Generative Adversarial Network for Radar-Based Human Activities Classification with Low Training Data Support

Deep learning has shown tremendous prospects in human activity recognition based on micro-Doppler radar. However, the deficiency of radar data because of the extremely high labor and costs involved in obtaining radar data has hindered deep learning-based radar applications. In this paper, we proposed to use the discriminator of the generative adversarial network(GAN) for the radar-based human activities classification with low training data support. In supervised adversarial training, the generated samples and real samples are both sent to the discriminator for joint training, and thus the performance of the discriminator is boosted by both the real samples and generated samples. When the training samples are limited, GAN might fail to converge. In this paper, we firstly proposed a novel parameters initialization method of GAN to speed its convergence. The trained discriminator is fine-tuned on the training set for a few epochs. The classification results indicate that our proposed model can improve the classification accuracy and outperform the state-of-art models, especially when the training samples are limited.