Blind spectrum sensing algorithm based on cyclic spectrum and deep learning

Lihao Li; Yun Lin; Chenxi Liang; Zheng Dou

doi:10.1117/12.2679555

16 June 2023 Blind spectrum sensing algorithm based on cyclic spectrum and deep learning

Lihao Li, Yun Lin, Chenxi Liang, Zheng Dou

Proceedings Volume 12702, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023); 1270221 (2023) https://doi.org/10.1117/12.2679555
Event: International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023), 2023, Changsha, China

Abstract

With the Internet of Things and big data advancing so quickly, spectrum resources are increasingly in short supply. For unauthorized users, to achieve reliable and stable wireless communication, they must rely on spectrum sensing technology. Traditional spectrum sensing methods have poor performance in situations with a low signal-to-noise ratio, but deep learning's evolution can effectively solve this problem. However, with the improvement of perception accuracy in practical application, the neural network now has many layers and has many large model parameters., which makes the actual deployment of the algorithm require high computing power equipment. To address the issues with conventional spectrum sensing models' excessive resource consumption, poor real time performance, and limited detection accuracy, a deep learning and cyclic spectrum-based approach for blind spectrum sensing is suggested. In this method, a lightweight sensing network based on MobileNet V2 is built, and the fast Fourier transformation accumulation method is used to extract the features of the signals, which are normalized and sent into the network for training. Experimental results show that this algorithm can sense many kinds of digital modulation signals, and the perceived performance is better than other algorithms.

Citation Download Citation

Lihao Li, Yun Lin, Chenxi Liang, and Zheng Dou "Blind spectrum sensing algorithm based on cyclic spectrum and deep learning", Proc. SPIE 12702, International Conference on Intelligent Systems, Communications, and Computer Networks (ISCCN 2023), 1270221 (16 June 2023); https://doi.org/10.1117/12.2679555

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

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
8 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Signal to noise ratio

Education and training

Feature extraction

Modulation

Interference (communication)

Detection and tracking algorithms

Convolution

Show All Keywords

Keywords/Phrases

Search In:

Publication Years