• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.36 no.8
• /
• pp.873-879
• /
• 2012

Metamodels have been developed with a variety of design optimization techniques in the field of structural engineering over the last decade because they are efficient, show excellent prediction performance, and provide easy interconnections into design frameworks. To construct a metamodel, a sequential procedure involving steps such as the design of experiments, metamodeling techniques, and validation techniques is performed. Because validation techniques can measure the accuracy of the metamodel, the number of presampled points for an accurate kriging metamodel is decided by the validation technique in the sequential kriging metamodel. Because the interpolation model such as the kriging metamodel based on computer experiments passes through responses at presampled points, additional analyses or reconstructions of the metamodels are required to measure the accuracy of the metamodel if existing validation techniques are applied. In this study, we suggest a sensitivity validation that does not require additional analyses or reconstructions of the metamodels. Fourteen two-dimensional mathematical problems and an engineering problem are illustrated to show the feasibility of the suggested method.

• 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.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2005.09a
• /
• pp.86-87
• /
• 2005

• 한국도로학회:학술대회논문집
• /
• 2010.09a
• /
• pp.53-56
• /
• 2010

• Proceedings of the Korean Nuclear Society Conference
• /
• 1999.05a
• /
• pp.361-361
• /
• 1999

• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2016.09a
• /
• pp.127-134
• /
• 2016

• Korean Journal of Remote Sensing
• /
• v.38 no.4
• /
• pp.395-409
• /
• 2022

The purpose of this study is to evaluate the classification performance and applicability when land cover datasets constructed for AI training are cross validation to other areas. For study areas, Gyeongsang-do and Jeolla-do in South Korea were selected as cross validation areas, and training datasets were obtained from AI-Hub. The obtained datasets were applied to the U-Net algorithm, a semantic segmentation algorithm, for each region, and the accuracy was evaluated by applying them to the same and other test areas. There was a difference of about 13-15% in overall classification accuracy between the same and other areas. For rice field, fields and buildings, higher accuracy was shown in the Jeolla-do test areas. For roads, higher accuracy was shown in the Gyeongsang-do test areas. In terms of the difference in accuracy by weight, the result of applying the weights of Gyeongsang-do showed high accuracy for forests, while that of applying the weights of Jeolla-do showed high accuracy for dry fields. The result of land cover classification, it was found that there is a difference in classification performance of existing datasets depending on area. When constructing land cover map for AI training, it is expected that higher quality datasets can be constructed by reflecting the characteristics of various areas. This study is highly scalable from two perspectives. First, it is to apply satellite images to AI study and to the field of land cover. Second, it is expanded based on satellite images and it is possible to use a large scale area and difficult to access.

• Structural Engineering and Mechanics
• /
• v.10 no.3
• /
• pp.289-298
• /
• 2000

Based on the two-dimensional constitutive relationship of the piezoelastic material, this paper derived an analytic solution to the elastic beam with the piezoelectric layer under the electric field, presented the explicit expressions of its displacement and stress. It is helpful for understanding the electrical and mechanical behavior of piezoelectric materials as actuators and the validation of the numerical methods such as FEM.

• 한국전산유체공학회:학술대회논문집
• /
• 1996.05a
• /
• pp.131-136
• /
• 1996

The numerical method for the flow field of a gas atomization process is presented. For the analysis of the compressible supersonic jet flow of a gas. an axisymmetric Navier-Stokes equations are solved using a LU-factored upwind method. The MUSCL type TVD scheme is used for the discretization of inviscid flux, whereas Steger-Warming splitting and LU factorization is applied to the implicit operator. For the validation of the present method, we computed the flow field around the simple gas atomizer proposed by Issac. The numerical results has shown excellent agreement with the experimental data.

• Proceedings of the KSR Conference
• /
• 2011.10a
• /
• pp.2539-2547
• /
• 2011

This paper will introduce the safety authorization system for light rail transit(LRT) through investigating safety certification & safety authorization in foreign country and aviation field in Korea. The safety authorization system proposed by the government these day was also investigated. Korea Transportation Safety Authority(KOTSA) have conducted safety validation process on Busan-Gimhae LRT before its revenue service during three months since Jan. of 2011. We describe the overview of these validation activities, results and safety certification issued. Learning from this process, we propose the standardized safety validation process including checklists which can be applied to common unmanned light rail system. This study will be a basis of railway safety authorization for LRT and will be continually improve its application ability by the future study.