Saved in:
Bibliographic Details
Main Authors: Gansekoele, Arwin, Balatsoukas-Stimming, Alexios, Brusse, Tom, Hoogendoorn, Mark, Bhulai, Sandjai, van der Mei, Rob
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2405.09909
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917667777019904
author Gansekoele, Arwin
Balatsoukas-Stimming, Alexios
Brusse, Tom
Hoogendoorn, Mark
Bhulai, Sandjai
van der Mei, Rob
author_facet Gansekoele, Arwin
Balatsoukas-Stimming, Alexios
Brusse, Tom
Hoogendoorn, Mark
Bhulai, Sandjai
van der Mei, Rob
contents As telecommunication systems evolve to meet increasing demands, integrating deep neural networks (DNNs) has shown promise in enhancing performance. However, the trade-off between accuracy and flexibility remains challenging when replacing traditional receivers with DNNs. This paper introduces a novel probabilistic framework that allows a single DNN demapper to demap multiple QAM and APSK constellations simultaneously. We also demonstrate that our framework allows exploiting hierarchical relationships in families of constellations. The consequence is that we need fewer neural network outputs to encode the same function without an increase in Bit Error Rate (BER). Our simulation results confirm that our approach approaches the optimal demodulation error bound under an Additive White Gaussian Noise (AWGN) channel for multiple constellations. Thereby, we address multiple important issues in making DNNs flexible enough for practical use as receivers.
format Preprint
id arxiv_https___arxiv_org_abs_2405_09909
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Machine Learning Approach for Simultaneous Demapping of QAM and APSK Constellations
Gansekoele, Arwin
Balatsoukas-Stimming, Alexios
Brusse, Tom
Hoogendoorn, Mark
Bhulai, Sandjai
van der Mei, Rob
Machine Learning
Artificial Intelligence
Information Theory
As telecommunication systems evolve to meet increasing demands, integrating deep neural networks (DNNs) has shown promise in enhancing performance. However, the trade-off between accuracy and flexibility remains challenging when replacing traditional receivers with DNNs. This paper introduces a novel probabilistic framework that allows a single DNN demapper to demap multiple QAM and APSK constellations simultaneously. We also demonstrate that our framework allows exploiting hierarchical relationships in families of constellations. The consequence is that we need fewer neural network outputs to encode the same function without an increase in Bit Error Rate (BER). Our simulation results confirm that our approach approaches the optimal demodulation error bound under an Additive White Gaussian Noise (AWGN) channel for multiple constellations. Thereby, we address multiple important issues in making DNNs flexible enough for practical use as receivers.
title A Machine Learning Approach for Simultaneous Demapping of QAM and APSK Constellations
topic Machine Learning
Artificial Intelligence
Information Theory
url https://arxiv.org/abs/2405.09909