A Zynq-Based Platform With Conditional- Reconfigurable Complex-Valued Neural Network for Specific Emitter Identification

In wireless communication security and spectrum management, specific emitter identification (SEI) is a potential technology to identify individual emitters. Recently, a novel SEI algorithm based on complex-valued neural network (CVNN) has emerged, which exhibits powerful processing capabilities in complex domains. However, it also brings high computational complexity, which makes it difficult to meet the power efficiency requirements of the system. To address the above challenge, a Zynq-based SEI platform with conditional-reconfigurable CVNN is proposed in this article, including processing system (PS) and programming logic (PL). The platform can adaptively reconfigure CVNN based on sample difficulty to perform conditional computation between lightweight student network and high-performance teacher network, which achieves high power efficiency while maintaining high accuracy. Inside the PL, a conditional configuration engine and a configurable CVNN engine are specifically designed for CVNN acceleration and controlled by the PS. The experiment results on the public ORACLE RF dataset show that our platform can achieve a high power efficiency of 88.32 giga operations per second per watt (GOPS/W) and a high accuracy of 99.18%.