Abstract
Automatic modulation classification (AMC) used in cognitive radio networks is an important class of methods apt to utilize spectrum resources efficiently. However, conventional likelihood-based approaches have high computational complexity. Thus, this paper proposes a novel convolutional neural network architecture for AMC. A bottleneck and asymmetric convolution structure are employed in the proposed model, which can reduce the computational complexity. The skip connection technique is used to solve the vanishing gradient problem and improve the classification accuracy. The dataset DeepSig:RadioML, which is composed of 24 modulation classes, is used for the performance analysis. Simulation results show that the classification accuracy performance of the proposed model is outstanding in the signal-to-noise ratio (SNR) range from $- 4\,\,dB$ to $20~dB$ compared with MCNet that is the best model in the conventional models, where the proposed model achieves 5.52% and 5.92% improvement regarding classification accuracy at the SNRs of $0~dB$ and $10~dB$ , respectively. In terms of the computational complexity, the proposed model not only saves the trainable parameters by more than 67% but also reduces the prediction time for a signal by more than 54.4% compared with those of MCNet.
Funding Information
  • MSIT (Ministry of Science, ICT), Korea, under the Grand Information Technology Research Center Support Program, supervised by the IITP (IITP-2020-2020-0-01612)
  • Priority Research Centers Program (2018R1A6A1A03024003)
  • Basic Science Research Program through the National Research Foundation of Korea
  • Ministry of Education, Science and Technology (2019R1I1A1A01063895)

This publication has 43 references indexed in Scilit: