Finding Fuzzy Rules for IRIS by Neural Network with Weighted Fuzzy Membership Function

Joon Shik Lim 한국지능시스템학회 2004 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.4 No.2

Fuzzy neural networks have been successfully applied to analyze/generate predictive rules for medical or diagnostic data. However, most approaches proposed so far have not considered the weights for the membership functions much. This paper presents a neural network with weighted fuzzy membership functions. In our approach, the membership functions can capture the concentrated and essential information that affects the classification of the input patterns. To verify the performance of the proposed model, well-known Iris data set is performed. According to the results, the weighted membership functions enhance the prediction accuracy. The architecture of the proposed neural network with weighted fuzzy membership functions and the details of experimental results for the data set is discussed in this paper.

Note on the expected value of a function of a fuzzy variable

홍덕헌 한국전산응용수학회 2009 Journal of applied mathematics & informatics Vol.27 No.3

Recently, Xue et al. [Computers and Mathematics with Applications 55 (2008) 1215-1224] proposed a formula for the expected value of a function of a fuzzy variable based on the assumption that the fuzzy variable has a continuous membership function. In conclusion, they remained the case where the membership function of the fuzzy variable is discontinuous for the future research, and then expected to get similar results. Thus this note is to propose a new formula for the expected value of a function of a general fuzzy variable which is not restricted on having a continuous membership function. Furthermore, we give an example which cannot be applied to the formula that Xue et al. proposed. We also use the same example given by Xue et al. to show how to apply the new formula. Recently, Xue et al. [Computers and Mathematics with Applications 55 (2008) 1215-1224] proposed a formula for the expected value of a function of a fuzzy variable based on the assumption that the fuzzy variable has a continuous membership function. In conclusion, they remained the case where the membership function of the fuzzy variable is discontinuous for the future research, and then expected to get similar results. Thus this note is to propose a new formula for the expected value of a function of a general fuzzy variable which is not restricted on having a continuous membership function. Furthermore, we give an example which cannot be applied to the formula that Xue et al. proposed. We also use the same example given by Xue et al. to show how to apply the new formula.

An Optimized Multiple Fuzzy Membership Functions based Image Contrast Enhancement Technique

( Pushpa Mamoria ),( Deepa Raj ) 한국인터넷정보학회 2018 KSII Transactions on Internet and Information Syst Vol.12 No.3

Image enhancement is an emerging method for analyzing the images clearer for interpretation and analysis in the spatial domain. The goal of image enhancement is to serve an input image so that the resultant image is more suited to the particular application. In this paper, a novel method is proposed based on Mamdani fuzzy inference system (FIS) using multiple fuzzy membership functions. It is observed that the shape of membership function while converting the input image into the fuzzy domain is the essential important selection. Then, a set of fuzzy If-Then rule base in fuzzy domain gives the best result in image contrast enhancement. Based on a different combination of membership function shapes, a best predictive solution can be determined which can be suitable for different types of the input image as per application requirements. Our result analysis shows that the quality attributes such as PSNR, Index of Fuzziness (IOF) parameters give different performances with a selection of numbers and different sized membership function in the fuzzy domain. To get more insight, an optimization algorithm is proposed to identify the best combination of the fuzzy membership function for best image contrast enhancement.

Fuzzy PID Control by Grouping of Membership Functions of Fuzzy Antecedent Variables with Neutrosophic Set Approach and 3-D Position Tracking Control of a Robot Manipulator

Mehmet Serhat Can,Omerul Faruk Ozguven 대한전기학회 2018 Journal of Electrical Engineering & Technology Vol.13 No.2

This paper aims to design of the neutrosophic fuzzy-PID controller and it has been compared with the conventional fuzzy-PID controller for position tracking control in terms of robustness. In the neutrosophic fuzzy-PID controller, error (e) and change of error (ce) were assessed separately on two fuzzy inference systems (FISs). In this study, the designed method is different from the conventional fuzzy logic controller design, membership degrees of antecedent variables were determined by using the T(true), I(indeterminacy), and F(false) membership functions. These membership functions are grouped on the universe of discourse with the neutrosophic set approach. These methods were tested on three-dimensional (3-D) position-tracking control application of a spherical robot manipulator in the MATLAB Simulink. In all tests, reference trajectory was defined for movements of all axes of the robot manipulator. According to the results of the study, when the moment of inertia of the rotor is changed, less overshoot ratio and less oscillation are obtained in the neutrosophic fuzzy-PID controller. Thus, our suggested method is seen to be more robust than the fuzzy-PID controllers.

Membership-Function-Dependent Stability Conditions Using Fuzzy Lyapunov Functions

Kyung Soo Kim,Ho Sub Lee,PooGyeon Park 제어로봇시스템학회 2022 제어로봇시스템학회 국제학술대회 논문집 Vol.2022 No.11

This paper proposes the membership-function-dependent stability conditions for T-S fuzzy systems using fuzzy Lyapunov functions. The properties of both membership functions (MFs) and the derivative of MFs are utilized to obtain the stability condition of the fuzzy system. The fuzzy Lyapunov functions are employed for stability analysis to exploit the information of the derivative of MFs. For achieving the less conservative stability result, the convex polytopes capturing the distributions of MFs and the derivative of MFs provide the stability condition in the shape of linear matrix inequalities. Under the same fuzzy Lyapunov function, two different way to derive the stabilization condition is investigated. Simulation shows the effectiveness of the proposed approach compared with the previous method, which is a quadratic Lyapunov function.

Fuzzy Controller Design for Discrete-time T-S Fuzzy Systems with Partially Unknown Membership Functions

Guo-Yi Liu,Juan Zhou 제어·로봇·시스템학회 2022 International Journal of Control, Automation, and Vol.20 No.12

This paper is concerned with the controller design problem for discrete-time T-S fuzzy systems with partially unknown membership functions. If the membership functions are partially unknown, then the existing stabilization conditions which are based on the parallel distributed compensator (PDC) strategy cannot be applied. To tackle this problem, a new type of fuzzy controller is proposed to close the feedback loop. Based on this new type fuzzy controller, some sufficient stabilization conditions, including membership-function-dependent and independent conditions, are given in the form of LMIs. Finally, two examples are given to illustrate the the effectiveness of the proposed fuzzy controller design approaches.

Finding Fuzzy Rules for IRIS by Neural Network with Weighted Fuzzy Membership Function

Lim, Joon Shik Korean Institute of Intelligent Systems 2004 INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGE Vol.4 No.2

Fuzzy neural networks have been successfully applied to analyze/generate predictive rules for medical or diagnostic data. However, most approaches proposed so far have not considered the weights for the membership functions much. This paper presents a neural network with weighted fuzzy membership functions. In our approach, the membership functions can capture the concentrated and essential information that affects the classification of the input patterns. To verify the performance of the proposed model, well-known Iris data set is performed. According to the results, the weighted membership functions enhance the prediction accuracy. The architecture of the proposed neural network with weighted fuzzy membership functions and the details of experimental results for the data set is discussed in this paper.

A Fuzzy Traffic Controller Considering the spillback on the Multiple Crossroads

Kim, Young-Sik Korean Institute of Intelligent Systems 2003 한국지능시스템학회논문지 Vol.13 No.6

In this paper, we propose a fuzzy traffic controller of Sugeno`s fuzzy model so as to model the nonlinear characteristics of controlling the traffic light. It use a degree of the traffic congestion of the preceding roads as an input so that it can cope with traffic congestion appropriately, which causes the loss of fuel and our discomfort. First, in order to construct fuzzy traffic controller of Sugeno`s fuzzy model, we model the control process of the traffic light by using Mamdani`s fuzzy model, which has the uniform membership functions of the same size and shape. Second, we make Mamdani`s fuzzy model with the non-uniform membership functions so that it can exactly reflect the knowledge of experts and operators. Last, we construct the fuzzy traffic controller of Sugeno`s fuzzy model by learning from the input/output data, which is retrieved from Mamdani`s fuzzy model with the non-uniform membership functions. We compared and analyzed the fixed traffic light controller, the fuzzy traffic controller of Mamdani`s fuzzy model and the fuzzy traffic controller of Sugeno`s fuzzy model by using the delay time and the proportion of the entered vehicles to the occurred vehicles. As a result of comparison, the fuzzy traffic controller of Sugeno`s fuzzy model showed the best performance.

Fuzzy PID Control by Grouping of Membership Functions of Fuzzy Antecedent Variables with Neutrosophic Set Approach and 3-D Position Tracking Control of a Robot Manipulator

Can, Mehmet Serhat,Ozguven, Omerul Faruk The Korean Institute of Electrical Engineers 2018 Journal of Electrical Engineering & Technology Vol.13 No.2

This paper aims to design of the neutrosophic fuzzy-PID controller and it has been compared with the conventional fuzzy-PID controller for position tracking control in terms of robustness. In the neutrosophic fuzzy-PID controller, error (e) and change of error (ce) were assessed separately on two fuzzy inference systems (FISs). In this study, the designed method is different from the conventional fuzzy logic controller design, membership degrees of antecedent variables were determined by using the T(true), I(indeterminacy), and F(false) membership functions. These membership functions are grouped on the universe of discourse with the neutrosophic set approach. These methods were tested on three-dimensional (3-D) position-tracking control application of a spherical robot manipulator in the MATLAB Simulink. In all tests, reference trajectory was defined for movements of all axes of the robot manipulator. According to the results of the study, when the moment of inertia of the rotor is changed, less overshoot ratio and less oscillation are obtained in the neutrosophic fuzzy-PID controller. Thus, our suggested method is seen to be more robust than the fuzzy-PID controllers.

Fuzzy DP를 이용한 저수지 시스템 최적운영 (Ⅰ) : Fuzzy DP 기법 개발

이재응(Yi Jaeeung),최성규(Choi Sung Gyu) 대한토목학회 2007 대한토목학회논문집 B Vol.27 No.1B

우리나라에서도 최근 이상기후의 영향으로 인해 매년 봄가뭄과 여름홍수가 반복적으로 발생하여 효율적 수자원 관리의 중요성이 더욱 강조되고 있다. 최적 저수지 운영을 통한 효율적인 수자원 이용으로 과다한 무효 방류와 같이 낭비되는 수자원을 절감시켜 신규 수자원 개발과 유사한 효과를 획득할 필요가 있다. fuzzy 동적 계획법은 저수지 운영의 불확실성과 사용자의 우전순위를 잘 반영하며, 주어진 목적과 제약조건 하에서 체계적으로 최적해를 선정할 수 있다. fuzzy 동적계획법은 일반 동적계획법과 비교하여 목적함수와 제약조건의 적용에 탄력성이 크다는 장점이 있다. 본 연구에서는 fuzzy 집합이론과 membership 함수를 이용한 fuzzy 동적 프로그래밍으로 이와 같은 문제의 해결책을 제시하였다. 본 연구의 결과는 향후 저수지의 효율적인 운영을 위한 지침으로 시용될 수 있을 것이며 유역의 수자원 영향 평가에 활용할 수 있을 것으로 기대된다. In Korea, spring drought and summer flood occurs repeatedly almost every year because of climate change. Accordingly, the efficient water resources management should be emphasized more and more. It is necessary to obtain the similar effects such as new water resources development by reducing the wasted water like unnecessary spillway release and by emphasizing the effective water lise like optimal reservoir operation. Fuzzy dynamic programming has the capability of representing uncertainty of reservoir operation and developer's priority efficiently. Also, it can find the optimal solution under given objectives and constraints. Fuzzy dynamic programming is more elastic approach to be applied for fuzzy goals and constraints than general dynamic programming. Solutions for these kinds of problems are presented by fuzzy dynamic programming using fuzzy set theory and membership function. It is expected that the results of this study can be used as a guideline of optimal reservoir operation and evaluation of water resources in basin.