摘要
针对目前大多盲源分离算法只适用于实信号,而在通信对抗中处理的一般都是通信复信号这一问题,推导了一种适用于通信复信号的盲源分离算法.该算法以Kullback-Leibler发散度作为信号之间独立性的测度准则.另外由于自然梯度比随机梯度性能更优,因此利用代价函数的自然梯度进行优化,根据白化后信号混合矩阵为正交矩阵的结论,对分离矩阵做正交性约束,推导出了算法的迭代公式.仿真结果表明,即使在有噪环境下,该算法也能够有效地分离出源信号.
Most of the blind source separation algorithms are only applicable to the real signals at present, but in communication reconnaissance, the processed signals often are complex. To solve this problem, a blind source separation algorithm for communication complex signals is deduced, which is obtained by considering the Kullback-leibler divergence as the measurement of signal's independence. On the other hand, the performance of the natural gradient is better than that of the stochastic gradient, so the natural gradient of the cost function is used to optimize the algorithm. At the same time, according to the conclusion that the signal's mixing matrix after whitening is orthogonal, we deduce the iterative algorithm by constraining the separating matrix to an orthogonal matrix. Simulation result shows that this algorithm can efficiently separate the source signals even if there is noise.
出处
《华中科技大学学报(自然科学版)》
EI
CAS
CSCD
北大核心
2007年第4期33-36,共4页
Journal of Huazhong University of Science and Technology(Natural Science Edition)
基金
国家自然科学基金资助项目(60672038)
关键词
通信侦察
盲源分离
复信号
communication reconnaissance
blind source separation
complex signal