• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2008.04a
• /
• pp.43-45
• /
• 2008

위 인식은 이동 로봇의 자율 주행을 위한 필수 기능이다. 위치 추정을 위해서 Bayes Filter를 기본으로한 칼만 필터 방법들이 주로 제안되어졌고 최근에는 Particle Filter 방법이 제안되어져 사용되고 있다. 본 연구에서는 영역센서를 장착한 이동 로봇의 위치 추정을 위해 레이저 영역 센서를 이용하는 Particle Filter 방법을 구현하였다. Particle Filter방법은 Kalman Filter 방법에 비해서 구현이 간단하면서도 Kidnapping 문제에도 대응할 수 있는 장점이 있다. 본 연구를 통하여 위치 추정의 수렴도, 정확도, 그리고 Kidnapping 발생시의 위치 추정 성능등을 분석하여, 기존 방법의 성능을 개선하는 방법을 제안한다.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.94-99
• /
• 2015

With the recent machine learning paradigm of using nonparametric Bayesian statistics and statistical inference based on random sampling, the Dirichlet distribution finds many uses in a variety of graphical models. It is a multivariate generalization of the gamma distribution and is defined on a continuous (K-1)-simplex. This paper presents a sampling method for a Dirichlet distribution for the problem of dividing an integer X into a sequence of K integers which sum to X. The target samples in our problem are all positive integer vectors when multiplied by a given X. They must be sampled from the correspondingly gridded simplex. In this paper we develop a Markov Chain Monte Carlo (MCMC) proposal distribution for the neighborhood grid points on the simplex and then present the complete algorithm based on the Metropolis-Hastings algorithm. The proposed algorithm can be used for the Markov model, HMM, and Semi-Markov model for accurate state-duration modeling. It can also be used for the Gamma-Dirichlet HMM to model q the global-local duration distributions.

• Proceedings of the Korea Society for Industrial Systems Conference
• /
• 2009.05a
• /
• pp.196-199
• /
• 2009

높아지는 Graphic Processing Unit (GPU)의 연산 성능과 GPU에서의 범용 프로그래밍을 위한 개발 환경의 개발, 보급으로 인해 GPU를 일반연산에 활용하는 연구가 활발히 진행되고 있다. 이와같이 일반 연산에 활용되고 있는 GPU로 nVidia Tesla와 AMD/ATI의 FireStream 들이 있다. 특수목적 연산 장치인 GPU를 일반 연산을 위해 프로그래밍하기 위해서는 그에 맞는 프로그램 개발 환경이 필요한데 nVidia에서 개발한 CUDA (Compute Unified Device Architecture) 환경은 자사의 GPU 프로그램 개발을 위해 제공되는 개발 환경이다. CUDA 개발 환경은 nVidia GPU 프로그래밍 뿐만 아니라 차세대 이종 병렬 프로그램 개발 환경의 공개 표준으로 논의되고 있는 OpenCL (Open Computing Language) 와 유사한 특징을 보일 것으로 예상되기 때문에 그 중요성은 특정 GPU 에만 국한되지 않는다. 본 논문에서는 경로 적분 몬테 카를로 (Path Integral Monte Carlo) 방법을 CUDA 개발 환경을 사용하여 nVidia GPU 상에서 병렬화한 결과를 제시하였다.

• The Journal of the Korea Contents Association
• /
• v.21 no.11
• /
• pp.77-86
• /
• 2021

A method of constructing a war simulation based on Bayesian Inference was proposed as a method of constructing heterogeneous historical war data obtained with a time difference into a single model. A method of applying a linear regression model can be considered as a method of predicting future battles by analyzing historical war results. However it is not appropriate for two heterogeneous types of historical data that reflect changes in the battlefield environment due to different times to be suitable as a single linear regression model and violation of the model's assumptions. To resolve these problems a Bayesian inference method was proposed to obtain a post-distribution by assuming the data from the previous era as a non-informative prior distribution and to infer the final posterior distribution by using it as a prior distribution to analyze the data obtained from the next era. Another advantage of the Bayesian inference method is that the results sampled by the Markov Chain Monte Carlo method can be used to infer posterior distribution or posterior predictive distribution reflecting uncertainty. In this way, it has the advantage of not only being able to utilize a variety of information rather than analyzing it with a classical linear regression model, but also continuing to update the model by reflecting additional data obtained in the future.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1A
• /
• pp.55-65
• /
• 2006

This paper presents the closing analysis of a symmetric steel cable-stayed bridge erected by a free cantilever method. Two independent structural systems are formed before the closing procedure of a bridge is performed, and thus the compatibility conditions for vertical displacement and rotational angle are not satisfied at the closing section without the application of proper sectional forces. Since, however, it is usually impossible to apply sectional forces at the closing section, the compatibility conditions should be satisfied by proper external forces that can be actually applicable to a bridge. Unstrained lengths of selected cables and the pull-up force of a derrick crane are adjusted to satisfy nonlinear compatibility conditions, which are solved iteratively by the Newton-Raphson method. Cable members are modeled by the elastic catenary cable elements, and towers and main girders are discretized by linear 3-D frame elements. The sensitivities of displacement with respect to the unstrained lengths of selected cables and the pull-up force of the derrick crane are evaluated by the direct differentiation of the equilibrium equation. A Monte-Carlo simulation approach is proposed to estimate expected construction errors for a given confidence level. The proposed method is applied to the second Jindo Grand Bridge to demonstrate its validity and effectiveness.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.193-196
• /
• 2005

This paper presents a Monte-Carlo based method to obtain a probability of interference among systems. We show an efficient algorithm to calculate not only in-band interference for a given emission mask, but out-of-band interference, which depends on the blocking performance of a victim receiver filter. Applying the proposed method to an arbitrary system, we show the simulation results by Matlab and compare them with those by a SEAMCAT software

• The Journal of Engineering Geology
• /
• v.2 no.2
• /
• pp.147-154
• /
• 1992

A computer simulation of earthquake sequence in the time and magnitude space was done using random number generation. The theory of the simulation are based on the two statistical models of earthquake events. Those models are Stationary Poisson Process for independent earthquakes and Branching Markov Process for aftershocks. The generated earthquake sequnces resemble the actual earthquake catalogs.

• Electrical & Electronic Materials
• /
• v.10 no.3
• /
• pp.268-273
• /
• 1997

In this paper the transient electron transport in GaAs bulk is simulated by using ensemble Monte Carlo method. To analyze the transient electron transport the 10000 electrons in the .GAMMA. valley are simulated simultaneously for 10 picoseconds. The electric field-velocity relation is obtained. The high impurity density reduces the negative differential resistance effect. The result of transient average velocity shows the electron velocity in the transient state is faster than that in the steady state. This transient velocity overshoot is caused by the intervalley scattering mechanism. And we confirmed the fact that the energy relaxation time is longer than the momentum relaxation time.

• Journal of Korean Port Research
• /
• v.13 no.2
• /
• pp.427-436
• /
• 1999

Simulation model for diffusion of oil spill is developed. The model can perform real time simulation in the case of oil spill accident in the ocean. The model consists of three dimensional ocean circulation model and model for diffusion of oil spill. Real time flow fields which are used in the calculation of advection of oil spill are obtained in the three dimensional ocean circulation model. The model for diffusion of oil spill includes the evaporation dissolution emulsification and downward diffusion. For the verification of the model it is applied to the oil spill from the accident of Sea Prince. The results shows good agreement.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2009.11a
• /
• pp.273-274
• /
• 2009

본 논문은 완전히 잘못된 데이터가 포함된 회귀(regression) 문제에 사용되는 가우스-균일 혼합확률분포의 두 개의 매개변수 추정에 관하여 고찰한다. 논문에서는 기대값 최대화(Expectation Maximization)와 최우도추정(Maximum Likelihood Estimation)을 이용한 매개변수 추정 방법을 비교한다. 두 기법은 최적화 문제로 기술할 수 있고, 논문에서는 두 기법에서 사용하는 매개변수에 대한 적합도 척도의 개형을 도시하고 비교한다. 몬테-카를로(Monte Carlo) 접근을 통한 두 기법이 추정한 매개변수의 분포를 살펴본다.