• 한국컴퓨터정보학회논문지
• /
• 제16권11호
• /
• pp.245-253
• /
• 2011

화석 연료의 무분별한 사용으로 환경이 심각하게 오염되고, 화석 연료의 고갈에 대한 문제가 대두됨에 따라서 화석 연료에 대한 문제를 해결 할 수 있는 대체 에너지원에 대해 관심이 집중되기 시작하였다. 현재 신재생 에너지 중에서 가장 각광을 받고 있는 에너지는 중에 하나가 풍력에너지이다. 풍력에너지 발전단지와 기존의 전력 발전소는 소비되는 전력에 대한 생산의 균형을 맞춰야하며, 풍력에너지단지에서 균형적인 생산을 하기 위해서는 풍력에너지에 대한 분석 및 예측이 필요하다. 이를 위해서 데이터마이닝 분야의 예측 기법이 활용 될 수 있다. 본 논문에서는 풍력 데이터를 이용하여 발전 패턴을 예측하기 위해 SOM(Self-Organizing Feature Map) Clustering 기법과 의사결정나무(decision tree)를 이용한 연구를 진행하였다. 즉, 1) 풍력 데이터의 누락된 데이터와 이상치 데이터를 처리하기 위하여, 전처리 과정을 수행하였고, 이 과정에서 특징 벡터를 추출하였다. 2) 전처리 단계를 거쳐 정제되고 정규화된 데이터 집합을 MIA(Mean Index Adequacy) 척도와 SOM Clustering 기법에 적용하여 대표 발전 패턴을 찾아내고 각각의 데이터에 해당하는 대표 패턴을 클래스 레이블로 할당하도록 하였다. 3) 의사결정나무 기반의 분류 기법에 데이터 집합을 적용시켜 새로운 풍력에너지에 대한 분석 및 예측 모델을 생성하였다. 실험 결과, 의사결정나무를 통한 풍력에너지 발전 패턴을 예측하기 위한 모델을 구축하였다.

• 한국소음진동공학회논문집
• /
• 제24권9호
• /
• pp.695-705
• /
• 2014

In this paper, two types of techniques for the prediction of radiated sound pressure due to vibration of a structure are investigated. The prediction performance using wave-number sensing technique is compared to that of conventional prediction method, such as Rayleigh's integral method, for the prediction of far-field radiated sound pressure. For a coupled plate, wave-number components are predicted by the vibration response of plate and the prediction performance of far-field sound is verified. In addition, the applicability of distributed sensors that are not allowable to Rayleigh's integral method is considered and these can replace point sensors. Experimental implementation verified the prediction accuracy of far-field sound radiation by the wave-number sensing technique. Prediction results from the technique are as good as those of Rayleigh's integral method and with distributed sensors, more reduced computation time is expected. To predict the radiated sound by the efficient configuration of structural sensors, composed(synthesized) mode considering sound power contribution is determined and from this size and location of sensors are chosen. Four types of sensor configuration are suggested, simulated and compared.

• 한국전산유체공학회지
• /
• 제21권2호
• /
• pp.12-24
• /
• 2016

The standard ${\kappa}-{\varepsilon}$ and realizable ${\kappa}-{\varepsilon}$ models are adopted to improve the prediction performance on the recirculating flow. In this paper, the backward facing step flows are used to assess the prediction performance of the recirculation zone. The model constants of turbulence model are obtained by the experimental results and they have a different value according to the flow. In the case of an isotropic flow situation, decaying of turbulent kinetic energy should follow a power law behavior. In accordance with the power law, the coefficients for the dissipation rate of turbulent kinetic energy are not universal. Also, the other coefficients as well as the dissipation coefficient are not constant. As a result, a suitable coefficients can be varied according to each of the flow. The changes of flow over the backward facing step in accordance with model constants of the ${\kappa}-{\varepsilon}$ models show that the reattachment length is dependent on the growth rate(${\lambda}$) and the ${\kappa}-{\varepsilon}$ models can be improved the prediction performance by changing the model constants about the recirculating flow. In addition, it was investigated for the curvature correction effect of the ${\kappa}-{\varepsilon}$ models in the recirculating flow. Overall, the curvature corrected ${\kappa}-{\varepsilon}$ models showed an excellent prediction performance.

• Journal of the Korean Data and Information Science Society
• /
• 제14권2호
• /
• pp.265-274
• /
• 2003

Time series data are influenced by the external events such as holiday, strike, oil shock, and political change, so the external events cause a sudden change to the time series data. We regard the observation as outlier that occurred as a result of external events. In general, it is called intervention if we know the period and the reason of external events, and it makes an analyst difficult to establish a time series model. Therefore, it is important that we analyze the styles and effects of intervention. In this paper, we considered the linear time series model with invention and compared with nonlinear time series models such as ARCH, GARCH model and also we compared with the combination prediction method that Tong(1990) introduced. In the practical case study, we compared prediction power with RMSE among linear, nonlinear time series model with intervention and combination prediction method.

• 한국해양공학회:학술대회논문집
• /
• 한국해양공학회 2001년도 추계학술대회 논문집
• /
• pp.258-263
• /
• 2001

In this paper, the real-time prediction of high temperature creep life was carried out for the friction welded joints of dissimilar heat resistintg steels (CulCr0.5Zr-STS316L). Various life prediction methods such as LMP (Larson-Miller Parameter) and ISM (initial strain method) were applied. The creep behaviors of those steels and the welds under static load were examined by ISM combined with LMP at 300, 400 and 50$0^{\circ}C$, and the relationship between these two methods was investigated. A real-time creep life (tsub/r/, hr) prediction equation by initial strain ($\varepsilon_0$, %) under any creep stress ($\sigma$, MP$\alpha$) at any high temperature (T, K) was developed

• 대한전기학회논문지:전기물성ㆍ응용부문C
• /
• 제52권3호
• /
• pp.137-143
• /
• 2003

The degree of contamination on outdoor insulator is ons of the most importance factor to determine the pollution level of outdoor insulation, and the sea salt is known as the most dangerous pollutant. As shown through the preceding study, the generation of salt pollutant and the pollution degree of outdoor insulator have a close relation with meteorological conditions, such as wind velocity, wind direction, precipitation and so fourth. So, in this paper, we made an investigation on the prediction method, a statistical estimation technique for equivalent salt deposit density of outdoor insulator with multiple linear regression analysis. From the results of the analysis, we proved the superiority of the prediction method in which the variables had a very close(about 0.9) correlation coefficient. And the results could be applied to establish the Pollution Prediction System for power utilities, and the system could provide an invaluable information for the design and maintenance of outdoor insulation system.

• 한국경영과학회지
• /
• 제30권1호
• /
• pp.55-74
• /
• 2005

Bankruptcy prediction has drawn a lot of research interests in previous literature, and recent studies have shown that machine learning techniques achieved better performance than traditional statistical ones. This paper employs a relatively new machine learning technique, support vector machines (SVMs). to bankruptcy prediction problem in an attempt to suggest a new model with better explanatory power and stability. To serve this purpose, we use grid search technique using 5-fold cross-validation to find out the optimal values of the parameters of kernel function of SVM. In addition, to evaluate the prediction accuracy of SVM. we compare its performance with multiple discriminant analysis (MDA), logistic regression analysis (Logit), and three-layer fully connected back-propagation neural networks (BPNs). The experiment results show that SVM outperforms the other methods.

• 한국품질경영학회:학술대회논문집
• /
• 한국품질경영학회 2004년도 품질경영모델을 통한 가치 창출
• /
• pp.655-673
• /
• 2004

This paper is concerned with analysing the bankruptcy prediction power of three models: Multivariate Discriminant Analysis(MDA ), Logit Analysis, Neural Network. The after-crisis bankrupted companies were limited to the research data and the listed companies belonging to manufacturing industry was limited to the research data so as to improve prediction accuracy and validity of the model. In order to assure meaningful bankruptcy prediction, training data and testing data were not extracted within the corresponding period. The result is that prediction accuracy of neural network model is more excellent than that of logit analysis and MDA model when considering that execution of testing data was followed by execution of training data.

• 한국소음진동공학회:학술대회논문집
• /
• 한국소음진동공학회 2012년도 추계학술대회 논문집
• /
• pp.161-166
• /
• 2012

This Study, as part of a study on the application plan of overseas noise prediction models suitable for making domestic noise maps, analyzed the correlation between the differences in predicted noise levels by individual noise prediction model and surveyed data on General roads and Expressways. Separation distances of 5m and 10m, respectively were set from the ends of the general roads and the expressways at the points of measurements and to check the distribution patterns of sound power levels, the levels were measured at the heights of 1.5m and 3m, respectively. The latest revised versions of the five models (CRTN, RLS90, NMPB, Nord2000, ASJ2008) suggested in The Method of making Noise Maps were used as prediction models, and predicted noise levels were calculated by using commercial software SoundPLAN (Ver 7.1).

• 대한안전경영과학회지
• /
• 제7권1호
• /
• pp.199-210
• /
• 2005

Customer segmentation prediction has attracted a lot of research interests in previous literature, and recent studies have shown that artificial neural networks (ANN) method achieved better performance than traditional statistical ones. However, ANN approaches have suffered from difficulties with generalization, producing models that can overfit the data. This paper employs a relatively new machine learning technique, support vector machines (SVM), to the customer segmentation prediction problem in an attempt to provide a model with better explanatory power. To evaluate the prediction accuracy of SVM, we compare its performance with logistic regression analysis and ANN. The experiment results with real data of insurance company show that SVM superiors to them.