Fabian Poignée M. Sc.

2021

1.
Supervisor: Poignée, F.: Simulating Group-based Communication with Omnet++, (2021).
[ BibTeX ] [ EndNote ]
 
@mastersthesis{info3-praktikum-2021-10, author = {Supervisor: Poignée, Fabian}, keywords = {sys:hidden:praktikum myown sys:hidden:unassigned sys:hidden:supervisor:fabian.poignée}, school = {University of Würzburg}, title = {Simulating Group-based Communication with Omnet++}, year = 2021 }
%0 Thesis %1 info3-praktikum-2021-10 %A Supervisor: Poignée, Fabian %D 2021 %T Simulating Group-based Communication with Omnet++
2.
Loh, F., Poignée, F., Wamser, F., Leidinger, F., Hoßfeld, T.: Uplink vs. Downlink: Machine Learning-Based Quality Prediction for HTTP Adaptive Video Streaming. Sensors. 21, 4172 (2021).
[ Abstract ] [ BibTeX ] [ EndNote ]
 
Streaming video is responsible for the bulk of Internet traffic these days. For this reason, Internet providers and network operators try to make predictions and assessments about the streaming quality for an end user. Current monitoring solutions are based on a variety of different machine learning approaches. The challenge for providers and operators nowadays is that existing approaches require large amounts of data. In this work, the most relevant quality of experience metrics, i.e., the initial playback delay, the video streaming quality, video quality changes, and video rebuffering events, are examined using a voluminous data set of more than 13,000 YouTube video streaming runs that were collected with the native YouTube mobile app. Three Machine Learning models are developed and compared to estimate playback behavior based on uplink request information. The main focus has been on developing a lightweight approach using as few features and as little data as possible, while maintaining state-of-the-art performance.
@article{info3-article-2021-3, abstract = {Streaming video is responsible for the bulk of Internet traffic these days. For this reason, Internet providers and network operators try to make predictions and assessments about the streaming quality for an end user. Current monitoring solutions are based on a variety of different machine learning approaches. The challenge for providers and operators nowadays is that existing approaches require large amounts of data. In this work, the most relevant quality of experience metrics, i.e., the initial playback delay, the video streaming quality, video quality changes, and video rebuffering events, are examined using a voluminous data set of more than 13,000 YouTube video streaming runs that were collected with the native YouTube mobile app. Three Machine Learning models are developed and compared to estimate playback behavior based on uplink request information. The main focus has been on developing a lightweight approach using as few features and as little data as possible, while maintaining state-of-the-art performance.}, author = {Loh, Frank and Poignée, Fabian and Wamser, Florian and Leidinger, Ferdinand and Hoßfeld, Tobias}, journal = {Sensors}, keywords = {youtube myown sys:hidden:article can}, number = 12, pages = 4172, title = {Uplink vs. Downlink: Machine Learning-Based Quality Prediction for HTTP Adaptive Video Streaming}, volume = 21, year = 2021 }
%0 Journal Article %1 info3-article-2021-3 %A Loh, Frank %A Poignée, Fabian %A Wamser, Florian %A Leidinger, Ferdinand %A Hoßfeld, Tobias %D 2021 %J Sensors %N 12 %P 4172 %T Uplink vs. Downlink: Machine Learning-Based Quality Prediction for HTTP Adaptive Video Streaming %V 21 %X Streaming video is responsible for the bulk of Internet traffic these days. For this reason, Internet providers and network operators try to make predictions and assessments about the streaming quality for an end user. Current monitoring solutions are based on a variety of different machine learning approaches. The challenge for providers and operators nowadays is that existing approaches require large amounts of data. In this work, the most relevant quality of experience metrics, i.e., the initial playback delay, the video streaming quality, video quality changes, and video rebuffering events, are examined using a voluminous data set of more than 13,000 YouTube video streaming runs that were collected with the native YouTube mobile app. Three Machine Learning models are developed and compared to estimate playback behavior based on uplink request information. The main focus has been on developing a lightweight approach using as few features and as little data as possible, while maintaining state-of-the-art performance.

2020

1.
Poignée, F.: Machine Learning Approach to Predict Video Streaming Behavior at Network Layer, (2020).
[ BibTeX ] [ EndNote ]
 
@mastersthesis{info3-master-2020-15, author = {Poignée, Fabian}, keywords = {myown sys:hidden:master sys:hidden:completed sys:hidden:supervisor:frank.loh}, month = 9, school = {University of Würzburg}, title = {Machine Learning Approach to Predict Video Streaming Behavior at Network Layer}, year = 2020 }
%0 Thesis %1 info3-master-2020-15 %A Poignée, Fabian %D 2020 %T Machine Learning Approach to Predict Video Streaming Behavior at Network Layer

2018

1.
Poignée, F.: Influence of Tension on QoE in Video Streaming, (2018).
[ BibTeX ] [ EndNote ]
 
@mastersthesis{info3-bachelor-2018-4, author = {Poignée, Fabian}, keywords = {myown sys:hidden:supervisor:anika.schwind sys:hidden:completed sys:hidden:bachelor can sys:hidden:supervisor:frank.loh}, month = 4, school = {University of Würzburg}, title = {Influence of Tension on QoE in Video Streaming}, year = 2018 }
%0 Thesis %1 info3-bachelor-2018-4 %A Poignée, Fabian %D 2018 %T Influence of Tension on QoE in Video Streaming