Description:
Continuing to build upon the progress we made in Phase I, "Information Analysis and Visualization for Cancer Literature," we will test the Second Prototype concept space which utilizes 500,000 CANCERLIT abstracts and includes noun parsing, automatic indexing, and UMLS metathesaurus components. We will also explore the integration of a Biosys based concept space, integration of category map generation into the CancerLit concept space, and vocabulary switching across the CancerLit space, UMLS meta-thesaurus, and the Biosys concept space.

Description:
The University of Arizona Artificial Intelligence Group will be involved with the development of algorithms, system prototyping and user evaluation of various multimedia analysis, advanced visualization, and information management techniques for digital libraries, multimedia databases, and the Internet.

Description:
The integration and access of criminal information databases is a problem faced by many law enforcement agencies. The University of Arizona's Artificial Intelligence Lab will work with the Tucson Police Department to find a solution to this problem by developing an integrated database solution based on secured Intranet technologies. This will include an Intranet-based universal graphical interface for multimedia justice information, information containing both text and images.

Description:
This research aims to examine semantic interoperability issues related to spatially-oriented, multimedia geographic information access. Based on the concept space approach developed by the Illinois Digital Library Initiative (DLI) project and the Alexandria (University of California at Santa Barbara) geo-referenced collections, this research proposes to develop knowledge representations and structures to capture concepts of relevance to spatial and multimedia information (natural language phrases and geo-related textures). Selected machine learning techniques and general Artificial Intelligence (AI) graph traversal algorithms will also be adopted to assist in semantic, concept-based spreading activation in integrated knowledge networks.

Description:
This project aims to develop concept spaces (networks of vocabularies) to assist in toxicology and environmental health information access. Based on selected automatic indexing, linguistic parsing, and cluster analysis techniques, the system-generated concept spaces will be integrated with the NLM's fine-grained UMLS (Unified Medical Language System) knowledge sources.

Description:
This project aims to develop concept spaces (networks of vocabularies) and category maps for cancer-related literature and documents. Based on selected automatic indexing, linguistic parsing, cluster analysis, neural networks, and information visualization techniques, the system-generated concept spaces and category maps will be used to enhance cancer-related information retrieval and knowledge sharing.

Description:
Our proposed approach, which is grounded on automatic textual analysis of Internet documents (homepages), attempts to address the Internet search problem by first categorizing the content of Internet documents and subsequently providing semantic search capabilities based on a concept space and a genetic algorithm spider (agent). The categorization, concept space, and agent components would be developed sequentially over three years. As Internet information space continues to grow at the present (exponential) pace, we believe this research would shed light on potentially robust and scalable solutions to the increasingly more complex and urgentinformation access and sharing problems.

Publications:

• H.Chen, C. Schuffels, and R. Orwig, "Internet Categorization and Search: A Machine Learning Approach," Journal of Visual Communication and Image Representation, Special Issue on Digital Libraries, Volume 7, Number 1, Pages 88-102, 1996.
• H. Chen, Y. Chung, M. Ramsey, and C. Yang, ``A Smart Itsy Bitsy Spider for the Web,'' CMI Working Paper, 1996.
• H. Chen, M. Ramsey, and H. Li, ``The Java Search Agent Workshop,'' CMI Working Paper, 1996.

Description :
The project goal is to develop a large-scale testbed for building the next-generation digital libraries for the National Information Infrastructure (NII). The testbed collections will be in the engineering domains, to be contributed by major engineering societies and publishers e.g., IEEE, John Wiely & Sons, etc. Project researchers mainly are information science and computer science faculty from the University of Illinois at Urbana-Champaign and research scientists from Illinois's National Center for Supercomputer Applications. The initial platform will be based on the NCSA Mosaic. The AI Group is responsible for developing semantic retrieval, customized IR, and content-based information routing capabilities for digital libraries.

Publications:

• H. Chen and B. Schatz, "Semantic Retrieval for the NCSA Mosaic," Proceedings of the Second International World Wide Web Conference '94, Chicago, Illinois, October 17-20, 1994.
• H. Chen, B. R. Schatz, T. D. Ng, J. P. Martinez, A. J. Kirchhoff, C. Lin, ``A Parallel Computing Approach to Creating Engineering Concept Spaces for Semantic Retrieval: The Illinois Digital Library Initiative Project,'' IEEE Transactions on Pattern Analysis and Machine Intelligence, Special Section on Digital Libraries: Representation and Retrieval, Volume 18, Number 8, Pages 771-782, August, 1996,
• B. Schatz and H. Chen, ``Building Large-Scale Digital Libraries,'' IEEE Computer, Special Issue on ``Building Large-scale Digital Libraries,'' Volume 29, Number 5, Pages 22-27, May, 1996.
• B. Schatz, B. Mischo, T. Cole, J. Harden, A. Bishop, and H. Chen, ``Federating Diverse Collections of Scientific Literature,'' IEEE Computer, Special Issue on ``Building Large-scale Digital Libraries,'' Volume 29, Number 5, Pages 28-36, May, 1996.

Description:
The project aims to develop and experiment with use of various information analysis and machine learning algorithms for various knowledge discovery (data mining) and digital library applications. Thinking Machine's CM-5 (512 nodes), SGI's Power Challenge Array (48 nodes), Cray's CS6400 (8 nodes), and Convex's Exemplar (64 nodes) supercomputers provided by NCSA have been used in this project.

Publications:

• H. Chen, B. R. Schatz, T. D. Ng, J. P. Martinez, A. J. Kirchhoff, C. Lin, ``A Parallel Computing Approach to Creating Engineering Concept Spaces for Semantic Retrieval: The Illinois Digital Library Initiative Project,'' submitted to Transactions on Pattern Analysis and Machine Intelligence, Special Issue on Digital Libraries: Representation and Retrieval, Volume 18, Number 8, Pages 771-782, August, 1996.
• H. Chen, J. Martinez, A. Kirchhoff, T. D. Ng, and B. R. Schatz, ``Alleviating Search Uncertainty Through Concept Associations: Automatic Indexing, Co-occurrence Analysis, and Parallel Computing,'' Journal of the American Society for Information Science, Special Issue on ``Management of Imprecision and Uncertainty in Information Retrieval and Database Management Systems,'' 1997, forthcoming.

Description:
The project goal is to design a concept-based information retrieval and information sharing software for molecular biologists whose work is related to the Human Genome Initiative. A (nematode) worm concept space which can assist in concept exploration and term suggestion during IR has been created and is in use by worm biologists. We are in the process of creating a fly (Drosophila) concept space and a human concept space for assisting automatic, cross-domain, concept-based IR.

Publications:

• H. Chen, B. Schatz, T. Yim, and D. Fye, "Automatic Thesaurus Generation for an Electronic Community System," Journal of the American Society for Information Science, Volume 46, Number 3, Pages 175-193, April 1995.
• H. Chen, "Machine Learning for Information Retrieval: Neural Networks, Symbolic Learning, and Genetic Algorithms," Journal of the American Society for Information Science, Volume 46, Number 3, Pages 194-216, April 1995.
• H. Chen and T. Ng, "An Algorithmic Approach to Concept, Exploration in a Large Knowledge Network (Automatic Thesaurus Consultation): Symbolic Branch- and-bound Search vs. Connectionist Hopfield Net Activation," Journal of the American Society for Information Science, Volume 46, Number 5, Pages 348-369, June 1995.

Description:
Artificial intelligence and information science techniques for assisting concept classification and content-based information retrieval that have been tested include: neural network classification, genetic algorithms, inductive learning algorithms, vector space modeling, and parallel search and clustering algorithms. We have successfully developed an AI tool(agent) to automatically extract and classify topics (concepts) from the electronic brainstorming comments generated by meeting participants (using GroupSystems). We are in the process of using similar techniques to develop software which could automatically classify email and assist in email routing and filtering. We are also designing an "intelligent" (concept-based) meeting memory system.

Publications:

• H. Chen, "Collaborative Systems: Solving the Vocabulary Problem," IEEE COMPUTER, Special Issue on Computer-Supported Cooperative Work, Volume 27, Number 5, Pages 58-66, May, 1994.
• H. Chen, P. Hsu, R. Orwig, L. Hoopes, and J. Nunamaker, "Automatic Concept Classification of Text from Electronic Meetings," Communications of the ACM, Volume 37, Number 10, Pages 56-73, October 1994.
• H. Chen and J. Kim, "GANNET: A Machine Learning Approach to Document Retrieval," Journal of Management Information Systems, Volume 11, Number 3, Winter 1994/95.
• H. Chen, A. Houston, J. Yen, and J. F. Nunamaker, ``Toward Intelligent Meeting Agents,'' IEEE Computer, Volume 29, Number 8, Pages 62-70, August, 1996.

Description:
The project develops an intelligence analysis and retrieval system, which supports intelligence analysts who study information technology policy, manufacturing, and proliferation in the (former) USSR countries. Extensive user requirements studies were conducted. A content-based intelligence analysis and retrieval system was developed in ANSI C and runs on VAX/VMS and DECStation (UNIX based). It includes a system-generated Russian computing "concept space" and a system-assisted relevance feedback and query refinement process. The system is currently in use by the intelligence analysts.

Publications:

• E. M. Roche, S. E. Goodman, and H. Chen, "The Landscape of International Computing," Advances in Computers, Edited by M. C. Yovits, Volume 35, Pages 326-371, 1992.
• H. Chen and K. J. Lynch, "Automatic Construction of Networks of Concepts Characterizing Document Databases," IEEE Transactions on Systems, Man, and Cybernetics, Volume 22, Number 5, Pages 885-902, 1992.
• E. Carmel, S. F. Crawford, and H. Chen, "Browsing in Hypertext: A Cognitive Study," IEEE Transactions on Systems, Man, and Cybernetics, Volume 22, Number 5, Pages 865-884, 1992.
• H. Chen, K. J. Lynch, K. Basu, and T. Ng, "Generating, Integrating, and Activating Thesauri for Concept-Based Document Retrieval," IEEE Expert, Special Series on Artificial Intelligence in Text-Based Information Systems, Volume 8, Number 2, Pages 25-34, April, 1993.
• H. Chen and C. Lin, `` An Automatic Indexing and Neural Network Approach to Concept Retrieval and Classification of Multilingual (Chinese-English) Documents,'' IEEE Transactions on Systems, Man, and Cybernetics, Volume 26, Number 1, Pages 1-14, February 1996.

Description:
This NIH-funded project investigates a neural network approach to pharmaceutical applications. Sample applications include drug solubility prediction and non-linear pharmacokinetics functions approximation. 1992-present.

Publications:

• H. Chow, H. Chen, T. Ng, P. Myrdal, and S. H. Yalkowsky, "Using Backpropagation Networks for the Estimation of Aqueous Activity Coefficients of Aromatic Organic Compounds," Journal of Chemical Information and Computer Sciences, 1995, forthcoming.
• H. Chen, P. Buntin, L. She, S. Sutjahjo, C. Sommer, and D. Neely, "Expert Prediction, Symbolic Learning, and Neural Networks: An Experiment on Greyhound Racing," IEEE EXPERT, Volume 9, Number 6, Pages 21-27, December 1994.