• Journal of Korean Society on Water Environment
• /
• v.36 no.6
• /
• 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.

• Journal of the Architectural Institute of Korea Structure & Construction
• /
• v.36 no.3
• /
• 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
• /
• v.33 no.4
• /
• 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
• /
• v.11 no.1
• /
• 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.

• Korean Journal of Computational Design and Engineering
• /
• v.14 no.2
• /
• 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.

• Journal of the Korea Society for Simulation
• /
• v.18 no.4
• /
• pp.185-195
• /
• 2009

As most systems get more complicated, system analysis using simulation has been taken notice of. One of the core parts of simulation analysis is validation of a simulation model, and we can identify how well the simulation model represents the real system with this validation process. The difference between input data of two systems has an effect on the comparison between a simulation model and a real system at validation stage, and the result with such difference is not enough to ensure high credibility of the model. Accordingly, in this paper, we construct a model based on Trace-driven simulation which uses identical input data with the real system. On the other hand, to validate a model by each class, not by an unique statistic, we validate the model using a metric transformed from F-measure which estimates performance of a classifier in data mining field. Finally, this procedure enables precise validation process of a model, and it helps modification by offering feedback at the validation phase.

• The Korean Journal of Archival Studies
• /
• no.79
• /
• pp.305-341
• /
• 2024

This study explored the possibilities of a new approach to developing the provenance concept to electronic records in the data-driven digital environments by reviewing and adopting data provenance concepts and models. It then conducted basic literature review to develop a ground for a model representing the provenance of data-driven electronic records. In particular, it proposed to embrace to the concepts of retrospective and prospective provenance, and to develop a different model for representing provenance from records management metadata. If the model can be developed that can represent provenance independently while maintaining a dynamic relationship with records, it can be ensure the fluidity of records and even support to secure the record's attributes and play the roles of provenance. Eventually, it proposed the direction to develop the provenance model which can support the fixity of records, the reproducibility of activities, and the trustworthiness of representations. It is expected to be a fit provenance model in the data-driven digital environment.

• Composites Research
• /
• v.36 no.5
• /
• pp.329-334
• /
• 2023

The classical multiscale finite element (FE² ) method involves iterative calculations of micro-boundary value problems for representative volume elements at every integration point in macro scale, making it a computationally time and data storage space. To overcome this, we developed the data-driven multiscale analysis method based on the mean-field homogenization (MFH). Data-driven computational mechanics (DDCM) analysis is a model-free approach that directly utilizes strain-stress datasets. For performing multiscale analysis, we efficiently construct a strain-stress database for the microstructure of composite materials using mean-field homogenization and conduct data-driven computational mechanics simulations based on this database. In this paper, we apply the developed multiscale analysis framework to an example, confirming the results of data-driven computational mechanics simulations considering the microstructure of a hyperelastic composite material. Therefore, the application of data-driven computational mechanics approach in multiscale analysis can be applied to various materials and structures, opening up new possibilities for multiscale analysis research and applications.

• Speech Sciences
• /
• v.9 no.1
• /
• 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.

• Journal of Sensor Science and Technology
• /
• v.32 no.6
• /
• 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.