Graduate Thesis Or Dissertation
 

Expert system prototype for food aid distribution

Public Deposited
default representative image
https://ir.library.oregonstate.edu/concern/graduate_thesis_or_dissertations/6q182q75m

Descriptions

Attribute NameValues
Creator
Abstract
  • Numerous investigative reports have cited the problems of inefficient food aid distribution by various international disaster relief agencies. These problems not only deprive the disaster victims of life giving support, but can also discourage potential sources of contributions. Lack of a feedback process has been attributed as a cause of organizational inefficiencies in these agencies. Existing old-fashioned distribution processes failed to incorporate present day tools for advanced process control. Investigations of food distribution organizations revealed a need for a state-of-the-art monitoring system. Typically, these systems incorporate an expert knowledge base which aids an adaptive decision making process. This research identified data related to food aid monitoring and evaluation processes of various international organizations. It then applied an artificial intelligence based expert system to develop a prototype for those processes. Existing data related to monitoring and evaluation program cycles were obtained from two international food relief organizations. An expert system shell called CLIPS (©NASA) was utilized to develop a prototype system named FAM (Food Aid Monitor) for monitoring and evaluating food aid distribution. FAM, a rule based expert system, uses facts and heuristic rules to provide advice regarding food aid monitoring and evaluation processes at various stages of an operation. The FAM was evaluated and validated by three expert panels checking the prototype system for: (1) completeness and relevancy, by a faculty expert panel; (2) consistency, (3) correctness, (4) and precision, by a software engineering expert panel; and (5) usability, by a field expert panel. The faculty panel identified some modifications to the original set of rules. Their review indicated a relatively complete set of rules and high rule relevancy to the knowledge base. Upon revision of the rule source code by the researcher, the software experts validated the prototype in two iterations. The panel determined a system accuracy of approximately 95% and 100% in the two iterations. This exceeded the initial objective of the research. Finally, usability experts commented upon the generic nature of the prototype and indicated a belief that the system might have an overall positive impact on the stages of monitoring and evaluating food aid distribution.
Resource Type
Date Available
Date Issued
Degree Level
Degree Name
Degree Field
Degree Grantor
Commencement Year
Advisor
Committee Member
Academic Affiliation
Non-Academic Affiliation
Subject
Rights Statement
Publisher
Peer Reviewed
Language
Digitization Specifications
  • File scanned at 300 ppi (Monochrome) using Capture Perfect 3.0.82 on a Canon DR-9080C in PDF format. CVista PdfCompressor 4.0 was used for pdf compression and textual OCR.
Replaces

Relationships

Parents:

This work has no parents.

In Collection:

Items