Deep Semi-Supervised Learning-Based Spectrum Sensing at Low SNR

Deep learning (DL) has been introduced to spectrum sensing to improve spectrum utilization effectively. However, some DL-based methods struggle to sense spectrum occupancy at low-signal-to-noise ratio (SNR) and require significant quantities of labeled samples for training in new environments. There...

Full description

Saved in:
Bibliographic Details
Published in:IEEE communications letters 2024-11, Vol.28 (11), p.2558-2562
Main Authors: Xu, Guanghai, Wang, Yonghua, Zheng, Bingfeng, Li, Jiawen
Format: Article
Language:English
Subjects:
Adaptation models
Artificial neural networks
CNN
Convolution
Deep learning
deep semi-supervised learning
Feature extraction
GAN
Generative adversarial networks
Generators
low-SNR
Machine learning
Probability
Robustness
Semi-supervised learning
Semisupervised learning
Sensors
Signal to noise ratio
Spectrum sensing
Training
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Deep learning (DL) has been introduced to spectrum sensing to improve spectrum utilization effectively. However, some DL-based methods struggle to sense spectrum occupancy at low-signal-to-noise ratio (SNR) and require significant quantities of labeled samples for training in new environments. Therefore, this letter proposes a novel spectrum sensing method based on deep semi-supervised learning (DSSL). Specifically, adopting the DSSL during offline training can effectively mitigate the issue of insufficient labeled samples, while introducing an improved Generative Adversarial Network (GAN) makes the convolutional neural network (CNN) model robust to incorrect pseudo-labels through adversarial learning, thereby enhancing the adaptability and performance of the CNN model. Simulation results show that the proposed approach is more effective and robust than existing methods, particularly under low SNR levels.
ISSN:1089-7798
1558-2558
DOI:10.1109/LCOMM.2024.3468299