Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cyberspace

Research Article

Automatic Modulation Classification Using Hybrid Convolutional Neural Network

Download396 downloads
  • @INPROCEEDINGS{10.4108/eai.27-8-2020.2295027,
        author={Xiaofei  Zhang and Li  Anping and Chai  Lu and Ma  Xiaoying and Wei  Meiying},
        title={Automatic Modulation Classification Using Hybrid Convolutional Neural Network},
        proceedings={Proceedings of the 13th EAI International Conference on Mobile Multimedia Communications, Mobimedia 2020, 27-28 August 2020, Cyberspace},
        publisher={EAI},
        proceedings_a={MOBIMEDIA},
        year={2020},
        month={11},
        keywords={amc deep convolutional neural network hybrid convolutional neural networks spectral correlation features regular constellation images},
        doi={10.4108/eai.27-8-2020.2295027}
    }
    
  • Xiaofei Zhang
    Li Anping
    Chai Lu
    Ma Xiaoying
    Wei Meiying
    Year: 2020
    Automatic Modulation Classification Using Hybrid Convolutional Neural Network
    MOBIMEDIA
    EAI
    DOI: 10.4108/eai.27-8-2020.2295027
Xiaofei Zhang1, Li Anping1, Chai Lu2,*, Ma Xiaoying3, Wei Meiying3
  • 1: The State Radio Monitorning Center, Beijing, P.R.China, 100037
  • 2: Key Laboratory of Universal Wireless Communications, Ministry of Education, Beijing University of Posts and Telecommunications, Beijing, P.R.China, 100876.
  • 3: The State Radio Monitorning Center, Beijing, P.R.China, 100037.
*Contact email: chaibyr@bupt.edu.cn

Abstract

Automatic modulation classification (AMC) plays an essential role in signal demodulation and interference identifica-tion. In this paper, we propose a novel AMC method using the Hybrid Convolutional Neural Network (HCNN), which combines with two different convolutional neural networks (CNNs) jointly using various signal features. In the former CNN, spectral correlation features (SCFs) are generated as network input, to classify FSK and BPSK. In the latter CNN, the Attention-based Densely Convolutional Neural Network (AD-CNN), which is trained using regular constellation images (RCs), is proposed to identify the modulation formats that are hardly recognized by the former CNN, such as QPSK, 16-QAM and 64-QAM. The simulation results demonstrate that HCNN displays superior classification performance than existing AMC methods with lower computational complexity.