Research Article
Active User Blind Detection Through Deep Learning
@INPROCEEDINGS{10.1007/978-3-030-73423-7_1, author={Cyrille Morin and Diane Duchemin and Jean-Marie Gorce and Claire Goursaud and Leonardo S. Cardoso}, title={Active User Blind Detection Through Deep Learning}, proceedings={Cognitive Radio-Oriented Wireless Networks. 15th EAI International Conference, CrownCom 2020, Rome, Italy, November 25-26, 2020, Proceedings}, proceedings_a={CROWNCOM}, year={2021}, month={3}, keywords={Non-coherent active user detection Machine learning Massive random access}, doi={10.1007/978-3-030-73423-7_1} }- Cyrille Morin
Diane Duchemin
Jean-Marie Gorce
Claire Goursaud
Leonardo S. Cardoso
Year: 2021
Active User Blind Detection Through Deep Learning
CROWNCOM
Springer
DOI: 10.1007/978-3-030-73423-7_1
Abstract
Active user detection is a standard problem that concerns many applications using random access channels in cellular orad hocnetworks. Despite being known for a long time, such a detection problem is complex, and standard algorithms for blind detection have to trade between high computational complexity and detection error probability. Traditional algorithms rely on various theoretical frameworks, including compressive sensing and bayesian detection, and lead to iterative algorithms, e.g. orthogonal matching pursuit (OMP). However, none of these algorithms have been proven to achieve optimal performance.
This paper proposes a deep learning based algorithm (NN-MAP) able to improve on the performance of state-of-the-art algorithm while reducing detection time, with a codebook known at training time.
