{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-machine-learning-based-optimal-has","title":"Towards Machine Learning-Based Optimal HAS","arxiv_id":"1808.08065","date":"2018-08-24","proceeding":null,"authors":["Christian Sieber","Korbinian Hagn","Christian Moldovan","Tobias Hoßfeld","Wolfgang Kellerer"],"abstract":"Mobile video consumption is increasing and sophisticated video quality\nadaptation strategies are required to deal with mobile throughput fluctuations.\nThese adaptation strategies have to keep the switching frequency low, the\naverage quality high and prevent stalling occurrences to ensure customer\nsatisfaction. This paper proposes a novel methodology for the design of machine\nlearning-based adaptation logics named HASBRAIN. Furthermore, the performance\nof a trained neural network against two algorithms from the literature is\nevaluated. We first use a modified existing optimization formulation to\ncalculate optimal adaptation paths with a minimum number of quality switches\nfor a wide range of videos and for challenging mobile throughput patterns.\nAfterwards we use the resulting optimal adaptation paths to train and compare\ndifferent machine learning models. The evaluation shows that an artificial\nneural network-based model can reach a high average quality with a low number\nof switches in the mobile scenario. The proposed methodology is general enough\nto be extended for further designs of machine learning-based algorithms and the\nprovided model can be deployed in on-demand streaming scenarios or be further\nrefined using reward-based mechanisms such as reinforcement learning. All\ntools, models and datasets created during the work are provided as open-source\nsoftware.","url_abs":"http://arxiv.org/abs/1808.08065v1","url_pdf":"http://arxiv.org/pdf/1808.08065v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"towards-machine-learning-based-optimal-has","repo_url":"https://github.com/csieber/hasbrain","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":null},{"paper_slug":"towards-machine-learning-based-optimal-has","repo_url":"https://github.com/csieber/pydashsim","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"machine-learning","task_name":"BIG-bench Machine Learning"},{"task_slug":"reinforcement-learning","task_name":"Reinforcement Learning"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}