Exploring the impact of novelty and objective-directed evolution in company with MAP-Elites and HyperNEAT by Breytenbach, Jeremy

“…Objective search refers to evolutionary algorithms that explicitly optimize a predetermined performance metric, whereas nonobjective search refers to evolutionary approaches that primarily focuses on exploration and diversity within the search space. …”
Get full text

Improvements to longitudinal clean development mechanism sampling designs for lighting retrofit projects

Get full text

The design and characterization of diode detectors by Koen, W. J. C.

Get full text

Assessment of bridges' expansion joints in Egypt by Badawy, Abdelhay Mohamed

“…Moreover, an expansion joint management system (EJMS) is developed with the aim of recommending the optimum maintenance strategy for bridges that optimizes annual condition index (ACI) and cost. This model uses a combination of Fuzzy Logic (FL) and Genetic Algorithm (GA) in order to provide optimal recommendations. …”
Get full text
Get full text

Computational fluid dynamic based optimisation of an industrial axial fan for rapid prototyping by Van Rooyen, Jacobus A

“…The resulting optimised fan (Fan-Optim) is manufactured and experimentally tested, in accordance with the ISO 5801 standard. …”
Get full text

Energy efficient coordinate establishment in wireless sensor networks

Get full text
Get full text

Modelling control and optimisation of a dual circuit induced draft cooling water system

Get full text

Protection-based Distributed Generation Penetration Limits on MV feeders - Using Machine Learning by Nxumalo, Emmanuel

“…Gradient descent, which is an optimisation algorithm that iterates and finds optimal values of the parameters that correspond to the local or global minimum values of the cost function using calculus was used to measure the accuracy of each model's hypothesis function. …”
Get full text

Channel parameter tuning in a hybrid Wi-Fi-Dynamic Spectrum Access Wireless Mesh Network by Zlobinsky, Natasha

“…This contribution is realised by providing and analysing the performance of near-optimal Channel Assignment (CA) solutions using metaheuristic algorithms for the MRMC WMNs using DSA bands. …”
Get full text

A study of current and possible future industrial engineering methodologies used to increase energy effieciency by Van der Merwe, Este

Get full text

Link prediction in knowledge graphs using latent feature modelling and neural tensor factorisation by Magangane, Luyolo

Get full text

Machine Learning Based Critical Resource Allocation in Mixed-Traffic Cellular Networks by Nomeir, Mohamed

“…The results show that the proposed algorithms produce near-optimal results in real-time.…”
Get full text
Get full text
Get full text
Get full text
Get full text

Mathematical optimisation of the suspension system of an off-road vehicle for ride comfort and handling

Get full text
Get full text

Dataset shift in land-use classification for optical remote sensing

Get full text

Efficient adaptive sampling applied to multivariate, multiple output rational interpolation models, with applications in electromagnetics-based device modelling by Lehmensiek, Robert

Get full text

Data-driven augmentation of pronunciation dictionaries by Loots, Linsen

Get full text

Condition monitoring of induction motors in the nuclear power station environment by Rylands, Naasef

“…The induction motor is a highly utilised electrical machine in industry, with the nuclear industry being no exception. …”
Get full text

Mobility Management in 5G Heterogeneous Networks: A Handover Scheme for Reducing Handover Failures by Monaheng, Reitumetse

“…This dissertation focuses on reducing handover failures due to the unavailability of resources at the target cell when a user equipment moves out of small cells, which have the highest rate of handover failure. By utilising a semi-Markov mobility prediction algorithm for handover management, we have implemented a handover scheme that reduces the number of handover calls dropping. …”
Get full text

An investigation into the relationship between design approaches, student engagement and agency in a blended learning computer science course by Van Der Merwe, Brendan Kenneth

“…Disengagement among learners in tertiary Computer Science (CS) courses, particularly those focusing on algorithmic design, poses challenges to the achievement of learning outcomes. …”
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