Computational Inference and Control of Quality in Multimedia Services

• Κύριος συγγραφέας: Menkovski, Vlado (Συγγραφέας)
• Συγγραφή απο Οργανισμό/Αρχή: SpringerLink (Online service)
• Μορφή: Ηλεκτρονική πηγή Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: Cham : Springer International Publishing : Imprint: Springer, 2015.
• Έκδοση: 1st ed. 2015.
• Σειρά: Springer Theses, Recognizing Outstanding Ph.D. Research,
• Θέματα: Computer science.; Data mining.; Multimedia information systems.; Management information systems.; Electrical engineering.; Computer Science.; Multimedia Information Systems.; Communications Engineering, Networks.; Data Mining and Knowledge Discovery.; Management of Computing and Information Systems.

 This thesis focuses on the problem of optimizing the quality of network multimedia services. This problem spans multiple domains, from subjective perception of multimedia quality to computer networks management. The work done in this thesis approaches the problem at different levels, developing methods for modeling the subjective perception of quality based on objectively measurable parameters of the multimedia coding process as well as the transport over computer networks. The modeling of subjective perception is motivated by work done in psychophysics, while using Machine Learning techniques to map network conditions to the human perception of video services. Furthermore, the work develops models for efficient control of multimedia systems operating in dynamic networked environments with the goal of delivering optimized Quality of Experience. Overall this thesis delivers a set of methods for monitoring and optimizing the quality of multimedia services that adapt to the dynamic environment of computer networks in which they operate. 

 Supervisor's Foreword -- Preface -- Introduction -- Objective QoE Models -- Subjective QoE Models -- QoE Management Framework -- QoE Active Control -- Conclusions.