一种信号源数目的盲估计方法

源数目估计在阵列信号处理,特别是盲处理技术中具有重要意义.本文通过分析信号空间的构成,给出了一种基于特征值估计的源数目盲估计方法.分析了算法在不同信号传递(瞬时混合和卷积混合)形式、不同信噪比下的估计精度.仿真研究了传感器数目对源数目估计的影响.结果表明,该算法具有较好的估计能力和可靠性.

A Blind Method for Estimating the Number of Signal Sources

Estimation of the number of signal sources is an important problem in array signal processing, especially in blind signal processing. An estimation method of the number of sources based on eigenvalue analysis is presented in this paper by principal component analysis (PCA) of the signal space. The estimation accuracy of the algorithm is analyzed with respective to different transmission forms of signals, i.e., instantaneous mixture and convolutive mixture, and different signal-noise-ratio. The effect on the estimation of the number of signals using different number of sensors is discussed. Simulation results show that the presented algorithm has good estimation ability and reliability.;