Hierarchical Jamming Recognition with Spectrum Fusion Feature and Twin-bound SVM for Cognitive Satellite Communications

In satellite communications, signals are vulnerable to radio frequency jamming, especially in aerospace tracking telemetry and command (TT&C) systems and global navigation satellite system (GNSS). It is quite essential to jamming suppression for unknown jamming signals to ensure the safety of co...

Full description

Saved in:
Bibliographic Details
Main Authors: Wei, Yi, Ou-Yang, Shang-Rong, Li, Chao, Liu, Qi, Qian, Yu-Bi
Format: Conference Proceeding
Language:English
Subjects:
and spectrum sensing
Classification algorithms
cognitive satellite communication
Global navigation satellite system
hierarchical classification
Jamming recognition
machine learning
Satellite broadcasting
Satellites
Sensors
Simulation
Support vector machines
twin-bound support vector machine (SVM)
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In satellite communications, signals are vulnerable to radio frequency jamming, especially in aerospace tracking telemetry and command (TT&C) systems and global navigation satellite system (GNSS). It is quite essential to jamming suppression for unknown jamming signals to ensure the safety of communication links, and the design of the jamming type recognition algorithm is a basic prerequisite of effectively anti-jamming, especially for the cognitive satellite communications. In this work, considering the limited resource of satellites, a fast jamming recognition algorithm is proposed to detect and classify the jamming signals with low time complexity in the process of data transmission. By taking advantage of the spectrum fusion feature and making full use of the anti-jamming prior information, the proposed algorithm combines the idea of the twin support vector machine (SVM) and the solution-oriented hierarchical classification to reduce the online time complexity with high recognition accuracy. Simulation results demonstrate the clear superiority of the proposed algorithm vis-à-vis other baseline competitors.
ISSN:1558-2612
DOI:10.1109/WCNC55385.2023.10119124