DNN-Based Cross Layer Resource Allocation of NOMA-OFDMA Video Transmissions without Post Processing

Shu Ming Tseng, Cheng Hsun Tsai, Yueh Teng Hsu

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

In the previous study [1], deep-neural-network-aided physic al/application layer resource management for NOMA-OFDMA video transmissions was proposed. Meeting the constraints that every user has one or more subcarrier and exact two users on every subcarrier, a post processing involving the sorting in the testing stage was necessary. To remove the post processing and the corresponding latency, we propose in this paper a new loss function during the training stage such that no sorting-based post processing is necessary. The numerical results show the average PSNR is close (slightly poorer) to that in [1].

Original languageEnglish
Title of host publication2021 IEEE International Conference on Consumer Electronics, ICCE 2021
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728197661
DOIs
StatePublished - 10 01 2021
Externally publishedYes
Event2021 IEEE International Conference on Consumer Electronics, ICCE 2021 - Las Vegas, United States
Duration: 10 01 202112 01 2021

Publication series

NameDigest of Technical Papers - IEEE International Conference on Consumer Electronics
Volume2021-January
ISSN (Print)0747-668X

Conference

Conference2021 IEEE International Conference on Consumer Electronics, ICCE 2021
Country/TerritoryUnited States
CityLas Vegas
Period10/01/2112/01/21

Bibliographical note

Publisher Copyright:
© 2021 IEEE.

Keywords

  • NOMA
  • constrained optimization
  • deep learning
  • loss function
  • multimedia communications

Fingerprint

Dive into the research topics of 'DNN-Based Cross Layer Resource Allocation of NOMA-OFDMA Video Transmissions without Post Processing'. Together they form a unique fingerprint.

Cite this