Rhodes Artificial Intelligence Research Group (RAIRG)

 The Rhodes Artificial Intelligence Research Group (RAIRG) is a group based under the Department of Mathematics. We are a new research group with some members having over half a decade of experience in high-bandwidth signal processing, big data, machine learning, and data science. Members of the group have a varied background in applied mathematics, computer science, artificial intelligence, signal processing, statistics, and astronomical data processing/analysis. We are currently a small group of 7 members working on topics such as machine learning, big data, optimization, computer vision, and signal processing. We welcome MSc, Ph.D., and postdoc candidates excited to work with us.


Dr Marcellin Atemkeng (Coordinator), email: m.atemkeng@ru.ac.za 

Dr Patrice Okouma, email: p.okouma@ru.ac.za 


Current students:

Irene Nandutu

Degree: PhD

Subject: Applied mathematics

Field of Study: Machine Learning
Research: Understanding the integration of sensor technology and machine learning to mitigate conservation problems, with a keen focus on animal-vehicle collisions.
Based: Grahamstown
Future aims: She hopes to continue her journey of building skills for contributing towards a transition to sustainable practices in Research and Artificial Intelligence in the developing world.


Masechaba Sydil Kupa


Degree: Masters of Science
Subject: Physics
Field of Study: Machine Learning
Research: Automating Image Segmentation and Classifying Radio Galaxies Using Deep Neural Network
Based: Cape Town
Future aims: Simultaneous to my MSC, I am a Junior Software Developer at SARAO( South African Radio Astronomy Observatory). My Future endeavors involve proceeding with the development of technical tools that will be useful in Astronomy and later translated to solve social problems. 


Avuya Deyi


Degree: Masters of Science
Subject: Applied Mathematics
Field of Study: Machine Learning
Research: Tackling deep learning models compression for medicinal plant classification. 
Based: Grahamstown
Future aims: His interest in the field of machine learning is rooted from the passion he has for mathematics. He hopes to work for a corporate company as a data scientist. He holds an honours degree in Applied Mathematics and Information Systems.
sisipho hamlomo


Degree: MSc
Subject: Statistics
Field of Study: Machine Learning
Research: Detection of credit fraud using statistical and machine learning techniques
Based: Grahamstown
Future aims: His future plan is to join the industry once the degree is fully completed, more specifically he wants to be in the consulting industry where he would be able to extensively apply his mathematical skills in solving the daily challenges that arise in real life.  
Vanqa Kamva


Degree: Honours
Subject: Pure and applied mathematics
Field of Study: Big data and interferometric techniques
Research: Understanding and modeling aliasing source sidelobes contamination in the field of view of a radio interferometer
Based: Grahamstown
Future aims: I am aspiring to develop myself to a more sophisticated scientist particularly in the study of mathematical sciences, I also wish to extend my interest to fields like computer science and modern physics.
Myren Govender


Degree: Honours
Subject:  Applied mathematics
Field of Study: Machine learning
Research: Exploring the effects of downsampling in deep convolutional neural networks
Based: Grahamstown
Future aims:  He wants to further his education and eventually become a lecturer in applied mathematics.

Recent Publications (selected)

  • Atemkeng, M.,  Perkins,  S., Kenyon, J., Hugo, B. and Oleg Smirnov (2021).  Xova: Baseline-Dependent Time and Channel Averaging for Radio Interferometry, Proceedings of the Astronomical Data Analysis Software and Systems (ADASS) conference
  • Atemkeng, M., Smirnov, O., Tasse, C., Foster, G., & Makhathini, S. (2020). Fast algorithms to approximate the position-dependent point spread function responses in radio interferometric wide-field imaging. Monthly Notices of the Royal Astronomical Society.
  • Fountsop, A. N., Ebongue Kedieng Fendji, J. L., & Atemkeng, M. (2020). Deep Learning Models Compression for Agricultural Plants. Applied Sciences10(19), 6866.
  • Tchakounté F, Pagore AE, Kamgang JC, Atemkeng M. (2020). CIAA-RepDroid: A Fine-Grained and Probabilistic Reputation Scheme for Android Apps based on Sentiment Analysis of Reviews. Future Internet, 12(9), 145.
  • Ebiele F, Ansah-Narh T, Djiokap S, Proven-Adzri E, Atemkeng M. (2020). Conventional Machine Learning based on Feature Engineering for Detecting Pneumonia from Chest X-rays. ACM Annual Conference of the South African Institute of Computer Scientists and Information Technologists, Cape Town Sep 14, 2020.
  • Tchakounté, F., Faissal, A., Atemkeng, M., & Ntyam, A. (2020). A Reliable Weighting Scheme for the Aggregation of Crowd Intelligence to Detect Fake News. Information11(6), 319.
  • Cotton, W.D., Thorat, K., Condon, J.J., Frank, B.S., Józsa, G.I.G., White, S.V., Deane, R., Oozeer, N., Atemkeng, M., Bester, L. and Fanaroff, B. (2020). Hydrodynamical backflow in X-shaped radio galaxy PKS 2014− 55. Monthly Notices of the Royal Astronomical Society495(1), pp.1271-1283.
  • Mulongo, J., Atemkeng, M., Ansah-Narh, T., Rockefeller, R., Nguegnang, G. M., & Garuti, M. A. (2020). Anomaly Detection in Power Generation Plants Using Machine Learning and Neural Networks. Applied Artificial Intelligence34(1), 64-79.

Last Modified: Fri, 05 Mar 2021 13:26:22 SAST