No description available.

No description available.

No description available.

Fuzzy Cognitive Maps (FCMs) are a widely used, neuro-fuzzy based qualitative approach for the modeling of dynamic systems, which allow for both static and dynamic analyses. They are capable of modeling complex systems with nonlinearities and unknown physical behaviour. FCMs describe a given system by means of concepts connected by quantified cause-effect relationships. This dissertation contributes to the subject of computer-driven generation of FCMs that can be used to perform an accurate dynamic analysis of the modeled system. The dynamic analysis provides insights into the degree of presence, and dependencies between the concepts in successive iterations of the simulation of a given FCM model. Such simulation studies could be used to analyze what-if scenarios in the context of decision support and to perform time series predictions. Two research directions within the framework of FCM development, which concern the learning of FCMs from historical data and an aggregation of FCMs that were proposed by multiple experts, are investigated. Several new automated computational methods for data-driven learning and aggregation of FCMs are introduced and empirically evaluated. These methods utilize real-coded genetic algorithms (RCGA)-based optimization. This choice of the optimization vehicle was motivated by their well-documented efficiency in searching large and continuous search spaces, which are inherent to our problem. Experimental evaluation demonstrates that the proposed RCGA-based learning method outperforms modern existing approaches when the dynamic analysis is considered. A novel divide and conquer-based learning strategy to improve scalability of the RCGA approach, is also proposed. This strategy is shown to be competitive or even better than solutions based on the parallelization of the underlying genetic algorithm. The RCGA-based learning method is further extended to provide improved FCMs when the number of connections of the map is known a priori. Experimental evaluation shows that the density-based learning method outperforms the generic RCGA-based approach when using a relatively accurate density estimate, and that both methods are equivalent when the estimate is inaccurate. In addition, a novel method for the aggregation of multiple input FCMs, is proposed. When compared to existing aggregation approaches, this method provides solutions that are more accurate when dynamic analysis is the objective. / Software Engineering and Intelligent Systems

Mode of access: World Wide Web. / Thesis (Ph. D.)--University of Hawaii at Manoa, 2004. / Includes bibliographical references (leaves 167-178). / Electronic reproduction. / Also available by subscription via World Wide Web / xvi, 178 leaves, bound ill. 29 cm

One of the fundamental properties of an antenna is its ability to radiate or receive more energy in one given direction over all the others. This property is called the directivity. The optimization of the directivity usually requires a great deal of attention when an antenna is being designed. There are a number of iterative analytical and experimental procedures available for the optimization of the directivity, however they can be manually intensive, and very time consuming when computer simulation is employed. / Optimization of antenna parameters has been hindered by the need of techniques that prove to be reliable, robust and can search and find a global maximum. Past efforts have focused on techniques confined to small search volumes due to the time overheads of searching. With the increasing utility of the personal computer, techniques have emerged which can search large volumes efficiently and economically. Genetic Algorithms are one such technique. / Genetic Algorithms are an optimization technique based on the mechanics of natural selection, which combines the biological concepts of survival of the fittest among string structures. They operate on a population of candidate solutions and are able to change a number of parameters simultaneously while testing the solutions for goodness-of-fit. They also possess memory so that a good solution can be saved and tested from generation to generation. In this way they are able to quickly find and maintain the best solution to the problem. / A Genetic Algorithm is used to optimize the directivity of a linear array of dipole radiators. Mutual and self-coupling is taken into consideration through the use of the Method of Moments. The inter-element spacing as well as the radiator length are allowed to vary. This gives the optimization many degrees of freedom. The arrays so optimized are verified using a standard industrial antenna software simulation program. The optimized array achieves a directivity of approximately 1.5 dB better than published data for a uniform array of the same size. There is an overall reduction in the length of the array of one wavelength and the currents on the radiating elements are realisable. The final product is a basic computer aided design package capable of optimizing the directivity of a linear antenna array with the only inputs needed being the frequency of operation and the number of dipole elements. / Thesis (MEng(ElectronicsEngineering))--University of South Australia, 2005.

Thesis (PhD) -- University of South Australia, 1998

Thesis (PhD in Computer and Information Science)--University of South Australia, 1995

Thesis (PhD in Computer and Information Science)--University of South Australia, 1995

Thesis (PhD in Computer and Information Science)--University of South Australia, 1995