• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.18-20
• /
• 2017

In this paper, we propose a new classification method to complement a $na{\ddot{i}}ve$ Bayesian classifier. This classifier assumes data distribution to be Gaussian, finds the discriminant function, and derives the decision curve. However, this method does not investigate finding the decision curve in much detail, and there are some minor problems that arise in finding an accurate discriminant function. Our findings also show that this method could produce errors when finding the decision curve. The aim of this study has therefore been to investigate existing problems and suggest a more reliable classification method. To do this, we utilize the gradient to find the decision curve. We then compare/analyze our algorithm with the $na{\ddot{i}}ve$ Bayesian method. Performance evaluation indicates that the average accuracy of our classification method is about 10% higher than $na{\ddot{i}}ve$ Bayes.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.12 no.2
• /
• pp.222-227
• /
• 2009

The bias characteristics due to the changes of temperature and temperature gradient of fiber coil are investigated in fiber-optic gyroscope. The bias performance is degraded with the changes of temperature and temperature gradient of fiber coil. The temperature compensation using both the temperature-dependent bias measurement and the temperature-induced error model of fiber-optic gyroscope improves the bias stability about 3 times as much as the uncompensated original case, which leads to very stable bias performance over the temperature range from $-35^{\circ}C$ to $+77^{\circ}C$.

• Transactions on Control, Automation and Systems Engineering
• /
• v.4 no.4
• /
• pp.330-340
• /
• 2002

In this Paper. a non-linear approach to a design of model reference adaptive control is presented. The approach is demonstrated by a case study of a simple single-pole and no zero, linear, discrete-time plant. The essence of the idea is to generate a full non-linear model of the plant dynamics and the parameter adaptation dynamics as a gradient descent algorithm with respect to a Riemannian metric. It is shown how a Riemannian metric can be chosen so that the modelled plant dynamics do in fact match the true plant dynamics. The performance of the proposed scheme is compared to a traditional model reference adaptive control scheme using the classical sensitivity derivatives (Euclidean gradients) for the descent algorithm.

• Communications of the Korean Mathematical Society
• /
• v.9 no.2
• /
• pp.439-448
• /
• 1994

It is known that the steepest descent(SD) method and the conjugate gradient(CG) method [1, 2, 5, 6] converge when these methods are applied to solve linear systems of the form Ax = b, where A is symmetric and positive definite. For some finite difference discretizations of elliptic problems, one gets positive definite matrices that are almost symmetric. Practically, the SD method and the CG method work for these matrices. However, the convergence of these methods is not guaranteed theoretically. The SD method is also called Orthores(1) in iterative method papers. Elman [4] states that the convergence proof for Orthores($\kappa$), with $\kappa$ a positive integer, is not heard. In this paper, we prove that the SD method and the CG method converge when the $\iota$$^2$ matrix norm of the non-symmetric part of a positive definite matrix is less than some value related to the smallest and the largest eigenvalues of the symmetric part of the given matrix.(omitted)

• Structural Engineering and Mechanics
• /
• v.78 no.1
• /
• pp.103-116
• /
• 2021

In this work, a model of a functionally graded (FG) nanotube conveying fluid embedded in an elastic medium is developed based on the nonlocal strain gradient theory (NSGT) in conjunction with Euler-Bernoulli beam theory (EBT). The main objective of this research is to investigate the nonlinear vibration and stability analysis of fluid-conveying nanotubes. The governing equations of motion are derived by means of Hamiltonian principle. The analytical expressions of nonlinear frequencies and critical flow velocities for two different types of boundary conditions including pinned-pinned (P-P) and clamped-clamped (C-C) conditions are obtained by employing Galerkin method as well as Hamiltonian Approach (HA). Comparison of the obtained results with the published works show the acceptable accuracy of the current solutions. The effects of the power-law index, the nonlocal and material length scale parameters and the elastic medium on the stability and nonlinear responses of FG nanotubes are thoroughly investigated and discussed.

• Journal of Korean Society of Rural Planning
• /
• v.21 no.2
• /
• pp.127-135
• /
• 2015

In recent years, meteorological disasters have frequently occurred in rural areas. As a result, there have been growing concerns over the protective measures needed. In order to avoid natural risks and damage, and to strengthen countermeasure to meteorological disasters, local governments needs to be prepared. Therefore, this paper seeks to prevent meteorological disasters through mapping of inundation vulnerability in agricultural land, Chungcheongnam-do. In doing so, this study were considered 5 variables (i.e. precipitation, region of altitude below 50m, region of slope gradient is below 10 degree, distance from river within less 50m) for creating vulnerability map. The precipitation was excluded in five variables. Since, the precipitation which include Daily maximum precipitation, 2-Daily maximum precipitation, summer precipitation was not any correlation among them. The results of analysing four variables, exclusive of precipitation, were showed that the agricultural lands where located in Dangjin, Buyeo, Hongseong and Asan were low correlation of inundation vulnerability by overlapping analysis. Moreover, The correlation analysis was showed low correlation between each factors and the annual average area of agricultural lands' inundation, whereas, the correlation analysis which was overlapping each factor showed high correlation. In conclusion, in order to create reliable vulnerability map in agricultural lands, Chungcheongnam-do, it must be considered to overlap analysis of the four main factors such region of altitude below 50m, region of slope gradient is below 10 degree, distance from river within less 50m. We suppose that this study's analysis can help to set the preparedness site of agricultural lands inundation.

• Journal of the Korean earth science society
• /
• v.27 no.1
• /
• pp.61-72
• /
• 2006

Numerical studies on the influence of interaction between atmosphere and ocean on the variation of Karman vortex at the lee side of Jeju Island were carried out. Karman vortex tends to be occurred at limited height associated with Hanla mountain. And we can find clear Karman vortex at 900 hPa height in this study. One big vortex cell occurred at lee side of Jeju Island in the begging stage of its development and the cell was divided into three small cells as time goes by. And the strength and lifetime of small vortexes depend on the distribution of SST (Sea Surface Temperature). Weak gradient of SST makes long-lasting Karman vortex but produces weak potential vorticity at lee side of Jeju-do in comparison with the vortex under strong SST gradient. Strong SST gradient also increases not only the mixing depth but also the mixing ratio at lower level of troposphere. And the increased atmospheric mixing decreases the mechanical forcing due to isolated topography. Then the strength of Karman vortex at the lee side of Jeju Island becomes weak under strong gradient of SST. Thus the evolution of Karman vortex is closely related to distribution of SST around the isolated island.

• The Journal of the Korea Contents Association
• /
• v.18 no.9
• /
• pp.623-632
• /
• 2018

Both investors and researchers are attentive to the prediction of stock price movement directions since the accurate prediction plays an important role in strategic decision making on stock trading. According to previous studies, taken together, one can see that different factors are considered depending on stock markets and prediction periods. This paper aims to analyze what data mining techniques show better performance with some representative index and stock price datasets in the Korea stock market. In particular, extreme gradient boosting technique, proving itself to be the fore-runner through recent open competitions, is applied to the prediction problem. Its performance has been analyzed in comparison with other data mining techniques reported good in the prediction of stock price movement directions such as random forests, support vector machines, and artificial neural networks. Through experiments with the index/price datasets of 12 years, it is identified that the gradient boosting technique is the best in predicting the movement directions after 1 to 4 days with a few partial equivalence to the other techniques.

• Journal of Biomedical Engineering Research
• /
• v.16 no.4
• /
• pp.431-438
• /
• 1995

Functional imaging based on the susceptibility only is achieved by separation of the susceptibility effect from the mixture of flow effect by use of a tailored RF pulse in conjunction with gradient echo sequence. Using the tailored RF pulse the susceptibility enhanced functional imaging appears to be explicitly related to the deoxygenation processes, while in the conventional gradient echo technique functional contrast on $T2^{*}$ effect images appear to be mixed with a significant fraction of blood flow (in- flow) signals of both arterial as well as venous bloods due to the nature of the fast sequence employed with the gradient echo technique. In this paper, using the tailored RF pulses, one can unambiguously separate the susceptibility and flow effects in functional imaging. Since the signal obtained can be made sufficiently high and represents oxygenation process more accurately, it seems possible to study quantitative oxygen metabolisms in brain function hitherto difficult to do with other gradient echo techniques.

• Geophysics and Geophysical Exploration
• /
• v.10 no.2
• /
• pp.147-153
• /
• 2007

The conjugate gradient (CG) method is one of the most efficient algorithms for solving a linear system of equations. In addition to being used as a linear equation solver, it can be applied to a least-squares problem. When the CG method is applied to large-scale three-dimensional inversion of magnetotelluric data, two approaches have been pursued; one is the linear CG inversion in which each step of the Gauss-Newton iteration is incompletely solved using a truncated CG technique, and the other is referred to as the nonlinear CG inversion in which CG is directly applied to the minimization of objective functional for a nonlinear inverse problem. In each procedure we only need to compute the effect of the sensitivity matrix or its transpose multiplying an arbitrary vector, significantly reducing the computational requirements needed to do large-scale inversion.