• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.10 no.5
• /
• pp.57-62
• /
• 2010

Recently, decision tree techniques have been studied in terms of quick searching and extracting of massive data in medical fields. Although many different techniques have been developed such as CART, C4.5 and CHAID which are belong to a pie in Clermont decision tree classification algorithm, those methods can jeopardize remained data by the binary method during procedures. In brief, C4.5 method composes a decision tree by entropy levels. In contrast, CART method does by entropy matrix in categorical or continuous data. Therefore, we compared C4.5 and CART methods which were belong to a same pie using breast cancer data to evaluate their performance respectively. To convince data accuracy, we performed cross-validation of results in this paper.

• Advances in nano research
• /
• v.12 no.2
• /
• pp.223-239
• /
• 2022

Object detection has always been to pursue objects with particular properties or representations and to predict details on objects including the positions, sizes and angle of rotation in the current picture. This was a very important subject of computer vision science. While vision-based object tracking strategies for the analysis of competitive videos have been developed, it is still difficult to accurately identify and position a speedy small ball. In this study, deep learning (DP) network was developed to face these obstacles in the study of tennis motion tracking from a complex perspective to understand the performance of athletes. This research has used CNN-VGG 16 to tracking the tennis ball from broadcasting videos while their images are distorted, thin and often invisible not only to identify the image of the ball from a single frame, but also to learn patterns from consecutive frames, then VGG 16 takes images with 640 to 360 sizes to locate the ball and obtain high accuracy in public videos. VGG 16 tests 99.6%, 96.63%, and 99.5%, respectively, of accuracy. In order to avoid overfitting, 9 additional videos and a subset of the previous dataset are partly labelled for the 10-fold cross-validation. The results show that CNN-VGG 16 outperforms the standard approach by a wide margin and provides excellent ball tracking performance.

• Elastomers and Composites
• /
• v.22 no.1
• /
• pp.20-28
• /
• 1987

The characteristic of the dielectric relaxation in silicone rubbers were studied in the frequency range of $1{\times}10^2{\sim}3{\times}10^6Hz$ at the temperature range of $30^{\circ}{\sim}170^{\circ}C$. As the results of the study, it has been confirmed that the silicone rubber containing the cross-linking agants of 2,5-bis(tert-butylperoxy)-2, 5-dimethyl hexane exhibit the dissipation spectra of two kind(${\alpha},\;{\beta}$ dissipation) due to the siloxane and methyl groups. Particularly, the maximum value of dielectric loss spectra of silicone rubber combinning the cross-linking agents of 0.7phr to 1.0phr are on the increasing in high frequency region, but the specimen of above 1.0phr become smaller again. The energy and the entropy of activation on the molicular motion obtained 18.32 kcal/mole and $1.48ca1/mole{\cdot}deg$ in measuring condition respectively.

• Journal of the Optical Society of Korea
• /
• v.20 no.5
• /
• pp.601-606
• /
• 2016

In this study, in order to analyze the low-temperature sintering process of silver and copper nanoparticles, we calculate their melting temperatures and surface melting temperatures with respect to particle size. For this calculation, we introduce the concept of mean-squared displacement of the atom proposed by Shi (1994). Using a parameter defined by the vibrational component of melting entropy, we readily obtained the surface and bulk melting temperatures of copper and silver nanoparticles. We also calculated the absorption cross-section of nanoparticles for variation in the wavelength of light. By using the calculated absorption cross-section of the nanoparticles at the melting temperature, we obtained the laser threshold energy for the sintering process with respect to particle size and wavelength of laser. We found that the absorption cross-section of silver nanoparticles has a resonant peak at a wavelength of close to 350 nm, yielding the lowest threshold energy. We calculated the intensity distribution around the nanoparticles using the finite-difference time-domain method and confirmed the resonant excitation of silver nanoparticles near the wavelength of the resonant peak.

• Journal of the Mineralogical Society of Korea
• /
• v.23 no.4
• /
• pp.367-375
• /
• 2010

Understanding the interactions between earth materials and fluids is essential for studying the diverse geological processes in the Earth's surface and interior. In order to better understand the interactions between earth materials and fluids, we explore the effect of specific surface area and porosity on structural parameters of pore structures. We obtained 3D pore structures, using random packing simulations of porous media composed of single sized spheres with varying the particle size and porosity, and then we analyzed configurational entropy for 2D cross sections of porous media and cube counting fractal dimension for 3D porous networks. The results of the configurational entropy analysis show that the entropy length decreases from 0.8 to 0.2 with increasing specific surface area from 2.4 to $8.3mm^2/mm^3$, and the maximum configurational entropy increases from 0.94 to 0.99 with increasing porosity from 0.33 to 0.46. On the basis of the strong correlation between the liquid volume fraction (i.e., porosity) and configurational entropy, we suggest that elastic properties and viscosity of mantle melts can be expressed using configurational entropy. The results of the cube counting fractal dimension analysis show that cube counting fractal dimension increases with increasing porosity at constant specific surface area, and increases from 2.65 to 2.98 with increasing specific surface area from 2.4 to $8.3mm^2/mm^3$. On the basis of the strong correlation among cube counting fractal dimension, specific surface area, and porosity, we suggest that seismic wave attenuation and structural disorder in fluid-rock-melt composites can be described using cube counting fractal dimension.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.509-516
• /
• 2020

Since the 1960s, many rivers have been polluted and destroyed due to river repair projects for economic development and the covering of small rivers due to urbanization. Many studies have analyzed rivers using measured river topographic factors, but surveying is not easy when the flow rate changes rapidly, such as during a flood. In addition, the previous research has been mainly about the cross section of a river, so information on the longitudinal profile is insufficient. This research used informational entropy theory to obtain an equation that can calculate the average river slope, river slope, and river longitudinal elevation for a river basin in real time. The applicability was analyzed through comparison with measured data of a river's characteristic factors obtained from a river plan. The parameters were calculated using informational entropy theory, nonlinear regression analysis, and actual data. The longitudinal elevation entropy equation for each stream was then calculated, and so was the average river slope. All of the values were over 0.96, so it seems that reliable results can be obtained when calculating river characteristic factors.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.25 no.9
• /
• pp.952-958
• /
• 2014

In this paper, we propose a parametric sparse recovery algorithm(SRA) applied to a radar signal model, based on the compressive sensing(CS), for the ISAR(Inverse Synthetic Aperture Radar) image reconstruction from an incomplete radar-cross-section(RCS) data and for the estimation of rotation rate of a target. As the SRA, the iteratively-reweighted-least-square(IRLS) is combined with the radar signal model including chirp components with unknown chirp rate in the cross-range direction. In addition, the particle swarm optimization(PSO) technique is considered for searching correct parameters related to the rotation rate. Therefore, the parametric SRA based on the IRLS can reconstruct ISAR image and estimate the rotation rate of a target efficiently, although there exists missing data in observed RCS data samples. The performance of the proposed method in terms of image entropy is also compared with that of the traditional interpolation methods for the incomplete RCS data.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.22 no.3
• /
• pp.291-297
• /
• 2012

Conventional Fourier analysis can give only limited information about the dynamic characteristics of nonstationary signals. Instead, time-frequency analysis is widely used to investigate the nonstationary signal in detail. Several time-frequency analysis methods are compared for a typical acoustic emission burst generated during the impact between a ferrite ceramic and aluminum plate. This AE burst is inherently nonstationary and random containing many frequency contents, which leads to severe interference between cross terms in bilinear convolution type distributions. The smoothing and reassignment processes can improve the readability and resolution of the results. Spectrogram and scalogram of the AE burst are obtained and compared to get the characteristics information. Renyi entropies are computed for various bilinear time-frequency transforms to evaluate the randomness. These bilinear transforms are reassigned by using the improved algorithm in discrete computation.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.4
• /
• pp.209-216
• /
• 1996

In this paper, we propose a learning method of multi-layer perceptrons (MLPs) with 8-bit data precision. The suggested method uses the cross-entropy cost function to remove the slope term of error signal in output layer. To decrease the possibility of overflows, we use 16-bit weighted sum results into the 8-bit data with appropriate range. In the forwared propagation, the range for bit-conversion is determined using the saturation property of sigmoid function. In the backwared propagation, the range for bit-conversion is derived using the probability density function of back-propagated signal. In a simulation study to classify hadwritten digits in the CEDAR database, our method shows similar generalization performance to the error back-propagation learning with 16-bit precision.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2005.09a
• /
• pp.183-187
• /
• 2005

In this paper, we propose a heuristic method to select features using a Two-Phase Markov Blanket-based (TPMB) algorithm. The first phase, filtering phase, of TPMB algorithm works by filtering the obviously redundant features. A non-linear correlation method based on Information theory is used as a metric to measure the redundancy of a feature [1]. In second phase, approximating phase, the Markov Blanket (MB) of a system is estimated by employing the concept of cross entropy to identify the MB. We perform experiments on microarray data and report two popular dataset, AML-ALL [3] and colon tumor [4], in this paper. The experimental results show that the TPMB algorithm can significantly reduce the number of features while maintaining the accuracy of the classifiers.