Multimedia QoE evaluation / Xin Wei, Liang Zhou.
Wei, Xin, author.; Zhou, Liang, author.
2019
QA76.575 .W45 2019
Available Online

Linked e-resources

Linked Resource Online Access
Concurrent users Unlimited
Authorized users Authorized users
Document Delivery Supplied Can lend chapters, not whole ebooks

Details

Title Multimedia QoE evaluation / Xin Wei, Liang Zhou.
Author Wei, Xin, author.
ISBN 9783030233501 (electronic book)
3030233502 (electronic book)
3030233499
9783030233495
DOI https://doi.org/10.1007/978-3-030-23
Published Cham, Switzerland : Springer, [2019]
Language English
Description 1 online resource
Item Number 10.1007/978-3-030-23
Call Number QA76.575 .W45 2019
Dewey Decimal Classification 006.7
Summary This SpringerBrief discusses the most recent research in the field of multimedia QoE evaluation, with a focus on how to evaluate subjective multimedia QoE problems from objective techniques. Specifically, this SpringerBrief starts from a comprehensive overview of multimedia QoE definition, its influencing factors, traditional modeling and prediction methods. Subsequently, the authors introduce the procedure of multimedia service data collection, preprocessing and feature extractions. Then, describe several proposed multimedia QoE modeling and prediction techniques in details. Finally, the authors illustrate how to implement and demonstrate multimedia QoE evaluation in the big data platform. This SpringerBrief provides readers with a clear picture on how to make full use of multimedia service data to realize multimedia QoE evaluation. With the exponential growth of the Internet technologies, multimedia services become immensely popular. Users can enjoy multimedia services from operators or content providers by TV, computers and mobile devices. User experience is important for network operators and multimedia content providers. Traditional QoS (quality of service) can not entirely and accurately describe user experience. It is natural to research the quality of multimedia service from the users perspective, defined as multimedia quality of experience (QoE). However, multimedia QoE evaluation is difficult, because user experience is abstract and subjective, hard to quantify and measure. Moreover, the explosion of multimedia service and emergence of big data, all call for a new and better understanding of multimedia QoE. This SpringerBrief targets advanced-level students, professors and researchers studying and working in the fields of multimedia communications and information processing. Professionals, industry managers, and government research employees working in these same fields will also benefit from this SpringerBrief.
Bibliography, etc. Note Includes bibliographical references.
Access Note Access limited to authorized users.
Source of Description Description based on online resource; title from digital title page (viewed on September 10, 2019).
Added Author Zhou, Liang, author.
Series SpringerBriefs in computer science.
Available in Other Form Print version: 9783030233495
Linked Resources Online Access
Record Appears in Online Resources > Ebooks
All Resources
Intro; Preface; Acknowledgments; Contents; 1 Introduction; 1.1 Background; 1.2 Motivation; 1.3 Necessity; References; 2 Technical Premise; 2.1 Definition and Quantification; 2.1.1 Definition of Multimedia QoE; 2.1.2 Quantification of Multimedia QoE; 2.2 Influencing Factors; 2.2.1 System-Related Influencing Factors; 2.2.2 Context-Related Influencing Factors; 2.2.3 User-Related Influencing Factors; 2.3 Multimedia QoE Evaluation Based on Machine Learning; 2.3.1 Decision Tree; 2.3.2 Support Vector Machine; 2.3.3 Artificial Neural Network; 2.3.4 Bayesian Network; 2.3.5 Hidden Markov Model

2.3.6 Other Models2.4 Challenges; 2.5 Summary; References; 3 Multimedia Service Data Preprocessing and Feature Extraction; 3.1 Multimedia Service Data Collection and Preprocessing; 3.1.1 IPTV Service Dataset; 3.1.2 OTT Service Dataset; 3.1.3 Dataset Crawled Across the Web; 3.2 Feature Extraction for Subjective Influencing Factors; 3.2.1 User Viewing Time Ratio Calculation; 3.2.2 User Interest Inference; 3.2.3 User Type Classification; 3.2.4 User Behavior Analysis; 3.2.5 User Comment & Danmaku Parsing; 3.3 Summary; References; 4 Multimedia QoE Modeling and Prediction

4.1 Multimedia User Complaint Prediction for Imbalanced Dataset4.1.1 GMM-Based Oversampling Algorithm; 4.1.2 Decision Tree-Based Cost-Sensitive Algorithm; 4.2 Multimedia QoE Modeling and Prediction Based on NeuralNetworks; 4.2.1 Artificial Neural Networks (ANN); 4.2.2 LSTM-Attention Model; 4.3 Multimedia QoE Modeling and Prediction Based on Broad Learning System; 4.4 Summary; References; 5 Implementation and Demonstration; 5.1 Establishment of Big Data Platform; 5.2 Multimedia QoE Data Management Tool; 5.2.1 Architecture of Cloudera Manager; 5.2.2 Cluster and Service Management

5.3 Multimedia QoE Data Collection and Storage5.3.1 Multimedia QoE Data Collection; 5.3.2 Multimedia QoE Data Storage; 5.4 Multimedia QoE Data Analysis and Mining; 5.4.1 Operating Principle of Spark; 5.4.2 Data Analysis and Mining by Spark; 5.5 Multimedia QoE Evaluation Result Demonstration; 5.5.1 User Complaint Prediction Result; 5.5.2 User Interest Inference Result; 5.5.3 User QoE Prediction Result; 5.6 Summary; References; 6 Conclusion; 6.1 Concluding Remarks; 6.2 Future Work

Browse Subjects

Show more subjects...

Statistics

from
to
Export