• 지능정보연구
• /
• 제13권2호
• /
• pp.15-26
• /
• 2007

본 연구에서는 기존 Bagging Predictors에 수정을 가한 Modified Bagging Predictors를 이용하여 SOHO에 대한 부도예측 모델을 제시한다. 대기업 및 중소기업에 대한 기업부도예측 모델에 대한 많은 선행 연구가 있어왔지만 SOHO만의 기업부도 예측 모델에 관한 연구는 미비한 상태이다. 금융기관들의 대출 심사 시 대기업 및 중소기업과는 달리 SOHO에 대한 대출심사는 아직은 체계화되지 못한 채 신용정보점수 등의 단편적인 요소를 사용하고 있는 것이 현실이고 이에 따라 잘못된 대출로 인한 금융기관의 부실화를 초래할 위험성이 크다. 본 연구에서는 실제국내은행의 SOHO 대출 데이터 집합이 사용되었다. 먼저, 기업부도 예측 모델에서 우수하다고 연구되어진 인공신경망과 의사결정나무 추론 기법을 적용하여 보았지만 만족할 만한 성과를 이끌어내지 못하여, 기존 기업부도 예측 모델 연구에서 적용이 미비하였던 Bagging Predictors와 이를 개선한 Modified Bagging Predictors를 제시하고 이를 적용하여 보았다. 연구결과, SOHO 부도 예측에 있어서 본 연구에서 제시한 Modified Bagging Predictors가 인공신경망과 Bagging Predictors 등의 기존 기법에 비해서 성과가 향상됨을 알 수 있었다.

• 전기전자학회논문지
• /
• 제13권1호
• /
• pp.36-40
• /
• 2009

시간지연 시스템 제어에서 시스템 모델과 외란에 대한 정보를 정확히 구할 수 있으면 스미스 예측제어기를 이용하여 이상적인 출력 특성을 얻을 수 있다. 따라서 본 논문에서는 모델링 오차 및 외란이 존재하는 시간지연 시스템을 효과적으로 제어할 수 있는 적응제어 알고리즘을 제시하였다. 이를 위하여 시스템 모델과 외란을 검출 할 수 있는 적응관측자 및 적응 알고리즘을 제안하였으며 이 신호들을 이용한 스미스 예측제어기를 구성하였다. 그 결과 모델링 오차 및 외란의 영향을 소거할 수 있는 제어기를 설계 할 수 있었다. 이렇게 구성된 제어기에 대하여 컴퓨터 시뮬레이션을 행하여 제안된 시스템의 효용성 및 우수성을 입증하였다.

• 제어로봇시스템학회논문지
• /
• 제5권8호
• /
• pp.923-931
• /
• 1999

In this paper, a modeling and a robust time-delay control for the reclaimer are investigated. Supplying the same amount of a raw material throughout the reclamation process from the raw yard to a sinter plant is important to keep the quality of the molten steel uniform in blast furnaces. As the actual parameter values of the reclaimer are not available, the boom rotational dynamics are modeled as a second order differential equation with unknown coefficients. The unknown parameters in the nominal model are estimated using a recursive estimation method. Another important factor in the control design of the reclaimer is the large time-delay in output measurement. Assuming a multiplicative uncertainty, that accounts for both the unstructured uncertainty neglected in the modeling and the structured uncertainty contained in the parameter estimation, a robust Smith predictor is designed. A robust stability criterion for the multiplicative uncertainty is also derived. Following the work of Goodwin et al. [4], a quantifying procedure of the multiplicative uncertainty bound, through experiments , is described. Experimental and simulation results are provided.

• 한국산림과학회지
• /
• 제99권2호
• /
• pp.204-212
• /
• 2010

This study was performed in 22 unthinned Larix olgensis plantations in northeast China. Data were collected on 95 sample trees of different canopy positions and the diameter at breast height ($d_{1.3}$) ranged from 5.7 cm to 40.2 cm. The individual tree models for the prediction of vertical distribution of live crown, branch and needle biomass were built. Our study showed that the crown, branch and needle biomass distributions were most in the location of 60% crown length. These results were also parallel to previous crown studies. The cumulative relative biomass of live crown, branch and needle were fitted by the sigmoid shape curve and the fitting results were quite well. Meanwhile, we developed the crown ratio and width models. Tree height was the most important predictor for crown ratio model. A negative competition factor, ccf and bas which reflected the effect of suppression on a tree, reduced the crown ratio estimates. The height-diameter ratio was a significant predictor. The higher the height-diameter ratio, the higher crown ratio is. Diameter at breast height is the strongest predictor in crown width model. The models can be used for the planning of harvesting operations, for the selection of feasible harvesting methods, and for the estimation of nutrient removals of different harvesting practices.

• 한국도로학회논문집
• /
• 제19권2호
• /
• pp.35-44
• /
• 2017

PURPOSES: This study suggests a specific methodology for the prediction of road surface temperature using vehicular ambient temperature sensors. In addition, four kind of models is developed based on machine learning algorithms. METHODS : Thermal Mapping System is employed to collect road surface and vehicular ambient temperature data on the defined survey route in 2015 and 2016 year, respectively. For modelling, all types of collected temperature data should be classified into response and predictor before applying a machine learning tool such as MATLAB. In this study, collected road surface temperature are considered as response while vehicular ambient temperatures defied as predictor. Through data learning using machine learning tool, models were developed and finally compared predicted and actual temperature based on average absolute error. RESULTS : According to comparison results, model enables to estimate actual road surface temperature variation pattern along the roads very well. Model III is slightly better than the rest of models in terms of estimation performance. CONCLUSIONS : When correlation between response and predictor is high, when plenty of historical data exists, and when a lot of predictors are available, estimation performance of would be much better.

• 산업경영시스템학회지
• /
• 제42권4호
• /
• pp.203-210
• /
• 2019

Recently, a number of researchers have produced research and reports in order to forecast more exactly air quality such as particulate matter and odor. However, such research mainly focuses on the atmospheric diffusion models that have been used for the air quality prediction in environmental engineering area. Even though it has various merits, it has some limitation in that it uses very limited spatial attributes such as geographical attributes. Thus, we propose the new approach to forecast an air quality using a deep learning based ensemble model combining temporal and spatial predictor. The temporal predictor employs the RNN LSTM and the spatial predictor is based on the geographically weighted regression model. The ensemble model also uses the RNN LSTM that combines two models with stacking structure. The ensemble model is capable of inferring the air quality of the areas without air quality monitoring station, and even forecasting future air quality. We installed the IoT sensors measuring PM2.5, PM10, H2S, NH3, VOC at the 8 stations in Jeonju in order to gather air quality data. The numerical results showed that our new model has very exact prediction capability with comparison to the real measured data. It implies that the spatial attributes should be considered to more exact air quality prediction.

• 산업융합연구
• /
• 제16권2호
• /
• pp.33-39
• /
• 2018

본 논문은 선형 PID 제어기의 설계 방법에 대해서 설명하였고, 향후 설계 방법에 대해서 제안 하였다. 첫 번째 PID 설계 방법으로는 위상여유와 이득여유를 보장하는 방법이다. 이 방법은 주파수 영역에서 설계하는 것으로 안정도를 보장한다. 두 번째 방법은 내부 모델 제어 방법이다. 이 방법은 제어 모델에 대한 내부 모델을 동정 후 내부 모델의 파라미터를 이용하여 PID 제어기를 설계하는 것이다. 따라서 이 방법은 외란에 강한 특성을 갖고 있다. 마지막으로 제안하는 것은 Cascade-smith-Predictor 제어기 이다. 이방 법의 Cascade 제어기와 smith-Predictor의 구조를 결합한 것으로 강인제어와 최적제어 두 가지 장점을 갖는 제어기 구조이다. 이 방법은 최적 제어기 설계 방법으로 성능 평가지수를 얻을 수 있을 것이다. 이와 같은 PID 제어기 설계 방법은 비선형 방법의 기초가 되며, 지속적인 연구가 수행되고 있다.

• 한국지능시스템학회논문지
• /
• 제21권4호
• /
• pp.449-455
• /
• 2011

본 논문에서는 원격제어 시스템의 시간지연 문제를 분석하고 그 문제를 신경망으로 보상한다. 스미스 예측기는 시간지연 시스템에서 정확한 모델을 필요로 한다. 스미스 예측기의 모델링 오차를 보상하기 위해 신경회로망을 사용한다. 스미스 예측기를 구성하기 위해 Radial Basis Function(RBF) 신경회로망이 사용된다. 시뮬레이션과 실험을 통해 제안하는 방법의 동작을 검증한다.

• 대한간호학회지
• /
• 제28권3호
• /
• pp.550-562
• /
• 1998

The purpose of this study was to test the Theory of Planned Behavior in the prediction of contraceptive behavior among married women. This study used a descriptive correlational design to examine the relationships among the study variables. Eighty married women in Seoul and Kyungki-do participated in this study, Research instruments used were the tool for measuring TPB variables search as attitude toward contraception, subjective norm, perceived behavioral control, and intention ; and the tool for measuring contraceptive behavior. The former was modified by the researcher according to Ajzen & Fishbein(1980)'s guidelines for tool development and Jee (1993)'s tool. The latter was developed by the researcher Data was collected from July 20, 1996 to October 25, 1996. The results are as follows ; The three factors, attitude, subjective norm and perceived behavioral control of contraception can explain 30% of the variance in contraceptive intention. Inspection of path coefficient for each of the three predictor variables revealed that subjective norm and perceived behavioral control were the predictor variables on intention, while attitude was not. ; and intention and percevied behavioral control factors can explain 42% of the variance in contraceptive behavior. Inspection of path coefficient for each of the two predictor variables revealed that intention and perceived behavioral control were the predictor variables on behavior. In conclusion, this study identified that Theory of Planned Behavior was a useful model in the prediction of contraceptive behavior, and the contraceptive service program based on the TPB variables would be an effective nursing intervention for the change in contraceptive behavior.

• Journal of Power Electronics
• /
• 제11권4호
• /
• pp.583-590
• /
• 2011

Three-level NPC inverters have been put into practical use for years especially in high voltage high power grids. This paper researches three-level active power filters (APFs). In this paper a mathematical model in the d-q coordinates is presented for 3-phase 3-wire NPC APFs. The deadbeat control scheme is obtained by using state equations. Canceling the delay of one sampling period and providing the predictive value of the harmonic current is a key problem of the deadbeat control. Based on this deadbeat control, the predictive output current value is obtained by the state observer. The delay of one sampling period is remedied in this digital control system by the state observer. The predictive harmonic command current value is obtained by the repetitive predictor synchronously. The repetitive predictor can achieve a better prediction of the harmonic current with the same sampling frequency, thus improving the overall performance of the system. The experiment results indicate that the steady-state accuracy and the dynamic response are both satisfying when the proposed control scheme is implemented.