A radio-signal interference suppression approach based on denoising autoencoder

Hui Huang; Dan Shen; Xin Tian; Peng Cheng; Genshe Chen; Khanh Pham; Erik Blasch

doi:10.1117/12.2666242

13 June 2023 A radio-signal interference suppression approach based on denoising autoencoder

Hui Huang, Dan Shen, Xin Tian, Peng Cheng, Genshe Chen, Khanh Pham, Erik Blasch

Proceedings Volume 12546, Sensors and Systems for Space Applications XVI; 125460R (2023) https://doi.org/10.1117/12.2666242
Event: SPIE Defense + Commercial Sensing, 2023, Orlando, Florida, United States

Abstract

The scarcity and finite nature of the wireless spectrum drives technology development for spectrum utilization. With the increased complexity of the radio-access environment and susceptibility to interference disruption, challenges exist which demand advanced interference suppression techniques. Recently, the advance of artificial intelligence (AI) promotes technology for data-driven modeling of complicated relationships, which provides numerous tools and techniques for signal processing and analysis. This paper develops a deep learning-based radio signal interference suppression method by leveraging the adaptive features and Convolutional Neural Network (CNN) based Denoising autoencoder (DAE). By simulating the communication system with stochastic channel effects (AWGN channel), the proposed Suppression of Interference DEA (S-IDEA) method is validated using the original signals and the corrupted signals through channel effects. The results show that S-IDEA can effectively perform interference suppression from AWGN channel at different SNR levels and achieve excellent SNR improvement.

Conference Presentation

Citation Download Citation

Hui Huang, Dan Shen, Xin Tian, Peng Cheng, Genshe Chen, Khanh Pham, and Erik Blasch "A radio-signal interference suppression approach based on denoising autoencoder", Proc. SPIE 12546, Sensors and Systems for Space Applications XVI, 125460R (13 June 2023); https://doi.org/10.1117/12.2666242

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