The Road Utilization Learning Expert System (RULES): An expert system for emergency vehicle routing and control.
Item
-
Title
-
The Road Utilization Learning Expert System (RULES): An expert system for emergency vehicle routing and control.
-
Identifier
-
AAI9510683
-
identifier
-
9510683
-
Creator
-
Listowsky, Philip.
-
Contributor
-
Adviser: Jerry Waxman
-
Date
-
1994
-
Language
-
English
-
Publisher
-
City University of New York.
-
Subject
-
Computer Science | Artificial Intelligence | Transportation
-
Abstract
-
The major objective of this research is the description of a process for the design and production of a computer expert system which emulates the vehicle routing decision making and expert knowledge processes of human expert emergency service professionals. A project goal is the production of a system which places this expert knowledge at the disposal of non-expert emergency services personnel. It is expected that this will facilitate optimal emergency services personnel and resource utilization by effectively allowing all personnel to function as effectively as the expert personnel. The knowledge-based, Road Utilization Learning Expert System (RULES) determines the best route to get from a starting location to a given destination at different times and under varying conditions. Several techniques are employed, including the production of inference rules, the coding of a knowledge-base, and applying heuristic solutions to a special routing problem not soluble by ordinary algorithmic methods.;A rule-based system was formulated from knowledge of significant factors that may influence path choices, and expert considerations of how these factors interact with each other. One source for this information was a survey of professionals in the emergency services dispatching field, conducted to determine critical factors influencing route decisions. In addition to providing raw data used in weighting factors which affect the routing decision making process, the participants were queried about their need for a system like RULES. These survey results indicated that about 70% of emergency services chiefs nationwide would trust a computer with the task of dispatching their units. These respondents also chose a computer system containing the knowledge of all human experts in the department, as a method that elicits the greatest confidence and trust. We have designed a strategy for the gathering of knowledge and the production of a rule-of-inference model from this information. A description of techniques which have been developed for the testing, operation, and maintenance of this model are also presented. The long term significance of the original methods created and described here is in their providing a method for producing expert systems which emulate the expert decision making processes of human emergency services experts.
-
Type
-
dissertation
-
Source
-
PQT Legacy CUNY.xlsx
-
degree
-
Ph.D.
