Predicting financial distress of JSE-Listed companies using Bayesian networks by Cassim, Ziyad

“…This study aims to test the suitability of using Bayesian probabilistic models to predict bankruptcy of JSE-listed companies. …”
Get full text

Towards the development of an optimal SDN controller placement framework to expedite SDN deployment in emerging markets by Mamushiane, Lusani

“…This problem constitutes competing objectives such as load balancing, latency, reliability and CapEx, thus no single best placement solution is available. This study aims to address the controller placement problem by leveraging machine learning algorithms. …”
Get full text

Investigating the use of ray tracing for signal-level radar simulation in space monitoring applications: a comparison of radio propagation models by Martin, Mogamat Yaaseen

“…This utilises a ray-tracing algorithm to simulate the effects of debris size, shape, orientation, and material properties when computing radar signals in a typical simulation. …”
Get full text

Application of vibration-based damage detection techniques to civil infrastructure : incorporating uncertainty quantification by Dzvukamanja, Setonam Komla

Get full text

A framework for the analysis and evaluation of enterprise models by Van Belle, Jean-Paul

Get full text

Approximation approaches for training neural network problems with dynamic mini-batch sub-sampled losses

Get full text

Efficient radio resource management for the fifth generation slice networks by Oladejo, Sunday Oladayo

“…The core aim of this research is to develop and evaluate efficient radio resource management algorithms and schemes that will be implemented in 5G slice networks to guarantee the QoS of users in terms of throughput and latency while ensuring that 5G slice networks are energy efficient and economically profitable. …”
Get full text

Development and testing of a laboratory digital controller by Closel, Andre Gerard

“…The aim of this thesis was to develop a fast and continuous digital sampling controller to study and compare some of the common arrangements of modern digital and analogue controllers. …”
Get full text

Dynamic matrix control of milling circuits by Mkhize, Sikhumbuzo Cazwell

Get full text

Optimisation of complex simulation models by Bezuidenhoudt,Cecile Margaret

“…Choosing optimal simulation parameters leads to improved operation of the model but it is still a challenge as to how to go about optimally selecting these parameter values. The aim of this thesis was to see if a method could be found to optimise a simulation model provided by a client. …”
Get full text

Investigation of Environmental Influences on Multiple Sclerosis: A Study for Egypt’s Health by Ali, Noha EzzAldin Alziny

“…Objective: This study aimed to comprehensively profile and compare serum levels of selected trace elements and protein biomarkers between Egyptian patients with MS and matched healthy controls. …”
Get full text
Get full text

GSM based Communication-Sensor (CommSense) System by Bhatta, Abhishek

“…We have compared two widely accepted supervised learning algorithms, called Support Vector Machines (SVM) and Multi-Layer Perceptron (MLP). …”
Get full text

Disaggregating employment data to building level : a multi-objective optimisation approach

Get full text

Application of machine learning and knowledge-based systems to support decision-making on fate and behaviour of engineered nanoparticles in aqueous environment

Get full text
Get full text

Predictive maintenance using clustering methods for the use-case of bolted connections in the automotive industry by Bekker, Emmarentia Lydia

Get full text

Efficient registration of limited field of view ocular fundus imagery by Van der Westhuizen, Christo Carel

Get full text

Incremental inference on higher-order probabilistic graphical models applied to constraint satisfaction problems by Streicher, Simon

Get full text

Interference Management of Inband Underlay Device-toDevice Communication in 5G Cellular Networks by Boamah, Sharon Ampomaa

“…The channel allocation problem is solved as an assignment problem by using a proposed heuristic channel allocation, random channel allocation, Kuhn-Munkres (KM) and Gale-Shapley (GS) algorithms. A comparative performance evaluation for the algorithms are carried out in the two system model scenarios, and the results indicated that D2D communication with relay assistance outperformed the conventional D2D communication without relay assistance. …”
Get full text

Quantifying phytoplankton biomass and sediment in river plumes along the Agulhas Bank using remotely sensed data with deep learning techniques by Pillay, Humeshni

“…For the developed [Chl-a] MLP algorithm, the constrained and full MLP models were similar, with C2RCC's AC producing the best results. …”
Get full text

A figure of merit for the x-band all-sky survey by Kriel, Scott

Get full text