Joint BME/CS/ICES Seminar Middleware Support for Data Ensemble Analysis


Joel H. Saltz, M.D., Ph.D.

Professor, Department of Computer and Information Science
The Ohio State University School of Engineering

Professor and Chair, Department of Biomedical Informatics
The Ohio State University College of Medicine and Public Health

Professor, Vice Chair Department of Pathology; Director of Pathology Informatics
The Ohio State University College of Medicine and Public Health

Associate Vice President for Health Sciences
The Ohio State University Medical Center

Dramatic decreases in the cost of storage, combined with equally dramatic improvements in network connectivity will make it possible for communities to collaboratively generate and analyze very large distributed datasets. We will describe application scenarios that motivate this work and provide a broad view of what advances in systems software are needed to make this vision a reality. In many application scenarios, datasets describe spatio-temporal regions. Our approach is to develop systems software able to leverage spatio-temporal descriptive metadata to support a broad range of application areas. We will describe techniques for optimized distributed data storage, indexing, retrieval and processing of ensembles of spatio-temporal datasets. We will then describe techniques for handing spatio-temporal and relational queries directed against these datasets distributed among storage systems located in multiple parallel machines and clusters. Finally, we will describe multiple-query optimization techniques that involve grid based semantic caching along with identification and exploitation of intermediate results shared between the queries.

Tuesday, June 10, 2003 3:30-5:00
ICES Seminar Room ACES 6.304

Tags:

Comments

Post new comment

The content of this field is kept private and will not be shown publicly.

Comments are moderated. They will be posted if they stick to the topic and contribute to the conversation. They will not be published if they contain or link to abusive material, personal attacks, profanity or spam.