Overview
Kenneth is a Postdoctoral Research Fellow in the College of Engineering, Mathematics & Physical Sciences, and a member of the Applied Dynamics and Control Laboratory. He is currently involved in an EPSRC New Horizons project exploring intelligent models for early and hard-to-visualise bowel cancer detection. With bowel cancer being the second most common cancer in Europe and the second deadliest in the UK, Kenneth will be exploring the dynamics of a newly developed self-propelled robotic capsule for early cancer detection using machine learning.
Kenneth completed his PhD studies at the University of Exeter under the Applied Dynamic and Control Laboratory where he investigated the rich dynamics of a rotary-percussive drilling system and machine learning methods for impact modes categorisation and downhole rock characterisation. He was supervised by Dr Yang Liu and Dr Evangelos Papatheou under the sponsorship of the Petroleum Technology Development Fund (PTDF) of the Federal Republic of Nigeria. He plans to extend the knowledge from his PhD study in exploring the impact dynamics of Dr Yang Liu’s self-propelled endoscopic capsule for detecting hard-to-visualise early bowel cancers. The idea is based on the fact that, like downhole rock units, cancerous lesions right from onset, present biomechanical inhomogeneities that are reflected in the dynamics and long-term behaviours of their impacting system such as a robotic capsule traversing the bowel.
Kenneth holds a BSc (Hons) degree in Geology from the University of Ibadan, Nigeria, and a Master of Science degree in Applied Geophysics from the same university before proceeding to the University of Salford, UK where he obtained a Master of Science degree in Petroleum and Gas Engineering with distinction. Over the years, Kenneth’s work and research experience have revolved around geological and geophysical investigations for structural integrity and mineral exploration, core drilling for mineral deposit assessment, flow dynamics for pipeline monitoring, vibration signal analysis for system characterisation and machine learning with real-life application.
Publications
Copyright Notice: Any articles made available for download are for personal use only. Any other use requires prior permission of the author and the copyright holder.
2023
- Afebu KO, Tian J, Papatheou E, Liu Y, Prasad S. (2023) Two-stage machine learning models for bowel lesions characterisation using self-propelled capsule dynamics, Nonlinear Dynamics, volume 111, no. 20, pages 19387-19410, DOI:10.1007/s11071-023-08852-6.
- Tian J, Afebu K, Wang Z, Liu Y. (2023) Dynamic analysis of a soft capsule robot self-propelling in the small intestine via finite element method, Nonlinear Dynamics, DOI:10.1007/s11071-023-08376-z.
- Afebu K, Tian J, Liu Y, Prasad S. (2023) AI-assisted dynamic tissue evaluation for early bowel cancer diagnosis using a vibrational capsule, IEEE Robotics and Automation Letters, volume 8, pages 2341-2348, DOI:10.1109/LRA.2023.3251853.
- Tian J, Afebu K, Bickerdike A, Liu Y, Prasad S, Nelson B. (2023) Fundamentals of Bowel Cancer for Biomedical Engineers, Annals of Biomedical Engineering, DOI:10.1007/s10439-023-03155-8.
2022
- Afebu KO, Liu Y, Papatheou E. (2022) Machine learning-based rock characterisation models for rotary-percussive drilling, Nonlinear Dynamics, volume 109, no. 4, pages 2525-2545, DOI:10.1007/s11071-022-07565-6. [PDF]
- Afebu KO, Liu Y, Papatheou E. (2022) Feature-based intelligent models for optimisation of percussive drilling, Neural Networks, volume 148, pages 266-284, DOI:10.1016/j.neunet.2022.01.021. [PDF]
2021
- Afebu KO. (2021) Intelligent models for optimisation of the vibro-impact drilling system.
- Afebu KO, Liu Y, Papatheou E. (2021) Application and comparison of feature-based classification models for multistable impact motions of percussive drilling, Journal of Sound and Vibration, volume 508, pages 116205-116205, article no. 116205, DOI:10.1016/j.jsv.2021.116205. [PDF]
- Afebu K, Liu Y, Papatheou E, Guo B. (2021) LSTM-based approach for predicting periodic motions of an impacting system via transient dynamics, Neural Networks, volume 140, pages 49-64, DOI:10.1016/j.neunet.2021.02.027.
2015
- Afebu KO, Abbas AJ, Nasr GG, Kadir A. (2015) Integrated Leak Detection in Gas Pipelines Using OLGA Simulator and Artificial Neural Networks, Abu Dhabi International Petroleum Exhibition and Conference, 9th - 12th Nov 2015, Day 1 Mon, November 09, 2015, DOI:10.2118/177459-ms. [PDF]