• Journal of Korea Water Resources Association
• /
• v.45 no.10
• /
• pp.1023-1034
• /
• 2012

Linear regression technique has been used widely in water resources field as well as various fields such as economics and statistics, and so on. Using fuzzy regression technique, it is possible to quantify uncertainty and reflect them to the regression model. In this study, fuzzy regression model is developed to compute design floods in any place in Pyeongchang River basin. In ungaged basins, it is usually difficult to obtain data required for flood discharge analysis. In this study, basin characteristics elements are analyzed spatially using GIS and the technique of estimating design flood in ungaged mountainous basin is studied based on the result. Fuzzy regression technique is applied to Pyeongchang River basin which has mountainous basin characteristics and well collected rainfall and runoff data through IHP test basin project. Fuzzy design flood estimation equations are developed using the basin characteristics elements for Pyeongchang River basin. The suitability of developed fuzzy equations are examined by comparing the results with design floods computed in 9 locations along the river. Using regional regression method and fuzzy regression analysis, the uncertainties of the design floods occurred from the data monitoring can be quantified.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2011.05a
• /
• pp.25-25
• /
• 2011

우리나라는 국토의 60% 이상이 산지로 이루어져 있다. 최근 산지하천 유역에서 발생한 홍수와 토석류 등에 의해 많은 인적 물적 피해가 발생하고 있다. 현재 산지하천 유역은 유량자료에 비해 강우관측 자료는 비교적 많이 축적되어있으며, 최근에는 레이더를 이용한 강우관측도 지속적으로 이루어져 강우특성을 분석하는 것은 용이하다. 이에 비해서 산지하천 유역의 하천 유량에 대한 자료는 부족하거나 자료가 있더라도 결측치가 많고 보유연한이 분석에 필요한 만큼 충분하지 못하다. 또한 산지하천 유역의 유출특성을 분석하기 위해서는 강우관측 자료와 수위자료로부터 환산된 유량자료가 필수적인 인자이나 산지하천 유역의 수위관측소는 설치 및 유지관리 등의 어려움으로 인하여 유량자료가 상대적으로 부족한 실정이다. 이와 같은 제약을 해소하기 위해서는 많은 비용과 시간이 소요되므로 단 시간 내에 해결하는 것은 쉬운 일이 아니다. 따라서 유역의 물리적 특성을 이용하여 임의의 지점의 설계홍수량을 손쉽고, 정확하게 산정할 수 있다면 산지유역의 홍수와 토석류에 의해 발생하는 홍수 피해에 대한 대책을 마련하는데 큰 도움이 될 것이다. 일반적인 통계적 회귀분석은 여러 분야에서 널리 적용되고 있으나, 산지하천 유역의 강우-유출해석의 경우 관측자료의 수가 적고 발생하는 사상이 애매한 경우가 많아 일반적인 통계학적 선형 회귀분석을 적용하는 데 어려움이 많다. 이와 같은 어려움을 해결하기 위해 본 연구에서는 fuzzy regression 기법을 사용하였다. Fuzzy regression 기법의 하나인 possibilistic 모형을 사용하여 주어진 관측값과 산정값의 오차를 최소화함으로써 모형의 fuzziness를 최소화하였다. fuzzy regression 기법을 사용하면 변수들 간의 애매한 관계를 쉽게 해석하고 관측값과 산정값의 오차를 최소화하여 연구목적에 적합한 결과를 도출할 수 있다. 산지유역에서 발생하는 홍수는 많은 인명 및 재산피해뿐 아니라 사회 및 경제적 측면, 환경 및 생태계 그리고 인간의 정신적인 측면까지도 깊이 영향을 미친다. 따라서 본 연구에서 제안한 fuzzy regression 기법을 사용한 홍수량 산정기법을 통해 임의 지점의 빈도별 설계홍수량을 보다 신속하고 정확하게 산정하여 수공구조물의 설계에 적용하면 집중호우에 의해 발생하는 피해를 최소할 할 수 있을 것으로 기대된다.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.17 no.6
• /
• pp.54-59
• /
• 2003

This paper presents hourly system marginal price forecasting of the Korea electric power system using a fuzzy linear regression analysis method. The proposed method is tested by forecasting hourly system marginal price for a week of spring in 2002. The percent average of forecasting error for the proposed method is from 3.14% to 6.10% in the weekdays, from 7.04% to 8.22% in the weekends, and comparable with a artificial neural networks method.

• Journal of The Geomorphological Association of Korea
• /
• v.23 no.2
• /
• pp.109-125
• /
• 2016

This study aims to identify the landslide susceptible zones of Boeun area and provide reliable landslide susceptibility maps by applying different modeling methods. Aerial photographs and field survey on the Boeun area identified landslide inventory map that consists of 388 landslide locations. A total ofseven landslide causative factors (elevation, slope angle, slope aspect, geology, soil, forest and land-use) were extracted from the database and then converted into raster. Landslide causative factors were provided to investigate about the spatial relationship between each factor and landslide occurrence by using fuzzy set and logistic regression model. Fuzzy membership value and logistic regression coefficient were employed to determine each factor's rating for landslide susceptibility mapping. Then, the landslide susceptibility maps were compared and validated by cross validation technique. In the cross validation process, 50% of observed landslides were selected randomly by Excel and two success rate curves (SRC) were generated for each landslide susceptibility map. The result demonstrates the 84.34% and 83.29% accuracy ratio for logistic regression model and fuzzy set model respectively. It means that both models were very reliable and reasonable methods for landslide susceptibility analysis.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.12 no.4
• /
• pp.334-340
• /
• 2002

This paper proposes a self-organizing fuzzy modeling which can create a new hyperplane-shaped cluster by applying multiple regression to input/output data with relatively large fuzzy entropy, add the new cluster to fuzzy rule base and adjust parameters of the fuzzy model in repetition. Tn the coarse tuning, weighted recursive least squared algorithm and fuzzy C-regression model clustering are used and in the fine tuning, gradient descent algorithm is used to adjust parameters of the fuzzy model precisely And learning rates are optimized by utilizing meiosis-genetic algorithm. To check the effectiveness and feasibility of the suggested algorithm, four representative examples for system identification are examined and the performance of the identified fuzzy model is demonstrated in comparison with that of the conventional fuzzy models.

• Journal of Korean Society of Steel Construction
• /
• v.9 no.4 s.33
• /
• pp.579-588
• /
• 1997

During the construction of cable stayed bridge, errors are always caused by various reasons, accumulated and amplified through the complex construction steps. It is likely that the undesirable stress distribution of members and the large deflection of the bridge different from design values come out The adjustment of cables during construction is absolutely indispensable to correct the stress distribution of the members and the geometrical configuration of the bridge. In the conventional method, weight coefficients are used to consider the difference of units between cable forces and girder deflections during the optimization process of cable adjustment. However, it is not easy to determine weight coefficients and the adjustment must be repeated several times with the time consuming process of the determination of new weight coefficients in case that errors are out of design allowable limits. In this paper, fuzzy linear regression analysis is applied to the cable adjustment to overcome those problems. In the application of fuzzy linear regression analysis method the designer's intention and the design allowable limits can be formulated in the form of the constraints of the linear optimization problem. Therefore, the cable adjustment in construction site can be carried out with the fuzzy linear regression analysis more rapidly than with the convetional method.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2012.05a
• /
• pp.382-386
• /
• 2012

최근 산지하천 유역에서 발생하는 홍수와 이를 동반한 토석류에 의해 많은 인적, 물적 피해가 빈번히 발생하고 있다. 이러한 피해를 최소화하기 위해서는 유역의 정확한 홍수유출량 해석이 동반되어야 하지만 산치하천 유역은 유출특성 분석에 기본이 되는 수위관측소의 수가 적고, 관측소가 존재하더라도 결측치가 많거나 자료보유 연한이 짧아 자료의 활용성이 떨어진다. 따라서 선행 연구에서는 미비한 자료만으로도 회귀분석이 가능하며 높은 신뢰도를 갖는 Fuzzy 회귀분석 기법을 도입하여 수위자료 없이도 산지하천 유역의 유역면적과 하도경사를 바탕으로 홍수유출량을 평가할 수 있는 기술을 개발하였다. 본 연구에서는 여기에 빈도별 강우량을 새롭게 추가하여 홍수량 산정식을 개선 및 보완하였다. 새롭게 도출된 홍수량 산정식의 정확도는 기존 대상유역 내 특정지점 설계홍수량을 기준으로 기존 개발된 홍수량 산정식과 비교하여 검토하였고 비교적 높은 정확도를 나타냈다. 이를 바탕으로 일반 사용자도 손쉽게 홍수량을 산정할 수 있도록 MATLAB을 이용하여 홍수량 산정 프로그램을 개발하였다.

• Journal of Korean Institute of Industrial Engineers
• /
• v.28 no.3
• /
• pp.331-343
• /
• 2002

This paper proposes a fuzzy rule-based model as a means to build usability models between emotional satisfaction and design variables of consumer products. Based on a subtractive clustering algorithm, this model obtains partially overlapping rules from existing data and builds multiple local models each of which has a form of a linear regression equation. The best subset procedure and cross validation technique are used to select appropriate input variables. The proposed technique was applied to the modeling of luxuriousness, balance, and attractiveness of office chairs. For comparison, regression models were built on the same data in two different ways; one using only potentially important variables selected by the design experts, and the other using all the design variables available. The results showed that the fuzzy rule-based model had a great benefit in terms of the number of variables included in the model. They also turned out to be adequate for predicting the usability of a new product. Better yet, the information on the product classes and their satisfaction levels can be obtained by interpreting the rules. The models, when combined with the information from the regression models, are expected to help the designers gain valuable insights in designing a new product.

• Proceedings of the KIEE Conference
• /
• 2001.11c
• /
• pp.416-419
• /
• 2001

In this paper a new approach to estimate scaling factors of fuzzy controllers such as the fuzzy PID controller and the fuzzy PD controller is presented. The performance of the fuzzy controller is sensitive to the variety of scaling factors[1]. The desist procedure dwells on the use of evolutionary computing(a genetic algorithm) and estimation algorithm for dynamic systems (the inverted pendulum). The tuning of the scaling factors of the fuzzy controller is essential to the entire optimization process. And then we estimate scaling factors of the fuzzy controller by means of two types of estimation algorithms such as Neuro-Fuzzy model, and regression polynomial [7]. This method can be applied to the nonlinear system as the inverted pendulum. Numerical studies are presented and a detailed comparative analysis is also included.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2007.11a
• /
• pp.345-349
• /
• 2007

In this study a fuzzy trend monitoring method for detecting the engine mechanical faults was proposed through analyzing performance trends of measurement data. The trend monitoring is an engine conditioning method which can find engine faults by monitoring important measuring parameters such as fuel flow, exhaust gas temperatures, rotational speeds, vibration. etc. Using engine condition data set as a input which generated by linear regression analysis of real engine instrument data, an application of fuzzy logic in diagnostics estimate a cause of fault in each components.