• Journal of the Korean Statistical Society
• /
• v.22 no.2
• /
• pp.361-368
• /
• 1993

In recent years, kernel type estimates are abundant. In this paper, we propose a bandwidth selection method for kernel regression of fixed design based on bootstrap procedure. Mathematical properties of proposed bootstrap-based bandwidth selection method are discussed. Performance of the proposed method for small sample case is compared with that of cross-validation method via a simulation study.

• 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.

• ETRI Journal
• /
• v.15 no.2
• /
• pp.35-51
• /
• 1993

This paper presents function approximation based on nonparametric estimation. As an estimation model of function approximation, a three layered network composed of input, hidden and output layers is considered. The input and output layers have linear activation units while the hidden layer has nonlinear activation units or kernel functions which have the characteristics of bounds and locality. Using this type of network, a many-to-one function is synthesized over the domain of the input space by a number of kernel functions. In this network, we have to estimate the necessary number of kernel functions as well as the parameters associated with kernel functions. For this purpose, a new method of parameter estimation in which linear learning rule is applied between hidden and output layers while nonlinear (piecewise-linear) learning rule is applied between input and hidden layers, is considered. The linear learning rule updates the output weights between hidden and output layers based on the Linear Minimization of Mean Square Error (LMMSE) sense in the space of kernel functions while the nonlinear learning rule updates the parameters of kernel functions based on the gradient of the actual output of network with respect to the parameters (especially, the shape) of kernel functions. This approach of parameter adaptation provides near optimal values of the parameters associated with kernel functions in the sense of minimizing mean square error. As a result, the suggested nonparametric estimation provides an efficient way of function approximation from the view point of the number of kernel functions as well as learning speed.

• Korean Journal of Agricultural Science
• /
• v.4 no.2
• /
• pp.215-228
• /
• 1977

In order to provide good germplasm for developing good corn hybrids, a total of 948 Korean indigenous corn lines were collected from various parts of country and major morphological characterstics of ears were investigated. The results obtained were as follows; 1) Ear Type; From the east-north mountaionus region where more than 80% of total corn production is practiced, cylinder (type I) or similar types to cylinder corn were collected, and from the southern plain region, where rather small scales of corn is grown, cone type (type IV) or similar types to cone were prevalent. 2) Kernel color; In the ear colors of all the indigenous corn lines collected from ten regions, ears with mono color were 54.4%, ears with two color mixed were 39.0% and ears with three or more color mixed were 6.6%. In northern mountainous region, region A and region I, ear color was mostly white or white plus other colors, while in other regions ear color was yellow or yellow plus other colors. 3) Denting; Dent type was only 4.3% of Korean indigenous corn lines collected, and others were flint type. Dent type was collected from northern regions, where foreign corn varieties were introduced and grown. 4) Ear row number; Ear row numbers of indigenous corn lines collected were 12 to 16. There was no significant differences among the ear row numbers in a ear ciassified by regions. However, it was observed that ear row number was closely related to kernel size. For instance, the ears with 24 ear-rows were the smallest in kernel size. 5) Quality of starch; 70.9% of the indigenous corn lines collected were kernels with hard starch. Corn with soft starch was 26.0% and medium type was 3.1%. In region A and region I, where lot of corn is grown, corn with hard starch was more frequently collected. 6) Pop corn and waxy corn; In all the indigenous corn lines collected, popcorn was distributed uniformly through the regions except region I, and waxy corn was found more in the northern mountainous region. 7) Ear length; The mean ear length of indigenous corn lines collected was 13cm. In region A and region I ear length was larger than that in other regions. 8) Ear diameter; The mean ear diameter of indigenous corn lines collected was 3.3cm. In region A and region I ear diameter was larger than that in other regions. 9) Kernel length, kernel width and kernel thickness; The mean kernel length, kernel width and kernel thickness of indigenous corn lines collected were 0.82cm, 0.42cm, and 0.78cm, respectively. The kernel size in the region A and region I was larger than that in other regions. 10) Ear weight; The mean ear weight of indigenous corn lines collected was 58.04gr. Ear weight was remarkably heavier in region A and region I. The heaviest ear weighed 330gr, and the lightest ear weighed 5 gr. 11) Kernel weight of a ear and 100 kernel weight; Kernel weight of a ear and 100 kernel of indigenous corn lines collected were 47.07gr and 15.07gr, respectively. Kernel weights and 100 kernel weights were much heavier in region A and region I than other regions.

• Kyungpook Mathematical Journal
• /
• v.50 no.2
• /
• pp.297-306
• /
• 2010

In this paper, the integral operator is used. We give a new Hilbert-type integral inequality, whose kernel is the homogeneous form with degree - $\lambda$ and with three pairs of conjugate exponents and the best constant factor and its reverse form are also derived. It is shown that the results of this paper represent an extension as well as some improvements of the earlier results.

• Kyungpook Mathematical Journal
• /
• v.50 no.2
• /
• pp.281-288
• /
• 2010

By introducing some parameters and using the way of weight function and the technic of real analysis and complex analysis, a new Hilbert-type integral inequality with a best constant factor and a combination kernel involving two mean values is given, which is an extension of Hilbert's integral inequality. As applications, the equivalent form and the reverse forms are considered.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.11 no.4
• /
• pp.267-274
• /
• 2011

Recently, actor-critic methods have drawn significant interests in the area of reinforcement learning, and several algorithms have been studied along the line of the actor-critic strategy. In this paper, we consider a new type of actor-critic algorithms employing the kernel methods, which have recently shown to be very effective tools in the various fields of machine learning, and have performed investigations on combining the actor-critic strategy together with kernel methods. More specifically, this paper studies actor-critic algorithms utilizing the kernel-based least-squares estimation and policy gradient, and in its critic's part, the study uses a sliding-window-based kernel least-squares method, which leads to a fast and efficient value-function-estimation in a nonparametric setting. The applicability of the considered algorithms is illustrated via a robot locomotion problem and a tunnel ventilation control problem.

• Speech Sciences
• /
• v.12 no.4
• /
• pp.17-29
• /
• 2005

Time-frequency representation reveals some useful information about instantaneous frequency, instantaneous bandwidth and boundary of each AM-FM component of a speech signal. In many cases, the instantaneous frequency of each component is not constant. The variability of instantaneous frequency causes degradation of resolution in time-frequency representation. This paper presents a method of adaptively adjusting the transform kernel for preventing degradation of resolution due to time-varying instantaneous frequency. The transform kernel is the form of frequency modulated function. The modulation function in the transform kernel is determined by the estimate of instantaneous frequency which is approximated by first order polynomial at each time instance. Also, the window function is modulated by the estimated instantaneous. frequency for mitigation of fringing. effect. In the proposed method, not only the transform kernel but also the shape and the length of. the window function are adaptively adjusted by the instantaneous frequency of a speech signal.

• 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.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.7
• /
• pp.3076-3092
• /
• 2020

An IKPCA-ELM-based intrusion detection method is developed to address the problem of the low accuracy and slow speed of intrusion detection caused by redundancies and high dimensions of data in the network. First, in order to reduce the effects of uneven sample distribution and sample attribute differences on the extraction of KPCA features, the sample attribute mean and mean square error are introduced into the Gaussian radial basis function and polynomial kernel function respectively, and the two improved kernel functions are combined to construct a hybrid kernel function. Second, an improved particle swarm optimization (IPSO) algorithm is proposed to determine the optimal hybrid kernel function for improved kernel principal component analysis (IKPCA). Finally, IKPCA is conducted to complete feature extraction, and an extreme learning machine (ELM) is applied to classify common attack type detection. The experimental results demonstrate the effectiveness of the constructed hybrid kernel function. Compared with other intrusion detection methods, IKPCA-ELM not only ensures high accuracy rates, but also reduces the detection time and false alarm rate, especially reducing the false alarm rate of small sample attacks.