PERFORMING THE RETRIEVE STEP IN A CASE-BASED REASONING SYSTEM FOR DECISION MAKING IN INTRUSION SCENARIOS

摘要

The present paper describes implementation of a case-based reasoning system involved in a crisis management project for infrastructural building security. The goal is to achieve an expert system, capable of making decisions in real-time to quickly neutralize one or more intruders that threaten strategic installations. This article presents development of usual CBR stages, such as case representation, retrieval phase and validation process, mainly focusing on the retrieving phase, approaching it through two strategies: similarity functions and decision tree structures. The designing case, such as the discretization values that are adopted, will also discussed. Finally, results on the retrieving phase performance are shown and analyzed according to well-known cross-validations, such as k-validations or leave-one-out. This work is supported by project CENIT-HESPERIA.