AN ABSTRACT OF THE THESIS OF Adem Zaid for the degree of Master of Science in Computer Science presented on March 15, 2017. Title: Leveraging Compressive Sampling and Machine Learning for Adaptive and Cooperative Wideband Spectrum Sensing Abstract approved:

approved: Bechir Hamdaoui This thesis proposes a novel technique that exploits spectrum occupancy behaviors inherent to wideband spectrum access to enable efficient cooperative spectrum sensing. The proposed technique reduces the number of required sensing measurements while accurately recovering spectrum occupancy information. It does so by leveraging compressive sampling theory to exploit the block-like occupancy structure of wideband spectrum access. The proposed technique is also adaptive in that it accounts for the variability of spectrum occupancy over time. It does so by leveraging supervised learning models to provide and use accurate, real time estimates of the spectrum occupancy. Using simulations, I show that the proposed technique outperforms existing approaches by making accurate spectrum occupancy decisions with lesser sensing communication and energy overheads. c ⃝Copyright by Adem Zaid March 15, 2017 All Rights Reserved Leveraging Compressive Sampling and Machine Learning for Adaptive and Cooperative Wideband Spectrum Sensing