Date of Award

Fall 2002

Document Type

Legacy Thesis

Degree Name

Bachelor of Science (BS)

Department

Computing Sciences

College

College of Science

First Advisor

Terrence Fries

Abstract/Description

As a consequence of the increasing dependence on intelligent (or smart) agents and systems in virtually all aspects of computing and business, research into improving the capability of these software tools is more important now than ever. Transaction monitoring, action tracking, and data collection tools used in financial, marketing, and information-processing activities are but a few examples of the applications of intelligent agents. However, as a result of the not-too-uncommon absence of discrete input data upon which these agents can act, further research is necessary to develop methods of enabling intelligent systems operate upon fuzzy data i.e. data that is not discrete by nature. Fuzzy number ranking methods, as they are called, are used to discretely order data that is naturally equivocal or "fuzzy." These methods are the focus of this research. This paper introduces a new fuzzy number ranking method, the Fuzzy Preference Function, developed by Dr. Terrence Fries of Coastal Carolina University. Prior to discussing the new method, the paper presents a review of existing methods of ranking fuzzy numbers that have been developed by several scientists. Following the introduction of the Fuzzy Preference Function, there is an evaluation of this new method by comparing it to some existing ones on the bases of accuracy and ease of use. The paper concludes with a statement about the direction of the research from this point on.

Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.

Share

COinS