MIRAGE-Video
Traffic of 14 video mobile apps with associated ground truth, collected between June 2019 and March 2020.
MIRAGE-Video is a human-generated dataset for mobile traffic analysis with associated ground truth, having the goal of advancing the state of the art in mobile app traffic analysis.
It takes into consideration the traffic generated by more than 280 experimenters using 14 video mobile apps via 3 devices. The dataset was collected during the time period June 2019 – March 2020.
Hosted on Zenodo ↗ · DOI 10.5281/zenodo.23158634
- Experimenters
- 280+
- Apps
- 14
- Devices
- 3
- Period
- Jun 2019 – Mar 2020
Apps
14 apps in the downloadable release.
-
DiscoveryVR
com.discovery.DiscoveryVRGoogle Play ↗ -
Facebookcom.facebook.katanaGoogle Play ↗ -
FulldiveVRin.fulldive.shellGoogle Play ↗ -
Instagramcom.instagram.androidGoogle Play ↗ -
Messengercom.facebook.orcaGoogle Play ↗ -
Netflixcom.netflix.mediaclientGoogle Play ↗ -
Prime Videocom.amazon.avod.thirdpartyclientGoogle Play ↗ -
Skypecom.skype.raiderGoogle Play ↗ -
Snapchatcom.snapchat.androidGoogle Play ↗ -
TikTokcom.zhiliaoapp.musicallyGoogle Play ↗ -
VR Roller Coaster 360com.coaster.roller.vrGoogle Play ↗ -
WhatsAppcom.whatsappGoogle Play ↗ -
Youtubecom.google.android.youtubeGoogle Play ↗ -
Zoomus.zoom.videomeetings
How to cite
If you use MIRAGE-Video for scientific papers, academic lectures, project reports or technical documents, please help us increase its impact by citing:
Antonio Montieri, Giampaolo Bovenzi, Giuseppe Aceto, Domenico Ciuonzo, Valerio Persico, Antonio Pescapè, “Packet-level prediction of mobile-app traffic using multitask Deep Learning”, Computer Networks, Volume 200, 2021.
To cite the dataset itself:
Montieri, A., Bovenzi, G., Aceto, G., Ciuonzo, D., Persico, V., & Pescapè, A. (2026). MIRAGE-Video [Data set]. Zenodo. https://doi.org/10.5281/zenodo.23158634