Details
| Original language | English |
|---|---|
| Pages (from-to) | 1-15 |
| Number of pages | 15 |
| Journal | Electronic Communications of the EASST |
| Volume | 80 |
| Publication status | Published - 8 Sept 2021 |
Abstract
Keywords
- In-Network Processing, Multimedia Streaming, Quality Of Experience, Reinforcement Learning
ASJC Scopus subject areas
- Computer Science(all)
- Software
- Computer Science(all)
- Computational Theory and Mathematics
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Electronic Communications of the EASST, Vol. 80, 08.09.2021, p. 1-15.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Towards QoE-Driven Optimization of Multi-Dimensional Content Streaming
AU - Tahir, Anam
N1 - Publisher Copyright: © 2021. Electronic Communications of the EASST.All Rights Reserved
PY - 2021/9/8
Y1 - 2021/9/8
N2 - Whereas adaptive video streaming for 2D video is well established and frequently used in streaming services, adaptation for emerging higher-dimensional content, such as point clouds, is still a research issue. Moreover, how to optimize resource usage in streaming services that support multiple content types of different dimensions and levels of interactivity has so far not been sufficiently studied. Learning-based approaches aim to optimize the streaming experience according to user needs. They predict quality metrics and try to find system parameters maximizing them given the current network conditions. With this paper, we show how to approach content and network adaption driven by Quality of Experience (QoE) for multi-dimensional content. We describe components required to create a system adapting multiple streams of different content types simultaneously, identify research gaps and propose potential next steps.
AB - Whereas adaptive video streaming for 2D video is well established and frequently used in streaming services, adaptation for emerging higher-dimensional content, such as point clouds, is still a research issue. Moreover, how to optimize resource usage in streaming services that support multiple content types of different dimensions and levels of interactivity has so far not been sufficiently studied. Learning-based approaches aim to optimize the streaming experience according to user needs. They predict quality metrics and try to find system parameters maximizing them given the current network conditions. With this paper, we show how to approach content and network adaption driven by Quality of Experience (QoE) for multi-dimensional content. We describe components required to create a system adapting multiple streams of different content types simultaneously, identify research gaps and propose potential next steps.
KW - In-Network Processing
KW - Multimedia Streaming
KW - Quality Of Experience
KW - Reinforcement Learning
UR - http://www.scopus.com/inward/record.url?scp=85120308819&partnerID=8YFLogxK
U2 - 10.14279/TUJ.ECEASST.80.1167
DO - 10.14279/TUJ.ECEASST.80.1167
M3 - Article
VL - 80
SP - 1
EP - 15
JO - Electronic Communications of the EASST
JF - Electronic Communications of the EASST
ER -