An Expert System Decision Aid for a Command, Control and Communications Operator.
Abstract
The growing complexity and quantity of information used in Command, Control and Communications (C3) networks makes it essential to reduce the workload on the operators of these networks. The SENTINEL project uses the Artificial Intelligence concept of an expert system to produce a decision aid for the strategic Missiles Warning Officer, using a simulation of a C3 network that involves multiple missile launches and up to 20 countries. In this research, a blackboard model expert system using rule bases and object oriented programming techniques was developed to permit SENTINEL to offer several layers of explanation. SENTINEL analyzes patterns and causes of reported events into higher level yet less precise forms to provide the upper layer of explanation. SENTINEL deals with uncertainty by using the statistical concepts of feature sets and decision thresholding. The feature sets represent the essential characteristics of a launch event and are evaluated to see how well they fit a particular hypothesis. The decision threshold used to select an interpretation is determined by appraising the distance from each hypothesis, as well as by previous events. This project demonstrates the feasibility of building expert system decision aids for C3 operators by using specialized explanation capabilities, and reasoning with uncertainty in a more statistically conventional way. Keywords: Artificial Intelligence, Missile Warning System Expert System, Decision Aid Command, Control and Communications.
Document Details
- Document Type
- Technical Report
- Publication Date
- Dec 01, 1985
- Accession Number
- ADA163827
Entities
People
- Daniel L. Tobat
Organizations
- Air Force Institute of Technology