• 한국원자력학회:학술대회논문집
• /
• 한국원자력학회 1999년도 추계학술발표회요약집
• /
• pp.133-133
• /
• 1999

• 산업경영시스템학회지
• /
• 제23권54호
• /
• pp.155-165
• /
• 2000

The fault diagnosis is a systematic and unified method to find based on the observing data resulting in noises. This paper presents the fault prediction and diagnosis using fuzzy expert system technique to manipulate the uncertainties efficiently in predictive perspective. We apply a fuzzy event tree analysis to the computer system, and build up the fault prediction and diagnosis using fuzzy expert system that predicts and diagnoses the error of the system in the advance of error.

• 한국지리정보학회지
• /
• 제17권4호
• /
• pp.101-111
• /
• 2014

공간사건들은 데이터마이닝 분류알고리즘을 이용하여 예측 가능하며, 의사결정 트리는 대표적인 분류알고리즘들 중 하나로 사용되고 있다. 의사결정 트리는 레이블 값을 갖는 분류작업에 주로 사용되었으나 규칙평가 기법을 트리 리프노드 등급 계산에 응용하면서부터 공간사건 예측에 이용되고 있다. 이 논문에서는 의사결정 트리에서 사용되는 규칙평가 방법들을 공간예측에 적용하여 비교하였다. 실험을 위해 의사결정 트리 알고리즘인 C4.5알고리즘과 규칙 평가기법인 Laplace, M-estimate 및 m-branch 기법들을 구현하여 자연환경에서 발생되는 대표적인 공간예측 응용분야인 산사태에 적용하였다. 적용한 규칙 평가 기법들의 정확도 평가결과, 그 특성에 따라 정확도의 차이가 있었으며 m-branch가 가장 높은 성능을 보였다. 그러나 m-branch 및 M-estimate와 같이 별도의 파라미터를 갖는 경우 반복적으로 최적의 파라미터 값을 찾는 과정을 요구하였다. 따라서 적용 대상에 따라 선택적으로 활용할 수 있다. 이러한 의사결정 트리를 이용한 공간예측은 예측 결과뿐만 아니라 특정 위치에서의 예측결과에 대한 원인분석을 가능하게 함으로 다양한 응용을 가능하게 한다.

• International Journal of Advanced Culture Technology
• /
• 제11권2호
• /
• pp.196-201
• /
• 2023

The future is complex and unpredictable. In particular, it is unlikely to occur, but once it occurs, no one knows how it will affect our society if X-event, which has a tremendous impact, is created. This study was conducted only in the climate field to offset the ripple effect of this X-event, and was conducted through in-depth interviews with experts from the Korea Army Research Center for Future & Innovation and the Army College. As a result, it was possible to explore what factors would trigger X-event from their discourse and what X-event would be newly created by spreading them to other fields. Starting with this study, if we accumulate the discourse of experts in various fields such as population, science and technology, as well as climate, and other fields other than the Army, we can predict X-event and offset the threats that may arise.

• 한국대기환경학회지
• /
• 제19권3호
• /
• pp.249-261
• /
• 2003

A three-dimensional mesoscale atmospheric dispersion modeling system consisting of the Lagrangian particle dispersion model (LPDM) and the meteorological mesoscale model (MM5) was employed to simulate the transport and dispersion of non-reactive pollutant during the nuclear spill event occurred from Sep. 31 to Oct. 3, 1999 in Tokaimura city, Japan. For the comparative analysis of numerical experiment, two more sets of foreign mesoscale modeling system; NCEP (National Centers for Environmental Prediction) and DWD (Deutscher Wetter Dienst) were also applied to address the applicability of air pollution dispersion predictions. We noticed that the simulated results of horizontal wind direction and wind velocity from three meteorological modeling showed remarkably different spatial variations, mainly due to the different horizontal resolutions. How-ever, the dispersion process by LPDM was well characterized by meteorological wind fields, and the time-dependent dilution factors ($\chi$/Q) were found to be qualitatively simulated in accordance with each mesocale meteorogical wind field, suggesting that LPDM has the potential for the use of the real time control at optimization of the urban air pollution provided detailed meteorological wind fields. This paper mainly pertains to the mesoscale modeling approaches, but the results imply that the resolution of meteorological model and the implementation of the relevant scale of air quality model lead to better prediction capabilities in local or urban scale air pollution modeling.

• International Journal of Advanced Culture Technology
• /
• 제11권2호
• /
• pp.186-190
• /
• 2023

There are unimaginable possibilities ahead of us. As a result, it is difficult to predict the future, but the prediction itself is not meaningless. This is because it can have the flexibility to cope with contingencies by predicting various possibilities. This study was conducted to explore extreme events (X-event) in the Korean population sector. To this end, in-depth interviews were conducted with experts from the Korea Army Research Center for Future & Innovation and the Army College, and based on this, significant research results were derived that population problems such as population decline and aging can affect various fields such as economy. With this study, we hope that discussions on extreme events (X-event) that can occur in our society will be further activated.

• Communications for Statistical Applications and Methods
• /
• 제31권4호
• /
• pp.365-375
• /
• 2024

Diverse methods to evaluate the prediction model of a time to event have been proposed in the context of right censored data where all subjects are subject to be susceptible. A time-dependent AUC (area under curve) measures the predictive ability of a marker based on case group and control one which are varying over time. When a substantial portion of subjects are event-free, a population consists of a susceptible group and a cured one. An uncertain curability of censored subjects makes it difficult to define both case group and control one. In this paper, our goal is to propose a time-dependent AUC for a cure rate model when a censoring distribution is related with covariates. A class of inverse probability of censoring weighted (IPCW) AUC estimators is proposed to adjust the possible sampling bias. We evaluate the finite sample performance of the suggested methods with diverse simulation schemes and the application to the melanoma dataset is presented to compare with other methods.

• 대기
• /
• 제15권1호
• /
• pp.35-46
• /
• 2005

Today, the outreach of National Meteorological Service such as PC cluster based Numerical Weather Prediction (NWP) technique is vigorous in the world wide. In this regard, WMO (World Meteorological Organization) asked KMA (Korea Meteorological Administration) to formulate a regional project, which cover most of RA II members, using similar technical system with KMA's. In that sense, Meteorological Research Institute (METRI) in KMA developed Mongolian NWP System (MNWPS) based on PC cluster and transferred the technology to Weather Service Center in Mongolia. The hybrid parallel algorithm and channel bonding technique were adopted to cut cost and showed 41% faster performance than single MPI (Message Passing Interface) approach. The cluster technique of Beowulf type was also adopted for convenient management and saving resources. The Linux based free operating system provide very cost effective solution for operating multi-nodes. Additionally, the GNU software provide many tools, utilities and applications for construction and management of a cluster. A flash flood event happened in Mongolia (2 September 2003) was selected for test run, and MNWPS successfully simulated the event with initial and boundary condition from Global Data Assimilation and Prediction System (GDAPS) of KMA. Now, the cluster based NWP System in Mongolia has been operated for local prediction around the region and provided various auxiliary charts.

• 비파괴검사학회지
• /
• 제16권2호
• /
• pp.79-85
• /
• 1996

복합 재료의 single-lap 및 double-strap adhesive bonding joint 시험편에서 피로 및 인장시험시 방출되는 AE 신호의 분석에 의한 피로 수명 예측 및 파괴 과정의 감시에 대한 연구를 수행하였다. Bonding 시험편의 피로시험시 AE event의 발생양상은 피로에 의해 축적된 elastic strain energy의 방출과 관계되며, peak amplitude가 높고 event duration이 긴 event의 발생 영역과 peak amplitude가 낮고 event duration이 짧으나 많은 event가 발생되는 영역으로 나눌 수 있었다. 그리고 두 영역 사이의 경계 cycle은 피로 수명의 70-80% 근방에 존재하였으며, 이를 이용한다면 피로 수명의 예측이 가능하리라 판단된다.

• 한국IT서비스학회지
• /
• 제17권4호
• /
• pp.75-83
• /
• 2018

Enterprises need to monitor systems for reliable IT service operations to quickly detect and respond to events affecting the service, thereby preventing failures. Events in non-critical systems can be seen as a precursor to critical system incidents. Therefore, event relationship analysis in the operation of IT services can proactively recognize and prevent faults by identifying non-critical events and their relationships with incidents. This study used the Recurrent Neural Network and Long Short Term Memory techniques to create a model to analyze event relationships in a system and to verify which models are suitable for analyzing event relationships. Verification has shown that both models are capable of analyzing event relationships and that RNN models are more suitable than LSTM models. Based on the pattern of events occurring, this model is expected to support the prediction of the next occurrence of events and help identify the root cause of incidents to help prevent failures and improve the quality of IT services.