… of deep learning in AMC. In this paper, a novel modulation classification framework is
proposed. This framework further considers the intrinsic properties of the modulated signals. It …

… We also apply our method on two existing AMC networks, FiF-Net, and CCNN and observe
an accuracy increase of 1.13% and 0.93%, respectively. We especially observe a big …

… AMC usually assumes an environment of fixed signal to noise ratio (SNR). This paper considers
DL based AMC for … neural network (CNN) is utilized to classify modulation types. In [16], …

… modulation classification (AMC). In this paper, a novel compressive convolutional neural
network (CCNN) is proposed for AMC, … the original loss function of CNN network. CCNN aims at …

… modulation classification (AMC) has been deployed in the physical layer to blindly identify
the modulation … RanNet also defeats several existing networks in terms of accuracy with a …

… AMC methods, wherein DL is exploited as the core technology to improve the overall performance
of modulation classification. … SNR were first reconstructed by U-Net [104] for signal re-…

… ) to realize this AMC. The CNN-AMC can approximate the ML-AMC with minimal performance
… The MLAMC is used as a benchmark for our proposed CNN-AMC, and can also generate …

… modulation classification (AMC) has played a vital role in various civilian and military applications.
AMC … DHN is a simple, one-stage network inspired by feature pyramid network (FPN) […

… Abstract—Automatic modulation classification (AMC) is be… a better classification performance,
several AMC methods … However, most existing AMC methods based on CNNs only use …

… Automatic modulation classification (AMC) is one of the most … AMC is generically modeled
as a pattern recognition problem… networks on digital signal modulation classification,”Comput. …