Abstract: Based on the research of identifying individual radio transmitters with the same model, a novel method for identifying individual radio transmitters with the selected local surrounding-line integral bi-spectrum is proposed. The selected spectra and parameters significant for classification of the received signal form the identification feature vector, and Support Vector Machine（SVM） based on mixed kernel function is used to realize the individual identification. The experimental results demonstrate that the suggested technique has a recognition rate of 90%, and  it can solve the problem of identifying individual transmitters with the same model and manufacturing lot.

Key words: radio transmitters, local surrounding-line integral bi-spectrum, Support Vector Machine（SVM）, mixed kernel function

摘要： 对同类通信辐射源个体识别方法进行了深入的研究，提出了基于局部围线积分双谱的通信辐射源个体识别算法，融合了辐射源调制特征参量作为分类特征向量，采用了基于混合核函数的支持向量机（SVM）实现辐射源个体识别。实验结果表明，该方法具有较高的正确识别率（90%以上），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。

关键词: 通信辐射源, 局部围线积分双谱, 支持向量机（SVM）, 混合核函数