• International Journal of Control, Automation, and Systems
• /
• v.6 no.1
• /
• pp.109-118
• /
• 2008

We present two estimators for discrete non-Gaussian and nonstationary probability density estimation based on a dynamic Bayesian network (DBN). The first estimator is for off line computation and consists of a DBN whose transition distribution is represented in terms of kernel functions. The estimator parameters are the weights and shifts of the kernel functions. The parameters are determined through a recursive learning algorithm using maximum likelihood (ML) estimation. The second estimator is a DBN whose parameters form the transition probabilities. We use an asymptotically convergent, recursive, on-line algorithm to update the parameters using observation data. The DBN calculates the state probabilities using the estimated parameters. We provide examples that demonstrate the usefulness and simplicity of the two proposed estimators.

• Journal of Information Processing Systems
• /
• v.8 no.4
• /
• pp.669-684
• /
• 2012

Discrete wavelet transforms are extensively preferred in biomedical signal processing for denoising, feature extraction, and compression. This paper presents a new denoising method based on the modeling of discrete wavelet coefficients of ECG in selected sub-bands with Kernel density estimation. The modeling provides a statistical distribution of information and noise. A Gaussian kernel with bounded support is used for modeling sub-band coefficients and thresholds and is estimated by placing a sliding window on a normalized cumulative density function. We evaluated this approach on offline noisy ECG records from the Cardiovascular Research Centre of the University of Glasgow and on records from the MIT-BIH Arrythmia database. Results show that our proposed technique has a more reliable physical basis and provides improvement in the Signal-to-Noise Ratio (SNR) and Percentage RMS Difference (PRD). The morphological information of ECG signals is found to be unaffected after employing denoising. This is quantified by calculating the mean square error between the feature vectors of original and denoised signal. MSE values are less than 0.05 for most of the cases.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.15 no.5
• /
• pp.601-614
• /
• 2012

Since the optimized use of sonar systems available for detection is a very practical problem for a given ocean environment, the measure of mission achievability is needed for operating the sonar system efficiently. In this paper, a theory on Measure Of Effectiveness(MOE) for specific mission such as detection is described as the measure of mission achievability, and a recursive Cumulative Detection Probability(CDP) algorithm is found to be most efficient from comparing three CDP algorithms for discrete glimpses search to reduce computation time and memory for complicated scenarios. The three CDPs which are MOE for sonar-maneuver pattern are calculated as time evolves for comparison, based on three different formula depending on the assumptions as follows; dependent or independent glimpses, unimodal or non-unimodal distribution of Probability of Detection(PD) as a function of observation time interval for detection. The proposed CDP algorithm which is made from unimodal formula is verified and applied to OASPP(Optimal Acoustic Search Path Planning) with complicated scenarios.

• The Korean Journal of Applied Statistics
• /
• v.27 no.3
• /
• pp.445-459
• /
• 2014

As a certain job is repeatedly done by a worker, the outcome comparative to the effort to complete the job gets more remarkable. The outcome may be the time required and fraction defective. This phenomenon is referred to a learning-curve effect. We focus on the parametric modeling of the learning-curve effects on count data using a logistic cumulative distribution function and some probability mass functions such as a Poisson and negative binomial. We conduct various simulation scenarios to clarify the characteristics of the proposed model. We also consider a real application to compare the two discrete-type distribution functions.

• Kyungpook Mathematical Journal
• /
• v.57 no.3
• /
• pp.493-502
• /
• 2017

We propose an accurate approximation method via discrete Krawtchouk orthogonal polynomials to the distribution of a sum of independent but non-identically distributed binomial random variables. This approximation is a weighted binomial distribution with no need for continuity correction unlike commonly used density approximation methods such as saddlepoint, Gram-Charlier A type(GC), and Gaussian approximation methods. The accuracy obtained from the proposed approximation is compared with saddlepoint approximations applied by Eisinga et al. [4], which are the most accurate method among higher order asymptotic approximation methods. The numerical results show that the proposed approximation in general provide more accurate estimates over the entire range for the target probability mass function including the right-tail probabilities. In addition, the method is mathematically tractable and computationally easy to program.

• Structural Engineering and Mechanics
• /
• v.39 no.6
• /
• pp.795-812
• /
• 2011

Estimation of damage probability of buildings under a future earthquake is an essential issue to ensure the seismic reliability. Fragility curves are useful tools for showing the probability of structural damage due to earthquakes as a function of ground motion indices. The purpose of this study is to compare the damage probability of R/C buildings with low and high level of strength and ductility through fragility analysis. Two different types of sample buildings have been considered which represent the building types mentioned above. The first one was designed according to TEC-2007 and the latter was designed according to TEC-1975. The pushover curves of sample buildings were obtained via pushover analyses. Using 60 ground motion records, nonlinear time-history analyses of equivalent single degree of freedom systems were performed using bilinear hysteretic model and peak-oriented hysteretic model with stiffness - strength deterioration for each scaled elastic spectral displacement. The damage measure is maximum inter-story drift ratio and each performance level considered in this study has an assumed limit value of damage measure. Discrete damage probabilities were calculated using statistical methods for each considered performance level and elastic spectral displacement. Consequently, continuous fragility curves have been constructed based on the lognormal distribution assumption. Furthermore, the effect of hysteresis model parameters on the damage probability is investigated.

• Proceedings of the KSME Conference
• /
• 2004.04a
• /
• pp.1813-1818
• /
• 2004

Discrete Wavelet Transform (DWT) has been applied to the Direct Numerical Simulation (DNS) data of turbulent channel flow. DWT splits the turbulent flow into two orthogonal parts, one corresponding to coherent structures and the other to incoherent background flow. The coherent structure is extracted from not vorticity field but velocity's since the channel flow is not isotropic. By comparing DWT's result of channel flow with that of isotropic flow, it is shown that coherent structure maintains the properties of original channel flow. The velocity field of coherent structures can be represented by few wavelet modes and that these modes are sufficient to reproduce the velocity probability distribution function (PDF) and the energy spectrum over the entire inertial range. The remaining incoherent background flow is homogeneous, has small amplitude, and is uncorrelated. These results are compared with those obtained for the same compression rate using large eddy simulation (LES) filtering. In contrast to the incoherent background flow of DWT, the LES subgrid scales have a much larger amplitude and are correlated, which makes their statistical modeling more difficult.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.33 no.3
• /
• pp.93-105
• /
• 2008

Semi-supervised learning uses a small amount of labeled data to predict labels of unlabeled data as well as to improve clustering performance, whereas unsupervised learning analyzes only unlabeled data for clustering purpose. We propose a new clustering-based semi-supervised learning method by reflecting the initial predicted labels of unlabeled data on the objective function. The initial prediction should be done in terms of a discrete probability distribution through a classification method using labeled data. As a result, clusters are formed and labels of unlabeled data are predicted according to the Information of labeled data in the same cluster. We evaluate and compare the performance of the proposed method in terms of classification errors through numerical experiments with blinded labeled data.

• 한국연소학회:학술대회논문집
• /
• 1999.10a
• /
• pp.139-148
• /
• 1999

In oder to analyze the effect of operating conditions on pulverized coal combustion, a numerical study is conducted at the pulverized coal combustor. Eulerian approach is used for the gas phase, whereas Lagrangian approach is used for the particle phase. Turbulence is modeled using standard ${\kappa}-{\varepsilon}$ model. The description of species transport and combustion chemistry is based on the mixture fraction/probability density function(PDF) approach. Radiation is modeled using P-l model. The turbulent dispersion of particles is modeled using discrete random walk model. Swirl number of secondary air affects the flame front, particle residence time and carbon conversion. Primary/Secondary air mass ratio also affects the flame front but little affects the carbon conversion and particle residence time. Air-fuel ratio only affects the flame front due to lack of oxygen. Radiation strongly affects the flame front and gas temperature distribution because pulverized coal flame of high temperature is considered.

• 한국전산유체공학회:학술대회논문집
• /
• 1999.05a
• /
• pp.199-204
• /
• 1999

Three dimensional numerical analysis for the turbulent reactive flow and radiative heat transfer in the walking beam type of a reheat furnace in POSCO has been carried out by the industrial code FLUENT. Computations an based on the conservation equations of mass, momentum, energy and species with the $k-{\varepsilon}$ turbulence model and mixture fraction/PDF(Probability Density Function) approach for the combustion rate. Radiative heat transfer is computed by the discrete ordinates radiation model in combination with the weighted-sum-of-gray-gas model for the absorption coefficient of gas medium. The predicted temperture distribution in the reheat furnace and energy flow fractions are in reasonable agreement with the measurement data.