Automated learning rates in machine learning for dynamic mini-batch sub-sampled losses

Get full text

Efficient gradient-based optimisation of suspension characteristics for an off-road vehicle

Get full text
Get full text

Tττ-framework for the evaluation and improvement of phase behaviour description with the NRTL activity coefficient model by Lamprecht, Danielle Lee

Get full text

An investigation into higher and partial moment portfolio selection frameworks by Polden, Stuart John

“…It solves the endogeneity issue present in the co-semivariance matrices, through the usage of a direct multi-search algorithm. The two frameworks were tested across multiple datasets, including one of pure stocks and one of asset classes, to test the ability to both allocate assets and select stocks. …”
Get full text

Nonlinear heat transfer and thermo mechanical stress analysis using finite elements. by Pennington, Derek Steven

“…Four, eight and nine noded isoparametric continuum finite elements with the option of the plane stress, plane strain and axisymetric cases are utilized. Nonlinear heat transfer due to temperature dependent thermal conductivity and/or internal heat generation is solved using an iterative method based on the Newton-Raphson algorithm. …”
Get full text

Distributed autonomous intersection management with neuro-evolution by Cherry, Matthew P

“…In particular we investigate three key hyper-parameters: Neuro-Evolution algorithm, task difficulty and problem exposure. A traffic simulator was developed and the hyper-parameters were used to evolve car controllers, which where then tested on unseen tasks. …”
Get full text

Project Leanness Score: A Machine Learning Approach by Said, Julia

“…Lean construction is a philosophy, backed with principles and tools, aiming at maximizing value, eliminating waste, optimizing efficiency, and seeking continuous improvement. …”
Get full text
Get full text

Using Machine Learning and the Water Evaluation and Planning model to Evaluate Climate Change Impacts on Surface Water Allocation in the Upper Awash Sub-Basin, Ethiopia by Hirko, Deme Betele

Get full text

Field D* pathfinding in weighted simplicial complexes by Perkins, Simon

Get full text

Uterine balloon volume shifts using a free-flow uterine balloon in the management of refractory postpartum haemorrhage by Hassim, Tasleem, Kidd, Martin

Get full text

Dental implant recognition by Kohlakala, Aviwe

Get full text

Low bit rate speech coding by Kritzinger, Carl

Get full text

Radar-Based Multi-Target Classification Using Deep Learning by Mashanda, Nyasha Ernest

“…To achieve these objectives, radar data was collected using a C-band pulse-Doppler radar and converted to spectrograms using the Short-time Fourier transform (STFT) algorithm. Spectrograms of the following classes were utilised in classification: one human walking, two humans walking, one human running, moving vehicles, a swinging sphere and clutter/noise. …”
Get full text

Mixed-Criticality Scheduling Using Reinforcement Learning by ElSeadawy, Omar

“…Our customized Ape-X model is capable of successfully scheduling sets of jobs of size 50 with an average accuracy of 95% in comparison to other Reinforcement learning algorithms benchmarks conducted, e.g., Augmented Random Search, Proximal Policy Optimization, and Deep Q Networks. …”
Get full text
Get full text

Artificial neural networks and the cross-section of equity returns: identifying nonlinear opportunities on the Johannesburg Stock Exchange by Reed, Joshua

“…The activation function, training algorithm, learning rate, number of epochs, batch size, and loss function are kept constant across architectures. …”
Get full text

Optimisation study of geographical allocation of solar PV generation capacity for grid support by Vermeulen, Vicki-Mari

Get full text

Multi-objective optimisation of water distribution systems design using metaheuristics by Raad, Darian Nicholas

Get full text

Image-Based Models for Left Heart Flow Morphodynamics in Hypertrophic Obstructive Cardiomyopathy by Sultan, Abdelrahman A

“…This has been achieved by employing a velocity mapping algorithm along with integrating 4D-CT-derived wall motion information, resulting in a significant reduction in analysis time. …”
Get full text
Get full text

Effective visualisation of callgraphs for optimisation of parallel programs: a design study by Mabakane, Mabule Samuel

“…Visualisation tools are used to identify performance bottlenecks of parallel applications in an attempt to optimize the execution of the programs and fully utilise the available computational resources. …”
Get full text

4D schedule generation for flat slab BIM models by Hosny, Amir Ossama

“…Planning & scheduling has made some amazing progress in the past 20 years, a period when numerous site engineers felt that utilizing formal planning was unnecessary to everyday operations and a period expending diversion. …”
Get full text
Get full text