Massey Documents by Type

Permanent URI for this communityhttps://mro.massey.ac.nz/handle/10179/294

Browse

Subject: search.filters.subject.Expert systems (Computer science)

Search Results

Now showing 1 - 5 of 5
  • Thumbnail Image
    Item
    SES : a soils expert system : a thesis presented in fulfilment of the requirements for the degree of Master of Science in Computer Science
    (Massey University, 1988) Todd, E G
    An Expert System Development Methodology is proposed, based on experimentation in developing a soils expert system (SES) which identifies a soil from incomplete field data. Tools for conceptual modeling of the soils domain are examined. The tools developed provide a means of recording the conceptual model of the knowledge from three different view points: the inference structures, the domain objects and the functional aspects. A review of the structures used in the knowledge bases of existing classification problems identifies eleven categories for grouping these structures. Using this information with the conceptual model, a detailed design of the knowledge base for SES is created. This design closely models those structures identified as important in the soils domain ensuring that important knowledge is represented explicitly.
  • Thumbnail Image
    Item
    The use of frames in knowledge-based systems : a thesis submitted in partial fulfilment of the requirements for the degree of Master of Science in Computer Science at Massey University
    (Massey University, 1986) Teahan, William John
    The general aim of this study was to investigate the use of frames as a means of representing knowledge in computer knowledge-based systems. This thesis examines the application of frames to two particular situations, the playing of an opening bid in Bridge, and the recognition of birds from field observations. The Frame Representation Language FRL was used in the implementation of the two different systems. Three aspects of frames are investigated the problems of matching two different frames; the problems of structuring frame systems for searching; and the problem of improving the interface between the frame system and the user of the knowldege base. A comparison is also made of frames with other methods of knowledge representation such as production systems and semantic networks. Finally, further areas of research into the use of frames are suggested such as the extension of frame matching, research into the aspects of knowledge representation and application of frames to specific problems.
  • Thumbnail Image
    Item
    Enriched property ontology for knowledge systems : a thesis presented in partial fulfilment of the requirements for the degree of Master of Information Systems in Information Systems, Massey University, Palmerston North, New Zealand
    (Massey University, 2006) Minchin, Robert
    "It is obvious that every individual thing or event has an indefinite number of properties or attributes observable in it and might therefore be considered as belonging to an indefinite number of different classes of things" [Venn 1876]. The world in which we try to mimic in Knowledge Based (KB) Systems is essentially extremely complex especially when we attempt to develop systems that cover a domain of discourse with an almost infinite number of possible properties. Thus if we are to develop such systems how do we know what properties we wish to extract to make a decision and how do we ensure the value of our findings are the most relevant in our decision making. Equally how do we have tractable computations, considering the potential computation complexity of systems required for decision making within a very large domain. In this thesis we consider this problem in terms of medical decision making. Medical KB systems have the potential to be very useful aids for diagnosis, medical guidance and patient data monitoring. For example in a diagnostic process in certain scenarios patients may provide various potential symptoms of a disease and have defining characteristics. Although considerable information could be obtained, there may be difficulty in correlating a patient's data to known diseases in an economic and efficient manner. This would occur where a practitioner lacks a specific specialised knowledge. Considering the vastness of knowledge in the domain of medicine this could occur frequently. For example a Physician with considerable experience in a specialised domain such as breast cancer may easily be able to diagnose patients and decide on the value of appropriate symptoms given an abstraction process however an inexperienced Physician or Generalist may not have this facility.[FROM INTRODUCTION]
  • Thumbnail Image
    Item
    The role of functional prototyping within the KADS methodology : a thesis presented in partial fulfilment of the requirements for the degree of Master of Science in Computer Science at Massey University
    (Massey University, 1995) Pacitto, Damian
    Knowledge-based systems have until recent times lacked a clear and complete methodology for their construction. KADS was the result of the early 1980's project (ESPRIT-I P1098) which had the aim of developing a comprehensive, commercially viable methodology for knowledge-based system construction. KADS has subsequently proved to be one of the more popular approaches, focusing on the modelling approach to knowledge based system development. One area of the KADS methodology that has not been examined to any great depth is that of model validation. Model validation is the process of ensuring that a derived model is an accurate representation of the domain from which it has been derived from. The two approaches which have been suggested for this purpose within the KADS framework are that of protocol analysis and functional prototyping. This project seeks to apply the second of these choices, that of functional prototyping, to the model of expertise created by da Silva (1994) for model validation purposes. The problem domain is that of farm management, under an joint program of research between the Computer Science, Information Systems and Agricultural Management departments of Massey University. The project took the model of expertise and created a knowledge representation model in compliance with the selected object-oriented paradigm. After this the creation of a functional prototype in a Microsoft Windows based PC environment took place, using Kappa-PC as the application development tool. The validation took place through a demonstration session to a number of domain experts. Conclusions drawn from the experience gained through the creation and use of the prototype are presented, outlining the reasons why functional prototyping was deemed to be an appropriate method for model validation.
  • Thumbnail Image
    Item
    Adding an intelligent component to an existing decision support system : a thesis presented in partial fulfilment of the requirements for the degree of Master of Science in Information Systems at Massey University
    (Massey University, 1996) Jeffries, Anna Elizabeth
    A framework to guide the development of an intelligent component and its integration with an existing decision support system has been proposed. An initial framework was outlined, drawing concepts from the fields of decision support systems, knowledge based systems and intelligent decision support systems. This framework was applied to a problem in the domain of dairy farm management. A prototype intelligent decision support system was developed. Experiences gained during the development process enabled refinements to the framework to be made. The prototype was tested to assess the success of the framework in producing the desired results. The development framework was evaluated based on criteria drawn from relevant literature. The proposed development framework is considered to be a useful tool for intelligent decision support system development from an existing decision support system. Its success is attributed to the integration of methods and techniques drawn from a number of well established methodologies.