• Proceedings of the Korea Water Resources Association Conference
• /
• 2020.06a
• /
• pp.264-264
• /
• 2020

최근 기후변화로 우리나라는 과거에 비해 태풍이나 국지성 집중호우 및 가뭄 등 극심한 수문현상이 빈번하게 발생하고 그 피해가 더욱 커지고 있는 추세이다. 특히 우리나라의 경우 산지가 많으며 대부분의 하천이 유역면적이 작고 유로연장이 짧아 단시간에 유출이 발생하며 수문학적 특성이 연중 큰 편차를 보이고 있다. 이러한 이상기후에 따른 수문현상 파악 및 피해 경감을 위해 신뢰성 있는 수문자료는 매우 중요하다. 따라서 수문자료에 대한 품질관리는 필수적이지만 자료 결측 및 오측에 대한 신뢰성 높은 품질관리가 이뤄지지 못하고 있는 실정이다. 현재 수위자료의 결측이 발생한 경우 해당 관측소의 수위 자료를 사용해 선형보간 및 운형자법으로 수정하거나 상·하류 관측소의 관계를 이용하여 회귀분석을 통해 자료 결측의 수정 및 보완을 수행하는 등 담당자의 주관적 판단에 의존하고 있다. 본 논문에서는 신뢰성 높은 수문자료의 결측치 보완 및 예측을 위한 방안을 제시하고자 상류의 관측소의 수문자료를 이용한 하류의 단시간 수문 자료예측에 관한 연구를 수행하였다. 이를 위해 자료지향형 모델인 적응형 뉴로-퍼지 기법(Adaptive Network-based Fuzzy Inference System, ANFIS)을 이용한 모형을 적용하였다. 기존의 연구에서 가장 일반적으로 사용되는 물리적 모형은 수문자료를 활용하여 수위 및 유출을 산정함에 있어 매개변수의 결정이 어렵고 많은 오차들을 내포하고 있다. 본 연구에서 사용한 ANFIS는 입력자료와 출력자료만을 고려하여 구축할 수 있기 때문에 자료 수집단계에서 유역의 물리적 자료 및 지형 자료와 같은 방대한 양의 자료 수집이 필요가 없다. 이후 모형이 구축이 된다면 입·출력 자료만을 이용하여 신뢰성 높은 결과를 획득할 수 있지만 입력 자료의 품질에 따라 결과가 좌우되기 때문에 자료의 구성이 매우 중요하다. 본 연구에서는 ANFIS를 통해 무주남대천 유역의 무주군(여의교) 관측소의 수위자료를 입력자료를 사용하여 하류에 위치한 무주군(취수장) 관측소의 수문자료의 결측 보완 및 예측하는 모형을 구축하고 모형의 구조 변화를 통해 가장 정확도 높은 모형을 결정하였다.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.1
• /
• pp.107-112
• /
• 2015

This paper introduces an evolutionary nonlinear regression based compensation technique for the short-range prediction of wind speed using AWS(Automatic Weather Station) data. Development of an efficient MOS(Model Output Statistics) is necessary to correct systematic errors of the model, but a linear regression based MOS is hard to manage an irregular nature of weather prediction. In order to solve the problem, a nonlinear and symbolic regression method using GP(Genetic Programming) is suggested for a development of MOS wind forecast guidance. Also FCM(Fuzzy C-Means) clustering is adopted to mitigate bias of wind speed data. The purpose of this study is to evaluate the accuracy of the estimation by a GP based nonlinear MOS for 3 days prediction of wind speed in South Korean regions. This method is then compared to the UM model and has shown superior results. Data for 2007-2009, 2011 is used for training, and 2012 is used for testing.

• Journal of Korea Port Economic Association
• /
• v.32 no.4
• /
• pp.73-87
• /
• 2016

The purpose of this study is to investigate the empirical results of Analytic Hierarchy Process/Data Envelopment Analysis-Assurance Region(AHP/DEA-AR) by using multiple regression analysis during the period of 2009-2012 with 5 inputs (number of gantry cranes, number of berth, berth length, terminal yard, and mean depth) and 2 outputs (container TEU, and number of direct calling shipping companies). Assurance Region(AR) is the most important tool to measure the efficiency of seaports, because individual seaports are characterized in terms of inputs and outputs. Traditional AHP and multiple regression analysis techniques have been used for measuring the AR. However, few previous studies exist in the field of seaport efficiency measurement. The main empirical results of this study are as follows. First, the efficiency ranking comparison between the two models (AHP/DEA-AR and multiple regression) using the Wilcoxon signed-rank test and Mann-Whitney signed-rank sum test were matched with the average level of 84.5 % and 96.3% respectively. When data for four years are used, the ratios of the significant probability are decreased to 61.4% and 92.5%. The policy implication of this study is that the policy planners of Korean port should introduce AHP/DEA-AR and multiple regression analysis when they measure the seaport efficiency and consider the port investment for enhancing the efficiency of inputs and outputs. The next study will deal with the subjects introducing the Fuzzy method, non-radial DEA, and the mixed analysis between AHP/DEA-AR and multiple regression analysis.

• Journal of Intelligence and Information Systems
• /
• v.20 no.4
• /
• pp.43-58
• /
• 2014

As the use of trading systems has increased rapidly, many researchers have become interested in developing effective stock market prediction models using artificial intelligence techniques. Stock market prediction involves multifaceted interactions between market-controlling factors and unknown random processes. A successful stock prediction model achieves the most accurate result from minimum input data with the least complex model. In this research, we develop a combination model of ${\pi}$-fuzzy logic and support vector machine (SVM) models, using a genetic algorithm to optimize the parameters of the SVM and ${\pi}$-fuzzy functions, as well as feature subset selection to improve the performance of stock market prediction. To evaluate the performance of our proposed model, we compare the performance of our model to other comparative models, including the logistic regression, multiple discriminant analysis, classification and regression tree, artificial neural network, SVM, and fuzzy SVM models, with the same data. The results show that our model outperforms all other comparative models in prediction accuracy as well as return on investment.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.38 no.4
• /
• pp.295-304
• /
• 2020

The IPCC (Intergovernmental Panel on Climate Change) recommended the importance of preventive measures against extreme weather, and heat waves are one of the main themes for establishing preventive measures. In this study, we tried to analyze the heat vulnerable areas by considering not only spatial characteristics but also social characteristics. Energy consumption, popu lation density, normalized difference vegetation index, waterfront distance, solar radiation, and road distribution were examined as variables. Then, by selecting a suitable model, SLM (Spatial Lag Model), available variables were extracted. Then, based on the Fuzzy theory, the degree of vulnerability to heat waves was analyzed for each variable, and six variables were superimposed to finally derive the heat vulnerable area. The study site was selected as the Daegu area where the effects of the heat wave were high. In the case of vulnerable areas, it was confirmed that the existing urban areas are mainly distributed in Seogu, Namgu, and Dalseogu of Daegu, which are less affected by waterside and vegetation. It was confirmed that both spatial and social characteristics should be considered in policy support for reducing heat waves in Daegu.

• Korea Journal of Hospital Management
• /
• v.10 no.4
• /
• pp.75-97
• /
• 2005

The research objective is to empirically investigate the compensation packages maximizing the utilities of internal customers by applying the market segmentation theory. Data was collected from four Korean hospitals in Seoul, Busan and Gyunggi-do. The research is designed to seek the compensation package maximizing the utility of doctors by mixture regression model, which has been applied as latent structure and other type of finite mixture models from various academic fields since early 1980s. The mixture regression model shows the optimal segments number and fuzzy classification for each observation by EM(expectation-maximization algorism). The finite mixture regression model is to unmix the sample, to identify the groups, and to estimate the parameters of the density function underlying the observed data within each group. The doctors were segmented into 5 groups by their preference for the compensation package. The results of this study imply that the utility of doctors increases with differentiated compensation package segmented by their preference.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2768-2770
• /
• 2001

본 논문은 지능형 알고리즘과 이미지 프로세싱 방법을 결합한 새로운 방법으로 칼라 매칭 시스템에 구현한다. 칼라 매칭 시스템은 이미지 프로세싱을 이용하여 칼라의 RGB 데이터를 분석한 후 얻어진 색상정보를 가지고 사용자가 원하는 칼라는 구현하는 시스템이다. 칼라 매칭 시스템의 모델링에 이용되는 지능형 모델은 퍼지 추론과 적응 퍼지 추론 시스템(Adaptive Neuro-Fuzzy Inference System: ANFIS)이며, 최소 자승법을 기반으로 한 회귀 다항식과 비교하여 제안된 지능형 모델에 대한 성능과 실용성을 검증한 후 델파이를 이용하여 구현하였다.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 2004.05a
• /
• pp.434-436
• /
• 2004

Load forecasting is essential in the electricity market for the participants to manage the market efficiently and stably. The percentage errors of 24 hourly load forecasting for holidays is relatively large. In this paper, we propose the maximum and minimum load forecasting method for holidays using a fuzz linear regression algorithm. 24 hourly loads are forecasted from the maximum and minimum loads and the 24 hourly normalized values. The proposed algorithm is tested for 24 hourly load forecasting in 1996. The test results show the proposed algorithm improves the accuracy of the load forecasting.

• Journal of Korean Society of Transportation
• /
• v.16 no.2
• /
• pp.177-195
• /
• 1998

지능형교통체계(ITS:Intellegent Transport System)의 구현을 위한 가장 중요한 요소중의 하나는 교통정보의 생성이다. 교통정보의 생성은 루프 검지기, 폐쇄회로(CCTV), probe 차량, 경찰, 통신원 등을 수집된 제보자료들을 분석 및 가공함으로써 이루어진다. 그러나 이들 수집원은 주어진 시간에 있어 모든 네트웍을 통해서 자료가 완전히 수집되어지는 것은 아니다. 즉, 특정 지역에 수집원이 몰려 있는 경우가 있는 반면, 전혀 수집되어지지 않는 지역이 발생할 수도 있다. 이러한 공간적인 불균형적 특성은 동시에 발생한 다량의 자료를 처리하는 기술과 자료가 수집되지 않은 지역에 대한 처리기술을 요하게 된다. 본 논문은 전술한 바와 같은 사항에 대하여 ITS의 진행 단계별로 드러날 수 있는 문제점을 검토하고, 자료통합에 대한 일반적인 개념을 우선 설명한다. 다음에 특정시각에 주어진 자료의 통합을 위해 퍼지선형회귀모형(fuzzy linear regression model)과 데이터 퓨전(data fusion)기법의 내용을 소개하고, 신뢰성있는 단일 교통정보생성을 위한 테이터 퓨전 알고리즘을 제시한다. 또한 제시된 알고리즘을 토대로 가상의 자료를 이용하여 적용가능 봉? 타진해 보았다. 제시되어진 알고리즘은 향후 교통정보 수집환경이 어느 정도 형성된다고 볼 때, 예측치와 실측자료간의 자료검증을 통하여 신뢰도를 가질 경우 보다 광범위하게 사용되어질 수 있을 것으로 판단된다.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.34 no.5
• /
• pp.1395-1408
• /
• 2014

In this research, a River Recreation Index Model (RRIM) was developed to provide sufficient information on the water quality of rivers to the public in order to secure safety of publics. River Recreation Index (RRI) is an integrated water quality information for recreation activities in rivers and expressed as the point from 0 to 100. The proposed RRIM consisted of two sub models: Fecal Coliform Model (FCM) and Water Quality Index Model (WQIM). FCM predicted Fecal Coliform Grade (FCG) using a logistic regression and WQIM synthesized water quality parameters of, DO, pH, turbidity and chlorophyll a into Water Quality Index (WQI). FCG and WQI were integrated into RRI by the integrating algorithm. The proposed model was applied to upstream of Gangjeong Weir in Nakdong River, and compared with Real Time Water Quality Index (RTWQI) which is the existing water quality information system for recreation use. The results show that calculated RRI reflected change of integrated water quality parameters well. Especially chlorophyll a showed Pearson correlation coefficient -0.85 with RRI. Also, RRIM produced more conservative index than RTWQI because RRI was calculated considering uncertainty of water quality criteria. Further, RRI showed especially low values when fecal coliform was predicted as low grade.