• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.4
• /
• pp.121-128
• /
• 2018

A Korean morphological analyzer adopts sequence-to-sequence (seq2seq) model, which can generate an output sequence of different length from an input. In general, a seq2seq based Korean morphological analyzer takes a syllable-unit based sequence as an input, and output a syllable-unit based sequence. Syllable-based morphological analysis has the advantage that unknown words can be easily handled, but has the disadvantages that morpheme-based information is ignored. In this paper, we propose a reranking model as a post-processor of seq2seq model that can improve the accuracy of morphological analysis. The seq2seq based morphological analyzer can generate K results by using a beam-search method. The reranking model exploits morpheme-unit embedding information as well as n-gram of morphemes in order to reorder K results. The experimental results show that the reranking model can improve 1.17% F1 score comparing with the original seq2seq model.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.147-147
• /
• 2019

The Numerical Weather Prediction (NWP) models determine the future state of the weather by forcing current weather conditions into the atmospheric models. The NWP models approximate mathematically the physical dynamics by nonlinear differential equations; however these approximations include uncertainties. The errors of the NWP estimations can be related to the initial and boundary conditions and model parameterization. Development in the meteorological forecast models did not solve the issues related to the inevitable biases. In spite of the efforts to incorporate all sources of uncertainty into the forecast, and regardless of the methodologies applied to generate the forecast ensembles, they are still subject to errors and systematic biases. The statistical post-processing increases the accuracy of the forecast data by decreasing the errors. Error prediction of the NWP models which is updating the NWP model outputs or model output statistics is one of the ways to improve the model forecast. The regression methods (including linear, polynomial and scaling regression) are applied to the present study to improve the real time forecast skill. Such post-processing consists of two main steps. Firstly, regression is built between forecast and measurement, available during a certain training period, and secondly, the regression is applied to new forecasts. In this study, the WRF real-time forecast data, in comparison with the observed data, had systematic biases; the errors related to the NWP model forecasts were reflected in the underestimation of the meteorological data forecast by the WRF model. The promising results will indicate that the post-processing techniques applied in this study improved the meteorological forecast data provided by WRF model. A comparison between various bias correction methods will show the strength and weakness of the each methods.

• Journal of the Korea Society of Computer and Information
• /
• v.13 no.5
• /
• pp.163-170
• /
• 2008

As the degree of dependency and application of component increases, the need to strengthen security of component is also increased as well. The component gives an advantage to improve development productivity through its reusable software. Even with this advantage, vulnerability of component security limits its reuse. When the security level of a component is raised in order to improve this problem, the most problematic issue will be that it may extend its limitation on reusability. Therefore, a component model concerning its reusability and security at the same time should be supplied. We suggest a Separation of Concerns Security Model for Extension of Component Reuse which is integrated with a wrapper model and an aspect model and combined with a reuse model in order to extend its security and reusability by supplying information hiding and easy modification, and an appropriate application system to verify the model's compatibility is even constructed. This application model gives the extension of component function and easy modification through the separation of conceits, and it raise its security as doll as extends its reusability.

• Nuclear Engineering and Technology
• /
• v.53 no.7
• /
• pp.2377-2386
• /
• 2021

To model the atmospheric dispersion of radionuclides released from nuclear accident is very important for nuclear emergency. But the uncertainty of model parameters, such as source term and meteorological data, may significantly affect the prediction accuracy. Data assimilation (DA) is usually used to improve the model prediction with the measurements. The paper proposed a parameter bias transformation method combined with Lagrangian puff model to perform DA. The method uses the transformation of coordinates to approximate the effect of parameters bias. The uncertainty of four model parameters is considered in the paper: release rate, wind speed, wind direction and plume height. And particle swarm optimization is used for searching the optimal parameters. Twin experiment and Kincaid experiment are used to evaluate the performance of the proposed method. The results show that the proposed method can effectively increase the reliability of model prediction and estimate the parameters. It has the advantage of clear concept and simple calculation. It will be useful for improving the result of atmospheric dispersion model at the early stage of nuclear emergency.

• Korean Medical Education Review
• /
• v.23 no.1
• /
• pp.56-67
• /
• 2021

Educational program evaluation can improve the quality of the curriculum, instructional methods, and resources and provide useful data for making educational decisions and policies. Developing and implementing a program evaluation system is essential in competency-based medical education. The purpose of this study was to explore and establish an educational program evaluation system adapting an integrated program evaluation model to promote competency-based medical education. First, an Educational Evaluation Committee was organized, consisting of faculty, staff members, and students. The committee established an integrated program evaluation model, combining Stufflebeam's Context, Input, Process, and Product (CIPP) model of a process-oriented approach and Kirkpatrick's four-level model of an outcome-oriented approach. Kirkpatrick's model was applied to the product evaluation of the CIPP model. The committee then developed evaluation criteria, indicators, and data collection methods according to the components of the CIPP model and the four levels (reaction, learning, behavior, and results) of Kirkpatrick's model, and collected and analyzed data. Finally, the committee reported the results of evaluation to a Medical Education Quality Improvement Committee, and the results were used to improve the curriculum and student selection. To enhance the quality of education, identifying educational deficiencies and developing various elements of education in a balanced way through educational evaluation will be needed. Furthermore, it will be necessary to listen to opinions of various stakeholders, work with all members involved in education, and communicate with decision-makers in the process of educational evaluation.

• Journal of the Society of Disaster Information
• /
• v.18 no.2
• /
• pp.364-373
• /
• 2022

Purpose: The purpose of this paper is to develope smoke detection using AI model for detecting the initial fire in underground utility tunnels using CCTV Method: To improve detection performance of smoke which is high irregular, a deep learning model for fire detection was trained to optimize smoke detection. Also, several approaches such as dataset cleansing and gradient exploding release were applied to enhance model, and compared with results of those. Result: Results show the proposed approaches can improve the model performance, and the final model has good prediction capability according to several indexes such as mAP. However, the final model has low false negative but high false positive capacities. Conclusion: The present model can apply to smoke detection in underground utility tunnel, fixing the defect by linking between the model and the utility tunnel control system.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.415-424
• /
• 2021

Objective: To determine whether noncontrast computed tomography (NCCT) models based on multivariable, radiomics features, and machine learning (ML) algorithms could further improve the discrimination of early hematoma expansion (HE) in patients with spontaneous intracerebral hemorrhage (sICH). Materials and Methods: We retrospectively reviewed 261 patients with sICH who underwent initial NCCT within 6 hours of ictus and follow-up CT within 24 hours after initial NCCT, between April 2011 and March 2019. The clinical characteristics, imaging signs and radiomics features extracted from the initial NCCT images were used to construct models to discriminate early HE. A clinical-radiologic model was constructed using a multivariate logistic regression (LR) analysis. Radiomics models, a radiomics-radiologic model, and a combined model were constructed in the training cohort (n = 182) and independently verified in the validation cohort (n = 79). Receiver operating characteristic analysis and the area under the curve (AUC) were used to evaluate the discriminative power. Results: The AUC of the clinical-radiologic model for discriminating early HE was 0.766. The AUCs of the radiomics model for discriminating early HE built using the LR algorithm in the training and validation cohorts were 0.926 and 0.850, respectively. The AUCs of the radiomics-radiologic model in the training and validation cohorts were 0.946 and 0.867, respectively. The AUCs of the combined model in the training and validation cohorts were 0.960 and 0.867, respectively. Conclusion: NCCT models based on multivariable, radiomics features and ML algorithm could improve the discrimination of early HE. The combined model was the best recommended model to identify sICH patients at risk of early HE.

• Proceedings of the KSCN Conference
• /
• 1997.10a
• /
• pp.1-18
• /
• 1997

no Abstract, See Full Text

• Proceedings of the Korean Radioactive Waste Society Conference
• /
• 2016.05a
• /
• pp.45-46
• /
• 2016

• Journal of the Korean Operations Research and Management Science Society
• /
• v.30 no.1
• /
• pp.75-94
• /
• 2005

Research in the decision sciences has continued to develop a variety of mathematical models as well as software tools supporting corporate decision-making. Yet. in spite of their potential usefulness, the models are little used in real-world decision making since the model solution processes are too complex for ordinary users to get accustomed. This paper proposes an intelligent and flexible model-solver integration framework that enables the user to solve decision problems using multiple models and solvers without having precise knowledge of the model-solution processes. Specifically, for intuitive model-solution, the framework enables a decision support system to suggest the compatible solvers of a model autonomously without direct user intervention and to solve the model by matching the model and solver parameters intelligently without any serious conflicts. Thus, the framework would improve the productivity of institutional model solving tasks by relieving the user from the burden of leaning model and solver semantics requiring considerable time and efforts.