• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2013년도 추계학술발표대회
• /
• pp.87-89
• /
• 2013

이 논문에서는 비침윤성 방광암 환자의 재발 예측을 위해 마이크로어레이 데이터에서 최적의 속성 부분 집합을 찾고 이를 비교 평가한다. 정보 이득(information gain)을 통해 구한 상위 40개, 80개, 100개의 속성 집합과 FCBF(fast correlation based filter) 알고리즘을 적용하여 구한 최적의 속성 부분집합을 SVM 분류 모델에 적용하여 정확도를 비교 평가한 결과 정보 이득을 적용한 상위 100개 속성 부분집합의 분류 정확도가 가장 높게 나왔으며, FCBF 알고리즘을 적용한 속성 집합은 비교적 적은 속성을 사용하면서 이와 비슷한 분류 정확도를 보임을 확인할 수 있었다.

• 한국해양공학회지
• /
• 제17권2호
• /
• pp.77-84
• /
• 2003

The excessive cost of building ships causes the instability of payability, which manage poorly fishing vessels longer than 24m. As a result, an officer evades embarkation and a vicious circle is repeated. In this study, the optimal engine horsepower system for fishing vessels longer than 24m was invented to develop the most efficient engine horsepower, and also a database program for the most efficient engine horsepower has been developed based on the type of and their size.

• 한국병원경영학회지
• /
• 제12권4호
• /
• pp.1-21
• /
• 2007

The relaxation of the regulation in selection of medical institution allows patients to use their own judgement in choosing proper institution for their diseases. Since the change of the regulation, there should have been many changes in medical institution selection behavior. The analysis of the change in disease specific selection pattern is critical because there be an optimal selection criteria that ensure the efficient and effective utilization of medical resources. This study analysis the institution selection factors by comparing the choice among the cases of acute diseases, the cases of chronic diseases, inpatient services, outpatient services, and emergency medical service. The comparisons performed in terms of size, class and other characteristics of medical institutions. For the study the nationally surveyed database was used and the data were analyzed using logistic regression procedure. The results indicates that the primary care facilities were not properly utilized. This study speculates that the reason for the undesirable pattern of utilization is that the roles of primary care facilities in the healthcare delivery system was not clearly defined. Based on the results, the medical policy implications are discussed.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2021년도 춘계학술발표대회
• /
• pp.323-325
• /
• 2021

In this article, we have improved the prediction of hypertension detection using the feature selection method for the Korean national health data named by the KNHANES database. The study identified a variety of risk factors associated with chronic hypertension. The paper is divided into two modules. The first of these is a data pre-processing step that uses a factor analysis (FA) based feature selection method from the dataset. The next module applies a predictive analysis step to detect and predict hypertension risk prediction. In this study, we compare the mean standard error (MSE), F1-score, and area under the ROC curve (AUC) for each classification model. The test results show that the proposed FIFA-OE-NB algorithm has an MSE, F1-score, and AUC outcomes 0.259, 0.460, and 64.70%, respectively. These results demonstrate that the proposed FIFA-OE method outperforms other models for hypertension risk predictions.

• 한국공간정보시스템학회 논문지
• /
• 제11권1호
• /
• pp.79-86
• /
• 2009

제약 데이터베이스의 투플은 제약 논리식으로 구성되었으며, 공간 데이터의 표현 및 질의를 비교적 간결하게 처리할 수 있다. 제약 데이터베이스를 통한 공간 데이터의 실렉션, 합집합, 교집합 등의 질의 연산 처리는 간단하게 관련 투플 간에 제약식을 포함시켜 주면 된다. 그러나 중복되거나 불필요한 데이터가 증가할 수 있으며, 그에 따른 질의 비용이 증가될 수도 있다. 이 논문에서는 제약 데이터베이스에서의 질의처리 결과에 대한 문제점을 밝히고, 효율적인 질의처리를 위해서 결과 릴레이션에 대한 투플 최소화 정리기법의 제안 및 그 효과를 분석했다. 우리는 투플 최소화 기법을 이용하여 제약 릴레이션의 불필요한 제약식을 제거함에 따른 질의처리의 효율성이 개선됨을 확인할 수 있었다.

• 한국정보통신학회논문지
• /
• 제6권5호
• /
• pp.653-660
• /
• 2002

본 논문은 관계형 데이터베이스 기반하여 그래프를 저장하고 그래프 알고리즘을 정의할 수 있는 방법을 제안한다. 이 방법에서 그래프는 릴레이션으로 표현되며, 그래프의 각 정점과 간선은 이 릴레이션의 튜플로서 데이터베이스에 저장된다. 이를 위해 그래프의 저장 및 관리뿐만 아니라 다양한 응용프로그램 개발에도 사용될 수 있는 기본적인 그래프 함수들을 라이브러리로 개발하였다. 또한, 그래프에 대한 알고리즘을 추출, 선택, 죠인과 같은 관계대수 연산을 이용하여 정의하였으며, SQL과 같은 데이터베이스 언어를 사용하여 구현하였다. 이와 같은 데이터베이스에 기반한 방법은 메모리에 수용되지 않는 크기의 그래프를 효과적으로 처리할 수 있을 뿐만 아니라 다양한 응용프로그램 개발을 용이하게 할 것이다.

• 한국측량학회지
• /
• 제30권5호
• /
• pp.435-444
• /
• 2012

웹 환경에서의 지도서비스 및 위치기반서비스를 제공하기 위해서는 다축척 지도 데이터베이스를 구축하여야 하나, 제작과정이 아직까지 수동편집에 의존하는 경우가 많았다. 본 연구에서는 기본 지도 자료로부터 다축척 지도 데이터베이스를 자동으로 구축하기 위한 지도 일반화 기법을 제안하고 이를 실제 지도 데이터에 적용하여 프로토타입의 다축척 지도 데이터셋을 생성하고자 한다. 지도 일반화 기법으로는 선택 및 삭제, 단순화, 병합 등의 연산자를 조합하여 적용하였으며, 각각 연산자의 알고리듬과 파라미터들은 T$\ddot{o}$pfer's radical law, 지도의 최소도화 기준, 시각적 표현정도 등을 종합적으로 고려하여 실험적으로 결정하였다. 목표 축척수준은 1:1,000, 1:5,000, 1:25,000, 1:100,000, 1:500,000 의 5단계로 설정하였으며, 대상이 되는 기본 지도 자료는 도로명주소 전자지도와 수치지형도를 사용하였다.

• 간호행정학회지
• /
• 제2권1호
• /
• pp.73-96
• /
• 1996

In the complexity and diversity of modern society, there is an urgent need for an information system which can systematically collect, manage and analyze data. Especially in the discipline of nursing, a nursing informarion system is necessary to maximize nursing resources and improve nursing care in the present system which is faced with increases in client needs and multiple changes in hospital environments. This research was done to provide a basis for the development of an integrative nursing information system for the future, by designing dababases items which were extracted from an analysis of the ward nursing information system on general wards excluding the OPD, ICU, OR and CSR with functions using a different system from the wards, and the design of output screen used the database items. The ward nursing information system was analysed through analysis of nursing practice related to recordings, such as the worksheet, kardex, and other nursing practice recordings, on 25 wards. The development of the database was the part of the construction of hospital information system and used the database development life cycle which is related to the system development life cycle. The database development steps included selection of database management system and design of a physical database following the principles of the order communication system which is been developing at Y University Hospital. Conceptual database and Logical database were designed using the base of 25 data items and fields derived from analysing the worksheet, the data items and fields derived from the kardex and other nursing practice recording, from these 19 data base tables were framed through transforming the relational database. Through this process, four types of output material for nursing practice recording which nurses can carry and use during their nursing practice were produced.

• 한국지반공학회:학술대회논문집
• /
• 한국지반공학회 2010년도 추계 학술발표회
• /
• pp.1274-1281
• /
• 2010

Cut Slope Management System(CSMS) is a systematic maintenance and management system designed to prevent the collapse of cut slopes located along national roads and to minimize damages caused by slope collapse related accidents. In order to implement a maintenance and management system that will ensure safe road operation, the Korean government has started the inventory of cut slopes and developed a cut slope database since 2006. The study on the application of cut slope database is on-going and part of this study is the development of cut slope database management system (Slope-navi) using GIS technology and navigation system for the effective and efficient cut slope management using Information Technology. Using the Navigation Cut Slope Data Management System the previously developed database was checked and verified. The converted cut slope inventory data and field investigation reports of about 20,000 cut slopes were loaded in the navigation map. Through the development of the navigation's cut slope data search system, a systematic and efficient cut slope database management and operation in the prevention of slope collapse and remedial measure selection was established.

• Water Engineering Research
• /
• 제5권4호
• /
• pp.157-176
• /
• 2004

This research presents a prototype development and implementation of Decision Support System (DSS) for integrated river basin water management for the flood control. The DSS consists of Relational Database Management System, Hydrologic Data Monitoring System, Spatial Analysis Module, Spatial and Temporal Analysis for Rainfall Event Tool, Flood Forecasting Module, Real-Time Operation of Multi Reservoir System, and Dialog Module with Graphical User Interface and Graphic Display Systems. The developed DSS provides an automated process of alternative evaluation and selection within a flexible, fully integrated, interactive, centered relational database management system in a user-friendly computer environment. The river basin decision-maker for the flood control should expect that she or he could manage the flood events more effectively by fully grasping the hydrologic situation throughout the basin.