Use of machine learning for rate adaptation in MPEG-DASH for quality of experience improvement

Research output: Chapter in Book/Report/Conference proceedingConference contribution

44 Downloads (Pure)

Abstract

Dynamic adaptive video streaming over HTTP (DASH) has been developed as one of the most suitable technologies for the transmission of live and on-demand audio and video content over any IP network. In this work, we propose a machine learning-based method for selecting the optimal target quality, in terms of bitrate, for video streaming through an MPEG-DASH server. The proposed method takes into consideration both the bandwidth availability and the client’s buffer state, as well as the bitrate of each video segment, in order to choose the best available quality/bitrate. The primary purpose of using machine learning for the adaptation is to let clients know/learn about the environment in a supervised manner. By doing this, the efficiency of the rate adaptation can be improved, thus leading to better requests for video representations. Run-time complexity would be minimized, thus improving QoE. The experimental evaluation of the proposed approach showed that the optimal target quality could be predicted with an accuracy of 79%, demonstrating its potential.
Original languageEnglish
Title of host publication5th International Symposium on Data Mining Applications (SDMA 2018)
EditorsMamdouh Alenezi, Basit Qureshi
PublisherSpringer
Pages3-11
Number of pages9
ISBN (Electronic)978-3-319-78753-4
ISBN (Print)978-3-319-78752-7
DOIs
Publication statusE-pub ahead of print - 29 Mar 2018
Event5th International Symposium on Data Mining Applications - Prince Sultan University, Riyadh, Saudi Arabia
Duration: 21 Mar 201822 Mar 2018
http://info.psu.edu.sa/ResearchEvents/SDMA2018/

Publication series

NameAdvances in Intelligent Systems and Computing
PublisherSpringer
Volume753
ISSN (Electronic)2194-5357

Conference

Conference5th International Symposium on Data Mining Applications
Abbreviated titleSDMA2018
CountrySaudi Arabia
CityRiyadh
Period21/03/1822/03/18
Internet address

Fingerprint

HTTP
Video streaming
Learning systems
Servers
Availability
Bandwidth

Cite this

Alzahrani, I., Ramzan, N., Katsigiannis, S., & Amira, A. (2018). Use of machine learning for rate adaptation in MPEG-DASH for quality of experience improvement. In M. Alenezi, & B. Qureshi (Eds.), 5th International Symposium on Data Mining Applications (SDMA 2018) (pp. 3-11). (Advances in Intelligent Systems and Computing; Vol. 753). Springer. https://doi.org/10.1007/978-3-319-78753-4_1
Alzahrani, Ibrahim ; Ramzan, Naeem ; Katsigiannis, Stamos ; Amira, Abbes. / Use of machine learning for rate adaptation in MPEG-DASH for quality of experience improvement. 5th International Symposium on Data Mining Applications (SDMA 2018). editor / Mamdouh Alenezi ; Basit Qureshi. Springer, 2018. pp. 3-11 (Advances in Intelligent Systems and Computing).
@inproceedings{183ae8183d5e4b1da10ab8f243e0aeb8,
title = "Use of machine learning for rate adaptation in MPEG-DASH for quality of experience improvement",
abstract = "Dynamic adaptive video streaming over HTTP (DASH) has been developed as one of the most suitable technologies for the transmission of live and on-demand audio and video content over any IP network. In this work, we propose a machine learning-based method for selecting the optimal target quality, in terms of bitrate, for video streaming through an MPEG-DASH server. The proposed method takes into consideration both the bandwidth availability and the client’s buffer state, as well as the bitrate of each video segment, in order to choose the best available quality/bitrate. The primary purpose of using machine learning for the adaptation is to let clients know/learn about the environment in a supervised manner. By doing this, the efficiency of the rate adaptation can be improved, thus leading to better requests for video representations. Run-time complexity would be minimized, thus improving QoE. The experimental evaluation of the proposed approach showed that the optimal target quality could be predicted with an accuracy of 79{\%}, demonstrating its potential.",
author = "Ibrahim Alzahrani and Naeem Ramzan and Stamos Katsigiannis and Abbes Amira",
year = "2018",
month = "3",
day = "29",
doi = "10.1007/978-3-319-78753-4_1",
language = "English",
isbn = "978-3-319-78752-7",
series = "Advances in Intelligent Systems and Computing",
publisher = "Springer",
pages = "3--11",
editor = "Alenezi, {Mamdouh } and Basit Qureshi",
booktitle = "5th International Symposium on Data Mining Applications (SDMA 2018)",
address = "United States",

}

Alzahrani, I, Ramzan, N, Katsigiannis, S & Amira, A 2018, Use of machine learning for rate adaptation in MPEG-DASH for quality of experience improvement. in M Alenezi & B Qureshi (eds), 5th International Symposium on Data Mining Applications (SDMA 2018). Advances in Intelligent Systems and Computing, vol. 753, Springer, pp. 3-11, 5th International Symposium on Data Mining Applications, Riyadh, Saudi Arabia, 21/03/18. https://doi.org/10.1007/978-3-319-78753-4_1

Use of machine learning for rate adaptation in MPEG-DASH for quality of experience improvement. / Alzahrani, Ibrahim; Ramzan, Naeem; Katsigiannis, Stamos; Amira, Abbes.

5th International Symposium on Data Mining Applications (SDMA 2018). ed. / Mamdouh Alenezi; Basit Qureshi. Springer, 2018. p. 3-11 (Advances in Intelligent Systems and Computing; Vol. 753).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Use of machine learning for rate adaptation in MPEG-DASH for quality of experience improvement

AU - Alzahrani, Ibrahim

AU - Ramzan, Naeem

AU - Katsigiannis, Stamos

AU - Amira, Abbes

PY - 2018/3/29

Y1 - 2018/3/29

N2 - Dynamic adaptive video streaming over HTTP (DASH) has been developed as one of the most suitable technologies for the transmission of live and on-demand audio and video content over any IP network. In this work, we propose a machine learning-based method for selecting the optimal target quality, in terms of bitrate, for video streaming through an MPEG-DASH server. The proposed method takes into consideration both the bandwidth availability and the client’s buffer state, as well as the bitrate of each video segment, in order to choose the best available quality/bitrate. The primary purpose of using machine learning for the adaptation is to let clients know/learn about the environment in a supervised manner. By doing this, the efficiency of the rate adaptation can be improved, thus leading to better requests for video representations. Run-time complexity would be minimized, thus improving QoE. The experimental evaluation of the proposed approach showed that the optimal target quality could be predicted with an accuracy of 79%, demonstrating its potential.

AB - Dynamic adaptive video streaming over HTTP (DASH) has been developed as one of the most suitable technologies for the transmission of live and on-demand audio and video content over any IP network. In this work, we propose a machine learning-based method for selecting the optimal target quality, in terms of bitrate, for video streaming through an MPEG-DASH server. The proposed method takes into consideration both the bandwidth availability and the client’s buffer state, as well as the bitrate of each video segment, in order to choose the best available quality/bitrate. The primary purpose of using machine learning for the adaptation is to let clients know/learn about the environment in a supervised manner. By doing this, the efficiency of the rate adaptation can be improved, thus leading to better requests for video representations. Run-time complexity would be minimized, thus improving QoE. The experimental evaluation of the proposed approach showed that the optimal target quality could be predicted with an accuracy of 79%, demonstrating its potential.

U2 - 10.1007/978-3-319-78753-4_1

DO - 10.1007/978-3-319-78753-4_1

M3 - Conference contribution

SN - 978-3-319-78752-7

T3 - Advances in Intelligent Systems and Computing

SP - 3

EP - 11

BT - 5th International Symposium on Data Mining Applications (SDMA 2018)

A2 - Alenezi, Mamdouh

A2 - Qureshi, Basit

PB - Springer

ER -

Alzahrani I, Ramzan N, Katsigiannis S, Amira A. Use of machine learning for rate adaptation in MPEG-DASH for quality of experience improvement. In Alenezi M, Qureshi B, editors, 5th International Symposium on Data Mining Applications (SDMA 2018). Springer. 2018. p. 3-11. (Advances in Intelligent Systems and Computing). https://doi.org/10.1007/978-3-319-78753-4_1