• ETRI Journal
• /
• 제33권5호
• /
• pp.814-817
• /
• 2011

In this letter, the distributions of direct current (DC) coefficients for P-frames in H.264/AVC are analyzed, and the distortion model of the Gaussian source under the quantization of the dead-zone plus-uniform threshold quantization with uniform reconstruction quantizer is derived. Experimental results show that the DC coefficients of P-frames are best approximated by the Laplacian distribution and the Gaussian distribution at small quantization step sizes and at large quantization step sizes, respectively.

• 한국컴퓨터정보학회논문지
• /
• 제15권2호
• /
• pp.127-134
• /
• 2010

연속 어휘 인식 확률 분포의 공유 방법에서는 사용될 모델 파라미터들의 초기 추정치를 생성하기 위한 각 문맥들에 대한 음소 데이터가 반드시 필요하지만 이들 음소 데이터에 대한 모델을 구성할 수 없는 단점으로 가우시안 모델의 정확성을 확보하지 못한다는 단점이 있다. 이를 개선하기 위하여 확률 분포의 혼합 가우시안 모델을 최적화하고, 음소 단위로 데이터를 탐색을 지원하는 형상 형성 시스템을 제안한다. 본 논문의 형상 형성 시스템은 확장 facet 분류를 이용하여 사용자에게 음소 단위의 형상 형성 정보를 제공하므로 가우시안 모델의 정확성을 제공한다. 본 논문에서 제안한 시스템을 적용한 결과 시스템 성능에서 어휘 종속 인식률은 98.31%, 어휘 독립 인식률은 97.63%의 인식률을 나타내었다.

• International Journal of Naval Architecture and Ocean Engineering
• /
• 제12권1호
• /
• pp.755-767
• /
• 2020

A significant development has been made on a new fatigue damage model applicable to Gaussian wide band stress response spectra using numerical approximation methods such as data processing, time simulation, and regression analysis. So far, most of the alternative approximate models provide slightly underestimated or overestimated damage results compared with the rain-flow counting distribution. A more reliable approximate model that can minimize the damage differences between exact and approximate solutions is required for the practical design of ships and offshore structures. The present paper provides a detailed description of the development process of a new fatigue damage model. Based on the principle of the Gaussian wide band model, this study aims to develop the best approximate fatigue damage model. To obtain highly accurate damage distributions, this study deals with some prominent research findings, i.e., the moment of rain-flow range distribution MRR(n), the special bandwidth parameter μk, the empirical closed form model consisting of four probability density functions, and the correction factor QC. Sequential prerequisite data processes, such as creation of various stress spectra, extraction of stress time history, and the rain-flow counting stress process, are conducted so that these research findings provide much better results. Through comparison studies, the proposed model shows more reliable and accurate damage distributions, very close to those of the rain-flow counting solution. Several significant achievements and findings obtained from this study are suggested. Further work is needed to apply the new developed model to crack growth prediction under a random stress process in view of the engineering critical assessment of offshore structures. The present developed formulation and procedure also need to be extended to non-Gaussian wide band processes.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권4호
• /
• pp.202-208
• /
• 2015

In this study, we propose a new inference algorithm for a multiclass Gaussian process classification model using a variational EM framework and the Laplace approximation (LA) technique. This is performed in two steps, called expectation and maximization. First, in the expectation step (E-step), using Bayes' theorem and the LA technique, we derive the approximate posterior distribution of the latent function, indicating the possibility that each observation belongs to a certain class in the Gaussian process classification model. In the maximization step, we compute the maximum likelihood estimators for hyper-parameters of a covariance matrix necessary to define the prior distribution of the latent function by using the posterior distribution derived in the E-step. These steps iteratively repeat until a convergence condition is satisfied. Moreover, we conducted the experiments by using synthetic data and Iris data in order to verify the performance of the proposed algorithm. Experimental results reveal that the proposed algorithm shows good performance on these datasets.

• KIEE International Transaction on Electrical Machinery and Energy Conversion Systems
• /
• 제5B권3호
• /
• pp.258-261
• /
• 2005

The Preisach model needs a distribution function or Everett function to simulate the hysteresis phenomena. To obtain these functions, many experimental data obtained from the first order transition curves are usually required. In this paper, a simple procedure to determine the Preisach density function using the Gaussian distribution function and genetic algorithm is proposed. The Preisach density function for the interaction field axis is known to have Gaussian distribution. To determine the density and distribution, genetic algorithm is adopted to decide the Gaussian parameters. With this method, just basic data like the initial magnetization curve or saturation curves are enough to get the agreeable density function. The results are compared with experimental data and we got good agreements comparing the simulation results with the experiment ones.

• 대한음성학회:학술대회논문집
• /
• 대한음성학회 2005년도 춘계 학술대회 발표논문집
• /
• pp.87-90
• /
• 2005

Today's state-of the-art speech recognition systems typically use continuous distribution hidden Markov models with the mixtures of Gaussian distributions. To obtain higher recognition accuracy, the hidden Markov models typically require huge number of Gaussian distributions. Such speech recognition systems have problems that they require too much memory to run, and are too slow for large applications. Many approaches are proposed for the design of compact acoustic models. One of those models is subspace distribution clustering hidden Markov model. Subspace distribution clustering hidden Markov model can represent original full-space distributions as some combinations of a small number of subspace distribution codebooks. Therefore, how to make the codebook is an important issue in this approach. In this paper, we report some experimental results on various quantization methods to make more accurate models.

• Wind and Structures
• /
• 제31권6호
• /
• pp.549-560
• /
• 2020

Methods for stochastic simulation of non-Gaussian wind pressure have increasingly addressed the efficiency and accuracy contents to offer an accurate description of the extreme value estimation of the long-span and high-rise structures. This paper presents a linear prediction and z-transform (LPZ) based Cumulative distribution function (CDF) mapping algorithm for the simulation of multivariate non-Gaussian fluctuating wind pressure. The new algorithm generates realizations of non-Gaussian with prescribed marginal probability distribution function (PDF) and prescribed spectral density function (PSD). The inverse linear prediction and z-transform function (ILPZ) is deduced. LPZ is improved and applied to non-Gaussian wind pressure simulation for the first time. The new algorithm is demonstrated to be efficient, flexible, and more accurate in comparison with the FFT-based method and Hermite polynomial model method in two examples for transverse softening and longitudinal hardening non-Gaussian wind pressures.

• Structural Engineering and Mechanics
• /
• 제17권1호
• /
• pp.29-50
• /
• 2004

A total life model was developed to assess the service life of aging aircraft. The primary focus of this paper is the development of crack growth life projection using the response surface method. Crack growth life projection is a necessary component of the total life model. The study showed that the number of load cycles N needed for a crack to propagate to a specified size can be linearly related to the geometric parameter, material, and stress level of the component considered when all the variables are transformed to logarithmic values. By the Central Limit theorem, the ln N was approximated by Gaussian distribution. This Gaussian model compared well with the histograms of the number of load cycles generated from simulated crack growth curves. The outcome of this study will aid engineers in designing their crack growth experiments to develop the stochastic crack growth models for service life assessments.

• Journal of the Optical Society of Korea
• /
• 제19권4호
• /
• pp.363-370
• /
• 2015

The current waveform model of a laser altimeter is based on a Gaussian laser beam of fundamental mode, while the flattened Gaussian beam has many advantages such as nearly constant energy distribution on the center of the cross-section. Following the theory of the flattened Gaussian beam and the waveform theory of the laser altimeter, some of the primary parameters of the received waveform were derived, and a laser altimetry waveform simulator and waveform processing software were programmed and improved under the circumstance of a flattened Gaussian beam. The result showed that the bias between theoretical and simulated waveforms was less than 3% for every order mode, the waveform width and range error would increase as target slope or order number rose. Under higher order mode, the shapes of the received waveforms were no longer Gaussian, and could be fitted more precisely as a generalized Gaussian function with power bigger than 2. The flattened beam got much better performance for a multi-surface target, especially when the small surface is far from the center of the laser footprint. This article provides the waveform theoretical basis for the use of a flattened Gaussian beam in a laser altimeter.

• 제어로봇시스템학회논문지
• /
• 제15권9호
• /
• pp.939-945
• /
• 2009

In this paper, we proposed a method which corresponds people under the structured spaces with multiple cameras. The correspondence takes an important role for using multiple camera system. For solving this correspondence, the proposed method consists of three main steps. Firstly, moving objects are detected by background subtraction using a multiple background model. The temporal difference is simultaneously used to reduce a noise in the temporal change. When more than two people are detected, those detected regions are divided into each label to represent an individual person. Secondly, the detected region is segmented as features for correspondence by a criterion with the color distribution and context information of human body. The segmented region is represented as a set of blobs. Each blob is described as Gaussian probability distribution, i.e., a person model is generated from the blobs as a Gaussian Mixture Model (GMM). Finally, a GMM of each person from a camera is matched with the model of other people from different cameras by maximum likelihood. From those results, we identify a same person in different view. The experiment was performed according to three scenarios and verified the performance in qualitative and quantitative results.