• Proceedings of the Korea Water Resources Association Conference
• /
• 2010.05a
• /
• pp.1164-1168
• /
• 2010

수자원이 우리 생활의 전반적으로 중요한 역할을 차지하면서 댐의 효율적인 운영과 안정적인 용수공급에 대한 연구는 지속적으로 수행되어지고 있다. 1990년대 이후 비선형적인 특성을 잘 모의하는 장점을 가진 인공신경망(ANN)을 이용하여 유입량 예측에 대한 많은 연구가 수행되었다. 하지만 ANN 모형을 포함한 회귀모형은 월 강우 및 유입량의 예측에 대해 간편하게 사용을 할 수 있지만, 예측의 정확성에 한계를 가지고 있다. 본 연구에서는 ANN 모형과 회귀모형의 예측오차를 후처리 과정을 통하여 오차를 줄임으로써 예측모형의 성과를 향상시키는 방법을 제안하였다. 연구지역은 금강수계의 대청댐 유역으로, 1982년 9월부터 2005년 12월에 해당하는 유역 내 11개 지점의 강우관측소에서 관측한 월 강우와 댐 유입량을 수집하여 모형을 구축하였다. 강우량과 유입량 자료에 대해 자기상관함수와 교차상관함수를 이용하여 입력변수를 결정하였고, 정규화를 통한 전처리 과정을 거쳐 ANN 모형과 회귀모형을 이용한 예측모형을 구축하였으며, 예측성과의 향상을 위하여 군집 분석을 이용하여 오차를 재조정하였다. 이러한 오차 후처리 과정을 포함한 모형은 RMSE와 상관계수를 이용하여 비교 평가한 결과, 예측성과를 약 40% 정도 향상시켰다.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2019.05a
• /
• pp.380-380
• /
• 2019

본 연구에서는 일반 상호보완이론(Generalized Complementary Relationship, GCR)을 활용하여 실제증발산량을 추정하고, 추정한 실제증발산량기반 가뭄지수로부터 미국 전역에 대한 가뭄을 해석하는 것이다. 월강수량, 최고 최저기온, 이슬점온도 등의 필요한 기상자료는 Parameter-elevation Relationships on Independent Slopes Model(PRISM)으로부터 수집하였으며, 1981년부터 2015년까지 총 35년의 미국 전역에 대한 실제증발산량을 추정하였다. 대상지역의 유역평균 강수량과 유출량의 차(P-Q)와 North American Land Data Assimilation System(NLDAS-2) Noah 지표모형(Land surface models)으로 산정한 실제증발산량과 비교 검증하였다. GCR로부터 증발산 부족량(ET Deficit, ETD)을 산정하고 이를 표준정규화하여 미국 전역에 대해 Standardized Evapotranspiration Deficit Index(SEDI)를 산정하였다. 본 연구로부터 GCR 기반 실제증발산량은 P-Q의 값과 상관계수가 0.94로 매우 높은 상관성을 보였으며, NLDAS-2 Noah모형의 실제증발산량보다 다소 크게 추정하는 경향을 보였다. SEDI와 Standard Precipitation Index(SPI)의 상관성은 지속시간이 클수록 더 크게 나타났다. 증발산 상호보완이론활용 실제증발산기반 SEDI이 강수자료를 사용하지 않고서도 적절한 가뭄해석에 이용될 수 있을 것으로 판단된다.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.29 no.5
• /
• pp.1007-1017
• /
• 2019

Currently, most biometrics system authenticates users by using single biometric information. This method has many problems such as noise problem, sensitivity to data, spoofing, a limitation of recognition rate. One method to solve this problems is to use multi biometric information. The multi biometric authentication system performs information fusion for each biometric information to generate new information, and then uses the new information to authenticate the user. Among information fusion methods, a score-level fusion method is widely used. However, there is a problem that a normalization operation is required, and even if data is same, the recognition rate varies depending on the normalization method. A rank-level fusion method that does not require normalization is proposed. However, a existing rank-level fusion methods have lower recognition rate than score-level fusion methods. To solve this problem, we propose a rank-level fusion method with higher recognition rate than a score-level fusion method using correlation coefficient. The experiment compares recognition rate of a existing rank-level fusion methods with the recognition rate of proposed method using iris information(CASIA V3) and face information(FERET V1). We also compare with score-level fusion methods. As a result, the recognition rate improve from about 0.3% to 3.3%.

• The Korean Journal of Applied Statistics
• /
• v.29 no.2
• /
• pp.301-308
• /
• 2016

The process capability index is used to determine whether a production process is capable of producing items within a specified tolerance. Some process capability indices $C_p$, $C_{pk}$ and $C_{pm}$ have been of particular interest as useful management tools for tracking process performance. Most evaluations on process capability indices focus on statistical estimation and test of hypothesis. It is necessary to investigate their asymptotic correlationship among basic estimators ${\hat{C}}_p$, ${\hat{C}}_{pk}$ and ${\hat{C}}_{pm}$ of process capability indices $C_p$, $C_{pk}$ and $C_{pm}$. In this paper, we study their asymptotic correlationship for three process capability indices ${\hat{C}}_p$, ${\hat{C}}_{pk}$ and ${\hat{C}}_{pm}$ under bivariate normal distribution BN(${\mu}_x,{\mu}_y,{\sigma}^2_x,{\sigma}^2_y,{\rho}$). With some nonnormal processes, the asymptotic correlation coefficient of any two respective process capability index estimators could be established.

• KIISE Transactions on Computing Practices
• /
• v.23 no.9
• /
• pp.557-563
• /
• 2017

When large-scale gene expression data are analyzed using lasso regression, the estimation of regression coefficients may be unstable due to the highly correlated expression values between associated genes. This irregularity, in which the coefficients are reduced by L1 regularization, causes difficulty in variable selection. To address this problem, we propose a regression model which exploits the repetitive bootstrapping of gene expression values prior to lasso regression. The genes selected with high frequency were used to build each regression model. Our experimental results show that several genes were consistently selected in all regression models and we verified that these genes were not false positives. We also identified that the sign distribution of the regression coefficients of the selected genes from each model was correlated to the real dependent variables.

• Land and Housing Review
• /
• v.4 no.1
• /
• pp.125-131
• /
• 2013

To predict the real bearing capacity and settlement of the shallow foundation the plate load test results were used. But there is no field estimation method about igneous weathered soil and rock. Therefore, to predict the settlement equation, the plate load test about igneous weathered soil and rock was done in this study. To analyze the load ~ relative settlement curve by normalization, it did not use normal analysis method, but the load ~ relative settlement (s/B, s : settlement, B : breadth of plate) was used. As a result of normalization by load ~ relative settlement conception, the curve was regular regardless of plate diameter and it was suggested the relationship of in-situ soil condition and results.

• Journal of the Korean Society of Radiology
• /
• v.13 no.3
• /
• pp.407-414
• /
• 2019

Recently, after the reorganization as the basis of NCS education, various learning methods are being sought for improving the basic occupational ability and job ability required by NCS, and the evaluation method accordingly is urgently needed. The purpose of this study was to evaluate the applicability of meta-cognitive learning and Havruta learning as evaluation cases in order to improve the job skills and basic skills required in the NCS curriculum. As a result, the meta-cognitive learning response sample statistic showed an average of 2.6883 when the pre-meta-cognitive learning questionnaire was a 5-point scale, and an average of 4.2468 after the meta-cognitive learning questionnaire. The correlation coefficient was 0.782 and the significance probability was 0.045. In the case of the Havruta learning correspondence sample statistic, the average of 3.1515 when the preliminary Havruta learning questionnaire was a 5 point scale and the average of the post-Havruta learning questionnaire was 4.3853, which was improved by 1.23 points. The correlation coefficient was 0.631 and the significance probability was 0.049. Meta-cognitive learning and Havruta learning were found to be correlated. The mean of meta cognition was 3.4675 and the mean of Havruta was 3.7684. Metacognitive learning and Havruta learning were -0.042 And there was no statistically significant difference. Therefore, the learning method to improve the job ability should be applied considering the characteristics of the subject.

• Journal of the Korean GEO-environmental Society
• /
• v.9 no.4
• /
• pp.37-45
• /
• 2008

Normally consolidated and slightly overconsolidated soft clay layer is widely distributed in the south coast of Korea. To ensure the efficient and economical construction design of any structure to be built on this soft soil, exhaustive studies are required related to geotechnical engineering properties. In this study, the relationship of the physical properties of southern marine clay in the Korea Peninsula were examined, including natural water content, specific gravity, total unit weight, initial void ratio, liquid limit, plastic limit, and physical properties of activity and soil parameters. For the parameter relationship analysis, the latest relatively reliable data on the large harbor construction work were used, optimum values were deducted with linear regression and non-linear regression between soil parameters, water content or initial void ratio appears to be very large. Moreover, in the linear and involution pattern regression, equal coefficient of determination appeared. The relationship of the different parameters was shown to be excellent in the non-linear regression of involution equation and exponential equation pattern compared with the findings of linear regression analysis.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.6
• /
• pp.995-1002
• /
• 2020

This paper investigates the achievable data rate for non-orthogonal multiple access(NOMA) with correlated information sources(CIS), under the binary phase shift keying(BPSK) modulation, in contrast to most of the existing NOMA designs using continuous Gaussian input modulations. First, the closed-form expression for the achievable data rate of NOMA with CIS and BPSK is derived, for both users. Then it is shown by numerical results that for the stronger channel user, the achievable data rate of CIS reduces, compared with that of independent information sources( IIS). We also demonstrate that for the weaker channel user, the achievable data rate of CIS increases, compared with that of IIS. In addition, the intensive analyses of the probability density function(PDF) of the observation and the inter-user interferennce(IUI) are provided to verify our theoretical results.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.1
• /
• pp.15-23
• /
• 2022

Among the learning methods for Continuous Learning environments, "Learning without Forgetting" has fixed regularization strengths, which can lead to poor performance in environments where various data are received. We suggest a way to set weights variable by identifying the features of the data we want to learn. We applied weights adaptively using correlation and complexity. Scenarios with various data are used for evaluation and experiments showed accuracy increases by up to 5% in the new task and up to 11% in the previous task. In addition, it was found that the adaptive weight value obtained by the algorithm proposed in this paper, approached the optimal weight value calculated manually by repeated experiments for each experimental scenario. The correlation coefficient value is 0.739, and overall average task accuracy increased. It can be seen that the method of this paper sets an appropriate lambda value every time a new task is learned, and derives the optimal result value in various scenarios.