• 한국정보과학회논문지:소프트웨어및응용
• /
• 제35권7호
• /
• pp.417-423
• /
• 2008

본 논문에서는 각 음원이 시간적 구조를 가졌을 경우 음원들을 분리해내는 확률적 음원분리 방법을 제안한다. 이를 위해 각 음원의 시간적 구조를 가우시안 프로세스(Gaussian process)로 모델링하고 기존의 음원분리 문제를 유사-가능도 최대화 문제(pseudo-likelihood maximization)로 공식화한다. 본 알고리즘을 통해 얻어진 데이타의 유사-가능도는 정규 분포이며 이는 가우시안 프로세스 회귀방법(Gaussian process regression)을 통해 쉽게 계산이 가능하다. 음원분리의 역혼합 행렬은 경도(gradient) 기반최적화 기법을 통해 데이타의 유사-가능도를 최대화하는 해를 찾음으로써 구해진다. 여러 실험을 통하여 제안 알고리듬이 몇 가지 특정 상황에서 기존의 분리 알고리듬들에 비해 우수한 성능을 보임을 확인 할 수 있다.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제13권3호
• /
• pp.186-199
• /
• 2013

We pose pattern classification as a density estimation problem where we consider mixtures of generative models under partially labeled data setups. Unlike traditional approaches that estimate density everywhere in data space, we focus on the density along the decision boundary that can yield more discriminative models with superior classification performance. We extend our earlier work on the recursive estimation method for discriminative mixture models to semi-supervised learning setups where some of the data points lack class labels. Our model exploits the mixture structure in the functional gradient framework: it searches for the base mixture component model in a greedy fashion, maximizing the conditional class likelihoods for the labeled data and at the same time minimizing the uncertainty of class label prediction for unlabeled data points. The objective can be effectively imposed as individual mixture component learning on weighted data, hence our mixture learning typically becomes highly efficient for popular base generative models like Gaussians or hidden Markov models. Moreover, apart from the expectation-maximization algorithm, the proposed recursive estimation has several advantages including the lack of need for a pre-determined mixture order and robustness to the choice of initial parameters. We demonstrate the benefits of the proposed approach on a comprehensive set of evaluations consisting of diverse time-series classification problems in semi-supervised scenarios.

• 한국소음진동공학회논문집
• /
• 제15권5호
• /
• pp.595-603
• /
• 2005

In this work, the multiple dynamic absorber( MDA ) is introduced to reduce several vibration modes of shadow mask simultaneously and its design method is developed from the theory of the simple dynamic absorber. When designing the dynamic absorber, there are three significant design parameters such as mass, damping ratio and tuning frequency. Therefore the sensitivity analysis for those parameters has been executed in order to find out the design criteria of multiple dynamic absorber using the finite element model of shadow mask. The multiple dynamic absorber(MDA) designed by the proposed method is tested theoretically and experimentally to estimate the efficiency of vibration reduction. From the results, it is verified that the method is feasible to apply the system having the multiple nitration modes and more efficient than the thin wire-type damper used commercially to reduce the vibration of shadow mask.

• 천문학회지
• /
• 제29권2호
• /
• pp.181-194
• /
• 1996

We present a study of the metallicity of the old open cluster NGC 1245 , based on the Washington CCD photometry obtained using the 0.6 m telescope at the Sobaeksan Observatory, Korea. NGC 1245 has been known to be a unique cluster among the known open clusters in the sense that the previous metallicity estimates for this cluster are much larger $(by\;\sigma)$ than the value expected from the radial metallicity gradient of the old open clusters in Our galaxy. We have estimated the metallicity of the cluster red giants using the four color-color diagrams, obtaining a value for the mean metallicity of $[Fe/H] = -0.04\pm0.05$ dex. The total error including the error of the metallicity calibration, 0.15 dex, is 0.16 dex. The metallicity estimate of NGC 1245 we have obtained in this study is smaller than previous estimates, and is consistent with the radial metallicity gradient of the old open clusters, showing that the mean metallicity of NGC 1245 is not abnormally high. The reddening, distance, and age of the cluster have also been derived using the isochrones based on the convective overshooting models: the reddening $E(B-V) = 0.28\pm0.03$; the distance $d = 2.5\pm0.2 kpc$ (the corresponding galactocentric distance is RGC = 10.7 kpc, and the distance from the galactic plane is z = -0.4 kpc); and the age $t = 1.1\pm0.1 Gyrs$.

• 한국컴퓨터정보학회논문지
• /
• 제20권12호
• /
• pp.67-74
• /
• 2015

The heat conduction equation, a type of a Poisson equation which can be applied in various areas of engineering is calculating its value with the iteration method in general. The equation which had difference discretization of the heat conduction equation is the simultaneous equation, and each line has the characteristic of expressing in sparse matrix of the equivalent number of none-zero elements with neighboring grids. In this paper, we propose a data structure for sparse matrix that can calculate the value faster with less memory use calculate the heat conduction equation. To verify whether the proposed data structure efficiently calculates the value compared to the other sparse matrix representations, we apply the representative iteration method, CG (Conjugate Gradient), and presents experiment results of time consumed to get values, calculation time of each step and relevant time consumption ratio, and memory usage amount. The results of this experiment could be used to estimate main elements of calculating the value of the general heat conduction equation, such as time consumed, the memory usage amount.

• 한국표면공학회지
• /
• 제49권6호
• /
• pp.498-506
• /
• 2016

Electrochemical measurement using a LSCF6428 electrode was performed to estimate the oxygen potential gradient in the electrode layer and a long time stability test was performed by applied potential to learn the overpotential effect on the LSCF6428 electrode. By fitting the observed impedance spectra, it was obtained that the amount of faradic current decreased with distance from cathode/electrolyte interface. Oxygen potential gradient was estimated to occur within 1 um region from the cathode/electrolyte interface at an oxygen partial pressure of 10-1 bar. The segregation of cation rich phases in the LSCF6428 electrode suggests that kinetic decomposition took place. However, impedance response after applying the potential showed no changes in the electrode compared with before applying potential. The obtained results suggest that segregation of a secondary phase in a LSCF6428 cathode is not related to performance degradation for solid oxide fuel cells (SOFCs).

• 한국철도학회:학술대회논문집
• /
• 한국철도학회 2000년도 춘계학술대회 논문집
• /
• pp.439-446
• /
• 2000

본 연구에서는 절점당 7자유도(뒤틀림 자유도 포함)를 갖는 보요소를 개발하여, 와그너 효과(Wagner Effect) 및 하중고 효과(Load Height Effect)가 일축 대칭 I 형보의 횡좌굴 강도에 미치는 영향을 파악하였다. 하중의 종류는 단면내 다양한 높이에 작용하는 횡방향 하중과 선형 모멘트 구배하중을 고려하였으며, 이들 하중에 의한 비지지 길이내 단일곡률의 휨과 역의 곡률의 휨이 생길때의 좌굴해석을 수행하였다. 현행 LRFD $C_{b}$ 계수의 일축 대칭 I 형 보에의 적용성을 검토하였으며, 하중고 효과(Load height effect) 및 비지지 길이내 역의 곡률(Reverse curvature bending) 발생시에 생기는 문제점들을 고찰해 보고, 해결방안을 제시하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제11권8호
• /
• pp.3965-3983
• /
• 2017

We propose a novel eye tracking method that can estimate 3D world coordinates using an infrared (IR) stereo camera for indoor and outdoor environments. This method first detects dark evidences such as eyes, eyebrows and mouths by fast multi-level thresholding. Among these evidences, eye pair evidences are detected by evidential reasoning and geometrical rules. For robust accuracy, two classifiers based on multiple layer perceptron (MLP) using gradient local binary patterns (GLBPs) verify whether the detected evidences are real eye pairs or not. Finally, the 3D world coordinates of detected eyes are calculated by region-based stereo matching. Compared with other eye detection methods, the proposed method can detect the eyes of people wearing sunglasses due to the use of the IR spectrum. Especially, when people are in dark environments such as driving at nighttime, driving in an indoor carpark, or passing through a tunnel, human eyes can be robustly detected because we use active IR illuminators. In the experimental results, it is shown that the proposed method can detect eye pairs with high performance in real-time under variable illumination conditions. Therefore, the proposed method can contribute to human-computer interactions (HCIs) and intelligent transportation systems (ITSs) applications such as gaze tracking, windshield head-up display and drowsiness detection.

• 한국산업정보학회논문지
• /
• 제13권1호
• /
• pp.57-67
• /
• 2008

본 논문에서는 광류를 이용한 적응 블록 정합 움직임 추정 방법을 제안하였다. 제안 방법에서는 먼저 각 화소의 시간 경사값과 공간 경사값을 미분필터를 통하여 계산한 후, 이 경사값들로부터 최소 자승 추정법을 이용하여 광류를 추정하여 탐색영역의 위치와 크기를 결정하였다. 특히 움직임 특성에 따라 탐색영역을 결전함으로써 움직임 추정 오차가 큰 영역인 크고 복잡한 움직임을 갖는 영상에 대해서 뛰어난 성능을 갖는다. 다양한 움직임 특성을 가지는 실험 영상들에 대한 기존의 방법과 제안한 방법의 움직임 추정 성능 평가를 위한 컴퓨터 모의실험을 통하여, 제안한 방법이 움직임이 크고 복잡한 영상에 대해서 기존의 방법에 비해 우수한 PSNR을 나타냄을 확인하였다.

• 한국컴퓨터정보학회논문지
• /
• 제17권2호
• /
• pp.59-67
• /
• 2012

본 논문에서는 실제 영상에 일반적으로 존재하는 지역성과 실제 영상에 존재하는 단순 볼록 곡면 특성과 단순 오목 곡면의 특성을 충실히 반영하도록 확대 영상의 보간 픽셀 값들을 추정하기 위하여 인접 픽셀 값과의 기울기 정보를 이용하는 효율적인 보간 기법을 제안하였다. 제안된 기법을 적용하여 확대한 영상의 화질 향상을 측정하기 위하여 PSNR(Peak Signal to Noise Ratio)을 사용하였다. 제안된 기법을 적용하여 확대한 다양한 영상들의 PSNR 값들이 기존의 보간 기법들을 적용하여 확대한 영상들의 PSNR 값보다 큰 것을 확인하였다.