• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.46-46
• /
• 2017

지역가뭄빈도분석의 분위산정에 대한 신뢰성은 수문학적으로 균일한 지역으로 구분하기 위해 사용된 장기간의 과거 자료와 분석절차에 의해 결정된다. 그러나 극심한 가뭄은 매우 드물게 발생하며 신뢰 할 수 있는 지역빈도분석을 위한 지속기간이 충분치 않는 경우가 많이 발생한다. 이 외에도 우리나라의 복잡한 지형적 및 기후적 특징은 동질한 지역으로 구분하기 위한 통계적인 처리방법이 필요하였다. 본 연구에서 적용한 지역빈도분석은 여러 지역의 다양한 변수인 수문기상 특성을 분석하여 동질한 지역을 확인하고, 주요 가뭄변수(지속 시간 및 심각도)를 통합 적용하여 각각의 동질한 지역 분위를 추정함으로써 동질한 지역을 구분하는 해결책을 제시하였다. 본 연구에서는 가우시안 혼합 모형(Gaussian Mixture Model)을 기반으로 기반 군집분석 방법을 적용하여 최적의 동질한 지역을 구분하고 그 결과를 우도비검정 및 다른 유효성 검사 지수를 이용해서 확인하였다. 가우시안 혼합 모델에서 산정했던 매개변수를 방향저감 공간으로 표현하기 위해서 가우시안 혼합 모델방향 저감(GMMDR)방법을 적용하였다. 이 변수는 가뭄빈도분석을 위해 다양한 분포와 코풀라(copula) 적합도를 이용하여 추정 비교하였다. 그 결과 우리나라를 4개의 동질한 지역으로 나누게 되었다. 가우시안과 Frank copula를 이용한 Pearson type III(PE3) 분포는 우리나라의 가뭄 기간과 심각도의 공동 분포를 추정하는데 적합한 것으로 나타났다.

• Journal of Korean Society of Transportation
• /
• v.21 no.3
• /
• pp.15-22
• /
• 2003

In general, the linear regression model has been used to estimate trip generation in the travel demand forecasting procedure. However, the model suffers from several methodological limitations. First, trips as a dependent variable with non-negative integer show discrete distribution but the model assumes that the dependent variable is continuously distributed between -$\infty$ and +$\infty$. Second, the model may produce negative estimates. Third, even if estimated trips are within the valid range, the model offers only forecasted trips without discrete probability distribution of them. To overcome these limitations, a poisson model with a assumption of equidispersion has frequently been used to analyze count data such as trip frequencies. However, if the variance of data is greater than the mean. the poisson model tends to underestimate errors, resulting in unreliable estimates. Using overdispersion test, this study proved that the poisson model is not appropriate and by using Vuong test, zero inflated negative binomial model is optimal. Model reliability was checked by likelihood test and the accuracy of model by Theil inequality coefficient as well. Finally, marginal effect of the change of socio-demographic characteristics of households on trips was analyzed.

• Management & Information Systems Review
• /
• v.28 no.4
• /
• pp.93-108
• /
• 2009

This study examines the asymmetric volatility in the Korean bond market and stock market by using the KTB Prime Index and KOSPI. Because accurate estimation and forecasting of volatility is essential before investing assets, it is important to understand the asymmetric response of volatility in bond market. Therefore I investigate the existence of asymmetric volatility in Korean bond market unlike the previous studies which mainly focused on stock returns. The main results of the empirical analysis with GARCH and GJR-GARCH model are as follow. At first, it exists the asymmetric volatility on KOSPI returns like the previous studies. Also, I find that the GJR-GARCH is more suitable one than GARCH model for forecasting volatility. Second, it does not exist the asymmetric volatility on KTB Prime Index returns. This result is showed by that using the GARCH model for forecasting volatility in bond market is sufficient.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37A no.11
• /
• pp.943-951
• /
• 2012

In this paper, we propose a novel spectrum sensing scheme based on the order statistic for cooperative cognitive radio network in non-Gaussian noise environments. Specifically, we model the ambient noise as the bivariate isotropic symmetric ${\alpha}$-stable random variable, and then, propose a cooperative spectrum sensing scheme based on the order of observations and the generalized likelihood ratio test. From numerical results, it is confirmed that the proposed scheme offers a substantial performance improvement over the conventional scheme in non-Gaussian noise environments.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.369-385
• /
• 1999

For the growth curve model with arbitrary covariance structure, known as unstructured covariance matrix, the problems of detecting outliers are discussed in this paper. In order to detect outliers in the growth curve model, the likelihood ratio testing statistics in mean shift model is established and its distribution is derived. After we detected outliers in growth curve model, we test homo and/or hetero-geneous covariance matrices using PSR Quasi-Bayes Criterion. For illustration, one numerical example is discussed, which compares between before and after outlier deleting.

• Journal of the Korean Data and Information Science Society
• /
• v.10 no.2
• /
• pp.319-327
• /
• 1999

Zero-Inflated Poisson distributions have been widely used for defect-free products in manufacturing processes. It is very interesting to check the shift after the unknown changepoint. If the detectives are caused by the two different types of factor, we should use bivariate zero-inflated model. In this paper, likelihood ratio tests were used to detect the shift of changes after the changepoint. Some inferences for the parameters in this model were made.

• Journal of the Korea Society for Simulation
• /
• v.18 no.3
• /
• pp.103-112
• /
• 2009

In a nuclear power plant (NPP), periodic sensor calibrations are required to assure sensors are operating correctly. However, only a few faulty sensors are found to be calibrated. For the safe operation of an NPP and the reduction of unnecessary calibration, on-line calibration monitoring is needed. In this paper, principal component-based Auto-Associative support vector regression (PCSVR) was proposed for the sensor signal validation of the NPP. It utilizes the attractive merits of principal component analysis (PCA) for extracting predominant feature vectors and AASVR because it easily represents complicated processes that are difficult to model with analytical and mechanistic models. With the use of real plant startup data from the Kori Nuclear Power Plant Unit 3, SVR hyperparameters were optimized by the response surface methodology (RSM). Moreover the statistical techniques are integrated with PCSVR for the failure detection. The residuals between the estimated signals and the measured signals are tested by the Shewhart Control Chart, Exponentially Weighted Moving Average (EWMA), Cumulative Sum (CUSUM) and generalized likelihood ratio test (GLRT) to detect whether the sensors are failed or not. This study shows the GLRT can be a candidate for the detection of sensor drift.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.3
• /
• pp.312-317
• /
• 2005

Ubiquitous computing has had an effect to politics, economics, society, culture, education and so forth. For effective management of huge Ubiquitous networks environment, various computers which are connected to networks has to decide automatic optimum with intelligence. Currently in many areas, data mining has been used effectively to construct intelligent systems. We proposed a hybrid support vector machine for Ubiquitous data mining which realized intelligent Ubiquitous computing environment. Many data were collected by sensor networks in Ubiquitous computing environment. There are many noises in these data. The aim of proposed method was to eliminate noises from stream data according to sensor networks. In experiment, we verified the performance of our proposed method by simulation data for Ubiquitous sensor networks.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.33-39
• /
• 2013

In the transformation of response variable in partial linear models outliers can cause a bad effect on estimating the transformation parameter, just as in the linear models. To solve this problem the processes of estimating transformation parameter and detecting outliers are needed, but have difficulties to be performed due to the arbitrariness of the nonparametric function included in the partial linear model. In this study, through the estimation of nonparametric function and outlier detection methods such as a sequential test and a maximum trimmed likelihood estimation, processes for transforming response variable robust to outliers in partial linear models are suggested. The proposed methods are verified and compared their effectiveness by simulation study and examples.

• Journal of the Korean Data and Information Science Society
• /
• v.20 no.2
• /
• pp.377-385
• /
• 2009

Twenty five female students in Seoul participated and were divided into two group in the experiment of weight loss effect of two treatments. Fourteen students(Treatment A group), randomly chosen from the students, had fed on diet foods and exercised over 8 weeks, and the remaining students(Treatment B group) had fed on diet foods only for the same periods. Weights of 25 students had been measured repeatedly four times at an interval of two weeks during 8 weeks, It resulted from mixed model analysis of repeated measurements data that separate Toeplitz pattern for each treatment group was selected as the optimal covariance pattern. Based upon the optimal covariance pattern model, the baseline effect and time effect were found to be highly significant, but the treatment-time interaction effect was found to be insignificant. Finally, the students with diet foods and exercises were more effective in losing weight than the students with only diet foods were.