• Major conferences in 2010
• Hardware/Machines in LAIR
• Xiangyu Fan's space
• Weimao Ke's space
• Yan Zhang
• Mayank Agarwal
• Ongoing Research / Papers
• Important Due Dates
• Database design for VCGS backend support
• FTP Access to the NAS storage
• FTP Client
• Details of fields in ADNI dataset

• [CHAPTER] Biomedical Text Mining by Javed Mostafa, Kazuhiro Seki, and Weimao Ke
• [CHAPTER] Viewfinder / Image Retrieval by Javed Mostafa and Mayank Agarwal
• [BOOK] Personalization in IR by Javed Mostafa

• NCDetect Concept Discovery
• Visualization and Clustering
• SigIR 2008 Related Papers
• Parallel algorithm papers
• View Finder
• Data Discovery Tool
• Personalization
• SPIROMICS Wiki

• ACM SigIR Special Interest Group on Information Retrieval, due January 21 (abs), 28, 2010 (18-23 July 2010, Geneva, Switzerland)
• Joint Conference on Digital Libraries, due Mid-January 2010 (meeting June 21 - 25 2010, Gold Coast, Australia)
• Conference on Information and Knowledge Management (CIKM), due TBD (probably end of May), 2010 (meeting Oct 25, 2010 - Oct 29, 2010, Toronto, ON, Canada)
• International World Wide Web Conference, due Oct 26 (abs), Nov 2, 2009 (meeting April 26-30, 2010, Raleigh, NC)
• American Society for Information Science and Technology (ASIS&T) annual meetings, due TBA (prob. Jan 25 (paper), Feb 25 (poster)), 2010, (meeting October 22-27, 2010, Pittsburgh, PA)

• iSchool Conference, papers and posters due January 25, 2008
• American Medical Informatics Association, due March 13, 2009
• Association for Library and Information Science Education, July 31 (paper), October 1 (poster), 2008
• ACM SigCHI, due September 19th, 2008
• International Conference on Intelligent User Interfaces, due October 1, 3, 2008

• Workshop: Information Retrieval in P2P Networks

• ACM Transactions on Information Systems, CONTENT
• Information Processing & Management - Elsevier, CONTENT
• Information Retrieval, CONTENT
• Journal of the American Society for Information Science and Technology (JASIST), CONTENT

• ACM Digital Library - Online Portal
• IEEE Explore, IEEE Computer Society Digital Library
• AMIA Proceedings

http://miksa.ils.unc.edu:8080/vcgs/sifter/vcgs

MACCI stands for Multi-Agent Collaboration for Classification of Information. The official site of MACCI is at: http://lair.ils.unc.edu/macci/.

LUCAS stands for Library of User-Oriented Concepts for Access Services. In Lucas II, we developed and deployed three web service methods (operations) for term extraction, text classification, and clustering. The system mainly consists of three components: the Lucas II web services, which are deployed on Tomcat and Apache Axis server; the client, which passes the user selected parameters to the web services and gets the results back based on the SOAP protocol; and data access modules to access domain terms and document collections.

→ Details

Among existing implementations of various browsing methods, Scatter/Gather browsing is well known for its ease to use and effectiveness in situations where it is difficult to precisely specify a query (Cutting, Karger, Pedersen, and Tukey 1992; Hearst and Pedersen 1996). This project aims to implement a Scatter-Gather browser, a dynamic visualization for text navigation/search. Using visualization techniques, this browser will help users refine their search queries and narrow down search results interactively and visually. We are going to constraint ourselves to a smaller text corpus for proof of concept. We will modularize it to be able to attach to any text collections in the future.

→ Details

MedSifter, or Medical Sifter, stands for Smart Information Filtering Technology for Electronic Resources. Here is the MedSifter demo: http://lair.ils.unc.edu:8080/medsifter/demo.html.

The OHSUMED test collection is a set of 348,566 references from MEDLINE, the on-line medical information database, consisting of titles and/or abstracts from 270 medical journals over a five-year period (1987-1991). The available fields are title, abstract, MeSH indexing terms, author, source, and publication type. The National Library of Medicine has agreed to make the MEDLINE references in the test database available for experimentation, restricted to the following conditions:

1. The data will not be used in any non-experimental clinical, library, or other setting.

2. Any human users of the data will explicitly be told that the data is incomplete and out-of-date.

The OHSUMED document collection was obtained by William Hersh (hersh@OHSU.EDU) and colleagues. Click here for more information.

This is the document collection (including documents, topics, and relevance judgements) used in the TREC-9 Filtering Track.

• Hersh WR, Buckley C, Leone TJ, Hickam DH, OHSUMED: An interactive retrieval evaluation and new large test collection for research, Proceedings of the 17th Annual ACM SIGIR Conference, 1994, 192-201.

• Hersh WR, Hickam DH, Use of a multi-application computer workstation in a clinical setting, Bulletin of the Medical Library Association, 1994, 82: 382-389.

The document collection for the TREC 2006 Genomics Track consists of full-text HTML documents from 49 journals who publish electronically via Highwire Press that granted permission for research use of their articles in the Genomics Track. The track continues in 2007. The documents have been obtained by a Web crawl of the Highwire site, with postprocessing to eliminate as much non-article material as we could. This material should only be used for research purposes and should not be posted on public Web sites.

The TREC 2007 Genomics Track protocol is available at http://ir.ohsu.edu/genomics/2007protocol.html.

The documents are in the directory. The data files themselves are located in the active user portion of the track Web site at http://ir.ohsu.edu/genomics/data/. This area is password-protected, with the password only available to those who have completed data usage agreements and/or are registered for TREC.

The GEDData repository has a number of datasets for bio-medical data analysis and Gene Expression applications, provided by the Institute for Infocomm Research in Singapore. The data collections are offerred in three formats, i.e. C4.5 format, Weka's ARFF format, and the Comma Separated Values (or CSV) format.

The data repository is avialable at http://sdmc.lit.org.sg/GEDatasets/.

• “Molecular Classification of Cancer: Class Discovery and Class Prediction by Gene Expression Monitoring”. Science, 286:531-537, October 1999