Particle swarm optimisation (PSO) is a stochastic, population-based optimisation algorithm. PSO has been applied successfully to a variety of domains. This thesis examines the behaviour of PSO when applied to high dimensional optimisation problems. Empirical experiments are used to illustrate the problems exhibited by the swarm, namely that the particles are prone to leaving the search space and never returning. This thesis does not intend to develop a new version of PSO speci cally for high dimensional problems. Instead, the thesis investigates why PSO fails in high dimensional search spaces. Four di erent types of approaches are examined. The rst is the application of velocity clamping to prevent the initial velocity explosion and to keep particles inside the search space. The second approach selects values for the acceleration coe cients and inertia weights so that particle movement is restrained or so that the swarm follows particular patterns of movement. The third introduces coupling between problem variables, thereby reducing the swarm's movement freedom and forcing the swarm to focus more on certain subspaces within the search space. The nal approach examines the importance of initialisation strategies in controlling the swarm's exploration to exploitation ratio. The thesis shows that the problems exhibited by PSO in high dimensions, particularly unwanted particle roaming, can not be fully mitigated by any of the techniques examined. The thesis provides deeper insight into the reasons for PSO's poor performance by means of extensive empirical tests and theoretical reasoning. / Dissertation (MSc)--University of Pretoria, 2017. / Computer Science / MSc / Unrestricted

South Africa is a developing country with great potential to be leaders in technology and research, especially in the medical field. Rural areas in many countries do not have access to basic healthcare services due to the distance and inaccessibility of these services. Currently people living in the rural areas in South Africa are required to rely on the people within the area, who may not be trained; on doctors who make house calls, who may not be able to access the patient in time or on finding transport to the nearest hospital, which may be hundreds of kilometres away. This leads to many rural residents not seeking aid for aliments thereby often lowering life expectancy. South Africa has many world-renowned medical practitioners who would be able to assist the residents in these areas if there were methods for observation and recording of health statuses without the need for either party to travel. This dissertation studied and developed a method to assist not only the residents in rural areas, but also urban residents to record their vital signs without the assistance of a licenced medical practitioner, to upload the data to a database and to then allow the data to be viewable by the medical practitioner who may be situated elsewhere in South Africa or the world. This system allows for the elimination of human error when recording vital sign data as recording is not done through human intervention. Through the use of communications technologies such as Bluetooth, NFC and Wi-Fi a system was designed which ensures that a patient can record medical data without the presence of a medical practitioner, the patient can access previous health records and readings and the patient can give a new medical practitioner a full medical history. The patient's data has been secured using AES and RSA encryption as well as verification through hash values at all points of transfer and access is granted to the patients' medical data only through the patient or a licenced medical practitioner. The data recording and transfer has been completed taking into consideration all the medical legislation and laws in South Africa. This system allows the South African medical health sector to service all South Africa residents, including the residents in rural areas. / Dissertation (MEng)--University of Pretoria, 2016. / Electrical, Electronic and Computer Engineering / MEng / Unrestricted

Most heat transfer tubes are designed for either fully uniform wall temperature or fully uniform wall heat flux boundary conditions under forced convection. Several applications, including but not limited to the solar collectors of renewable energy systems, do however operate with non-uniform boundary conditions. Limited research has been conducted on non-uniform wall heat flux heat transfer coefficients in circular tubes, especially for mixed convection conditions. Such works are normally numerical in nature and little experimental work is available. In this experimental investigation the effects of the circumferential heat flux distribution and heat flux intensity on the single phase (liquid) internal heat transfer coefficient were considered for a horizontal circular tube. Focus was placed on the laminar flow regime of water within a stainless steel tube with an inner diameter of 27.8 mm and a length to diameter ratio of 72. Different outer wall heat flux conditions, including fully uniform and partially uniform heat fluxes were studied for Reynolds numbers ranging from 650 to 2 600 and a Prandtl number range of 4 to 7. The heat flux conditions included 360˚ (uniform) heating, lower 180˚ heating, upper 180˚ heating, 180˚ left and right hemispherical heating, lower 90˚ heating, upper 90˚ heating and slanted 180˚ heating. Depending on the angle span of the heating, local heat fluxes of 6 631 W/m2 , 4 421 W/m2 , 3 316 W/m2 , 2 210 W/m2 and 1 658 W/m2 were applied. Results indicate that the local and average steady state Nusselt numbers are greatly influenced by the applied heat flux position and intensity. Highest average heat transfer coefficients were achieved for case where the applied heat flux was positioned on the lower half (in terms of gravity) of the tubes circumference, while the lowest heat transfer coefficients were achieved when the heating was applied to the upper half of the tube. Variations in the heat transfer coefficient were found to be due to the secondary buoyancy induced flow effect. The relative thermal performance of the different heating scenarios where characterised and described by means of newly developed heat transfer coefficient correlations for fully uniform heating, lower 180° heating, and upper 180° heating. / Dissertation (MEng)--University of Pretoria, 2018. / Mechanical and Aeronautical Engineering / MEng / Unrestricted

Traditional manual survey methods for collecting reliable origin-destination data to develop large strategic transport model is notoriously expensive and the sample sizes are often relatively small. Arguably, the least reliable data required for the development of strategic traffic models is the origin-destination data. Recent technological advances, such as probe data from on-board devices, have been successful in providing data for some needs such as journey times and routing options. However, varying degrees of success have been achieved in obtaining reliable origin-destination (OD) data from these new technologies. Automatic Number Plate Recognition (ANPR) is one if the newer technologies that could be used to collect large-scale data sets over the large study areas that strategic traffic models cover. The aim of this study is to examine ANPR data collected from the Gauteng Freeway Improvement Project's (GFIP) Open Road Tolling (ORT) gantries in terms of its accuracy and uses in the development and improvement of strategic traffic models. Of particular interest is the use of the ANPR data to contribute towards the improvement of the distribution of trips in the OD matrices. This is achieved by developing methodologies to derive comparable gantry to gantry traffic volumes from the ANPR data and the GFIP traffic model. The above comparisons enabled the undertaking of a post opening project evaluation of the GFIP traffic model's 2015 forecasts using as many characteristics of the traffic flows and patterns that can be derived from the ANPR data. Characteristics such as traffic volumes and journey times are directly comparable with standard traffic model outputs. Tracking vehicles between gantries enabled the calculation of the number of trips that travel between gantry pairs giving rise to gantry-to-gantry (G2G) trips, which can be represented in a G2G count matrix. This G2G count matrix has probably the most beneficial data that can be derived from the ANPR systems as it contains an "accurate" element of the trip distribution on the road network. A methodology was developed to derive equivalent trip matrices from a traffic model's select-link trip matrices where the links are those where the gantry (ANPR camera) is located. The sums of the trips in the derived sub-matrices match the G2G counts. This enabled the comparison between the modelled trip distribution represented by the select link to select link (SL2SL) volumes and the actual ANPR G2G counts. This is in fact a comparison of a portion of the model's distribution to actual, comprehensive data. This study demonstrates that ANPR data has the potential to improve strategic traffic models. The automation of the processes to derive the SL2SL assigned volumes from the models and combining it with existing matrix estimation techniques will enhance the trip distribution in the output trip matrix. The current practice of using individual traffic counts in matrix estimation has the adverse tendency to affect the trip distribution. Hence, the recommendation to use traffic counts in matrix estimation to traffic counts with caution. / Dissertation (MEng)--University of Pretoria, 2017. / Civil Engineering / MEng / Unrestricted

The demands of railway transport have been changing over the 150 years of existence of this type of transport in South Africa, specifically the performance requirements of the formation to cater for new traffic requirements. As such, it is important to assess the condition of this vital part of a railway track. This dissertation covers a research project conducted on two railway lines in which measurements of ground vibration were conducted in order to perform geophysical analysis and characterise the formation based on the results obtained. Measurements were taken on a 26 ton axle load track (Coal line, at Bloubank) and on a 20 ton axle load track (at Amandelbult) in South Africa. Planning and implementation of several test procedures to characterise track formation require considerable effort to minimize the impact on railway operations. Coupled with track occupation and the destructive nature of some of the test procedures, it is relevant to investigate alternative testing techniques to address the issues stated above. The use of surface waves for geotechnical characterization of sites is increasing worldwide. Applications to railway engineering have so far been limited to light load, high speed lines to minimize the use of poor geomaterials with reduced Rayleigh wave velocity. Four sites were identified where trains are operated at heavy loads, with the formation condition varying from poor to good. Seismic testing (geophysical) and conventional testing (deflection measurements) were performed at the identified sites. Seismic measurements were recorded using geophones as receivers, coupled to an amplifier and a computer. The source of the seismic events was the trains operating on the track and a hammer for impact testing. For the deflection measurements, the Remote Video Monitoring (RVM) technique was adopted. Dispersion analysis of the ground vibration experimental data was conducted using the multiple receiver method. The main conclusions reached with the analysis indicated that: __ Dispersion analysis had a good correlation with the formation deflection analysis; __ Phase velocity can be used as an indicator of the quality of a certain site; __ There are limitations when using trains as the energy source in terms of the generation of excitation frequency, which greatly reduces the phase velocity information in individual layers in the formation (i.e. wavelengths are not short enough). / Dissertation (MSc)--University of Pretoria, 2016. / Civil Engineering / MSc / Unrestricted

Research shows that software projects have a high failure rate. User involvement has been identified as one of the most important success factors for software projects. User experience (UX) practices have been shown to engender several benefits with respect to the implementation and delivery of information systems. However, the institutionalisation of UX within organisations remains low. The question thus arises on why the managers of software programmes or projects neglect to incorporate UX practices into their teams� information systems development methodologies (ISDMs). This dissertation presents a study that investigated the perceptions of software programme or project managers in large South African enterprises about UX and its related concepts, its benefits, and the factors that restrict the adoption of associated practices. Interviews were conducted with six software programme or project managers working for large companies in six different industries. The main contribution is an explanation of the potential reasons for the lack of integration of UX activities into software development projects. The study finds that UX is often disregarded because the quality of software solutions as perceived by its users is not typically a measure of success for the project. A secondary contribution is an appraisal of eight potential instruments for persuading non-UX IT practitioners to integrate UX activities into their software projects. Results show that the demonstration of credible business cases and coherent recommendations from UX specialists have the highest power to persuade. / Dissertation (MIS)--University of Pretoria, 2017. / Informatics / MIT / Unrestricted

Road safety is a serious problem in many countries and affects the lives of many people. Improving road safety starts with the drivers, and the best way to make them change their habits is to offer incentives for better, safer driving styles. This project aims to make that possible by offering a means to calculate a quantified indicator of how safe a driver's habits are. This is done by developing an on-board, visual road-sign recognition system that can be coupled with a vehicle tracking system to determine how often a driver violates the rules of the road. The system detects stop signs, red traffic lights and speed limit signs, and outputs this data in a format that can be read by a vehicle tracking system, where it can be combined with speed information and sent to a central database where the driver safety rating can be calculated. Input to the system comes from a simple, standard dashboard mounted camera within the vehicle, which generates a continuous stream of images of the scene directly in front of the vehicle. The images are subjected to a number of cascaded detection sub-systems to determine if any of the target objects (road signs) appear within that video frame. The detection system software had to be optimized for minimum false positive detections, since those will unfairly punish the driver, and it also had to be optimized for speed to run on small hardware that can be installed in the vehicle. The first stage of the cascaded system consists of an image detector that detects circles within the image, since traffic lights and speed signs are circular and a stop sign can be approximated by a circle when the image is blurred or the resolution is lowered. The second stage is a neural network that is trained to recognize the target road sign in order to determine which road sign was found, or to eliminate other circular objects found in the image frame. The output of the neural network is then sent through an iterative filter with a majority voted output to eliminate detection 'jitter' and the occasional incorrect classifier output. Object tracking is applied to the 'good' detection outputs and used as an additional input for the detection phase on the next frame. In this way the continuity and robustness of the image detector are improved, since the object tracker indicates to it where the target object is most likely to appear in the next frame, based on the track it has been following through previous frames. In the final stage the detection system output is written to the chosen pins of the hardware output port, from where the detection output can be indicated to the user and also used as an input to the vehicle tracking system. To find the best detection approach, some methods found in literature were studied and the most likely candidates compared. The scale invariant feature transform (SIFT) and speeded up robust features (SURF) algorithms are too slow compared to the cascaded approach to be used for real-time detection on an in-vehicle hardware platform. In the cascaded approach used, different detection stage algorithms are tested and compared. The Hough circle transform is measured against blob detection on stop signs and speed limit signs. On traffic light state detection two approaches are tested and compared, one based on colour information and the other on direct neural network classification. To run the software in the user's vehicle, an appropriate hardware platform is chosen. A number of promising hardware platforms were studied and their specifications compared before the best candidate was selected and purchased for the project. The developed software was tested on the selected hardware in a vehicle during real public road driving for extended periods and under various conditions. / Dissertation (MEng)--University of Pretoria, 2017. / Electrical, Electronic and Computer Engineering / MEng / Unrestricted

With the increase in wireless technology devices and mobile users, wireless radio spectrum is coming under strain. Networks are becoming more and more congested and free usable spectrum is running out. This creates a resource allocation problem. The resource, wireless spectrum, needs to be allocated to users in a manner such that it is utilised efficiently and fairly. The objective of this research is to find a solution to the resource allocation problem in radio networks, i.e to increase the efficiency of spectrum utilisation by making maximum use of the spectrum that is currently available through taking advantage of co-existence and exploiting interference limits. The solution proposed entails adding more secondary users (SU) on a cognitive radio network (CRN) and having them transmit simultaneously with the primary user. A typical network layout was defined for the scenario. The interference temperature limit (ITL) was exploited to allow multiple SUs to share capacity. Weighting was applied to the SUs and was based on allowable transmission power under the ITL. Thus a more highly weighted SU will be allowed to transmit at more power. The weighting can be determined by some network-defined rule. Specific models that define the behaviour of the network were then developed using queuing theory, specifically weighted processor sharing techniques. Optimisation was finally applied to the models to maximize system performance. Convex optimization was deployed to minimize the length of the queue through the power allocation ratio. The system was simulated and results for the system performance obtained. Firstly, the performance of the proposed models under the processor-sharing techniques was determined and discussed, with explanations given. Then optimisation was applied to the processor-sharing results and the performance was measured. In addition, the system performance was compared to other existing solutions that were deemed closest to the proposed models. / Dissertation (MEng)--University of Pretoria, 2017. / Electrical, Electronic and Computer Engineering / MEng / Unrestricted

Extensive work has been done on characterising convective heat transfer and pressure drop in smooth tubes in the laminar and turbulent flow regimes. However, little work was completed in the transitional flow regime. In all previous transitional studies, experiments that were conducted between the laminar and turbulent flow regimes were with mixed convection in the laminar flow regime and not in the forced convection flow regime. The secondary flow that occurs during mixed convection should most probably influence the characteristics in the transitional flow regime. It can therefore be expected that the transitional flow characteristics of forced convection and mixed convection will be different. However, the transitional characteristics of forced convection flow have not yet been determined. The purpose of this study was therefore to determine the heat transfer and pressure drop transitional characteristics specifically in the forced convection flow regime. Furthermore, to focus on determining these factors for a circular, horizontal smooth tube for fully developed flow. The characteristics were determined in an experimental set-up through which flow occurred through a test section consisting of a horizontal and circular smooth tube. The test-section inside diameter was 4.04 mm, and the tube length was 8.4 m. Water was used as the test fluid and was circulated through the test section which was heated at a constant heat flux. A calming section with a square edge inlet was upstream of the test section. Temperatures at the tube inlet, outlet and outer surface of the test section were measured with a total of 58 thermocouples. Two pressure taps was also installed on the test section and was connected to a pressure transducer for pressure drop measurements. Experiments were conducted mainly on the last part of the test section where fully developed flow occurred. Experiments were conducted between Reynolds numbers of 1 000 to 10 000, Prandtl numbers of 3 to 8, and Rayleigh numbers of 330 and 11 000 (heat fluxes of 0.89 kW/m2 to 3.26 kW/m2). It was found that the heat transfer transitional range coincided with the friction factor transition range with a Reynolds number range of 2 484 to 2 849. Forced convection results in the laminar regime was achieved and compared well to literature. The results were mapped on published flow regime maps. This was inconclusive as the published flow regime maps have been specifically developed for fixed parameters that did not match the parameters of this study. / Dissertation (MEng)--University of Pretoria, 2017. / Mechanical and Aeronautical Engineering / MEng / Unrestricted

South Africa is currently struggling to deal with a significant poaching and livestock theft problem. This work is concerned with the detection and classification of ground based targets using radar micro- Doppler signatures to aid in the monitoring of borders, nature reserves and farmlands. The research starts of by investigating the state of the art of ground target classification. Different radar systems are investigated with respect to their ability to classify targets at different operating frequencies. Finally, a Gaussian Mixture Model Hidden Markov Model based (GMM-HMM) classification approach is presented and tested in an operational environment. The GMM-HMM method is compared to methods in the literature and is shown to achieve reasonable (up to 95%) classification accuracy, marginally outperforming existing ground target classification methods. / Dissertation (MEng)--University of Pretoria, 2017. / Electrical, Electronic and Computer Engineering / MEng / Unrestricted