通过基于重要性采样和蒙特卡罗模拟方法得到一高斯分布来近似未知状态变量的后验分布。
A single Gaussian distribution is obtained to approximate the posterior distribution of state parameters based on sequential importance sampling and Monte Carlo methods.
结果表明，与普通随机采样相比，拉丁超几何体采样能捕获更多的不确定性，特别是在蒙特卡罗模拟次数较少时。
Results showed that Latin Hypercube sampling can capture more variability in the sample space than simple random sampling especially when the number of simulations is small.
讨论了贯序蒙特卡罗方法在无线传感器网络节点定位算法中的实现，并针对再采样阶段的样本缺失现象，对基本算法进行了改进。
Discuss the Sequential Monte Carlo localization method for wireless sensor networks scheme and modify the basic algorithm to overcome the sample degeneracy problem in resampling stage.
应用推荐