Journal Publications

Refereed Conference Publications

Symposium and Workshop Articles

Thesis Work

Technical Reports

(Co)-chairing Workshops

Tutorial Presentations

 

Journal Publications

[available upon request]
One can also read selected sections of this work (unfortunately without proper quotation and reference) in Lynn Ling X Li (1999) Knowledge-based problem solving: An approach to health assessment. Expert Systems with Applications, 16(1):33-42. See also Expert Systems with Applications 18:153, 2000. (Follow this link to see further details)"

In vitro fertilization (IVF) is a medically-assisted reproduction technique, enabling infertile couples to achieve successful pregnancy. Given the unpredictability of the task, we propose to use a case-based reasoning system that exploits past experiences to suggest possible modifications to an IVF treatment plan in order to improve overall success rates. Once the system's knowledge base is populated with a sufficient number of past cases, it can be used to explore and discover interesting relationships among data, thereby achieving a form of knowledge mining.

The article describes the TA3IVF system -- a case-based reasoning system which relies on context-based relevance assessment to assist in knowledge visualization, interactive data exploration and discovery in this domain. The system can be used as an advisor to the physician during clinical work and during research to help determine what knowledge sources are relevant for a treatment plan.

 

Refereed Conference Publications

Symposium and Workshop Articles

  1. Albert, M., Jurisica, I., Park, P., Squire, J., Macgregor, P. (2001). Comparative microarray study of T7-based and PCR-based RNA amplification approaches: A pilot study for the expression profiling of laser capture microdissected prostate cancer samples. Conference on Laser Capture Microdissection and Macromolecular Analysis of Normal Development and Pathology, NIH, Bethesda, MD, July 17-18. Abstract for oral presentation.
  2. Mouka, J., Jurisica, I., Huner, O. (2001). MicroArray eXperiment (MAX): A collaborative on-line research environment for large-scale cDNA microarray projects. The Third International Meeting on Microarray Data Standards, Annotations, Ontologies and Databases (MGED-3), Stanford University, Palo Alto, CA. Poster.
  3. Jurisica, I., Rogers, P., Glasgow, J., Fortier, S., Collins, R., Wolfley, J., Luft, J. and DeTitta, G. (2001). High Throughput Macromolecular Crystallization: An Application of Case-Based Reasoning and Data Mining, in Methods in Macromolecular Crystallography, L. Johnson and D. Turk (Eds.), Volume 325, NATO Science Series: Life Sciences, Kluwer Academic Press.
  4. Luft, J. R., J. Wolfley, M. Bianca, D. Weeks, I. Jurisica, P. Rogers, J. Glasgow, S. Fortier, G. T. DeTitta. (2000). High throughput protein crystallization: Keeping up with the genomics. Gordon Conference on Diffraction Methods in Molecular Biology , Andover, NH.
  5. Luft, J.R., Bianca, M., Owczarczak, L. M., Weeks, D. R., Jurisica, I., Rogers, P., Glasgow, J., Fortier, S. and DeTitta, G.T. The development of high througput methods for macromolecular microbatch crystallization. Recent Advances in Macromolecular Crystallization, San Diego, CA, 1999.
  6. Jurisica, I., DeTitta, G.T., Luft, J., Glasgow, J., Fortier, S. Knowledge Management in Scientific Domains, AAAI-99 Workshop on Exploring  Synergies of Knowledge Management and Case-Based Reasoning, Orlando, FL, 1999.
  7. Luft, J.R., Bianca, M., Jurisica, I., Rogers, P., Glasgow, J., Fortier, S. and DeTitta, G.T. An Opening Strategy for Macromolecular Crystallization: Case-Based Reasoning and the Exploitation of a Precipitation Reaction Outcome Database. Conference of the American Crystallography Association, Buffalo, NY, 1999.
  8. Errico, B. and I. Jurisica. Adaptive Agent-based Systems for the Web: An Application to the NECTAR Project. AAAI Spring Symposium on Intelligent Agents in Cyberspace, Stanford University, March 22 - 24, 1999.
  9. Jurisica, I. Supporting evidence-based medicine by cooperative information systems. In Digital Knowledge Conference III, Toronto, 1999.
  10. Jurisica, I. Library as a Knowledge Broker: Knowledge Management and Sharing. Ontario Library Association Super Conference, Toronto, January 21-23, 1999.
  11. Glasgow, J. and Jurisica, I. Integration of case-based and image-based reasoning, American Association for Artificial Intelligence, Workshop on Case-Based Reasoning, Madison, WI, July 28, 1998.AAAI-CBRW'98.ps.Z
  12. Jurisica, I. Supporting flexibility. A case-based reasoning approach. In The AAAI Fall Symposium. Flexible Computation in Intelligent Systems: Results, Issues, and Opportunities, Cambridge, Massachusetts, 1997.
  13. Jurisica, I. Inductive learning and case-based reasoning, Canadian AI Conference, Workshop on What is Inductive Learning? Toronto, Ontario, 1996.
  14. Jurisica, I. A Similarity-Based Retrieval Tool for Software Repositories The 3rd Workshop on AI and Software Engineering: Breaking the Mold. IJCAI-95, Montreal, Quebec, 1995
  15. Jurisica, I. and Glasgow, J. Applying Case-Based Reasoning to Control in Robotics 3rd Robotics and Knowledge-Based Systems Workshop, St. Hubert, Quebec, 1995.
  16. Jurisica, I. How to Retrieve Relevant Information? Proceedings of the AAAI Fall Symposium Series on Relevance. New Orleans, Louisiana, 1994.

Thesis Work

Similarity plays a central role in theories of human problem solving and thus is important for artificial intelligence research. Although there are different approaches to similarity assessment, the underlying idea is to classify information according to some features, so that we can use it in similar situations. Depending on the application domain, the task at hand, and user preferences, the relevance of individual features may vary, and so will the similarity of the concepts they represent. It is paramount to know what affects feature relevance and how to represent such information explicitly.

The objective of this thesis is to improve case-based reasoning by: (1) achieving better accuracy during classification; (2) retrieving cases that are more relevant to a given problem; and (3) obtaining scalability with respect to case base size, case and query complexity. We achieve this goal by introducing a new theory of similarity-based retrieval that uses variable-context similarity assessment, and by defining an efficient iterative retrieval algorithm that employs ideas of incremental view maintenance algorithms from database management systems. Context is a parameter of similarity that specifies what attributes are involved in similarity assessment between cases, and what set of values may be considered for these attributes. It defines which aspects of a case are important in a particular situation. We also define a set of operations, namely relaxation and restriction, which enable to control the relevance of retrieved cases.

We evaluate competence, scalability and algorithmic complexity of a prototype system on diverse real-world domains. We show how the proposed similarity measure supports flexible computation by trading off the accuracy or precision of the computation process for time and space resources. In addition, the case representation used supports case base organization so that cases similar in a given context can be grouped into clusters. This representation also lends itself to attribute-oriented discovery, a technique that finds relevant attributes and their values. The discovery process improves the representation by grouping together relevant, removing unneeded or adding essential attributes. Performance evaluation shows how the discovery process improves system's competence. Iterative retrieval of cases is efficiently handled by the adoption of incremental view maintenance algorithms from database management systems. Performance evaluation shows that this approach improves efficiency of case retrieval and thus helps to achieve system scalability with respect to case base size, case representation and query complexity.
 

  • Jurisica, I. (1993). Query Optimization for Knowledge Base Management Systems: A Machine Learning Approach. MSc thesis, Department of Computer Science, University of Toronto, Toronto, Ontario.

  •   This thesis proposes new machine learning applications to optimize queries in a knowledge base management systems. In particular, an explanation-based machine learning algorithm is adopted, extended and tested. The algorithm, called PALO (Probably Approximately Locally Optimal), is a general model of a learning system and is directly applicable to a variety of systems as a speedup learning module. The algorithm is based on the theoretical work of Valiant [Valiant-CACM84] and uses statistical information to produce a close approximation of a locally optimal search strategy. Some additions are made to the original version of the algorithm, to solve a broader range of problems. In addition, the termination condition in the algorithm is changed in order to make it run faster without any degradation of its performance.The learning module is implemented and its integration into an architecture of a knowledge base management system is shown. The proposed optimization technique is tested with real and artificial examples to establish its effectiveness.

    Technical Reports

    1. I. Jurisica. Data Mining and Knowledge Discovery, IBM Technical Report 74.165-a, IBM Centre for Advanced Studies, Toronto, December 1, 1998.
    2. J. Glasgow and I. Jurisica. Data Storage, Retrieval and Mining in Biomedical Applications. IBM Technical Report 74.165-b, IBM Centre for Advanced Studies, Toronto, December 1, 1998.
    3. I. Jurisica. Context-based similarity applied to retrieval of relevant cases. Technical Report DKBS-TR-94-5, University of Toronto, Department of Computer Science, Toronto, 1994.
    4. R. Greiner and I. Jurisica. An EBL system that (almost) always improve performance. Technical Report, Siemens Corporate Research, Princeton, NJ, 1992.

     

    (Co)-chairing Workshops

    The aim of the panel is to discuss state-of-the-art in telemedicine, present experience gained, and to consider advantages and disadvantages of telemedicine. We plan to propose architecture for telemedicine systems that would support currently available systems, but would enable extensions. We recognize two possible approaches: (1) Human – human; (2) Human - Intelligent Decision Support System. The first approach has the advantage of being simple and readily available. However, it does not solve the problem of shortage of experts, which can be handled by the second approach. In addition, the second approach has the advantage of providing better transaction processing since it uses global repository (a case base) to store and manage experience. The main advantage is that experts collect global experience and thus progress with domain understanding faster and that the communication between experts is asynchronous. The panel will bring together telemedicine specialists, practicing physicians, technology providers and researchers. The panel brought together healthcare specialists, researchers in medical informatics, psychology and computer science, technology providers, and government agencies to discuss the issues related to building medical information management systems. Panel aimed at identifying a blueprint for medical information systems in Canada by discussing limitations of existing decision support tools, identifying technological challenges and the key organizational factors that arise from the implementation of large scale distributed information systems. On the basis of the response from the conference organizers and the audience, we believe the panel engendered collaborative research and development, and will steer the research and development into right direction. Summary of the panel is being prepared for publication in AI in Medicine journal.

     

    Tutorial Presentations

    I have presented tutorials on case-based reasoning (CBR), machine learning and knowledge base management systems (KBMS) on several occasions, including:
    1. Igor Jurisica, Isidore Rigoutsos, Aris Floratos. "Knowledge Discovery in Biological Domains", ACM KDD'2000, Boston, MA, August, 2000.
    2. Janice Glasgow and Igor Jurisica. "Introduction to Data Mining for Molecular Databases". Pacific Symposium on Biocomputing (PSB'99), Hawaii, January 4, 1999.
    3. Igor Jurisica and Janice Glasgow. "Data Mining and Knowledge Discovery". CASCON'98, Toronto, Ontario, December 2, 1998.
    4. John Mylopoulos, Vinay Chaundhri, Igor Jurisica, Dimitris Plexousakis, Adel Shrufi, Thodoros Topaloglou, and Huaiqing Wang. "Development and Application of Knowledge Base Management Systems’. Australian Joint Conference on AI, Canberra, Australia, November 1995. Tutorial notes. Presented by Igor Jurisica and Huaiqing Wang.
    5. John Mylopoulos, Vinay Chaundhri, Igor Jurisica, Dimitris Plexousakis, Adel Shrufi, Thodoros Topaloglou, and Huaiqing Wang. "Knowledge Base Management Systems". International Joint Conference on AI, Montreal, Quebec, August 1995. Tutorial notes. Presented by John Mylopoulos and Thodoros Topaloglou.
    6. John Mylopoulos, Vinay Chaundhri, Igor Jurisica, Dimitris Plexousakis, Adel Shrufi, Thodoros Topaloglou, and Huaiqing Wang. "Knowledge Base Management and its Application". IEEE Conference on AI Applications, IEEE Computer Society, San Antonio, TX, March 1994. Tutorial notes. Presented by Igor Jurisica and Huaiqing Wang.
    7. Igor Jurisica. "Representation and management issues for case-based reasoning systems". TRIO/ITRC Research Retreat, Queen's University, Kingston, May 10-12 1994. Technology mini-tutorial.
    8. John Mylopoulos, Vinay Chaundhri, Igor Jurisica, Dimitris Plexousakis, Adel Shrufi, Thodoros Topaloglou, and Huaiqing Wang. "Knowledge Base Management Systems". Database and Expert Systems Applications, Athens, Greece, September 1994. Tutorial notes. Presented by John Mylopoulos and Dimitris Plexousakis.
    9. John Mylopoulos, Vinay Chaundhri, Igor Jurisica, Dimitris Plexousakis, Adel Shrufi, Thodoros Topaloglou, and Huaiqing Wang. "Information and Knowledge Base Management". Information Technology Research Center, University of Toronto, Department of Computer Science, February 1993. Tutorial notes. Presented by all authors.