盖尔圆定理和最小描述长度准则相结合的信源数目估计方法研究

发布时间：2018-08-27 16:50

【摘要】：针对盲源分离算法应用中的源数估计问题,提出了一种结合盖尔圆定理(Geschgorin Disk Estimator,GDE)和最小描述长度准则(Minimum Description Length,MDL)的GDE-MDL源数估计方法。GDE-MDL方法集合了盖尔圆定理适用于空间色噪声的优点和MDL准则一致性估计的优点。该方法通过对观测信号协方差矩阵进行酉变换来抑制噪声,可以提高似然函数的灵敏度和信源数目的估计精度,更好的处理低信噪比和空间色噪声条件下的源数估计问题。仿真结果表明,GDE-MDL方法稳定性较好,适应性强,在白噪声和空间色噪声的情况下均可以较好的实现信源数目的估计。
[Abstract]:Aiming at the problem of source number estimation in blind source separation algorithm, In this paper, a method of GDE-MDL source number estimation based on Gale circle theorem (Geschgorin Disk Estimator,GDE) and minimum description length criterion (Minimum Description Length,MDL) is proposed. The GDE-MDL method sets the advantages of Gale circle theorem for spatial color noise and MDL criterion for consistency estimation. This method can improve the sensitivity of the likelihood function and the estimation accuracy of the number of sources by unitary transformation of the observed signal covariance matrix. It can better deal with the problem of source number estimation under the condition of low signal-to-noise ratio and spatial color noise. The simulation results show that the GDE-MDL method has good stability and adaptability, and can be used to estimate the number of sources in the case of white noise and spatial color noise.
【作者单位】：电子信息系统复杂电磁环境效应国家重点实验室;
【分类号】：TN911.7

【相似文献】