Dissertation in fufillment of the degree of MSc(Med), Faculty of Health Sciences, University of the Witwatersrand / Introduction: Measurement of small solute clearance is the objective means of quantifying dose of peritoneal dialysis (PD) and various organisations have issued guidelines on target values. Assessment of PD adequacy involves other factors such as blood pressure control, anaemia management, mineral metabolism, nutritional status and ultrafiltration. Membrane transport characteristic is important for PD prescription on an individual patient basis and is related to patient outcome. In this study the adequacy of PD, using small solute clearance measurement as well as other factors, and membrane characteristics have been assessed and classification of patients using our own reference values is reported for the first time. Nutritional status has been studied and the use of simple tools such as the subjective global assessment has been validated for use in our patients. Materials and Methods: A cross sectional study involving 80 adult continuous ambulatory peritoneal dialysis (CAPD) patients. Peritoneal equilibration test (PET) was performed to assess the membrane characteristics; 24 hour dialysate fluid and urine samples were collected and used for the measurement of solute clearance, while nutritional status was assessed using the subjective global assessment (SGA) instrument, anthropometric measurements and serum albumin estimation. Results: The mean age was 38 ± 12.43 years, 42.3% were females and 86% were blacks. Mean duration on CAPD was 19.8 ± 20.67 months. The mean of 4 hour D/P creatinine was 0.74 ± 0.13 and based on this, 18% were high transporters, 33.8% high average, 36.9% low average and 12% low transporters. Mean kt/v urea was 1.72± 0.32, and the recommended level of 1.7 was achieved by 62.8% of the patients. Mean haemoglobin was 10.99 ± 2.14 g/dl and the recommended target value of 11-12g/dl was reached by 55.8% of the patients. The mean BMI vi was 24.76 ± 3.50, mean Mid Upper Arm Circumference (MUAC) was 28.53±3.89 cm and mean serum albumin was 37.10 ± 7.6 g/l. Based on SGA scores, 42% of our patients were well nourished, 50% moderately undernourished while 8% were severely malnourished. We noted significant correlations between SGA score and BMI and MUAC while there was none with serum albumin level. The mean serum calcium and phosphate levels were within normal though the mean PTH level was higher. Conclusion: The D/P creatinine at 4 hours was higher than those reported in the literature, though the distribution of the transport types was similar. The recommended targets of kt/v and haemoglobin were achieved by the majority of our patients. Mineral metabolism parameters were within normal range. Malnutrition is common and SGA is a reliable method for nutritional assessment in our patients.

The use of inductive learning to extract general rules from examples would be a promising way to overcome the knowledge acquisition bottleneck. Over the last decade, many such techniques have been proposed. None of these have proved to be the efficient, general rule-extractors for complex real-world applications. Recent research has indicated that some kinds of hybrid-learning techniques which integrate two or more learning strategies outperform single learning techniques. In designing such a hybrid-learning method, neural network learning can be expected to be a good partner because it is tolerant for noisy data and is very flexible for approximate data. / This dissertation proposes another such method--a rule extraction method using an artificial neural network (ANN) that is trained by destructive learning. Unlike other published methods, the method proposed here takes advantage of the smart (pruned) network which contains more exact knowledge regarding the problem domain (environment). The method consists of three phases: training, pruning, and rule-extracting. The training phase is concerned with ANN learning, using a general backpropagation (BP) learning algorithm. In the pruning phase, redundant hidden units and links are deleted from a trained network, and then, the link weights remaining in the network are retrained to obtain near-saturated outputs from hidden units. The rule extraction algorithm uses the pruned network to extract rules. / The proposed method is evaluated empirically on three application domains--the MONK's problems, the IRIS-classification data set, and the thyroid-disease diagnosis data set--and its performance is compared with that of other classification and/or machine learning methods. It is shown that for discrete samples, the proposed method outperforms others, while for continuous samples it can beat most other methods with which it is compared. The classifying accuracy of the proposed method is higher than that of either backpropagation learning or the pruned network on which it is based. / Source: Dissertation Abstracts International, Volume: 55-04, Section: B, page: 1526. / Major Professor: R. C. Lacher. / Thesis (Ph.D.)--The Florida State University, 1994.

This dissertation presents Modified Election (or ME) methodology and shows how it may be used to describe the beliefs a human expert would form regarding the answer to a given question, based on the available evidence. For example, the methodology could be used to describe the beliefs a heart specialist would form, regarding the question whether a patient should be put on a low fat, low cholesterol diet, based on whether the patient is overweight, has a family history of heart problems, etc. ME methodology employs statistical methods used to interpret random samples, as well as the concept of a "Modified Election" which is developed in this dissertation. In ME methodology, the numbers of "votes" for the possible outcomes in a modified election are used to weight the different pieces of evidence which might affect an expert's beliefs. / Two other popular formalisms for describing beliefs are Bayesian theory and Dempster/Shafer theory. Certain problematic aspects of these two formalisms which motivated ME methodology are discussed. It is then shown how ME methodology overcomes these problems. ME methodology may be used as the basis for the design of expert systems. An expert system is presented which illustrates how to do this. / Source: Dissertation Abstracts International, Volume: 54-04, Section: B, page: 2068. / Major Professor: Daniel G. Schwartz. / Thesis (Ph.D.)--The Florida State University, 1993.

A framework is presented for the acquisition of domain-specific knowledge from experts. This framework is referred to as the ENVIRONMENTAL HINTING (ENVHINT) framework. ENVHINT attempts to steer the expert's focus to the derivation of expert knowledge by embedding acquisition of expert knowledge in the dynamics of the environment which influenced expertise development. Within this framework, the research focuses on the development of cognitive structures which can be used to develop probing domain-specific questions. / Cognitive structures are developed from urban residents' repertory grids which are based on personal construct theory. A cognitive structure reveals dependencies in the form of construct equivalence classes and implications from one equivalence class to another. / Weights are assigned to the implication lines of a cognitive structure. They are obtained from a fuzzy grid, from which the cognitive structure is derived. The weights allow paths to be accessed according to relevancy of urban concerns. The relevancy strengths of paths are used to derive hinting domain-specific questions for experts. / Source: Dissertation Abstracts International, Volume: 54-04, Section: B, page: 2071. / Major Professor: Wyllis Bandler. / Thesis (Ph.D.)--The Florida State University, 1993.

Much of human reasoning deals with imprecise, incomplete or vague information. However, the currently available commercial data base management systems handle only "exact" data items. Therefore, there is a need for an information system that allows representation and manipulation of imprecise information. Furthermore, it is desirable that an information system provides means for "individualization" of data to reflect the user's perception of data. / The proposed Fuzzy Relational Data Base (FRDB) model based on the research in the fields of relational data bases and theories of fuzzy sets and possibility is designed to satisfy the need for individualization and imprecise information processing. A commercial relational data base (RIM) is used as a host for the implementation of a FRDB system to demonstrate the feasibility of the model. / Source: Dissertation Abstracts International, Volume: 44-11, Section: B, page: 3460. / Thesis (Ph.D.)--The Florida State University, 1983.

The main aim of this dissertation has been to mimic natural language processing capabilities of human beings in a natural language processing system. The design and the development of the Syntax-Semantics analyzer (SS-analyzer) and the use of fuzzy in various language processing stages form the main crux of this dissertation. / The SS-analyzer is made up of two main modules: the syntax module and the semantics module. The SS-analyzer processes the input natural language sentences in an incremental fashion. The syntax and the semantics analyzer work in a coordinated manner to extract the meaning out of the input natural language sentences. This extracted meaning is then represented in a fuzzy relational representation structure. / The semantic interpreter complements the SS-analyzer in determining the meaning of input sentences when they are grammatically incorrect or do not make sense semantically. If the SS-analyzer is unable to determine the meaning of the input sentences, the semantic interpreter uses the contextual knowledge to determine the meaning. A prototype natural language processing system has been developed to test these theories. / Source: Dissertation Abstracts International, Volume: 53-09, Section: B, page: 4783. / Major Professor: L. J. Kohout. / Thesis (Ph.D.)--The Florida State University, 1992.

The successful application of fuzzy reasoning models to fuzzy control systems depends on a number of parameters, such as fuzzy membership functions, fuzzy implication operators, and the fuzzy relation matrix, that are usually decided upon subjectively by an expert operator. The purpose of this dissertation is to develop an intelligent fuzzy control system that combines fuzzy controller and learning mechanism in a hybrid system. Such hybrid system, which allows for imprecise information and/or uncertain environments, is imperative to the process of developing effective robust control systems for a large number of important real-time industrial processes. It is shown in this dissertation that the performance of fuzzy control systems can be improved considerably if the fuzzy reasoning model is supplemented by learning mechanisms. Two learning mechanisms are proposed in this research: one that uses genetic algorithms and the other is based on the utilization of neural networks. The genetic algorithm enables us to generate an optimal set of parameters for the fuzzy reasoning model based on their initial subjective selection. The exploitation of this initial selection, i.e., knowledge of the domain, by the genetic algorithm leads to an improved performance of the fuzzy controller. The neural-fuzzy reasoning model combines the computational paradigms of neural network and fuzzy rule-based reasoning in a hybrid system that also leads to an improved performance of the fuzzy control system. / Source: Dissertation Abstracts International, Volume: 53-07, Section: B, page: 3605. / Major Professor: Abraham Kandel. / Thesis (Ph.D.)--The Florida State University, 1992.

Neural network based word embeddings have demonstrated outstanding results in a variety of tasks, and become a standard input for Natural Language Processing (NLP) related deep learning methods. Despite these representations are able to capture semantic regularities in languages, some general questions, e.g., "what kinds of semantic relations do the embeddings represent?" and "how could the semantic relations be retrieved from an embedding?" are not clear and very little relevant work has been done. In this study, we propose a new approach to exploring the semantic relations represented in neural embeddings based on WordNet and Unified Medical Language System (UMLS). Our study demonstrates that neural embeddings do prefer some semantic relations and that the neural embeddings also represent diverse semantic relations. Our study also finds that the Named Entity Recognition (NER)-based phrase composition outperforms Word2phrase and the word variants do not affect the performance on analogy and semantic relation tasks. / A Thesis submitted to the Department of Computer Science in partial fulfillment of the requirements for the degree of Master of Science. / Summer Semester 2017. / July 17, 2017. / semantic relation, word2vec, word embedding, WordNet / Includes bibliographical references. / Xiuwen Liu, Professor Directing Thesis; Zhe He, Committee Member; Peixiang Zhao, Committee Member.

Modularity in the design and implementation of expert systems relies upon cooperation among the expert systems and communication of knowledge between them. A prerequisite for an effective modular approach is some standard for knowledge representation to be used by the developers of the different modules. In this work we present a schema for knowledge representation, and apply this schema in the design of a rule-based expert system. We also implement a cooperative expert system using the proposed knowledge representation method. / A knowledge representation schema is a formal specification of the internal, conceptual, and external components of a knowledge base, each specified in a separate schema. The internal schema defines the structure of a knowledge base, the conceptual schema defines the concepts, and the external schema formalizes the pragmatics of a knowledge base. The schema is the basis for standardizing knowledge representation systems and it is used in the various phases of design and specification of the knowledge base. Its main tasks are to govern the interface and communication of knowledge between expert systems as well as to support a modular approach in the design of a cooperative expert system. The schema is also used in the stages of testing, validation, and maintenance of a knowledge base. / The conceptual schema is the formal specifications of the domain-dependent semantics and can be implemented using fuzzy semantics. For this purpose, an axiomatic theory of fuzzy semantics is developed and formal methods of specification of concepts using fuzzy semantics are proposed. / A new model of knowledge representation based on a pattern recognition interpretation of implications is developed. This model implements the concept of linguistic variables and can, therefore, emulate human reasoning with linguistic imprecision. / The test case for the proposed schema of knowledge representation is a system for computer-aided design of a man-machine interface. The core of the system is a cooperative expert system composed of two expert systems. This system applies a pattern recognition interpretation of a generalized one-variable implication with linguistic variables. / A process of validation of the system is performed, including testing of the system and verification that the system is acyclic, consistent, and in compliance with its specifications. / Source: Dissertation Abstracts International, Volume: 50-08, Section: B, page: 3580. / Major Professor: Abraham Kandel. / Thesis (Ph.D.)--The Florida State University, 1989.

The process of redistricting involves the division of a land surface into two or more pieces. In a political setting, the districts thus formed provide groups of voters that elect the same public officials. Other types of redistricting applications include the formation of school districts, transportation districts, or water management districts. / In this work we propose a knowledge-based expert system prototype as a solution to the redistricting problem. A number of key issues are addressed by the solution, including equality of population, contiguity, and graphical display of possible districts. In addition, we explore the need for dynamic user interaction within knowledge-based systems and outline a method (the Grouper approach) for dramatically reducing the complexity of the redistricting problem by restricting activity to a specific level of detail. / The prototype solution, a PC-based system implemented using Tecknowledge's M.1 expert system shell, is described in depth with particular emphasis on techniques for minimizing search. An annotated Grouper session is included, as are listings of the knowledge base and supporting C functions. Lastly, there is a discussion of the far-reaching significance of the redistricting problem and promising uses or extensions of the Grouper system in this regard. / Source: Dissertation Abstracts International, Volume: 51-12, Section: B, page: 5975. / Major Professor: Abe Kandel. / Thesis (Ph.D.)--The Florida State University, 1990.