Video streaming datasets: Improving the Transfer of Machine Learning-Based Video QoE Estimation Across Diverse Networks

Skup podataka

• Autor: Irena Oršolić; University of Zagreb, Faculty of Electrical Engineering and Computing
• Autor: Michael Seufert; University of Augsburg
• Znanstveno / umjetničko područje, polje i grana: TEHNIČKE ZNANOSTI; Elektrotehnika; Telekomunikacije i informatika

Sažetak (engleski)

The datasets in this repository consist of video on demand streaming data collected at two locations (Würzburg, Germany and Zagreb, Croatia) and across two years (2020 and 2021). We refer to the datasets by using the following labels: Wue_2020, Wue_2021, Zag_2020, Zag_2021. The data includes network traffic features used to estimate Quality of Experience (QoE) and Key Performance Indicators (KPI) of video streaming sessions using machine learning. The traffic features are annotated with QoE/KPI classes, with samples considered both on a session-level (per-video) and in real-time fashion (per-second). The datasets are collected for and presented in the journal article entitled "Improving the Transfer of Machine Learning-Based Video QoE Estimation Across Diverse Networks", authored by Michael Seufert and Irena Oršolić, published in IEEE Transactions on Network and Service Management in 2023.

• Metodologija (engleski): The measurements were conducted using a browser automation tool, that initiated the streaming of predefined videos from a popular video streaming service. The set of 2000 distinct videos was streamed to a laptop at two different locations, both in 2020 and 2021, with and without using an ad-blocking plugin, under 3 different bandwidth constraints (unlimited, 1Mbps, and stochastic). Given all the combinations of the conditions, this results in 48000 streamed videos. After eliminating log inconsistencies, the dataset published in this repository includes 8833 videos from Wue_2020, 9410 from Zag_2020, 5310 from Wue_2021, and 6640 from Zag_2021.
• Ključne riječi (engleski): video streaming; QoE estimation; Quality of Experience; machine learning
• Jezik: engleski
• URN:NBN: urn:nbn:hr:168:227338
• Datum objave: 2023-10-08
• Verzija: 1.0
• Geolokacija: Zagreb, Hrvatska
• Geolokacija: Würzburg, Njemačka
• Projekt: Šifra: IP-2019-04-9793; Naziv (hrvatski): Modeliranje i praćenje iskustvene kvalitete imerzivnih višemedijskih usluga u 5G mrežama; Naziv (engleski): Modeling and Monitoring QoE for Immersive 5G-Enabled Multimedia Services; Kratica: Q-MERSIVE; Voditelj: Lea Skorin-Kapov; Pravna nadležnost: Hrvatska; Financijer: HRZZ; Linija financiranja: IP
• Izdavač: Fakultet elektrotehnike i računarstva; Faculty of Electrical Engineering and Computing
• Prava pristupa: Otvoreni pristup
• Datum i vrijeme pohrane: 2023-10-08 18:08:15