Pegelotlhotlhomisi ka ga metara mo Setswaneng

Get full text
Get full text

Viewpoint estimation in medical imaging by Hounkanrin, Mahouclo Anicet

“…Given a 2D image of a 3D scene, the problem of viewpoint estimation aims to determine the position and the orientation of the imaging sensor that resulted in that view. …”
Get full text

Wearable device localisation and its effect on activity recognition using machine learning

Get full text

Ship target recognition by Robinson, Anthony David

Get full text

Efficient energy management in ultra-dense wireless networks by Wambi, Paul James

“…The proposed solution to the formulated optimization problem makes use of constraint relaxation to transform the NP-hard problem into a more solvable, convex and linear optimization one. …”
Get full text

Human action recognition with 3D convolutional neural networks by Cronje, Frans

“…Furthermore, CNNs are more readily transferable between different image classification problems when compared to common alternatives. …”
Get full text

Reliable likelihoods for out-of-distribution data from continuous-time normalising flows by Josias, Shane

Get full text

An investigation of a pattern recognition system to analyse and classify dried fruit by Henry, Karen Jane

Get full text

Discriminant analysis using sparse graphical models by Botha, Dylon

Get full text

Computer aided identification of biological specimens using self-organizing maps

Get full text
Get full text

Protection-based Distributed Generation Penetration Limits on MV feeders - Using Machine Learning by Nxumalo, Emmanuel

“…For future work, the collection of more data points (results from detailed analytical studies on the impact of DG on MV feeders) to use as training data to solve the observed high variance problem is recommended. Also, modifying the model by adding upstream and downstream network features as inputs in the classification model to solve the high bias problem is recommended.…”
Get full text

Marginale en liminale karakters in die werk van Lettie Viljoen/Ingrid Winterbach : sosiale kommentaar en die ondermyning van grense by Foster, Petronella Hermina,1980-

Get full text

Training Feedforward Neural Networks with Bayesian Hyper-Heuristics

Get full text

Multi-label feature selection with application to musical instrument recognition by Sandrock, Trudie

Get full text

3D convolution with two-stream convNets for human action recognition by Hosny, Karim Mohamed

“…Many methods have been researched to attempt to solve the problem, ranging from handcrafting techniques to deep neural network techniques and methods such as 3D convolution and recurrent neural networks has been used as well. …”
Get full text
Get full text

Insurance recommendation engine using a combined collaborative filtering and neural network approach by Pillay, Prinavan

“…The hybrid approach helps solve for cold start problems where users have no interaction history. The accuracy on the collaborative filtering produced 0.13 root mean square error based on implicit feedback rating of 0-1, and an overall Top-3 classification accuracy (ability to predict one of the top 3 choices of a customer) of 83.8%. …”
Get full text