Call for Papers
April 15th 2015
: The workshop website goes online.
Deadlines and Dates
- July 15, 2015: Deadline for workshop paper submission
- August 4, 2015: Notification of acceptance for workshop papers
- August 25, 2015: Final camera ready copies due
- September 20, 2015: Papers and agenda placed online
- September 28, 2015: Workshop Day at ICCBR 2015 (in parallel)
- September 29-30, 2015: ICCBR 2015 main conference
New to CBR?
Case-based reasoning is a methodology for reasoning and machine learning that emphasizes representation, retrieval and reuse of data/knowledge interpreted in terms of cases (i.e., contextualized problem-solution pairs). Building cyberinfrastructure for CBR is an interdisciplinary effort that requires expertise from various sub fields of Computer Science (e.g., distributed computing, grid computing, and service-oriented architectures) well as other fields like Library Sciences, Software Engineering, Information Systems, Economics, Social Sciences, Management, and many others. Please submit your ideas and explain how you think you can help us make the e-CBR vision a reality.
e-CBR WORKSHOP: BUILDING CYBERINFRASTRUCTURE FOR THE CBR COMMUNITY
The state we envision is a CBR researcher who delivers all her work in this virtual space for CBR research. She finds a scientific workflow (Gil et al. 2007) that interests her. She accesses various data sources, including the data sets used by the authors of that scientific workflow, runs all validation studies again and thinks of a potential improvement. She then adapts that scientific workflow by adding a step that accesses ontologies thus modifying the workflow. She runs the new workflow in various data sets, runs validation services and finds results that are significantly superior to the previous. She can now the call paper drafting service that asks as input to link to background and motivation workflows and to proposed workflows, data sets and validation services. The draft includes bibliographic references for the existing workflows and data sets (that now are cited as papers) and writes her submission in any style she wants. Her work is fully reproducible and accessible by other members of the community.
This context requires cyberinfrastructure (Atkins 2003), which is the infrastructure for eScience. e-CBR refers to computational infrastructure for CBR research and applications, where computational, data, and service resources are shared.
Building infrastructure for CBR research implies promoting CBR as a methodology for scientific practice. CBR research can advance in synergy with other scientific fields (Gil et al. 2014) once CBR is ready to contribute solving grand challenges. Grand challenges (Omenn 2006) are problems that might only be solved with interdisciplinary teams of researchers. Examples of grand challenges include questions about environmental and social resilience and strategies that preserve rights, privacy, safety, and securit
Please contact workshop co-chairs if you have any questions: Rosina Weber (Drexel University, USA) rosina - at - drexel.edu or Pinar Öztürk (Norwegian University of Science and Technology, Norway) pinar - at - idi.ntnu.no
We invite two submission types, papers and statements of interest. Both should be formatted according to the ICCBR 2015 formatting instructions. Papers should be limited to 10 pages and statements to 3 pages.
Authors' instructions along with LaTeX and Word macro files are available on the web at
Submissions should be made through the workshop conference management system: ICCBR-ECBR-2015@EasyChair. For further information do not hesitate to contact the workshop organizers.
In order for e-CBR to produce its intended results, many research questions need to be answered. Fortunately, important steps have been taken in this direction. For example, the community is already contributing open access tools for CBR development (e.g., jCOLIBRI); methodologies for managing workflows (e.g., Minor et al. 2014); similarity measure studies to retrieve workflows (Bergman & Gil 2014), approaches for multi CBR (2001), and big CBR (Leake 2013).
The goals of this workshop are to gather community members interested in discussing (presenting and learning) potential directions and research questions, including recent research relevant to e-CBR including challenges and impediments to building cyberinfrastructure for CBR.
Contributions to this workshop may include various categories of submissions, namely eScience for CBR (e.g., Leake & Kendall-Morwick 2008), CBR for eScience (e.g., Nassif et al. 2007), contributions that can benefit or require cyberinfrastructure (e.g., Koo et al. 2013) and collaborative projects. Some example areas are:
- Data (e.g., data access, data sharing, data curation, metadata)
- CBR Cycle
- Validation & Verification
- Economic models
- Workflow management
- Shared/linked repositories
- Service oriented CBR tools
- Networked Ontologies
- Proposed collaborative project
- Linked data
- Cloud computing
- Submission Drafting
- Recommender services
- Knowledge services
- David W. Aha (NRL, USA)
- Kerstin Bach (Norwegian University of Science and Technology, Norway)
- Ralph Bergmann (University of Trier, Germany)
- Odd Erik Gundersen (Norwegian University of Science and Technology, Norway)
- Pedro Gonzalez Calero (Complutense University of Madrid, Spain)
- David Leake (Indiana University, USA)
- Santiago Ontanon (Drexel University, USA)
- Pinar Ozturk, (Norwegian University of Science and Technology, Norway)
- Enric Plaza (IIIA, Artificial Intelligence Research Institute CSIC, Spain)
- Luigi Portinale (University of Piemonte Orientale, Italy)
- Rosina Weber, (Drexel University, USA)
- Ian Watson (University of Auckland, New Zealand)
References and Further Reading
- Aha, D.W., & Gunderson, O.E. (2013). A reproducibility process for case-based reasoning. In M. Floyd & J. Rubin (Eds.) Proceedings of the Workshops for ICCBR-13. Unpublished.
- Atkins, D. (2003). Revolutionizing Science and Engineering Through Cyberinfrastructure: Report of the NSF Blue-Ribbon Advisory Panel on Cyberinfrastructure.
- Bergmann, R., & Gil, Y. (2014). Similarity assessment and efficient retrieval of semantic workflows. Information Systems, 40, 115-127.
- Gil, Y., Deelman, E., Ellisman, M., Fahringer, T., Fox, G., Gannon, D., ... & Myers, J. (2007). Examining the challenges of scientific workflows. IEEE Computer, 40(12), 24-32.
- Gil, Y., Gonzalez-Calero, P. A., Kim, J., Moody, J., & Ratnakar, V. (2011). A semantic framework for automatic generation of computational workflows using distributed data and component catalogues. Journal of Experimental & Theoretical Artificial Intelligence, 23(4), 389-467.
- Gil, Y., Greaves, M., Hendler, J., Hirsh, H. (2015). Amplify scientific discovery with artificial intelligence. Science 346, 6206, 171-172.
- Hey, T.; Tansley, S., & Tolle, K. M. (Eds.). (2009). The fourth paradigm: data-intensive scientific discovery (Vol. 1). Redmond, WA: Microsoft Research.
- Jalali, V., & Leake, D. (2013). Extending case adaptation with automatically-generated ensembles of adaptation rules. In Case-Based Reasoning Research and Development (pp. 188-202). Springer Berlin Heidelberg.
- Koo, Choongwan ; Hong, Taehoon; Lee, Minhyun, and Park, Hyo Seon (2013). Estimation of the Monthly Average Daily Solar Radiation using Geographic Information System and Advanced Case-Based Reasoning. Environ. Sci. Technol. 2013, 47, 4829−4839
- Leake, D. (2013). Large-Scale Case-Based Reasoning: Opportunity and Questions. Large Scale Data Analytics Workshop. August 2013, School of Informatics and Computing. Bloomington, IN. Online: salsahpc.indiana.edu/summerworkshop2013/slides/davidL.pptx
- Leake, D., & Kendall-Morwick, J. (2008). Towards case-based support for e-science workflow generation by mining provenance. In Advances in Case-Based Reasoning (pp. 269-283). Springer Berlin Heidelberg.
- Leake, DB Sooriamurthi, R (2001) When two case bases are better than one: Exploiting multiple case bases. Case-Based Reasoning Research and Development
- Minor, M.; Bergmann, R.; and Görg, S. Adaptive Workflow Management in the Cloud – Towards a Novel Platform as a Service . Information Systems, 40:142--152. 2014.
- Nassif, L. N., Nogueira, J. M., Karmouch, A., Ahmed, M., & de Andrade, F. V. (2007). Job completion prediction using case‐based reasoning for Grid computing environments. Concurrency and Computation: Practice and Experience, 19(9), 1253-1269.
- Omenn, G. (2006). Grand Challenges and Great Opportunities in Science, Technology, and Public Policy. Science, 314, 1696-1704.