Open Collections

Garlick, Eli

University of British Columbia

Cognitive tactical wireless networks (TWNs) require spectrum aware- ness to avoid interference and jamming in the communication channel and assure quality-of-service in data transmission. Conventional supervised ma- chine learning (ML) algorithm’s capability to provide spectrum awareness is confronted by the requirement of labeled interference signals. Due to the dynamic nature of interference signals in the frequency bands used by cognitive TWNs, it is non-trivial to acquire manually labeled data sets of all interference signals. Detecting the presence of an unknown and remote interference source in a frequency band from the transmitter end is also challenging, especially when the received interference power remains at or below the noise floor. To address these issues, this thesis proposes an automated interference detection framework, entitled MARSS (Machine Learning Aided Resilient Spectrum Surveillance). MARSS is a fully unsupervised method, which first extracts the low-dimensional representative features from spectrograms by suppressing noise and background information and employing a Convolu- tional Neural Network (CNN) with novel loss function, and subsequently, distinguishes signals with and without interference by applying an isolation forest model on the extracted features. The uniqueness of MARSS is its ability to detect hidden and unknown interference signals in multiple fre- quency bands without using any prior labels, thanks to its superior feature extraction capability. The capability of MARSS is further extended to infer the level of interference by designing a multi-level interference classifica- tion framework. Using extensive simulations in GNU Radio, the superiority of MARSS in detecting interference over existing ML methods is demon- strated. The effectiveness MARSS is also validated by over-the-air (OTA) experiments using software-defined radios.

Text

2024-12-16

Attribution-NonCommercial-NoDerivatives 4.0 International

http://hdl.handle.net/2429/89879

Electrical Engineering

University of British Columbia

UBCO

http://creativecommons.org/licenses/by-nc-nd/4.0/