Deep learning based automatic signal modulation classification

Jingyang Lu; Yi Li; Genshe Chen; Dan Shen; Xin Tian; Khanh Pham

doi:10.1117/12.2520544

29 July 2019 Deep learning based automatic signal modulation classification

Jingyang Lu, Yi Li, Genshe Chen, Dan Shen, Xin Tian, Khanh Pham

Proceedings Volume 11017, Sensors and Systems for Space Applications XII; 110170M (2019) https://doi.org/10.1117/12.2520544
Event: SPIE Defense + Commercial Sensing, 2019, Baltimore, MD, United States

Abstract

In this paper, a Cognitive Radio Network (CRN) based on artificial intelligence is proposed to automatically classify signal modulation more efficiently, which can further help in radio frequency modeling and pattern recognition problem solving. Three different approaches Deep Neural Network (DNN), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) have been deployed and evaluated in the signal modulation classification. In this paper, the signals for training and validation are generated using our MATLAB based RF signal generator, which can simulate various types of modulated signal according to the configuration specification. The numerical results show that CNN network can outperform the DNN and RNN in terms of the signal modulation classification accuracy.

Conference Presentation

Citation Download Citation

Jingyang Lu, Yi Li, Genshe Chen, Dan Shen, Xin Tian, and Khanh Pham "Deep learning based automatic signal modulation classification", Proc. SPIE 11017, Sensors and Systems for Space Applications XII, 110170M (29 July 2019); https://doi.org/10.1117/12.2520544

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available