Immobility is one of the factors associated with the accumulation of respiratory secretion in mechanically ventilated patients. Placing patients in a semi-recumbent position between 30° and 45° and frequent manual turning in every two hours are the standard ventilator nursing care practice adopted worldwide. However, the prevalence of pulmonary complications remains high. The use of continuous lateral rotation therapy (CLRT) to improve drainage of secretion within the lung and the lower airways was proposed and has been investigated in numerous studies. The purposes of this dissertation are (1) to perform a comprehensive systematic review for a critical appraisal of the current evidence on the use of CLRT to prevent pulmonary complications in mechanically ventilated patients, (2) to develop an evidence-based guideline and to assess the implementation potential, and (3) to develop an implementation and evaluation plan for translating the guideline to an adult intensive care unit (ICU) of a teaching hospital in Hong Kong. In order to identify studies that compared CLRT with the standard care, four electronic databases, including CINAHL Plus, Medline, British Nursing Index and PubMed, were searched. 94 studies were identified and eight of them met the inclusion criteria. These studies included one randomized controlled trial (RCT), two non-randomized controlled clinical trials, one pretest-posttest clinical trial and four retrospective cohort studies. The quality of these reviewed studies was assessed by using the appraisal instruments of the Scottish Intercollegiate Guidelines Network. Four of the reviewed studies were graded as high quality. No major adverse patient outcome was reported. Instead, beneficial patient outcomes that reached statistical significance were consistently reported in the CLRT group. There were reductions in ventilator-associated pneumonia (VAP), atelectasis, duration of mechanical ventilation and length of stay. However, its effect on health care cost and mortality was inconclusive. The implementation potential, in terms of the transferability, feasibility, and the cost-benefit ratio, was considered as high in the target setting. Based on the synthesized finding, a CLRT guideline is developed and is proposed to translate into practice. The implementation plan includes a communication plan with stakeholders and a pilot test. The guideline will be revised after the trial run of the proposed innovation for one and a half months. A full-scale controlled trial using a quasi-experimental design will be conducted. The primary outcome is to evaluate whether there is a reduction in the prevalence of VAP after the use of CLRT. According to previous studies, the use of CLRT can lead to a 49% reduction in VAP. The proposed innovation will be considered as clinical effective when similar observation is obtained. / published_or_final_version / Nursing Studies / Master / Master of Nursing

Endotracheal suctioning is a procedure performed on a daily basis in hospitals, and is mostly take place in intensive care units (ICUs). (Annapoorna, 2005; Day et al, 2009). It helps removing sputum or secretion out from patients’ trachea. For patients who are under mechanical ventilation, this procedure is vital to maintain their airway patency when they are intubated with endotracheal tube or tracheostomized (Finucane & Santora, 2003). However, the procedure has its own risk and complications such as hypoxaemia, atelectasis, cardiovascular instability and more (Thomson, 2000). There are in general two types of endotracheal suctioning: open and closed system. As disconnection of mechanical ventilation from patients is needed for open endotracheal suctioning (OES), it has a higher risk of complications. However, the cost for OES is much cheaper compared to the closed system. Although OES is widely used in Hong Kong, there is no evidence-based guideline for nurses to follow. The guideline developed by American Association of Respiratory Care (2010) is lack of specificity on the target population and its recommendations were based on mixed literatures targeting on adult and infant patients. Therefore, the aim of this dissertation is to develop an evidence-based guideline for OES in adult patients under mechanical ventilation in ICU. To develop a guideline for OES, search was performed in multiple electronic databases (British Nursing Index, CINAHL, Cochrane Library, Ovid MEDLINE, and PubMed) with keywords related to OES and its complications. A total of 457 studies fulfilled the inclusion criteria and 11 of them were selected. The selected studies were evaluated by quality appraisal checklists, which are developed by Scottish Intercollegiate Guidelines Network (SIGN). Data were extracted for developing the guideline. Evidence have shown that the incidence of post-OES hypoxemia can be reduced by performing hyperoxygenation with 100% oxygen for 4-6 breaths prior and after each open endotracheal suction, accompanying with hyperinflation with 150% of patient’s tidal volume at most 8 breaths/40 seconds delivered by ventilator and prohibiting normal saline instillation into trachea for diluting the sputum. The grades of the recommendations in the guideline were rated with using of the SIGN grading system. The implementation potential was analyzed by the patients’ characteristics, transferability of the findings, feasibility of implementation and cost-benefit ratio. A 12-month implementation program was developed including communication with stakeholders, 4-week pilot testing, and training of ICU staffs, and implementation of OES guideline. The effectiveness of the guideline will be evaluated based on the primary outcome (i.e. oxygen level in blood) for detecting the incidence of hypoxemia. Also, the acceptability of the guideline, compliance of the guideline, financial cost reduction and better quality of service will be used as other evaluation indicators. / published_or_final_version / Nursing Studies / Master / Master of Nursing

Not available / text

Not available / text

Artificial Neural Networks (ANNs) have been developed for many applications but no detailed study has been made in the measure of their quality such as efficiency and complexity using appropriate metrics. Without an appropriate measurement, it is difficult to tell how an ANN performs on given applications. In addition, it is difficult to provide a measure of the algorithmic complexity of any given application. Further, it is difficult to make use of the results obtained in an application to predict the ANN's quality in a similar application. This research was undertaken to develop metrics, named Neural Metrics, that can be used in the measurement, construction and specification of backpropagation based supervised feedforward ANNs for applied science and engineering applications. A detailed analysis of backpropagation was carried out with a view to studying the mathematical definitions of the proposed metrics. Variants of backpropagation using various optimisation techniques were evaluated with similar computational and metric analysis. The research involved the evaluation of the proposed set of neural metrics using the computer implementation of training algorithms across a number of scientific and engineering benchmark problems including binary and real type training data. The result of the evaluation, for each type of problem, was a specification of values for all neural metrics and network parameters that can be used to successfully solve the same type of problem. With such a specification, neural users can reduce the uncertainty and hence time in choosing the appropriate network details for solving the same type of problem. It is also possible to use the specified neural metric values as reference points to further the experiments with a view to obtaining a better or sub-optimal solution for the problem. In addition, the generalised results obtained in this study provide users not only with a better understanding of the algorithmic complexity of the problem but also with a useful guideline on predicting the values of metrics that are normally determined empirically. It must be emphasised that this study only considers metrics for assessment of construction and off-line training of neural networks. The operational performance (e.g. on-line deployment of the trained networks) is outside the scope. Operational results (e.g. CPU time and run time errors) on training the networks off-line were obtained and discussed for each type of application problem.

<p> In this dissertation, I introduce modularization as a means of efficiently solving problems represented by dynamic Bayesian networks and study the properties and effects of modularization relative to traditional solutions. Modularizing a Bayesian filter allows its results to be calculated faster than a traditional Bayesian filter. Traditional Bayesian filters can have issues when large problems must be solved within a short period of time. Modularization addresses this issue by dividing the full problem into a set of smaller problems that can then be solved with separate Bayesian filters. Since the time complexity of Bayesian filters is greater than linear, solving several smaller problems is cheaper than solving a single large problem. The cost of reassembling the results from the smaller problems is comparable to the cost of the smaller problems. This document introduces the concept of both exact and approximate modular Bayesian filters and describes how to design each of the elements of a modular Bayesian filters. These concepts are clarified by using a series of examples from the realm of vehicle state estimation and include the results of each stage of the algorithm creation in a simulated environment. A final section shows the implementation of a modular Bayesian filter in a real-world problem tasked with addressing the problem of vehicle state estimation in the face of transitory sensor failure. This section also includes all of the attending algorithms that allow the problem to be solved accurately and in real-time.</p>

M. Tech. Computer Science / This dissertation reports on the development of a new game playing technique based on Probabilistic Distance clustering (pd-clustering) method to evolve an Awale game player. Game playing is one classic and complex problems of artificial intelligence that has attracted the attention of researchers in computer science field of study.

This dissertation is concerned with the development of neural network-based methods to the control of robot manipulators and focusses on three different approaches for this purpose. In the first approach, an implementation of an intelligent adaptive control strategy in the execution of complex trajectory tracking tasks by using multilayer neural networks is demonstrated by exploiting the pattern classification capability of these nets. The network training is provided by a rule-based controller which is programmed to switch an appropriate adaptive control algorithm for each component type of motion constituting the overall trajectory tracking task. The second approach is based on the capability of trained neural networks for approximating input-output mappings. The use of dynamical networks with recurrent connections and efficient supervised training policies for the identification and adaptive control of a nonlinear process are discussed and a decentralized adaptive control strategy for a class of nonlinear dynamical systems with specific application to robotic manipulators is presented. An effective integration of the modelling of inverse dynamics property of neural nets with the robustness to unknown disturbances property of variable structure control systems is considered as the third approach. This methodology yields a viable procedure for selecting the control parameters adaptively and for designing a model-following adaptive control scheme for a class of nonlinear dynamical systems with application to robot manipulators.

published_or_final_version / Botany / Master / Master of Philosophy

published_or_final_version / Computer Science / Master / Master of Philosophy