• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1997.10a
• /
• pp.247-251
• /
• 1997

FCM(Fuzzy Cognitive Map) is a fuzzy signed directed graph for representing causal reasoning which has fuzziness between causal concepts. Authors have already proposed FCM-based fault diagnostic scheme and verified its usefulness. However, the previously proposed scheme has the problem of lower diagnostic resolution as in the case of other qualitative approaches. In order to improve the diagnostic resolution, a concept of fuzzy number is introduced into the basic FCM-based fault diagnostic algorithm. By incorporation the fuzzy number into fault FCM models, quantitative information such as the transfer gain between the state variables can be effectively utilized for better diagnostic resolution. Furthermore, an enhanced TAM(Temporal Associative Memory) recall procedure and modified and modified pattern matching scheme are also proposed.

• Proceedings of the IEEK Conference
• /
• 2001.06b
• /
• pp.269-272
• /
• 2001

In this paper we proposed the format converter design and implementation for real time image processing. This design method is based on realized the large processor-per-pixel array by integrated circuit technology in which this two types of integrated structure is can be classify associative parallel processor and parallel process with DRAM cell. Layout pitch of one-bit-wide logic is identical memory cell pitch to array high density PEs in integrate structure. This format converter design has control path implementation efficiently, and can be utilized the high technology without complicated controller hardware. Sequence of array instruction are generated by host computer before process start, and instructions are saved on unit controller. Host computer is executed the pixel-parallel operation starting at saved instructions after processing start

• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2007.05a
• /
• pp.1043-1047
• /
• 2007

수질오염사고로 발생할 수 있는 시나리오를 통해서 스스로 수질오염사고를 판단할 수 있는 지능형 알고리즘들을 검토하였다. 지능형 알고리즘의 학습을 위해 개발된 기준축과 학습지표는 적절한 결과를 유도하는데 유용하였다. 다층신경망, 뉴로-퍼지 알고리즘은 TOC와 DO의 이상 수질에 대하여 안정, 주의, 경고 상태를 적합하게 구별하는 것으로 나타났으며, 다중퍼셉트론 알고리즘은 모호한 자료에 대해서는 판단능력이 부족한 것으로 나타났다. 구조가 단순하지만 양방향 연산을 수행하는 BAM(Bidirectional Associative Memory) 알고리즘은 다층신경망과 뉴로-퍼지 알고리즘과 비교할 때, 학습 및 구동시간이 짧을 뿐만아니라 결과 또한 안정적인 것으로 나타났다.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1996.10a
• /
• pp.267-270
• /
• 1996

In this paper, we present a new design method to implement autoassociative memories based on BSB neural networks. With a concrete mathematical model proposed after analyzing some new qualitative properties of autoassociative memories, we reinterpret design of autoassociative memories as a constrained optimization problem and use an evolution program as an optimal search tool to solve this. The proposed method satisfies many of the criteria used to evaluate the effectivencess of a given associative memory and has improvements with respect to correctness and performance. Comparing simulation results with other methods, we demonstrate the effectiveness of the proposed method.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.30B no.6
• /
• pp.86-92
• /
• 1993

In this paper, we present a VLSI chip design of Multi-layer Bidirectionsl Associative Memory with good error-correction performance. The MBAM neural chip utilizes inner product implementation schems with binary storage and analog calculation.. Multi-layer can be constructed by direct cascading of these chips, and the number of neurons is expandable by parallel connection of these chips. We made proto-type chips and interface board to test the expansion. Currently the Chip has 32 input nodes, 32 output nodes, and can store up to 48 patterns, 32x48x2 SRAMs are included in the chip.

• 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.

• Proceedings of the Korean Information Science Society Conference
• /
• 2004.04b
• /
• pp.760-762
• /
• 2004

본 논문에서는 저해상도 및 저대비의 특성을 지니는 문자 영상으로부터 특징을 추출하고 연상메모리를 이용하여 대상 문자를 인식하는 방법을 소개한다. 저해상도 영상의 이진화 과정에서 발생할 수 있는 정보의 왜곡 현상을 피하기 위하여 입력 영상의 gradient 정보를 이용하여 특징을 추출한다 저해상도 일 저대비의 특성을 지니는 문자 영상의 경우 입력 영상에 noise가 존재하거나 충분한 정보가 포함되어 있지 않은 경우 특징벡터에 상당한 왜곡을 초래하게 된다. 손상된 특징을 복원하기 위하여 연상메모리를 이용한다. 인식하고자 하는 문자 영상들의 prototype 영상들을 이용하여 연상메모리의 weight matrix를 구성한다. weight matrix를 이용해서 입력 영상이 가지는 특징과 가장 비슷한 특징을 가지는 prototype 영상의 특징벡터를 생성함으로써 손상된 특징을 복원하게 된다. 제안된 시스템을 이용하여 실험한 결과 noise가 존재하거나 정보가 충분하지 않은 입력 영상에 대해서 비교적 놀은 인식률을 얻음을 볼 수 있었다.

• The Journal of the Korea Contents Association
• /
• v.22 no.2
• /
• pp.224-236
• /
• 2022

This study tests the hypotheses that city slogan reduces the retrieval of city memory unrelated to the slogan from the long term memory and that some variables moderate this effect, using the experimental method. The theoretical basis for the hypotheses is from the structure of the long term memory and the principle of memory retrieval discussed in ANM(Associative Network Model). For the test of hypotheses, the study adopted 4 experimental groups (2(slogan relevance: high or low) * 2(slogan concreteness: high or low)) and 1 control group. Each experimental group was exposed to one slogan corresponding to its condition while the control group was not. Then, the recall score was compared among experimental and control groups. One hundred and seventy-four undergraduate students belonging to the college of the authors participated in the study. The sample group was between 18 and 27 years of age, with an average of 22.4 years, and 54 percent comprised males. Results showed that city slogan had a negative effect on the retrieval of city memory unrelated to the slogan in most experimental conditions. This effect was more evident when the slogan had high relevance or high concreteness. But the main effect did not appear when the slogan had low relevance and low concreteness.

• The Journal of the Korea Contents Association
• /
• v.10 no.3
• /
• pp.64-71
• /
• 2010

Recently, to achieve high performance of the processor, the cache is splits physically into two parts, one for instruction and one for data. This paper proposes an architecture of asynchronous instruction cache based on mixed-delay model that are DI(delay-insensitive) model for cache hit and Bundled delay model for cache miss. We synthesized the instruction cache at gate-level and constructed a test platform with 32-bit embedded processor EISC to evaluate performance. The cache communicates with the main memory and CPU using 4-phase hand-shake protocol. It has a 8-KB, 4-way set associative memory that employs Pseudo-LRU replacement algorithm. As the results, the designed cache shows 99% cache hit ratio and reduced latency to 68% tested on the platform with MI bench mark programs.