提出一种基于循环谱切片的通信辐射源个体识别方法.通过计算信号的循环谱密度矩阵,将循环谱密度切片作为初始高维特征,再采用主成分分析方法对其进行降维处理得到指纹特征矢量,最后采取概率神经网络分类器实现辐射源的个体识别.通过对20部手持机的实验表明,使用该方法提取的特征矢量能够较好地反映信号的循环平稳特性,并且特征参数对噪声干扰不敏感,在较低信噪比条件下,系统仍具有较高的正确识别率,说明该方法确实能够较好地解决同型号、同批次、同工作参数通信辐射源的个体识别问题.%A method based on cyclic spectrum density slice for emitter identification is presented.The signal cyclic spectrum density matrix is calculated and its slice is used as the initial high-dimension feature.Then the principal component analysis method is used to descend the dimension and obtain the fingerprint feature vector.Finally,the emitter identification is realized by using the neural network classifier.The experimental results based on 20 interphones show that the feature vector extracted by the method can reflect the signal cyclostation characteristic and the feature parameter is insensitive to noise and interference.Under the condition of low signal-to-noise ratio (SNR),the system still has a high correct recognition rate.It shows that the method can deal with the individual identification of emitters with same model and same batch.
展开▼