• Journal of the Korean Institute of Intelligent Systems
• /
• v.7 no.4
• /
• pp.74-81
• /
• 1997

This paper proposes an evolutionary learning algorithm to discipline the projection neural nctworks (PNNs) with special type of hidden nodes which can activate radial basis functions as well as sigmoid functions. The proposed algorithm not only trains the parameters and the connection weights hut also c~ptimizes the network structure. Through the structure optimization, the number of hidden node:; necessary to represent a given target function is determined and the role of each hidden node is decided whether it activates a radial basis function or a sigmoid function. To apply the algorithm, PNN is realized by a self-organizing genotype representation with a linked list data structure. Simulations show that the algorithm can build the PNN with less hidden nodes than thc existing learning algorithm using error hack propagation(EE3P) and network growing strategy.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.3
• /
• pp.242-247
• /
• 2015

In this study, we propose the design of Radial Basis Function Neural Network(RBFNN) classifier in order to classify between precipitation and non-precipitation echo. The characteristics of meteorological radar data is analyzed for classifying precipitation and non-precipitation echo. Input variables is selected as DZ, SDZ, VGZ, SPN, DZ_FR, VR by performing pre-processing of UF data based on the characteristics analysis and these are composed of training and test data. Finally, QC data being used in Korea Meteorological Administration is applied to compare with the performance results of proposed classifier.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.9 no.5
• /
• pp.467-477
• /
• 2004

A new scheme to estimate the moment of inertia in the servo motor drive system in very low speed is proposed in this paper. The typical speed estimation scheme in most servo system for low speed operation is sensitive to the variation of machine parameters, especially the moment of inertia. To estimate the motor inertia value, the observer using the Radial Basis Function Networks(RBFN) is applied. The effectiveness of the proposed inertia estimation method is verified by experiments. It is concluded that the speed control performance in the low speed region is improved with the proposed disturbance observer using RBFN.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.20 no.3
• /
• pp.311-319
• /
• 2007

A Meshfree is a method used to establish algebraic equations of system for the whole problem domain without the use of a predefined mesh for the domain discretization. A point interpolation method is based on combining radial and polynomial basis functions. Involvement of radial basis functions overcomes possible singularity Furthermore, the interpolation function passes through all scattered points in an influence domain and thus shape functions are of delta function property. This makes the implementation of essential boundary conditions much easier than the meshfree methods based on the moving least-squares approximation. This study aims to investigate a stress analysis of structural element between a meshfree method and the finite element method. Examples on cantilever type plate, hollow cylinder and stress concentration problems show that the accuracy and convergence rate of the meshfree methods are high.

• Parasites, Hosts and Diseases
• /
• v.23 no.1
• /
• pp.111-122
• /
• 1985

The present study was performed to observe the ultrastructure of the integument of adult Paragonimus westermani. Dogs experimentally infected with 60 metacercariae of F. westermani were autopsied 4 months after the infection. Adult p. westermani were extracted from the dogs and the fine structure was studied by means of scanning and transmission electron microscope. The findings are as follows: 1. Scanning electron microscopic findings showed that the spines and the papillae are distributed at whole body surface but the well developed spines or papaillae are shown around the oral sucker and ventral sucker. 2. At the end of the body, excretory pore was found, the shape was irregular. 3. Transmission electron microscopic findings showed that plasma membrane, tegument, basal lamina, connective tissue, circular muscle layer, longitudinal muscle layer. nerve axon and tegumental cell were observed. 4. In higher magnification, plasma membrance and bar-shaped granules were found at the outer surface of the tegument.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.6
• /
• pp.124-131
• /
• 2014

This paper describes a design of an adaptive baseband modem based on TDMA(time division multiple access) with a relay protocol function for wireless personal area networks. The designed baseband modem is controlled by a master synchronization signal and can be configured a relay network up to 14 hops. For efficient data relay communications, the internal buffer design is optimized by implementing a priority memory bus controller to a single port memory. And the priority memory bus controller is also designed to minimize the number of synthesized logic gates. To implement the synchronization function of the narrowband TDMA relay communication, the number of gates has been reduced by dividing the frame synchronization circuits and the network slot synchronization circuits. By using these methods, the number of gates are used about 37%(34,000 gates) on Xilinx FPGA XC6SLX9 which has 90,000 gates. For the 1024-bit frame size with a 32-bit synchronization word, the communication reception rate is 96.4%. The measured maximum transmission delay of the designed baseband modem is 230.4 msec for the 14-hop relay communication.

• Water for future
• /
• v.29 no.6
• /
• pp.131-139
• /
• 1996

The main goal of this study is a rainfall-runoff analysis using atopographically-based distributed model. It consists of two parts: one is a direct runoff submodel and the other is a baseflow submodel. The direct runoff submodel is a distributed model which routed through the drainage networks with a kinematic wave model. The baseflow submodel is considered as a lumped system. This model makes it possible to take the effect of areal and temporal distribution of storm into accout.

• The Journal of Information Technology
• /
• v.5 no.2
• /
• pp.69-80
• /
• 2002

Conventionally, we have used an acoustic microscope at single operating frequency. The resolution and quality of the measured images are determined by transducer of the microscope. In this paper, we have studied Vertical Resolution Enhancement with Acoustic Reflection Microscope using combining bases of support for SFR(Spatial Frequency Response). Increased Vertical resolution can be obtained by taking three-dimensional images at more that one frequency and numerically combining the results. As results of the experiment, we could get enhanced images with the rate of contrast in proportion to the changing rate of depth.

• Investigative Magnetic Resonance Imaging
• /
• v.17 no.1
• /
• pp.55-58
• /
• 2013

Persistent proatlantal artery (PPA) is a rare embryologically remnant carotico-vertebrobasilar anastomoses. There are two types of PPA according to embryological considerations, origin and anatomic course. Type I PPA usually originate from internal carotid artery and not traversing transverse foramen. Type II PPA traverses from external carotid artery to C1 transverse foramen. The PPA is usually found incidentally without clinical symptoms, but can be related to several clinically significant vascular lesions, such as hypoplastic vertebral artery, intracranial arteriovenous malformation and in a case of carotid endarterectomy or external carotid artery embolization. So, thorough understanding of this anomaly is needed and we report a case of type II PPA diagnosed by MR angiography.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.34 no.4
• /
• pp.199-204
• /
• 2021

In this study, an isogoemetric analysis (IGA) method that uses NURBS (Non-Uniform Rational B-Spline) basis functions in computer-aided design (CAD) systems is employed to account for the geometric exactness of curved electrodes constituting an electro-adhesive pad in electrostatic problems. The IGA is advantageous for obtaining precise normal vectors when computing the electro-adhesive forces on curved surfaces. By performing parametric studies using numerical examples, we demonstrate the superior performance of the curved electrodes, which is attributed to the increase in the normal component of the electro-adhesive forces. In addition, concave curved electrodes exhibit better performance than their convex counterparts.