The Conjugate Unscented Transform — An approach to evaluate multi-dimensional expectation integrals
The Conjugate Unscented Transform — An approach to evaluate multi-dimensional expectation integrals
复制标题
共轭无味变换 - 一种评估多维期望积分的方法
DOI：
--
复制
发表时间：
2012
期刊：
影响因子：
--
通讯作者：
T. Singh
中科院分区：
文献类型：
--
作者：
Nagavenkat Adurthi;P. Singla;T. Singh
通过满足高阶矩方程，将Unscented变换推广到一般N维空间中求期望积分。定义了新的Sigma点集，以满足高达八阶的力矩方程。该方法可以作为高斯求积规则的一种有效替代方法，大大减少了函数求值的次数，但精度没有任何损失。数值模拟结果表明了该方法在计算高维期望积分时的有效性，同时大大减少了函数求值次数。
This paper presents an extension to the unscented transformation to evaluate expectation integrals in general N-dimensional space by satisfying higher order moment equations. New sets of sigma points are defined to satisfy moment equations up to eighth order. The proposed methodology can be used as an efficient alternative to Gaussian quadrature rule with significantly reduced number of function evaluations but without any loss in accuracy. Numerical simulation results illustrates the effectiveness of the proposed methodology in computing high dimension expectation integrals with significantly reduced number of function evaluations.