Automatic Modulation Classification Using a Deep Multi-Stream Neural Network
Open Access
- 7 February 2020
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 43888-43897
Abstract
In wireless communication, modulation classification is an important part of the non-cooperative communication, and it is difficult to classify the various modulation schemes using conventional methods. The deep learning network has been used to handle the problem and acquire good results. In the deep convolutional neural network (CNN), the data length in the input is fixed. However, the signal length varies in communication, and it causes that the network cannot take advantage of the input signal data to improve the classification accuracy. In this paper, a novel deep network method using a multi-stream structure is proposed. The multi-stream network form increases the network width, and enriches the types of signal features extracted. The superposition convolutional unit in each stream can further improve the classification performance, while the shallower network form is easier to train for avoiding the over-fitting problem. Further, we show that the proposed method can learn more features of the signal data, and it is also shown to be superior to common deep networks.Keywords
Funding Information
- Qingdao National Laboratory for Marine Science and Technology (2018SDKJ0210)
- National Natural Science Foundation of China (61701462, 41527901)
- Equipment for the Pre-research Field Fund Project (61404160502)
- National Defense Science and Technology Innovation Zone H863 Program (18-H863-**-**-***-***-01)
- Aoshan Science and Technology Innovation Plan (2017ASKJ01)
- Qingdao National Laboratory for Marine Science and Technology (7-1-1-7-jch)
- Fundamental Research Funds for the Central Universities (201713018)
- Doctoral Fund of QUST (010029029)
- Opening Foundation of Key Laboratory of Opto-technology and Intelligent Control (Lanzhou Jiaotong University), Ministry of Education (KFKT2019-2)
- Natural Science Foundation of Shandong Province (ZR2017BF023)
- Shandong Province Postdoctoral Innovation Project (201703032)
- Natural Science Foundation of Shandong Province (ZR2016AL10)
- State Key Laboratory of Acoustics, Chinese Academy of Sciences (SKLA201903)
This publication has 32 references indexed in Scilit:
- Modulation recognition using hierarchical deep neural networks2017
- Automatic Modulation Classification using combination of Wavelet Transform and GARCH model2016
- Deep Residual Learning for Image Recognition2016
- Signal Identification for Multiple-Antenna Wireless Systems: Achievements and ChallengesIEEE Communications Surveys & Tutorials, 2016
- Neural Network Based Transmit Power Control and Interference Cancellation for MIMO Small Cell NetworksIEICE Transactions on Communications, 2016
- Software-defined underwater acoustic networks: toward a high-rate real-time reconfigurable modemIEEE Communications Magazine, 2015
- Intercell-Interference Cancellation and Neural Network Transmit Power Optimization for MIMO Channels2015
- Deep learningNature, 2015
- Modulation classification in fading channels using antenna arrays2005
- A fast automatic modulation recognition algorithm and its implementation in a spectrum monitoring application2002