• 산업공학
• /
• 제23권3호
• /
• pp.221-228
• /
• 2010

With the development of science and technology, modern submarines are equipped with high technology devices and multi-functioned precise armaments, consequently, acquisition cost as well as maintenance cost of the submarines are getting higher and higher. However, tight defense budget forces navy to significantly reduce military operating and maintenance costs. In this study, the maintenance and operating costs of submarine Jangbogo-II are estimated through M&S (Modeling and simulation) methodologies in order to reasonably and consistently work out the requirement verification system of Jangbogo-II. The maintenance and operating costs of Jangbogo-II along the next 25 years are estimated as 312.65 billion won via engineering analysis methods while 312.69 billion won from PRICE Model, which shows only 0.04 billion won differences as a whole. This study is expected to be able to provide meaningful decision making data for not only short and/or mid term operating planning but military budgeting.

• Coupled systems mechanics
• /
• 제8권6호
• /
• pp.489-500
• /
• 2019

With drinking water standards becoming more rigorous and increasing demands for additional water quantities, while water resources are becoming more polluted, mathematical models became an important tool to improve water treatment processes performance in the water supply system. Water treatment processes models reflect the knowledge of the processes and they are useful tools for water treatment process optimization, design, operator training for decision making and fundamental research. Unfortunately, in the current practice of drinking-water production and distribution, water treatment processes modeling is not successfully applied. This article presents a review of some existing water treatment processes simulators and the experience of their application and indicating the main weak points of each process. Also, new approaches in the modeling of water treatment are presented and recommendations are given for the work in the future.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2023년도 학술발표회
• /
• pp.287-287
• /
• 2023

Surface water-groundwater interaction (SWGI) is an important hydrological process that influences both the quantity and quality of water resources. However, regional scale SWGI model calibration and uncertainty analysis have been a challenge because integrated models inherently carry a vast number of parameters, modeling assumptions, and inputs, potentially leaving little time and budget to explore questions related to model performance and forecasting. In this study, we have proposed the application of iterative ensemble smoother (IES) for uncertainty analysis and calibration of the widely used integrated surface-subsurface model, SWAT-MODFLOW. SWAT-MODFLOW integrates Soil and Water Assessment Tool (SWAT) and a three-dimensional finite difference model (MODFLOW). The model was calibrated using a parameter estimation tool (PEST). The major advantage of the employed IES is that the number of model runs required for the calibration of an ensemble is independent of the number of adjustable parameters. The pilot point approach was followed to calibrate the aquifer parameters, namely hydraulic conductivity, specific storage, and specific yield. The parameter estimation process for the SWAT model focused primarily on surface-related parameters. The uncertainties both in the streamflow and groundwater level were assessed. The work presented provides valuable insights for future endeavors in coupled surface-subsurface modeling, data collection, model development, and informed decision-making.

• Journal of Information Technology Applications and Management
• /
• 제30권1호
• /
• pp.53-70
• /
• 2023

Artificial intelligence has become familiar with modern society, not the distant future. As artificial intelligence and machine learning developed more highly and became more complicated, it became difficult for people to grasp its structure and the basis for decision-making. It is because machine learning only shows results, not the whole processes. As artificial intelligence developed and became more common, people wanted the explanation which could provide them the trust on artificial intelligence. This study recognized the necessity and importance of explainable artificial intelligence, XAI, and examined the trends of XAI research by analyzing social networks and analyzing topics with IEEE published from 2004, when the concept of artificial intelligence was defined, to 2022. Through social network analysis, the overall pattern of nodes can be found in a large number of documents and the connection between keywords shows the meaning of the relationship structure, and topic modeling can identify more objective topics by extracting keywords from unstructured data and setting topics. Both analysis methods are suitable for trend analysis. As a result of the analysis, it was found that XAI's application is gradually expanding in various fields as well as machine learning and deep learning.

• 한국건설관리학회논문집
• /
• 제22권1호
• /
• pp.3-12
• /
• 2021

리모델링사업에서 건축적 전문 지식이 없는 클라이언트의 경우 요구사항을 정확하게 제시하는데 한계가 있다. 그 결과, 시공자와 설계자는 요구를 정확하게 인지하지 못해 클라이언트의 의도와 다른 설계를 진행하기도 한다. 이를 극복하기 위해 3차원 모델링 방법이 도입되고 있지만, 향후 지어질 결과를 가상으로 보여주는 이러한 방식도 한계가 있다. 리모델링 프로젝트의 경우 남겨진 구조물에 새로 지어질 부분을 더해 이해도를 높일 수 있는 증강현실을 도입할 경우 프로젝트 참여자의 이해도를 높일 수 있을 것으로 기대된다. 이에 본 연구에서는 고층 오피스 건물 리모델링 프로젝트를 대상으로 혼합현실을 도입했을 때 클라이언트가 설계 내용을 어느 정도 이해할 수 있고, 이를 바탕으로 의사결정을 원활하게 내릴 수 있는지를 검증하고자 한다. 실행연구를 통해 클라이언트, 프로젝트참여자가 2D CAD 도면, BIM, 혼합현실을 각각 체험한 후 12가지 의사결정 준거별로 어느 정도 지원 효과가 있는지 분석했다. 혼합현실의 경우 현실감 향상을 통해 향후 결과를 예측할 수 있는 장점이 부각된 반면, 바닥과 같은 일부 부위의 경우 패턴 인식에 어려움이 있었고 어지럼증을 호소하는 단점이 파악되었다.

• 한국임상약학회지
• /
• 제18권2호
• /
• pp.84-96
• /
• 2008

In the recent, pharmacokinetic (PK)/pharmacodynamic (PD) modeling has appeared as a critical path tools in new drug development to optimize drug efficacy and safety. PK/PD modeling is the mathematical approaches of the relationships between PK and PD. This approach in new drug development can be estimated inaccessible PK and PD parameters, evaluated competing hypothesis, and predicted the response under new conditions. Additionally, PK/PD modeling provides the information about systemic conditions for understanding the pharmacology and biology. These advantages of PK/PD model development are to provide the early decision-making information in new drug development process, and to improve the prediction power for the success of clinical trials. The purpose of this review article is to summarize the PK/PD modeling process, and to provide the theoretical and practical information about widely used PK/PD models. This review also provides model schemes and the differential equations for the development of PK/PD model.

• 한국농공학회지
• /
• 제39권2호
• /
• pp.97-103
• /
• 1997

DO concentration in the aquatic system is important for the water quality management perspective. Water quality model uses available reaeration coefficient (K2) estimation equations in calculating DO, however, they might include inevitable uncertainty that the model output can be less reliable. In this study, the calibrated QUAL2E model for the Passaic River in New Jersey, U.S., was used to examine the effect of K2 estimation equation on the output DO concentration of the river. The model was run with six commonly used equations separately with all the other conditions remained same. The result showed that the output DO concentration profiles varied widely with different equations, and maximum difference was 4.96 mg/L for the same location which is unacceptably large. It implies that the development of reliable equation is required for proper water quality management. The unreliable model output can lead to a wrong decision in water quality management such as unnecessarily high or too low treatment of wastewater, which will cause serious effect on the community economically and socially in either case. Generating more reliable model output with slight investment to develop a site specific K$_2$ equation can improve the decision making process significantly and is highly recommended.

• 정보처리학회논문지B
• /
• 제12B권4호
• /
• pp.437-442
• /
• 2005

화자독립 음성인식기의 화자 정규화를 위해 GMM(Gaussian mixture model)분포를 이용하는 방법에 대해 실험한다. 이 방법은 벡터 양자화기를 이용한 선행 연구를 개선한 것으로, 정규화된 학습용 특징벡터들의 확률분포를 최적의 클러스터의 수를 갖는 GMM분포로 모델링한 다음, 이 분포를 이용하여 시험용화자의 워핑계수를 추정한다. 이 연구의 목적은 기존의 ML을 이용한 방법의 단점을 개선하는 동시에 벡터 양자화기를 이용한 선행연구와'soft decision'이라 불리는 확률 분포를 이용한 방법의 성능을 비교하는데 있다. TIMIT 코퍼스를 대상으로 한 음소 인식 실험에서 클러스터의 수를 적절한 크기로 설정한 GMM분포를 이용함으로써 벡터 양자화기를 이용한 방법에 비해 약간 나은 인식률을 얻을 수 있었다.

• 대한영양사협회학술지
• /
• 제25권1호
• /
• pp.44-58
• /
• 2019

Predicting the number of meals in a foodservice organization is an important decision-making process that is essential for successful food production, such as reducing the amount of residue, preventing menu quality deterioration, and preventing rising costs. Compared to other demand forecasts, the menu of dietary personnel includes diverse menus, and various dietary supplements include a range of side dishes. In addition to the menus, diverse subjects for prediction are very difficult problems. Therefore, the purpose of this study was to establish a method for predicting the number of meals including predictive modeling and considering various factors in addition to menus which are actually used in the field. For this purpose, 63 variables in eight categories such as the daily available number of people for the meals, the number of people in the time series, daily menu details, weekdays or seasons, days before or after holidays, weather and temperature, holidays or year-end, and events were identified as decision variables. An ensemble model using six prediction models was then constructed to predict the number of meals. As a result, the prediction error rate was reduced from 10%~11% to approximately 6~7%, which was expected to reduce the residual amount by approximately 40%.

• Structural Engineering and Mechanics
• /
• 제57권6호
• /
• pp.1125-1142
• /
• 2016

Tunneling is one of the challenging tasks in civil engineering because it involves a variety of decision making and engineering judgment based on knowledge and experience. One of the challenges is to construct tunnels in risky areas under shallow overburden. In order to prevent the collapse of ceilings and walls of a large tunnels, in such conditions, either a sequential excavation method (SEM) or ground reinforcing method, or a combination of both, can be utilized. This research deals with the numerical modeling of L-profiles and pipe fore-poling pre-support systems in the adit tunnel in northwestern Iran. The first part of the adit tunnel has been drilled in alluvial material with very weak geotechnical parameters. Despite applying an SEM in constructing this tunnel, analyzing the results of numerical modeling done using FLAC3D, as well as observations during drilling, indicate the tunnel instability. To improve operational safety and to prevent collapse, pre-support systems, including pipe fore-poling and L-profiles were designed and implemented. The results of the numerical modeling coupled with monitoring during operation, as well as the results of instrumentation, indicate the efficacy of both these methods in tunnel collapse prevention. Moreover, the results of modeling using FLAC3D and SECTION BUILDER suggest a double angle with equal legs ($2L100{\times}100{\times}10mm$) in both box profile and tee array as an alternative section to pipe fore-poling system while neither $L80{\times}80{\times}8mm$ nor $2L80{\times}80{\times}8mm$ can sustain the axial and shear stresses exerted on pipe fore-poling system.