No description available.

This thesis is concerned with measuring and predicting the performance and effectiveness of a data fusion process. Its central proposition is that information entropy may be used to quantify concisely the effectiveness of the process. The personal and original contribution to that subject which is contained in this thesis is summarised as follows: The mixture of performance behaviours that occur in a data fusion system are described and modelled as the states of an ergodic Markov process. An new analytic approach to combining the entropy of discrete and continuous information is defined. A new simple and accurate model of data association performance is proposed. A new model is proposed for the propagation of information entropy in an minimum mean square combination of track estimates. A new model is proposed for the propagation of the information entropy of object classification belief as new observations are incorporated in a recursive Bayesian classifier. A new model to quantify the information entropy of the penalty of ignorance is proposed. New formulations of the steady state solution of the matrix Riccati equation to model tracker performance are proposed.

Text categorization (TC) is the task of automatically categorizing textual digital documents into pre-set categories by analyzing their contents. The purpose of this study is to develop an effective TC model to resolve the difficulty of automatic classification. In this study, two primary goals are intended. First, a Hidden Markov Model (HAM is proposed as a relatively new method for text categorization. HMM has been applied to a wide range of applications in text processing such as text segmentation and event tracking, information retrieval, and information extraction. Few, however, have applied HMM to TC. Second, the Library of Congress Classification (LCC) is adopted as a classification scheme for the HMM-based TC model for categorizing digital documents. LCC has been used only in a handful of experiments for the purpose of automatic classification. In the proposed framework, a general prototype for an HMM-based TC model is designed, and an experimental model based on the prototype is implemented so as to categorize digitalized documents into LCC. A sample of abstracts from the ProQuest Digital Dissertations database is used for the test-base. Dissertation abstracts, which are pre-classified by professional librarians, form an ideal test-base for evaluating the proposed model of automatic TC. For comparative purposes, a Naive Bayesian model, which has been extensively used in TC applications, is also implemented. Our experimental results show that the performance of our model surpasses that of the Naive Bayesian model as measured by comparing the automatic classification of abstracts to the manual classification performed by professionals.

The asymptotic properties of discrete time stochastic systems operating under feedback is addressed. It is assumed that a Markov chain $ Phi$ evolving on Euclidean space exists, and that the input and output processes appear as functions of $ Phi$. The main objectives of the thesis are (i) to extend various asymptotic properties of Markov chains to hold for arbitrary initial distributions; and (ii) to develop a robustness theory for Markovian systems. / A condition called local stochastic controllability, a generalization of the concept of controllability from linear system theory, is introduced and is shown to be sufficient to ensure that the first objective is met. The second objective is explored by introducing a notion of convergence for stochastic systems and investigating the behavior of the invariant probabilities corresponding to a convergent sequence of stochastic systems. / These general results are applied to two previously unsolved problems: The asymptotic behavior of linear state space systems operating under nonlinear feedback, and the stability and asymptotic behavior of a class of random parameter AR (p) stochastic systems under optimal control.

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

Thesis (PhD)--University of South Australia, 1997

The Hamiltonian cycle problem (HCP) can be succinctly stated as: "Given a graph, find a cycle that passes through every single vertex exactly once, or determine that this cannot be achieved". Such a cycle is called a Hamiltonian cycle. The HCP is a special case of the better known Travelling salesman problem, both of which are computationally difficult to solve. An efficient solution to the HCP would help solving the TSP effectively, and therefore would have a great impact in various fields such as computer science and operations research. In this thesis, we obtain novel theoretical results that approach this discrete, deterministic, problem using tools from stochastic processes, matrix analysis, and graph theory. / PhD Doctorate

This thesis presents the potential opportunities of global asset allocation and the possible enhancement of these opportunities from using a Markov Switching Model. The thesis extends upon previous conditional asset pricing studies in global asset allocation, such as those done by Ilamnen (1995), Harvey, Solnik and Zhou (1992) and Bilson (1993), where expected future returns are forecast based on conditional variables. The finding of these studies, and many others, are combined with the works on Markov Switching models and market segmentation theories to create a uniform structure for analysing regime switching properties in currencies, international equities and international bond markets. This thesis is segregated into 4 major sections. The chapters 1-4 develop a unified framework that is used in the analysis of markets. The chapters 5-7 are focused on currencies, international equities and international bonds. For each market a model is constructed that is based upon the structure proposed by Frankel and Froot (1988). In this model the market is segmented into two groups ?? value based investors and momentum based investors. To replicate this structure, a two regime Markov Switching model is used, where one regime is constructed as a value regime and the second is constructed as a momentum regime. These models are then compared to linear versions of the models, to see whether there is any additional benefit to the application of regime switching methods. In conjunction with testing the potential benefits of the Markov Regime Switching process, this study also investigates the very nature, or characteristics of regime switching in the international markets. This is undertaken though some alternate models and enhancements to see whether there is any predictability, or characterisations can be made of the switching process. To ensure a comprehensive analysis, several analytical methods have been used, including extensive econometric modelling, statistical analysis of forecasts and portfolio back testing. A number of conclusions can be drawn from the results. Firstly it appears that there is substantial evidence of regime switching in international markets, such as that shown in a Frankel-Froot framework. This in turn has major implication for the understanding of the way in which international markets function, and further the empirical evidence supports many of the anecdotal observations of market based participants. Secondly, there appears to be a strong level of economic relevance to the modelling. The models are shown to generate a theoretical economic profit, which shows that the international markets are only semi efficient. Further, forecasts generated from the Markov Switching models outperform the linear counterparts in economic significance in portfolio tests. However, for both equities and bonds, the general accuracy of the forecast tends to be inferior to the linear counterparts. Finally, the nature of regime switching is investigated in detail, particularly in reference to 3 potential drivers ?? greed, fear and success. The evidence shows that these can help explain the characteristics of regime switching, as in some cases potentially adding economic value. However, it seems that success is more important than a broader economic environment.

Project report (M.S.)--Virginia Polytechnic Institute and State University, 1990. / Abstract. Includes bibliographical references (leaves 99-100). Also available via the Internet.

Thesis (Ph.D.) -- University of Adelaide, Dept. of Statistics, 1978.