基于复数域上元度量学习的小样本辐射源个体识别方法

Specific Emitter Identification Method with Small Sample Based on Meta Metric Learning in Complex Field

当带标签样本数较少时,现有的基于深度学习的辐射源个体识别方法,识别性能退化。针对上述问题,提出一种基于复数域上元度量学习的小样本辐射源个体识别方法。该方法将元学习中基于度量的方法与复数神经网络结合,设计嵌入模块,在小样本条件下更充分地学习辐射源复信号波形中隐藏的个体指纹信息,提升识别精度。仿真实验结果表明,提出的复原型网络、复匹配网络和复关系网络,与它们的实数域形式相比,识别准确率均得到了提升,且其中性能最好的是复关系网络。复关系网络在5类待识别辐射源个体分别仅有5个带标签样本(5-way5-shot)的情况下,20 dB信噪比条件下的识别准确率达到了85%。

When the number of labeled samples is small,the performance of the existing emitter recognition methods based on deep learning degrades.To solve the above problem,this paper proposes a meta metric learning method in complex field under small sample condition.This method combines the meta metric learning with complex neural network,and designs an embedded module to more fully learn the individual fingerprint information hidden in the complex signal waveform of the emitter under the condition of small samples,so as to improve the recognition accuracy.The simulation results show that the recognition accuracy of the complex prototype network,complex matching network and complex relation network proposed in this paper is improved compared with their real domain forms,and the complex relation network has the best performance.The recognition accuracy of complex relation network under the condition of 20 dB signal-to-noise ratio is more than 85% when there are only five labeled samples(5-way 5-shot) for five types of emitters to be identified.