• Journal of Intelligence and Information Systems
• /
• v.26 no.2
• /
• pp.105-129
• /
• 2020

This study uses corporate data from 2012 to 2018 when K-IFRS was applied in earnest to predict default risks. The data used in the analysis totaled 10,545 rows, consisting of 160 columns including 38 in the statement of financial position, 26 in the statement of comprehensive income, 11 in the statement of cash flows, and 76 in the index of financial ratios. Unlike most previous prior studies used the default event as the basis for learning about default risk, this study calculated default risk using the market capitalization and stock price volatility of each company based on the Merton model. Through this, it was able to solve the problem of data imbalance due to the scarcity of default events, which had been pointed out as the limitation of the existing methodology, and the problem of reflecting the difference in default risk that exists within ordinary companies. Because learning was conducted only by using corporate information available to unlisted companies, default risks of unlisted companies without stock price information can be appropriately derived. Through this, it can provide stable default risk assessment services to unlisted companies that are difficult to determine proper default risk with traditional credit rating models such as small and medium-sized companies and startups. Although there has been an active study of predicting corporate default risks using machine learning recently, model bias issues exist because most studies are making predictions based on a single model. Stable and reliable valuation methodology is required for the calculation of default risk, given that the entity's default risk information is very widely utilized in the market and the sensitivity to the difference in default risk is high. Also, Strict standards are also required for methods of calculation. The credit rating method stipulated by the Financial Services Commission in the Financial Investment Regulations calls for the preparation of evaluation methods, including verification of the adequacy of evaluation methods, in consideration of past statistical data and experiences on credit ratings and changes in future market conditions. This study allowed the reduction of individual models' bias by utilizing stacking ensemble techniques that synthesize various machine learning models. This allows us to capture complex nonlinear relationships between default risk and various corporate information and maximize the advantages of machine learning-based default risk prediction models that take less time to calculate. To calculate forecasts by sub model to be used as input data for the Stacking Ensemble model, training data were divided into seven pieces, and sub-models were trained in a divided set to produce forecasts. To compare the predictive power of the Stacking Ensemble model, Random Forest, MLP, and CNN models were trained with full training data, then the predictive power of each model was verified on the test set. The analysis showed that the Stacking Ensemble model exceeded the predictive power of the Random Forest model, which had the best performance on a single model. Next, to check for statistically significant differences between the Stacking Ensemble model and the forecasts for each individual model, the Pair between the Stacking Ensemble model and each individual model was constructed. Because the results of the Shapiro-wilk normality test also showed that all Pair did not follow normality, Using the nonparametric method wilcoxon rank sum test, we checked whether the two model forecasts that make up the Pair showed statistically significant differences. The analysis showed that the forecasts of the Staging Ensemble model showed statistically significant differences from those of the MLP model and CNN model. In addition, this study can provide a methodology that allows existing credit rating agencies to apply machine learning-based bankruptcy risk prediction methodologies, given that traditional credit rating models can also be reflected as sub-models to calculate the final default probability. Also, the Stacking Ensemble techniques proposed in this study can help design to meet the requirements of the Financial Investment Business Regulations through the combination of various sub-models. We hope that this research will be used as a resource to increase practical use by overcoming and improving the limitations of existing machine learning-based models.

• Journal of Korean Ophthalmic Optics Society
• /
• v.14 no.2
• /
• pp.31-34
• /
• 2009

Purpose: We are to analyze optically how to affect the eye related with movement of the iris. Methods: Using the schematic eye to have the crystalline lens of the radial GRIN and the spherical GRIN forms that come to be planned in existing, the iris centre was moved 0.5 mm with nasal direction in order to be identical with the real eye. Also, considering that the iris centre move according to increase of the pupil size, the iris centre was moved 0.4 mm with temporal direction to analyze the optical performance change of the eye respectively. Results: Because of decrease in the spherical aberration, the schematic eye with nasal direction 0.5 mm eccentricity of the iris showed a different consequence plentifully compared with the performance of the real eye. Besides, the schematic eye with temporal direction 0.4 mm eccentricity of the iris showed that the spherical aberration somewhat increased. Conclusions: In case of design of the schematic eye with the similar real eye performance which the iris centre was moved 0.5 mm with nasal direction, we need to research about aspheric coefficient of optical constants of each refracting surface considering the performance change of a spherical aberration, a peripheral power error and astigmatism etc, owing to change of the real eye hence to be affected by the iris movement.

• Journal of Aerospace System Engineering
• /
• v.14 no.5
• /
• pp.33-41
• /
• 2020

The landing gear of an aircraft is a device that absorbs and dissipates shock energy transmitted from the ground to the fuselage. Among the landing gears, the semi-active MR damper landing gear is supposed to show high-shock absorption efficiency under various landing conditions and secure the stability when out of control. In the case of the MR damper landing gear using an annular channel rather than orifice, Amesim, a commercial multi-physics program, is considered as more useful than the conventional two-degree-of-freedom model because the damping force generated by the pressure drop through the flow annular path can cause cavitation in the low-pressure chamber of the MR damper with a specific internal structure. In this paper, the main dynamic characteristics of the MR damper landing gear with an annular type flow path structure has been analyzed under the condition of cavitation. Based on the analysis results using Amesim, a design guideline for the MR damper flow path that prevents cavitation has been proposed based on the modification of the arrangement of internal components of the damper. The guideline was verified through a drop simulation.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.5 no.1
• /
• pp.13-20
• /
• 1985

Two Cable-Stayed bridge on south coast in Korea has not constructed until a quarter of a century past since the beginning of it's own era. Our country is about to be interested in such a type of bridge. It has succeeded in constructing the 500 m spanned bridge against wind and earthquake in other several countries. Many contries are striving for designning a long spanned bridge to 1000m. For the realization of such a long spanned bridge in Korea clues to the problems, "How to design it", should be solved one by one. One of difficulties is in analysing the mechanical system because of multi-orter indeterminacy. In this study one of the numerical methods is proposed in order to eliminate the troublesome.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2002.11a
• /
• pp.139-143
• /
• 2002

1990 년대 후반부터 다양한 디지털 통신망을 이용하여 멀티미디어 컨텐츠 서비스가 가능하게 되었다. 하지만, 멀티미디어 컨텐츠의 전달 및 이용을 위한 기반 구조들의 독자적 발전 및 다양한 통합적 관리 체계 시스템으로 인해, 멀티미디어 컨텐츠 표현 방식의 호환성 문제, 혼재하는 네트워크 전달 방식과 단말 방식의 호환성 문제 등의 잠재적인 문제점이 발생한다. 이런 문제의 대안으로 현재 존재하는 기술 및 기반 구조들 사이의 연동을 통한 큰 프레임워크인 MPEG-21이 진행 중이다. MPEG-21 의 목표는 표준화 목표를 구체화하는 것부터 진행하여, 최종적으로 “다양한 네트워크 환경과 단말기에 있어서, 투명하고 통합적으로 멀티미디어 자원의 이용을 가능하게 하는 것”이다. 본 논문에서는 현재 표준화 작업이 진행 중인 MPEG-21 을 기반으로 하는 Testbed를 제안한다. Testbed는 server, client, DIA(Digital Item Adaptation) 의 세 모듈로 구성된다. Server 의 역할은 멀티미디어 컨텐츠를 Digital Item(DI)으로 생성하고, client 가 DI를 요구할 경우 DIA 모듈을 통해서 변환된 DI를 client 에게 제공한다. DIA 모듈은 server 에서 동작되며 client로부터 요청된 DI를 분석하고 client로부터 전송된 환경 정보를 이용하여 client 환경에 적합하게 변환된 (adapted) DI를 생성하는 것이 주 기능이다. Client 는 server 에 저장되어 있는 DI를 선택하고 user preference, terminal capability 등의 필요한 정보를 server로 전송한다. Testbed 에서는 스포츠 경기의 동영상, 정지 영상, 경기 내용 역사를 기록한 파일 등의 DI를 이용한다. 표현 언어는 XML이며, HTTP 기반의 Web 환경에서 구동되도록 설계된다.스템 사이에 의미 있는 데이터 전송, 지식 획득을 위해 정보 기술 분야에서 활용해야 할 영역으로 XML Web Services, Multi-agent Systems, 전문가 컴뮤니티를 위한 그룹웨어 연구 개발에 관해 사례 중심으로 발표한다.다 신선한 공기를 넣어 주었을 때는 배의 발달이 많이 늦어져 배양 3주째에 다른 처리보다 배의 수가 훨씬 적었다. 체세포배가 발달하는 동안에는 산소를 많이 요구하지 않으나 성숙하는 동안에는 산소를 많이 요구하는 것으로 생각된다.적인 것으로 나타났다. 다만, 곡선형은 물론 직선형에서도 열교환 튜브의 배치밀도, 튜브 길이 및 두께 등의 변화에 따른 최적화 연구가 수반되어야 할 것으로 판단된다.에서 제공된 API는 객체기반 제작/편집 도구에 응용되어 다양한 멀티미디어 컨텐츠 제작에 사용되었다.x factorization (NMF), generative topographic mapping (GTM)의 구조와 학습 및 추론알고리즘을소개하고 이를 DNA칩 데이터 분석 평가 대회인 CAMDA-2000과 CAMDA-2001에서 사용된cancer diagnosis 문제와 gene-drug dependency analysis 문제에 적용한 결과를 살펴본다.0$\mu$M이 적당하며, 초기배발달을 유기할 때의 효과적인 cysteamine의 농도는 25~50$\mu$M인 것으로 판단된다.N)A(N)/N을 제시하였다(A(N)=N에 대한 A값). 위의 실험식을 사용하여 헝가리산 Zempleni 시료(15%$S_{XRD}$)의 기본입자분포로부터 %$S_{XRD}$를 계산한 결과, 16%$S_{XRD}$의 결과값을 얻을 수 있었다. 따라서, 본 연구에서 도출한 관계식들이 유효함을 확인할 수 있었다.계식들이 유효함을 확인할 수 있었다.할 때 약간의 증가

• Applied Microscopy
• /
• v.42 no.2
• /
• pp.67-76
• /
• 2012

The biomimetic approach on the cuticular spinning nozzles of the major ampullate silk glands in the golden-web spider Nephila calvata has been attempted using various visualizing techniques of light and electron microscopes to improve the design of spinning nozzle for producing synthetic nanofibers spun from electrospinning apparatus. The major ampullate spigot which has the most effective nozzle system to produce nanofibers for dragline silk with high strength and elasticity is connected via the bullet type spigot on anterior spinneret with flexible terminal segment. The excretory duct which transports the liquid silk feedstock from ampulla to spigot is divided into 3 limbs by loops back on itself to form an S-shape morphology that is bundled in connective tissue. Final diameter of the nanofibers at nozzle was dramatically reduced by gradual narrowing of duct cuticle less than 10 times comparing to its original size of funnel region. Moreover, the funnel has a characteristic cuticular organization with porous microstructure which seems to be related to water removal from feedstock of silk precursors. High magnification electron micrographs also reveal the presence of the spiral grooves on the surface of the cuticular intima near the valve which presumed to reduce friction during rapid flow of liquid silk.

• Journal of Radiation Protection and Research
• /
• v.30 no.2
• /
• pp.69-75
• /
• 2005

Gas avalanche microdetectors, such as micro-strip gas chamber (MSGC), micro-gap chamber (MGC), micro-dot chamber (MDOT), etc., are operated under high voltage to induce large electron avalanche signal around micro-size anodes. Therefore, the anodes are highly exposed to electrical damage, for example, sparking because of the interaction between high electric field strength and charge multiplication around the anodes. Gas electron multiplier (GEM) is a charge preamplifying device in which charge multiplication can be confined, so that it makes that the charge multiplication region can be separate from the readout micro-anodes in 9as avalanche microdetectors possible. Primary electron collection efficiency is an important measure for the GEM performance. We have defined that the primary electron collection efficiency is the fractional number of electron trajectories reaching to the collection plane from the drift plane through the GEM holes. The electron trajectories were estimated based on 3-dimensional (3D) finite element method (FEM). In this paper, we present the primary electron collection efficiency with respect to various GEM operation parameters. This simulation work will be very useful for the better design of the GEM.

• Journal of Korean Society of Forest Science
• /
• v.94 no.6
• /
• pp.362-369
• /
• 2005

Readability, an indicator measuring the easiness of reading letters, is an important element that determines the communicative effectiveness of self-guided signs. This study examined how the letter design elements of self-guided signs influence on readability to provide basic information for more effective sign designs. Data were collected from August to November of 2003 at a self-guided trail of Naejangsan National Park, Korea. A total of 375 subjects participated in the questionnaire survey, and 94.7% of them were used for data analysis. Among the total of 19 attributes, five attributes such as number of letters, number of type styles, ratio of picture area on the signs, space between letters, type size influenced on readability. These five attributes explained 50.0% of the variation in readability. The number of letters was the most influential attributes on readability, followed by the number of type styles, ratio of picture area on the signs, space between letters, and type size. The effectiveness of signs may be efficiently increased by managing these five major attributes with more concern.

• Journal of Korea Water Resources Association
• /
• v.42 no.3
• /
• pp.213-225
• /
• 2009

A stationary Markov chain model is a stochastic process with the Markov property. Having the Markov property means that, given the present state, future states are independent of the past states. The Markov chain model has been widely used for water resources design as a main tool. A main assumption of the stationary Markov model is that statistical properties remain the same for all times. Hence, the stationary Markov chain model basically can not consider the changes of mean or variance. In this regard, a primary objective of this study is to develop a model which is able to make use of exogenous variables. The regression based link functions are employed to dynamically update model parameters given the exogenous variables, and the model parameters are estimated by canonical correlation analysis. The proposed model is applied to daily rainfall series at Seoul station having 46 years data from 1961 to 2006. The model shows a capability to reproduce daily and seasonal characteristics simultaneously. Therefore, the proposed model can be used as a short or mid-term prediction tool if elaborate GCM forecasts are used as a predictor. Also, the nonstationary Markov chain model can be applied to climate change studies if GCM based climate change scenarios are provided as inputs.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.1
• /
• pp.140-145
• /
• 2010

In this work, to theoretically analyze the nonlinear charging characteristic, a Radial Basis Function Neural Network (RBFNN) is adopted. Based on the RBFNN, an charging characteristic tendency of a Linear Type Magnetic Flux Pump (LTMFP) is analyzed. In the paper, we developed the LTMFP that generates stable and controllable charging current and also experimentally investigated its charging characteristic in the cryogenic system. From these experimental results, the charging current of the LTMFP was also found to be frequency dependent with nonlinear quality due to the nonlinear magnetic behaviour of superconducting Nb foil. On the whole, in the case of essentially cryogenic experiment, since cooling costs loomed large in the cryogenic environment, it is difficult to carry out various experiments. Consequentially, in this paper, we estimated the nonlinear characteristic of charging current as well as realized the intelligent model via the design of RBFNN based on the experimental data. In this paper, we view RBF neural networks as predominantly data driven constructs whose processing is based upon an effective usage of experimental data through a prudent process of Fuzzy C-Means clustering method. Also, the receptive fields of the proposed RBF neural network are formed by the FCM clustering.