• 산업공학
• /
• 제10권2호
• /
• pp.79-90
• /
• 1997

Documents in a traditional PDM(Product Data Management) system have been managed in a form of scanned document files or electronic documents developed by specific tools. Though each tool manages documents with its own systematical methods, it has drawbacks in data search, data integration and interchange, etc. For this reason, in this research we propose an efficient document management system for PDM by using the SGML(Standard Generalized Markup Language), one of CALS and ISO standards for document interchanges. Among documents to be managed in PDM, the engineering change notification (ECN) is taken into account. The DTD (Document Type Definition) has been constucted based on the logical analysis of the documents format, In addition, based on the DTD, DB classes have been designed by object-oriented paradigms and a prototype for document input/output and search has been developed using UniSQL ORDBMS (Object-Relational DBMS) and PowerBuilder under the client/server environment.

• Management Science and Financial Engineering
• /
• 제2권1호
• /
• pp.147-176
• /
• 1996

The main objective of this study is to uncover the differences in the programming behavior between methodology creators and methodology users. We conducted an experiment with methodology creators who have invented one of the major object-oriented methodologies and with professional programmers who have used the same methodology for their software-development projects. In order to explain the difference between the two groups, we propose a theoretical framework that views programming as search in four problem spaces: representation, rule, instance and paradigm spaces. The main problem spaces in programming are the representation and rule spaces, while the paradigm and instance spaces are the supporting spaces. The results of the experiment showed that the methodology creators mostly adopted the paradigm space as their supporting space, while the methodology users chose the instance space as their supporting space. This difference in terms of the supporting space leads to different search behaviors in the main problem spaces, which in turn resulted in different final programs and performance.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.89-92
• /
• 1996

In this paper, we developed visual tracking algorithm using double active bar. The active bar model to represent the object can reduce the search space of energy surface and better performance than those of snake model. However, the contour will not find global equilibrium when driving force caused by image may be weak. To overcome this problem. Double active bar is proposed for finding the global minimum point without any dependence on initialization. To achieve the goal, an deformable model with two initial contours in attempted to search for a global minimum within two specific initial contours. This approach improve the performance of finding the contour of target. To evaluate the performance, some experiments are executed. We can achieved the good result for tracking a object on noisy image.

• 전자공학회논문지C
• /
• 제34C권10호
• /
• pp.89-97
• /
• 1997

Because a map consists of many lines, a process of recognizing an object in a map is one to group lines that are consistent with the structure of the object. Therefore, it is important to establish an efficient method for finding lines which constitute objects. In this paper, a novel method for recognizing roads and districts in a land register map is proposed. In this method, lines that constitute objects are searched in a reduced search space by defining some relations between lines, and objects are recognized by using the structural information of the objects. As a result, the search space is reduced effetively, and even objects that embody the broken lines and the crossed lines are recognized.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2008년도 제38차 하계학술발표논문집 16권1호
• /
• pp.33-38
• /
• 2008

최근 컴퓨터비전이나 로봇 공학 분야에서 가격이 저렴한 웹캠을 이용한 영상, 즉 2차원 영상으로부터 물체를 인식하는 연구가 활발히 이루어지고 있다. 이러한 로봇이나 비전에서 물체를 찾아내는 여러 가지 방향들이 제시되고 있으며, 지속적으로 로봇은 사람과 유사해져가고 있다. 이를 실현하기 위해서는 사람이 사과를 보고 사과라고 알기 때문에 사과라고 인식하듯이 로봇 또한 미리 알고 있어야 한다는 가정 하에 내용기반의 물체인식이 필요하다. 그러나 엄청난 양의 내용의 데이터베이스가 필요하다. 그래서 용량은 하드웨어기술로 커버가 가능하지만 화면상에 있는 물체들을 빠르게 데이터베이스상의 자료와 매칭이 되어야한다. 본 논문에서는 이미지를 SIFT(Scale Invariant Feature Transform)알고리즘으로 BTS(Binary Search Tree)로 트리구조의 데이터베이스를 구축하여 많은 양의 데이터베이스 중 빠르게 검색하여 화면에 있는 물체를 인식하는 방법을 제안하였다.

• 한국어교육
• /
• 제23권1호
• /
• pp.25-45
• /
• 2012

The purpose of this article is to examine types and construction method of multimedia materials for the Korean language education, finally in order to construct digital library on Nuri-Sejonghakdang. Firstly, this article reviews some major concepts such as teaching material, multimedia, learning object, meta-data, reusability, etc. Secondly, various multimedia materials are divided into three types(namely, example material, explanation material, training and evaluating material) according to their characteristics as a learning objects. And then, this article tries to propose the classification-search system and meta-data elements for effective search and use of multimedia materials. Finally, this article is concluded by presenting the long-term plan of digital library construction on Nuri-Sejonghakdang and some follow-up task of this study.

• 한국컴퓨터정보학회:학술대회논문집
• /
• 한국컴퓨터정보학회 2023년도 제68차 하계학술대회논문집 31권2호
• /
• pp.685-687
• /
• 2023

최근에 이르러 인공신경망의 발전은 CNN(Convolutional Neural Network) 알고리즘을 활용한 이미지 분석 및 검색 시스템에 비약적인 기여를 하고 있다. 이는 이미지를 입력으로 받아 유사한 이미지를 찾아내는 기능을 향상시키는 연구를 촉진시켰다. 이와 같은 기술의 실용화는 다양한 분야를 포괄하며, 대표적으로 쇼핑몰의 상품검색, 검색 엔진 등에 응용되어 사용자의 편의를 제고하고 있다. 이에 따라 상품명에 대한 정보가 없는 상황에서도 단순한 이미지 정보를 통해 원하는 상품을 검색하는 것이 가능해졌다. 그러나, 실제 세계의 이미지에는 다양한 객체들이 복잡하게 혼재하고 있어 CNN 알고리즘 단독으로는 이미지 내부의 객체를 정확히 분석하고, 그 객체가 포함된 다른 이미지들을 효과적으로 검색하는데 한계가 있음이 인지되고 있다. 본 연구는 이러한 문제점을 개선하기 위해 객체 탐지 알고리즘을 적용하는 방안을 모색하였다. 본 논문에서는 객체 탐지 알고리즘을 통해 이미지 내부의 객체를 분석하고, 그에 따른 유사 객체를 포함하는 이미지를 찾아내는 전략을 제시한다. 이를 통해 이미지 분석 및 검색의 정확성을 더욱 향상시킬 수 있는 가능성을 제안한다.

• 로봇학회논문지
• /
• 제19권2호
• /
• pp.196-202
• /
• 2024

The ability to understand given environments and plan a sequence of actions leading to goal state is crucial for personal service robots. With recent advancements in deep learning, numerous studies have proposed methods for state representation in planning. However, previous works lack explicit information about relationships between objects when the state observation is converted to a single visual embedding containing all state information. In this paper, we introduce graph-based state representation that incorporates both object and relationship features. To leverage these advantages in addressing the task planning problem, we propose a Graph Neural Network (GNN)-based subgoal prediction model. This model can extract rich information about object and their interconnected relationships from given state graph. Moreover, a search-based algorithm is integrated with pre-trained subgoal prediction model and state transition module to explore diverse states and find proper sequence of subgoals. The proposed method is trained with synthetic task dataset collected in simulation environment, demonstrating a higher success rate with fewer additional searches compared to baseline methods.

• Management Science and Financial Engineering
• /
• 제10권2호
• /
• pp.1-28
• /
• 2004

The integrated supply chain of business partners for e-Commerce in cyber space is defined as Logistics Chain if the cooperative activities are logistics-related. Logistics Chain could be managed effectively and efficiently by cooperative technologies of logistics chain execution. In this paper, we propose a routing and scheduling algorithm based on the Tabu search by adding geographical information into existing constraint for pick-up and delivery process to minimize service time and cost in logistics chain. And, we also consider an uncertainty processing for the tracing of moving object to control pick-up and delivery vehicles based on GPS/GIS/ITS. Uncertainty processing is required to minimize amount of telecommunication and database on vehicles tracing. Finally, we describe the Logistics Chain Execution (LCE) system to perform plan and control activities for postal logistics chain. To evaluate practical effects of the routing and scheduling system, we perform a pretest for the performance of the tabu search algorithm. And then we compare our result with the result of the pick-up and delivery routing plan generated manually by postmen.

• 한국공간정보시스템학회 논문지
• /
• 제11권4호
• /
• pp.85-88
• /
• 2009

멀티미디어 시스템에서 최대근접질의는 매우 빈번히 발생하며, 다른 유형의 공간질의에 비하여 처리비용이 많이 요구된다. 최대근접질의의 처리비용을 최적화하기 위해서는 색인에서 검색되는 노드의 수와 연산시간을 최소화할 수 있는 검색거리 측도가 필요하다. 또한 최대근접질의에 따른 검색 노드들을 정확히 선택하기 위해서는 객체들의 순환적 위치 속성을 고려해야 한다. 본 논문은 순환도메인을 갖는 검색공간에서 객체의 순환적 위치속성을 고려한 최대근접질의 처리방법을 제안하고 그 특성을 보인다. 제안한 방법은 최대근접질의의 처리비용을 최적화하기 위한 검색거리 측도인 순환최소거리와 순환최적거리를 사용한다.