Evolutionary deep learning by Dufourq, Emmanuel

“…An extensive analysis of twelve sentiment datasets reveal that accurate compression is possible with 3.3% loss in classification accuracy even with 75% compression of text size, which is useful in environments where data volumes are a problem. …”
Get full text

Metabarcoding pollen to identify allergenic species of grasses (Poaceae) and ragweed (Ambrosia spp.) across six monitored sites in South Africa by Sidla, Siyavuya

“…The three taxonomic classification tools; UTAX, RDP, and BLAST were used to assign taxa, with a 50-read cutoff applied as the minimum read count, with confidence scores of ≥80% for UTAX and ≥0.8 for RDP. …”
Get full text

Metabarcoding pollen to identify allergenic species of grasses (Poaceae) and ragweed (Ambrosia spp.) across six monitored sites in South Africa by Sidla, Siyavuya

“…The three taxonomic classification tools; UTAX, RDP, and BLAST were used to assign taxa, with a 50-read cutoff applied as the minimum read count, with confidence scores of ≥80% for UTAX and ≥0.8 for RDP. …”
Get full text

Ba’da and qabla in online news: A corpus-based study by Eddakrouri, Ayman

“…Three linguistic qualities were addressed in the present analysis: semantic values and cohesive functions, syntactic features, and idiomatic usages. …”
Get full text
Get full text

An investigation of character variation in Chaetobromus Nees (Danthonieae: Poaceae) in relation to taxonomic and ecological pattern by Verboom, George Anthony

“…Phenetic methods revealed the existence of three groups, approximating three formerly described taxa and reflecting divergent ecological strategies in Chaetobromus. …”
Get full text

Examining the reliability of discharge ICD coding in the Red Cross War Memorial Children's Hospital administrative database by Daniels, Adriaan

“…Agreement of primary diagnosis coding to four characters was 26.3% with slight improvement to 34.3% when assessed to three characters. …”
Get full text

Left ventricular submitral aneurysms by Du Toit, Henning

Get full text

Predicting household poverty with machine learning methods: the case of Malawi by Chinyama, Francis

“…This was achieved by comparing the performance of three off-the-shelf, open-source machinelearning classification algorithms namely Logistic Regression, Extra Gradient Boosting Machine and Light Gradient Boosting Machine, in correctly predicting poor and non-poor households from Malawi survey data. …”
Get full text

Detection and Analysis of Molten Aluminium Cleanliness Using a Pulsed Ultrasound System by Matlala, Kgothatso

“…For the inclusion type classification, the multi-layer perceptron performs within 5% of the target metrics. …”
Get full text

Comparing outcomes of group and individualized physiotherapy treatment models for children with cerebral palsy in Ghana: a quasi-experimental study by Banini, Sandra

“…Participating children preand post-measurements were recorded over a three-month treatment period, accessing their motor function (using the Gross Motor Functional Measure-88 (GMFM-88), Gross Motor Function Classification System Expanded & Revised version (GMFCS E&R) and Manual Ability Classification Scale (MACS)) and the caregivers' burden of care (MCSI), health-related quality of life (EQ5D 3L version of HRQoL) and satisfaction with physical therapy (MRPS). …”
Get full text

The Quartz Conundrum : understanding the role of quartz in the composition of late Pleistocene and Holocene lithic assemblages from the Verlorenvlei area, Western Cape by Orton, Jayson

Get full text

The diversity of smallholder wool production and its marketing aspects : a case study at Xume, Eastern Cape, South Africa

Get full text
Get full text

Landslide susceptibility mapping : remote sensing and GIS approach by Tyoda, Zipho

Get full text

Deverbal nominals in Xhosa by Mletshe, Loyiso Kevin

Get full text

Die ekologie en taksonomie van die mondlaktobasille van kinders

Get full text

Assessing the discoverability of variant proteins causing rare forms of paediatric diabetes using proteogenomics by Naidoo, Lorensha

Get full text

AI Stock-Screening Methodology for Portfolio Construction by Khater, Omar Ahmed

“…Based on portfolio quality factors of risk and return, the obtained results outperformed three commonly used stock screeners and the relative market indices as well. …”
Get full text
Get full text