• Journal of KIISE:Software and Applications
• /
• v.35 no.7
• /
• pp.417-423
• /
• 2008

In this paper we present a probabilistic method for source separation in the case here each source has a certain temporal structure. We tackle the problem of source separation by maximum pseudo-likelihood estimation, representing the latent function which characterizes the temporal structure of each source by a random process with a Gaussian prior. The resulting pseudo-likelihood of the data is Gaussian, determined by a mixing matrix as well as by the predictive mean and covariance matrix that can easily be computed by Gaussian process (GP) regression. Gradient-based optimization is applied to estimate the demixing matrix through maximizing the log-pseudo-likelihood of the data. umerical experiments confirm the useful behavior of our method, compared to existing source separation methods.

• The Korean Journal of Applied Statistics
• /
• v.3 no.1
• /
• pp.59-78
• /
• 1990

The subset selection approach introduced by Gupta plays an important role in the multiple decision procedures. For the normal means problem with common unknown variance, some operating characteristics of the selection procedure have been investigated via Monte Carlo simulation. Also some properties including efficiencies of the selection procedure are examined when the data are contaminated.

• Journal of the Korea Society of Computer and Information
• /
• v.15 no.7
• /
• pp.11-17
• /
• 2010

This paper proposes an improved SMO solving a quadratic optmization problem for class imbalanced learning. The SMO algorithm is aproporiate for solving the optimization problem of a support vector machine that assigns the different regularization values to the two classes, and the prosoposed SMO learning algorithm iterates the learning steps to find the current optimal solutions of only two Lagrange variables selected per class. The proposed algorithm is tested with the UCI benchmarking problems and compared to the experimental results of the SMO algorithm with the g-mean measure that considers class imbalanced distribution for gerneralization performance. In comparison to the SMO algorithm, the proposed algorithm is effective to improve the prediction rate of the minority class data and could shorthen the training time.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.11 no.2
• /
• pp.169-174
• /
• 2018

In general, the methods of the analysis of variance(ANOVA) for the continuous data and the chi-square test for the discrete data are used for statistical analysis of the effect and the association. In multidimensional data, analysis of hierarchical structure is required and statistical linear model is adopted. The structure of the linear model requires the normality of the data. A multidimensional categorical data analysis methods are used for causal relations, interactions, and correlation analysis. In this paper, Bayesian network model using probability distribution is proposed to reduce analysis procedure and analyze interactions and causal relationships in categorical data analysis.

• Journal of Korean Society for Quality Management
• /
• v.15 no.2
• /
• pp.10-19
• /
• 1987

Statistical control charts are useful tools to monitor and control the manufacturing processes and are widely used in most Korean industries. Many Korean companies, however, do not always obtain desired results from the traditional control charts by Shewhart such as the $\overline{X}$-chart, X-chart, $\widetilde{X}$-chart, etc. This is partly because the quality charterstics of the process are not distributed normally but are skewed due to the intermittent production, small lot size, etc. In the Shewhart $\overline{X}$-chart, which is the most widely used one in Korea, such skewed distributions make the plots to be inclined below or above the central line or outside the control limits although no assignable causes can be found. To overcome such shortcomings in nonnormally distributed processes, a distribution-free type of confidence interval can be used, which should be based on order statistics. This thesis is concerned with the design of control chart based on a sample median which is easy to use in practical situation and therefore properties for nonnormal distributions may be easily analyzed. Control limits and central lines are given for the more famous nonnormal distributions, such as Gamma, Beta, Lognormal, Weibull, Pareto, and Truncated-normal distributions.

• Journal of the Korean Geosynthetics Society
• /
• v.17 no.4
• /
• pp.103-108
• /
• 2018

The fragility curves for CFRD dams are derived in this study for probabilistic damage estimation as a function of a ground motion intensity. The dam crest settlement, which is a widely used damage index, is used for minor, moderate, and extensive damage states. The settlement is calculated from nonlinear dynamic numerical simulations. The accuracy of the numerical model is validated through comparison with a centrifuge test. The fragility curve is represented as a log normal distribution function and presented as a function of the peak ground acceleration. The fragility curves developed in this study can be utilized for real time assessment of the damage of dams.

• Journal of the Korean Society for Railway
• /
• v.15 no.6
• /
• pp.623-630
• /
• 2012

Formation used as trackbed foundation for providing vertical bearing capacity onto rail foundation are composed of crushed stones usually with certain type of grain size distribution. Permanent deformation in trackbed foundation can be generated by increasing number of load repetition due to train traffic increases, causing track irregularity. In this study, a specially prepared trackbed foundation materials (M-40) used in Korea has been tested using a large repetitive triaxial compression apparatus in order to understand resilient and permanent deformation characteristics of the material. From these test results, resilient and permanent deformation characteristic are analyzed so that a permanent deformation model is developed which can consider number of load repetition N, confining stress (${\sigma}_3$), shear stress ratio(${\tau}/{\tau}_f$) and stiffness of the material.

• Bulletin of the Society of Naval Architects of Korea
• /
• v.26 no.2
• /
• pp.25-31
• /
• 1989

Two-dimensional large-amplitude motions in regular harmonic wave are treated in time domain, by satisfying the exact body boundary condition and the linear free surface condition. For the present numerical calculation, the method of free-surface spectral representation with simple source distribution on the instantaneous body surface has been extended to include the effect of the incident wave. Calculations of the wave exciting force are performed for a submerged circular cylinder fixed or oscillating with large amplitude. Especially, nonlinear effects on the time-mean forces are studied in detail. It is shown that relative motion between the body and the fluid particle gives a significant effect on the lift and drift forces. Also, large-amplitude motion of a submerged circular cylinder and that of a floating Lewis-form cylinder are directly simulated in time domain. In the calculation results, some nonlinear effects are shown.

• The Journal of the Korea Contents Association
• /
• v.13 no.2
• /
• pp.52-61
• /
• 2013

In wireless sensor networks, the geographical positioning scheme is one of core technologies for sensor applications such as disaster monitoring and environment monitoring. For this reason, studies on range-free positioning schemes have been actively progressing. The density probability scheme based on central limit theorem and normal distribution was proposed to improve the location accuracy in non-uniform sensor network environments. The density probability scheme measures the final positions of unknown nodes by estimating distance through the sensor node communication. However, it has a problem that all of the neighboring nodes have the same 1-hop distance. In this paper, we propose an efficient sensor positioning scheme that overcomes this problem. The proposed scheme performs the second positioning step through the sensing range control after estimating the 1-hop distance of each node in order to minimize the estimation error. Our experimental results show that our proposed scheme improves the accuracy of sensor positioning by about 9% over the density probability scheme and by about 48% over the DV-HOP scheme.

• Journal of Advanced Navigation Technology
• /
• v.14 no.2
• /
• pp.191-197
• /
• 2010

Many does an application and application but the image analysis of face detection considerably is difficult. In order for with effect of the illumination which is irregular in the present paper America the illumination to range evenly in the face which is detected, detects a face territory, Complemented the result which detects only the front face of existing. With LAB color illumination revisions compared in Adaboost face detection of existing and 32% was visible the face detection result which improves. Bought two images which are input and executed Glassfire label rings. Compared Area critical price and became the area of above critical value and revised from RGB smooth anger and LAB images with LCFD system algorithm. The operational conversion image which is extracted like this executed a face territory detection in the object. In order to extract the feature which is necessary to a face detection used AdaBoost algorithms. The face territory remote login with the face territory which tilts in the present paper, until Multi-view face territory detections was possible. Also relationship without high detection rate seems in direction of illumination, With only the public PC application is possible was given proof user authentication field etc.