The dynamic modelling of a laboratory-scale packed distillation column, used to separate mixtures of tetrafluoroethylene, hexafluoropropylene and octafluorocyclobutane at sub-zero...

Get full text

Concrete and symbolic linearisability checking of non-blocking concurrent data structures by Du Toit, Nicole Cathryn

Get full text

Improved explainability through uncertainty estimation in automatic target recognition of SAR images

Get full text

Growth-based computer aided design strategies for multimode waveguide design with the aid of functional blocks by Vale, Christopher A. W.

Get full text

Sea state estimation from inertial platform data for real-time ocean wave prediction by Gwatiringa, Tinashe G

“…Additionally, local sea state information is not taken into consideration while manoeuvring, hence energy extraction from ocean waves is not optimal. More sophisticated navigation algorithms operating on a per-wave strategy may improve accuracy along a specified path and maximise the energy uptake from the waves. …”
Get full text

Towards a framework for multi class statistical modelling of shape, intensity, and kinematics in medical images by Fouefack, Jean-Rassaire

“…Both sampling and parametric based registration algorithms are proposed, which allow the establishment of dense correspondence across volumetric shapes (such as tetrahedral meshes) while preserving the spatial relationship between them. …”
Get full text

Towards a framework for multi class statistical modelling of shape, intensity and kinematics in medical images by Fouefack, Jean-Rassaire

“…Both sampling and parametric based registration algorithms are proposed, which allow the establishment of dense correspondence across volumetric shapes (such as tetrahedral meshes) while preserving the spatial relationship between them. …”
Get full text

Rapid distributed processing of medium velocity geospatial datastreams into contextualised 3D visualisations : evaluating the cloud computing paradigm

Get full text

Semiquantitative analysis of FDG PET brain scans using Neurostat and SPM by Munemo, Lionel Tapiwa

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 generic computer vision human activity recognition tool. by Jacobs, Johannes Jacobus

Get full text

Money Laundering Alert Prioritisation Using Machine Learning and Benford’s Law by Spies, Luka

Get full text

Modelling the technical influence of randomly distributed solar PV uptake on electrical distribution networks by Steyn, Anrich Frederik Willem

Get full text

An analysis of prognostic, endoscopic and transjugular intrahepatic portosystemic salvage shunting factors influencing rebleeding and death in portal hypertensive patients with lif... by Krige, Jacobus

“…In making recommendations for future research, new prognostic scoring systems incorporating artificial intelligence, machine learning algorithms and neural network models will need to be assessed and included as part of essential variceal bleeding clinical algorithms. …”
Get full text

Thermal and colour data fusion for people detection and tracking by Joubert, Pierre

Get full text

The Design of a Low-Cost Traffic Calming Radar - Development of a radar solution intended to demonstrate proof of concept by Matu, Unathi Neo

“…The target detection and the velocity estimation algorithms were executed on a Samsung Series 7 Chronos laptop. …”
Get full text

Systematic conservation planning and South Africa's Forest Biome: An assesment of the conservation status of South Africa's forest and reccomdentations for their conservation by Berliner Derek David

“…Three forest types, Eastern Scarp, Pondoland Scarp and Kwazulu-Natal Dune forests stand out as being highly vulnerable to biodiversity loss, of these; Pondoland Scarp forests have the lowest level of formal protection, and the highest number of endemic species, making this forest type, the highest conservation priority in the country. 10 PhD thesis: Forest conservation planning: Derek Berliner The limitations of the mathematical selection algorithms (C-plan and MARXAN) to incorporate ecological heuristics and context specific information within reserve selection were recognised. …”
Get full text

Internal variable formulation for the plastic analysis of plane frames by Rennie, Myles Peter

Get full text

Development of a stereo vision mixed reality framework by Le Roux, Christiaan Johannes Hendrik

Get full text

Evaluating image classification techniques on ASTER data for lithological discrimination in the Barberton Greenstone Belt, Mpumalanga, South Africa by Kemp, Jacobus Nicholas, Zietsman, H. L., Stevens, G.

Get full text