Faculty of Engineering
Recent Submissions
-
Comparing Transformer-based and gradient boosted decision tree (GBDT) Models on Tabular Data: A Rossmann Case Study
(2023)Heterogeneous tabular data is a common and important data format. This empirical study investigates how the performance of deep transformer models compares against benchmark gradient boosting decision tree (GBDT) methods, ... -
Parsimonious airfoil Parameterisation: A deep learning framework with Bidirectional LSTM and Gaussian Mixture models
(Elsevier, 2024)The choice of airfoil parameterisation method significantly influences the overall wing optimisation performance by affecting the flexibility and computational efficiency of the process. Ideally, one should be able to ... -
Transformer-based Text Generation for Code-Switched Sepedi-English News
(2023)Code-switched data is rarely available in written form and this makes the development of large datasets required to train code switched language models difficult. Currently, available Sepedi-English code-switched corpora ... -
Neural network-based vehicular channel estimation performance: Effect of noise in the training set.
(2025-02-12)Vehicular communication systems face significant challenges due to high mobility and rapidly changing environments, which affect the channel over which the signals travel. To address these challenges, neural network ... -
A data pilot-aided temporal convolutional network for channel estimation in IEEE 802.11P vehicle-to-vehicle communications
(2025-02-06)In modern communication systems, having an accurate channel estimator is crucial. However, when there is mobility, it becomes difficult to estimate the channel and the pilot signals, which are used for channel estimation, ... -
Sequence Based Deep Neural Networks for Channel Estimation in Vehicular Communication Systems
(Springer Nature ( Pre-print), 2023)Channel estimation is a critical component of vehicular communications systems, especially in high-mobility scenarios. The IEEE 802.11p standard uses preamble-based channel estimation, which is not sufficient in these ... -
Is network fragmentation a useful complexity measure?
(2024)It has been observed that the input space of deep neural network classifiers can exhibit ‘fragmentation’, where the model function rapidly changes class as the input space is traversed. The severity of this fragmentation ... -
Passive Electrochemical Hydrogen Recombiner For Hydrogen Safety Systems: Prospects
(Springer, 2023)This paper presents the concept of a passive electrochemical hydrogen recombiner (PEHR). The reaction energy of the recombination of hydrogen and oxygen is used as a source of electrical energy according to the operating ... -
Prioritisation Of Environmental Improvement Projects In Deep-Level Mine Ventilation Systems
(Springer, 2023)Deep-level underground mining costs in South Africa are continuously rising due to the increased depth at which gold is being mined, resulting in a rise in virgin rock temperature and an increase in cooling requirements. ... -
Implementation of a Reduced Order Model for rotating seal annular leakage flow inside a centrifugal pump
(Elsevier, 2023)Sustainability and net zero emissions targets drive the importance of turbomachinery design, optimisation, and efficient operation in modern geoenergy systems. To further enable integration of advanced large-scale ... -
Aromatic liquid organic hydrogen carriers for hydrogen storage and release
(Elsevier, 2023)Hydrogen production from renewable energy sources has the potential to significantly reduce the carbon footprint of critical economic sectors that rely heavily on fossil fuels. Liquid organic hydrogen carrier (LOHC) ... -
Improved energy graph-based visualisation fault detection and isolation — A spectral theorem approach
(Elsevier, 2023)This paper illustrates how the energy graph-based visualisation (EGBV) fault detection and isolation (FDI) method may be interpreted in terms of the spectral theorem to gain insight into the sensitivity and robustness ... -
Concentration contextualisation, temporal patterns and sources of hydrogen sulphide at a site on the South African Highveld
(Elsevier B.V., 2023)South Africa is one of the largest atmospheric sulphur emitting countries, but the contribution of H2S to this regional burden is not known. Also, no H2S source apportionment for South Africa have been undertaken, ... -
The Development of a Sepedi Text Generation Model Using Transformers
(Southern Africa Telecommunication Networks and Applications Conference (SATNAC) 2022, 2022)Text generation is one of the important sub-tasks of natural language generation (NLG), and aims to produce humanly readable text given some input text. Deep learning approaches based on neural networks have been proposed ... -
Developing a full core model of the North Anna Reactor using SCALE 6.2.3, NESTLE and MCNP 6.2
(North West University, 2022)This study presents the development of the modelling for a T-NEWT/NESTLE* lattice-to-nodal diffusion calculation. The reactor selected for this study is the North-Anna (NA) Unit 1 Pressurized Water Reactor (PWR) of the ... -
The Radial Variation of the Solar Wind Turbulence Spectra near the Kinetic Break Scale from Parker Solar Probe Measurements
(American Astronomical Society, 2023)In this study we examine the radial dependence of the inertial and dissipation range indices, as well as the spectral break separating the inertial and dissipation range in power density spectra of interplanetary magnetic ... -
The Analysis of the Sepedi-English Code-switched Radio News Corpus
(UP Jornals, 2022)Code-switching is a phenomenon that occurs mostly in multilingual countries where multilingual speakers often switch between languages in their conversations. The unavailability of largescale code-switched corpora ... -
A Comparative Study of Graph Neural Network Speed Prediction during Periods of Congestion
(SciTePress, 2022)Traffic speed prediction using deep learning has been the topic of many studies. In this paper, we analyse the performance of Graph Neural Network-based techniques during periods of traffic congestion. We first compare ... -
Minimum phase finite impulse response filter design
(Wiley, 2022)The design of minimum phase finite impulse response (FIR) filters is considered. The study demonstrates that the residual errors achieved by current state‐of‐the‐art design methods are nowhere near the smallest error ... -
The influence of calcium lignosulphonate addition on non-isothermal pyrolysis and gasification of demineralised bituminous coal fines
(Elsevier BV, 2022)Amorphous calcium lignosulphonate (CaLS), a by-product of the paper industry, was evaluated as an adhesive to bind demineralised bituminous coal fines in various weight percentage ratios. Sequential acid (HCl, HF, ...