• Proceedings of the Korea Society of Design Studies Conference
• /
• 1996.04a
• /
• pp.25-28
• /
• 1996

• Journal of the Korean Society of Radiology
• /
• v.16 no.5
• /
• pp.595-602
• /
• 2022

This study tried to suggest the most efficient learning rate for accurate and efficient automatic diagnosis of medical images for chest X-ray pneumonia images using deep learning. After setting the learning rates to 0.1, 0.01, 0.001, and 0.0001 in the Inception V3 deep learning model, respectively, deep learning modeling was performed three times. And the average accuracy and loss function value of verification modeling, and the metric of test modeling were set as performance evaluation indicators, and the performance was compared and evaluated with the average value of three times of the results obtained as a result of performing deep learning modeling. As a result of performance evaluation for deep learning verification modeling performance evaluation and test modeling metric, modeling with a learning rate of 0.001 showed the highest accuracy and excellent performance. For this reason, in this paper, it is recommended to apply a learning rate of 0.001 when classifying the presence or absence of pneumonia on chest X-ray images using a deep learning model. In addition, it was judged that when deep learning modeling through the application of the learning rate presented in this paper could play an auxiliary role in the classification of the presence or absence of pneumonia on chest X-ray images. In the future, if the study of classification for diagnosis and classification of pneumonia using deep learning continues, the contents of this thesis research can be used as basic data, and furthermore, it is expected that it will be helpful in selecting an efficient learning rate in classifying medical images using artificial intelligence.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.975-976
• /
• 2008

Reliable channel modeling becomes an important measure in performance evaluation on various data detection algorithms. For this reason, correct and accurate modeling is required. This paper presents a nonlinear modeling of Super-RENS (Super-Resolution Near Field Structure) read-out signal using the second-order Volterra model.

• Journal of Magnetics
• /
• v.16 no.4
• /
• pp.386-390
• /
• 2011

This paper deals with the magnetic equivalent circuit modeling and permanent magnet (PM) performance evaluations of a pole changing memory motor (PCMM). We use a coupled transient finite element method (FEM) and Preisach modeling, which is presented to analyze the magnetic characteristics of the permanent magnets. The focus of this paper is on the evaluation of characteristics such as the magnetizing direction and the pole number of the machine under re- and de-magnetization conditions.

• Korean Institute of Interior Design Journal
• /
• v.25 no.4
• /
• pp.147-155
• /
• 2016

In order to ensure a certain level of the quality of design, standardized evaluation indicators are being used as an objective criterion. Even though the evaluation indicators are quantifiable, limitations such as inefficiency and inconsistency caused by manual task in the evaluation process still have been found. BIM (Building Information Modeling) technology that is commonly adopted in architectural design process provides an environment which enables us to figure out a building model to be interpreted quantitatively with the basis of the building information model. It supports quantitative, consistent, accurate and quick evaluations so as to improve quality of design even in the initial design phase. This paper aims to establish BIM-enabled quantitative indicators and an evaluation framework to analyze building circulation even in early phase of design. The indicators are composed of 4 types (relative distance, accessibility, simplicity, pedestrian friendliness) and 7 sub-types. The evaluation framework is the process to derive Parameterized Path Value (PPV) as weighting on each indicator. For demonstrating the scalability of the suggested evaluation indicators and the framework, the authors implemented an evaluation tool and a case study has been carried out by using an actual building remodel project.

• Journal of The Korean Association For Science Education
• /
• v.40 no.5
• /
• pp.543-563
• /
• 2020

This study explores how the teaching practices of two teachers changed during scientific modeling classes. It also aims to understand these changes in terms of the teachers' modeling pedagogical content knowledge (PCK) development. The study participants were two elementary school teachers and their fifth-grade students. The teachers taught eight lessons of scientific modeling classes about the human body. The data analysis was conducted for lessons 1-2 and 7-8, which best showed the change in teaching practice. The two teachers' teaching practices were analyzed in terms of feedback frequency, feedback content, and the time allocated for each stage of model generation, evaluation, and modification. Teacher A led the evaluation and modification stages in a teacher-driven way throughout the classes. In terms of feedback, teacher A mainly used answer evaluation feedback in lesson 1-2; however, in lesson 7-8, the feedback content changed to thought-provoking feedback. Meanwhile, teacher B mostly led a teacher-driven model evaluation and modification in lesson 1-2; however, in lesson 7-8, she let her students lead the model evaluation and modification stages and helped them develop models through various feedbacks. The analysis shows that these teaching changes were related to the development of modeling PCK components. Furthermore, the two teachers' modeling PCK differed in teaching orientation, in understanding the modeling stages, and in recognizing the value of modeling, suggesting the importance of these in modeling teaching practice. This study can help improve the understanding of modeling classes by revealing the relationship between teaching practices and modeling PCK.

• Architectural research
• /
• v.16 no.3
• /
• pp.93-100
• /
• 2014

Existing BIM(Building Information Modeling) based energy evaluation tools cannot be utilized enough for the potential performance of BIM because most of them have not provided the integrated model for energy evaluation, assessment of the material, cost of the construction, and so on. This research aims to propose and develop a new application, EcoBIM, to support an integrated evaluation of the energy and cost efficiencies of the design alternatives within the design process. The proposed application functions as a BIM-based evaluation system that calculates energy-savings performance as well as the construction cost of the alternatives at the design stage. This study mainly focuses on the possibilities of developing the proposed technology. We also suggest an advanced design process using the proposed system, corresponding to changes of national regulations in Korea. This study deduce that EcoBIM can allow architects to make suitable decisions regarding energy- and cost-efficient designs. The proposed design process will allow architects not only to check the eco-friendly performance of design alternatives but also predict the operation cost in a certain period in the future. EcoBIM can prevent large-scale design changes required to obtain environmental certification and enable the owner to make an informed decision about the initial investment of construction according to the result of the analysis of the energy requirement at the design stage.

• Journal of the Korean earth science society
• /
• v.43 no.1
• /
• pp.210-223
• /
• 2022

This study explores the criteria of climate change model evaluation by preservice Earth science teachers. The participants in this study were 25 preservice Earth science teachers who attended lectures on modeling-based science learning for 3 weeks in an Earth science education major course. The evaluation criteria of climate change models were categorized inductively using reports written by preservice Earth science teachers and post-interviews. The results showed that preservice Earth science teachers used various epistemic and communicative criteria to evaluate climate change models. Implications for modeling-based climate-change learning were suggested based on these results.

• Journal of the Korean Society for Precision Engineering
• /
• v.29 no.9
• /
• pp.938-945
• /
• 2012

To design and estimate material failures of Type III pressure vessels, which have excellent stability and performance, various modeling techniques have been introduced. This paper provided a hybrid modeling technique composed of ply-based modeling for a cylinder part and laminate-base modeling technique for a dome part for enhancing modeling efficiency. The ply-based modeling technique provided accurate ply stresses directly for predicting material failure, on the other hand, additional manipulations in stress calculations, which may cause some errors, were needed for the case of the laminate-based modeling technique. The ply stresses in fiber, transverse and in-plane shear directions were compared with the corresponding material strengths to predict material failure.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.591-595
• /
• 2010

Conventional methods of model evaluation usually rely only on model performance based on a comparison of simulated variables to corresponding observations. However, this type of model evaluation has been criticized because of its insufficient consideration of the various uncertainty sources involved in modeling processes. This study aims to propose an extended model evaluation method using multiple assesment indices (MAIs) that consider not only the model performance but also the model structure and parameter uncertainties in rainfall-runoff modeling. A simple reservoir model (SFM) and distributed kinematic wave models (KWMSS1 and KWMSS2 using topography from 250m, 500m, and 1km digital elevation models) were developed and assessed by three MAIs for model performance, model structural stability, and parameter identifiability. All the models provided acceptable performance in terms of a global response, but the simpler SFM and KWMSS1 could not accurately represent the local behaviors of hydrographs. In addition, SFM and KWMSS1 were structurally unstable; their performance was sensitive to the applied objective functions. On the other hand, the most sophisticated model, KWMSS2, performed well, satisfying both global and local behaviors. KMSS2 also showed good structural stability, reproducing hydrographs regardless of the applied objective functions; however, superior parameter identifiability was not guaranteed. Numerous parameter sets could lead to indistinguishable hydrographs. This result supports that while making a model complex increases its performance accuracy and reduces its structural uncertainty, the model is likely to suffer from parameter uncertainty. The proposed model evaluation process can provide an effective guideline for identifying a reliable hydrologic model.