A radar waveform recognition method based on ambiguity function generative adversarial network data enhancement under the condition of small samples

Abstract

This study proposes a small sample recognition method for radar waveforms based on data enhancement of ambiguity function generative adversarial networks (AFGAN) to address the issue of low recognition rate and unbalanced class recognition rate. First, the concept of ambiguity function efficient contour lines (AFECL) and AFECL subject resolution constant are proposed in order to effectively extract radar waveform features. Based on this, the AFGAN model is proposed for radar waveform data enhancement. Simulation experiments classified and identified six types of radar waveforms, which verifies the effectiveness of the model. The experimental results show that the overall recognition rate is increased by 18.64%–99.25% and the class recognition unbalance is reduced by 40.67%–1.33% under the condition of small samples. Compared with short‐time Fourier transform (STFT) and Wigner‐Ville distribution (WVD), the proposed AFECL features are more suitable for recognition in small samples, and the AFGAN model performs significantly better than that of the classical data enhancement models GAN and general WGAN‐GP. The signal recognition rate reached 94.28% when the SNR was −8 dB. The effectiveness of the AFGAN data enhancement method is verified using comparative experiments.

A Novel Adversarial Learning Framework for Passive Bistatic Radar Signal Enhancement

“…Recently, there has been a significant interest in deep learning models, such as autoencoder (AE) [25], generative adversarial network (GAN) [26], and convolutional neural networks (CNN) [27], due to their remarkable ability to automatically extract features and process data. GAN is an effective generative model based on game theory, and various GAN versions have been proposed for different tasks, such as image-to-image translation [28], speech enhancement [29], classification [30][31][32], sample generation [33,34], redundant information mitigation [35][36][37], and image dehazing [38]. Moreover, GAN has been applied to various radar systems, such as synthetic aperture radar (SAR) [39][40][41][42], inverse synthetic aperture radar [43,44], LPI radar [45], and weather radar [46].…”