论文部分内容阅读
为实现复杂多信号环境下的通信信号侦察,采用一种新的盲侦察技术,即运用盲源分离算法,在没有任何先验知识的情况下分离出源信号,然后对分离的各个信号进行后续处理。提出一种改进的基于峭度的盲分离算法,可以自适应地确定激活函数。将其应用在通信信号盲侦察中,可以实现对任意源信号进行盲分离,而不管它是超高斯还是亚高斯信号。选择超高斯和亚高斯混合通信信号进行了仿真实验,结果验证了该算法的有效性。
In order to realize the communication signal reconnaissance in complex multi-signal environment, a new blind reconnaissance technique is adopted, that is, the blind source separation algorithm is used to separate the source signal without any prior knowledge and then the subsequent signals deal with. This paper proposes an improved blind separation algorithm based on kurtosis, which can adaptively determine the activation function. Applying it to the blind detection of communication signals, blind separation of any source signal can be realized, whether it is a super-Gaussian or a sub-Gaussian signal. Simulation results show that the proposed algorithm is validated by choosing the mixed Gaussian and Gaussian signals.