• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.36 no.4
• /
• pp.59-63
• /
• 2013

In biomass gasification, efficiency of energy quantification is a difficult part without finishing the process. In this article, a radial basis function neural network (RBFN) is proposed to predict biomass efficiency before gasification. RBFN will be compared with a principal component regression (PCR) and a multilayer perceptron neural network (MLPN). Due to the high dimensionality of data, principal component transform is first used in PCR and afterwards, ordinary regression is applied to selected principal components for modeling. Multilayer perceptron neural network (MLPN) is also used without any preprocessing. For this research, 3 wood samples and 3 other feedstock are used and they are near infrared (NIR) spectrum data with high-dimensionality. Ash and char are used as response variables. The comparison results of two responses will be shown.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.14 no.7
• /
• pp.878-882
• /
• 2004

In this paper, we propose a hierarchical hybrid neural network for detecting faults of induction motor. Implementing the classifier based on the input and output data, we apply appropriate transform and classification method at each step. In the proposed method, after obtaining the current of state of motor for each period, we transform it by Principle Component Analysis(PCA) to reduce its dimension. Before the training process, we use the conditional Fuzzy C-means(FCM) for obtaining the initial parameters of neural network for more effective learning procedure. From the various simulations, we find that the proposed method shows better performance to detect and diagnosis of induction motor and compare than other methods.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.10
• /
• pp.35-41
• /
• 2012

We propose a new marker driven Watershed algorithm for automated segmentation of clustered cell from microscopy image with less over segmentation. The Watershed Transform is able to segment extremely complex objects which are highly touched and overlapped each other. The success of the Watershed Transform depends essentially on the finding markers for each of the objects of interest. For extracting of markers positioning around center of each cell we used radial symmetry and iterative voting algorithms. With synthetic and real images, we quantitatively demonstrate the performance of our method and achieved better results than the other compared methods.

• Coupled systems mechanics
• /
• v.12 no.2
• /
• pp.127-149
• /
• 2023

A theoretical method is developed to analyze the free vibration of an elastic annular plate in contact with an ideal liquid. The displacement potential functions of the contained liquid are expressed as a combination of the Bessel functions that satisfy the Laplace equation and the liquid boundary conditions. The compatibility condition along the interface between the annular plate and the contained liquid is taken into account to consider the fluid-structure coupling. The dynamic displacement of the wet annular plate is assumed to be a combination of dry eigenfunctions, allowing for prediction of the natural frequencies using the Rayleigh-Ritz method. The study investigates the effect of radial liquid boundary conditions on the natural frequencies of the wet annular plate, considering four types of liquid bounding: outer container bounded, outer and inner bounded, inner bounded, and radially unbounded. The proposed theoretical method is validated by comparing the predicted wet natural frequencies with those obtained from finite element analysis, showing excellent accuracy. The results indicate that the radial liquid bounding effect on the natural frequencies is negligible for the axisymmetric vibrational mode, but relatively significant for the mode with one nodal diameter (n =1) and no nodal circle (m' = 0). Furthermore, the study reveals that the wet natural frequencies are the largest for the plate with an inner bounded cylinder among the radial liquid boundary cases, regardless of the vibration mode.

• Korean Journal of Mathematics
• /
• v.28 no.3
• /
• pp.449-457
• /
• 2020

We focus on the interations of the weighted Berezin transform T_α on L^p(τ), where τ is the invariant measure on the complex unit ball B_n. Iterations of T_α on L¹_R(τ) the space of radial integrable functions played important roles in proving 𝓜-harmonicity of bounded functions with invariant mean value property. Here, we introduce more properties on iterations of T_α on L¹_R(τ) and observe differences between the iterations of T_α on L1(τ) and L^p(τ) for 1 < p < ∞.

• Bulletin of the Korean Mathematical Society
• /
• v.47 no.1
• /
• pp.113-119
• /
• 2010

If f is M-harmonic and integrable with respect to a weighted radial measure $\upsilon_{\alpha}$ over the unit ball $B_n$ of $\mathbb{C}^n$, then $\int_{B_n}(f\circ\psi)d\upsilon_{\alpha}=f(\psi(0))$ for every $\psi{\in}Aut(B_n)$. Equivalently f is fixed by the weighted Berezin transform; $T_{\alpha}f = f$. In this paper, we show that if a function f defined on $B_n$ satisfies $R(f\circ\phi){\in}L^{\infty}(B_n)$ for every $\phi{\in}Aut(B_n)$ and Sf = rf for some |r|=1, where S is any convex combination of the iterations of $T_{\alpha}$'s, then f is M-harmonic.

• International Journal of Precision Engineering and Manufacturing
• /
• v.9 no.4
• /
• pp.45-50
• /
• 2008

The Fourier-Mellin transform is the theoretical basis for the translation, rotation, and scale invariance of an image. However, its implementation requires a log-polar map of the original image, which requires logarithmic sampling of a radial variable in that image. This means that the mapping process is accompanied by considerable loss of data. To solve this problem, we propose a dual log-polar map that uses both a forward image map and a reverse image map simultaneously. Data loss due to the forward map sub-sampling can be offset by the reverse map. This is the first step in creating an invertible log-polar map. Experimental results have demonstrated the effectiveness of the proposed scheme.

• Korean Journal of Mathematics
• /
• v.27 no.2
• /
• pp.437-444
• /
• 2019

For c > -1, let ${\nu}_c$ denote a weighted radial measure on ${\mathbb{C}}$ normalized so that ${\nu}_c(D)=1$. For $c_1,c_2>-1$ and $f{\in}L^1(D^2,\;{\nu}_{c_1}{\times}{\nu}_{c_2})$, we define the weighted Berezin transform $B_{c_1,c_2}f$ on $D^2$ by $$(B_{c_1,c_2})f(z,w)={\displaystyle{\smashmargin2{\int\nolimits_D}{\int\nolimits_D}}}f({\varphi}_z(x),\;{\varphi}_w(y))\;d{\nu}_{c_1}(x)d{\upsilon}_{c_2}(y)$$. This paper is about the space $M^p_{c_1,c_2}$ of function $f{\in}L^p(D^2,\;{\nu}_{c_1}{\times}{\nu}_{c_2})$ ) satisfying $B_{c_1,c_2}f=f$ for $1{\leq}p<{\infty}$. We find the identity operator on $M^p_{c_1,c_2}$ by using invariant Laplacians and we characterize some special type of functions in $M^p_{c_1,c_2}$.

• Journal of the Korean Mathematical Society
• /
• v.59 no.5
• /
• pp.927-944
• /
• 2022

Let $\vec{p}{\in}(0,\;1]^n$ be an n-dimensional vector and A a dilation. Let $H^{\vec{p}}_A(\mathbb{R}^n)$ denote the anisotropic mixed-norm Hardy space defined via the radial maximal function. Using the known atomic characterization of $H^{\vec{p}}_A(\mathbb{R}^n)$ and establishing a uniform estimate for corresponding atoms, the authors prove that the Fourier transform of $f{\in}H^{\vec{p}}_A(\mathbb{R}^n)$ coincides with a continuous function F on ℝⁿ in the sense of tempered distributions. Moreover, the function F can be controlled pointwisely by the product of the Hardy space norm of f and a step function with respect to the transpose matrix of A. As applications, the authors obtain a higher order of convergence for the function F at the origin, and an analogue of Hardy-Littlewood inequalities in the present setting of $H^{\vec{p}}_A(\mathbb{R}^n)$.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.1
• /
• pp.91-96
• /
• 2015

In this study, we introduce robust face recognition system with illumination variation realized with the aid of CT preprocessing method. As preprocessing algorithm, Census Transform(CT) algorithm is used to extract locally facial features under unilluminated condition. The dimension reduction of the preprocessed data is carried out by using $(2D)^2$PCA which is the extended type of PCA. Feature data extracted through dimension algorithm is used as the inputs of proposed radial basis function neural networks. The hidden layer of the radial basis function neural networks(RBFNN) is built up by fuzzy c-means(FCM) clustering algorithm and the connection weights of the networks are described as the coefficients of linear polynomial function. The essential design parameters (including the number of inputs and fuzzification coefficient) of the proposed networks are optimized by means of artificial bee colony(ABC) algorithm. This study is experimented with both Yale Face database B and CMU PIE database to evaluate the performance of the proposed system.