• Proceedings of the Korea Water Resources Association Conference
• /
• 2008.05a
• /
• pp.2061-2065
• /
• 2008

본 연구는 강우-유출 및 TOC의 패턴 분류를 위하여 광주 광산 강우관측소의 강우량자료와 나주지점의 유출량 그리고 기존의 BOD 및 COD 수질농도 측정값에 비하여 적은 오차요인과 빠른 시간에 결과 값을 얻을 수 있으며 유출량과 난분해성 물질에 대한 해석이 가능하고 재현성이 탁월한 TOC자료를 사용하였다. SOM을 적용하기 위해 먼저 Map의 크기는 Garcia가 제시한 $M=5{\sqrt{N}}$을 이용하여 결정한다. 이러한 비선형적인 다변량 자료를 분석하기 위해서 Map에 의해 구분된 자료 위치를 추출하여 원자료를 재구축하고 이를 통해 원자료를 패턴별로 분류 할 수 있었다. 이러한 패턴별 분류를 통해 유출량에 따른 TOC자료를 2차원의 Map 상에 시각적으로 가시화하여 비선형적인 경향이 강한자료의 분포적 양상을 이해하는데 큰 도움이 되며, 향후 이를 통해 예측을 위한 모형화 과정에도 크게 도움을 줄 것으로 기대된다. 또한, 강우자료 또는 유출량 자료만을 이용한 단일변량의 패턴분류를 위해 SOM의 적용이 가능할 것으로 판단되며, 이는 각 변량의 본질적인 특성을 파악할 수 있을 것으로 기대된다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.376-380
• /
• 2011

강우사상은 강우량, 지속기간, 강우강도 등의 특성으로 표현될 수 있으며 이런 인자들을 같이 고려할수록 그 현상을 보다 종합적으로 표현할 수 있다. 하지만 현재 일반적으로 이루어지는 일변량 빈도해석절차에서는 지속기간을 고정시켜놓고 각 지속시간에 따른 결과만을 도출해 낼 수 있기 때문에 지속기간에 대해 제약적이고 입력자료에 존재하지 않는 지속기간에 대한 결과를 얻기가 어렵다. Copula모델은 두 일변량 분포형을 다변량 분포형으로 연결하여 주는 모델이다. 따라서 강우량과 지속기간을 변수로 사용하면 Copula모델을 통한 이변량 강우빈도해석은 보편적으로 이루어지고 있는 일변량 지점빈도해석보다 지속기간에 대해 유연한 결과를 나타낼 수 있다. 즉, 강우와 지속기간이 동시에 변수로 사용되기 때문에 임의의 지속기간이나 강우에 대해서 확률강우량 및 확률지속기간을 얻을 수 있다. 본 연구에서는 서울지점을 대상으로 1961∼2009년 동안 발생한 강우사상 중 각 년도에서 최대강우량이 발생한 사상을 추출하여 입력자료로 사용하였다. Copula 모형은 Gumbel-Hougaard, Frank, Joe, Clayton, Galambos등 총 5개의 모델을 적용하였고 각 Copula의 매개변수는 준모수방법인 maximum pseudolikelihood estimator를 이용하여 추정하였다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2017.05a
• /
• pp.463-463
• /
• 2017

최근 다변량 확률모형 연구 및 기후변화에 따른 강우패턴 연구의 증가에 따라 시계열로 기록되어 있는 강우량 자료로부터 강우사상(Event)을 분리하는 연구 또한 활발히 이루어지고 있다. 일반적으로 강우사상은 최소무강우시간(Inter-Event Time)을 기준으로 전후강우가 독립적인 강우인지 연속적인 강우인지 구별하는데 이 최소무강우시간을 결정하는 방법이 각 사용되는 분야마다 일관되지 않은 점이 있다. 본 연구에서는 30년 이상 기록된 기상청 강우관측소 자료를 이용하였으며, 설계강우의 시간분포를 위한 Huff 4분위법에서 사용되는 6시간의 최소무강우시간분터 지수확률분포 방법으로 얻어지는 최소무강우시간(일반적으로 12시간 내외)까지 최소무강우시간의 변화에 따라 분리된 강우사상의 특성을 분석하였다. 또한 강우사상의 이변량 빈도해석 적합성을 검토하기 위해 연최대강우량 사상을 선정하여 빈도해석을 수행하였으며 최소무강우 시간에 따라 이변량 확률분포형 적합성을 검토하였다.

• International Area Studies Review
• /
• v.21 no.4
• /
• pp.223-245
• /
• 2017

This study is examined interaction between carbon market with stock market using a multivariate GARCH(DCC) model. Carbon market is EU ETS EUA price, stock market is the iron and cement stock price which has relatively energy intensive and massive carbon emissions sector in the industrial sector. It also analyzed changes in the correlation between the markets through an analysis of correlation coefficients. Moreover, it checked whether there was marketability expansion(or expansion of carbon emissions reduction) through the analysis above. As a result of empirical tests, it showed that the price spillover effect was insignificant. In addition, it represented that there was a weak correlation between the two markets since the volatility spillover effect disappeared in the second phase by an external shock(a financial crisis). Moreover, it was revealed that there were no significant changes although there was a weak upward trend in terms of the correlation between the carbon market and the stock market. This implies that emission rights could not expand marketability to financial market as a commodity(or did not play its natural role of the reduction of carbon emission).

• Water for future
• /
• v.29 no.2
• /
• pp.235-247
• /
• 1996

Meteorological and soil water content data measured from semiarid watersheds of Lucky Hills and Kendall during the summer rainy and winter periods were used to study the interrelationships between the controlling variables of the evapotranspiration, and to evaluate the effects of variables on daily actual evapotranspiration (ET) estimation. Simple and multiple linear regression (MLR) analyses were employed to evaluate the order of importance of the meteorological and soil water factors involved. The information gained was used for MLR model development. Theavailable energy and vapor pressure deficit were found to be the important variables to estimate actual ET (AET) for both periods and at both watersheds. Therefore, the important variables of evapotranspiration process in these semiarid watersheds appear to be simply the components of energy term in available energy and aerodynamic term in vapor pressure deficit of Penman potential evapotranspiration (PET) equation.

• Communications for Statistical Applications and Methods
• /
• v.16 no.6
• /
• pp.925-936
• /
• 2009

There very many approaches to impute missing values in the iid. case. However, it is hardly found the imputation techniques in the Markov random field(MRF) case. In this paper, we show that the imputation under MRF is just to impute by fitting the normal mixture model(NMM) under several practical assumptions. Our multivariate normal mixture model based approaches under MRF is applied to impute the missing pixel values of 3-variate (R, G, B) color image, providing a technique to smooth the imputed values.

• Communications for Statistical Applications and Methods
• /
• v.16 no.3
• /
• pp.449-461
• /
• 2009

Higher sigma quality level is generally perceived by customers as improved performance by assigning a correspondingly higher satisfaction score. The process capability indices and the sigma level $Z_{st}$ ave been widely used in six sigma industries to assess process performance. Most evaluations on process capability indices focus on statistical estimation under normal process which may result in unreliable assessments of process performance. In this paper, we consider statistical estimation for bivariate VPCI(Vector-valued Process Capability Index) $C_{pkl}=(C_{pklx},\;C_{pklx})$ under Marshall and Olkin (1967)'s bivariate exponential process. First, we derive some limiting distribution for statistical inference of bivariate VPCI $C_{pkl}$. And we propose two asymptotic normal confidence regions for bivariate VPCI $C_{pkl}$. The proposed method may be very useful under bivariate exponential process. A numerical result based on our proposed method shows to be more reliable.

• Economic and Environmental Geology
• /
• v.55 no.4
• /
• pp.353-366
• /
• 2022

Spatial estimation of geoscience data (geo-data) is challenging due to spatial heterogeneity, data scarcity, and high dimensionality. A novel spatial estimation method is needed to consider the characteristics of geo-data. In this study, we proposed the application of Gaussian Mixture Model (GMM) among machine learning algorithms with multivariate data for robust spatial predictions. The performance of the proposed approach was tested through soil chemical concentration data from a former smelting area. The concentrations of As and Pb determined by ex-situ ICP-AES were the primary variables to be interpolated, while the other metal concentrations by ICP-AES and all data determined by in-situ portable X-ray fluorescence (PXRF) were used as auxiliary variables in GMM and ordinary cokriging (OCK). Among the multidimensional auxiliary variables, important variables were selected using a variable selection method based on the random forest. The results of GMM with important multivariate auxiliary data decreased the root mean-squared error (RMSE) down to 0.11 for As and 0.33 for Pb and increased the correlations (r) up to 0.31 for As and 0.46 for Pb compared to those from ordinary kriging and OCK using univariate or bivariate data. The use of GMM improved the performance of spatial interpretation of anthropogenic metals in soil. The multivariate spatial approach can be applied to understand complex and heterogeneous geological and geochemical features.

• Asia-Pacific Journal of Business Venturing and Entrepreneurship
• /
• v.11 no.3
• /
• pp.1-15
• /
• 2016

This study has analyzed predication capabilities leveraging multi-variate model, logistic regression model, and artificial neural network model based on financial information of medium-small sized companies list in KOSDAQ. 83 delisted companies from 2009 to 2012 and 83 normal companies, i.e. 166 firms in total were sampled for the analysis. Modelling with training data was mobilized for 100 companies inlcuding 50 delisted ones and 50 normal ones at random out of the 166 companies. The rest of samples, 66 companies, were used to verify accuracies of the models. Each model was designed by carrying out T-test with 79 financial ratios for the last 5 years and identifying 9 significant variables. T-test has shown that financial profitability variables were major variables to predict a financial risk at an early stage, and financial stability variables and financial cashflow variables were identified as additional significant variables at a later stage of insolvency. When predication capabilities of the models were compared, for training data, a logistic regression model exhibited the highest accuracy while for test data, the artificial neural networks model provided the most accurate results. There are differences between the previous researches and this study as follows. Firstly, this study considered a time-series aspect in light of the fact that failure proceeds gradually. Secondly, while previous studies constructed a multivariate discriminant model ignoring normality, this study has reviewed the regularity of the independent variables, and performed comparisons with the other models. Policy implications of this study is that the reliability for the disclosure documents is important because the simptoms of firm's fail woule be shown on financial statements according to this paper. Therefore institutional arragements for restraing moral laxity from accounting firms or its workers should be strengthened.

• Journal of Technology Innovation
• /
• v.27 no.4
• /
• pp.21-48
• /
• 2019

In the basic research field, quantitative expansion is carried out with active support from the government, but there is no research and policy data suggesting systematic investment plans or data-based financial requirements yet. Therefore, this study predicted future financial requirements of basic research support programs by using time series prediction model. In order to consider various factors including the characteristics of the basic research field, we selected the ARIMAX model which can reflect the effect of multi valuable factors rather than the ARIMA model which predicts the value of single factor over time. We compared the predictions of ARIMAX and ARIMA models for model suitability and found that the ARIMAX model improves the prediction error rate. Based on the ARIMAX model, we predicted the fiscal spending of basic research support programs for five years from 2017 to 2021. This study has significance in that it considers the financial requirements of the basic research support programs as a pilot research conducted by applying a time series model, which is a statistical approach, and multi-variate rather than single-variate. In addition, considering the policy trends that emphasize the importance of basic research investment such as 'the expansion of basic research budget twice', which is the current government's national policy task, it can be used as reference data in establishing basic research investment strategy.