Complexity Modelling for CBR Systems

CBR systems solve new problems by retrieving and reusing solutions for previously solved problems that are stored as case knowledge in a database. The contents of the case knowledge container are critical to the performance of classification CBR systems. Our research is developing competence models for CBR systems based on complexity. The complexity measure provides a local indicator of uncertainty within the problem space and is useful in informing case base maintenance. A complexity-guided case discovery algorithm combines the local complexity measure and boundary identification techniques to actively discover cases close to boundaries. In contrast, a complexity-guided redundancy reduction algorithm uses the local complexity measure to identify redundant cases but actively retains cases close to boundaries. An error reduction algorithm similarly differentiates between boundary cases and outliers. The reduction algorithms offer control over the balance between maintaining competence and reducing case-base size. Funding RGU RDI Research Team Susan Craw (PI) Stewart Massie Nirmalie Wiratunga Related Projects CBR for Remote Patient Health-Care Monitoring (KTP) CBR for Anomaly Report Processing MediCACE - Medical Decision Support with CBR Knowledge Acquisition for Case-Based Design Posters Complexity-Guided Case Knowledge Maintenance Informed Case Base Maintenance: A Complexity Profiling Approach (AAAI 2007 Nectar Paper)

Publications

Craw, S. (2007). The case base — the sequel, Proceedings of the 12th UK CBR Workshop, Cambridge, UK. Invited Talk.

Craw, S., Massie, S. & Wiratunga, N. (2007). Informed case base maintenance: A complexity profiling approach, Proceedings of the 22nd AAAI Conference on Artificial Intelligence (AAAI-07), AAAI Press, Vancouver, BC, pp. 1618—1621.

Massie, S., Craw, S. & Wiratunga, N. (2007). When similar problems don't have similar solutions, Proceedings of the 7th International Conference on Case-Based Reasoning (ICCBR-07), LNCS 4626, Springer, Heidelberg, Belfast, Northern Ireland, pp. 92—106. doi: 10.1007/978-3-540-74141-1_7.

Massie, S., Craw, S., & Wiratunga, N. (2006). Complexity profiling for informed case-base editing. 8th European Conference on Case-Based Reasoning (ECCBR-06), Fethiye, Turkey

Massie, S., Craw, S., & Wiratunga, N. (2005). Complexity-guided case discovery for case based reasoning. 20th National Conference on Artificial Intelligence (AAAI-05), Pittsburgh, PA

Massie, S., Craw, S., & Wiratunga, N. (2004). A Visualisation Tool to Explain Case-Base Reasoning Solutions for Tablet Formulation. 24th SGAI International Conference on Innovative Techniques and Applications of Artificial Intelligence , Cambridge, UK

Massie, S., Craw, S., & Wiratunga, N. (2004). Visualisation of Case-Based Reasoning for Explanation. Explanation Workshop of the 7th European Conference on Case-Based Reasoning , Madrid, Spain

Wiratunga, N., Craw, S., & Massie, S. (2003). Index driven selective sampling for CBR. 5th International Conference on Case-Based Reasoning (ICCBR 03) , Trondheim, Norway