• Smart Structures and Systems
• /
• 제15권2호
• /
• pp.409-424
• /
• 2015

Structural nonlinearity is a common phenomenon encountered in engineering structures under severe dynamic loading. It is necessary to localize and identify structural nonlinearities using structural dynamic measurements for damage detection and performance evaluation of structures. However, identification of nonlinear structural systems is a difficult task, especially when proper mathematical models for structural nonlinear behaviors are not available. In prior studies on nonparametric identification of nonlinear structures, the locations of structural nonlinearities are usually assumed known and all structural responses are measured. In this paper, an identification algorithm is proposed for locating and identifying model-free structural nonlinearities and systems using incomplete measurements of structural responses. First, equivalent linear structural systems are established and identified by the extended Kalman filter (EKF). The locations of structural nonlinearities are identified. Then, the model-free structural nonlinear restoring forces are approximated by power series polynomial models. The unscented Kalman filter (UKF) is utilized to identify structural nonlinear restoring forces and structural systems. Both numerical simulation examples and experimental test of a multi-story shear building with a MR damper are used to validate the proposed algorithm.

• 재무관리연구
• /
• 제20권2호
• /
• pp.73-94
• /
• 2003

일반적으로 이자율예측모형은 특정한 이자율 분포모형을 가정하여 모수적 방법에 의해 추정되었다. 그러나 특정한 분포모형을 가정한다는 것은 예측능력을 저하시킬 수 있다는 단점이 있다. 따라서 이자율변화에 특정한 분포모형을 가정하지 않는 비모수적 추정이 이자율 예측의 우월한 방법으로 제시되었다. 본 논문에서는 통화안정증권을 대상으로 이자율 예측 모형을 모수적 방법과 비모수적 방법으로 추정한다. 다음 이자율의 시장위험과 채권가격을 결정하여 두 방법 사이에 유의한 차이가 있는가를 분석한다. 1999년 8월 9일부터 2003년 2월 7일까지 통화안정증권의 일별, 주별 자료를 사용하여 분석한다. 액면이자 효과를 제거하기 위해 복리채만을 분석대상으로 한다. 모수적 방법을 이용할 때 이자율 변화의 추세항은 선형으로 나타나지만 변동성항은 이자율변화에 비해 급격히 변하는 비선형을 나타낸다. 비모수적 분석방법을 이용할 때 추세항과 변동성항 모두 이자율 변화에 비해 급격히 변하는 비선형을 나타낸다. 모수적 방법과 비교하여 추세항은 다른 결과를, 그리고 변동성항은 같은 결과를 보인다. 추세항과 변동성항의 예측을 감안하여 이자율의 시장위험 및 채권가격을 산출한 결과 모수적 방법과 비모수적 방법은 유의적인 차이를 보인다. 이는 이자율 및 이자율의 시장위험가격 예측은 비모수적 방법을 사용하는 것이 적합하다는 것을 뜻한다.

• Communications for Statistical Applications and Methods
• /
• 제17권2호
• /
• pp.141-151
• /
• 2010

Hybrid fuzzy regression analysis is used for integrating randomness and fuzziness into a regression model. Least squares support vector machine(LS-SVM) has been very successful in pattern recognition and function estimation problems for crisp data. This paper proposes a new method to evaluate hybrid fuzzy linear and nonlinear regression models with crisp inputs and fuzzy output using weighted fuzzy arithmetic(WFA) and LS-SVM. LS-SVM allows us to perform fuzzy nonlinear regression analysis by constructing a fuzzy linear regression function in a high dimensional feature space. The proposed method is not computationally expensive since its solution is obtained from a simple linear equation system. In particular, this method is a very attractive approach to modeling nonlinear data, and is nonparametric method in the sense that we do not have to assume the underlying model function for fuzzy nonlinear regression model with crisp inputs and fuzzy output. Experimental results are then presented which indicate the performance of this method.

• Journal of the Korean Data and Information Science Society
• /
• 제28권2호
• /
• pp.461-471
• /
• 2017

In this paper we propose a feature selection method identifying important features in the semivarying coefficient model. One important issue in semivarying coefficient model is how to estimate the parametric and nonparametric components. Another issue is how to identify important features in the varying and the constant effects. We propose a feature selection method able to address this issue using generalized cross validation functions of the varying coefficient least squares support vector regression (LS-SVR) and the linear LS-SVR. Numerical studies indicate that the proposed method is quite effective in identifying important features in the varying and the constant effects in the semivarying coefficient model.

• 한국수자원학회논문집
• /
• 제39권12호
• /
• pp.997-1012
• /
• 2006

본 연구에서는 조건부 핵밀도함수와 CAFPE(Corrected Asymptotic Final Prediction Error) 차수결정 방법에 근거한 비매개변수적 비선형 자기회귀 (Nonlinear AutoRegressive, NAR) 모형을 소개하고 이를 SOI(Southern Oscillation Index)에 적용하였다. SOI 자료에 대해서 선형 AR 모형을 적용하였으나 잔차에 대한 검정결과 이분산성(heteroscedasticity)을 나타내었다. 또한 BDS(Brock-Dechert-Sheinkman) 검정에서 비선형성이 존재함을 확인하였다. 따라서 NAR 모형에 SOI 자료를 적용시켰다. CAFPE를 이용하여 가장 적합한 모형으로 지체 1, 2와 4가 선택되었으며 조건부 평균함수를 추정하여 SOI 자료를 모의한 결과 잔차에 대해서 정규성과 이분산성 가정이 Jarque-Bera 검정과 ARCH-LM 검정에서 각각 기각되었으며 또한 조건부 표준편차함수의 최적 차수로 3, 8과 9가 CAPFE를 통해 선택되었다. 조건부 평균함수와 표준편차함수를 모두 고려한 모형에 대한 잔차 검정 결과 잔차의 I.I.D 가정을 만족하였으며 특히, BDS 검정에서 신뢰구간 95%와 99%에서 모두 만족한 결과를 나타내었다. 마지막으로 전체의 15%에 해당하는 SOI 자료에 대해서 One-Step 예측을 수행하였으며 선형 모형에 비해 평균제곱예측오차가 7% 적게 나타났다. 따라서, NAR 모형은 여타의 매개변수적 방법과 달리 모형 선택에 있어 자유로우며 비선형성을 고려할 수 있는 모형으로서 SOI 자료와 같은 비선형 자료를 위한 모의방법으로 선형 모형에 비해 많은 장점을 가지고 있다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국지능시스템학회 2008년도 춘계학술대회 학술발표회 논문집
• /
• pp.306-310
• /
• 2008

Fuzzy regression, a nonparametric method, can be quite useful in estimating the relationships among variables where the available data are very limited and imprecise. It can also serve as a sound methodology that can be applied to a variety of management and engineering problems where variables are interacting in an uncertain, qualitative, and fuzzy way. A close examination of the fuzzy regression algorithm reveals that the resulting possibility distribution of fuzzy parameters, which makes this technique attractive in a fuzzy environment, is dependent upon an h parameter value. The h value, which is between 0 and 1, is referred to as the degree of fit of the estimated fuzzy linear model to the given data, and is subjectively selected by a decision maker (DM) as an input to the model. The selection of a proper value of h is important in fuzzy regression, because it determines the range of the posibility ditributions of the fuzzy parameters. In this paper, we discuss the interdependent relationship among the h value, membership function shape, and the spreads of fuzzy parameters in fuzzy linear regression with fuzzy input-output using shape-preserving operations.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제8권4호
• /
• pp.306-311
• /
• 2008

Fuzzy regression, a nonparametric method, can be quite useful in estimating the relationships among variables where the available data are very limited and imprecise. It can also serve as a sound methodology that can be applied to a variety of management and engineering problems where variables are interacting in an uncertain, qualitative, and fuzzy way. A close examination of the fuzzy regression algorithm reveals that the resulting possibility distribution of fuzzy parameters, which makes this technique attractive in a fuzzy environment, is dependent upon an h parameter value. The h value, which is between 0 and 1, is referred to as the degree of fit of the estimated fuzzy linear model to the given data, and is subjectively selected by a decision maker (DM) as an input to the model. The selection of a proper value of h is important in fuzzy regression, because it determines the range of the posibility ditributions of the fuzzy parameters. In this paper, we discuss the interdependent relationship among the h value, membership function shape, and the spreads of fuzzy parameters in fuzzy linear regression with fuzzy input-output using shape-preserving operations.

• 한국인공지능학회지
• /
• 제10권1호
• /
• pp.1-7
• /
• 2022

In this paper, a study was conducted to predict natural disasters in Afghanistan based on machine learning. Natural disasters need to be prepared not only in Korea but also in other vulnerable countries. Every year in Afghanistan, natural disasters(snow, earthquake, drought, flood) cause property and casualties. We decided to conduct research on this phenomenon because we thought that the damage would be small if we were to prepare for it. The Azure Machine Learning Studio used in the study has the advantage of being more visible and easier to use than other Machine Learning tools. Decision Forest is a model for classifying into decision tree types. Decision forest enables intuitive analysis as a model that is easy to analyze results and presents key variables and separation criteria. Also, since it is a nonparametric model, it is free to assume (normality, independence, equal dispersion) required by the statistical model. Finally, linear/non-linear relationships can be searched considering interactions between variables. Therefore, the study used decision forest. The study found that overall accuracy was 89 percent and average accuracy was 97 percent. Although the results of the experiment showed a little high accuracy, items with low natural disaster frequency were less accurate due to lack of learning. By learning and complementing more data, overall accuracy can be improved, and damage can be reduced by predicting natural disasters.

• Communications for Statistical Applications and Methods
• /
• 제15권2호
• /
• pp.265-271
• /
• 2008

It is commonly believed that diseases of human or economic traits of livestock are caused not by single genes acting alone, but multiple genes interacting with one another. This issue is difficult due to the limitations of parametric-statistic methods of gene effects. So we introduce multifactor-dimensionality reduction(MDR) as a methods for reducing the dimensionality of multilocus information. The MDR method is nonparametric (i. e., no hypothesis about the value of a statistical parameter is made), model free (i. e., it assumes no particular inheritance model) and is directly applicable to case-control studies. Application of the MDR method revealed the best model with an interaction effect between the SNPs, SNP1 and SNP3, while only one main effect of SNP1 was statistically significant for LMA (p < 0.01) under a general linear mixed model.

• Journal of the Korean Data and Information Science Society
• /
• 제27권5호
• /
• pp.1389-1397
• /
• 2016

Semi-parametric frailty model with nonparametric baseline hazards has been widely used for the analyses of clustered survival-time data. The frailty models can be fitted via an auxiliary Poisson hierarchical generalized linear model (HGLM). For the inferences of the frailty model marginal likelihood, which gives MLE, is often used. The marginal likelihood is usually obtained by integrating out random effects, but it often requires an intractable integration. In this paper, we propose to obtain the MLE via Laplace approximation using a Poisson HGLM approach for semi-parametric frailty model. The proposed HGLM approach uses hierarchical-likelihood (h-likelihood), which avoids integration itself. The proposed method is illustrated using a numerical study.