• 제어로봇시스템학회:학술대회논문집
• /
• 2002.10a
• /
• pp.49.2-49
• /
• 2002

This paper describes the configuration of a multi-agent system that can recognize human intentions. This system constructs ontologies of human intentions and enables knowledge acquisition and sharing between intelligent agents operating in different environments. This is achieved by using a bi-directional associative memory network. The process of intention recognition is based on fuzzy association inferences. This paper shows the process of information sharing by using ontologies. The purpose of this research is to create human-centered systems that can provide a natural interface in their interaction with people.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.315-320
• /
• 1997

Rule minimization technique adapted from rough set theory was applied to remove redundant knowledge which is not necessary to make a knowledge base. New algorithm to diagnose fault using Improved Fuzzy Cognitive Maps(I-FCMs), and Fuzzy Associative Memory(FAM) is proposed. I-FCM[22] is superior to gathering knowledge from many experts and descries dynamic behaviors of systems very well. I-FCM is not only a knowledge base, but also a inference engine. FAM has learning capability like neural network[12]. Rule minimization and composition of I-FCM and FAM make it possible to construct compact knowledge base and breaks the border between inference engine and knowledge base.

• Journal of applied mathematics & informatics
• /
• v.30 no.5_6
• /
• pp.1031-1049
• /
• 2012

In this paper, a class of impulsive fuzzy bi-directional associative memory (BAM) neural networks with distributed delays and variable coefficients are considered. Using Lyapunov functional method and fixed point theorem, we derived some sufficient conditions for the existence and globally exponential stability of unique periodic solution of the networks. The results obtained are new and extend the previous known results. In addition, an example is given to show the effectiveness of our results obtained.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.2
• /
• pp.231-238
• /
• 1993

A rules of fuzzy control is to represent an expert‘s and engineer‘s ambiguous control knowledge of system with some lingustic rules. This rule is very difficult to represent perfectly because expert‘s knowledge is not precise and the rule is not perfect. We propose the fuzzy reasoning and learning to upgrade precision of imperfect rules successively after system running. In the proposed method, the precision of the backward part of a fuzzy rule is improved by back propagation learning method. Also, the method reasons the compatibility degree of the forward part of fuzzy rule by associative memory method. This method this is successfully applied to design auto-parking fuzzy controller in which expert‘s technology and knowledge are required in the limited area.

• Journal of KIISE:Software and Applications
• /
• v.31 no.9
• /
• pp.1171-1179
• /
• 2004

We describe word boundary detection that extracts the boundary between speech and non-speech. The proposed method uses two features. One is the normalized root mean square of speech signal, which is insensitive to white noises and represents temporal information. The other is the normalized met-frequency band energy of voice signal, which is frequency information of the signal. Our method detects word boundaries using a recurrent fuzzy associative memory(RFAM) that extends FAM by adding recurrent nodes. Hebbian learning method is employed to establish the degree of association between an input and output. An error back-propagation algorithm is used for teaming the weights between the consequent layer and the recurrent layer. To confirm the effectiveness, we applied the suggested system to voice data obtained from KAIST.

• Annual Conference on Human and Language Technology
• /
• 1993.10a
• /
• pp.317-328
• /
• 1993

본 논문은 신경망과 퍼지 이론을 결합한 한국어 철자 교정기 KSCNN(Korean Spelling Corrector using Neural Network)에 대하여 기술한다. KSCNN은 퍼셉트론(perceptron) 학습을 이용한 연상 메모리(associative memory)로 구성되며 자판 배열 특성을 고려한 퍼지 멤버쉽 함수에 의해 신경망의 입력값을 정한다. 본 철자 교정기의 장점은 인지적인 방법으로 철자를 교정하기 때문에 기존의 VA나 BNA와는 달리 오류의 종류에 영향을 받지 않으며 교정된 철자나 후보자들에 대한 견인값(attraction value)을 측정하여 시스템의 신뢰도를 높일 수 있다는 데 있다. 또한, 본 논문은 실험을 통해서 퍼지 멤버쉽 함수에 의한 입력 노드의 활성화가 자판 배열특성을 고려할 수 있기 때문에 시스템의 성능을 향상시킨다는 사실을 보여준다.

• The KIPS Transactions:PartB
• /
• v.10B no.6
• /
• pp.611-618
• /
• 2003

In this paper, we describe a fuzzy inference approach for detecting and classifying shot transitions in video sequences. Our approach basically extends FAM (Fuzzy Associative Memory) to detect and classify shot transitions, including cuts, fades and dissolves. We consider a set of feature values that characterize differences between two consecutive frames as input fuzzy sets, and the types of shot transitions as output fuzzy sets. The inference system proposed in this paper is mainly composed of a learning phase and an inferring phase. In the learning phase, the system initializes its basic structure by determining fuzzy membership functions and constructs fuzzy rules. In the inferring phase, the system conducts actual inference using the constructed fuzzy rules. In order to verify the performance of the proposed shot transition detection method experiments have been carried out with a video database that includes news, movies, advertisements, documentaries and music videos.

• 제어로봇시스템학회:학술대회논문집
• /
• 1993.10a
• /
• pp.233-238
• /
• 1993

In this paper, two diagnosis algorithms using the simple fuzzy, cognitive map (FCM) that is an useful qualitative model are proposed. The first basic algorithm is considered as a simple transition of Shiozaki's signed directed graph approach to FCM framework. And the second one is an extended version of the basic algorithm. In the extension, three important concepts, modified temporal associative memory (TAM) recall, temporal pattern matching algorithm and hierarchical decomposition are adopted. As the resultant diagnosis scheme takes short computation time, it can be used for on-line fault diagnosis of large scale and complex processes that conventional diagnosis methods cannot be applied. The diagnosis system can be trained by the basic algorithm and generates FCM model for every experienced process fault. In on-line application, the self-generated fault model FCM generates predicted pattern sequences, which are compared with observed pattern sequences to declare the origin of fault. In practical case, observed pattern sequences depend on transport time. So if predicted pattern sequences are different from observed ones, the time weighted FCM with transport delay can be used to generate predicted ones. The fault diagnosis procedure can be completed during the actual propagation since pattern sequences of tvo different faults do not coincide in general.