• 한국정보처리학회논문지
• /
• 제1권1호
• /
• pp.99-104
• /
• 1994

본 논문은 LSI의 물리적 레이아웃 설계시 다량의 패턴 데이타를 고속으로 처리할 수 있는 새로운 2차원 병렬처리 방법을 제안한고 메모리와 프로세서간에 데이타를 양방향으로 고속 전송 하는 스위칭 네트워크를 설계하였다.이스위칭 네트워크를 VHDL 설계 시스템을 이용하여 시뮬레이션하여 그 동작을 확인하였다.

• 한국정보처리학회논문지
• /
• 제7권3호
• /
• pp.1025-1031
• /
• 2000

Pre-existing pattern recognition techniques, in the case of character recognition, have limited on the application field. But CAI character learning system and writer's recognition system are very important parts. The application field of pre-existing system can be expanded in the content that the learning of characters and the recognition of writers in the proposed paper. In order to achieve these goals, the development contents are the following: Firstly, pre-processing method by understanding the image structure is proposed, secondly, recognition of characters are accomplished b the histogram distribution characteristics. Finally, similarity measure functions are defined from standard character pattern for matching of the input character pattern. Also the effectiveness of this system is demonstrated by experimenting the standard primitive image.

• 한국정보처리학회논문지
• /
• 제1권2호
• /
• pp.272-278
• /
• 1994

본 논문에서는 BIST(Built-In Self Test)시 순서회로내의 조합회로를 pseudoexhaustive 시험하는데 필요한 테스트 패턴 생성기와 응답 분석기를 제안한다. 제안하는 테스트 패턴 생성기는 테스트 패턴의 초기값을 스캔 인 할 수 있고, exhaustive test pattern 을 생성할 수 있다. 또한, 응답 분석기는 회로의 응답을 분 석할 수 있을 뿐만 아니라 응답 결과를 스캔 아웃할 수 있다. 이러한 테스트 패턴 생 성기와 응답분석기는 SRL과 LFSR을 결합하여 설계하였다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권3호
• /
• pp.215-220
• /
• 2002

This paper proposes a method to apply the Backpropagation(BP) algorithm of MVL(Multi-Valued Logic) Neural Network to pattern recognition. It extracts the property of an object density about an original pattern necessary for pattern processing and makes the property of the object density mapped to MVL. In addition, because it team the pattern by using multiple valued logic, it can reduce time f3r pattern and space fer memory to a minimum. There is, however, a demerit that existed MVL cannot adapt the change of circumstance. Through changing input into MVL function, not direct input of an existed Multiple pattern, and making it each variable loam by neural network after calculating each variable into liter function. Error has been reduced and convergence speed has become fast.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2012년도 춘계학술대회 논문집
• /
• pp.167-168
• /
• 2012

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2003년도 추계학술발표논문집 (하)
• /
• pp.1539-1542
• /
• 2003

최근 소프트웨어 개발에서의 핵심어인 객체지향(object oriented)은 1970년대 초부터 중요하게 인식 되기 시작했다. 현재는 객체지향에 대한 많은 관련 연구를 통하여 그 활용범위가 증대되고 있다. 본 연구에서는 객체지향 연구의 한 부분인 디자인 패턴 중에서 많이 이용되는 Iterator(Cursor) Pattern을 활용하여 닷넷(.NET) 기반에서의 특정 비즈니스를 위한 데이터 접속 객체를 연구하였다.

• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.643-652
• /
• 2017

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제6권10호
• /
• pp.2632-2649
• /
• 2012

Most approaches to human action recognition is limited due to the use of simple action datasets under controlled environments or focus on excessively localized features without sufficiently exploring the spatio-temporal information. This paper proposed a framework for recognizing realistic human actions. Specifically, a new action representation is proposed based on computing a rich set of descriptors from keypoint trajectories. To obtain efficient and compact representations for actions, we develop a feature fusion method to combine spatial-temporal local motion descriptors by the movement of the camera which is detected by the distribution of spatio-temporal interest points in the clips. A new topic model called Markov Semantic Model is proposed for semantic feature selection which relies on the different kinds of dependencies between words produced by "syntactic " and "semantic" constraints. The informative features are selected collaboratively based on the different types of dependencies between words produced by short range and long range constraints. Building on the nonlinear SVMs, we validate this proposed hierarchical framework on several realistic action datasets.

• 대한본초학회지
• /
• 제20권4호
• /
• pp.133-140
• /
• 2005

Objectives : We have been used many herbal medicines after processing to improve the effect, decrease toxicity and side-effect, and change property. We have studied the physico-chemical change and HPLC pattern of Morindae Radix by means of processing method. Methods : This study was investigated the contents of loss on drying, residue on ignition, residue on acid insoluble ignition, 50% ethanol extract and HPLC pattern of Morindae Radix(Morinda officinalis How.) by processed and non-processed. We have conducted Morindae Radix and Damnacanthi Radix which is circulated in herbal medicine market by forgery. Processed Morindae Radix was prepared by heating of added to salt(SP), liquor(LP) and Glycyrrhizae Radix solution(GP) for 20-40 minutes. Results and Conclusions : From this analysis, we found that the content of 50% ethanol extract was increased by processing method. And we were detected distinguishable marker of processed and non-processed from Morindae Radix(Morinda officinalis How.) by HPLC pattern analysis.

• 정보학연구
• /
• 제7권2호
• /
• pp.43-54
• /
• 2004

홉필드 네트웍(Hopfield Network)은 존 홉필드(John J. Hopfield) 박사에 의해 제안된 이래 패턴인식과 최적화 문제에 활용되어 왔다. 특히 리(Jian-Hua Li)에 의해 제안된 방식은 SVD(singular value decomposition) 기법을 사용하여 입력패턴을 재구성함으로써 효율향상에 기여하였다. 본 논문은 리(Li)가 제안한 홉필드 네트웍에 사용할 패턴 집합의 선형 선처리 방식에 따른 성능 향상을 실험하였다. 선형 선처리 방식에 하다마드 방식과 랜덤 방식이 최대 30%, 하다마드 방식이 최대 15%의 성능이 향상되었다. 수렴시간 측면에서 보면 랜덤 방식이 최대 5 이터레이션, 하다마드 방식이 최대 2.5 이터레이션의 성능 향상을 확인하였다.