基于SIB/PCA的通信辐射源个体识别

Identification of individual radio transmitters using SIB/PCA

提出了一种新的同类通信辐射源个体识别方法.该方法选择矩形积分双谱(SIB)作为个体识别的主体特征参数,然后采用主元分析(PCA)方法从大量训练样本特征参数集中挑选低维、低复杂度的特征矢量,并在识别特征矢量中融合对分类具有显著贡献的辐射源调制特征参量,最后采用基于核函数的支撑矢量机(SVM)实现对辐射源个体识别.实验表明该方法在较低信噪比条件下具有较高的正确识别率(90%),并能够较好地解决同型号、同批次通信辐射源的个体识别问题.

A novel method for identifying individual radio transmitters with the same model is proposed.Square integral bispectra（SIB） were used as the main parametric features,and principal component analysis（PCA） was utilized to extract low-dimensional feature vectors with low complexity from a large of training sample features.Moreover,the modulation parameters of individual transmitter significant to classification are merged into the identification feature vector.Then,a support vector machine（SVM） based on kernel-function is implemented to realize individual transmitter identification.The experimental results demonstrate that the suggested technique has a recognition rate of 90 % in low signal noiseratio,and it can solve the problem of identifying individual transmitters with the same model and manufacturing lot.