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 10, Issue 6 - Dec 2000
Volume 10, Issue 5 - Oct 2000
Volume 10, Issue 4 - Aug 2000
Volume 10, Issue 3 - Jun 2000
Volume 10, Issue 2 - Apr 2000
Volume 10, Issue 1 - 00 2000
Selecting the target year
A Neural Network based Block Classifier for High Speed Fractal Image Compression
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 179~187
Fractal theory has strengths such as high compression rate and fast decoding time in application to image compression, but it suffers from long comparison time necessary for finding an optimally similar domain block in the encoding stage. This paper proposes a neural network based block classifier which enhances the encoding time significantly by classifying domain blocks into 4 patterns and searching only those blocks having the same pattern with the range block to be encoded. Size of a block is differently determined depending on the image complexity of the block. The proposed algorithm has been tested with three different images having various featrues. The experimental results have shown that the proposed algorithm enhances the compression time by 40% on average compared to the conventional fractal encoding algorithms, while maintaining allowable image qualify of PSNR 30 dB.
A Neuro-Fuzzy Model Optimization Using Rough Set Theory
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 188~193
This paper presents an approach to obtain a reduced neuro-fuzzy model for a plant. The Neuro-Fuzzy Network are compose of the Radial Basis Function Networks with Gausis membership and learned by using temporal back propagation. The dependency in rough set theory is used to eliminate rules. Dependency between the condition membership value of each rule in a model and the output of the plant can allow us to see how much contribution the rule is to identify the plant. While the reduced model maintains the same performance as the original one, the selection algorithm can minimize its complexity and redundancy of the structure.
An Automatic Fuzzy Rule Extraction using CFCM and Fuzzy Equalization Method
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 194~202
In this paper, an efficient fuzzy rule generation scheme for Adaptive Network-based Fuzzy Inference System(ANFIS) using the conditional fuzzy-means(CFCM) and fuzzy equalization(FE) methods is proposed. Usually, the number of fuzzy rules exponentially increases by applying the gird partitioning of the input space, in conventional ANFIS approaches. Therefore, CFCM method is adopted to render the clusters which represent the given input and output fuzzy and FE method is used to automatically construct the fuzzy membership functions. From this, one can systematically obtain a small size of fuzzy rules which shows satisfying performance for the given problems. Finally, we applied the proposed method to the truck backer-upper control and Box-Jenkins modeling problems and obtained a better performance than previous works.
A New Unsupervised Learning Network and Competitive Learning Algorithm Using Relative Similarity
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 203~210
In this paper, we propose a new unsupervised learning network and competitive learning algorithm for pattern classification. The proposed network is based on relative similarity, which is similarity measure between input data and cluster group. So, the proposed network and algorithm is called relative similarity network(RSN) and learning algorithm. According to definition of similarity and learning rule, structure of RSN is designed and pseudo code of the algorithm is described. In general pattern classification, RSN, in spite of deletion of learning rate, resulted in the identical performance with those of WTA, and SOM. While, in the patterns with cluster groups of unclear boundary, or patterns with different density and various size of cluster groups, RSN produced more effective classification than those of other networks.
Actuator Fault Diagnostic Algorithm based on Hopfield Network
Park, Tae-Geon ; Ryu, Ji-Su ; Hur, Hak-Bom ; Ahn, In-Mo ; Lee, Kee-Sang ;
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 211~217
A main contribution of this paper is the development of a Hopfield network-based algorithm for the fault diagnosis of the actuators in linear system with uncertainties. An unknown input decoupling approach is introduced to the design of an adaptive observer so that the observer is insensitive to uncertainties. As a result, the output observation error equation does not depend on the effect of uncertainties. Simultaneous energy minimization by the Hopfield network is used to minimize the least mean square of errors of errors of estimates of output variables. The Hopfield network provides an estimate of the gains of the actuators. When the system dynamics changes, identified gains go through a transient period and this period is used to detect faults. The proposed scheme is demonstrated through its application to a simulated second-order system.
Effectual Fuzzy Query Evaluation Method based on Fuzzy Linguistic Matrix in Information Retrieval
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 218~227
In this paper, we present a new fuzzy information retrieval method based on thesaurus. In the proposed method th thesaurus is represented by a fuzzy linguistic matrix, where the elements in fuzzy linguistic matrix represent a qualitative linguistic values between terms. In the fuzzy linguistic matrix, there are three kinds of fuzzy relationships between terms, i.e., similar relation, hierarchical relation, and associative relation. The implicit fuzzy relationships between terms are inferred by the transitive closure of the fuzzy linguistic matrix based on fuzzy theory. And the proposed method has the capability to deal with a qualitative linguistic weights in a query and in indexing of information items to reflect qualitative measure of human based on vague and uncertain decisions rather than a quantitiative measure. Therefore the proposed method is more flexible than the ones presented in papers[1-3]. Moreover our method is more effectual of time than the ones presented in papers[1-3] because we use a fuzzy linguistic matrix and AON (Associate Ordinary Number) values in query evaluation process. As a result, the proposed method allows the users to perform fuzzy queries in a more flexible and more intelligent manner.
Generalized Common Fixed Point Theorems on Menger PM-spaces
Lee, Byung-Soo ; Yang, Kyu-Han ;
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 228~231
More generalized common fixed point theorems for a sequence of fuzzy mappings to the nonexpansive case on Menger probabilistic metric spaces, which generalize recent results of Lee et al., are obtained.
An Implementation of Optimal Rules Discovery System: An Integrated Approach Based on Concept Hierarchies, Information Gain, and Rough Sets
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 232~241
This study suggests an integrated method based on concept hierarchies, information gain, and rough set theory for efficient discovery rules from a large amount of data, and implements an optimal rules discovery system. Our approach applies attribute-oriented concept ascension technique to extract generalized knowledge from a database, knowledge reduction technique to remove superfluous attributes and attribute values, and significance of attributes to induce optimal rules. The system first reduces the size of database by removing the duplicate tuples through the condition attributes which have no influences on the decision attributes, and finally induces simplified optimal rules by removing the superfluous attribute values by analyzing the dependency relationships among the attributes. And we induce some decision rules from actual data by using the system and test rules to new data, and evaluate that the rules are well suited to them.
Performance Improvement of Information Retrieval System by means of Fuzzy Relational Product
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 242~251
Learning of Rules for Edge Detection of Image using Fuzzy Classifier System
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 252~259
In this paper, we propose a Fuzzy Classifier System(FCS) to find a set of fuzzy rules which can carry out the edge detection of a image. The FCS is based on the fuzzy logic system combined with machine learning. Therefore the antecedent and consequent of a classifier in FCS are the same as those of a fuzzy rule. There are two different approaches, Michigan and Pittsburgh approaches, to acquire appropriate fuzzy rules by evolutionary computation. In this paper, we use the Michigan style in which a single fuzzy if-then rule is coded as an individual. Also the FCS employs the Genetic Algorithms to generate new rules and modify rules when performance of the system needs to be improved. The proposed method is evaluated by applying it to the edge detection of a gray-level image that is a pre-processing step of the computer vision. the differences of average gray-level of the each vertical/horizontal arrays of neighborhood pixels are represented into fuzzy sets, and then the center pixel is decided whether it is edge pixel or not using fuzzy if-then rules. We compare the resulting image with a conventional edge image obtained by the other edge detection method such as Sobel edge detection.
Design of the Hybrid Controller using the Fuzzy Switching Mode
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 260~269
The fuzzy and state-feedback control systems have been applied in various areas from non-linear to linear systems. A Fuzzy controller is endowed with control rules and membership function that are constructed on the knowledge of expert, as like intuition and experience. but It is very difficult to obtain the exact values which are the membership function and consequent parameters. though apply back-propagation algorithm to the system, the convergence time a much. Besides, the state-feedback system is most widely used in industry due to its simple control structure and easily able to design the controller. but it is weak in complex system of higher degree and non-linear. In this paper presents the design of a fuzzy switching mode, it these two controllers work at different operation conditions, the advantages of both controller can be retained and the disadvantages can be removed. Between the Fuzzy and the State-feedback controlles, the good outputs are selected by the switching mode. Moreover it is powerful in complex system of higher degree and non-linear. In these sense compared with the state-feedback controller, the performance of the proposed controller was improvedin the section of linearization.
On-chip Learning Algorithm in Stochastic Pulse Neural Network
Journal of Korean Institute of Intelligent Systems, volume 10, issue 3, 2000, Pages 270~279
This paper describes the on-chip learning algorithm of neural networks using the stochastic pulse arithmetic. Stochastic pulse arithmetic is the computation using the numbers represented by the probability of 1' and 0's occurrences in a random pulse stream. This stochastic arithmetic has the merits when applied to neural network ; reduction of the area of the implemented hardware and getting a global solution escaping from local minima by virtue of the stochastic characteristics. And in this study, the on-chip learning algorithm is derived from the backpropagation algorithm for effective hardware implementation. We simulate the nonlinear separation problem of the some character patterns to verify the proposed learning algorithm. We also had good results after applying this algorithm to recognize printed and handwritten numbers.