Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation

Doreid Ammar; Katrien De Moor; Lea Skorin-Kapov; Markus Fiedler; Poul E. Heegaard

doi:10.1109/LCN44214.2019.8990677

Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation

Doreid Ammar
, Katrien De Moor
, Lea Skorin-Kapov
, Markus Fiedler
, Poul E. Heegaard

EMLYON Business School
Norwegian University of Science and Technology
University of Zagreb, Faculty of Electrical Engineering and Computing
Blekinge Institute of Technology

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

13 Scopus citations

Abstract

We address the challenge faced by service providers in monitoring Quality of Experience (QoE) related metrics for WebRTC-based audiovisual communication services. By extracting features from various application-layer performance statistics, we explore the potential of using machine learning (ML) models to estimate perceivable quality impairments and to identify root causes. We argue that such performance-related data can be valuable and informative from a QoE assessment point of view, by allowing to identify the party/parties in a call that is/are experiencing quality impairments, and to trace the origins and causes of the problem. The paper includes case studies of multi-party videoconferencing that are established in a laboratory environment and exposed to various network disturbances and CPU limitations. Our results show that perceivable quality impairments in terms of video blockiness and audio distortions may be estimated with a high level of accuracy, thus proving the potential of exploiting ML models for automated QoE-driven monitoring and estimation of WebRTC performance.

Original language	English
Title of host publication	Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019
Editors	Karl Andersson, Hwee-Pink Tan, Sharief Oteafy
Publisher	IEEE Computer Society
Pages	406-413
Number of pages	8
ISBN (Electronic)	9781728110288
DOIs	https://doi.org/10.1109/LCN44214.2019.8990677
State	Published - Oct 2019
Externally published	Yes
Event	44th Annual IEEE Conference on Local Computer Networks, LCN 2019 - Osnabruck, Germany Duration: 14 Oct 2019 → 17 Oct 2019

Publication series

Name	Proceedings - Conference on Local Computer Networks, LCN
Volume	2019-October

Conference

Conference	44th Annual IEEE Conference on Local Computer Networks, LCN 2019
Country/Territory	Germany
City	Osnabruck
Period	14/10/19 → 17/10/19

Keywords

Quality of Experience (QoE)
WebRTC
audio distortion
machine learning
video-blockiness

Access to Document

10.1109/LCN44214.2019.8990677

Cite this

Ammar, D., Moor, K. D., Skorin-Kapov, L., Fiedler, M., & Heegaard, P. E. (2019). Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation. In K. Andersson, H.-P. Tan, & S. Oteafy (Eds.), Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019 (pp. 406-413). Article 8990677 (Proceedings - Conference on Local Computer Networks, LCN; Vol. 2019-October). IEEE Computer Society. https://doi.org/10.1109/LCN44214.2019.8990677

Ammar, Doreid ; Moor, Katrien De ; Skorin-Kapov, Lea et al. / Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation. Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019. editor / Karl Andersson ; Hwee-Pink Tan ; Sharief Oteafy. IEEE Computer Society, 2019. pp. 406-413 (Proceedings - Conference on Local Computer Networks, LCN).

@inproceedings{aea255a7ce85467fa45d130df8849c8c,

title = "Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation",

abstract = "We address the challenge faced by service providers in monitoring Quality of Experience (QoE) related metrics for WebRTC-based audiovisual communication services. By extracting features from various application-layer performance statistics, we explore the potential of using machine learning (ML) models to estimate perceivable quality impairments and to identify root causes. We argue that such performance-related data can be valuable and informative from a QoE assessment point of view, by allowing to identify the party/parties in a call that is/are experiencing quality impairments, and to trace the origins and causes of the problem. The paper includes case studies of multi-party videoconferencing that are established in a laboratory environment and exposed to various network disturbances and CPU limitations. Our results show that perceivable quality impairments in terms of video blockiness and audio distortions may be estimated with a high level of accuracy, thus proving the potential of exploiting ML models for automated QoE-driven monitoring and estimation of WebRTC performance.",

keywords = "Quality of Experience (QoE), WebRTC, audio distortion, machine learning, video-blockiness",

author = "Doreid Ammar and Moor, \{Katrien De\} and Lea Skorin-Kapov and Markus Fiedler and Heegaard, \{Poul E.\}",

note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 44th Annual IEEE Conference on Local Computer Networks, LCN 2019 ; Conference date: 14-10-2019 Through 17-10-2019",

year = "2019",

month = oct,

doi = "10.1109/LCN44214.2019.8990677",

language = "English",

series = "Proceedings - Conference on Local Computer Networks, LCN",

publisher = "IEEE Computer Society",

pages = "406--413",

editor = "Karl Andersson and Hwee-Pink Tan and Sharief Oteafy",

booktitle = "Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019",

}

Ammar, D, Moor, KD, Skorin-Kapov, L, Fiedler, M & Heegaard, PE 2019, Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation. in K Andersson, H-P Tan & S Oteafy (eds), Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019., 8990677, Proceedings - Conference on Local Computer Networks, LCN, vol. 2019-October, IEEE Computer Society, pp. 406-413, 44th Annual IEEE Conference on Local Computer Networks, LCN 2019, Osnabruck, Germany, 14/10/19. https://doi.org/10.1109/LCN44214.2019.8990677

Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation. / Ammar, Doreid; Moor, Katrien De; Skorin-Kapov, Lea et al.
Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019. ed. / Karl Andersson; Hwee-Pink Tan; Sharief Oteafy. IEEE Computer Society, 2019. p. 406-413 8990677 (Proceedings - Conference on Local Computer Networks, LCN; Vol. 2019-October).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation

AU - Ammar, Doreid

AU - Moor, Katrien De

AU - Skorin-Kapov, Lea

AU - Fiedler, Markus

AU - Heegaard, Poul E.

PY - 2019/10

Y1 - 2019/10

N2 - We address the challenge faced by service providers in monitoring Quality of Experience (QoE) related metrics for WebRTC-based audiovisual communication services. By extracting features from various application-layer performance statistics, we explore the potential of using machine learning (ML) models to estimate perceivable quality impairments and to identify root causes. We argue that such performance-related data can be valuable and informative from a QoE assessment point of view, by allowing to identify the party/parties in a call that is/are experiencing quality impairments, and to trace the origins and causes of the problem. The paper includes case studies of multi-party videoconferencing that are established in a laboratory environment and exposed to various network disturbances and CPU limitations. Our results show that perceivable quality impairments in terms of video blockiness and audio distortions may be estimated with a high level of accuracy, thus proving the potential of exploiting ML models for automated QoE-driven monitoring and estimation of WebRTC performance.

AB - We address the challenge faced by service providers in monitoring Quality of Experience (QoE) related metrics for WebRTC-based audiovisual communication services. By extracting features from various application-layer performance statistics, we explore the potential of using machine learning (ML) models to estimate perceivable quality impairments and to identify root causes. We argue that such performance-related data can be valuable and informative from a QoE assessment point of view, by allowing to identify the party/parties in a call that is/are experiencing quality impairments, and to trace the origins and causes of the problem. The paper includes case studies of multi-party videoconferencing that are established in a laboratory environment and exposed to various network disturbances and CPU limitations. Our results show that perceivable quality impairments in terms of video blockiness and audio distortions may be estimated with a high level of accuracy, thus proving the potential of exploiting ML models for automated QoE-driven monitoring and estimation of WebRTC performance.

KW - Quality of Experience (QoE)

KW - WebRTC

KW - audio distortion

KW - machine learning

KW - video-blockiness

UR - https://www.scopus.com/pages/publications/85080932466

U2 - 10.1109/LCN44214.2019.8990677

DO - 10.1109/LCN44214.2019.8990677

M3 - Conference contribution

AN - SCOPUS:85080932466

T3 - Proceedings - Conference on Local Computer Networks, LCN

SP - 406

EP - 413

BT - Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019

A2 - Andersson, Karl

A2 - Tan, Hwee-Pink

A2 - Oteafy, Sharief

PB - IEEE Computer Society

T2 - 44th Annual IEEE Conference on Local Computer Networks, LCN 2019

Y2 - 14 October 2019 through 17 October 2019

ER -

Ammar D, Moor KD, Skorin-Kapov L, Fiedler M, Heegaard PE. Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation. In Andersson K, Tan HP, Oteafy S, editors, Proceedings of the 44th Annual IEEE Conference on Local Computer Networks, LCN 2019. IEEE Computer Society. 2019. p. 406-413. 8990677. (Proceedings - Conference on Local Computer Networks, LCN). doi: 10.1109/LCN44214.2019.8990677

Exploring the Usefulness of Machine Learning in the Context of WebRTC Performance Estimation

Abstract

Publication series

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this