Thesis (M. Eng.)--Carleton University, 1992. / Also available in electronic format on the Internet.

Thesis (M.S. in Computer Science) Naval Postgraduate School, September 1996. / Thesis advisor(s): Robert McGhee and Don Brutzman. "September 1996." Appendix videotape located at Circulation Desk, call number VHS 5000067. Includes bibliographical references (p. 179-184). Also available online.

Thesis (Ph. D.)--University of Maryland, 1990. / Includes bibliographical references (leaves 400-407).

Thesis (Ph.D.)--Aberdeen University, 2009. / Title from web page (viewed on June 26, 2009). Includes bibliographical references.

Thesis (M.S. in Systems Engineering)--Naval Postgraduate School, December 2005. / Thesis Advisor(s): John Osmundson. Includes bibliographical references (p. 81-84). Also available online.

Thesis (Ph. D.)--University of Texas at Austin, 2007. / Vita. Includes bibliographical references.

Thesis (M.S.)--University of Akron, Dept. of Computer Science, 2009. / "May, 2009." Title from electronic thesis title page (viewed 11/18/2009) Advisor, Chien-Chung Chan; Committee members, Kathy J. Liszka, Zhong-Hui Duan; Department Chair, Wolfgang Pelz; Dean of the College, Chand Midha; Dean of the Graduate School, George R. Newkome. Includes bibliographical references.

The ability of an expert system to explain its reasoning is fundamental to the system's credibility. Explanations become even more vital in systems which use methods of uncertainty propagation. The research documented here describes the development of an explanation sub-system which interfaces with the P.R.O. Expert System Toolkit. This toolkit has been used in the development of three small ecological expert systems. This project has involved adapting the results of research in the field of explanation-generation, to the requirements of the ecologist users. The subsystem contains two major components. The first lists the rules that fired during a consultation. The second component comprises routines responsible for quantifying the effects on the system conclusions of the answers given to questions. These latter routines can be used to perform sensitivity analyses on the answers given. The incorporation of such routines in small expert systems is quite unique

WATREX is an expert system used to aid in potable water treatment plant design and was developed several years ago by the Water Research Commission. More recently, this system was tested and a number of deficiencies identified. Amongst these deficiencies were the list of possible chemicals that should be additionally included in the system, as well as the prediction of turbidity removal. The objectives of this project were to investigate and improve these deficiencies. This was achieved in two ways. The chemical addition deficiency was improved through the introduction of new chemicals as separate processes and via improved formulation to model the effects of these chemicals using a spreadsheet with automated calculation abilities. Turbidity removal prediction was improved by the mathematical modelling using data obtained from existing water treatment plants throughout South Africa. The results obtained from the chemical addition improvements were compared to those obtained from other models and found to be correct. The modelling of the turbidity removal data resulted in a series of equations that predict turbidity removal based on plant performance and incoming turbidity values, a first of its kind. Though complete, these models have yet to be incorporated into the existing WATREX system. / Prof. J. Haarhoff

M.Sc. / Surgical patients admitted to an intensive care unit, are susceptible to infection by a large number of micro-organisms. Host defence mechanisms are breached by severe injuries or operations, or the use of life-support systems such as ventilators, catheters and endotracheal tubes. These organisms, some of which are resistant to antibiotics, can therefore invade sterile tissue. Although tissue samples from infected sites are sent to a laboratory to be analyzed, treatment of the patient has to commence before the results are known. Intelligent computer systems, of which expert systems are one of the most popular applications, can be utilized to support diagnostic and therapeutical decisions. This thesis describes the development of an expert system that supports clinical decision-making in the diagnosis and treatment of hospital-aquired pneumonia in an intensive care unit. Input data required by the expert system module are extracted from a data base with patient records. The data base and expert system module communicates by means of a program written in a conventional programming language. The system, which is only a prototype, can be extended to include additional expert system modules addressing other infections. Aquiring knowledge to be encoded in the expert system's knowledge base, remains a problem. In this case an existing scoring system that assigns weights to measurements and the outcomes of certain investigations, is used to obtain a score according to which pneumonia can be diagnosed. The infection is subsequently classified as one of several categories, according to existing guidelines. Appropriate therapy is recommended. The system can also consult a file containing sensitivities of bacteria for antibiotics for the unit, in order to facilitate the choice of drugs. The system has been implemented and tested with a few cases.