Case-Based Reasoning - learning through experience
The CBR Shell Applet performing diagnosis on the Wisconsin Cancer dataset, and view of the genetic algorithm optimiser
|
LICENSING OPPORTUNITY
Researchers in the Artificial Intelligence Applications Institute at the University of Edinburgh have developed a Case-Based Reasoning Shell that can be applied to large and complex databases.
CBR is particularly applicable to problems where the domain is not understood well enough for a robust statistical model or system of equations to be formulated. While the general case-based reasoning methodology can be applied across different application domains, the implementation of the case retrieval and similarity scoring functions is typically highly customised to the problem at hand.
Case-Based Reasoning is based on the intuition that new problems are often similar to previously encountered problems and, therefore, that past solutions may be of use in the current situation. Commercial and industrial applications can, therefore, be developed rapidly, and existing corporate databases can be used as knowledge sources.
AIAI's CBR Shell has an advanced performance optimisation module, based on a genetic algorithm, implemented in JAVA.Key Benefits
- CBR is an efficient, robust and readily-understood technique for data analysis
- CBR converts existing organisational resources into exploitable knowledge
- CBR understands the underlying patterns and discovers the knowledge implicit in datasets that are critical to improving products and decreasing unnecessary investigations
- CBR can be applied to large and complex databases
Applications
- Helpdesk applications – search appropriate past solutions from corporate databases
- Pharmaceutical industry
- Diagnosis/Treatment Decisions – eg. determining whether or not cancer treatment is necessary, given a set of past cases
- Medical Trials – for the analysis of data from trials and high-throughput experimental processes
- Protein Structure Prediction – prediction of structure in combination with other knowledge-based AI methods
- Fraud Detection – reduce the number of applications referred for expert investigation
- Test & Diagnostic trouble-shooting
- Reduction in Aircraft engine diagnostics test time
IP Status
The University of Edinburgh is seeking suitable industrial partners for licensing of core case-based reasoning engine technology.
If you would like further information about
this opportunity please fill out the form below. Your enquiry will
be passed on to the relevant University who will respond to you directly.
