• 제목/요약/키워드: Poisson Distribution

검색결과 586건 처리시간 0.026초

공유환경효과를 고려한 수리가능한 시스템의 수명과 고장회수의 결합모형 개발 (Joint Modeling of Death Times and Number of Failures for Repairable Systems using a Shared Frailty Model)

  • 박희창;이석훈
    • 품질경영학회지
    • /
    • 제26권4호
    • /
    • pp.111-123
    • /
    • 1998
  • We consider the problem of modeling count data where the observation period is determined by the life time of the system under study. We assume random effects or a frailty model to allow for a possible association between the death times and the counts. We assume that, given a random effect or a frailty, the death times follow a Weibull distribution with a hazard rate. For the counts, given a frailty, a Poisson process is assumed with the intensity depending on time. A gamma distribution is assumed for the frailty model. Maximum likelihood estimators of the model parameters are obtained. A model for the time to death and the number of failures system received is constructed and consequences of the model are examined.

  • PDF

유한요소법을 이용한 ZnO 바리스터의 전위분포 해석 (Analysis for potential distribution of ZnO varistor using Finite Element Method)

  • 이수길;김도영;장경욱;이준옹
    • 대한전기학회:학술대회논문집
    • /
    • 대한전기학회 1992년도 하계학술대회 논문집 B
    • /
    • pp.733-736
    • /
    • 1992
  • In this paper, Finite Element Method was used for the analysis of Potential Distribution of ZnO varistor and visualizing the characteristics of conduction mechanism. The results can be obtained by 2-dimensional element division and numerical method for Poisson's equation.

  • PDF

Network 최적 설계를 위한 네트워크 트래픽의 self-similar 특성 분석에 관한 연구 (A study about analysis of self-similar characteristics for the optimized design networks)

  • 이동철;김창호;황인수;김동일
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국해양정보통신학회 2000년도 추계종합학술대회
    • /
    • pp.267-271
    • /
    • 2000
  • 최근 인터넷 사용의 급증은 전체적인 망 이용율의 증가를 야기시켜 트래픽의 증가 원인이 된다. 이러한 트래픽 분석을 통해 통계적인 특성을 갖는 장치의 설계와 배치가 요구된다. 따라서, 이러한 인터넷 트래픽의 자기유사성을 분석하고, Simulation 과정을 통해 최적화된 설계요소를 찾아서 실제 네트워크의 성능향상을 연구하고자 한다.

  • PDF

Bayesian Inferences for Software Reliability Models Based on Beta-Mixture Mean Value Functions

  • Nam, Seung-Min;Kim, Ki-Woong;Cho, Sin-Sup;Yeo, In-Kwon
    • 응용통계연구
    • /
    • 제21권5호
    • /
    • pp.835-843
    • /
    • 2008
  • In this paper, we investigate a Bayesian inference for software reliability models based on mean value functions which take the form of the mixture of beta distribution functions. The posterior simulation via the Markov chain Monte Carlo approach is used to produce estimates of posterior properties. Its applicability is illustrated with two real data sets. We compute the predictive distribution and the marginal likelihood of various models to compare the performance of them. The model comparison results show that the model based on the beta-mixture performs better than other models.

Network에서 트래픽의 self-similar 특성 분석 (Analysis of self-similar characteristics in the networks)

  • 황인수;이동철;박기식;최삼길;김동일
    • 한국정보통신학회:학술대회논문집
    • /
    • 한국해양정보통신학회 2000년도 춘계종합학술대회
    • /
    • pp.263-267
    • /
    • 2000
  • 기존의 트래픽 분석은 포아손 분포나 마르코프 모델로 트래픽을 모델링하고, 패킷의 큐 도착을 지수분포로 가정하였으나, 지난 몇 년간의 연간결과 네트워크 트래픽은 비주기성 및 버스트 특성을 가심을 알게 되었다 이러한 트래픽의 특성은 자기유사 특성을 가진 새로운 트래픽 모델로 분석 하므로써, 네트워크의 확장성, QoS, 그리고 최적화된 설계를 가능하게 한다. 본 논문에서는 시뮬레이션 망을 통한 small-scale 에서의 혼재된 트래픽 특성과 실제 WAN의 도착 지연시간, 그리고 전체망의 이용률에 대한 각각의 자기유사특성을 분석 한다.

  • PDF

멀티미디어 서비스를 제공하는 네트워크의 지연 특성과 처리율 분석 (Delay characteristics and Throughput analysis on Network offered Multi-media service)

  • 황인수;김동일
    • 한국정보통신학회논문지
    • /
    • 제4권2호
    • /
    • pp.289-295
    • /
    • 2000
  • 인터넷에서 제공되는 멀티미디어 데이터의 서비스 품질 및 트래픽 파라메타인 사용자 트래픽의 최대 발생률, 데이터 전송시간지연과 변동 허용치, 최대 버스트 길이의 자기유사 특성을 가진 트래픽 모델로 분석 하므로써, 네트워크의 확장성, Quality of Service 그리고 최적화된 설계를 유추하였으며 시뮬레이션 네트워크를 통한 트래픽 지연 특성과 처리율을 분석하였다.

  • PDF

Joint Modeling of Death Times and Counts Using a Random Effects Model

  • Park, Hee-Chang;Klein, John P.
    • Journal of the Korean Data and Information Science Society
    • /
    • 제16권4호
    • /
    • pp.1017-1026
    • /
    • 2005
  • We consider the problem of modeling count data where the observation period is determined by the survival time of the individual under study. We assume random effects or frailty model to allow for a possible association between the death times and the counts. We assume that, given a random effect, the death times follow a Weibull distribution with a rate that depends on some covariates. For the counts, given the random effect, a Poisson process is assumed with the intensity depending on time and the covariates. A gamma model is assumed for the random effect. Maximum likelihood estimators of the model parameters are obtained. The model is applied to data set of patients with breast cancer who received a bone marrow transplant. A model for the time to death and the number of supportive transfusions a patient received is constructed and consequences of the model are examined.

  • PDF

Electromagnetic Behavior of High -$T_c$ Superconductors underthequenchstate -

  • 정동철;최효상;황종선;윤기웅;한병성
    • Progress in Superconductivity
    • /
    • 제3권2호
    • /
    • pp.183-187
    • /
    • 2002
  • In this paper we analyzed the electromagnetic behavior of high $-T_{c}$ superconductor under the quench state using finite element method. Poisson equation was used in finite element analysis as a governing equation and was solved using algebra equation using Gallerkin method. We first investigate d the electromagnetic behavior of U-type superconductor. Finally we applied our analysis techniques to 5.5 kVA meander-line superconducting fault current limiters (SFCL) which are currently developed by many power-system researcher in the world. Meshes of 14,600 elements were used in analysis of this SFCL. Analysis results show that the distribution of current density was concentrated to inner curvature in meander-line type-superconductors and maximum current density 14.61 $A/\m^2$ and also maximum Joule heat was 6,420 W/㎥. We concluded that this meander line-type SFCL was not pertinet fur uniform electromagnetic field distribution.n.

  • PDF

Bayesian Multiple Change-Point Estimation and Segmentation

  • Kim, Jaehee;Cheon, Sooyoung
    • Communications for Statistical Applications and Methods
    • /
    • 제20권6호
    • /
    • pp.439-454
    • /
    • 2013
  • This study presents a Bayesian multiple change-point detection approach to segment and classify the observations that no longer come from an initial population after a certain time. Inferences are based on the multiple change-points in a sequence of random variables where the probability distribution changes. Bayesian multiple change-point estimation is classifies each observation into a segment. We use a truncated Poisson distribution for the number of change-points and conjugate prior for the exponential family distributions. The Bayesian method can lead the unsupervised classification of discrete, continuous variables and multivariate vectors based on latent class models; therefore, the solution for change-points corresponds to the stochastic partitions of observed data. We demonstrate segmentation with real data.

Numerical Modeling of an Inductively Coupled Plasma Sputter Sublimation Deposition System

  • Joo, Junghoon
    • Applied Science and Convergence Technology
    • /
    • 제23권4호
    • /
    • pp.179-186
    • /
    • 2014
  • Fluid model based numerical simulation was carried out for an inductively coupled plasma assisted sputter deposition system. Power absorption, electron temperature and density distribution was modeled with drift diffusion approximation. Effect of an electrically conducting substrate was analyzed and showed confined plasma below the substrate. Part of the plasma was leaked around the substrate edge. Comparison between the quasi-neutrality based compact model and Poisson equation resolved model showed more broadened profile in inductively coupled plasma power absorption than quasi-neutrality case, but very similar Ar ion number density profile. Electric potential was calculated to be in the range of 50 V between a Cr rod source and a conductive substrate. A new model including Cr sputtering by Ar+was developed and used in simulating Cr deposition process. Cr was modeled to be ionized by direct electron impact and showed narrower distribution than Ar ions.