Online playtime prediction for cognitive video streaming
Document Type
Conference Proceeding
Publication Date
9-14-2015
Publication Title
2015 18th International Conference on Information Fusion, Fusion 2015
First Page
1886
Keywords
human factors, internet video, machine learning, mean opinion score (MOS), nearest neighbor classification, neural networks, quality of experience (QoE), survival models, video quality metrics, Video quality of service (QoS)
Last Page
1891
Abstract
In this paper, we consider the problem of cognitive video streaming in video on demand (VoD) services. The focus lies on quantities that are indicative of the quality of experience (QoE) of the subscriber, such as playtime ratio, probability of return, probability of replay and startup time. Especially, in this paper, we develop and evaluate a playtime prediction tool. For this purpose, the applicability of different machine learning algorithms such as k-nearest neighbor, neural network regression, and survival models is investigated; then, we develop an approach to identify the most relevant factors that contributed to the prediction. The proposed approaches are tested by means of a data set provided by Comcast.
ISBN
9780982443866
Recommended Citation
Pasupuleti, D.; Mannaru, P.; Balasingam, B.; Baum, M.; Pattipati, K.; Willett, P.; Lintz, C.; Commeau, G.; Dorigo, F.; and Fahrny, J.. (2015). Online playtime prediction for cognitive video streaming. 2015 18th International Conference on Information Fusion, Fusion 2015, 1886-1891.
https://scholar.uwindsor.ca/computersciencepub/141