• 한국지능시스템학회논문지
• /
• 제23권5호
• /
• pp.400-405
• /
• 2013

The purpose of this study is to develop a composite platform for knowledge extractions, visualizations, and inference. Generally, the big data sets were frequently used in the healthcare and medical area. To help the knowledge managers/users working in the field, this study is focused on knowledge management (KM) based on Data Mining (DM), Knowledge Distribution Map (KDM), Decision Tree (DT), RDBMS, and SQL-inference. The proposed mechanism is composed of five key processes. Firstly, in Knowledge Parsing, it extracts logical rules from a big data set by using DM technology. Then it transforms the rules into RDB tables. Secondly, through Knowledge Maintenance, it refines and manages the knowledge to be ready for the computing of knowledge distributions. Thirdly, in Knowledge Distribution process, we can see the knowledge distributions by using the DT mechanism.Fourthly, in Knowledge Hierarchy, the platform shows the hierarchy of the knowledge. Finally, in Inference, it deduce the conclusions by using the given facts and data.This approach presents the advantages of diversity in knowledge representations and inference to improve the quality of computer-based medical diagnosis.

• 한국CDE학회논문집
• /
• 제19권1호
• /
• pp.61-67
• /
• 2014

This paper proposes a procedure enabling the extraction of view-dependent triangular approximations from a height map. In general, procedures to approximate a height map use tree hierarchies. These methods, however, have a limitation in terms of accuracy, because they depend on tree hierarchy than terrain features. To overcome the difficult, we apply the simplification method for triangular meshes to a height map. The proposed procedure maintains full decimation procedure to support multiresolution. The maintenance of decimation procedure results in creation of the groups (trees), each of which consists of vertices that can be merged into one vertex (root node). As the groups have tolerance which is determined by some tests, they support the generation of view-dependent arbitrary triangular meshes.

• 한국안전학회지
• /
• 제23권6호
• /
• pp.7-13
• /
• 2008

It is important to prevent roll failure in hot rolling process for reducing maintenance cost and production loss. The relationship between rolling pass schedule and the work roll wear profile will be presented. The roll wear pattern is related with roll catastrophic failure. The irregular and deep roll wear pattern should be removed by On-line Roll Grinder(ORG) for roll failure prevention. In this study, a computer roll wear prediction model under real process working condition is developed and evaluated with hot rolling pass schedule. The method of building wear calculation functions for center portion abrasion and marginal abrasion respectively was used to develop a work roll wear prediction mathematical model. The three type rolling schedule are evaluated by wear prediction model. The optimum roll grinding methods is suggested for schedule tree rolling technique.

• 한국조경학회지
• /
• 제15권3호
• /
• pp.1-10
• /
• 1988

The initial selection of plants is the decisive step in the ultimate success of any landscape planting. This study intended to establish a reasonable selecting criteria of tree in the landscape through the holistic consideration of aesthetic, functional, cultural, operational and ecological viewpoints. The matrices of evaluating the fitness of tree were modulated to 10 categories ; availability from the established nursery. aesthetic value, indigenous to the locality, maintenance, soil fertility requirement, environmental tolerances. growth rate. wild-life food production. use of plants in design and user's likes. This 10 categories were weighted to their fitness as high(10 points), medium(8 points) and low(5points). Thus suitable plants were identified which got 70 more points from total 100 points. Such a method was believed as a rational process to get trust from client. to persuade uneducated client and to be free from designer's prejudice through a case study. But it is important to landscape designer to recognize the relationship between the rationality which prevails throughout the modern technical world and the intuitive aspects of design that are essential for developing creative solutions to encourage creativity as well as analytical responsibility.

• 정보보호학회논문지
• /
• 제27권4호
• /
• pp.981-987
• /
• 2017

클라우드 컴퓨팅의 대중화로 개인 및 기업의 로컬 저장소에서 관리되던 데이터가 클라우드 스토리지 등 제 3의 공간에 아웃소싱 되면서 유지, 관리 비용의 절감 효과를 얻을 수 있게 됨과 동시에, 다수의 원격저장 서비스 제공자는 공간 자원의 효율화를 위하여 아웃소싱된 데이터의 중복제거 기법을 도입하고 있다. 동일 데이터의 중복성 판단에 해시 트리가 사용되는 경우에는 검증 데이터의 크기 및 트리의 일부 정보에 대한 부채널이 존재하게 되는데, 이로부터 특정 데이터에 대한 정보 수집 및 검증의 우회 가능성이 증가하게 된다. 이러한 부채널로 인한 검증의 유효성 문제를 개선하기 위하여, 본 논문에서는 멀티 셋 해시함수를 이용한 동일성 검증 기법을 제시한다.

• Journal of Platform Technology
• /
• 제6권3호
• /
• pp.47-54
• /
• 2018

하드웨어 산업에서의 예측 분석은 생산설비의 고장을 방지하기 위해 적절한 시점에 유지보수를 수행할 수 있고 관리비용을 절감할 수 있다. 이는 고장원인분석의 자동화를 통해 보다 효율적이고 과학적인 유지보수를 수행할 수 있도록 도와준다. 그중에서도 예측 관리는 정보 기술을 활용하여 설비 상태의 수집, 분석, 과학적 데이터 관리를 통해 예측 모델을 구성하며, 이를 바탕으로 이상상태를 파악하고 개선함으로써 이상상태가 발생하는 것을 사전에 예방하는 것을 목적으로 한다. 본 연구에서는 Relex 도구를 통해 결함트리(Fault Tree)를 만들고 하드웨어들의 에러코드를 분석하여 안전성을 연구했다.

• 디지털콘텐츠학회 논문지
• /
• 제18권1호
• /
• pp.191-195
• /
• 2017

본 연구에서는 우리나라의 대표수종 소나무의 치명적인 해충인 소나무재선충 피해목의 확산을 조기에 차단하고 산림수목에 대한 지속적인 관리를 위하여 소나무재선충 피해수목 신고 어플리케이션을 개발하였다. 어플리케이션은 다음과 같이 3개 핵심항목을 중심으로 개발되었다. 첫째, 소나무재선충에 대한 정보제공, 둘째, 피해목의 자가진단, 셋째, 수목안전지도 등으로 구성하였다. 향후 본 어플리케이션의 활성화를 위해서 실제로 어플리케이션을 사용하는 이용자들의 적극적인 참여와 산림청 어플리케이션과의 통합개발이 이뤄진다면 보다 많은 활용이 가능할 것이다.

• 산업경영시스템학회지
• /
• 제4권4호
• /
• pp.63-69
• /
• 1981

As enterprises are getting bigger and bigger and more competecious, an engineering economy for the maximization of profit based on basic theory must be considered. This thesis present dynamic computer model for the decision which controls complicated and various man- machine system optimally. This model occur in general stage can be adaptable to every kind of enterprises. So, any one who has no expert knowledge is able to get the optimal solution. And decision tree used in this paper can be applied in every kinds of academic circles as well as whole the industrial world. This paper studied optimal management of engineering project based upon basic theory of engineering economy. It introduces and functionizes the variables which generalize every possible elements, set up a model in order to find out the variable which maximize the calculated value among many other variables. And the selected values ate used as decision- marking variables for the optimal management of engineering projects. It found out some problem of this model. They are : 1. In some kinds of man-machine system it refers to Probability, but other case, it depends on only experimental probability. 2. Unless decision making process (decision tree) goes on, this model can not be applied. So these cases, this paper says, can be solved by adapting finite decision tree which is analyzed by using the same technic as those in product introduction problem. And this paper set up the computer model in order to control every procedure quickly and optimally, using Fortran IV.

• 인간식물환경학회지
• /
• 제24권1호
• /
• pp.85-94
• /
• 2021

Background and objective: This study examined, compared, and analyzed the tree vitality of the trees growing on the artificial ground of Seoullo 7017 that transformed the overpass that was to be demolished into a "sky garden" using portable tree pots. Methods: Based on the summer season when the metabolic activity of plants is most active, this study measured the cambial electrical resistance in four directions(east, west, south and north), using the Shigometer (model OZ-93, Osmose) and compared the location and analysis of pots according to their means and standard errors. Results: Meanwhile, according to the analysis, vitality was relatively superior in pots with a big diameter, trees planted individually than in groups, trees of the ramp section rather than the bridge section, and in the southwest direction of the cambium. Conclusion: This study revealed the improper condition of the planting plan and implementation on the site, where various species of trees are displayed in a poor environment. Despite the significant assessment of the vitality of various trees introduced within Seoullo 7017 for the first time, this study is limited in that the data used were measured only once in summer. In this regard, it raised the need for continuous interest in and monitoring of a special plant environment and development of proper maintenance and management techniques, along with follow-up research on seasonal and temperature conditions, soil moisture and root development conditions to supplement this research.

• 한국항해항만학회:학술대회논문집
• /
• 한국항해항만학회 2019년도 춘계학술대회
• /
• pp.230-231
• /
• 2019

본 연구에서는 미래의 자율운항선박의 핵심기술인 상태기반 예지보전(Condition Based Maintenance, CBM) 기술에 관한 연구로써 고장진단을 위한 실 운항선박을 대상으로 상태 모니터링 시스템의 설계/탑재 및 데이터 취득/처리/분석 기술 개발을 수행하고 있다. 본 연구의 목적은 데이터 확보, 유효데이터 식별/검증을 통해 최종적인 고장진단 알고리즘 개발을 위함이며 이를 위해서는 대상 기기의 고장 메커니즘에 관한 이해가 필요하다. 따라서 선박 엔진의 FEMA 분석과 Fault Tree Analysis 과정이 수반되어야 하며 엔진의 주요 계통분류, 대상기기 식별, 고장유형, 고장원인과 현상에 대한 분석을 포함하여야 한다. 최종적으로 도출되는 CBM 시스템의 솔루션 S/W는 엔지니어링 지식기반의 실선 운항데이터에 대한 통합적인 데이터 분석을 통해 선박 엔진의 고장예측 및 진단이 가능하다. 본 연구를 통해 운항중인 실선의주 기관을 대상으로 기존 모니터링 항목 이외의 핵심 영향인자를 측정하고, 취득된 데이터에 대한 빅 데이터 분석기법을 통해 적절한 유지보수 방법과 해당 시점을 예측함으로써 향후 선박 엔진의 이상 징후에 대한 사전적 대처와 효율적인 관리가 가능하며 결과적으로 항해 중 해양사고 및 선박운항 손실을 미연에 방지할 수 있을 것으로 기대한다.