• 국제학술발표논문집
• /
• The 1th International Conference on Construction Engineering and Project Management
• /
• pp.503-508
• /
• 2005

In the modern, distributed and dynamic construction environment it is important to exchange information from different sources and in different data formats in order to improve the processes supported by these systems. Previous research has demonstrated that (i) a significant percentage of construction data is stored in semi-structured or unstructured data formats (ii) locating and identifying such data that are needed for the important decision making processes is a very hard and time-consuming task. In this paper, an automated methodology for the classification and retrieval of construction images in AEC/FM model based systems will be presented. Specifically, a combination of techniques from the areas of image processing, computer vision, and content-based image retrieval have been deployed to develop a method that can retrieve related construction site image data from components of a project model.

• 한국컴퓨터정보학회논문지
• /
• 제14권6호
• /
• pp.125-134
• /
• 2009

웹을 통한 생물 데이터 접근 방식은 많은 과학자들에게 대화식으로 서로 다른 형식의 생물 데이터베이스 내용을 검색할 뿐만 아니라, 한 데이터베이스에서 다른 분자생물 데이터베이스로의 연결을 위한 강력한 도구를 제공한다. 본 논문에서의 생물 개념 모델은 생물 데이터 제어를 위한 4가지 통합 레이어를 기반으로 각 생물 데이터 소스 간의 연관성에 따른 규칙 속성을 적용하고 데이터 소스 중에 관심 대상이 되는 개체를 표현하여 하이브리드 생물 데이터 모델을 구성하였다. 특정 사용자의 응용 서비스 요구가 발생하면 해당 생물 데이터베이스와 웹 서비스를 통한 데이터 소스로부터 정보를 획득한다. 본 논문에서는 통합 레이어를 기반으로 웹 데이터 소스 상에서 정보를 탐색하기 위해 메타 규칙을 적용한 질의어 처리 모형과 수행구조를 정형화하였다.

• 한국병원경영학회지
• /
• 제28권3호
• /
• pp.1-14
• /
• 2023

Purposes: It is very important to establish a clinical data warehouse based on a common data model to offset the different data characteristics of each medical institution and for drug surveillance. This study attempted to establish a clinical data warehouse for Dankook university hospital for drug surveillance, and to derive the main items necessary for development. Methodology/Approach: This study extracted the electronic medical record data of Dankook university hospital tracked for 9 years from 2013 (2013.01.01. to 2021.12.31) to build a clinical data warehouse. The extracted data was converted into the Observational Medical Outcomes Partnership Common Data Model (Version 5.4). Data term mapping was performed using the electronic medical record data of Dankook university hospital and the standard term mapping guide. To verify the clinical data warehouse, the use of angiotensin receptor blockers and the incidence of liver toxicity were analyzed, and the results were compared with the analysis of hospital raw data. Findings: This study used a total of 670,933 data from electronic medical records for the Dankook university clinical data warehouse. Excluding the number of overlapping cases among the total number of cases, the target data was mapped into standard terms. Diagnosis (100% of total cases), drug (92.1%), and measurement (94.5%) were standardized. For treatment and surgery, the insurance EDI (electronic data interchange) code was used as it is. Extraction, conversion and loading were completed. R language-based conversion and loading software for the process was developed, and clinical data warehouse construction was completed through data verification. Practical Implications: In this study, a clinical data warehouse for Dankook university hospitals based on a common data model supporting drug surveillance research was established and verified. The results of this study provide guidelines for institutions that want to build a clinical data warehouse in the future by deriving key points necessary for building a clinical data warehouse.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.2903-2923
• /
• 2023

Knowledge recommendation is a type of recommendation system that recommends knowledge content to users in order to satisfy their needs. Although using graph neural networks to extract data features is an effective method for solving the recommendation problem, there is information loss when modeling real-world problems because an edge in a graph structure can only be associated with two nodes. Because one super-edge in the hypergraph structure can be connected with several nodes and the effectiveness of knowledge graph for knowledge expression, a dual-channel hypergraph convolutional neural network model (DCHC) based on hypergraph structure and knowledge graph is proposed. The model divides user data and knowledge data into user subhypergraph and knowledge subhypergraph, respectively, and extracts user data features by dual-channel hypergraph convolution and knowledge data features by combining with knowledge graph technology, and finally generates recommendation results based on the obtained user embedding and knowledge embedding. The performance of DCHC model is higher than the comparative model under AUC and F1 evaluation indicators, comparative experiments with the baseline also demonstrate the validity of DCHC model.

• 대한안전경영과학회지
• /
• 제11권4호
• /
• pp.221-228
• /
• 2009

Electronic Product Code Information Services(EPCIS) is an EPCglobal standard for sharing EPC related information between trading partners. EPCIS provides a new important capability to improve efficiency, security, and visibility in the global supply chain. EPCIS data are classified into two categories, master data (static data) and event data (dynamic data). Master data are static and constant for objects, for example, the name and code of product and the manufacturer, etc. Event data refer to things that happen dynamically with the passing of time, for example, the date of manufacture, the period and the route of circulation, the date of storage in warehouse, etc. There are four kinds of event data which are Object Event data, Aggregation Event data, Quantity Event data, and Transaction Event data. This thesis we propose an event-based data model for EPC Information Service repository in RFID based integrated logistics center. This data model can reduce the data volume and handle well all kinds of entity relationships. From the point of aspect of data quantity, we propose a formula model that can explain how many EPCIS events data are created per one business activity. Using this formula model, we can estimate the size of EPCIS events data of RFID based integrated logistics center for a one day under the assumed scenario.

• 한국IT서비스학회지
• /
• 제10권1호
• /
• pp.135-149
• /
• 2011

In this paper, we propose the high-risk group detection model for patients with high blood pressure using case-based reasoning. The proposed model can be applied for public health maintenance organizations to effectively manage knowledge related to high blood pressure and efficiently allocate limited health care resources. Especially, the focus is on the development of the model that can handle constraints such as managing large volume of data, enabling the automatic learning to adapt to external environmental changes and operating the system on a real-time basis. Using real data collected from local public health centers, the optimal high-risk group detection model was derived incorporating optimal parameter sets. The results of the performance test for the model using test data show that the prediction accuracy of the proposed model is two times better than the natural risk of high blood pressure.

• 한국CDE학회논문집
• /
• 제12권1호
• /
• pp.74-85
• /
• 2007

During the lifecycle of a nuclear power plant many organizations are involved in KOREA. Korea Plant Engineering Co. (KOPEC) participates in the design stage, Korea Hydraulic and Nuclear Power (KHNP) operates and manages all nuclear power plants in KOREA, Dusan Heavy Industries manufactures the main equipment, and a construction company constructs the plant. Even though each organization has a digital data management system inside and obtains a certain level of automation, data sharing among organizations is poor. KHNP gets drawing and technical specifications from KOPEC in the form of paper. It results in manual re-work of definition and there are potential errors in the process. A data warehouse based on a neutral model has been constructed in order to make an information bridge between design and O&M phases. GPM(generic product model), a data model from Hitachi, Japan is addressed and extended in this study. GPM has a similar architecture with ISO 15926 "life cycle data for process plant". The extension is oriented to nuclear power plants. This paper introduces some of implementation results: 1) 2D piping and instrument diagram (P&ID) and 3D CAD model exchanges and their visualization; 2) Interface between GPM-based data warehouse and KHNP ERP system.

• 대한공간정보학회지
• /
• 제3권1호
• /
• pp.45-54
• /
• 1995

관계 데이타모델은 관계(relations)의 수학적인 개념에 기반을 두고 잘 정형화되어 있으며 실용분야에서 많은 검토가 되었으나, 대부분의 지리객체의 특징인 복합 계층구조를 표현하는데는 적합하지 않다. 반면에 객체지향 데이터모델은 복합 계충구조를 자연스럽게 표현할 수 있었으나, 현재 대부분의 상용 GIS시스템 사용자가 이용하고 있는 관계데이타모델과의 데이타 공유가 어려우며, 표준화된 구조(format)의 표준 질의어가 정립되어 있지 못하다. 본 논문에서는 RDBMS를 기반으로 하여 기존의 관계 데이타모델의 데이타를 사용할 수 있으면서 객체지향 데이타모델의 각종 개념을 지원할 수 있는 객체그룹화(Object Grouping)를 제안하였으며, 이를 이용하여 지리정보시스템을 설계하였다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2005년도 심포지엄 논문집 정보 및 제어부문
• /
• pp.6-8
• /
• 2005

In this paper, we discuss model identification of nonlinear data using GAs-based Fuzzy Polynomial Neural Networks(GAs-FPNN). Fuzzy Polynomial Neural Networks(FPNN) is proposed model based Group Method Data Handling(GMDH) and Neural Networks(NNs). Each node of FPNN is expressed Fuzzy Polynomial Neuron(FPN). Network structure of nonlinear data is created using Genetic Algorithms(GAs) of optimal search method. Accordingly, GAs-FPNN have more inflexible than the existing models (in)from structure selecting. The proposed model select and identify its for optimal search of Genetic Algorithms that are no. of input variables, input variable numbers and consequence structures. The GAs-FPNN model is select tuning to input variable number, number of input variable and the last part structure through optimal search of Genetic Algorithms. It is shown that nonlinear data model design using Genetic Algorithms based FPNN is more usefulness and effectiveness than the existing models.

• 지능정보연구
• /
• 제21권1호
• /
• pp.29-45
• /
• 2015

고객반응 예측모형은 마케팅 프로모션을 제공할 목표고객을 효과적으로 선정할 수 있도록 하여 프로모션의 효과를 극대화 할 수 있도록 해준다. 오늘날과 같은 빅데이터 환경에서는 데이터 마이닝 기법을 적용하여 고객반응 예측모형을 구축하고 있으며 본 연구에서는 사례기반추론 기반의 고객반응 예측모형을 제시하였다. 일반적으로 사례기반추론 기반의 예측모형은 타 인공지능기법에 비해 성과가 낮다고 알려져 있으나 입력변수의 중요도에 따라 가중치를 상이하게 적용함으로써 예측성과를 향상시킬 수 있다. 본 연구에서는 프로모션에 대한 고객의 반응여부에 영향을 미치는 중요도에 따라 입력변수의 가중치를 산출하여 적용하였으며 동일한 가중치를 적용한 예측모형과의 성과를 비교하였다. 목욕세제 판매데이터를 사용하여 고객반응 예측모형을 개발하고 로짓모형의 계수를 적용하여 입력변수의 중요도에 따라 가중치를 산출하였다. 실증분석 결과 각 변수의 중요도에 기반하여 가중치를 적용한 예측모형이 동일한 가중치를 적용한 예측모형보다 높은 예측성과를 보여주었다. 또한 고객 반응예측 모형과 같이 실생활의 분류문제에서는 두 범주에 속하는 데이터의 수가 현격한 차이를 보이는 불균형 데이터가 대부분이다. 이러한 데이터의 불균형 문제는 기계학습 알고리즘의 성능을 저하시키는 요인으로 작용하며 본 연구에서 제안한 Weighted CBR이 불균형 환경에서도 안정적으로 적용할 수 있는지 검증하였다. 전체데이터에서 100개의 데이터를 무작위로 추출한 불균형 환경에서 100번 반복하여 예측성과를 비교해 본 결과 본 연구에서 제안한 Weighted CBR은 불균형 환경에서도 일관된 우수한 성과를 보여주었다.