Multiscale image representation in deep learning

Get full text

Adapting Large-Scale Speaker-Independent Automatic Speech Recognition to Dysarthric Speech by Houston, Charles

“…In addition to investigating fine-tuning, layer freezing, data augmentation and re-initialization were also investigated. …”
Get full text

Classification of multiwavelength transients with machine learning by Sooknunan, Kimeel

“…However machine learning is often applied to such small datasets by making use of data augmentation. We develop a novel data augmentation technique based on Gaussian processes, able to generate new data statistically consistent with the original. …”
Get full text

Advancing security information and event management frameworks in managed enterprises using geolocation by Khan, Herah Anwar

Get full text

The relevance of performing 24-hour ambulatory blood pressure And pulse wave analysis in kidney transplant recipients by Mzingeli, Luvuyo

“…Data were analysed using standard statistical tests. …”
Get full text

Industrial yeast strains engineered for controlled flocculation by Govender, Patrick

Get full text

Probe characterisation, design and evaluation for the real-time quality Indication of milk by Van der Westhuyzen, Petrus Johannes

Get full text

Development of novel surveillance tools for rapid detection of citrus psyllids

Get full text

Mechanical handling effects on brewers' yeast by Robinson, Andrew

“…Brewery fermentation involves the conversion of sugars to ethanol by yeast with the repeated reuse of the yeast to maximise the overall conversion of sugars to ethanol. …”
Get full text

Object Detection and Size Determination of Pineapple Fruit at a Juicing Factory by Harris, Jessica

“…The best-performing detector made use of MS COCO starting weights, a ResNet50 CNN backbone, and horizontal flipping data augmentation during the training process. This model (Model 4: COCO Fliplr Res50) achieved an average precision of 91.4% on the validation set and an average precision of 90.1% on the test set, and was used to predict masks for an unseen dataset containing images of pre-measured pineapples. …”
Get full text

A Techno-economic evaluation of integrating first and second generation bioethanol production from sugarcane in Sub-Saharan Africa by Van der Westhuizen, Willem Andries

Get full text

Bioacoustic classification of Hainan gibbon call types using deep learning by Luphade, Nonhlanhla

“…Two steps were taken to train reliable models. Firstly, data augmentation techniques were explored to increase the amount of data as a means to train reliable models, and secondly, hyperparameter tuning was conducted. …”
Get full text

Predicting diarrhoea outbreak with climate change by Abdullahi, Tassallah Amina

“…Generative Adversarial Networks (GANs) was used to generate synthetic data which was used to augment the available dataset. …”
Get full text

Techno-economic study for sugarcane bagasse to liquid biofuels in South Africa : a comparison between biological and thermochemical process routes by Leibbrandt, Nadia H.

Get full text

The impact of wine yeast strains on the aromatic profiles of Sauvignon blanc wines derived from characterized viticultural treatments by Von Mollendorff, Anke

Get full text

Collaborative exploration of language teachers’ digital didactical designs for tablet classrooms

Get full text