• Journal of the Korean Institute of Intelligent Systems
• /
• v.6 no.3
• /
• pp.81-88
• /
• 1996

Cluster analysis is based on partitioning a collection of data points into a number of clusters, where the data points in side a cluster have a certain degree of similarity and it is a fundamental process of data analysis. So, it has been playing an important role in solving many problems in pattern recognition and image processing. For these many clustering algorithms depending on distance criteria have been developed and fuzzy set theory has been introduced to reflect the description of real data, where boundaries might be fuzzy. If fuzzy cluster analysis is tomake a significant contribution to engineering applications, much more attention must be paid to fundamental questions of cluster validity problem which is how well it has identified the structure that is present in the data. Several validity functionals such as partition coefficient, claasification entropy and proportion exponent, have been used for measuring validity mathematically. But the issue of cluster validity involves complex aspects, it is difficult to measure it with one measuring function as the conventional study. In this paper, we propose four performance indices and the way to measure the quality of clustering formed by given learning strategy.

• Journal of Advanced Navigation Technology
• /
• v.14 no.4
• /
• pp.512-520
• /
• 2010

As the applications based on Mobile and Ubiquitous becoming more extensive, the communication security issues of those applications are appearing to be the most important concern. Therefore, every part of the system should be thoroughly designed and mutually coordinated in order to support overall security of the system. In this paper. we propose new technique which uses the voice features in order to generate Mobile One Time Passwords(OTPs). Voice is considered to be one of the powerful personal authentication factors of biometrics and it can be used for generating variable passwords for one time use. Also we performed a simulation of homomorphic variability of voice feature points using dendrogram and distribution of voice feature points for proposed password generation method.

• Journal of IKEEE
• /
• v.7 no.1 s.12
• /
• pp.22-31
• /
• 2003

Conventional stimulus patterns have used DC for discrimination of acupoint and meridian which is the basic object of diagnosis and medical treatment in oriental medicine. Those discriminate conduction points by stimulation on body skin with DC. But, it is insufficient to reliability in discrimination ratio, coincident ratio, body effect, reproductivity. Therefore, this paper has extracted the optimal parameter of frequency and waveform in order to improve conventional pattern, and proposed the SPAC(Single Power Alternative Current) stimulus pattern applying that. Also, We proposes algorithm which is able to discriminate with low pressure of the electrode by displaying in the level meter both the absolution and relation value of the skin current. It can decrease pain and body effect by electrode pressure and discriminate acupoint regardless of skin current in difficult discrimination spot. We have compared the performance of system applying the extracted optimal parameter and algorithm. We have compared discrimination, coincident ratio of both conduction point and traditional acupoints by acupoint stimulation pattern. In the results, we confirmed reliability of SPAC stimulus pattern.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1302-1308
• /
• 2019

This paper presents an approach for classifying image made by acquired position data from a 2D Lidar sensor with a convolutional neural network (CNN). Lidar sensor has been widely used for unmanned devices owing to advantages in term of data accuracy, robustness against geometry distortion and light variations. A CNN algorithm consists of one or more convolutional and pooling layers and has shown a satisfactory performance for image classification. In this paper, different types of CNN architectures based on training methods, Gradient Descent(GD) and Levenberg-arquardt(LM), are implemented. The LM method has two types based on the frequency of approximating Hessian matrix, one of the factors to update training parameters. Simulation results of the LM algorithms show better classification performance of the image data than that of the GD algorithm. In addition, the LM algorithm with more frequent Hessian matrix approximation shows a smaller error than the other type of LM algorithm.

• The Journal of Society for e-Business Studies
• /
• v.9 no.4
• /
• pp.117-136
• /
• 2004

As the time-to-market gets more important for competitiveness of an enterprise in manufacturing industry, it becomes important to shorten the development cycle of a product. Reuse of existing design models and e-Catalog for components are required for faster product development. To achieve this goal, an electric catalog must provide parametric CAD models since parametric information is indispensable for configuration design. There are difficulties in building up a parametric library of all the necessary combination using a CAD system, since we have too many combinations of components for a product. For example, there are at least 80 million combinations of components on one page of paper catalog of a mold base. To solve this problem, we propose the method of table parametric for the automatic generation of parametric CAD models. Any combination of mold base can be generated by mapping between a classification system of an electric catalog and the design parameters set of the table parametric. We propose how to select parametric models and to construct the design parameters set.

• Journal of the Korean Institute of Gas
• /
• v.9 no.4 s.29
• /
• pp.36-43
• /
• 2005

In this paper, the optimized design of a roof structure f3r a LNG outer tank has been analyzed using the Taguchi design method. This method may efficiently optimize the design parameters of a LNG roof structure in terms of H beam and L beam structures, and a thickness of a concrete structure. The FEM computed results indicate that the thickness of a concrete structure is a dominant factor of a roof structure design. The H and L beam structures do not affect a maximum stress and deformation of a reinfarced roof structure. This means that H and L beam structures only support a dead weight of a concrete roof during a consolidation of a reinforced concrete. Based on the computed results by the Taguchi design method, the number of beams and thickness of a reinforced concrete are given as H=30, L=7, and t=1.2m.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.47 no.4
• /
• pp.102-108
• /
• 2010

The photovoltaic system changes solar energy into DC by solar cell and this DC is inverted into AC which is used in general houses by inverter. Recently, the use of power of the photovoltaic system is increased. Therefore, the study of 3 phase solar system to transmit large power is very important. This paper proposes a method that finds simply faults and diagnoses the switch open faults of 3-phase pulse width modulation (PWM) inverter of grid-connected photovoltaic system. The proposed method in $\alpha\beta$ plane uses the patterns of trajectory image as the characteristic parameters and differenciates a normal state and open states of switches. Then, the result is made into tree. The tree is composed of 21 fault patterns and the parameters to classify faults are a shape, a trajectory area, a distributed angle, and a typical vector angle. The result shows that the proposed method diagnosed fault diagnoses, classified correctly them, and made a pattern tree by fault patterns.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.4 no.1
• /
• pp.3-15
• /
• 2000

As an OLT in the central office controls up to 64 ONUs in the subscriber area via a passive optical splitter, the hU PON system can accomodate PTTx in a single platform with low cost. To operate the system, it is important to implement an efficient MAC protocol, however, the protocol is currently the further study area in the ITU-T 0.983.1. In this paper, we suggest the MAC protocol which is needed to send cells of ONU to upstream, and based on the ITU-T G.983.1. We survey conventional MAC protocols which are not based on G.983.1, and then formulate the minislot period and length for the grant request and determine the optimal value of each parameter. Also, we suggest a coding scheme for the grant field of the PLOAM cell and the procedure allocating optimal parameters to the ONU.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.7
• /
• pp.1759-1769
• /
• 1997

The Error BackPropagation (EBP) algorithm for multi-layered neural networks is widely used in various areas such as associative memory, speech recognition, pattern recognition and robotics, etc. Nevertheless, many researchers have continuously published papers about improvements over the original EBP algorithm. The main reason for this research activity is that EBP is exceeding slow when the number of neurons and the size of training set is large. In this study, we developed new learning speed acceleration methods using variable learning rate, variable momentum rate and variable slope for the sigmoid function. During the learning process, these parameters should be adjusted continuously according to the total error of network, and it has been shown that these methods significantly reduced learning time over the original EBP. In order to show the efficiency of the proposed methods, first we have used binary data which are made by random number generator and showed the vast improvements in terms of epoch. Also, we have applied our methods to the binary-valued Monk's data, 4, 5, 6, 7-bit parity checker and real-valued Iris data which are famous benchmark training sets for machine learning.

• The Journal of the Korea Contents Association
• /
• v.14 no.11
• /
• pp.355-361
• /
• 2014

The aim of the present study was to evaluate a relative emission of image plate (IP) in computed radiography (CR) system by using relative sensitivity in film/screen methods. The characteristic curve was obtained by using the uniform aluminum 11-step wedge penetrometer. X-ray exposure factors on radiographic digital image were 50 kVp, 10 mAs. We adjusted zero of all parameter of algorithms (MUSICA) so proximate to raw data and applied to 200 of exposure class. Modeling on relative emission of IP are used IP without fading time and IP after 4 hours, 8 hours, 12 hours, 24 hours in the respective storage after X-ray exposure. The results of this study showed that the sensitivity point density at the measuring of relative sensitivity in CR was suited pixel values of the 2000 easy to relatively measure the characteristic curve and when relative sensitivity is decreased, the amount of light emitted from the image signal for generating was also decreased. In conclusion, the proposed method of measurement of relative sensitivity can be utilized to evaluate the quantity of relative emission of IP in CR system.