Extremely Distributed Media Processing

Signal Processing in Distributed Systems with Limited Resources

Distributed wireless systems offer several advantages over their traditional wired and centralized counterparts, e.g., flexibility, easy installation, reconfiguration, and scalability. Although the resources in these distributed systems are often limited in order to achieve costeffective operation, the concept of distributed system design is in the focus of intensive research even in those appl...

Next-Generation Content Representation, Creation and Searching for New Media Applications in Education

Content creation, editing, and searching are extremely time consuming tasks that often require substantial training and experience, especially when high-quality audio and video are involved. “New media” represents a new paradigm for multimedia information representation and processing, in which the emphasis is placed on the actual content. It thus brings the tasks of content creation and search...

Automatic Resource-aware Construction of Media Indexing Applications for Distributed Processing Environments

Constructing pattern classification based media indexing applications for distributed processing environments (DPEs) often requires knowledge in feature extraction as well as distributed processing. In order to achieve an appropriate tradeoff between indexing error rate and processing time, feature extractors (FEs) must be carefully selected based on their application specific indexing and DPE ...

Simulation of cake formation for nano-fibrous filter media using image processing

XPS: EXPL: Scalable distributed GPU computing for extremely high-dimensional optimization

High-dimensional optimization is a challenging research problem and a computationally intensive task which requires innovative approaches from parallel and distributed computing perspectives. Extremely high-dimensional optimization involves very large problem dimensionalities with millions of variables. However, proposals to date limited the problem dimensionality to a few million variables due...