZY LOGIC TECHNIQUES 4.1: BASIC CONCEPT Problems in the real world are quite often very complex due to the element of uncertainty. Although probability theory has been an age old and effective tool to
More informationFuzzy Inspired Hybrid Genetic Approach to Optimize Travelling Salesman Problem
Fuzzy Inspired Hybrid Genetic Approach to Optimize Travelling Salesman Problem Bindu Student, JMIT Radaur binduaahuja@gmail.com Mrs. Pinki Tanwar Asstt. Prof, CSE, JMIT Radaur pinki.tanwar@gmail.com Abstract
More informationCHAPTER 4 FUZZY LOGIC, K-MEANS, FUZZY C-MEANS AND BAYESIAN METHODS
CHAPTER 4 FUZZY LOGIC, K-MEANS, FUZZY C-MEANS AND BAYESIAN METHODS 4.1. INTRODUCTION This chapter includes implementation and testing of the student s academic performance evaluation to achieve the objective(s)
More information12 IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 6, NO. 1, FEBRUARY An On-Line Self-Constructing Neural Fuzzy Inference Network and Its Applications
12 IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 6, NO. 1, FEBRUARY 1998 An On-Line Self-Constructing Neural Fuzzy Inference Network Its Applications Chia-Feng Juang Chin-Teng Lin Abstract A self-constructing
More informationEMBED SYSTEM FOR ROBOTIC ARM WITH 3 DEGREE OF FREEDOM CONTROLLER USING COMPUTATIONAL VISION ON REAL-TIME
EMBED SYSTEM FOR ROBOTIC ARM WITH 3 DEGREE OF FREEDOM CONTROLLER USING COMPUTATIONAL VISION ON REAL-TIME Luiz Cortinhas 1, Patrick Monteiro¹, Amir Zahlan¹, Gabriel Vianna¹ and Marcio Moscoso² 1 Instituto
More informationNeuro Fuzzy and Self Tunging Fuzzy Controller to Improve Pitch and Yaw Control Systems Resposes of Twin Rotor MIMO System
Neuro Fuzzy and Self Tunging Fuzzy Controller to Improve Pitch and Yaw Control Systems Resposes of Twin Rotor MIMO System Thair Sh. Mahmoud, Tang Sai Hong, and Mohammed H. Marhaban Abstract In this paper,
More information[Time : 3 Hours] [Max. Marks : 100] SECTION-I. What are their effects? [8]
UNIVERSITY OF PUNE [4364]-542 B. E. (Electronics) Examination - 2013 VLSI Design (200 Pattern) Total No. of Questions : 12 [Total No. of Printed Pages :3] [Time : 3 Hours] [Max. Marks : 100] Q1. Q2. Instructions
More informationA Predictive Controller for Object Tracking of a Mobile Robot
A Predictive Controller for Object Tracking of a Mobile Robot Xiaowei Zhou, Plamen Angelov and Chengwei Wang Intelligent Systems Research Laboratory Lancaster University, Lancaster, LA1 4WA, U. K. p.angelov@lancs.ac.uk
More informationReview on Methods of Selecting Number of Hidden Nodes in Artificial Neural Network
Available Online at www.ijcsmc.com International Journal of Computer Science and Mobile Computing A Monthly Journal of Computer Science and Information Technology IJCSMC, Vol. 3, Issue. 11, November 2014,
More informationModeling and Control of Non Linear Systems
Modeling and Control of Non Linear Systems K.S.S.Anjana and M.Sridhar, GIET, Rajahmudry, A.P. Abstract-- This paper a neuro-fuzzy approach is used to model any non-linear data. Fuzzy curve approach is
More informationUsing Artificial Neural Networks for Prediction Of Dynamic Human Motion
ABSTRACT Using Artificial Neural Networks for Prediction Of Dynamic Human Motion Researchers in robotics and other human-related fields have been studying human motion behaviors to understand and mimic
More informationCHAPTER 3 ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM
33 CHAPTER 3 ADAPTIVE NEURO-FUZZY INFERENCE SYSTEM The objective of an ANFIS (Jang 1993) is to integrate the best features of Fuzzy Systems and Neural Networks. ANFIS is one of the best tradeoffs between
More informationA New Neuro-Fuzzy Adaptive Genetic Algorithm
ec. 2003 Journal of Electronic Science and Technology of China Vol.1 No.1 A New Neuro-Fuzzy Adaptive Genetic Algorithm ZHU Lili ZHANG Huanchun JING Yazhi (Faculty 302, Nanjing University of Aeronautics
More informationLEARNING NAVIGATION MAPS BY LOOKING AT PEOPLE
LEARNING NAVIGATION MAPS BY LOOKING AT PEOPLE Roger Freitas,1 José Santos-Victor Mário Sarcinelli-Filho Teodiano Bastos-Filho Departamento de Engenharia Elétrica, Universidade Federal do Espírito Santo,
More informationReduced Image Noise on Shape Recognition Using Singular Value Decomposition for Pick and Place Robotic Systems
Reduced Image Noise on Shape Recognition Using Singular Value Decomposition for Pick and Place Robotic Systems Angelo A. Beltran Jr. 1, Christian Deus T. Cayao 2, Jay-K V. Delicana 3, Benjamin B. Agraan
More informationApplying Neural Network Architecture for Inverse Kinematics Problem in Robotics
J. Software Engineering & Applications, 2010, 3: 230-239 doi:10.4236/jsea.2010.33028 Published Online March 2010 (http://www.scirp.org/journal/jsea) Applying Neural Network Architecture for Inverse Kinematics
More informationAircraft Landing Control Using Fuzzy Logic and Neural Networks
Aircraft Landing Control Using Fuzzy Logic and Neural Networks Elvira Lakovic Intelligent Embedded Systems elc10001@student.mdh.se Damir Lotinac Intelligent Embedded Systems dlc10001@student.mdh.se ABSTRACT
More informationTransactions on Information and Communications Technologies vol 16, 1996 WIT Press, ISSN
Comparative study of fuzzy logic and neural network methods in modeling of simulated steady-state data M. Järvensivu and V. Kanninen Laboratory of Process Control, Department of Chemical Engineering, Helsinki
More informationTOOL WEAR CONDITION MONITORING IN TAPPING PROCESS BY FUZZY LOGIC
TOOL WEAR CONDITION MONITORING IN TAPPING PROCESS BY FUZZY LOGIC Ratchapon Masakasin, Department of Industrial Engineering, Faculty of Engineering, Kasetsart University, Bangkok 10900 E-mail: masakasin.r@gmail.com
More informationRULE BASED SIGNATURE VERIFICATION AND FORGERY DETECTION
RULE BASED SIGNATURE VERIFICATION AND FORGERY DETECTION M. Hanmandlu Multimedia University Jalan Multimedia 63100, Cyberjaya Selangor, Malaysia E-mail:madasu.hanmandlu@mmu.edu.my M. Vamsi Krishna Dept.
More informationImproving the Wang and Mendel s Fuzzy Rule Learning Method by Inducing Cooperation Among Rules 1
Improving the Wang and Mendel s Fuzzy Rule Learning Method by Inducing Cooperation Among Rules 1 J. Casillas DECSAI, University of Granada 18071 Granada, Spain casillas@decsai.ugr.es O. Cordón DECSAI,
More informationAnalysis of Control of Inverted Pendulum using Adaptive Neuro Fuzzy system
Analysis of Control of Inverted Pendulum using Adaptive Neuro Fuzzy system D. K. Somwanshi, Mohit Srivastava, R.Panchariya Abstract: Here modeling and simulation study of basically two control strategies
More informationHuman Identification at a Distance Using Body Shape Information
IOP Conference Series: Materials Science and Engineering OPEN ACCESS Human Identification at a Distance Using Body Shape Information To cite this article: N K A M Rashid et al 2013 IOP Conf Ser: Mater
More informationTime Complexity Analysis of the Genetic Algorithm Clustering Method
Time Complexity Analysis of the Genetic Algorithm Clustering Method Z. M. NOPIAH, M. I. KHAIRIR, S. ABDULLAH, M. N. BAHARIN, and A. ARIFIN Department of Mechanical and Materials Engineering Universiti
More informationInverse Kinematics Solution for Trajectory Tracking using Artificial Neural Networks for SCORBOT ER-4u
Inverse Kinematics Solution for Trajectory Tracking using Artificial Neural Networks for SCORBOT ER-4u Rahul R Kumar 1, Praneel Chand 2 School of Engineering and Physics The University of the South Pacific
More informationEfficient CPU Scheduling Algorithm Using Fuzzy Logic
2012 International Conference on Computer Technology and Science (ICCTS 2012) IPCSIT vol. 47 (2012) (2012) IACSIT Press, Singapore DOI: 10.7763/IPCSIT.2012.V47.3 Efficient CPU Scheduling Algorithm Using
More informationSimulation and Modeling of 6-DOF Robot Manipulator Using Matlab Software
Simulation and Modeling of 6-DOF Robot Manipulator Using Matlab Software 1 Thavamani.P, 2 Ramesh.K, 3 Sundari.B 1 M.E Scholar, Applied Electronics, JCET, Dharmapuri, Tamilnadu, India 2 Associate Professor,
More informationFuzzy if-then rules fuzzy database modeling
Fuzzy if-then rules Associates a condition described using linguistic variables and fuzzy sets to a conclusion A scheme for capturing knowledge that involves imprecision 23.11.2010 1 fuzzy database modeling
More informationGesture Identification Based Remote Controlled Robot
Gesture Identification Based Remote Controlled Robot Manjusha Dhabale 1 and Abhijit Kamune 2 Assistant Professor, Department of Computer Science and Engineering, Ramdeobaba College of Engineering, Nagpur,
More informationAutomatic Generation of Fuzzy Classification Rules from Data
Automatic Generation of Fuzzy Classification Rules from Data Mohammed Al-Shammaa 1 and Maysam F. Abbod Abstract In this paper, we propose a method for automatic generation of fuzzy rules for data classification.
More informationImage Compression: An Artificial Neural Network Approach
Image Compression: An Artificial Neural Network Approach Anjana B 1, Mrs Shreeja R 2 1 Department of Computer Science and Engineering, Calicut University, Kuttippuram 2 Department of Computer Science and
More informationGenetic Algorithm for Finding Shortest Path in a Network
Intern. J. Fuzzy Mathematical Archive Vol. 2, 2013, 43-48 ISSN: 2320 3242 (P), 2320 3250 (online) Published on 26 August 2013 www.researchmathsci.org International Journal of Genetic Algorithm for Finding
More informationSEMI-ACTIVE CONTROL OF BUILDING STRUCTURES USING A NEURO-FUZZY CONTROLLER WITH ACCELERATION FEEDBACK
Proceedings of the 6th International Conference on Mechanics and Materials in Design, Editors: J.F. Silva Gomes & S.A. Meguid, P.Delgada/Azores, 26-30 July 2015 PAPER REF: 5778 SEMI-ACTIVE CONTROL OF BUILDING
More informationFabric Defect Detection Based on Computer Vision
Fabric Defect Detection Based on Computer Vision Jing Sun and Zhiyu Zhou College of Information and Electronics, Zhejiang Sci-Tech University, Hangzhou, China {jings531,zhouzhiyu1993}@163.com Abstract.
More informationCAMERA CALIBRATION FOR VISUAL ODOMETRY SYSTEM
SCIENTIFIC RESEARCH AND EDUCATION IN THE AIR FORCE-AFASES 2016 CAMERA CALIBRATION FOR VISUAL ODOMETRY SYSTEM Titus CIOCOIU, Florin MOLDOVEANU, Caius SULIMAN Transilvania University, Braşov, Romania (ciocoiutitus@yahoo.com,
More information3/12/2009 Advanced Topics in Robotics and Mechanism Synthesis Term Projects
3/12/2009 Advanced Topics in Robotics and Mechanism Synthesis Term Projects Due date: 4/23/09 On 4/23/09 and 4/30/09 you will present a 20-25 minute presentation about your work. During this presentation
More informationCONTROLO th Portuguese Conference on Automatic Control
CONTROLO 2008 8 th Portuguese Conference on Automatic Control University of Trás-os-Montes and Alto Douro, Vila Real, Portugal July 21-23, 2008 414 BALL AND BEAM VIRTUAL LABORATORY: A TEACHING AID IN AUTOMATIC
More informationFUZZY INFERENCE SYSTEM AND PREDICTION
JOURNAL OF TRANSLOGISTICS 2015 193 Libor ŽÁK David VALIŠ FUZZY INFERENCE SYSTEM AND PREDICTION Keywords: fuzzy sets, fuzzy logic, fuzzy inference system, prediction implementation, employees ABSTRACT This
More informationA Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation
A Fast Personal Palm print Authentication based on 3D-Multi Wavelet Transformation * A. H. M. Al-Helali, * W. A. Mahmmoud, and * H. A. Ali * Al- Isra Private University Email: adnan_hadi@yahoo.com Abstract:
More informationApplication of Or-based Rule Antecedent Fuzzy Neural Networks to Iris Data Classification Problem
Vol.1 (DTA 016, pp.17-1 http://dx.doi.org/10.157/astl.016.1.03 Application of Or-based Rule Antecedent Fuzzy eural etworks to Iris Data Classification roblem Chang-Wook Han Department of Electrical Engineering,
More informationThree-Dimensional Off-Line Path Planning for Unmanned Aerial Vehicle Using Modified Particle Swarm Optimization
Three-Dimensional Off-Line Path Planning for Unmanned Aerial Vehicle Using Modified Particle Swarm Optimization Lana Dalawr Jalal Abstract This paper addresses the problem of offline path planning for
More informationA SELF-ORGANISING FUZZY LOGIC CONTROLLER
Nigerian Journal of Technology: Vol. 20, No. 1 March, 2001. 1 A SELF-ORGANISING FUZZY LOGIC CONTROLLER Paul N. Ekemezie Department of Electronic Engineering University of Nigeria, Nsukka. Abstract Charles
More informationSoft Computing Paradigms for Learning Fuzzy Controllers with Applications to Ro
Soft Computing Paradigms for Learning Fuzzy Controllers with Applications to Ro E. Tunstel! M.-R. Akbarzadeh-T, K. Kumbla and M. Jamshidi NASA Center for Autonomous Control Engineering Department of Electrical
More informationDesigning the Controller Based on the Approach of Hedge Algebras and Optimization through Genetic Algorithm
Designing the Controller Based on the Approach of Hedge Algebras and Optimization through Genetic Algorithm Duy Nguyen Tien 1, Trung Ngo Kien 2 1 Falcuty of Electronics, Thai Nguyen University of Technology,
More informationFigure 2-1: Membership Functions for the Set of All Numbers (N = Negative, P = Positive, L = Large, M = Medium, S = Small)
Fuzzy Sets and Pattern Recognition Copyright 1998 R. Benjamin Knapp Permission to make digital or hard copies of part or all of this work for personal or classroom use is granted without fee provided that
More informationSimultaneous Perturbation Stochastic Approximation Algorithm Combined with Neural Network and Fuzzy Simulation
.--- Simultaneous Perturbation Stochastic Approximation Algorithm Combined with Neural Networ and Fuzzy Simulation Abstract - - - - Keywords: Many optimization problems contain fuzzy information. Possibility
More informationFast Associative Memory
Fast Associative Memory Ricardo Miguel Matos Vieira Instituto Superior Técnico ricardo.vieira@tagus.ist.utl.pt ABSTRACT The associative memory concept presents important advantages over the more common
More informationTexture Image Segmentation using FCM
Proceedings of 2012 4th International Conference on Machine Learning and Computing IPCSIT vol. 25 (2012) (2012) IACSIT Press, Singapore Texture Image Segmentation using FCM Kanchan S. Deshmukh + M.G.M
More informationOptimizationOf Straight Movement 6 Dof Robot Arm With Genetic Algorithm
OptimizationOf Straight Movement 6 Dof Robot Arm With Genetic Algorithm R. Suryoto Edy Raharjo Oyas Wahyunggoro Priyatmadi Abstract This paper proposes a genetic algorithm (GA) to optimize the straight
More informationCONCEPT FORMATION AND DECISION TREE INDUCTION USING THE GENETIC PROGRAMMING PARADIGM
1 CONCEPT FORMATION AND DECISION TREE INDUCTION USING THE GENETIC PROGRAMMING PARADIGM John R. Koza Computer Science Department Stanford University Stanford, California 94305 USA E-MAIL: Koza@Sunburn.Stanford.Edu
More informationPLC IMPLEMENTATION OF A FUZZY SYSTEM
The 6 th edition of the Interdisciplinarity in Engineering International Conference Petru Maior University of Tîrgu Mureş, Romania, 202 PLC IMPLEMENTATION OF A FUZZY SYSTEM Adrian-Vasile DUKA # # Department
More informationA penalty based filters method in direct search optimization
A penalty based filters method in direct search optimization Aldina Correia CIICESI / ESTG P.PORTO Felgueiras, Portugal aic@estg.ipp.pt João Matias CM-UTAD UTAD Vila Real, Portugal j matias@utad.pt Pedro
More informationEVALUATION OF THE PERFORMANCE OF VARIOUS FUZZY PID CONTROLLER STRUCTURES ON BENCHMARK SYSTEMS
EVALUATION OF THE PERFORMANCE OF VARIOUS FUZZY CONTROLLER STRUCTURES ON BENCHMARK SYSTEMS Birkan Akbıyık İbrahim Eksin Müjde Güzelkaya Engin Yeşil e-mail: birkan@lycos.com e-mail:eksin@elk.itu.edu.tr e-mail:
More informationDESIGN OF AN ELEVATOR GROUP CONTROLLER USING TYPE-2 FUZZY LOGIC
bidang REKAYASA DESIGN OF AN ELEVATOR GROUP CONTROLLER USING TYPE-2 FUZZY LOGIC MUHAMMAD ARIA Department of Electrical Engineering Engineering and Computer Science Faculty Universitas Komputer Indonesia
More informationFuzzy Logic Control for Pneumatic Excavator Model
International Journal of Applied Engineering Research ISSN 0973-4562 Volume 10, Number 9 (2015) pp. 21647-21657 Research India Publications http://www.ripublication.com Fuzzy Logic Control for Pneumatic
More information^ Springer. Computational Intelligence. A Methodological Introduction. Rudolf Kruse Christian Borgelt. Matthias Steinbrecher Pascal Held
Rudolf Kruse Christian Borgelt Frank Klawonn Christian Moewes Matthias Steinbrecher Pascal Held Computational Intelligence A Methodological Introduction ^ Springer Contents 1 Introduction 1 1.1 Intelligent
More informationGENERATING FUZZY RULES FROM EXAMPLES USING GENETIC. Francisco HERRERA, Manuel LOZANO, Jose Luis VERDEGAY
GENERATING FUZZY RULES FROM EXAMPLES USING GENETIC ALGORITHMS Francisco HERRERA, Manuel LOZANO, Jose Luis VERDEGAY Dept. of Computer Science and Articial Intelligence University of Granada, 18071 - Granada,
More informationSubpixel Corner Detection Using Spatial Moment 1)
Vol.31, No.5 ACTA AUTOMATICA SINICA September, 25 Subpixel Corner Detection Using Spatial Moment 1) WANG She-Yang SONG Shen-Min QIANG Wen-Yi CHEN Xing-Lin (Department of Control Engineering, Harbin Institute
More informationCOMPUTER-BASED WORKPIECE DETECTION ON CNC MILLING MACHINE TOOLS USING OPTICAL CAMERA AND NEURAL NETWORKS
Advances in Production Engineering & Management 5 (2010) 1, 59-68 ISSN 1854-6250 Scientific paper COMPUTER-BASED WORKPIECE DETECTION ON CNC MILLING MACHINE TOOLS USING OPTICAL CAMERA AND NEURAL NETWORKS
More informationUnsupervised Feature Selection for Sparse Data
Unsupervised Feature Selection for Sparse Data Artur Ferreira 1,3 Mário Figueiredo 2,3 1- Instituto Superior de Engenharia de Lisboa, Lisboa, PORTUGAL 2- Instituto Superior Técnico, Lisboa, PORTUGAL 3-
More informationSelf generated fuzzy membership function using ANN clustering technique
Self generated fuzzy membership function using ANN clustering technique Shruti S. Jamsandekar Department of Computer Studies, SIBER, Kolhapur. (MS), India-416004 Ravindra R. Mudholkar Department of Electronics
More informationA TSK-Type Recurrent Fuzzy Network for Dynamic Systems Processing by Neural Network and Genetic Algorithms
IEEE TRANSACTIONS ON FUZZY SYSTEMS, VOL. 10, NO. 2, APRIL 2002 155 A TSK-Type Recurrent Fuzzy Network for Dynamic Systems Processing by Neural Network and Genetic Algorithms Chia-Feng Juang, Member, IEEE
More information