Diagnostic accuracy of C-reactive protein and procalcitonin, compared with composite reference standards, to discriminate between tuberculosis, Pneumocystis jirovecii pneumonia and... by Mendelson, Fiona

“…Simple, affordable tests are needed for developing improved clinical algorithms. C-reactive protein (CRP) and procalcitonin have shown diagnostic utility for respiratory tract infections, however few studies have focussed on their ability to distinguish between tuberculosis, CAP, and PJP in HIV-infected inpatients. …”
Get full text

Operational scheduling and investigative planning for electric public transport in South Africa by Wüst, Jacques

Get full text

2D irregular strip packing at Kohler signs by Bossenger, Wayne

Get full text

A decision support framework for machine learning applications by Du Preez, Anli

Get full text

Generating new data points using singular value decomposition by Biyana, Tlhologello

“…Motivated by challenges faced during algorithm development due to small data sets, the study proposes the SVD-based model, evaluates its efficacy in replicating original data attributes and compares model performance with new and original data. …”
Get full text

An analysis of hybrid hidden Markov models for cetacean detection by Edwards, David James Erich

Get full text

Variable selection for kernel methods with application to binary classification by Oosthuizen, Surette

Get full text

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

Get full text

The ride comfort vs. handling compromise for off-road vehicles

Get full text
Get full text

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

Get full text

Newer and novel sputum versus non-sputum-based tools for the diagnosis of active tuberculosis in different patient sub-populations by Esmail, Aliasgar

“…The utility of POC-Xpert Ultra in detecting likely infectious patients was also specifically evaluated. …”
Get full text

Low complexity turbo equalization using superstructures

Get full text

Robust control of a triple-effect evaporator

Get full text

Extracting failure modes from unstructured, natural language text by Malan, Francina

Get full text

Heterologous expression and partial characterisation of enzymes predicted in silico by deep feed-forward neural networks by Foster, Bryce John

Get full text

Applying the Herman-Beta probabilistic method to MV feeders by Chihota, Munyaradzi Justice

Get full text

Reducing the Burden of Aerial Image Labelling Through Human-in-the-Loop Machine Learning Methods by Razzak, Muhammed T

“…Active learning looks at reducing the number of labelled samples required by a model to achieve an acceptable performance level. Within the context of deep learning, the utility of the various active learning strategies developed is uncertain, with conflicting results within the literature. …”
Get full text

Geometric acceleration of complex chemical equilibrium calculations for inclusion in multiphysics and process models

Get full text

Distributed binary decision diagrams by Fasan, Mary Oluwasola

Get full text

Neural networks in control engineering by Trossbach, W

“…However, despite its superior modelling capability, the tests performed using the Williams and Zipser training algorithm show that such structures often fail to converge and require excessive computing power and time, when increased in size. …”
Get full text