Please use this identifier to cite or link to this item:
Title: Improving Quality of Experience in multimedia Internet of Things leveraging machine learning on big data
Authors: Huang, Xiaohong
Xie, Kun
Leng, Supeng
Yuan, Tingting
Ma, Maode
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2018
Source: Huang, X., Xie, K., Leng, S., Yuan, T., & Ma, M. (2018). Improving Quality of Experience in multimedia Internet of Things leveraging machine learning on big data. Future Generation Computer Systems, 86, 1413-1423. doi:10.1016/j.future.2018.02.046
Journal: Future Generation Computer Systems
Abstract: With rapid evolution of the Internet of Things (IoT) applications on multimedia, there is an urgent need to enhance the satisfaction level of Multimedia IoT (MIoT) network users. An important and unsolved problem is automatic optimization of Quality of Experience (QoE) through collecting/managing/processing various data from MIoT network. In this paper, we propose an MIoT QoE optimization mechanism leveraging data fusion technology, called QoE optimization via Data Fusion (QoEDF). QoEDF consists of two steps. Firstly, a multimodal data fusion approach is proposed to build a QoE mapping between the uncontrollable user data with the controllable network-related system data. Secondly, an automatic QoE optimization model is built taking fused results, which is different from the traditional way. QoEDF is able to adjust network-related system data automatically so as to achieve optimized user satisfaction. Simulation results show that QoEDF will lead to significant improvements in QoE level as well as be adaptable to dynamic network changes.
ISSN: 0167-739X
DOI: 10.1016/j.future.2018.02.046
Rights: © 2018 Elsevier B.V. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:EEE Journal Articles

Citations 20

Updated on Mar 10, 2021

Citations 20

Updated on Mar 7, 2021

Page view(s)

Updated on Jan 17, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.