MCformer: A Transformer Based Deep Neural Network for Automatic Modulation Classification

In this paper, we propose MCformer - a novel deep neural network for the automatic modulation classification task of complex-valued raw radio signals. MCformer architecture leverages convolution layer along with self-attention based encoder layers to efficiently exploit temporal correlation between the embeddings produced by convolution layer. MCformer provides state of the art classification accuracy at all signal-to-noise ratios in the RadioML2016.10b data-set with significantly less number of parameters which is critical for fast and energy-efficient operation.

[1]  Jakob Krzyston,et al.  High-Capacity Complex Convolutional Neural Networks For I/Q Modulation Classification , 2020, ArXiv.

[2]  Yi Zhong,et al.  A Numerical Study of Cosmic Proton Modulation Using AMS-02 Observations , 2019, IEEE Access.

[3]  Yonina C. Eldar,et al.  Fast Deep Learning for Automatic Modulation Classification , 2019, ArXiv.

[4]  Samuel R. Bowman,et al.  GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding , 2018, BlackboxNLP@EMNLP.

[5]  T. Charles Clancy,et al.  Over-the-Air Deep Learning Based Radio Signal Classification , 2017, IEEE Journal of Selected Topics in Signal Processing.

[6]  Lukasz Kaiser,et al.  Attention is All you Need , 2017, NIPS.

[7]  Alexander M. Rush,et al.  Structured Attention Networks , 2017, ICLR.

[8]  Timothy J. O'Shea,et al.  Radio Machine Learning Dataset Generation with GNU Radio , 2016 .

[9]  T. Charles Clancy,et al.  Convolutional Radio Modulation Recognition Networks , 2016, EANN.

[10]  Asoke K. Nandi,et al.  Automatic Modulation Classification: Principles, Algorithms and Applications , 2015 .

[11]  Yoshua Bengio,et al.  Neural Machine Translation by Jointly Learning to Align and Translate , 2014, ICLR.

[12]  K. C. Ho,et al.  Antenna array likelihood modulation classifier for BPSK and QPSK signals , 2002, MILCOM 2002. Proceedings.

[13]  M.P. Fargues,et al.  A hierarchical approach to the classification of digital modulation types in multipath environments , 2001, Conference Record of Thirty-Fifth Asilomar Conference on Signals, Systems and Computers (Cat.No.01CH37256).

[14]  Achilleas Anastasopoulos,et al.  Likelihood ratio tests for modulation classification , 2000, MILCOM 2000 Proceedings. 21st Century Military Communications. Architectures and Technologies for Information Superiority (Cat. No.00CH37155).

[15]  Brian M. Sadler,et al.  Hierarchical digital modulation classification using cumulants , 2000, IEEE Trans. Commun..

[16]  J. Sills.  Maximum-likelihood modulation classification for PSK/QAM , 1999, MILCOM 1999. IEEE Military Communications. Conference Proceedings (Cat. No.99CH36341).

[17]  K. C. Ho,et al.  Identification of digital modulation types using the wavelet transform , 1999, MILCOM 1999. IEEE Military Communications. Conference Proceedings (Cat. No.99CH36341).

[18]  J. D. Martin,et al.  Maximum likelihood PSK classifier , 1996, Proceedings of MILCOM '96 IEEE Military Communications Conference.

[19]  Lu Mingquan,et al.  Cyclic spectral features based modulation recognition , 1996, Proceedings of International Conference on Communication Technology. ICCT '96.

[20]  Charles L. Weber,et al.  Modulation classification of MFSK signals using the higher-order correlation domain , 1995, Proceedings of MILCOM '95.

[21]  Samir S. Soliman,et al.  Signal classification using statistical moments , 1992, IEEE Trans. Commun..

[22]  Kiseon Kim,et al.  On the detection and classification of quadrature digital modulations in broad-band noise , 1990, IEEE Trans. Commun..

[23]  Elsayed Elsayed Azzouz,et al.  Modulation recognition using artificial neural networks , 1997, Signal Process..