• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 1995년도 추계학술대회 논문집
• /
• pp.687-690
• /
• 1995

The configuration of design technology in 21st century must require collaborative design system, in which distributed design organizations and their related enterprises can mutually cooperate by overcoming time and regional restictions, and by exactily exchanging and sharing desing data. To achieve these objectives, it is necessary that the design system can propery deal with the dynamic change between regionally distributed modules. In this paper, we will discuss developing the dynamic virtual collaborative design system based on WWW by implementing recent web technologies such as Java and VRML.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2007년도 춘계학술발표대회
• /
• pp.14-15
• /
• 2007

Now-a-days, data and task migration in collaborative work provides enormous facilities to users. Here, we propose an ontology-based information management scheme to facilitate data and task migration in collaborative work. This ontologybased model will help us to organize huge information (e.g. device status, runtime state etc.) efficiently.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2004년도 춘계학술대회 논문요약집
• /
• pp.227-227
• /
• 2004

오늘날과 같은 무한 경쟁 시대 속에서 기업은 신제품을 좋은 품질을 유지하면서 얼마나 빠르게 시장에 출시하느냐가 기업의 경쟁력을 좌우하게 되었다. 이를 위해서는 설계 단계부터 제품 생산 단계까지의 주기를 단축시켜야만 한다. 이 때 설계 단계의 비용이 가장 크며 많은 시간이 소비된다 물론, 품질에 가장 커다란 영향을 미치는 부분도 바로 설계 단계인 것은 두말할 필요가 없을 것이다. 이에 본 논문에서는 제품 개발에서 중요한 설계 단계를 CPC(Collaborative Product Commerce) 개념을 도입하여 웹에 기반을 둔 설계 지원 시스템을 구축하였다.(중략)

• 산업공학
• /
• 제19권1호
• /
• pp.70-77
• /
• 2006

One of the problems in developing a collaborative recommendation system is the scalability. To alleviate the scalability problem efficiently, enhancing the performance of the recommendation system, we propose a new recommendation system using feature selection. In our experiments, the proposed system using about a third of all features shows the comparable performances when compared with using all features in light of precision, recall and number of computations, as the number of users and products increases.

• Current Optics and Photonics
• /
• 제4권3호
• /
• pp.210-220
• /
• 2020

Aiming at the problem that the Local Sparse Difference Index algorithm has low accuracy and low efficiency when detecting target anomalies in a hyperspectral image, this paper proposes a Weighted Collaborative Representation and Sparse Difference-Based Hyperspectral Anomaly Detection algorithm, to improve detection accuracy for a hyperspectral image. First, the band subspace is divided according to the band correlation coefficient, which avoids the situation in which there are multiple solutions of the sparse coefficient vector caused by too many bands. Then, the appropriate double-window model is selected, and the background dictionary constructed and weighted according to Euclidean distance, which reduces the influence of mixing anomalous components of the background on the solution of the sparse coefficient vector. Finally, the sparse coefficient vector is solved by the collaborative representation method, and the sparse difference index is calculated to complete the anomaly detection. To prove the effectiveness, the proposed algorithm is compared with the RX, LRX, and LSD algorithms in simulating and analyzing two AVIRIS hyperspectral images. The results show that the proposed algorithm has higher accuracy and a lower false-alarm rate, and yields better results.

• 지능정보연구
• /
• 제14권1호
• /
• pp.101-115
• /
• 2008

일반적으로 혼합 추천 시스템(hybrid recommender system)이란 협업적 여과 방법(collaborative filtering)을 다른 기술들과 결합하여 사용하여 사용자가 원하는 정보를 손쉽게 찾을 수 있도록 도와주는 시스템이다. 협업적 여과 방법과 결합된 혼합 시스템은 대체로 내용이 유사한 아이템들이 추천 되어 전반적인 아이템 추천 성능 및 새로이 추가된 아이템에 대한 추천의 질이 떨어지는 문제가 있다. 이러한 문제를 해결하기 위해, 본 논문에서는 다양성(diversity)을 고려한 새로운 혼합 추천 시스템을 제안한다. 제안된 시스템에서는 첫 번째 단계로 협업적 여과 방법으로부터 추천된 아이템들 간의 비유사도를 측정한다. 두 번째 단계로는 첫 번째 단계에선 추천된 비유사도가 높은 아이템들을 내용 기반의 여과 방법(content-based filtering)에 적용하여 새로운 아이템에 대한 추천 성능을 향상 시킨다. 제안된 방법의 성능 평가를 위해 movielens 데이터를 이용하여 기존의 내용기반 추천 시스템 및 단순 혼합 시스템과 비교 평가하였다. 실험 결과 제안된 방법이 내용기반 추천 시스템 및 단순 혼합시스템보다 높은 추천 성능을 보였다.

• Journal of Ship and Ocean Technology
• /
• 제8권4호
• /
• pp.45-55
• /
• 2004

How to achieve engineering collaboration among diverse engineering activities is one of the key topics in manufacturing fields nowadays. The infrastructure for collaborative engineering is essential, and it can be realized by information technologies and intelligent engineering applications in digital environments. Digital Manufacturing is a technology to facilitate effective product developments and agile productions by computer models representing the physical and logical schema and the behavior of real manufacturing systems including products, processes and factories. A digital factory as a well-designed and integrated digital environment is incorporated in it. In this paper, digital manufacturing is recommended as a good strategy for collaborative engineering, especially in product developments and productions. By business process analysis and some case studies, we suggested sophisticated digital models are very useful to concurrent and collaborative engineering. It is expected that digital manufacturing is a very good strategy for achieving dramatic time and cost savings in many engineering activities of many manufacturing industries, including machinery, automotive and shipbuilding.

• 지능정보연구
• /
• 제14권2호
• /
• pp.157-177
• /
• 2008

최근 웹 2.0의 영향으로 태깅을 지원하는 인터넷 서비스들이 많아졌다. 태깅의 원래 목적은 컨텐츠를 분류하고 재검색을 용이하게 하는 것이지만, 컨텐츠에 태깅되어 있는 태그들을 분석하여 컨텐츠의 특성을 파악할 수 있다. 본 논문에서는 내용 파악이 힘든 컨텐츠들이 증가함에 따라 이러한 컨텐츠들의 효과적인 추천을 위해, 여러 사용자들에 의해 협업적으로 태깅된 정보를 이용한 여과 기법을 제시한다. 제안하는 방법은 사용자가 태깅한 정보들을 바탕으로 사용자의 관심을 파악하는 부분과 파악된 관심에 맞는 컨텐츠를 선별하는 부분으로 나뉘어진다. 사용자의 관심을 파악하는 부분은 사용자가 태깅한 정보들을 협업적 여과를 이용하고, 컨텐츠 선별은 확률적인 방법인 나이브 베이지안 분류자를 이용한다. 이를 통해 협업적 여과 방법의 문제점인 희박성 문제(sparsity problem)와 초기 사용자 문제(cold-start user probleam) 대해 기존의 방법들과 비교하여 그 효과를 보인다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2006년도 춘계학술대회 논문집
• /
• pp.599-600
• /
• 2006

In order to promptly cope with the various requirements of consumers, the environment of product development is being globalized in manufacturing industrials. For this reason, it is necessary to build up an efficient collaborative system for communication between remote area designers. Specially, while Internet and information technologies were merged with the manufacturing or business process, the research for collaborative system has become an important issue. Therefore, we propose a Web-based Engineering Collaboration Framework using SPS(SharePoint Portal Server) which is an enterprise business solution that integrates information from various system into one solution through single sign-on and enterprise application integration capabilities, with flexible deployment options and management tool. Through a Web-based Engineering Collaboration Framework, designers can share knowledge assets and have a remote conference with others via web.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2005년도 춘계학술대회 논문집
• /
• pp.987-992
• /
• 2005

Manufacturing companies should perform process planning and its evaluation concurrently with new product developments so that they can be highly competitive in the modern market. Process planners should make decisions in the manner of concurrent and collaborative engineering in order to reduce the manufacturing preparation time and cost when developing new products. Automated generation of analysis models from the integrated database, which contains process and material information, reduces time to prepare analyses and makes the models reliable. In this research, we developed a web-based system for concurrent and collaborative system for production flow analysis, using web, database, and simulation technology. An integrated database is designed to automatically generate analysis models from process and material plans without reworking the data. This system enables process planners to evaluate their decision fast and share their opinions with others easily. With this system, it is possible to save time and cost for assembly process and material planning, and reliability of process plans can be improved