Supervision

Potential postgraduate students looking for a supervisor can read through my general research interests as well as completed and current projects listed below. If you find my area of research interesting, then you are welcome to contact me to discuss ideas and possible project topics. I am also open to discussing other topics of interest to you in the broad area of computational intelligence.

In the Department of Decision Sciences at UNISA, we offer MSc and PhD degrees in Operations Research. You are welcome to contact me via email for more information on postgraduate studies in our department. I can also supervise postgraduate degrees in Computer Science under the School of Computing, UNISA.

General research interests

My main research interest is in fitness landscape analysis and the link to metaheuristic performance. What does this mean? Population-based metaheuristics, such as evolutionary algorithms and particle swarm optimisation algorithms have been successful in solving complex optimisation problems, but it is well known that they sometimes fail. Although the algorithms are generally easy to understand, the resulting behaviour is largely unpredictable, due to not only the stochastic nature of the algorithms, but also due to the dynamic interactions between solutions during the search process. Fitness landscapes are a way of thinking about optimisation problems and can be used to analyse the characteristics of a problem. If we know more about the kinds of problems that particular algorithms fail to solve, then we can hopefully choose appropriate algorithms and also design better algorithms to solve those hard problems.

Completed supervision

  • Phlippie Bosman (as co-supervisor with Prof Andries Engelbrecht), MSc in CS at University of Pretoria, The Influence of Fitness Landscape Characteristics on the Search Behaviour of Particle Swarm Optimisers, 2019.
  • Wilna Pelser, BSc (Hons) in OR at UNISA, Optimisation of the Vertical Alignment of Steel Pipelines using Metaheuristic Techniques (with distinction), 2019.
  • Angelo Constantinou, BSc (Hons) in OR at UNISA, Recommendations for Movies using Neural Networks for Commercial Online Streaming (with distinction), 2019.
  • Odirile Moja, MIT (UP), Ethics and Benefits of Automated Decision Making for Optimal Retirement Portfolio Risk Matching in South Africa (with distinction), 2018.
  • Werner Mostert, Hons (UP), Feature Selection Fitness Landscape Analysis, 2016.
  • Willem van Aardt (as co-supervisor with Anna Bosman), Hons (UP), Characterising Neutrality in Neural Network Error Landscapes, 2016.
  • Christina Kroeze, MSc (UP), Touch Biometrics for Unobtrusive Continuous Authentication on Smartphones (with distinction), 2015.
  • Darren Pillay, MIT (UP), The Development of an Expert System Knowledge Base for the Calibration of Stand-Alone Engine Control Units, 2015.
  • Eduan Bekker (with Anna Rakitianskaia as co-supervisor), Hons (UP) , Analysis of Error Landscapes in Multi-layered Neural Networks for Classification, 2015.
  • Richard O'Brien (with Anna Rakitianskaia as co-supervisor), Hons (UP), Investigating the Link Between Exploratory Landscape Analysis and Backpropagation Performance, 2015.
  • Jhani de Bruin (with Prof Jan Eloff as co-supervisor), MSc (UP), Automated Usability Analysis and Visualisation of Eye Tracking Data (with distinction), 2014.
  • Stuart Reid, Hons (UP), Currency Carry Trade Portfolio Optimization (with distinction), 2013.
  • Christien Kroeze, Hons (UP), Matching Shapes Using a Genetic Algorithm with Hill Climbing (with distinction), 2011.
  • Jhani de Bruin, Hons (UP), An Investigation into Renko Charts for Genetic Algorithm Evolved Forex Traders (with distinction), 2010.

Current supervision

  • Odirile Moja, PhD in CS (UNISA), An Analysis of the Landscapes of Automated Program Repair Problems.
  • Wilson Mongwe, PhD in OR (UNISA), Automated Financial Statement Fraud Detection in South Africa.
  • Werner Mostert (co-supervisor with Prof Andries Engelbrecht), MSc in CS at Stellenbosch University, Landscape Aware Feature Selection for Data Mining.
  • Isaac Molekwa, BSc (Hons) in OR at UNISA, An Investigation into different constraint handling techniques for metaheuristics.
  • Vongani Sambo, BSc (Hons) in OR at UNISA, Forecasting of road accident fund claims using a neural network.
  • Tobias Bester (as co-supervisor with Dr C.W. Cleghorn), BSc (Hons) in CS at UP, A Benchmark Suite of Regression Problems to Evaluate Gradient-based Neural Network Training.