Department of Computer Science and Engineering
University of Washington

Biomedical information extraction and data integration

Project Summary:

While the amount of useful information generated by modern society keeps increasing exponentially, information access, analysis, and synthesis technologies are progressing at a much slower pace, thus making much of the data useless. Terabytes of data in public Biomedical data sources, in modern clinical setting, on the Web, E-books, and digital libraries could help solve thousands of our problems, if we just had the right leverage.

The goal of this research is to simplify access, thus opening the door to development of advanced applications that were previously infeasible. Heterogeneous, often distributed, large-scale real-world data makes this goal very challenging. Nevertheless, it is possible through interdisciplinary research in Biomedical Informatics, Information Retrieval, Natural Language Processing, and Machine Learning.

People:

Linda Shapiro
Lucian Popa
Michael Gubanov
Mark Agoncillo

Publications:

  • M. Gubanov, L. G. Shapiro, "Automatic Alzheimer's Disease diagnosis using Unified Famous Objects (UFO)", pdf, Proceedings of the IEEE Bioinformatics & Biomedicine, 2011, pp. 901-903.

  • M. Gubanov, A. Pyayt, L. G. Shapiro, "ReadFast: Browsing large documents through Unified Famous Objects (UFO),"  pdf
    Proceedings of the 12th IEEE International Conference on Information Reuse and Integration (IRI), Las Vegas, Nevada, 2011, acc. rate 29%

  • M. Gubanov, L. G. Shapiro, A. Pyayt, "Learning Unified Famous Objects (UFO) to Bootstrap Information Integration,"  pdf
    Proceedings of the 12th IEEE International Conference on Information Reuse and Integration (IRI), Las Vegas, Nevada, 2011, acc. rate 29%

  • M. Gubanov, L. Popa, H. Ho, H. Pirahesh, J. Chang, S. Chen, "IBM UFO Repository: Object-oriented data integration"   [pdf]
    Proceedings of the 35th International Conference on Very Large Data Bases (VLDB), Lyon, France, 2009, acc. rate 27%

  • B. Alexe, M. Gubanov, M. Hernandez, H. Ho, J. Huang, Y. Katsis, L. Popa, B. Saha, I. Stanoi, "Simplifying Information Integration: Object-based flow-of-mappings framework for integration",
    Invited paper in the book Business Intelligence for the Real Time Enterprise, Springer, pp. 108-121, 2008

  • B. Alexe, M. Gubanov, M. Hernandez, H. Ho, J. Huang, Y. Katsis, L. Popa, "Simplifying Information Integration: Object-based flow-of-mappings framework for integration",
    Proceedings of the 2nd International Workshop on Business Intelligence for the Real Time Enterprise, Auckland, New Zealand, 2007

  • Talks:

  • M. Gubanov, "Simplifying access to structured and unstructured data", Stanford University, Stanford, CA, 2011.

  • M. Gubanov, "ReadFast: Browsing large documents through Unified Famous Objects (UFO)", 12th IEEE International Conference on Information Reuse and Integration (IRI), Las Vegas, Nevada, 2011.

  • M. Gubanov, "Learning Unified Famous Objects (UFO) to Bootstrap Information Integration", 12th IEEE International Conference on Information Reuse and Integration (IRI), Las Vegas, Nevada, 2011.

  • M. Gubanov, "Object-oriented management of structured and unstructured data", University of Washington, Seattle, WA, 2010.

  • M. Gubanov, "Simplifying information integration using Unified Famous Objects (UFO)", University of Washington, Seattle, WA, 2010.

  • M. Gubanov, "IBM UFO Repository: Object-oriented data integration" Proceedings of the 35th International Conference on Very Large Data Bases (VLDB), Lyon, France, 2009

  • M. Gubanov, "IBM UFO Repository", IBM Almaden Research Center, San Jose, CA, 2007