• Title/Summary/Keyword: 지식

Search Result 19,762, Processing Time 0.039 seconds

Intelligent integration of Ontology and Multi-agents Coordination Mechanism in Ubiquitous Decision Support System Portal (유비쿼터스 환경에서 다중 의사결정지원을 위한 지능형 온톨로지 통합 및 다중에이전트 관리 시스템 : u-Fulfillment 도메인 중심)

  • Lee, Hyun-Jung;Lee, Kun-Chang;Sohn, M-Ye M.
    • Journal of Intelligence and Information Systems
    • /
    • v.14 no.1
    • /
    • pp.47-66
    • /
    • 2008
  • This study is aimed at proposing a new type of ubiquitous decision support system (u-DSS) portal which is embedded with two important mechanisms like an intelligent ontology management module (i-OMM) and multi-agent coordination mechanism (MACM). The proposed portal provides timely decision support to the involved decision entities (represented as agents) by taking advantage of the two mechanisms embedded on the portal. The most important virtue of the proposed portal is that it can resolve two problems such as semantic discordance and data confliction which are occurring very often in an ubiquitous computing environment. Frequent requests of revising the already established decision information due to the rapid changes in decision entities' requirements require the extremely flexible and intelligent u-DSS vehicle like theproposed mechanism. In this sense, the i-OMM is designed to provide support to solving the semantic discordance in the way that the i-OMM virtually integrates ontology view (IOV) to integrate heterogeneous ontology among the agents engaged inubiquitous commerce situations. Then the i-OMM sends the IOV to the MACM to resolve the conflicts among the involved agents. The proposed u-DSS portal was applied to the u-fulfillment problem in which all the involved decisionagents need their own requirements to be satisfied seamlessly and timely. The experimental results show that the proposed u-DSS portal is very robust and promising in the field of u-DSS and context modeling.

  • PDF

Impact of Ensemble Member Size on Confidence-based Selection in Bankruptcy Prediction (부도예측을 위한 확신 기반의 선택 접근법에서 앙상블 멤버 사이즈의 영향에 관한 연구)

  • Kim, Na-Ra;Shin, Kyung-Shik;Ahn, Hyunchul
    • Journal of Intelligence and Information Systems
    • /
    • v.19 no.2
    • /
    • pp.55-71
    • /
    • 2013
  • The prediction model is the main factor affecting the performance of a knowledge-based system for bankruptcy prediction. Earlier studies on prediction modeling have focused on the building of a single best model using statistical and artificial intelligence techniques. However, since the mid-1980s, integration of multiple techniques (hybrid techniques) and, by extension, combinations of the outputs of several models (ensemble techniques) have, according to the experimental results, generally outperformed individual models. An ensemble is a technique that constructs a set of multiple models, combines their outputs, and produces one final prediction. The way in which the outputs of ensemble members are combined is one of the important issues affecting prediction accuracy. A variety of combination schemes have been proposed in order to improve prediction performance in ensembles. Each combination scheme has advantages and limitations, and can be influenced by domain and circumstance. Accordingly, decisions on the most appropriate combination scheme in a given domain and contingency are very difficult. This paper proposes a confidence-based selection approach as part of an ensemble bankruptcy-prediction scheme that can measure unified confidence, even if ensemble members produce different types of continuous-valued outputs. The present experimental results show that when varying the number of models to combine, according to the creation type of ensemble members, the proposed combination method offers the best performance in the ensemble having the largest number of models, even when compared with the methods most often employed in bankruptcy prediction.

인터넷 기반 원스톱서비스 시스템 개발에 관한 연구+ -수출컨테이너화물 원스톱서비스 시스템 개발-

  • 박남규;최형림;김현수;박영재;조재형;이철우
    • Proceedings of the Korean Institute of Navigation and Port Research Conference
    • /
    • 1999.10a
    • /
    • pp.299-308
    • /
    • 1999
  • 오늘날 우리 나라가 당면한 최우선 경제과제중 하나는 물류부분의 혁신을 통한 국가경쟁력 강화라고 할 수 있으며, 이를 위해 정부도 1993년 물류체계 개선을 위한 장기구상으로 ‘화물유통체계 개선 10개년 기본계획’을 수립하여 적극 추진 중에 있다. 그러나 이러한 노력에도 불구하고 PORT-MIS사용자를 상대로 한 설문조사에서는 선박입출항 업무 관련 서류의 40%, 항만시설 사용 업무와 관련된 서류의 31%, 하역업무 관련 서류의 10%만이 EDI를 활용하고 있었다. EDI 활용이 저조한 사유로는 전송시간이 많이 걸리며, EDI 소프트웨어가 작동되지 않으며, 수신확인이 되지 않기 때문이라 응답을 하였다. 이처럼 오늘날 항만물류산업이 겪고 있는 물류 데이터 흐름이 단절적 현상은 시간이 흐를수록 해결 될 기미가 보이고 있지 않다. 따라서 본 논문에서는 우리 나라가 겪고 있는 물류관련 업무를 한번의 데이터 입력으로 해결할 수 있는 원스톱 서비스 시스템개발을 목표로 우선 PORT-MIS EDI 업무를 처리할 수 있는 시스템을 구축하였다. 이는 향후 화주, 운송사, 선사, 포워더, 창고업자,하역회사, 철도청, 화물터미널, 컨테이너 터미널, 해양수산청, 관세청, 출입국관리사무소, 검역소 사이에 서로 교환되는 적하목록, Booking List, 컨테이너 Pick up정보, 위험물 정보, COPINO 정보를 비롯하여 대 관세청 신고 등 수출컨테이너 화물업무의 전반적인 영역으로까지 쉽게 확대할 수 있을 것이다. 본 연구결과 구축된 시스템은 원천정보를 중앙의 통합데이터베이스에 저장하여 이를 사용자의 요구에 의해 인터넷을 통해 전달하는 FTP와 웹 EDI 방식을 결합한 하이브리드 형태이다.CS Cell 방식에 의한 위치결정방식을 채택하였는데, 이것은 PCS망을 기반으로 데이터를 주고받이며 인터넷 단말기로 확장 가능한 PCS 단말기를 사용해서 위치추적을 하는 시스템이다. 이러한 시스템을 선정하게된 배경은 단말기아 망 이용료의 가격이 저렴하여 현실적으로 트럭이 쉽게 부착할 수 있다는 장점이 있으며 나아가 인터넷 단말기를 활용하여 차량과 관제센터사이에 메시지 전송 등 부가적인 서비스가 가능하기 때문이다.비교한 결과 토사 유출 억제효과는 한지형과 나지형잔디들의 혼합형(MixtureIII)과 자생처리구(MixtureV), Italian ryegrass와 자생식물의 혼합형(MixtureIV)등에서 비교적 낮은 수치를 토사유출량을 기록하였다. 이러한 결과는 자생식물들이 비록 초기생육속도는 외래도입초종에 떨어지지만 토사유출의 억제효과면에서는 이들 외래초종에 필적할 수 있음을 나타낸다고 할 수 있겠다.중량이 약 115kg/$m^2$정도로 나타났다.소 들(환경의 의미, 사람의 목적과 지식)보다 미학적 경험에 주는 영향이 큰 것으로 나타났으며, 모든 사람들에게 비슷한 미학적 경험을 발생시키는 것 이 밝혀졌다. 다시 말하면 모든 사람들은 그들의 문화적인 국적과 사회적 인 직업의 차이, 목적의 차이, 또한 환경의 의미의 차이에 상관없이 아름다 운 경관(High-beauty landscape)을 주거지나 나들이 장소로서 선호했으며, 아름답다고 평가했다. 반면에, 사람들이 갖고 있는 문화의 차이, 직업의 차 이, 목적의 차이, 그리고 환경의 의미의 차이에 따라 경관의 미학적 평가가 달라진 것으로 나타났다.corner$적 의도에 의한 경관구성의 일면을 확인

  • PDF

Interoperability Framework between GRID and PACS based on Web Services (웹서비스 기반의 Grid-PACS 상호운용성 프레임워크)

  • Lee, Bong-Hwan;Cho, Hyun-Sug
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.14 no.8
    • /
    • pp.1799-1808
    • /
    • 2010
  • Recently the increasing collaborative research requires the remote medical and clinical data sharing and access of external institutions. In this paper, an interoperability framework between Grid and PACS using Web services is proposed and implemented in order to provide flexible and efficient medical data management. The Digital Imaging and Communications in Medicine(DICOM) standard defines medical image data exchange and transfer between PACSs and image databases. However, medical data exchange between hospitals is limited within the trusted and static environments. Moreover, DICOM does not provide medical data management and the Grid middleware does not include standard toolkit to access DICOM data. To address this issue, a Web services-based Grid Service Mediator (WGSM) which provides PACS integration and medical image data management is developed. The WGSM consists of several service mediators such as compress mediator, GridFTP mediator, RFT mediator, MyProxy mediator, MDS mediator, and RLS mediator and others. The proposed Web services-based framework provides user authentication and secure data access between PACSs in collaborative environments. In particular, the WGSM allows ordinary users to access remote PACS data in a simple and efficient manner without any the knowledge about underlying Grid middleware.

Traffic Information Extraction and Application When Utilizing Vehicle GPS Information (차량의 GPS 정보를 활용한 도로정보 추출 및 적용 방법)

  • Lee, Jong-Sung;Jeon, Min-Ho;Cho, Kyoung-Woo;Oh, Chang-Heon
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.17 no.12
    • /
    • pp.2960-2965
    • /
    • 2013
  • Customized services for individuals in analysis of recently collected GPS information have been investigated in various aspects. As the size of collected GPS data gets larger, a variety of services is being released accordingly. Existing studies, however, are limited to presenting service models for users while there is little study on developing intelligent computing technologies in the introduction of GPS information into the system. This study suggests an algorithm to analyze traffic information by introducing GPS information into the system in order to take the lead among intelligent computing technologies. The suggested algorithm analyzes a map by means of the collected vehicle GPS information and sectional traffic information interpretation method; thus, the computer judges the traffic information collected by humans. The experiment result shows that the traffic information was properly analyzed upon the utilization of the given data. Although a small quantity of analyzed data was less reliable, the system maintained high reliability as the data was sufficient.

A Study on a approach of venture management mothodology for improving the profitability of a private music-institute (음악학원의 성과를 위한 벤처경영 접근방식에 관한 연구)

  • Park, Ji-Young
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.16 no.5
    • /
    • pp.3099-3110
    • /
    • 2015
  • Recently, there are so many music school graduates. In addition, there are many private music institutes. For this reason, there is a fierce competition in music education market. In the past, those who worked in music education market earned big money and so many parents wanted their girls and boys to learn playing a piano and other musical instruments. In the recent times, however, birth ratio was reduced dramatically in Korea and parents do not want their children to learn musical instruments due to economic depression and deteriorated music market. Eventually, the size of music education market was diminished dramatically and the competition in music education market is getting fiercer. Therefore, it is difficult to expect good performance in music education market without having an improved management system. In this respect, this study aims to understand what main factors have an impact on business performance in music institutes. The main areas studied in this paper include successful factors, reason why they start up a business, and successful management factors. The survey of this study targeted music institute owners. Based on the surveyed results, for the owners of the music institute, the method of the venture management approach, in other words, the application of the marketing knowledge, the consideration of the company system, the application of the smart technologies, etc., has been presented.

The Design and Development of Online System to Improve Undergraduate Students' Competency (대학생의 역량개발을 위한 온라인 시스템 설계 및 개발)

  • Moon, Yun-Kyoung;Lee, Kyoung-Jae
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.16 no.6
    • /
    • pp.3807-3818
    • /
    • 2015
  • The objective of this study is to develop an on-line system for improving undergraduate students' competency development. After drawing elements necessary for the competency development such as assessment and planning, competency development, analysis of competency assessment, portfolio, analysis of job ability and community, based on the literature research related to competency and the analysis of the existing system, the direction of the system design was set up. The system was developed by using Microsoft Windows operating system in Windows server, ORACLE ver.10 as its database management system, and JSP and JAVA as its programing language. Reviewing errors and improvements of the system, it was modified and complemented. In order to examine the content functional utilization of the final competency development system, the utilization was verified. The competency development system for undergraduate students can be used as on-line space filled with the internalization of knowledge, self-directed competency development, convenience of record management and interactions between students-professors-alumna, owing to its functions such as boosting competency activities, cultivating career-pioneering ability and introspecting. When it is rare to find researches on the competency development system for undergraduate students, it is expected to be helpful to the development of competency education and the career education for undergraduate students as a new alternative for the competency development.

Comparison of Educational Effectiveness Between Instructor-Centered Learning and Video Self-Instruction about Automatic External Defibrillator for High School Girls (여고생의 자동제세동기에 대한 강사중심학습과 영상자가학습과의 교육효과 비교)

  • Park, Sang-Sub
    • Journal of the Korea Academia-Industrial cooperation Society
    • /
    • v.12 no.4
    • /
    • pp.1732-1739
    • /
    • 2011
  • This study aims to make a comparison of educational effectiveness between instructor-centered learning and video self-instruction(VSI) about automatic external defibrillator(AED) for high school girls in order to help select an effective teaching method concerning AED. A total of 59 high school girls (29 for the experimental group, 30 for the control group) in J Province participated in this study from July 7 to 14, 2010. The analysis was carried out by using an SPSS WIN 12.0 Version program. After the AED instruction, the knowledge increased more in the experimental group (1.72) than that in the control group (1.60); self-confidence increased more in the experimental group (1.58) than that in the control group (1.46); and accuracy of technical performance increased more in the control group (5.46) than that in the experimental group (4.20). The experimental group (5.68) was more satisfied with AED instruction than the control group (4.95). Since video self-instruction proved to be more educationally effective than instructor-centered learning in most areas, it is necessary to apply video self-instruction to AED instruction in the future. However, further researches are necessary to see if video self-instruction is effective.

Real-time and Parallel Semantic Translation Technique for Large-Scale Streaming Sensor Data in an IoT Environment (사물인터넷 환경에서 대용량 스트리밍 센서데이터의 실시간·병렬 시맨틱 변환 기법)

  • Kwon, SoonHyun;Park, Dongwan;Bang, Hyochan;Park, Youngtack
    • Journal of KIISE
    • /
    • v.42 no.1
    • /
    • pp.54-67
    • /
    • 2015
  • Nowadays, studies on the fusion of Semantic Web technologies are being carried out to promote the interoperability and value of sensor data in an IoT environment. To accomplish this, the semantic translation of sensor data is essential for convergence with service domain knowledge. The existing semantic translation technique, however, involves translating from static metadata into semantic data(RDF), and cannot properly process real-time and large-scale features in an IoT environment. Therefore, in this paper, we propose a technique for translating large-scale streaming sensor data generated in an IoT environment into semantic data, using real-time and parallel processing. In this technique, we define rules for semantic translation and store them in the semantic repository. The sensor data is translated in real-time with parallel processing using these pre-defined rules and an ontology-based semantic model. To improve the performance, we use the Apache Storm, a real-time big data analysis framework for parallel processing. The proposed technique was subjected to performance testing with the AWS observation data of the Meteorological Administration, which are large-scale streaming sensor data for demonstration purposes.

A News Video Mining based on Multi-modal Approach and Text Mining (멀티모달 방법론과 텍스트 마이닝 기반의 뉴스 비디오 마이닝)

  • Lee, Han-Sung;Im, Young-Hee;Yu, Jae-Hak;Oh, Seung-Geun;Park, Dai-Hee
    • Journal of KIISE:Databases
    • /
    • v.37 no.3
    • /
    • pp.127-136
    • /
    • 2010
  • With rapid growth of information and computer communication technologies, the numbers of digital documents including multimedia data have been recently exploded. In particular, news video database and news video mining have became the subject of extensive research, to develop effective and efficient tools for manipulation and analysis of news videos, because of their information richness. However, many research focus on browsing, retrieval and summarization of news videos. Up to date, it is a relatively early state to discover and to analyse the plentiful latent semantic knowledge from news videos. In this paper, we propose the news video mining system based on multi-modal approach and text mining, which uses the visual-textual information of news video clips and their scripts. The proposed system systematically constructs a taxonomy of news video stories in automatic manner with hierarchical clustering algorithm which is one of text mining methods. Then, it multilaterally analyzes the topics of news video stories by means of time-cluster trend graph, weighted cluster growth index, and network analysis. To clarify the validity of our approach, we analyzed the news videos on "The Second Summit of South and North Korea in 2007".