Mechanical interlocking of 3D printed concrete layers by Mostert, Jean-Pierre

Get full text

Flight control system for an autonomous parafoil by Van der Kolf, Gideon

Get full text

Unsupervised anomaly detection for the ATLAS Level-1 Trigger by Stern, Thomas

“…These methods rely on the availability of clean training data to teach the model what “normal” samples are. …”
Get full text

A machine learning framework for security forecasting and trading by Van Schalkwyk, Philip

Get full text

Synthesis and applications of aminated biopolymers by Phillips, Thaakirah

“…A simple, green and sustainable synthetic method was sought as an improvement to prior methods using hazardous reagents and producing immense amounts of waste. …”
Get full text

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

Get full text

DFT insight into the oxygen reduction reaction (ORR) on the Pt₃Co(111) surface by Matsutsu, Molefi

“…The calculations have been performed using the plane wave based code, the Vienna ab-initio Simulation Package (VASP). DFT spin-polarized calculations, utilizing the GGA-PW91 functional, have been used to study the adsorption of the ORR intermediates, viz. …”
Get full text

Navigating the Rules: Integrating TD3 and Sensor Fusion for Traffic-Aware Autonomous Vehicle Path Planning by Elsayed, Mahmoud Ayman Mohamed

“…This combined approach aims to overcome limitations associated with individual techniques, such as long training time for DRL and lack of generalizability of supervised learning methods. Results from the CARLA simulations demonstrated the effectiveness of the proposed method and sensor fusion in obstacle detection and navigation precision. …”
Get full text
Get full text

Essays on determinants spillovers and predictability of the South African stock returns

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

Machine Learning for Radio Frequency Interference Flagging by Harrison, Kyle

“…This work explores the application of supervised machine learning algorithms for RFI flagging, trained on real measurement data and simulated data with simulated RFI. The goal of this work is to investigate the prediction of RFI using specific machine learning algorithms; Naive Bayes Classifier, K-Nearest Neighbours Classifier, Random Forest Classifier, the U-Net convolution neural network and the Multilayer Perceptron. …”
Get full text

Leveraging genotypes imputation and polygenic risk scores in malaria susceptibility by Kimathi, Peter Opiyo

“…Methodology We evaluated the performance of five popular genotypes imputation methods (IMPUTE4, minimac 4, IMPUTE2, minimac3 and BEAGLE4) using case control datasets that mimics African populations, European populations and the admixed populations simulated with FractalSIM. …”
Get full text

Valuing risky income streams in incomplete markets by Johnson, Clare

Get full text

Development and control of a 3-axis stabilised platform by Bredenkamp, Adolf Friedrich Ludwig

Get full text

Dynamic catch-effort models for the southern African hake populations by Andrew, P A

“…Col"1sequerrt ly, discrete dynamic- versions of the Schaefer and Fo>t models are fitted, i..tsi ng nor11 l near tt1i ni1t1i Lat i or1 procedures, to catch-effort data for the fottr ICSEAF areas commonly chosen for hake stock assessment purposes, nEUl'lely Divisiol"1S 1.3 + 1.4, 1.5, 1.6 and 2.1 + 2.2 (all of which indicate generally downward CPUE trends for the maJOT' part of their histories>. Monte Carlo simulation methods are employed to estitt1ate coefficients of variation for· the trJodel parameter and yield values assessed. …”
Get full text

Design considerations and analysis of a bioreactor for application in a bio-artificial liver support system

Get full text
Get full text

Characterising the electromagnetic environment of MeerKAT by Phiri, Temwani Joshua

Get full text

A novel control mechanism for hybrid 5-level DC-DC converter for higher switching frequency and lower voltage ripple by Mazloum, Mohamed Samir

“…Simulations as well as a test circuit are used to illustrate the proper control functionality, with tabulated results that showcase the efficiency advantage over prior control methods as well as the buck and 3-level hybrid converters.…”
Get full text
Get full text

Developing a compressed air benchmark approach to be used as a metric to identify ventilation shortfalls by Van Gruting, Ulrich

Get full text

Fault-tolerant NCSs with video sensors by Ahmed, Hadeer

“…Simulations clearly indicated zero packet loss and no over-delayed packets. …”
Get full text
Get full text