Abstract
The modulation recognition method based on deep learning plays a significant role in the intelligent communication system. To further improve the recognition rate, especially in the case of small samples with a low signal-to-noise ratio, this paper proposes a new modulation recognition method based on flying fish swarm algorithm. First, Short-Time Fourier Transform, Choi-Williams Distribution, and Cyclic Spectrum are combined to complete multi-channel signal processing. Second, AlexNet, VGGNet, GoogLeNet, and ResNet are transferred to realize feature extraction. Third, the support vector machine classifies the modulations after dimension reduction and feature fusion. Finally, the flying fish swarm is proposed to optimize the signal processing methods, the types of networks, the layers of networks, the dimensions of features, and the parameters of the support vector machine. The method can accurately recognize BPSK, QPSK, OQPSK, 8PSK, 4ASK, QAM16, QAM32, and QAM64. The simulation results show that the average recognition rate of modulation is 94.5% at SNR of 0 dB and 84.7% at SNR of −4 dB. Besides, the proposed modulation recognition method possesses good robustness under low SNR conditions.
Highlights
Modulation recognition of communication signals has played an important role in new intelligent communication systems, which can help to demodulate and decode signals
The results show that the Principal Component Analysis (PCA) dimension reduction effect is better than that of feature classification without dimension reduction [24]
SIMULATION AND DISCUSSION This paper assumes that the received modulation includes Binary Phase-Shift Keying (BPSK), Quadrature Phase-Shift Keying (QPSK), 8 Phase-Shift Keying (8PSK), Offset Quadrature Phase-Shift Keying (OQPSK), 4 AmplitudeShift Keying (4ASK), Quadrature Amplitude Modulation 16 (QAM16), Quadrature Amplitude Modulation 32 (QAM32), and Quadrature Amplitude Modulation 64 (QAM64)
Summary
Modulation recognition of communication signals has played an important role in new intelligent communication systems, which can help to demodulate and decode signals. To achieve a better recognition rate, the dimension of features and the selection relationship between the signal processing methods, neural network, and corresponding network layer should be further considered. We build a Convolutional Neural Network Set (CNNS) based on transfer learning, including ResNet-50, VGGNet-19, GoogLeNet, and AlexNet. The selective relationship among the signal processing methods, the transferred network models in CNNS, and the appropriate number of network layers constitutes part of the feasible solution space. The main contributions of this paper are as follows: 1) A new modulation recognition method based on the FFS algorithm is proposed. This method can solve the problem of low recognition rate under low SNR and small sample size.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
