• 전자공학회논문지B
• /
• 제33B권12호
• /
• pp.95-105
• /
• 1996

This paper presents structure optimization of a feedforward neural netowrk controller using the genetic algorithm. It is important to design the neural network with minimum structure for fast response and learning. To minimize the structure of the feedforward neural network, a genralization of multilayer neural netowrks, the genetic algorithm uses binary coding for the structure and floating-point coding for weights. Local search with an on-line learnign algorithm enhances the search performance and reduce the time for global search of the genetic algorithm. The relative fitness defined as the multiplication of the error and node functions prevents from premature convergence. The feedforward neural controller of smaller size outperformed conventional multilayer perceptron network controller.

• 산업경영시스템학회지
• /
• 제21권47호
• /
• pp.219-232
• /
• 1998

A lot of difficulties exist in analyzing the structure of a system owing to the complex and organic relations in the systems we face in reality. Focuses have been put on the research of optimal solution in a defined structure, however, on the assumption that the structure of the system has been already defined. With the grasping of the structure as the most prior condition, ISM(Interpretive Structural Modeling) and FSM(Fuzzy Structural Modeling) are suggested as solutions in this paper. ISM uses the systematic application of some elementary notions of graph theory and boolean algebra, FSM uses Fuzzy conception for representing relationship between elements. In FSM, the entries in the relation matrix are taken to value on the interval [0,1] by virtue of a fuzzy binary relation. Numeric examples are used as the actual application as follows.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2001년도 ICCAS
• /
• pp.71.2-71
• /
• 2001

This paper deals with nonlinear system modelling using neural network and genetic algorithm. Application of neural network to control and identification is actively studied because of their approximating ability of nonlinear function. It is important to design the neural network with optimal structure for minimum error and fast response time. Genetic algorithm is getting more popular nowadays because of their simplicity and robustness. In this paper, We optimize neural network structure using genetic algorithm. The genetic algorithm uses binary coding for neural network structure and search for optimal neural network structure of minimum error and response time. Through extensive simulation, Optimal neural network structure is shown to be effective for ...

• 대한화학회지
• /
• 제15권3호
• /
• pp.133-145
• /
• 1971

액체구조의 천이상태이론을 이성분용액의 액체-증기 계면에 적용하여, $C_6H_{12}-C_6H_6$ $CCI_4-C_6H_6$, $CHCl_3-C_6H_6$, $CHCl_3-CCl_4$, $CCl_4-CS_2$계의 표면장력, 표면흡착량, 표면에서의 활동도 계수들을 계산하였다.

• International Journal of Contents
• /
• 제7권4호
• /
• pp.56-63
• /
• 2011

Quantum mechanics is a branch of physics for a mathematical description of the particle wave, and it is applied to information technology such as quantum computer, quantum information, quantum network and quantum cryptography, etc. In 1936, Garrett Birkhoff and John von Neumann introduced the logic of quantum mechanics (quantum logic) in order to investigate projections on a Hilbert space. As another type of quantum logic, orthomodular implication algebra was introduced by Chajda et al. This algebra has the logical implication as a binary operation. In pure mathematics, there are many algebras such as Hilbert algebras, implicative models, implication algebras and dual BCK-algebras (DBCK-algebras), which have the logical implication as a binary operation. In this paper, we introduce the definitions and some properties of those algebras and clarify the relations between those algebras. Also, we define the implicative poset which is a generalization of orthomodular implication algebras and DBCK-algebras, and research properties of this algebraic structure.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2004년도 ICCAS
• /
• pp.40-45
• /
• 2004

This work presents a boundary estimation approach in electrical impedance imaging for binary-mixture fields based on a parallel structured multi-layer neural network. The interfacial boundaries are expressed with the truncated Fourier series and the unknown Fourier coefficients are estimated with the parallel structure of multi-layer neural network. Results from numerical experiments shows that the proposed approach is insensitive to the measurement noise and has a strong possibility in the visualization of binary mixtures for a real time monitoring.

• 산업기술연구
• /
• 제20권A호
• /
• pp.203-209
• /
• 2000

The fluctuation integrals which give useful information in the structure of solution are associated with the mixed direct correlation integral ($C_{12}$) known. Using its weighted arithmetic mean of $C_{11}$ and $C_{22}$ and the activity coefficient model, the fluctuation integrals on solute-solute, solvent-solute, and solvent-solvent can be calculated in the function of mole fraction. In this work, several binary mixtures containing c-hexane were tested and the results on the fluctuation integrals were rather good.

• Journal of Biosystems Engineering
• /
• 제21권3호
• /
• pp.315-324
• /
• 1996

This study was one of a series of studies on application of machine vision and image processing to extract the geometrical features of plants and to analyze plant growth. Several algorithms were developed to measure morphological properties of plants and describing the growth development of in-situ lettuce(Lactuca sativa L.). Canopy, centroid, leaf density and fractal dimension of plant were measured from a top viewed binary image. It was capable of identifying plants by a thinning top viewed image. Overlapping the thinning side viewed image with a side viewed binary image of plant was very effective to auto-detect meaningful nodes associated with canopy components such as stem, branch, petiole and leaf. And, plant height, stem diameter, number and angle of branches, and internode length and so on were analyzed by using meaningful nodes extracted from overlapped side viewed images. Canopy, leaf density and fractal dimension showed high relation with fresh weight or growth pattern of in-situ lettuces. It was concluded that machine vision system and image processing techniques are very useful in extracting geometrical features and monitoring plant growth, although interactive methods, for some applications, were required.

• 전자공학회논문지B
• /
• 제31B권5호
• /
• pp.162-167
• /
• 1994

The binary image normalization method in image processing can be used in several fields, Especially, its high speed processing method and its hardware implmentation is more useful, A normalization process of each character in character recognition requires a lot of processing time. Therefore, the research was done as a part of high speed process of OCR (optical character reader) implementation as a pipeline structure with host computer in hardware to give temporal parallism. For normalization process, general purpose CPU,MC68000, was used to implement it. As a result of experiment, the normalization speed of the hardware is sufficient to implement high speed OCR which the recognition speed is over 140 characters per second.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2008년도 추계학술대회A
• /
• pp.625-630
• /
• 2008

In the manufacturing industries, viewing CAE analysis results is frequently required during the product development process for design verification. CAE data which include all related information of an analysis is, however, not efficiently shared among designers because CAE data size is in general large to deal with. In order to increase collaboration among designers this paper introduces the development of a CAE visualization system based on JT format exploiting for a large model visualization with a scene graph-based toolkit. Since CAE analysis results and JT format have different structure we developed a translator to convert the CAE result in binary format to the JT format. To show the effectiveness of JT format in showing the CAE result we also developed a prototype viewer offering basic functions provided by commercial systems. By using JT format we are able not only to reduce the size of analysis results, but to store a series of analysis results with several LOD in a data file.