Automatic modulation classification (AMC) aims to blindly recognize the
modulation type of a received signal in wireless systems. It is also a critical component
of non-cooperative communication systems after the detection of the presence of a
signal. In this paper, we introduce a robust approach, termed DET-AMC (joint
Detection and Automatic Modulation Classification), employing Convolutional Neural
Networks (CNNs) trained via transfer learning methodology. The main advantage of
our approach is its ability to handle a wide range of modulation types, including 10
different schemes generated in Gnuradio and their detection using the same model.
Through extensive experimentation, we evaluate the performance of our light CNNbased DET-AMC method across varying signal-to-noise ratio (SNR) levels, as well as
in the presence of phase noise and frequency offset. We find that the CNN’s learned
features, obtained through transfer learning, exhibit robustness, particularly in low
SNR and various challenging conditions, leading to accurate modulation classification.
In general, our approach outperforms existing methods by using the effectiveness
of deep learning in capturing relevant discriminative features. Additionally, our
model offers a robust solution for join detection and AMC by achieving an accurate
probability of detection and modulation classification without the need for manual
feature engineering or the consideration of frequency offset, phase noise or noise
estimation. Our model achieves 100% accuracy for synthetic and real data at an
SNR equal to -10 dB for detection, and 100% and 98% for classification of synthetic
and real signals at -4 dB, respectively.