多输入多输出盲解卷问题的最大熵解法

Multi-Input Multi-output (MIMO) Blind Deconvolution Via Maximum Entropy (ME) Method

本文研究的问题是从观察信号中分离出两个（或者更多个）输入信号，其中每一组信号分别通过不同的未知多输入多输出线性系统．本文证明了当输入信号是两两相互独立的独立同分布信号时可以分离出输入信号，并导出了基于最大熵的多输入多输出盲解卷新算法．这个算法不需要任何关于输入信号和混合滤波器的先验知识．

The problem discussed in this paper is to separate two (or more )input signals from observed signals which are generated by passing input signals through different unknown multi-input multi-output linear systems. It is proved that the input signals can be separated when they are independent identitically distributed (i.i.d) signals . A new algorithm for multi-input multi-output blind deconvolution via maximum entropy is presented which needs no information about the input signals and mixing filters.