首页> 外国专利> Method and system for utilizing Markov chain Monte Carlo simulations

Method and system for utilizing Markov chain Monte Carlo simulations

机译:利用马尔可夫链蒙特卡洛模拟的方法和系统

摘要

Systems and methods for determining a probability of changing from one state to another in a stochastic entity, comprising: determining the compact component matrix utilizing characteristic information of the stochastic entity; determining the compact composite component matrix by taking a Kroneker product of the compact component matrix and an identity matrix; determining and placing all current states for the stochastic entity into a state space matrix; determining a Q matrix and/or a transition rate matrix using the compact composite component matrix and basic conditions or variables of the problem domain and/or a compact transition rate matrix; and performing Markov chain Monte Carlo (MCMC) simulation using information from the state space matrix and information from the transition rate matrix to determine the probability of changing from one state to another state in the stochastic entity.
机译:用于确定随机实体中从一种状态改变为另一种状态的概率的系统和方法,包括:利用随机实体的特征信息确定紧凑分量矩阵;通过取紧凑成分矩阵和单位矩阵的克朗克乘积确定紧凑复合成分矩阵;确定随机实体的所有当前状态并将其置于状态空间矩阵中;使用紧凑的复合分量矩阵和问题域的基本条件或变量和/或紧凑的转换率矩阵来确定Q矩阵和/或转换率矩阵;然后使用状态空间矩阵中的信息和转换率矩阵中的信息执行马尔可夫链蒙特卡洛(MCMC)仿真,以确定随机实体中从一种状态转换为另一种状态的概率。

著录项

相似文献

  • 专利
  • 外文文献
  • 中文文献
获取专利

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号