Discrimination of Signal-Background Events with Supervised and Weakly Supervised Learning in the Search for New Bosons Decaying to Z + y Final State

Researcher: Nkateko Baloyi, University of the Witwatersrand, JohannesburgSupervisors: Prof. Bruce Mellado and Dr Xifeng Ruan, University of the Witwatersrand, Johannesburg The theory of Standard Model (SM) has successfully driven experiments and predictions since it was developed in 1975 and it has never been contradicted by experimental results.

Read More

Predicting Particle Fineness in a Cement Mill

Researcher: Rowan Lange, University of the Witwatersrand, JohannesburgSupervisors: Prof. Anton van Wyk, Dr. Terence van Zyl Cement production is a multi-billion dollar industry, of which one of the main subprocesses, cement milling, is complex and non-linear. There is a need to model the fineness of particles exiting

Read More

Identifying themes in online harassment using text analytics

Researcher:  Miss Safiyyah Ismail, The University of the WitwatersrandSupervisor: Professor Rod Alence, University of the Witwatersrand, Johannesburg Nothing quite affects human behaviour as much as the internet. With a cloak of invisibility and anonymity in cyberspace, a new phenomenon known as cyberharassment has been created. It is

Read More

Supervised versus Semi-supervised Machine Learning in the search for new Physics with the ATLAS data

Researcher: Lindiwe Malobola, University of the Witwatersrand, JohannesburgSupervisor: Professor Bruce Mellado, University of the Witwatersrand, Johannesburg Present-day machine learning methods can be used to build very powerful models for difficult collider physics problems. In numerous applications, the models are often built using fully supervised machine learning methods

Read More

The Impact of Initialization Strategies on the K-Means Convergence

Researchers: Tshauambea Murendeni, University of VendaSupervisor: Ms Nothabo Ndebele, University of the Witwatersrand, Johannesburg Clustering is a method where information items are grouped to attain the objective of maximizing within cluster resemblance and dissimilarity of different clusters [1]. The kmeans algorithm is commonly used, simple and ease

Read More