• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2005.04a
• /
• pp.335-339
• /
• 2005

본 논문에서는 퍼지 RBF 네트워크의 학습 성능을 개선하기 위하여 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하는 개선된 퍼지 RBF 네트워크를 제안한다. 제안된 학습 알고리즘은 일반화된 델타 학습 방법에 퍼지 C-Means 알고리즘을 결합한 방법으로, 중간층의 노드를 자가 생성하고 중간층과 출력충의 학습에는 일반화된 델타 학습 방법에 Delta-bar-Delta 알고리즘을 적용하여 학습률을 동적으로 조정하여 학습 성능을 개선한다. 제안된 RBF 네트워크의 학습 성능을 평가하기 위하여 컨테이너 영상에서 추출한 40개의 식별자를 학습 데이터로 적용한 결과, 기존의 ART2 기반 RBF 네트워크와 기존의 퍼지 RBF 네트워크 보다 학습 시간이 적게 소요되고, 학습의 수렴성이 개선된 것을 확인하였다.

• Journal of Korea Multimedia Society
• /
• v.9 no.3
• /
• pp.369-376
• /
• 2006

In this paper, we propose an improved fuzzy RBF network which dynamically adjusts the rate of learning by applying the Delta-bar-Delta algorithm in order to improve the learning performance of fuzzy RBF networks. The proposed learning algorithm, which combines the fuzzy C-Means algorithm with the generalized delta learning method, improves its learning performance by dynamically adjusting the rate of learning. The adjustment of the learning rate is achieved by self-generating middle-layered nodes and by applying the Delta-bar-Delta algorithm to the generalized delta learning method for the learning of middle and output layers. To evaluate the learning performance of the proposed RBF network, we used 40 identifiers extracted from a container image as the training data. Our experimental results show that the proposed method consumes less training time and improves the convergence of teaming, compared to the conventional ART2-based RBF network and fuzzy RBF network.

• Journal of the Korean Ceramic Society
• /
• v.34 no.2
• /
• pp.139-144
• /
• 1997

Structurally, the rare earth cuprate superconductor of Nd2-xCexCuO4-$\delta$ has T' structure and has been known as having a quite complicated microstructural phenomena, so far. In order to be superconductivity, both small amount of cation substitution of Nd3+ by Ce4+ and oxygen reduction are required. In the present study the crystallographic study on the structural transition for the Nd2-xCexCuO4-$\delta$ crystal has been con-ducted by observing the CBED (Convergent Beam Electron Diffraction) pattern with STEM(Scanning Transmission Electron Microscope). Three different samples of Nd2CuO3,Nd1.85Ce0.15CuO4 and Nd1.85Ce0.15CuO3.965 were prepared by solid-state sintering and their CBED patterns were observed by STEM to study the structural transition accompanying the substitution of Ce and the reduction of oxygen. Experimental HOLZ lines of these samples were compared with those plotted by a computer-programmed simulation to de-termine the lattice parameter of Nd2-xCexCuO4-$\delta$ crystal.

• Geophysics and Geophysical Exploration
• /
• v.19 no.3
• /
• pp.136-144
• /
• 2016

Since seismic inversion is based on the wave equation, it is important to calculate the solution of wave equation exactly. In particular, full waveform inversion would produce reliable results only when the forward modeling is accurately performed because it uses full waveform. When we use finite-difference or finite-element method to solve the wave equation, the convergence of numerical scheme should be guaranteed. Although the general proof of convergence is provided theoretically, the consistency and stability of numerical schemes should be verified for practical applications. The implementation of source function is the most crucial factor for the consistency of modeling schemes. While we have to use the sinc function normalized by grid spacing to correctly describe the Dirac delta function in the finite-difference method, we can simply use the value of basis function, regardless of grid spacing, to implement the Dirac delta function in the finite-element method. If we use frequency-domain wave equation, we need to use a conservative criterion to determine both sampling interval and maximum frequency for the source wavelet generation. In addition, the source wavelet should be attenuated before applying it for modeling in order to make it obey damped wave equation in case of using complex angular frequency. With these conditions satisfied, we can develop reliable inversion algorithms.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09b
• /
• pp.91-94
• /
• 2003

본 논문에서는 RBF 네트워크의 중간층과 출력층 사이의 연결강도를 효율적으로 조정하기 위해 퍼지 논리 시스템을 이용하여 학습률과 모멘텀을 동적으로 조정하는 개선된 RBF 네트워크를 제안한다. 입력층과 중간층 사이의 학습 구조로 ART2를 적용하고 중간층과 출력층 사이의 연결 강도 조정 방법으로는 제안된 학습률 자동 조정 방식을 적용한다. 제안된 방법의 학습 성능을 평가하기 위해 기존의 delta-bar-delta 알고리즘, 기존의 ART2 기반의 RBF 네트워크와 비교 분석한 결과, 제안된 방법이 학습 속도와 수렴성에서 개선된 것을 확인하였다.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.7
• /
• pp.1387-1393
• /
• 2007

Even if the linearly separable patterns can be classified by the conventional single layer perceptron, the non-linear problems such as XOR can not be classified by it. A fuzzy single layer perceptron can solve the conventional XOR problems by applying fuzzy membership functions. However, in the fuzzy single layer perception, there are a couple disadvantages which are a decision boundary is sometimes vibrating and a convergence may be extremely lowered according to the scopes of the initial values and learning rates. In this paper, for these reasons, we proposed an enhanced fuzzy single layer perceptron algorithm that can prevent from vibration the decision boundary by introducing a bias term and can also reduce the learn time by applying the modified delta rule which include the learning rates and the momentum concept and applying the new linear activation function. Consequently, the simulation results of the XOR and pattern classification problems presented that the proposed method provided the shorter learning time and better convergence than the conventional fuzzy single layer perceptron.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.28 no.3
• /
• pp.301-307
• /
• 2015

A bond-based peridynamic model has been shown to be capable of analyzing many of dynamic brittle fracture phenomena. However, there have been issued limitations on handling constitutive models of various materials. Especially, it assumes bonds act independently of each other, so that Poisson's ratio for 3D model is fixed as 1/4 as well as taking only account the bond stretching results in a volume change not a shear change. In this paper a state-based peridynamic model of dynamic brittle fracture is presented. The state-based peridynamic model is a generalized peridynamic model that is able to directly use a constitutive model from the standard theory. It permits the response of a material at a point to depend collectively on the deformation of all bonds connected to the point. Thus, the volume and shear changes of the material can be reproduced by the state-based peridynamic theory. For a linearly elastic solid, a plane stress model is introduced and the damage model suitable for the state-based peridynamic model is discussed. Through a convergence study under decreasing the peridynamic nonlocal region($\delta$-convergence), the dynamic fracture model is verified. It is also shown that the state-based peridynamic model is reliable for modeling dynamic crack propagatoin.

• Journal of the Institute of Convergence Signal Processing
• /
• v.11 no.1
• /
• pp.88-91
• /
• 2010

In this paper, We are composed the position recognition and speed control using the moving robot in the shield Room with a RF Module and Ultrasonic Sensors. Double look up tables are selected a reference value/duty ratio. The moving robot with the dual fuzzy rules which can decrease a Conversion time than basic fuzzy control rules at start point and curve region. Also, a changing times of double look up table are rise at specific points b1,c1,d1 in the e-${\Delta}e$ phase plane and the one of the look up table is used which for increase rising time at transition area, the other used for rapidly conversion to the reference value. We verified that a dual fuzzy control rules get the good response compare with the basic fuzzy control rule.

• Journal of Integrative Natural Science
• /
• v.1 no.3
• /
• pp.216-220
• /
• 2008

In general the Banach space $L^1(T^1)$ doesn't admit convergence in norm. Thus the convergence in norm of the partial sums can not be characterized in terms of Fourier coefficients without additional assumptions about the sequence$\{^{\^}f(\xi)\}$. The problem of $L^1(T^1)$-convergence consists of finding the properties of Fourier coefficients such that the necessary and sufficient condition for (1.2) and (1.3). This paper showed that let $\{{\alpha}_{\kappa}\}{\in}BV$ and ${\xi}{\Delta}a_{\xi}=o(1),\;{\xi}{\rightarrow}{\infty}$. Then (1.1) is a Fourier series if and only if $\{{\alpha}_{\kappa}\}{\in}{\Gamma}$.

• Journal of Biosystems Engineering
• /
• v.15 no.3
• /
• pp.186-198
• /
• 1990

인간 소뇌의 구조와 기능을 간략하게 수학적으로 모델링하여 입력에 따른 시스템의 적정 출력을 학습에 의한 적응 제어 방식으로 추출해 내는 소뇌모델 대수제어기(CMAC : Cerebellar Model Arithmetic Controller)가 제안되었다. 본 논문에서는 연구개발된 기존 신경회로망과의 비교 분석에 의거하여, 소뇌모델 대수제어기 대신 네트의 특성에 따라 소뇌모델 선형조합 신경망(CMLAN : Cerebellum Model Linear Associator Network)이라 하였다. 소뇌모델 선형조합 신경망은 시스템의 제어 함수치를 결정하는 데 있어, 기존의 제어방식이 시스템의 모델링을 기초로 하여 알고리즘에 의한 수치해석적 또는 분석적 기법으로 모델 해를 산출하는 것과 달리, 학습을 통하여 저장되는 분산기억 소자들의 함수치를 선형적으로 조합함으로써 시스템의 입출력을 결정한다. 분산기억 소자로의 함수치 산정 및 저장은 소뇌모델 선형조합 신경망이 갖는 고유의 구조적 상태공간 매핑(State Space Mapping)과 델타규칙(Delta Rule)에 의거한 시스템의 입출력 상태함수의 학습으로써 수행된다. 본 논문을 통하여 소뇌모델 선형조합신경망의 구조적 특성, 학습 성질과 상태공간 설정 및 시스템의 수렴성을 규명하였다. 또한 기존의 최대 편차수정 학습 알고리즘이 갖는 비능률성 및 적용 제한성을 극복한 효율적 학습 알고리즘들을 제시하였다. 언급한 신경망의 특성 및 제안된 학습 알고리즘들의 능률성을 다양한 학습이득(Learning Gain)하에서 비선형 함수를 컴퓨터로 모의 시험하여 예시하였다.