Department of Electrical and Mining Engineering

Prof Bhekisipho Twala

College of Science, Engineering and Technology
School of Engineering
Department: Electrical and Mining Engineering
Tel: 011 471 2354


  • B.A. in  Economics & Statistics, University of Swaziland, 1992.
  • M.Sc. in Statistics, Southampton University, UK, 1995.
  • PhD in Machine Learning & Statistical Science, Open University, UK, 2005.

NRF Rating


Fields of academic interests

Research interests

  • Image and Signal Processing
  • Intelligent Systems
  • Knowledge Discovery and Reasoning Under Uncertainty
  • Multivariate Statistics
  • Theoretical and Applied Research in Machine Learning

Field of Specialisation

  • Data Science
  • Artificial Intelligence


  1. Jitendra, R., Twala, B., Gopalratman, G (2017). Non-Linear Filtering: Concepts and Engineering Applications. CRC Press (Taylor & Francis Group).

Journal articles

Selected Journals

  1. [Accepted] Langa, H. and Twala, B. (2018). Identifying Top Performers in the Electrical Training Programme at FSASEC - The Vaal University of Technology Using Regression Analysis: Who are the Stars? International Journal of Modern Research in Engineering & Management.
  2. [Accepted] Mabaso, M., Withey, D., and Twala, B. (2018). Spot Detection Methods in Fluorescence Microscopy Imaging: A review. Journal of Image Analysis and Stereology.
  3. [In Press] Marwala, L. and Twala, B. (2018) Electricity Load Forecasting using an Ensemble of Optimally-Pruned, Online Sequential and Basic Extreme Learning Machines. Journal of Computing and Digital Systems.
  4. [In Press] Mpanza, L. and Twala, B. (2017). Rough Set Theory for Bushing Fault Detection with Improved Transparency. Journal of Advanced Computational Intelligence and Intelligent Informatics.
  5. Duma, M., and Twala, B. (2018) Optimising Latent Features Using Artificial Immune System in Collaborative Filtering for Recommender Systems. Applied Soft Computing, 71, pp. 183-198
  6. Mareli, M. and Twala, B. (2018). An Adaptive Cuckoo Search Algorithm for Optimisation. Applied Computing and Informatics, 14 (2), pp. 107-115.
  7. Muteba, M., Twala, B. and Nicolae, D.V. (2018). Performance Indexes of a Novel Synchronous Reluctance Motor with Sinusoidal Rotor Shape. IET Electric Power Applications, 12 (6), pp. 852-858
  8. Twala, B. (2017). When Partly Missing Data Matters in Software Effort Development Prediction. Journal of Advanced Computational Intelligence and Intelligent Informatics, 21 (5), pp 803-812.
  9. Twala B. (2014). Extracting Grey Relational Systems from Incomplete Road Traffic Accidents Data: The Case of the Gauteng Province in South Africa. Journal of Expert Systems – The Journal of Knowledge Engineering, 31 (3), pp. 220-231.
  10. Twala, B. (2014). Reasoning with Noisy Software Engineering Data. Applied Artificial Intelligence, 28 (6), pp. 533-554.
  11. Twala, B. and Phorah, M. (2010). Predicting Incomplete Gene Microarray Data with the Use of Supervised Learning Algorithms. Pattern Recognition Letters. 31 (13), pp. 2061-2069.
  12. Twala, B. and Cartwright, M. (2010). Ensemble Imputation Methods for Missing Software Engineering Data. Intelligent Data Analysis, 14 (3), pp. 1-33.
  13. Twala, B. (2010). Multiple Classifier Application to Credit Risk Assessment. Expert Systems with Applications, 37 (4), pp. 3326-3336.
  14. Twala, B. (2009). Comparison of Techniques for Handling Incomplete Data Using Decision Trees. Applied Artificial Intelligence.23 (5), pp. 373-405.
  15. Twala, B., Jones, C., and Hand, D.J. (2008). Good Methods for Coping with Missing Data in Decision Trees. Pattern Recognition Letters, 29, pp. 950-956.

Professional positions, fellowships & awards

Professional affiliation

  • Fellow of the Royal Statistical Society (RSS)
  • Association of Computing Machinery (ACM)
  • Chartered Institute of Transport South Africa (CITSA)
  • IEEE (Senior member)
  • International Association of Engineers (IAENG)
  • South African Council for Automation and Control (SACAC)
  • International Federation of Automatic Control (IFAC)
  • Professional Scientist (Pr.Sc.)


  • British Council Scholarship Award, 1993
  • Open University Award, UK, 1998
  • NSTF-South 32 TW Kambule (Research and its Outputs) Award, 2016


  • IDC Grant Funding Implementation Plan 2015. “Advancement of Automation and Control”. R1 Million awarded via a grant scheme.
  • ESKOM Tertiary Education Support Programme 2014.”Target Tracking and Fusion with H-infinity Filtering in the Presence of Missing and Delayed Measurements (TTFHIMDM). R30, 000 awarded via grant scheme.
  • ESKOM Tertiary Education Support Programme 2013.”Wireless laboratory Suburban Electrical Immune System (SEIS). R100, 000 awarded via grant scheme.
  • EPSRC GR/S55347/01 “Data Imputation Techniques for Software Engineering” 123K Sterling awarded via First Grant Scheme.
  • World Bank grant R150, 000 for “Modification of Sampling and Weighting Processes for Labour Force Surveys”.
  • Student Grants (for both undergraduate and postgraduate students)
    •   NRF, South Africa (R1, 970,000-00 per year for 5 PhD; 8 Masters; and 4 Beng students)
    •   Canon Collins, UK (R100,000-00 per year for 1 PhD student)
    •   URC, South Africa (R170,000 for 2 Masters students)


Short Biography

βhekisipho Twala is a Professor in Artificial Intelligence and Data Science with the Department of Electrical and Mining Engineering at the University of South Africa. Before then he was the Director of the Institute for Intelligent Systems at the University of Johannesburg (UJ) and was also Head of the Electrical and Electronic Engineering Science Department at UJ. Before then, Prof

Twala was a Principal Research Scientist at the Council for Science and Industrial Research (CSIR) within the Modelling and Digital Science Unit (where he is currently an Advisor). His research work at the CSIR involved an expanded swath of data, analytics, and optimization approaches that bring a complete understanding of digital customer experiences.

Prof. Twala was also a post-doctoral researcher at Brunel University in the UK, mainly focussing on empirical software engineering research and looking at data quality issues in software engineering. His broad research interests include image and signal processing, multivariate statistics, applied and theoretical machine learning, knowledge discovery and reasoning with uncertainty, and the interface between statistics and computing, and has published over 100 scientific papers.

Prof. Bhekisipho Twala has a wide-ranging work experience in organizations ranging from banks, through universities, to governments.