垂直分层空时码的MAP检测器及其神经网络实现

MAP Based Detection Algorithm for V-BLAST System

该文基于最大后验概率准则,给出了垂直分层空时码的最佳检测箅法.算法对接收到的符号矢量的符号分量进行逐个地判决以使误符号率最小.同时还详细说明了径向基函数神经网络可以完全等价于最大后验概率检测算法,由于神经网络的硬件可实现性,本文提出的算法是可能在实际中应用的.

This paper proposes the optimum detection algorithm for a multiple antenna system based on the Maximum A Posteriori (MAP) criterion. It makes symbol-by-symbol decisions so that the probability of a symbol error is minimized. It also shows that the radial basis function neural network has an identical structure to the proposed MAP algorithm and, therefore, can be employed in a multiple antennas system.