Haris Gacanin

TL;DR: In this paper , a semi-supervised learning-based specific emitter identification (SS-SEI) method using metric-adversarial training (MAT) is proposed, where pseudo labels are innovatively introduced into metric learning to enable Semi-Supervised metric learning (SSML), and an objective function alternatively regularized by SSML and virtual adversarial training is designed to extract discriminative and generalized semantic features of radio signals.

TL;DR: It was shown that the broadband ANC schemes with practical CE in a time- and frequency-selective channel should include a more sophisticated channel interpolation techniques since the impact of Doppler shift has prevalent effect on the achievable BER performance.

TL;DR: In this paper, the uplink and downlink resource allocation of transceivers and UAV relay for FD-NOMA systems were jointly optimized to improve the spectrum efficiency.

TL;DR: An on-demand learning offloading mechanism for edge-to-edge cooperative AI based on the concatenation of deep neural network (DNN) subtasks and their heterogeneous requirement of learning resources is proposed.