• 대한전자공학회논문지
• /
• 제27권5호
• /
• pp.757-766
• /
• 1990

In this paper a new knowledge based vision system using orientation information on each surface of the 3-dimensional object is discussed. The measurement of the orientation information is performed by photometric stereo method. And then the obtained orientations are segmented using Gaussian curvature and mean curvature. A hierarchical knowledge base which is based on the characteristics, shape, area and length of the surface is built up, and then the knowledge based system infers by the condition interprete system (CIS). As the results, an easier and more accurate 3-D object recognition system is implemented, because it uses the characteristics and shapes as units of the surface in the recognition process.

• 한국정보통신학회논문지
• /
• 제10권9호
• /
• pp.1691-1699
• /
• 2006

본 논문에서는 모든 분야의 지식 에 대해 온톨로지(ontology)화 하기보다는 회의 분야로 특화하여 회의 지을 온톨로지화 할 수 있는 지식기반회의 관리시스템 아키텍처를 제시한다. 또한, 시뮬레이션 및 분석을 통해 객관적 평가 기준을 마련한 다음 화상 회의, 음성 인식, 행동 인식 등의 각종 인식 시스템을 통해 변환되고 가공된 정보를 체계화하고 지식 화하여 분석 할 수 있는 시스템으로의 발전 가능성에 대해서 제시한다.

• 한국조리학회지
• /
• 제13권3호
• /
• pp.1-11
• /
• 2007

This study aims at inquiring into new generations' recognition of traditional foods to present the alternatives and suggestions of simplification, popularization and processed food for popularizing the foods suited to them. The findings on survey showed that they had a preference for development of simple food-oriented menu suited to new generation's way of thinking, under the maintenance of flavor and nutrition so that they can simply eat traditional foods through the simplification of cooking and the development of processed food. The result of this study showed significant influences that the first result is the knowledge on the cooking method in simplification, the second result is the knowledge on the flavor and nutrition in popularization of traditional food, and the third is the knowledge on the cooking method, the flavor and nutrition in the processed food.

• 전자공학회논문지B
• /
• 제31B권7호
• /
• pp.119-128
• /
• 1994

In this paper, we propose a method for facial feature extraction and recognition algorithm using neural networks. First we extract a face part from the background image based on the knowledge that it is located in the center of an input image and that the background is homogeneous. Then using vertical and horizontal projections. We extract features from the separated face image using knowledge base of human faces. In the recognition step we use the back propagation algorithm of the neural networks and in the learning step to reduce the computation time we vary learning and momentum rates. Our technique recognizes 6 women and 14 men correctly.

• 한국국방경영분석학회지
• /
• 제35권3호
• /
• pp.139-156
• /
• 2009

본 연구에서는 군 조직 내 지식공유의 확산을 위해 지식공유의 영향요인을 살펴보고 아울러 구성원들의 보안에 대한 태도와 인식이 국방인트라넷을 통한 실제 지식관련 활동을 하는 데 있어 어떠한 역할을 하는 지에 대해 검증하였다. 분석결과에 따르면 조직 내 신뢰와 컴퓨터에 대한 자기효능감이 지식공유의도를 높이는 영향요인으로 작용하였으며 조직구성원들의 보안에 대한 태도가 호의적일 경우 국방인트라넷을 통한 지식관련활동이 더 강화되는 결과를 도출하였다. 이에 따라 군 조직에서는 지식공유 확산을 위해 조직 및 제도적 측면에 대한 노력과 구성원들의 보안에 대한 태도를 호의적으로 유도하려는 노력이 필요하다.

• 한국음향학회지
• /
• 제18권5호
• /
• pp.44-51
• /
• 1999

본 논문에서는 음성과 자연언어의 통합처리를 위한 효과적인 병렬계산모델을 제안한다. 음소모델은 연속 Hidden Markov Model(HMM)에 기반을 둔 문맥종속형 음소를 사용하며, 언어모델은 지식베이스를 기반으로 한다. 또한 지식베이스를 구성하기 위해 계층구조의 semantic network과 병렬 marker-passing을 추론 메카니즘으로 쓰는 memory-based parsing 기술을 사용한다. 본 연구의 병렬 음성인식 알고리즘은 분산메모리 MIMD(Multiple Instruction Multiple Data) 구조의 다중 Transputer 시스템을 이용하여 구현되었다. 실험결과, 본 연구의 지식베이스 기반 음성인식 시스템의 인식률이 word network 기반 음성인식 시스템보다 높게 나타났으며 code-phoneme 통계정보를 활용하여 인식성능의 향상도 얻을 수 있었다. 또한, 성능향상도(speedup) 관련 실험들을 통하여 병렬 음성인식 시스템의 실시간 구현 가능성을 확인하였다.

• 디지털융복합연구
• /
• 제18권2호
• /
• pp.151-162
• /
• 2020

본 연구의 목적은 중국 사용자들을 대상으로 온라인 지식 콘텐츠의 구매의도에 영향을 미치는 요인을 살펴보기 위함이다. 연구모형은 선행연구를 통해서 온라인 지식 콘텐츠 특성, 저작권 및 유료화 인식, 계획된 행동이론 변인, 구매의도 변수를 제시하였다. 설문조사를 통해서 최종 457부를 수집하였으며 SPSS 25.0과 AMOS 23.0을 이용하여 제시한 연구가설을 검증하였다. 연구결과에 의하면 온라인 지식 콘텐츠 특성은 태도에 부분적으로 영향을 미치는 것으로 나타났다. 또한, 유료화 인식과 계획된 행동이론 변인들은 구매의도에 긍정적인 영향을 있는 것으로 나타났다. 그리고, 이러한 연구결과를 활용한 온라인 지식 콘텐츠의 구매의도를 제고하는데 도움이 되는 방안을 제시하였으며, 실무적인 측면에서 유료 지식 콘텐츠의 운영 기업에 대한 시사점을 제시하였다. 또한, 향후 각종 콘텐츠 유료화 관련 후속 연구를 위한 토대를 제공할 것으로 사료된다.

• 동서간호학연구지
• /
• 제17권1호
• /
• pp.9-15
• /
• 2011

Purpose: The purpose of this study was to investigate recognition and knowledge regarding clinical trials, in particular, after a clinical trial education program (CTEP) among student nurses. Methods: A cross-sectional survey design of 215 student nurses at a university in Seoul was used with structured questionnaires. Results: Respondents had a high level of need for clinical trial and moderate levels in favorable image, safety, and need for education regarding clinical trial. The respondents who had participated in the CTEP felt the clinical trial more favorable and safer than those who did not. However, there were no significant differences in necessity of clinical trials and need for education regarding clinical trial between the CTEP participation and no participation groups. Respondents had a high level of knowledge about clinical trial, even though half of the respondents misunderstood that the physician can convince the subject to participate in clinical trial. There was no significant difference in knowledge level between groups. One third of the respondents had an intention to work in the area related to clinical trial because of aptitude or future prospect. Conclusion: The results of this study demonstrated that the CTEP might have an effect on student nurses' recognition rather than knowledge. The CTEP should be therefore developed targeting specific areas of misconceptions and recognition changes.

• 한국식품조리과학회지
• /
• 제25권6호
• /
• pp.712-724
• /
• 2009

The purpose of this study was to examine the degree of concern about endocrine disruptors, the degree of recognition about the risk of endocrine disruptors towards humans, the degree of worry about the risk of endocrine disruptors towards ones self or family, information-obtaining behavior regarding endocrine disruptors, the degree of knowledge and the degree of behavior to decrease exposure to endocrine disruptors, and the degree of an educational need for endocrine disruptors in the dietary life of elementary school students. The data were collected from 162 students in Seoul, Incheon, Daejeon, Daegu, Busan and Gwangju. Frequencies, Cronbach's alpha, t tests, analysis of variance, Duncan's multiple range tests and chi-square tests were conducted using SPSS V.14.0 for WINDOWS. The results of this study were as follows. The degree of concern about endocrine disruptors was not high. The respondents obtained most of their information regarding endocrine disruptors from TV/radio. Respondents had difficulty in acquiring and understanding the information. Both the degree of knowledge and the degree of behavior to decrease exposure were not high. The respondents showed a high degree of educational need for endocrine disruptors, the most important was methods to prevent damage from endocrine disruptors followed by risk of endocrine disruptors.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2003년도 ISIS 2003
• /
• pp.480-483
• /
• 2003

We propose a new framework that aims at multi-purpose image recognition, a difficult task for the conventional rule-based systems. This framework is farmed based on the idea of computer-based learning algorithm. In this research, we introduce the new functions of an additional learning and a knowledge reconstruction on the Fuzzy Inference Neural Network (FINN) (1) to enable the system to accommodate new objects and enhance the accuracy as necessary. We examine the capability of the proposed framework using two examples. The first one is the capital letter recognition task from UCI machine learning repository to estimate the effectiveness of the framework itself, Even though the whole training data was not given in advance, the proposed framework operated with a small loss of accuracy by introducing functions of the additional learning and the knowledge reconstruction. The other is the scenery image recognition. We confirmed that the proposed framework could recognize images with high accuracy and accommodate new object recursively.