基于时频分析的自适应PCA辐射源调制识别

Research on emitter modulation recognition of the adaptive PCA based on time-frequency analysis

针对复杂环境非合作通信模式下,识别调制方式运算复杂度高、识别率低的问题,提出一种基于时频分析的自适应特征提取识别算法。该算法结合二阶四阶矩估计法,利用信噪比自适应选取主成分分析特征,通过支持向量机分类器对辐射源调制方式进行识别。仿真结果表明,所提算法识别效果优于其他特征提取识别算法。在信噪比为0 dB时,识别率达到98%以上,较Hu矩和伪Zernike矩有12 dB左右的提升。该算法识别率高、运算量低,有较好的工程应用价值。

Aiming at the problem existing in the modulation recognition such as high computational complexity and lowrecognition rate in the non-cooperative communication mode of a complex environment, this paper proposes an adaptivefeature extraction and recognition algorithm based on time-frequency analysis. The algorithm, which combined with thesecond-order and fourth-order moment estimation method, uses the signal-to-noise ratio to select the principalcomponent analysis feature adaptively, and identifies the emitter modulation method by the support vector classifier.The simulation results show that the proposed algorithm is superior to other feature extraction algorithms. When thesignal-to-noise ratio is 0dB, the recognition rate is over 98%, which is about 12dB higher than that of Hu and pseudoZernike moments. The algorithm has some advantages of a high recognition rate and a low calculated amount, havinggood application value in engineering application.