The problem of efficient modulation classification (MC) in multiple-input multiple-output (MIMO) systems is considered. Per-layer likelihood-based MC is proposed by employing subspace decomposition to partially decouple the transmitted streams. When detecting the modulation type of the stream of interest, a dense constellation is assumed on all remaining streams. The proposed classifier outperforms existing MC schemes at a lower complexity cost, and can be efficiently implemented in the context of joint MC and subspace data detection.
@article{arxiv.1610.03362,
title = {Modulation Classification via Subspace Detection in MIMO Systems},
author = {Hadi Sarieddeen and Mohammad M. Mansour and Ali Chehab},
journal= {arXiv preprint arXiv:1610.03362},
year = {2016}
}