Simplified approaches for portfolio decision analysis by Kantu, Dieudonne Kabongo

“…These are generally computationally-intensive algorithms that require substantial amounts of information from the decision maker, and in return yield portfolios that are provably optimal or optimal within certain bounds. These methods have proved popular for choice decisions — for example, those based on multiattribute value or utility theory. …”
Get full text

Dynamics of co-behaviour of climate processes over Southern Africa by Quagraine, Kwesi Akumenyi

“…This study details the development of such a methodology and demonstrates its utility in the analysis of the co-behaviour of largescale process interactions on regional precipitation and temperature variability over southern Africa. …”
Get full text

Traffic impacts of shared right-of-way public transport systems: A microsimulation-based case study

Get full text

Fast accurate diphone-based phoneme recognition by Du Preez, Marianne

Get full text

Autonomous racing on unseen tracks using reinforcement learning by Jefferies, Devin Wayne Patrick

Get full text

Influence of durability properties on performance of bitumen stabilised materials by Twagira, Elias Mathaniya

Get full text

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

“…The algorithm integrates the Twin Delayed Deep Deterministic Policy Gradient (TD3) with sensor fusion based on Nvidia Convolutional Neural Network (NCNN). The study utilizes the CARLA simulator, and real-world datasets, including KITTI and WAYMO, to train and evaluate the proposed algorithm. …”
Get full text
Get full text

Building a Hybrid Compton Camera System for Improving Medical Imaging Applications by Hart, Shanyn-Dee

“…CC2 was evaluated for three distinct geometries, utilising a 4 × 1 matrix of detector assemblies in both the scatterer and absorber layers. …”
Get full text

Aerodynamic losses and endwall heat transfer in a linear vane cascade with endwall film-cooling and endwall-leading edge contouring

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

The development of a spatial decision support system to optimise agricultural resource use in the Western Cape by Pretorius, C. E. (Cornelia Elizabeth)

Get full text

Techno-Economic modelling of hybrid renewable mini-grids for rural electrification planning in Sub-Saharan Africa by Ireland, Gregory

“…Given the intermittent and location-dependent nature of renewable energy sources, the evolving costs and performance characteristics of individual technologies, and the characteristics of interacting technologies, detailed system simulation and demand modelling is required to determine the cost optimal combinations of technologies for each-and-every potential mini-grid site. …”
Get full text

Continuum Damage Mechanics to Model Glulam Beams Reinforced with Glued-In Steel Cables by Rhodes, Aaron

“…However, it was unable to accurately represent interactions between the reinforcing steels and timber. …”
Get full text

Measuring cross-section data for prompt gammas emitted during proton-nucleus collisions by Ramanathan, Vijitha

“…The first part of this study was to experimentally measure the interaction cross section for proton-nucleus collisions in both carbon and oxygen. …”
Get full text

Development of scalable hybrid switching-based software-defined networking using reinforcement learning by Blose, Max

“…We implement a reinforcement algorithm to randomly explore new routes and discover the most optimal path through the Q-learning algorithm. This primitive and model-free form of reinforcement learning utilizes the Markov Decision Process and the Bellman's equation to reiteratively update Q-values in Q-table for every transition in the network environment state, until Q-function has converged to the best Q-Values. …”
Get full text

Development of scalable hybrid switching-based software-defined networking using reinforcement learning by Blose, Max

“…We implement a reinforcement algorithm to randomly explore new routes and discover the most optimal path through the Q-learning algorithm. This primitive and model-free form of reinforcement learning utilizes the Markov Decision Process and the Bellman's equation to reiteratively update Q-values in Q-table for every transition in the network environment state, until Q-function has converged to the best Q-Values. …”
Get full text

Extension and verification of the PWM_SA model to incorporate SANI-specific bioprocesses using experimental data from the Hong Kong SANI saline sewage treatment pilot plant. by Mudau, Hope Thendo

“…The extended model was implemented and verified in the WEST software, utilizing experimental data from the SANI pilot plant in Hong Kong to align the model with real world treatment conditions and verify the accuracy of kinetic rates and parameters. …”
Get full text

Reducing fumonisin exposure in African fermented maize-based foods with lactic acid bacteria

Get full text

The separation of detergent range alkanes and alcohol isomers with supercritical carbon dioxide by Zamudio, Michelle

Get full text

Advanced take-off and flight control algorithms for fixed wing unmanned aerial vehicles by De Hart, Ruan Dirk

Get full text