• 한국물환경학회지
• /
• 제36권6호
• /
• pp.611-620
• /
• 2020

Although process-based models have been a preferred approach for modeling freshwater aquatic systems over extended time intervals, the increasing utility of data-driven models in a big data environment has made the data-driven models increasingly popular in recent decades. In this study, international peer-reviewed journals for the relevant fields were searched in the Web of Science Core Collection, and an extensive literature review, which included total 2,984 articles published during the last two decades (2000-2020), was performed. The review results indicated that the rate of increase in the number of published studies using data-driven models exceeded those using process-based models since 2010. The increase in the use of data-driven models was partly attributable to the increasing availability of data from new data sources, e.g., remotely sensed hyperspectral or multispectral data. Consistently throughout the past two decades, South Korea has been one of the top ten countries in which the greatest number of studies using the data-driven models were published. Among the major data-driven approaches, i.e., artificial neural network, decision tree, and Bayesian model, were illustrated with case studies. Based on the review, this study aimed to inform the current state of knowledge regarding the biogeochemical water quality and ecological models using data-driven approaches, and provide the remaining challenges and future prospects.

• 대한건축학회논문집:구조계
• /
• 제36권3호
• /
• pp.169-176
• /
• 2020

The authors developed a nodal network model that simulates the flow of moist air and the thermal behavior of a target area. The nodal network model was enhanced using a parameter estimation technique based on the measured temperature, humidity, and schedule data. However, the nodal model is not good enough for predicting humidity of the target space, having 55.6% of CVRMSE. It is because re-evaporation effect could not be modeled due to uncertain factors in the field measurement. Hence, a data-driven model was introduced using an artificial neural network (ANN). It was found that the data-driven model is suitable for predicting the condensation compared to the nodal model satisfying ASHRAE Guideline with 3.36% of CVRMSE for temprature, relative humidity, and surface temperature on average. The model will be embedded in automated devices for real-time predictive control, to minimize the risk of surface condensation at dressroom in an apartment housing.

• Journal of Astronomy and Space Sciences
• /
• 제33권4호
• /
• pp.265-271
• /
• 2016

Interplanetary scintillation-driven (IPS-driven) ENLIL model was jointly developed by University of California, San Diego (UCSD) and National Aeronaucics and Space Administration/Goddard Space Flight Center (NASA/GSFC). The model has been in operation by Korean Space Weather Cetner (KSWC) since 2014. IPS-driven ENLIL model has a variety of ambient solar wind parameters and the results of the model depend on the combination of these parameters. We have conducted researches to determine the best combination of parameters to improve the performance of the IPS-driven ENLIL model. The model results with input of 1,440 combinations of parameters are compared with the Advanced Composition Explorer (ACE) observation data. In this way, the top 10 parameter sets showing best performance were determined. Finally, the characteristics of the parameter sets were analyzed and application of the results to IPS-driven ENLIL model was discussed.

• Coupled systems mechanics
• /
• 제11권1호
• /
• pp.43-54
• /
• 2022

In order to analyse the thermal performance of battery systems in electric vehicles complex simulation models with high computational cost are necessary. Using reduced order methods, real-time applicable model can be developed and used for on-board monitoring. In this work a data driven model of the cooling plate as part of the battery system is built and derived from a computational fluid dynamics (CFD) model. The aim of this paper is to create a meta model of the cooling plate that estimates the temperature at the boundary for different heat flow rates, mass flows and inlet temperatures of the cooling fluid. In order to do so, the cooling plate is simulated in a CFD software (ANSYS Fluent ®). A data driven model is built using the design of experiment (DOE) and various approximation methods in Optimus ®. The model can later be combined with a reduced model of the thermal battery system. The assumption and simplification introduced in this paper enable an accurate representation of the cooling plate with a real-time applicable model.

• 한국CDE학회논문집
• /
• 제14권2호
• /
• pp.96-104
• /
• 2009

It gradually becomes important to study on how to efficiently integrate and manage plant lifecycle data such as 2D schematic and 3D solid data, logical configuration data, and equipment specifications data. From this point of view, converting plant design data from various systems into neutral data independent from any commercial systems is one of important technologies for the operation and management of plants which usually have a very long period of life. In order to achieve this goal, a neutral model for efficient integration and management of plant data was defined. After schema mapping between one of specification-driven plant design systems and the neutral model was performed, a plant data translator is also implemented according to the mapping result. Finally, by experiments with nuclear power plant design, the feasibility of the translator was demonstrated.

• 한국시뮬레이션학회논문지
• /
• 제18권4호
• /
• pp.185-195
• /
• 2009

최근 시스템들이 복잡해지면서 시뮬레이션을 통한 시스템의 분석이 주목을 받고 있다. 시뮬레이션 분석에서 가장 핵심적인 부분 중의 하나가 시뮬레이션 모델의 검증이며, 이 과정을 통하여 시뮬레이션 모델이 얼마나 실제 시스템을 대변할 수 있는지를 판단한다. 모델의 검증에서 시뮬레이션 모델과 실제시스템의 데이터를 비교할 때 발생하는 차이는 입력 데이터의 차이에 의한 영향도 있으며, 이를 통한 모델의 검증 결과는 높은 신뢰성을 보장하지 못한다. 따라서 이 논문에서는 실제와 동일한 입력 데이터를 바탕으로 하는 Trace-Driven 시뮬레이션을 기반으로 모델을 설계하였다. 한편, 출력데이터들을 하나의 통계량을 통한 검증이 아닌 클래스 별 검증을 하기 위해 데이터마이닝 분야에서 분류기의 성능을 판단하는 F 척도를 응용하여 시뮬레이션 모델의 검증을 수행하였다. 그 결과, 제안된 검증 방법은 정밀한 모델의 검증을 가능하게 하고, 검증 시에 피드백을 제공함으로써 용이한 수정 작업을 가능하게 한다.

• 기록학연구
• /
• 제79호
• /
• pp.305-341
• /
• 2024

이 연구는 디지털 환경에서 데이터가 중심이 되는 전자기록의 출처에 새롭게 접근하기 위해, 데이터 출처 개념과 출처 모델을 검토하고 수용하여, 어떻게 전자기록을 대상으로 새롭게 출처 개념을 적용할 수 있을지의 가능성을 살펴보았다. 이어서 데이터 중심의 전자기록을 대상으로 한 출처 표현 모델을 개발하기 위해 기초 연구를 진행하였다. 특히 소급형 출처와 전망형 출처 개념으로 전환할 것과, 기록관리 메타데이터와는 별개의 모델을 통해 출처를 표현하고 기록과 연결할 수 있는 모델을 개발할 것을 제안하였다. 기록과 동적 관계를 맺으면서도 독립적으로 출처를 표현할 수 있는 모델을 개발할 수 있다면, 오히려 기록의 유동성을 보장할 수 있으면서도, 기록의 속성과 이를 지원할 출처의 역할을 더 충실히 수행할 수 있을 것이다. 결국, 이 연구가 제안한 기본적인 모델 개발 방향을 수용하는 출처 모델은 기록의 고정성과 활동의 재현성, 재현의 신빙성을 뒷받침할 수 있을 것이며, 디지털환경에서 적합한 출처 모델로서 역할을 할 수 있을 것이다.

• Composites Research
• /
• 제36권5호
• /
• pp.329-334
• /
• 2023

기존의 멀티스케일 유한요소법(Multiscale finite element, FE² )은 거시 스케일의 모든 적분점에서 대표 체적요소(representative volume element, RVE)의 미시 경계치 문제를 반복적으로 계산하기 때문에 긴 해석 시간과 많은 데이터 저장 공간을 필요로 한다. 이를 해결하기 위해 본 연구에서 평균장 균질화 데이터 기반 멀티스케일 해석 기법을 개발하였다. 데이터 기반 전산역학(data-driven computational mechanics, DDCM) 해석은 변형률-응력 데이터 셋을 직접적으로 사용하는 모델-프리(model-free)접근 방식이다. 멀티스케일 해석을 수행하기 위해, 평균장 균질화(mean-field homogenization)를 활용하여 복합재의 미세구조에 대한 변형률-응력 데이터베이스(database)를 효율적으로 구축하고, 이를 기반으로 데이터 기반 전산역학 시뮬레이션을 수행하였다. 본 논문에서는 개발한 멀티 스케일 해석 프레임워크(framework)를 예제에 적용하여, 초탄성(hyperelasticity) 복합재의 미세 구조를 고려한 데이터 기반 전산역학 시뮬레이션 결과를 확인하였다. 따라서, 데이터 기반 전산역학 접근 방식을 활용한 멀티스케일 해석기법은 다양한 재료 및 구조에 적용될 수 있으며, 멀티스케일 해석 연구 및 응용 가능성을 열어줄 것으로 기대된다.

• 음성과학
• /
• 제9권1호
• /
• pp.39-47
• /
• 2002

This paper proposes an effective method to remedy the acoustic modeling problem inherent in the usual log-normal Parallel Model Composition intended for achieving robust speech recognition. In particular, the Gaussian kernels under the prescribed log-normal PMC cannot sufficiently express the corrupted speech distributions. The proposed scheme corrects this deficiency by judiciously selecting the 'fairly' corrupted component and by re-estimating it as a mixture of two distributions using data-driven PMC. As a result, some components become merged while equal number of components split. The determination for splitting or merging is achieved by means of measuring the similarity of the corrupted speech model to those of the clean model and the noise model. The experimental results indicate that the suggested algorithm is effective in representing the corrupted speech distributions and attains consistent improvement over various SNR and noise cases.

• 센서학회지
• /
• 제32권6호
• /
• pp.475-480
• /
• 2023

When modeling a sensor system mathematically, we assume that the sensor noise is Gaussian and white to simplify the model. If this assumption fails, the performance of the sensor model-based controller or estimator degrades due to incorrect modeling. In practice, non-Gaussian or non-white noise sources often arise in many digital sensor systems. Additionally, the noise parameters of the sensor model are not known in advance without additional noise statistical information. Moreover, disturbances or high nonlinearities often cause unknown sensor modeling errors. To estimate the uncertain noise and model parameters of a sensor system, this paper proposes an iterative batch calibration method using data-driven machine learning. Our simulation results validate the calibration performance of the proposed approach.