published_or_final_version / abstract / Surgery / Master / Master of Philosophy

Functional parallel programming techniques for feed-forward artificial neural networks trained using backpropagation learning are analyzed. In particular, the Data Parallel Haskell extension to the Glasgow Haskell Compiler is considered as a tool for achieving data parallelism. We find much potential and elegance in this method, and determine that a sufficiently large workload is critical in achieving real gains. Several additional features are recommended to increase usability and improve results on small datasets. / text

Electronic book production is a developing field which is still in its infancy. As such, there is still relatively little material available in the form of design principles or guidelines for the production of such books. It is also extremely complex, in that electronic book designers can take advantage of a number of delivery techniques which are not available to authors of traditional paper-based books. Such techniques include: multimedia (the delivery of text, pictures, sound, and moving pictures); and hypermedia (the linking of reactive information items to form non-linear structures). This research investigates some of the key issues in the design of end-user interfaces to electronic books. Essentially, this centres on three basic problems: the use of metaphors in the design of interfaces to electronic books; models for the design of multimedia pages; and the provision of various knowledge corpus structures. Interface metaphors are investigated through the implementation and evaluation of the book metaphor. Applications were developed which either embedded or did not embed the book metaphor. Subjects used these applications while undertaking a number of information access tasks. Both qualitative and performance data werecollected and some significant results were obtained. Five page models were developed (referred to as: simple; tiled; overlay; oversize; and dynamic) which were used to design a number of page structures. These page structures were evaluated using qualitative measures of user reactions to the various page structures. Seven interface dimensions were measured and again significant results were obtained. To measure the effects of knowledge corpus structure on the design of electronic books three different book structures were created: linear; tree; and network. These were investigated in the light of some common information access tasks. The results indicated that some knowledge corpus structures were more appropriate for certain types of task.

This thesis investigates novel methodologies for modelling, simulation and control of gas turbines using ANNs. In the field of modelling and simulation, two different types of gas turbines are modelled and simulated using both Simulink and neural network based models. Simulated and operational data sets are employed to demonstrate the capability of neural networks in capturing complex nonlinear dynamics of gas turbines. For ANN-based modelling, the application of both static (MLP) and dynamic (NARX) networks are explored. Simulink and NARX models are set up to explore both steady-state and transient behaviours. To develop an offline ANN-based system identification methodology for a low-power gas turbine, comprehensive computer program code including 18720 different ANN structures is generated and run in MATLAB to create and train different ANN models with feedforward multi-layer perceptron (MLP) structure. The results demonstrate that the ANN-based method can be applied accurately and reliably for the system identification of gas turbines. In this study, Simulink and NARX models are created and validated using experimental data sets to explore transient behaviour of a heavy-duty industrial power plant gas turbine (IPGT). The results show that both Simulink and NARX models successfully capture dynamics of the system. However, NARX approach can model gas turbine behaviour with a higher accuracy compared to Simulink approach. Besides, a separate complex model of the start-up operation of the same IPGT is built and verified by using NARX models. The models are set up and verified on the basis of measured time-series data sets. It is observed that NARX models have the potential to simulate start-up operation and to predict dynamic behaviour of gas turbines. In the area of control system design, a conventional proportional-integral-derivative (PID) controller and neural network based controllers consisting of ANN-based model predictive (MPC) and feedback linearization (NARMA-L2) controllers are designed and employed to control rotational speed of a gas turbine. The related parameters for all controllers are tuned and set up according to the requirements of the controllers design. It is demonstrated that neural network based controllers (in this case NARMA-L2) can perform even better than conventional controllers. The settling time, rise time and maximum overshoot for the response of NARMA-L2 is less than the corresponding factors for the conventional PID controller. It also follows the input changes more accurately than the PID. Overall, it is concluded from this thesis that in spite of all the controversial issues regarding using artificial neural networks for industrial applications, they have a high and strong potential to be considered as a reliable alternative to the conventional modelling, simulation and control methodologies. The models developed in this thesis can be used offline for design and manufacturing purposes or online on sites for condition monitoring, fault detection and trouble shooting of gas turbines.

Our understanding of the neural control of breathing-swallowing coordination (BSC) is largely unclear. Although brainstem control is undoubtedly predominant, this research investigated the hypothesis that the cortex becomes increasingly influential in BSC between birth and adulthood. The main paradigm used to test this primary hypothesis was a comparison of BSC in conditions along a continuum of volitional through non-volitional swallowing on the basis of a decreasing level of cortical activation along this continuum. Voluntarily-initiated swallows during wakefulness were at one end of the continuum and reflexively-initiated swallows during sleep were at the other extreme. Non-volitional wakeful swallows were considered between these two conditions. The BSC of ten infants between birth and 1 year of age and twenty adults between the ages of 20 and 75 years was recorded using non-invasive time-locked recording methods. In order to apply the 'continuum-of-volition' paradigm to swallowing conditions in infants, BSC was monitored during nutritive (breast- or bottle-feeding), non-nutritive wake, and sleep swallows. Infants were monitored longitudinally to determine whether maturation of the cortex and corticobulbar tracts during the first year of life influenced the patterns of BSC. In adults, BSC was monitored during three non-nutritive conditions: volitional, spontaneous wake, and sleep conditions. Post-swallow expiration was found to be predominant in all conditions for all participants at all ages. In addition, the infant results revealed that nutritive BSC matured during the first year of life and differed to non-nutritive wakeful BSC, particularly in the first 2 months of life. Non-nutritive wakeful and sleep BSC did not differ from one another. In summary, the infant results support increasing cortical input into volitional nutritive BSC, an early impact of feeding on BSC, and no difference between BSC when asleep and non-volitional non-nutritive swallows when awake. The results obtained from adults revealed that irrespective of the level of arousal, volitional BSC is different to non-volitional BSC. These results imply that cortical influence on BSC is limited to conditions in which swallowing is voluntarily initiated. The combined interpretation of infant and adult results suggest that cortical influence over BSC, although increasing with maturation, is limited to the volitional swallowing conditions of feeding in infants and during non-nutritive but volitional swallows in adults. From this, it can be deduced that the most likely cortical sites involved in BSC are those involved in the voluntary initiation or planning of swallowing. Infant and adult swallowing apnoea duration (SAD) was also compared across all of the above conditions. SAD was influenced by feeding throughout the first year of life but was not influenced by level of arousal at any stage in the first year or in adulthood. Also, SAD did not change with age in any swallowing condition during infancy. However, comparison of non-nutritive wake SAD across the lifespan revealed that SAD of newborns and young adults is shorter than that of elderly adults, with no difference between consecutive age-groups: newborns, one-year-olds, and young adults. These results suggest SAD is largely mature at birth and impervious to descending suprabulbar influence. Finally, the effects of volitional swallowing and level of arousal on peak submental surface electromyography (SEMG) was investigated in adults. Like BSC, submental muscle activity was influenced only by volitional swallowing, being longer for volitional than non-volitional swallows without being influenced by level of arousal. Since peak submental SEMG activity represents a measure of relative hyolaryngeal excursion, these results suggest that the cortex has some degree of influence over this particular feature of pharyngeal-stage swallowing.

No description available.

No description available.

No description available.

No description available.

No description available.