• 충청수학회지
• /
• 제5권1호
• /
• pp.23-34
• /
• 1992

This is an extension of results of Wiener's nonlinear noise theory from noises generated by the Wiener process to noises generated by processes with stationary Gaussian increments. In particular, using Nisio's Approach, we show that every measurable ergodic noise can be approximated in law by Gaussian process-presentable noise.

• Korean Journal of Mathematics
• /
• 제22권1호
• /
• pp.71-84
• /
• 2014

By using the multidimensional normal approximation of functionals of Gaussian fields, we prove that functionals of Gaussian fields, as functions of t, converge weakly to a standard Brownian motion. As an application, we consider the convergence of the Stratonovich-type Riemann sums, as a function of t, of fractional Brownian motion with Hurst parameter H = 1/4.

• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2007년도 가을 학술발표논문집 Vol.34 No.2 (C)
• /
• pp.485-489
• /
• 2007

Gaussian process classifiers (GPCs) are fully statistical kernel classification models which have a latent function with Gaussian process prior Recently, EP approximation method has been proposed to infer the posterior over the latent function. It can have a special hyperparameter which can treat outliers potentially. In this paper, we propose the outlier robust algorithm which alternates EP and the hyperparameter updating until convergence. We also show its usefulness with the simulation results.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제2권2호
• /
• pp.81-95
• /
• 1998

The superconvergence of the Sloan iterate obtained from a Galerkin method for the approximate solution of the singular integral equation based on the use of two sets of orthogonal polynomials is investigated. The discrete Sloan iterate using Gaussian quadrature to evaluate the integrals in the equation becomes the Nystr$\ddot{o}$m approximation obtained by the same rules. Consequently, it is impossible to expect the faster convergence of the Sloan iterate than the discrete Galerkin approximation in practice.

• Korean Journal of Mathematics
• /
• 제23권1호
• /
• pp.1-10
• /
• 2015

This paper concerns the rate of convergence in the multidimensional normal approximation of functional of Gaussian fields. The aim of the present work is to derive explicit upper bounds of the Kolmogorov distance for the rate of convergence instead of Wasserstein distance studied by Nourdin et al. [Ann. Inst. H. Poincar$\acute{e}$(B) Probab.Statist. 46(1) (2010) 45-98].

• Journal of the Korean Statistical Society
• /
• 제36권4호
• /
• pp.479-488
• /
• 2007

The elliptic random field is an extension to the Gaussian random field. We proved a theorem which characterizes the elliptic random field. We proposed a heuristic approach to derive an approximation to the distribution of the size of one connected component of its excursion set above a high threshold. We used this approximation to approximate the distribution of the largest cluster size. We used simulation to compare the approximation with the exact distribution.

• Water Engineering Research
• /
• 제2권2호
• /
• pp.89-101
• /
• 2001

The theoretical treatments on jets, in which the flow is issuing into a stagnant medium, have been based on Prandtl's mixing theory. In this study, using Prandtl's mixing length hypothesis, a theoretical relationship for the velocity profile of a single round jet is derived. Furthermore, Gaussian expression is used to approximate the theoretical relationship, in which the Gaussian coefficient is assumed to be decreasing exponentially as the flow goes far from the orifice. Two data sets for a single round jet performed by tow different techniques of measurement are used to verify the suggested relationships. The theoretical and Gaussian distribution give close results in spite of the difference in approach. The observed mean velocity distributions are in good agreements with the suggested theoretical and Gaussian distributions.

• 한국통신학회논문지
• /
• 제31권9C호
• /
• pp.825-830
• /
• 2006

Capacity-approaching codes using iterative decoding have been the main subject of research activities during past decade. Especially, LDPC codes show the best asymptotic performance and density evolution has been used as a powerful technique to analyze and design good LDPC codes. In this paper, we apply density evolution with a Gaussian approximation to the concatenated zigzag (CZZ) codes by considering both flooding and two-way schedulings. Based on this density evolution analysis, the threshold values are computed for various CZZ codes and the optimal structure of CZZ codes for various code rates are obtained. Also, simulation results are provided to conform the analytical results.

• 전자공학회논문지A
• /
• 제30A권8호
• /
• pp.11-18
• /
• 1993

In a spread spectrum system, the bandwidth and period of spreading code is wide and long, respectively. So it is necessary to make the code acquisition time as short as possible. In particular, serial search code acquisition system requires optimum dwell time for fast acquisition. In this paper, code acquisition time is calculated by varying dwell time. Among them, minimum code acquisition time is chosen and then optimum dwell time can be obtained. Detection probability (P$_{D}$) and false alarm probability (P$_{FA}$) can be obtained by integrating chi-square pdf by numerical analysis. The results are compared with that of gaussian approximation method and then it is concluded gaussian approximation method is not suitable for obtaining optimum dwell time. Computer simulation supports theoretical results.

• 한국정보통신학회논문지
• /
• 제9권8호
• /
• pp.1656-1662
• /
• 2005

본 논문에서는 기존의 UWB 통신 시스템에서 많이 사용되는 펄스 위치 변조와 펄스 진폭 변조를 사용하여 하나의 펄스로서 여러 비트의 데이터를 전송할 수 있는 M-PPAM(M-ary Pulse Position and Amplitude Modulation) 구조를 소개하였다. 이 방법은 동일한 데이터 전송율을 얻기 위하여 보다 긴 펄스 반복 주기를 사용할 수 있는 장점이 있다. 따라서 실내 환경에서와 같은 다중 경로 페이딩이 심한 경우 대용량의 데이터를 전송하기에 적합하리라고 생각한다. 이때, 다중 사용자를 수용하기 위하여 DS(Direct Sequence) 기법을 사용하였다. 이와 같이 고려된 M-PPAM DS-UWB 수신기의 성능을 가우시안 채널 조건하에서 다중 사용자 간섭을 포함하여 표준 가우시안 근사(Standard Gaussian Approximation)를 사용하여 모델링 하였다. 또한, 수신기의 성능을 시뮬레이션을 통하여 확인하였다.