{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:51:31Z","timestamp":1785336691194,"version":"3.55.0"},"reference-count":52,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2021,6,17]],"date-time":"2021-06-17T00:00:00Z","timestamp":1623888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>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.<\/jats:p>","DOI":"10.3390\/s21124172","type":"journal-article","created":{"date-parts":[[2021,6,17]],"date-time":"2021-06-17T21:29:16Z","timestamp":1623965356000},"page":"4172","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":29,"title":["Uplink vs. Downlink: Machine Learning-Based Quality Prediction for HTTP Adaptive Video Streaming"],"prefix":"10.3390","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7410-0790","authenticated-orcid":false,"given":"Frank","family":"Loh","sequence":"first","affiliation":[{"name":"Institute of Computer Science, University of W\u00fcrzburg, 97074 W\u00fcrzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4972-2410","authenticated-orcid":false,"given":"Fabian","family":"Poign\u00e9e","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of W\u00fcrzburg, 97074 W\u00fcrzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0356-6291","authenticated-orcid":false,"given":"Florian","family":"Wamser","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of W\u00fcrzburg, 97074 W\u00fcrzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ferdinand","family":"Leidinger","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of W\u00fcrzburg, 97074 W\u00fcrzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tobias","family":"Ho\u00dffeld","sequence":"additional","affiliation":[{"name":"Institute of Computer Science, University of W\u00fcrzburg, 97074 W\u00fcrzburg, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,17]]},"reference":[{"key":"ref_1","unstructured":"Sandvine (2021, June 14). The Global Internet Phenomena Report COVID-19 Spotlight, Available online: https:\/\/www.sandvine.com\/covid-internet-spotlight-report."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1016\/j.comnet.2016.03.020","article-title":"Modeling the YouTube stack: From packets to quality of experience","volume":"109","author":"Wamser","year":"2016","journal-title":"Comput. Netw."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"469","DOI":"10.1109\/COMST.2014.2360940","article-title":"A survey on quality of experience of HTTP adaptive streaming","volume":"17","author":"Seufert","year":"2014","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Ho\u00dffeld, T., Egger, S., Schatz, R., Fiedler, M., Masuch, K., and Lorentzen, C. (2012, January 5\u20137). Initial delay vs. interruptions: Between the devil and the deep blue sea. Proceedings of the 4th International Workshop on Quality of Multimedia Experience (QoMEX), Melbourne, Australia.","DOI":"10.1109\/QoMEX.2012.6263849"},{"key":"ref_5","unstructured":"ABC-News (2021, June 14). YouTube Throttling Streaming Quality Globally as Coronavirus Forces People Indoors, Available online: https:\/\/abcnews.go.com\/Technology\/netflix-youtube-throttle-streaming-quality-europe-coronavirus-forces\/story?id=69754458."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Wamser, F., Staehle, D., Prokopec, J., Maeder, A., and Tran-Gia, P. (2012, January 4\u20137). Utilizing buffered YouTube playtime for QoE-oriented scheduling in OFDMA networks. Proceedings of the 24th International Teletraffic Congress (ITC), Cracow, Poland.","DOI":"10.1002\/ett.2636"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Tsilimantos, D., Karagkioules, T., Nogales-G\u00f3mez, A., and Valentin, S. (2017, January 21\u201325). Traffic profiling for mobile video streaming. Proceedings of the 2017 IEEE International Conference on Communications (ICC), Paris, France.","DOI":"10.1109\/ICC.2017.7996603"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Loh, F., Wamser, F., Moldovan, C., Zeidler, B., Ho\u00dffeld, T., Tsilimantos, D., and Valentin, S. (2019, January 18\u201321). From click to playback: A dataset to study the response time of mobile YouTube. Proceedings of the 10th ACM Multimedia Systems Conference, Amherst, MA, USA.","DOI":"10.1145\/3304109.3325819"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Qi, Y., and Dai, M. (2006, January 18\u201320). The effect of frame freezing and frame skipping on video quality. Proceedings of the International Conference on Intelligent Information Hiding and Multimedia, Pasadena, CA, USA.","DOI":"10.1109\/IIH-MSP.2006.265032"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Mazhar, M.H., and Shafiq, Z. (2018, January 16\u201319). Real-time video quality of experience monitoring for https and quic. Proceedings of the IEEE Conference on Computer Communications (INFOCOM), Honolulu, HI, USA.","DOI":"10.1109\/INFOCOM.2018.8486321"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"2007","DOI":"10.1109\/TNSM.2020.3036497","article-title":"ViCrypt to the Rescue: Real-Time, Machine-Learning-Driven Video-QoE Monitoring for Encrypted Streaming Traffic","volume":"17","author":"Wassermann","year":"2020","journal-title":"IEEE Trans. Netw. Serv. Manag. (TNSM)"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"74691","DOI":"10.1109\/ACCESS.2020.2988735","article-title":"A Framework for in-Network QoE Monitoring of Encrypted Video Streaming","volume":"8","author":"Orsolic","year":"2020","journal-title":"IEEE Access"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3366704","article-title":"Inferring streaming video quality from encrypted traffic: Practical models and deployment experience","volume":"3","author":"Bronzino","year":"2019","journal-title":"Proc. ACM Meas. Anal. Comput. Syst."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Dimopoulos, G., Leontiadis, I., Barlet-Ros, P., and Papagiannaki, K. (2016, January 14\u201316). Measuring video QoE from encrypted traffic. Proceedings of the 2016 Internet Measurement Conference, Santa Monica, CA, USA.","DOI":"10.1145\/2987443.2987459"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Shen, M., Zhang, J., Xu, K., Zhu, L., Liu, J., and Du, X. (2020, January 15\u201317). DeepQoE: Real-time Measurement of Video QoE from Encrypted Traffic with Deep Learning. Proceedings of the IEEE\/ACM 28th International Symposium on Quality of Service (IWQoS), Hang Zhou, China.","DOI":"10.1109\/IWQoS49365.2020.9212897"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"110","DOI":"10.1109\/MCOM.2018.1701156","article-title":"Deep learning model for multimedia quality of experience prediction based on network flow packets","volume":"56","author":"Carro","year":"2018","journal-title":"IEEE Commun. Mag."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Mangla, T., Halepovic, E., Ammar, M., and Zegura, E. (2018, January 26\u201329). emimic: Estimating http-based video qoe metrics from encrypted network traffic. Proceedings of the Network Traffic Measurement and Analysis Conference (TMA), Vienna, Austria.","DOI":"10.23919\/TMA.2018.8506519"},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3394498","article-title":"Requet: Real-time QoE metric detection for encrypted YouTube traffic","volume":"16","author":"Gutterman","year":"2020","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Mok, R.K., Chan, E.W., and Chang, R.K. (2011, January 23\u201327). Measuring the quality of experience of HTTP video streaming. Proceedings of the 12th IFIP\/IEEE International Symposium on Integrated Network Management (IM) and Workshops, Dublin, Ireland.","DOI":"10.1109\/INM.2011.5990550"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Karagkioules, T., Tsilimantos, D., Valentin, S., Wamser, F., Zeidler, B., Seufert, M., Loh, F., and Tran-Gia, P. (2018, January 26\u201329). A public dataset for youtube\u2019s mobile streaming client. Proceedings of the Network Traffic Measurement and Analysis Conference (TMA), Vienna, Austria.","DOI":"10.23919\/TMA.2018.8506503"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1984","DOI":"10.1109\/TNET.2014.2354262","article-title":"Measurement study of Netflix, Hulu, and a tale of three CDNs","volume":"23","author":"Adhikari","year":"2014","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Loh, F., Vomhoff, V., Wamser, F., Metzger, F., and Ho\u00dffeld, T. (2019, January 21). Traffic Measurement Study on Video Streaming with the Amazon Echo Show. Proceedings of the 4th Internet-QoE Workshop on QoE-based Analysis and Management of Data Communication Networks, Los Cabos, Mexico.","DOI":"10.1145\/3349611.3355543"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Reed, A., and Kranch, M. (2017, January 22\u201324). Identifying https-protected netflix videos in real-time. Proceedings of the Seventh ACM on Conference on Data and Application Security and Privacy, Scottsdale, AZ, USA.","DOI":"10.1145\/3029806.3029821"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Li, F., Chung, J.W., and Claypool, M. (2018, January 12\u201315). Silhouette: Identifying youtube video flows from encrypted traffic. Proceedings of the 28th ACM SIGMM Workshop on Network and Operating Systems Support for Digital Audio and Video, Amsterdam, The Netherlands.","DOI":"10.1145\/3210445.3210448"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1109\/SURV.2008.080406","article-title":"A survey of techniques for internet traffic classification using machine learning","volume":"10","author":"Nguyen","year":"2008","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Loh, F., Wamser, F., Moldovan, C., Zeidler, B., Tsilimantos, D., Valentin, S., and Ho\u00dffeld, T. (2020, January 20\u201324). Is the Uplink Enough? Estimating Video Stalls from Encrypted Network Traffic. Proceedings of the NOMS IEEE\/IFIP Network Operations and Management Symposium, Budapest, Hungary.","DOI":"10.1109\/NOMS47738.2020.9110267"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Schatz, R., Ho\u00dffeld, T., and Casas, P. (2012, January 4\u20136). Passive youtube QoE monitoring for ISPs. Proceedings of the 6th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing, Palermo, Italy.","DOI":"10.1109\/IMIS.2012.12"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Dimopoulos, G., Barlet-Ros, P., and Sanjuas-Cuxart, J. (2013, January 14\u201318). Analysis of YouTube user experience from passive measurements. Proceedings of the 9th International Conference on Network and Service Management (CNSM), Zurich, Switzerland.","DOI":"10.1109\/CNSM.2013.6727845"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"638","DOI":"10.1109\/TNET.2003.815292","article-title":"Modeling full-length video using Markov-modulated Gamma-based framework","volume":"11","author":"Sarkar","year":"2003","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"1778","DOI":"10.1109\/SURV.2013.010413.00071","article-title":"A survey of VBR video traffic models","volume":"15","author":"Tanwir","year":"2013","journal-title":"IEEE Commun. Surv. Tutor."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Loh, F., Poign\u00e9e, F., Wamser, F., Leidinger, F., and Ho\u00dffeld, F. (2021, June 17). Dataset for Uplink vs. Downlink: Machine Learning-Based Quality Prediction for HTTP Adaptive Video Streaming. Available online: https:\/\/zenodo.org\/record\/4890859#.YLZa0WYzb0o.","DOI":"10.3390\/s21124172"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Krunz, M.M., and Makowski, A.M. (1998). Modeling video traffic using M\/G\/inf input processes: A compromise between Markovian and LRD models. IEEE J. Sel. Areas Commun.","DOI":"10.1109\/49.700909"},{"key":"ref_33","unstructured":"Heyman, D.P., and Sobel, M.J. (1982). Stochastic Models in Operations Research. 1. Stochastic Processes and Operating Characteristics, McGraw-Hill."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1287\/opre.9.3.383","article-title":"A proof for the queuing formula: L = \u03bb W","volume":"9","author":"Little","year":"1961","journal-title":"Oper. Res."},{"key":"ref_35","unstructured":"Google (2021, March 03). Google Security Blog. Available online: https:\/\/security.googleblog.com\/2016\/08\/adding-youtube-and-calendar-to-https.html."},{"key":"ref_36","unstructured":"Wamser, F., Seufert, M., Casas, P., Irmer, R., Tran-Gia, P., and Schatz, R. (July, January 29). YoMoApp: A tool for analyzing QoE of YouTube HTTP adaptive streaming in mobile networks. Proceedings of the European Conference on Networks and Communications (EuCNC), Paris, France."},{"key":"ref_37","doi-asserted-by":"crossref","unstructured":"Seufert, M., Zeidler, B., Wamser, F., Karagkioules, T., Tsilimantos, D., Loh, F., Tran-Gia, P., and Valentin, S. (2018, January 26\u201329). A wrapper for automatic measurements with YouTube\u2019s native Android app. Proceedings of the Network Traffic Measurement and Analysis Conference (TMA), Vienna, Austria.","DOI":"10.23919\/TMA.2018.8506488"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"2177","DOI":"10.1109\/LCOMM.2016.2601087","article-title":"HTTP\/2-Based Adaptive Streaming of HEVC Video Over 4G\/LTE Networks","volume":"20","author":"Hooft","year":"2016","journal-title":"IEEE Commun. Lett."},{"key":"ref_39","unstructured":"(2020, May 04). Dataset: HSDPA-Bandwidth Logs for Mobile HTTP Streaming Scenarios. Available online: http:\/\/home.ifi.uio.no\/paalh\/dataset\/hsdpa-tcp-logs\/."},{"key":"ref_40","unstructured":"DeviceAtlas (2021, March 06). Most Used Smartphone Screen Resolutions in 2019. Available online: https:\/\/deviceatlas.com\/blog\/most-used-smartphone-screen-resolutions."},{"key":"ref_41","unstructured":"Ni, P., Eg, R., Eichhorn, A., Griwodz, C., and Halvorsen, P. (December, January 28). Flicker effects in adaptive video streaming to handheld devices. Proceedings of the 19th ACM international conference on Multimedia, Scottsdale, AZ, USA."},{"key":"ref_42","unstructured":"Scikit-Learn (2021, March 01). Select K Best. Available online: https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.feature_selection.SelectKBest.html."},{"key":"ref_43","unstructured":"Keras-Tuner (2021, January 28). Keras Tuner Documentation. Available online: https:\/\/keras-team.github.io\/keras-tuner\/."},{"key":"ref_44","unstructured":"Scikit-Learn (2021, March 03). GridSearchCV. Available online: https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.model_selection.GridSearchCV.html."},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"22267","DOI":"10.1007\/s11042-017-4728-4","article-title":"A machine learning approach to classifying YouTube QoE based on encrypted network traffic","volume":"76","author":"Orsolic","year":"2017","journal-title":"Multimed. Tools Appl."},{"key":"ref_46","unstructured":"TensorFlow (2021, January 28). Tensorflow. Available online: https:\/\/www.tensorflow.org\/."},{"key":"ref_47","unstructured":"Scikit-Learn (2021, January 27). Sklearn StandardScaler. Available online: https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.preprocessing.StandardScaler.html."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1016\/0020-0190(76)90095-8","article-title":"Constructing optimal binary decision trees is NP-complete","volume":"5","author":"Laurent","year":"1976","journal-title":"Inf. Process. Lett."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Finamore, A., Mellia, M., Munaf\u00f2, M.M., Torres, R., and Rao, S.G. (2011, January 15\u201319). Youtube everywhere: Impact of device and infrastructure synergies on user experience. Proceedings of the ACM SIGCOMM Conference on Internet Measurement Conference, Toronto, ON, Canada.","DOI":"10.1145\/2068816.2068849"},{"key":"ref_50","doi-asserted-by":"crossref","unstructured":"Ho\u00dffeld, T., Moldovan, C., and Schwartz, C. (2015, January 11\u201315). To each according to their needs: Dimensioning video buffer for specific user profiles and behavior. Proceedings of the IFIP\/IEEE International Symposium on Integrated Network Management (IM), Ottawa, ON, Canada.","DOI":"10.1109\/INM.2015.7140476"},{"key":"ref_51","unstructured":"International Organization for Standardization (2021, March 04). ISO\/IEC 23009-1:2014, Available online: https:\/\/www.iso.org\/standard\/65274.html."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"30831","DOI":"10.1109\/ACCESS.2019.2901778","article-title":"Qoe modeling for HTTP adaptive video streaming\u2014A survey and open challenges","volume":"7","author":"Barman","year":"2019","journal-title":"IEEE Access"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4172\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:17:56Z","timestamp":1760163476000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/12\/4172"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,17]]},"references-count":52,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21124172"],"URL":"https:\/\/doi.org\/10.3390\/s21124172","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,17]]}}}