Knowledge management for computational intelligence systems

  • Authors:

  • Rosina Weber;Duanqing Wu

  • Affiliations:

  • College of Information Science and Technology, Drexel University Philadelphia;College of Information Science and Technology, Drexel University Philadelphia

  • Venue:
  • HASE'04 Proceedings of the Eighth IEEE international conference on High assurance systems engineering
  • Year:
  • 2004

Quantified Score

Hi-index 0.00

Visualization

Abstract

Computer systems do not learn from previous experiences unless they are designed for this purpose. Computational intelligence systems (CIS) are inherently capable of dealing with imprecise contexts, creating a new solution in each new execution. Therefore, every execution of a CIS is valuable to be learned. We describe an architecture for designing CIS that includes a knowledge management (KM) framework, allowing the system to learn from its own experiences, and those learned in external contexts. This framework makes the system flexible and adaptable so it evolves, guaranteeing high levels of reliability when performing in a dynamic world. This KM framework is being incorporated into the computational intelligence tool for software testing at National Institute for Systems Test and Productivity. This paper introduces the framework describing the two underlying methodologies it uses, i.e. case-based reasoning and monitored distribution; it also details the motivation and requirements for incorporating the framework into CIS.