Data Augmentation and Classification of Sea-Land Clutter for Over-the-Horizon Radar Using AC-VAEGAN

TL;DR

This paper introduces AC-VAEGAN, an improved generative model that synthesizes high-quality sea-land clutter data to enhance over-the-horizon radar classification performance, especially with limited and imbalanced datasets.

Contribution

The paper proposes AC-VAEGAN, a novel architecture combining VAE and GAN for better synthetic data generation in sea-land clutter classification tasks.

Findings

AC-VAEGAN produces higher quality synthetic samples than AC-GAN.

Data augmentation with AC-VAEGAN improves classification accuracy on scarce, imbalanced datasets.

The evaluation method effectively assesses synthetic sample quality in both domain-specific and statistical terms.

Abstract

In the sea-land clutter classification of sky-wave over-the-horizon-radar (OTHR), the imbalanced and scarce data leads to a poor performance of the deep learning-based classification model. To solve this problem, this paper proposes an improved auxiliary classifier generative adversarial network~(AC-GAN) architecture, namely auxiliary classifier variational autoencoder generative adversarial network (AC-VAEGAN). AC-VAEGAN can synthesize higher quality sea-land clutter samples than AC-GAN and serve as an effective tool for data augmentation. Specifically, a 1-dimensional convolutional AC-VAEGAN architecture is designed to synthesize sea-land clutter samples. Additionally, an evaluation method combining both traditional evaluation of GAN domain and statistical evaluation of signal domain is proposed to evaluate the quality of synthetic samples. Using a dataset of OTHR sea-land clutter, both the quality of the synthetic samples and the performance of data augmentation of AC-VAEGAN are verified. Further, the effect of AC-VAEGAN as a data augmentation method on the classification performance of imbalanced and scarce sea-land clutter samples is validated. The experiment results show that the quality of samples synthesized by AC-VAEGAN is better than that of AC-GAN, and the data augmentation method with AC-VAEGAN is able to improve the classification performance in the case of imbalanced and scarce sea-land clutter samples.