Partial end-to-end reinforcement learning for robustness towards model-mismatch in autonomous racing’ by Murdoch, Andrew

Get full text

Multi-objective optimisation under deep uncertainty by Shavazipour, Babooshka

“…Nevertheless, analysis of the length of the planning horizon and its effects on the solutions to the proposed frameworks indicate that utilising the three-stage models is more efficient for longer periods because the differences between the solutions of the two proposed structures increase by any iteration of the algorithms in moving horizon models. …”
Get full text

Study of the TR Synchronization and Video Conversion Unit by Abraham, Justin Kuruvilla

“…A new SVCU architecture, utilizing high speed ADCs and digital integrators, was then tested. …”
Get full text

APIC: A method for automated pattern identification and classification by Goss, Ryan Gavin

“…While concepts such as Deep Learning have existed for many years, the computational power for realising the utility of these algorithms in real-world applications has only recently become available. …”
Get full text

Performance analysis of FBMC over OFDM in Cognitive Radio Network by Agoni, Amakan Elisha

“…A resource allocation algorithm was proposed where much attention was focused on interference and power constraint. …”
Get full text

Screening for Proteinopathic-related Dementias in Low-resource Clinical Contexts: A Machine Learning Approach by Lewis, Raphaella

“…Information from 20 clinical variables were used as features for the analysis. We used C5.0 algorithms to identify the most important features for PRD diagnosis and to derive an algorithm that could accurately diagnose these types of dementia. …”
Get full text

Genolve : a bioinformatics tool for the study of structure-driven genome evolution by Fouche, Helene

Get full text

Slotted time based protocol and polling strategies for low speed, narrow band applications by Ragadza, Ntakadzeni Ronald

Get full text

Application of data mining and machine learning on occupational health and safety struck-by incidents on south African construction sites: a CRISP-DM approach. by Adams, Logan Charl

Get full text

Bayesian analysis of historical functional linear models with application to air pollution forecasting by Junglee, Yovna

“…The efficiency of the MCMC algorithms is increased by implementing a Cholesky decomposition to sample from high-dimensional Gaussian distributions and by taking advantage of the orthogonal properties of the functional principal components used to model the functional covariates. …”
Get full text

A graph-based framework towards trading financial markets by Pretorious, Joshua Chance

Get full text

Pronunciation modelling and bootstrapping

Get full text
Get full text

Structural analysis in a distributed collaboratory by Van Rooyen, G. C. (Gert Cornelis)

Get full text

A comparative study of recurrent neural networks and statistical techniques for forecasting the stock prices of JSE-listed securities by Galant, Rushin

“…The number of input observations utilised were varied from four to fifteen observations whilst making forecasts from one up to ten timesteps into the future. …”
Get full text

A computer vision framework towards automated scene understanding & analysis by Sarah-lee de Greeff

“…Most computer vision algorithms are deep learning based approaches but differ significantly in architecture. …”
Get full text

Development of a decision-support tool for implementing circular value creation structures using machine learning and a digital ecosystem by Walter, Selina

Get full text

A critical evaluation of a community based mother-infant intervention project with special emphasis on infant attachment by Tomlinson, Mark

Get full text

Operational cost and emissions minimisation of a multi-microgrid system through energy management

Get full text

Metaheuristics for the selection and scheduling of jobs with time-dependent durations by Le Roux, Gavin James

Get full text

Some MIMO applications in cognitive radio networks by Salib, Feeby Magdy Girgis

“…In cognitive radio networks, the radio spectrum resources utilization is improved by allowing unlicensed users, known as secondary users, to share the spectrum with licensed users, known as primary users, as long as this sharing do not induce harmful interference on the primary users, which completely entitled to utilize the spectrum. …”
Get full text
Get full text