published_or_final_version / Electrical and Electronic Engineering / Doctoral / Doctor of Philosophy

published_or_final_version / Mechanical Engineering / Doctoral / Doctor of Philosophy

published_or_final_version / Mechanical Engineering / Doctoral / Doctor of Philosophy

published_or_final_version / Industrial and Manufacturing Systems Engineering / Doctoral / Doctor of Philosophy

Six alkalinity and oxidation classes of fresh igneous rocks were correlated with trace elements in rock chip samples from temporally and spatially associated ore deposits. Learning vector quantization and back-propagation artificial neural networks correctly classified 100 percent of whole rock oxides and 99 percent of mineralized samples; discriminant analysis correctly classified 96 and 83 percent, respectively. The high degree of correlation between chemistries of igneous rocks and related mineralization implies genetic links between magmatic processes or sources and the ore deposits studied. The petrochemical classification was evaluated by assigning 43 deposits to classes defined on eight variation diagrams, training neural networks to classify analyses of 569 igneous and 887 mineralized samples, and testing the networks on their ability to classify new data. Whole rock analyses were obtained from mining districts in which trace element geochemistry was also available. Half the data was eliminated using five alteration filter graphs. The K₂O and Fe₂O₃/FeO versus SiO₂ diagrams and iron mineralogy best defined alkalinity and oxidation classes. Neural networks trained with 90, 80, 70, or 50 percent of the samples correctly classified 81 to 100 percent of randomly withheld data. SiO₂/K₂O ratios of alkali-calcic igneous rocks are 14-20 and of calc-alkalic 20-30. Fe₂O₃/FeO ratios are >0.8 with abundant magnetite and sphene for oxidized, 0.5-1.2 with magnetite, sphene, and rare ilmenite for weakly oxidized, and <0.6 with ilmenite only in reduced subclasses. Lead-zinc-silver deposits as at Tombstone and Tintic are related to oxidized alkali-calcic igneous rocks. Polymetallic lead-zinc-copper-tin-silver deposits, such as Santa Eulalia and Tempiute, Nevada, are associated with weakly oxidized alkali-calcic rocks. Tin-silver deposits of Llallagua and Potosi are correlated with reduced alkali-calcic intrusives. Porphyry copper deposits as at Ray and Sierrita are connected with oxidized calc-alkalic plutons. Gold-rich porphyry copper deposits, such as Copper Canyon and Morenci are linked to weakly oxidized calc-alkalic plutons. Disseminated gold deposits, such as Chimney Creek, Nevada, are temporally and chemically correlated with reduced calc-alkalic igneous rocks, although physical connections between plutons and Carlin-type deposits remain unconfirmed. Magma series classification and neural networks have profound applications and implications to exploration, alteration and zoning studies, and metallogenesis.

An optical computer which performs the classification of an input object pattern into one of two learned classes is designed and demonstrated. The classifier is an optical implementation of a neural network model of computation featuring learning, self-organization, and decision-making competition. Neural computation is discussed including models for learning networks and motivation for optical implementation. A discussion of photorefractive crystal holographic storage and adaptation is presented followed by experimental results of writing and erasing gratings in several different crystals. The optical network features a photorefractive crystal to store holographic interconnection weights and an opto-electronic circuit to provide a means of competitive decision making and feedback. Results of the optical learning network and its operation as an associative memory are followed by extensions of the architecture to allow improved performance and greater flexibility.

Huge amounts of data are being collected as a result of the increased use of mobile telecommunications. Insight into information and knowledge derived from these databases can give operators a competitive edge in terms of customer care and retention,<br /> marketing and fraud detection. One of the strategies for fraud detection checks for signs of questionable changes in user behavior. Although the intentions of the mobile phone users cannot be observed, their intentions are reflected in the call data which define usage patterns. Over a period of time, an individual phone generates a large pattern of use. While call data are recorded for subscribers for billing purposes, we are making no prior assumptions about the data indicative of fraudulent call patterns, i.e. the calls made for billing purpose are unlabeled. Further analysis is thus, required to be able to isolate fraudulent usage. An unsupervised learning algorithm can analyse and cluster call patterns for each subscriber in order to facilitate the fraud detection process.<br /> <br /> This research investigates the unsupervised learning potentials of two neural networks for the profiling of calls made by users over a period of time in a mobile telecommunication network. Our study provides a comparative analysis and application of Self-Organizing Maps (SOM) and Long Short-Term Memory (LSTM) recurrent neural networks algorithms to user call data records in order to conduct a descriptive data mining on users call patterns.<br /> <br /> Our investigation shows the learning ability of both techniques to discriminate user call patterns / the LSTM recurrent neural network algorithm providing a better discrimination than the SOM algorithm in terms of long time series modelling. LSTM discriminates different types of temporal sequences and groups them according to a variety of features. The ordered features can later be interpreted and labeled according to specific requirements of the mobile service provider. Thus, suspicious call behaviours are isolated within the mobile telecommunication network and can be used to to identify fraudulent call patterns. We give results using masked call data<br /> from a real mobile telecommunication network.

Thesis submitted in compliance with the requirements for the Doctor's Degree in Technology: Electrical Engineering, Technikon Natal, 1999. / This study relates to applications of static artificial neural networks (ANNs) to two basic problems of process control: (a) process model identification, and (b) optimal controller tuning. The emphasis is on model identification, where several novel techniques are introduced. A review of the use of ANNs for determining optimal controller settings is included as a logical adjunct which would make the complete system suitable for realisation as a portable or networked system. Three methods for obtaining good approximations for the parameters of first-order processes with long dead time using artificial neural networks (ANNs) are proposed and described. These are termed in this study: time-domain, frequency-domain and model-based methods. In each case the aim was to develop a brief one-shot test that could be applied with minimal disturbance to a closed loop control system. These methods build on existing techniques, but introduce the following novel aspects: 2. The frequency-domain method makes use of the first 81 components of the FFT without further selection as input to a static ANN to yield process parameter estimates. 3. The model-based method uses a simple single-neuron implementation of an ARX model and uses a static ANN to relate process parameter values to the weights of this neuron. In making the analysis, the process input and output are applied repetitively to the neuron model with delays getting progressively larger. Useful effects arising from this are explored. A technique in which ANN training sets are slightly distorted in a random way during training of a radial basis function is developed as part of the time- and frequencydomain methods. The benefits arising from this technique are demonstrated. These experimental ANN-based control methods are evaluated by means of simulations in which accuracy in the presence of measurement noise and performance with higher order processes is measured and analysed. Although the main theme of this study is first-order-plus-dead-time (FOPDT) processes, the full autotuning scheme is tested with some representative higher order processes. Finally, the composition of a complete autotuning scheme is proposed which includes the automatic generation of controller parameters by means of ANN s. / M

Dissertation submitted in compliance with the requirements for Master's Degree in Technology: Electrical Engineering (Light Current), Technikon Natal, 2002. / M

There are three main results in this dissertation. They are PLS-completeness of discrete Hopfield network convergence with eight different restrictions, (degree 3, bipartite and degree 3, 8-neighbor mesh, dual of the knight's graph, hypercube, butterfly, cube-connected cycles and shuffle-exchange), exponential convergence behavior of discrete Hopfield network, and simulation of Turing machines by discrete Hopfield Network.