Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
Journal of Korean Institute of Intelligent Systems
Journal Basic Information
Journal DOI :
Korean Institute of Intelligent Systems
Editor in Chief :
Volume & Issues
Volume 7, Issue 5 - Dec 1997
Volume 7, Issue 4 - Oct 1997
Volume 7, Issue 3 - Aug 1997
Volume 7, Issue 2 - Jun 1997
Volume 7, Issue 1 - Mar 1997
Selecting the target year
On Development the Stable Learning Algorithm for Recurrent Neural Network Control System
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 3~11
One of major research areas in the recurrent neural network is to develop stable learning algorithm. In this paper, the stable learning algorithm is developed by utilizing the evolutionary programming. The effectiveness of the proposed learning algorithm will be verified by simulating two d.0.f. robot manipulator.
Automatic Tuning of Fuzzy Controller for Unknown Systems
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 12~20
In this paper, the authors propose a method of stepwise tuning a controller with unknown process properties through! its step response. A fuzzy controller is chosen to achieve this aim. The main object of this paper is to give knowledge for the improvement of the response, under the limited prop erties obtained from the step response of the process. We obtained the adequate tuning method through simulations of many control objects. And the method of selecting optimal sampling period is also shown.
A Method of Self-Organizing for Fuzzy Logic Controller Through Learning of the Proper Directioin of Control
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 21~33
In this paper, a method of self-organizing for fuzzy logic controller(FLC) through learning of the proper direction of coritrol is proposed. In case of designing a self-organizing FLC for unknown dynamic plants based on the gradient descent method, it is difficult to identify the desirable direction of the change of control inpul. in which the error would be decreased. To resolve this problem, we propose a method as fo1lows:at first, assign representative values for the direction of change of error with respect to control input to each partitioned region of the states, and then, learn the fuzzy control rules using the reinforced representative values through iterative trials. 'The proposed self-organizing FLC has simple structure and it is easy to design. The validity of the proposed method is proved by the computer simulation for an inverted pendulum system.
Fuzzy Learning Algorithms for Time Series Prediction
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 34~42
This paper presents new fuzzy learning algorithms and their applications to time series prediction. During generating fuzzy rules from numerical data, there is a tendency to produce conflicting rules which have same premise but different consequence. To resolve the problem, we propose MCM(Modified Center Method) which is proven to reduce the error in the prediction. We have applied MCM to the analysis of Mackey-Glass time series and Gas Furnace da.ta to verify its efficiency.
Fuzzy Rule Generation and Building Inference Network using Neural Networks
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 43~54
Knowledge acquisition is one of the most difficult problems in designing fuzzy systems. As application domains of fuzzy systems become larger and more complex, it is more difficult to find the relations among the system's input- outpiit variables. Moreover, it takes a lot of efforts to formulate expert's knowledge about complex systems' control actions by linguistic variables. Another difficulty is to define and adjust membership functions properly. Soin conventional fuzzy systems, the membership functions should be adjusted to improve the system performance. This is time-consuming process. In this paper, we suggest a new approach to design a fuzzy system. We design a fuzzy system using two neural networks, Kohonen neural network and backpropagation neural network, which generate fuzzy rules automatically and construct inference network. Since fuzzy inference is performed based on fuzzy relation in this approach, we don't need the membership functions of each variable. Therefore it is unnecessary to define and adjust membership functions and we can get fuzzy rules automatically. The design process of fuzzy system becomes simple. The proposed approach is applied to a simulated automatic car speed control system. We can be sure that this approach not only makes the design process of fuzzy systems simple but also produces appropriate inference results.
A Study on the Color Planning System Based on Fuzzy Set Theory
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 55~64
In this paper, a fuzzy set based decision support system is designed for the color planning, that uses the linguistic image words of the space to be colored and progressively recommend the harmoneous colors for each objects in the space. The linguistic image words denotes various emotional effects of the colored space represented as the adjectives like 'romantic', 'beautiful', and so on. The search for object color should not destroy the overall image of the colored space and should be harmoneous with the previously determined object colors. The developed color planning system is composed of five subsystems; two dimentional graphic tools to draw the color space, the input system to receive the linguistic image words, the system to determine and recommend the main colcrs, the system to determine the harmonious colors and the system to adjust the determined wlor objects. We expect that the system can help designers and the persons who are not good at color design, and it can be applied to various color design such as interior, fashions, and product design.
A Study onthe Modelling and control Using GMDH Algorithm
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 65~71
With the emergence of neural network, there is a revived interest in identification of nonlinear systems. So in this paper, to identify unknown nonlinear systems dynamically we propose DPNN(Dynamic Polynomial Neural Network) using GMDH (Group Method of Data Handling) algorithm. The dynamic system identification using GMDH consists of applying a set of inputloutput data to train the network by dynamically computing the necessary coeffici1:nt sets. Then, MRAC(Mode1 Reference Adaptive Control) is designed to control nonlinear systems using DPNN. In the result, we can see that the modelling and control using DPNN work well by computer simulation.
A New Design Method for T-S Fuzzy Controller with Pole Placement Constraints
Joh, Joongseon ; Jeung, Eun-Tae ; Chung, Won-Jee ; Kwon, Sung-Ha ;
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 72~80
A new design method for Takagi-Sugeno (T-S in short) fuzzy controller which guarantees global asymptotic stability and satisfies a desired performance is proposed in this paper. The method uses LMI(Linear Matrix Inequality) approach to find the common symmetric positive definite matrix P and feedback fains K/sub i/, i= 1, 2,..., r, numerically. The LMIs for stability criterion which treats P and K'/sub i/s as matrix variables is derived from Wang et al.'s stability criterion. Wang et al.'s stability criterion is nonlinear MIs since P and K'/sub i/s are coupled together. The desired performance is represented as $ LMIs which place the closed-loop poles of $ local subsystems within the desired region in s-plane. By solving the stability LMIs and pole placement constraint LMIs simultaneously, the feedback gains K'/sub i/s which gurarntee global asymptotic stability and satisfy the desired performance are determined. The design method is verified by designing a T-S fuzzy controller for an inverted pendulum with a cart using the proposed method.
Rosition control of a Flexible Finger Driven by Piezoelectric Bimorph Cells Using Fuzzy Algorithms
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 81~88
This paper dealt with the position control of a flexible miniature finger driven by piezoelectric bimorph cells, cemented on both side of the finger. Bending moments generated by cells drives the finger, and end-point of the finger is controlled, so as to move in synchrony with fluctation of target and maintain a constant distance between target surface and inger's tip. The voltage applied for the cell is controlled by tip displacement error and error rate. We proposed a PD-Fuzzy controller under conception of PD control strategy. It brought and advantage which reduce number of rules than that of same type conventional fuzzy system and more correct redponse than PID control results.
Relation between Multidimensional Linear Interpolation and Regularization Networks
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 89~95
This paper examines the relation between multidimensional linear interpolation (MDI) and regularization net-works, and shows that an MDI is a special form of regularization networks. For this purpose we propose a triangular basis function(TBF) network. Also we verified the condition when our proposed TBF becomes a well-known radial basis function (RBF).
Fuzzy Pariwise Almost Continuous Mappings on Fuzzy Bitopological Spaces
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 96~101
Fuzzy Syntopogenous Structures and Orders
Journal of Korean Institute of Intelligent Systems, volume 7, issue 3, 1997, Pages 102~106
We introduce the category [PFSyn] of saturated fuzzy syntopogenous preordered spaces and continuous isotones ans show that the category [PFSyn] is topological and cotopological. Furthermore, to consdier a compatibility between order structures and fuzzy syntopogenous structure, we introduce a category [IPFSyn] of increasing saturated fuzzy syntopogenous spaces and its dual category [IPFSyn] of decreasing fuzzy syntopogenous spaces, and show that [IPFSyn] and [DPFSyn] are both bireflective in the category [PFSyn].