• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1993.06a
• /
• pp.1177-1180
• /
• 1993

In this paper, a fuzzy-neural interpolating network is proposed to efficiently approximate a nonlinear function. Specifically, basis functions are first constructed by Fuzzy Membership Function based Neural Networks (FMFNN). And the fuzzy similarity, which is defined as the degree of matching between actual output value and the output of each basis function, is employed to determine initial weighting of the proposed network. Then the weightings are updated in such a way that square of the error is minimized. To show the capability of function approximation of the proposed fuzzy-neural interpolating network, a numerical example is illustrated.

• Korean Journal of Remote Sensing
• /
• v.24 no.5
• /
• pp.473-481
• /
• 2008

This paper presents an approach to Back-propagation and Radial Basis Function neural network method with various training set for automatic vehicle detection from aerial images. The initial extraction of candidate object is based on Mean-shift algorithm with symmetric property of a vehicle structure. By fusing the density and the symmetry, the method can remove the ambiguous objects and reduce the cost of processing in the next stage. To extract features from the detected object, we describe the object as a log-polar shape histogram using edge strengths of object and represent the orientation and distance from its center. The spatial histogram is used for calculating the momentum of object and compensating the direction of object. BPNN and RBFNN are applied to verify the object as a vehicle using a variety of non-car training sets. The proposed algorithm shows the results which are according to the training data. By comparing the training sets, advantages and disadvantages of them have been discussed.

• Journal of The Korean Astronomical Society
• /
• v.28 no.1
• /
• pp.45-59
• /
• 1995

In the best observed Pleiades cluster, the luminosity function(LF) and mass function(MF) for main sequence(MS) stars extended to $Mv{\approx}15.5(V{\approx}21)$ are very similar to the initial luminosity function(ILF) and initial mass function(IMF) for field stars in the solar neighborhood showing a bump at log $m{\simeq}-0.05$ and a dip at log $m{\simeq}-0.12$. This dip is equivalent to the Wielen dip appearing in the LF for the field stars. The occurence of these bump and dip is independent of adopted mass-luminosity relation(MLR) . and their characteristics could be explained by a time-dependent bimodal IMF. The model with this IMF gives a total cluster mass of $\~700M_\bigodot,\;\~25$ brown dwarfs and $\~3$ white dwarfs if the upper mass limit of progenitor of white dwarf is greater than $4.5M_\bigodot$. The cluster age on the basis of LF for brightest stars is given by $\~8\times10^7yr$ and all stars in the cluster lie along the single age sequence in the C-M diagram without showing a large dispersion from the sequence.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.05
• /
• pp.116-118
• /
• 1997

In hippocampal morphology Abnormalities, including unilateral or bilateral volume loss, are known to occur in epilepsy, Alzheimer's disease, and in certain amnestic syndromes. To detect such abnormalities in hippocampal morphology, we present a method that combines region growing and dynamic contour model to detect hippocampus from MRI brain data. The segmentation process is performed two steps. First region growing with a seed point is performed in the region of hippocampus and the initial contour of dynamic contour model is obtained. Second, the initial contour is modified on the basis of criteria that integrate energy with contour smoothness and the image gradient along the contour. As a result, this method improves fairly sensitivity to the choice of the initial seed point, which is often seen by conventional contour model. The power and practicality of this method have been tested on two brain datasets. Thus, we have developed an effective algorithm to extract hippocampus from MRI brain data.

• Journal of Environmental Science International
• /
• v.20 no.1
• /
• pp.25-34
• /
• 2011

The new empirical static model was constructed on the basis of dimension analysis to predict the pressure drop according to the operating conditions. The empirical static model consists of the initial pressure drop term (${\Delta}P_{initial}$) and the dust mass number term($N_{dust}=\frac{{\omega}_0{\nu}_f}{P_{pulse}t}$), and two parameters (dust deposit resistance and exponent of dust mass number) have been estimated from experimental data. The optimum injection distance was identified in the 64 experimental data at the fixed filtration velocity and pulse pressure. The dust deposit resistance ($K_d$), one of the empirical static model parameters got the minimum value at d=0.11m, at which the total pressure drop was minimized. The exponent of dust mass number was interpreted as the elasticity of pressure drop to the dust mass number. The elasticity of the unimodal behavior had also a maximum value at d=0.11m, at which the pressure drop increased most rapidly with the dust mass number. Additionally, the correlation coefficient for the new empirical static model was 0.914.

• Journal of The Korean Digital Architecture Interior Association
• /
• v.13 no.4
• /
• pp.5-12
• /
• 2013

Conceptual and technical design designated as digital architecture has been discussed with disorderly meaning as a conception only. Thus, this study aims at verification of development possibility for the digital architecture by analyzing how works of Frank Gehry have effect on nonlinearity of the digital architecture. Nonlinear characteristics appeared on works of Frank Gehry analyzed on the basis of expression techniques and modeling principle are as follows: 1) Initial works show a trend to gradually change and develop from horizontal and vertical linear structure to nonlinear pattern. 2) From a nonlinear modeling principle, initial works appear the primary deformation elements only, while afterwards, they are gradually developing to a pattern to mix the primary and secondary deformation elements as introduction of digital architecture. 3) Through specific cases, Frank Gehry has conducted attempts with various method for nonlinear pattern expression. 4) From the initial works to the latest works, continuity becomes higher and changed to nonlinear pattern. This study is significant from a viewpoint that it has verified development possibility of digital architecture by analyzing nonlinear trend of digital architecture for Frank Gehry and it is required to conduct multilateral researches related to the digital architecture.

• Structural Engineering and Mechanics
• /
• v.31 no.3
• /
• pp.333-347
• /
• 2009

Due to structural complicacy, structural health monitoring for civil engineering needs more accurate and effectual methods of damage identification. This study aims to import multi-source information fusion (MSIF) into structural damage diagnosis to improve the validity of damage detection. Firstly, the essential theory and applied mathematic methods of MSIF are introduced. And then, the structural damage identification method based on multi-mode information fusion is put forward. Later, on the basis of a numerical simulation of a concrete continuous box beam bridge, it is obviously indicated that the improved modal strain energy method based on multi-mode information fusion has nicer sensitivity to structural initial damage and favorable robusticity to noise. Compared with the classical modal strain energy method, this damage identification method needs much less modal information to detect structural initial damage. When the noise intensity is less than or equal to 10%, this method can identify structural initial damage well and truly. In a word, this structural damage identification method based on multi-mode information fusion has better effects of structural damage identification and good practicability to actual structures.

• Mycobiology
• /
• v.33 no.4
• /
• pp.223-229
• /
• 2005

A novel fungal strain Aspergillus sp. L117 that produced acid-stable and thermostable phytase was isolated on basis of the clearing zone on PSM plate and the ability of Na-phytate hydrolysis. The phytase of isolate showed a 3-fold higher activity than that of A. ficuun NRRL3135. The Aspergillus sp. L117 produced maximal level of phytase at initial pH of 5.0 and $30^{\circ}C$. The optimal pH and temperature for phytase activity were 5.5 and $50^{\circ}C$, respectively. The phytase showed totally stable activity after 20 min of exposure between 30 and $90^{\circ}C$, and even at $100^{\circ}C$. The highest level of residual phytase activity was obtained at pH 5.5, and still retained the stability at the broadest pH ranges (2.0 to 7.0) of all the aforementioned phytases. Storage stability of phytase was preserved over 96% of initial activities for 60 days at 4, -20, and $-70^{\circ}C$ and to retain even 70% of the initial activity at room temperature.

• Journal of KIISE
• /
• v.43 no.7
• /
• pp.812-819
• /
• 2016

This paper introduces and analyzes the theoretical basis and method of the conventional initial-value assignment problem and feasibility of image segmentation. The paper presents topological evidence and a method of appropriate initial-value assignment based on topology theory. Subsequently, the paper shows minimum conditions for feasibility of image segmentation based on separation axiom theory of topology and a validation method of effectiveness for image modeling. As a summary, this paper shows image segmentation with its mathematical validity based on topological analysis rather than statistical analysis. Finally, the paper applies the theory and methods to conventional Gaussian random field model and examines effectiveness of GRF modeling.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2004.07b
• /
• pp.1129-1133
• /
• 2004

반도체공정 최적화에 소요되는 시간과 경비를 줄이기 위해 신경망 모델이 개발되고 있다. 주로 역전파 신경망을 이용하여 모델이 개발되고 있으며, 본 연구에서는 Radial Basis Function Network (RBFN)을 이용하여 플라즈마 식각공정 모델을 개발한다. 실험데이터는 유도결합형 플라즈마를 이용한 Silicon Carbide 박막의 식각공정으로부터 수집되었다. 모델개발을 위해 $2^4$ 전인자 (full factorial) 실험계획법이 적용되었으며, 모델에 이용된 식각응답은 식각률과 atomic force microscopy로 측정한 식각표면 거칠기이다. 모델검증을 위해 추가적으로 16번의 실험을 수행하였다. RBFN의 예측성능은 세 학습인자, 즉 뉴런수, width, 초기 웨이트 분포 (initial weight distribution-IWD) 크기에 의해 결정된다. 본 연구에서는 각 학습인자의 영향을 최적화하였으며, IWD의 불규칙성을 고려하여 주어진 학습인자에 대해서 100개의 모델을 발생하고, 이중 최소의 IWD를 갖는 모델을 선택하였다. 최적화한 식각률과 표면거칠기 모델의 RMSE는 각기 26 nm/min과 0.103 nm이었다. 통계적인 회귀모델과 비교하여, 식각률과 표면거칠기 모델은 각기 52%와 24%의 향상된 예측정확도를 보였다. 이로써 RBFN이 플라즈마 공정을 효과적으로 모델링 할 수 있음을 확인하였다.