An Open-Set Modulation Recognition Scheme With Deep Representation Learning
Yanghong Chen, Xiaodong Xu, Xiaowei Qin
Abstract
This letter proposes a deep representation learning based automatic modulation recognition (AMR) algorithm in the open-set recognition (OSR) regime. The challenging recognition risk of unknown modulation classes is first analyzed for most state-of-the-art approaches, and interesting insights into this problem is then provided. Based on this, an open-set AMR scheme is proposed with a combination of feature representation and classification, where a triplet loss function from metric learning is employed for the representor to form distinct clusters for <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> known modulation classes. Then, the degree of membership is calculated via extreme value theory (EVT) by modeling the distance between known training data to its corresponding clustering center, followed by <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$N$ </tex-math></inline-formula> binary classifiers. Comprehensive experiments on public dataset confirm that the proposed scheme outperforms the other state-of-the-arts in terms of both balanced accuracy and openness.