Detecting Electrical Submersible Pump (ESP) Failures and Estimating Run Life Using Artificial Neural Networks by Sobhy, Mostafa Ahmed

“…Various strategies were applied for splitting the data into training, validation, and test sets. Model tuning included parameter adjustment and techniques such as SMOTE-Tomek resampling to address class imbalance and to prevent data leakage. …”
Get full text
Get full text

Combinatorial evolution of feedforward neural network models for chemical processes by Schmitz, Gregor Peter Josef

Get full text

State-based decision support for condition shifting of multimodal continuous processes by Noelle, Francois Frieder

Get full text

The development and implementation of an innovative smartphone application to collect route choice preference data

Get full text

Nutritional factors associated with oral lesions in HIV disease and TB infection by Phooko, Puleng M. (Puleng Mpopi)

Get full text

Influence of catalyst ink mixing procedures on catalyst layer properties and in-situ PEMFC performance by Jacobs, Clayton Jeffrey

“…Overall, fuel cell performance is not significantly affected by the mixing step however; mixing does have an observable impact on catalyst layer formulation. Generally, when optimizing membrane electrode assembly fabrication, mixing parameters should be carefully chosen. …”
Get full text

Southern African climate anomalies, summer rainfall and the Angola low by Mulenga, Henry Mubanga

Get full text

Temperature reconstruction and acoustic time of flight determination for boiler furnace exit temperature measurement by Raikes, Geoff

“…An improved reconstruction technique using radial basis functions (RBF) for interpolation and a least squares algorithm is simulated and its performance was compared to cubic spline interpolation, regression and Lagrange interpolation by evaluating its reconstruction accuracy in terms of mean and root-mean-squared (RMS) error when reconstructing set temperature profiles. Various parameters including transceiver positions, grid divisions and time of flight error, are investigated in terms of how they inform acoustic pyrometry implementation. …”
Get full text

A contingent claims analysis of the pricing of rights isssues with discontinuous diffusion processes by Botha, Russel John

Get full text

Satellite change detection in the albany thicket biome by Mahlasi, Craig

“…Finally, it was shown that using meta-learning the TempCNN can be adapted to be robust in shifting domains by learning the most optimal parameter initializations that allow for capturing the invariant embeddings that facilitate generalisation across domains possible.…”
Get full text

Effective fisheries management with few data: a management procedure approach by Geromont, Helena Francine

“…Complex stock assessments which typically rely on a comprehensive set of age or length data are traditionally seen as an essential requirement for sound fisheries management. …”
Get full text

Effective fisheries management with few data: A management procedure approach by Geromont, Helena Francine

Get full text

The search for biomarkers in the growth prediction of the West Coast Rock Lobster, Jasus lalandii by Munian, Andre

Get full text

Neurocontroller development for nonlinear processes utilising evolutionary reinforcement learning by Conradie, Alex van Eck

Get full text

Aspects of model development using regression quantiles and elemental regressions by Ranganai, Edmore

Get full text

Non-linear neurocontrol of chemical processes using reinforcement learning by Hunter, Stephen Leon

Get full text

Low-Complexity Algorithms for Channel Estimation in Optimised Pilot-Assisted Wireless OFDM Systems by Golovins, Eugene

“…The resultant contribution is manifested by the closed-form analytical expressions of the upper bound (suboptimal approximate value) on the optimal pilot-to-data power ratio (PDR) as a function of a number of design parameters (number of subcarriers, number of pilots, number of transmit antennas, effective order of the channel model, maximum Doppler shift, SNR, etc.). …”
Get full text

Identification of new therapeutic compounds against carbapenemase-producing Klebsiella pneumoniae using a novel agar-based high-throughput microarray compound screening approach by Mahlangu, Zandile

“…The optimized parameters for effectively running the high-throughput antibacterial screen were set at 1.5% (w/v) CNF immobilization matrix into which spots were printed, 1.6% hydroxypropyl methylcellulose printing solution – serving as a binding agent for compounds, inoculum density ranging between ~1 x 105 and 2 x 105 CFU/mL, 0.8% (w/v) seeding agar which formed a ~0.4 mm layer into which printed compounds diffused into and affected bacteria, and 1.5% (w/v) plain agar which formed a ~1.6 mm layer overlaying the thin seeded agar layer. …”
Get full text

Unsupervised Machine Learning Application for the Identification of Kimberlite Ore Facie using Convolutional Neural Networks and Deep Embedded Clustering by Langton, Sean

“…The aim of this research is to demonstrate the viability of implementing a computer vision solution to provide online information of the composition of material entering the plant, thus allowing the plant operators to adjust equipment settings and process parameters accordingly. Data is collected in the form of high resolution images captured every couple of seconds of material on the main feed conveyor belt into the Kao Diamond Mine processing plant. …”
Get full text

Buckling behaviour of thin concrete arch dams by Letsika, Malefetsane David

“…The results are presented in the form of design plots that allow a safe set of design parameters to be selected while simultaneously indicating the safety factor linked with the implemented design. …”
Get full text