• 한국정보통신설비학회:학술대회논문집
• /
• 2009.08a
• /
• pp.382-386
• /
• 2009

Online or sequential learning is one of the most basic and powerful method to train neuron network, and it has been widely used in disease detection, weather prediction and other realistic classification problem. At present, there are many algorithms in this area, such as MRAN, GAP-RBFN, OS-ELM, SVM and SMC-RBF. Among them, SMC-RBF has the best performance; it has less number of hidden neurons, and best efficiency. However, all the existing algorithms use signal normal distribution as kernel function, which means the output of the kernel function is same at the different direction. In this paper, we use multi-variable normal distribution as kernel function, and derive EKF learning formulas for multi-variable normal distribution kernel function. From the result of the experience, we can deduct that the proposed method has better efficiency performance, and not sensitive to the data sequence.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.201-209
• /
• 2013

For censored regression, it is often the case that some input variables are not important, while some input variables are more important than others. We propose a novel algorithm for selecting such important input variables for censored kernel regression, which is based on the penalized regression with the weighted quadratic loss function for the censored data, where the weight is computed from the empirical survival function of the censoring variable. We employ the weighted version of ANOVA decomposition kernels to choose optimal subset of important input variables. Experimental results are then presented which indicate the performance of the proposed variable selection method.

• Water Engineering Research
• /
• v.2 no.1
• /
• pp.1-10
• /
• 2001

The frequency analyses for the precipitation data in Korea were performed. We used daily maximum series, monthly maximum series, and annual series. For nonparametric frequency analyses, variable kernel estimators were used. Nonparametric methods do not require assumptions about the underlying populations from which the data are obtained. Therefore, they are better suited for multimodal distributions with the advantage of not requiring a distributional assumption. In order to compare their performance with parametric distributions, we considered several probability density functions. They are Gamma, Gumbel, Log-normal, Log-Pearson type III, Exponential, Generalized logistic, Generalized Pareto, and Wakeby distributions. The variable kernel estimates are comparable and are in the middle of the range of the parametric estimates. The variable kernel estimates show a very small probability in extrapolation beyond the largest observed data in the sample. However, the log-variable kernel estimates remedied these defects with the log-transformed data.

• Journal of the Korean Data and Information Science Society
• /
• v.22 no.4
• /
• pp.795-801
• /
• 2011

In machine learning and statistics it is often the case that some variables are not important, while some variables are more important than others. We propose a novel algorithm for selecting such relevant variables in the kernel Cox regression. We employ the weighted version of ANOVA decomposition kernels to choose optimal subset of relevant variables in the kernel Cox regression. Experimental results are then presented which indicate the performance of the proposed method.

• Journal of the Korean Data and Information Science Society
• /
• v.18 no.3
• /
• pp.767-772
• /
• 2007

A kernel machine is proposed as an estimating procedure for the linear and nonlinear Poisson regression, which is based on the penalized negative log-likelihood. The proposed kernel machine provides the estimate of the mean function of the response variable, where the canonical parameter is related to the input vector in a nonlinear form. The generalized cross validation(GCV) function of MSE-type is introduced to determine hyperparameters which affect the performance of the machine. Experimental results are then presented which indicate the performance of the proposed machine.

• Interaction and multiscale mechanics
• /
• v.3 no.3
• /
• pp.277-298
• /
• 2010

The complex variable reproducing kernel particle method (CVRKPM) and the FEM are coupled in this paper to analyze the two-dimensional potential problems. The coupled method not only conveniently imposes the essential boundary conditions, but also exploits the advantages of the individual methods while avoiding their disadvantages, resulting in improved computational efficiency. A hybrid approximation function is applied to combine the CVRKPM with the FEM. Formulations of the coupled method are presented in detail. Three numerical examples of the two-dimensional potential problems are presented to demonstrate the effectiveness of the new method.

• Journal of the Korean Data and Information Science Society
• /
• v.5 no.1
• /
• pp.11-20
• /
• 1994

In recent years, nonparametric kernel estimation of regresion function are abundant and widely applicable to many areas of statistics. Most of modern researches concerned with the fixed global bandwidth selection which can be used in the estimation of regression function with all the same value for all x. In this paper, we propose a method for selecting locally varing bandwidth based on bootstrap method in kernel estimation of fixed design regression. Performance of proposed bandwidth selection method for finite sample case is conducted via Monte Carlo simulation study.

• Journal of the Korean Data and Information Science Society
• /
• v.9 no.2
• /
• pp.179-188
• /
• 1998

Local polynomial regression estimation is the most popular one among kernel type regression estimator. In local polynomial regression function esimation bandwidth selection is crucial problem like the kernel estimation. When the regression curve has complicated structure variable bandwidth selection will be appropriate. In this paper, we propose a variable bandwidth selection method fully data driven. We will choose the bandwdith by selecting minimising estiamted MSE which is estimated by the pilot bandwidth study via croos-validation method. Monte carlo simulation was conducted in order to show the superiority of proposed bandwidth selection method.

• Journal of the Korean Data and Information Science Society
• /
• v.21 no.5
• /
• pp.959-965
• /
• 2010

For multiclassification, it is often the case that some variables are not important while some variables are more important than others. We propose a novel algorithm for selecting such relevant variables for multiclassification. This algorithm is base on multiclass least squares support vector machine (LS-SVM), which uses results of multiclass LS-SVM using one-vs-all method. Experimental results are then presented which indicate the performance of the proposed method.

• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.408-413
• /
• 2005

A new methodology for discrete non-Gaussian probability density estimation is investigated in this paper based on a dynamic Bayesian network (DBN) and kernel functions. The estimator consists of a DBN in which the transition distribution is represented with kernel functions. The estimator parameters are determined through a recursive learning algorithm according to the maximum likelihood (ML) scheme. A discrete-type Poisson distribution is generated in a simulation experiment to evaluate the proposed method. In addition, an unknown probability density generated by nonlinear transformation of a Poisson random variable is simulated. Computer simulations numerically demonstrate that the method successfully estimates the unknown probability distribution function (PDF).