Radar intra-pulse modulation classification using convolutional neural networks by Swart, Jean

“…This dissertation aims to address the increasing difficulty of pulse classification through the use of modern machine learning techniques - more specifically, by utilising convolutional neural networks. A wide range of modulation schemes was considered and simulated with realistic imperfections to create a dataset that was as representative of real-world scenarios as possible. …”
Get full text

Investigation of an optimalising controller by Luxat, J C

Get full text

Numerical investigation into the effects of multiple bubbles in microchannel flow boiling

Get full text

Automated machine learning driven quality of service management in resource-constrained software defined networks by White, Keegan

“…The deep learning models utilised by the framework are trained on data gathered from a community network and extensively tested in online network simulations. …”
Get full text

Autonomous landing of a tethered multi-rotor unmanned aerial vehicle on a stationary platform by Mfiri, Tatenda Joshua

Get full text

Bidirectional asynchronous generator and battery interface circuit by Coetzer, Adel

Get full text

Benchmarking excellence: navigating the Nexus of skill and luck in organisational performance evaluations by Joubert, Eugene

Get full text

3D tracking between satellites using monocular computer vision by Malan, Daniel Francois

Get full text

An efficient congestion control scheme for a lightweight constrained application protocol in the Internet of Things

Get full text

Design and development of a speculum-free digital cervical cancer screening device by Hefer, Lehan

“…It was validated to have diagnostic accuracy equivalent to that of the standard device and good usability in the simulated screening environment. While the validation testing strength lay in utilising highly experienced gynaecologists, limitations arose from inaccuracies introduced by the simplified anatomy and pathology of the female pelvic model and cervices. …”
Get full text

The performance of an integral greenhouse solar air-heater by Bam, Peter Jonathan

Get full text

Multi-h synchronisation for codes with long constraints-length by Nel, Eugéne Johannes

Get full text

Anomalous Reflection from Phase Gradient Metasurfaces for Arbitrary Incident Angles

Get full text

Development of a wake and backwater prediction approach for hydrokinetic turbines

Get full text

The interception drainage capabilities of slotted drains as pavement surface drainage systems

Get full text

Detecting change in complex process systems with phase space methods by Botha, Paul Jacobus

“…The second method applied to the data was mutual cross prediction, which utilises the prediction error from a multilayer perceptron network. …”
Get full text

SWASH: A robust numerical model for shallow water coastal engineering applications by Van Eeden, Frans

Get full text

Biomechanical assessment of RTSA functional outcomes towards optimising the prosthesis configuration by Glenday, Jonathan Daniel

“…A biomechanical assessment framework was established to characterise reverse shoulder function and the effect of modifying prosthesis configuration. It utilised the Newcastle Shoulder Model (NSM) and a custom-made impingement detection algorithm to simulate seven standardised motions that either elevated or rotated the humerus. …”
Get full text

Autonomous airborne refueling : relative state estimation by Runhaar, Anton Johan

Get full text

'n Ondersoek na enkeldeeltjie-nasporingsmetodes vir fotosintetiese komplekse

Get full text