Generative Adversarial Networks with Gramian Angular Field for Handling Imbalanced Data in Specific Emitter Identification

Abstract

Specific Emitter Identification (SEI) is a methodology employed to identify emitters by exploiting the hardware impairments inherent in transmitting devices. In the real world, there are challenges in performing SEI on radiation source signals, such as serious imbalance among samples, leading to low model accuracy, poor generalization, and limited practical application. These challenges widely occur in modern military, security, and other fields, but related research works have been conducted relatively late. In this paper, we propose a Generative Adversarial Network (GAN) with the Gramian Angular Field (GAF) method to address few-shot case data. Specifically, the proposed method employs GAF transformation to convert temporal radar data into a two-dimensional image format and utilizes an enhanced GAN to improve the classifier for imbalanced data based on the characteristics of GAF through training on both augmented and original samples. The experiments were conducted on real-world Automatic Dependent Surveillance-Broadcast (ADS-B) signals, demonstrating the effectiveness of the proposed method. The method could significantly improve the performance of the SEI model in inter-class imbalanced scenarios.