• Journal of Technology Innovation
• /
• v.17 no.1
• /
• pp.97-117
• /
• 2009

The Delphi is a popular technique for forecasting based on the opinions of experts. It is important to know how valid and reliable the technique is. In this paper, we analyze accuracy and precision of the Delphi in IT and BT of Korea, and also discuss the relationship between them. As a result of the analysis, the accuracy and precision of the forecasts partly have significant differences according to their area and degree of expertise. Besides, significant correlation between the accuracy and precision of forecasts with high expertise is found. The result indicates that the precision of forecasts can be a criterion of the accuracy of them.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.42 no.3
• /
• pp.270-278
• /
• 2014

This paper describes an improvement of space objects orbit prediction. To screen possible collisions between operational satellites and space objects, the TLE (Two-Line Element) was used as pseudo-measurement and than the orbit determination and orbit prediction were performed through the flight dynamics system. For determining the orbits, the state vectors were assumed by a series of TLEs within a certain period. The propagation error was analyzed according to the fitting period and a number of pseudo-observations. In order to find out the improvement of orbit prediction with the proposed method, KOMPSAT-2, 3 having the precise orbit in the meter-level range were first applied. Then the result applied to space objects under the same conditions was analyzed. As a result of the RMS error comparison with the orbit prediction of space object, the precision of orbit prediction was improved by approximately 90% for seven days prediction. The improved orbit prediction of space objects can be utilized in the daily analysis for initial screening of the close space objects at high risk.

• Journal of the KSME
• /
• v.50 no.4
• /
• pp.36-41
• /
• 2010

이 글에서는 정밀유도포탄의 국내외 개발 현황과 특징에 대하여 분석하고, 정밀유도포탄을 개발하기 위해 소프트웨어 관점에서의 주요 설계 요소와 설계 방법에 대하여 기술하였다. 소프트웨어적으로 해결해야 되는 문제로 초기자세 예측과 바람 예측을 제기하였으며, 칼만필터를 활용하여 각 알고리즘을 설계하는 방안에 대하여 제시하고 있다. 뿐만 아니라 정밀한 결과를 위하여 GPS/INS 통합 알고리즘과 유도명령을 구성하는 방안에 대하여 기술하였다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2011.06a
• /
• pp.557-558
• /
• 2011

• Journal of the Korea Convergence Society
• /
• v.12 no.6
• /
• pp.9-16
• /
• 2021

In the past, there have been various studies on predicting the stock market by machine learning techniques using stock price data and financial big data. As stock index ETFs that can be traded through HTS and MTS are created, research on predicting stock indices has recently attracted attention. In this paper, machine learning models for KOSPI's up and down predictions are implemented separately. These models are optimized through a grid search of their control parameters. In addition, a hybrid machine learning model that combines individual models is proposed to improve the precision and increase the ETF trading return. The performance of the predictiion models is evaluated by the accuracy and the precision that determines the ETF trading return. The accuracy and precision of the hybrid up prediction model are 72.1 % and 63.8 %, and those of the down prediction model are 79.8% and 64.3%. The precision of the hybrid down prediction model is improved by at least 14.3 % and at most 20.5 %. The hybrid up and down prediction models show an ETF trading return of 10.49%, and 25.91%, respectively. Trading inverse×2 and leverage ETF can increase the return by 1.5 to 2 times. Further research on a down prediction machine learning model is expected to increase the rate of return.

• Aerospace Engineering and Technology
• /
• v.4 no.1
• /
• pp.221-228
• /
• 2005

In this study, orbit prediction accuracy of the MPAS for the KOMPSAT-2 was analyzed in order to verify the TPF accuracy and operate the APS of the KOMPSAT-2 successfully. The analysis was performed using flight data of the KOMPSAT-1 in that the KOMPSAT-2 will be operated in the same orbit of the KOMPSAT-1. The periods to analyze were selected according to the solar activity. The results in this study verified the requirement for the TPF accuracy and will be used for the successful operation of the KOMPSAT-2.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2008.06a
• /
• pp.461-464
• /
• 2008

연안에서의 태풍 해일에 의한 침수범람 지역 예측을 위하여 GIS를 통한 정밀 육도-해도 접합 및 분석을 만리포 해변을 대상으로 시범 수행하였다. 만리포 해변의 정밀 육도-해도 접합을 위하여 고해상도 지상 LIDAR 시스템의 시범 측량 자료와 국토지리정보원의 수치지형도, 국립해양조사원의 수치해도 수심자료 및 한국 주변해역의 30초격자 수심자료를 사용하였다. 또한 평균해수면 산정을 위하여 만리포에 설치된 수압식파고계 조위자료와 해변의 표척을 통한 목측 관측을 통한 조위자료를 활용하였다. 다양한 자료의 GIS 기반 육도-해도 접합 및 분석을 통한 정밀 지형도 구축 기술은 태풍 해일에 의한 침수범람 예측을 위한 정밀 격자 수치모델의 입력 자료로 활용되어 침수 범람 예측 결과의 재해도(Hazard Map) 작성이 가능하고, 나아가 침식 퇴적 등의 지속적인 해안선 변화 모니터링에 활용될 수 있다.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2004.05a
• /
• pp.252-252
• /
• 2004

새로운 공작기계나 절삭공구의 설계 및 개선을 위하여 절삭 공정 중 발생되는 절삭력 성분을 정확히 예측하는 것이 필요하다. 절삭 과정에서 절삭력 정보의 중요성은 그동안 공작기계 분야에서 익히 강조되어 왔다. 특히 주 절삭력 정보는 공구 파손을 예측하고 마모를 감지하여 그 밖의 다른 오동작을 검출해 내는 것에 있어서 매우 중요한 것으로 잘 알려져 있다. 최근 공작기계 강성 및 성능의 향상, 고속절삭용 공구의 발전, 금형 산업의 생산성과 정밀도 향상의 요구로 머시닝센터를 중심으로 고속가공에 관한 연구가 활발히 진행되고 있다. (중략)

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 1994.10a
• /
• pp.757-762
• /
• 1994

본 연구에서는 정밀진단가공을 위한 파인 블랭킹 기술 개발을 위한 파인 블랭킹용 전용 프레스를 사용 하지 않고 범용 유압 프레스에서 조보 유압 장치에 의해 압력을 조절해가면서 가공특성에 관한 실험적 연구와 이론 해석을 수행한다. 실험을 위해 파인 블랭킹 금형과 유압 장치를 설계 제작하고, 정밀진단 특성에 제일 큰 영향을 미치고 있는 V-돌기( Vee-ring)의 유무와 위치 그리고 스트리핑력 및 카운터 펀 칭력 변화에 따른 제품 정밀도를 조사해 가면서 최적의 정밀도 예측 수단으로 적절함을 확인할 수 있었으며, 실험결과는 작업 조건에 관계없이 모든 제품이 깨끗한 전단면을 나타내고 있으며, 일반적으로 스트리핑력이 감소할수록, 그리고 카운터 펀칭력이 증가할수록 캠버량이 감소하고 특히 카운터 펀칭력에 큰 영향을 받고 있음을 알 수 있었다. 이와같은 현상은 유한 요소해석에 의한 캠버량의 예측에섣고 정성적으로 잘 일치하고 있는 것으로 나타났다.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.2
• /
• pp.1-9
• /
• 2023

Research using AI and big data is also being actively conducted in the health and medical fields such as disease diagnosis and treatment. Most of the existing research data used cohort data from research institutes or some patient data. In this paper, the difference in the prediction rate of survival and the factors affecting survival between breast cancer patients in their 40~50s and other age groups was revealed using health insurance review claim data held by the HIRA. As a result, the accuracy of predicting patients' survival was 0.93 on average in their 40~50s, higher than 0.86 in their 60~80s. In terms of that factor, the number of treatments was high for those in their 40~50s, and age was high for those in their 60~80s. Performance comparison with previous studies, the average precision was 0.90, which was higher than 0.81 of the existing paper. As a result of performance comparison by applied algorithm, the overall average precision of Decision Tree, Random Forest, and Gradient Boosting was 0.90, and the recall was 1.0, and the precision of multi-layer perceptrons was 0.89, and the recall was 1.0. I hope that more research will be conducted using machine learning automation(Auto ML) tools for non-professionals to enhance the use of the value for health insurance review claim data held by the HIRA.