• Communications for Statistical Applications and Methods
• /
• 제14권1호
• /
• pp.183-193
• /
• 2007

This paper shows that a response function for the center of fuzzy output nay not be the same as that for the spread in a fuzzy linear regression model and then suggests a separate fuzzy regression model makes a distinction between response functions of the center and the spread of fuzzy output. Also we use a least squares method to estimate the separate fuzzy regression model and compare an accuracy of proposed model with another fuzzy regression model developed by Diamond (1988) and Kao and Chyu (2003).

• Journal of the Korean Data and Information Science Society
• /
• 제25권2호
• /
• pp.447-454
• /
• 2014

In many practical machine learning and data mining applications, unlabeled training examples are readily available but labeled ones are fairly expensive to obtain. Therefore semi-supervised learning algorithms have attracted much attentions. However, previous research mainly focuses on classication problems. In this paper, a semi-supervised regression method based on support vector regression (SVR) formulation that is proposed. The estimator is easily obtained via the dual formulation of the optimization problem. The experimental results with simulated and real data suggest superior performance of the our proposed method compared with standard SVR.

• Journal of the Korean Data and Information Science Society
• /
• 제25권6호
• /
• pp.1539-1547
• /
• 2014

In this paper we apply the autoregressive process to the nonlinear quantile regression in order to infer nonlinear quantile regression models for the autocorrelated data. We propose a kernel method for the autoregressive data which estimates the nonlinear quantile regression function by kernel machines. Artificial and real examples are provided to indicate the usefulness of the proposed method for the estimation of quantile regression function in the presence of autocorrelation between data.

• Advances in aircraft and spacecraft science
• /
• 제6권4호
• /
• pp.333-348
• /
• 2019

Low fuel regression rate is the main drawback of hybrid rocket which should be overcome. One of the improvement techniques to this problem is usage of a solid fuel grain with a complicated geometry port, which has been promoted owing to the recent development of additive manufacturing technologies. In the design of a hybrid rocket fuel grain with a complicated geometry port, the understanding of fuel regression behavior is very important. Numerical investigations of fuel regression behavior requires a capturing method of solid fuel surface, i.e. gas-solid interface. In this study, level set method is employed as such a method and the preliminary numerical tool for capturing a hybrid rocket solid fuel surface is developed. At first, to test the adequacy of the numerical modeling, the simulation results for circular port are compared to the experimental results in open literature. The regression rates and oxidizer to fuel ratios show good agreements between the simulations and the experiments, after passing enough time. However, during the early period of combustion, there are the discrepancies between the simulations and the experiments, owing to transient phenomena. Second, the simulations of complicated geometry ports are demonstrated. In this preliminary step, a star shape is employed as complicated geometry of port. The slot number effect in star port is investigated. The regression rate decreases with increasing the slot number, except for the star port with many slots (8 slots) in the latter half of combustion. The oxidizer to fuel ratio increases with increasing the slot number.

• 한국멀티미디어학회논문지
• /
• 제20권8호
• /
• pp.1406-1420
• /
• 2017

Artificial neural networks (ANNs) play an important role in the fields of function approximation, prediction, and classification. ANN performance is critically dependent on the input parameters, including the number of neurons in each layer, and the optimal values of weights and biases assigned to each neuron. In this study, we apply the particle swarm optimization method, a popular optimization algorithm for determining the optimal values of weights and biases for every neuron in different layers of the ANN. Several regression models, including general linear regression, Fourier regression, smoothing spline, and polynomial regression, are conducted to evaluate the proposed method's prediction power compared to multiple linear regression (MLR) methods. In addition, residual analysis is conducted to evaluate the optimized ANN accuracy for both training and test datasets. The experimental results demonstrate that the proposed method can effectively determine optimal values for neuron weights and biases, and high accuracy results are obtained for prediction applications. Evaluations of the proposed method reveal that it can be used for prediction and estimation purposes, with a high accuracy ratio, and the designed model provides a reliable technique for optimization. The simulation results show that the optimized ANN exhibits superior performance to MLR for prediction purposes.

• 응용통계연구
• /
• 제29권1호
• /
• pp.157-169
• /
• 2016

이 논문에서는 비선형 자기회귀 과정을 따르는 오차항을 포함한 회귀모형에서 계수추정법의 비교를 다룬다. 비교를 위해 통상적 최소제곱추정량, 일반화 최소제곱추정량, 모수적 회귀오차 수정법, 비모수적 회귀오차 추정법을 비교하였다. 본 논문에서는 또한 비선형 자기회귀모형의 성질을 전형적인 몇가지 비선형자기회귀 모형을 예를 들어 설명한다. 비교연구의 결과 네 가지 추정량 중에 모든 상황에서 최선인 추정량은 존재하지 않았으나 비모수 회귀오차 수정 방법이 일반적으로 우수한 성능을 보임을 알 수 있다.

• Communications for Statistical Applications and Methods
• /
• 제4권2호
• /
• pp.453-463
• /
• 1997

Nonparametric kernel regression has recently gained widespread acceptance as an attractive method for the nonparametric estimation of the mean function from noisy regression data. Also, the practical implementation of kernel method is enhanced by the availability of reliable rule for automatic selection of the bandwidth. In this article, we propose a method for automatic selection of the bandwidth that minimizes the asymptotic mean square error. Then, the estimated bandwidth by the proposed method is compared with the theoretical optimal bandwidth and a bandwidth by plug-in method. Simulation study is performed and shows satisfactory behavior of the proposed method.

• 전기학회논문지P
• /
• 제67권4호
• /
• pp.183-190
• /
• 2018

Predicting accurate electricity prices is an important task in the electricity trading market. To address the electricity price forecasting problem, various approaches have been proposed so far and it is known that linear regression-based approaches are the best. However, the use of such linear regression-based methods is limited due to low accuracy and performance. In traditional linear regression methods, it is not practical to find a nonlinear regression model that explains the training data well. If the training data is complex (i.e., small-sized individual data and large-sized features), it is difficult to find the polynomial function with n terms as the model that fits to the training data. On the other hand, as a linear regression model approximating a nonlinear regression model is used, the accuracy of the model drops considerably because it does not accurately reflect the characteristics of the training data. To cope with this problem, we propose a new electricity price forecasting method that divides the entire dataset to multiple split datasets and find the best linear regression models, each of which is the optimal model in each dataset. Meanwhile, to improve the performance of the proposed method, we modify the proposed localized linear regression method in the map and reduce way that is a framework for parallel processing data stored in a Hadoop distributed file system. Our experimental results show that the proposed model outperforms the existing linear regression model. Specifically, the accuracy of the proposed method is improved by 45% and the performance is faster 5 times than the existing linear regression-based model.

• 한국지능시스템학회논문지
• /
• 제23권4호
• /
• pp.366-370
• /
• 2013

설명변수와 반응변수 사이의 통계적 관계를 설명하기 위해 사용되는 회귀모형을 분석하는 방법을 회귀분석이라 한다. 본 논문에서는 독립변수와 종속변수에 대한 퍼지관계를 표현하는 퍼지회귀모형를 추정하기 위하여 이상치에 민감하지 않은 로버스트한 추정량인 Theil방법을 소개한다. Theil방법은 설명변수와 반응변수의 ${\alpha}$-수준집합의 각 성분으로 구성된 집합에서 선택한 임의의 두 쌍 자료로부터 계산된 변화율의 중위수를 두 변수에 대한 변화량의 추정량으로 간주한다. 본 논문에서 제안된 Theil방법이 최소자승법을 이용하여 추정된 퍼지회귀모형보다 더 정확할 수 있음을 예제를 통하여 확인한다.

• Journal of the Korean Data and Information Science Society
• /
• 제8권2호
• /
• pp.127-134
• /
• 1997

A method is proposed for the choice of the number of principal components in principal component regression based on the predicted error sum of squares. To do this, we approximately evaluate that statistic using a linear approximation based on the perturbation expansion. In this paper, we apply the proposed method to various data sets and discuss some properties in choosing the number of principal components in principal component regression.