Multi Sensor Integration

Abstract

Knowledge acquisition (KA) is the interactive transfer of domain knowledge from the expert to the program and the embodiment of this information in a computer understandable from inside the machine. Refinement is the process of verifying this domain knowledge for consistency and completeness. In addition to acquiring, KA sometimes involves discovering new knowledge, verifying it, and augmenting the existing knowledge base. Knowledge acquisition is a major and important task in the development of an expert system. This is one of the more difficult tasks as there are not set methodologies to aid the process. Expert systems are knowledge based and their performance depends on the quality as well as the quantity of the domain knowledge. So far these expert systems are only in narrow domains with limited knowledge incorporated into them. This lack of generality makes them unattractive. For real applications, not only big chunks of knowledge base becomes bigger and bigger. Knowledge engineering is a separate field in AI which involves acquiring knowledge, checking the knowledge for contradictions or errors, notifying and (suggestions for) correcting these errors, and finally augmenting the preexisting knowledge.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 12, 1988
Accession Number
ADA196144

Tags

Communities of Interest

  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Acquisition
  • Artificial Intelligence
  • Computer Languages
  • Computer Programming
  • Computers
  • Consistency
  • Engineering
  • Expert Systems
  • Inference Engines
  • Knowledge Based Systems
  • Knowledge Management
  • Language
  • Machine Learning
  • Natural Languages
  • Production
  • Structural Components
  • Template Patterns

Fields of Study

  • Computer science

Readers

  • Applied Combinatorial Optimization and Logic Circuit Design.
  • Geospatial Intelligence and Artificial Intelligence Analytics
  • Systems Analysis and Design