Show simple item record

dc.contributor.authorWei, Yong
dc.date.accessioned2014-03-04T02:48:40Z
dc.date.available2014-03-04T02:48:40Z
dc.date.issued2007-08
dc.identifier.otherwei_yong_200708_phd
dc.identifier.urihttp://purl.galileo.usg.edu/uga_etd/wei_yong_200708_phd
dc.identifier.urihttp://hdl.handle.net/10724/24315
dc.description.abstractThis dissertation has focused on the design and implementation of a client-centered multimedia content adaptation system suitable for mobile environments comprising of resource-constrained handheld devices or clients. The current proliferation of mobile computing devices and network technologies has created enormous opportunities for mobile device users to communicate with multimedia servers, using multimedia streams. One of the natural limitations of these handheld devices is that they are constrained by their battery power capacity, rendering and display capability, viewing time limit and in many situations, by the available network bandwidth connecting these devices to video data servers. Thus, it is a necessity to develop a mobile client-centered multimedia personalization system to fulfill clients’ request while satisfying client-side resource constraints. The primary contributions of this work are (1) the overall architecture of the client-centered content adaptation system, (2) a data-driven multi-level hidden Markov model (HMM)-based approach to perform both video segmentation and video indexing in a single pass, (3) the formulation and implementation of a Multiple-choice Multi-dimensional Knapsack Problem (MMKP)-based video personalization strategy, (4) the multiple-stage client request aggregation strategy that reduces the mean client-experienced latency without significant reduction in the average relevance of the delivered video content to the client’s request, and (5) a client-side energy-aware multimedia streaming strategy to efficiently utilize client’s battery power. The overall framework of the system is modular and extensible. New techniques can be incorporated into the individual subsystems without changing other parts and the overall architecture of the system.
dc.languageeng
dc.publisheruga
dc.rightspublic
dc.subjectMultimedia personalization
dc.subjectVideo personalization
dc.subjectMobile computing
dc.subjectVideo Segmentation
dc.subjectVideo Indexing
dc.subjectHidden Markov Model
dc.subjectKnapsack problem
dc.subjectMultidimensional multiple-choice knapsack problem
dc.subjectRequest aggregation
dc.subjectClustering
dc.subjectK-means
dc.subjectHierarchical clus
dc.titleVideo personalization for resource-constrained environments
dc.typeDissertation
dc.description.degreePhD
dc.description.departmentComputer Science
dc.description.majorComputer Science
dc.description.advisorSuchendra M. Bhandarkar
dc.description.committeeSuchendra M. Bhandarkar
dc.description.committeeXiangrong Yin
dc.description.committeeKang Li
dc.description.committeeHamid R. Arabnia


Files in this item

FilesSizeFormatView

There are no files associated with this item.

This item appears in the following Collection(s)

Show simple item record