CNNs lack human-centred explainability in their natural forms, despite their efficiencies. An ongoing project and a requirement for the completion of a PhD at The School of Engineering and Built Environment, Griffith University, I aim to reveal what a CNN sees and not just where it looked. 
Read more
This project addresses the challenge of extracting discriminant information from multiple sensors exhibiting unique spectral and transient behaviors—a critical need in modern diagnostic systems. Focusing on high-precision automatic regrinding equipment used for micro drill bits, the study emphasizes real-time monitoring during the grinding process to safeguard drill bit longevity and overall equipment performance. 
Read more
Honoured to be on a panel discussion at the Data for Policy Conference hosted at the Evans School of Public Policy & Governance, University of Washington on Towards an Inclusive Data Governance Policy for the use of AI in Africa alongside Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC) colleagues (Jude Kong and Jake Okechukwu Effoduh), moderated by the International Development Research Centre (IDRC) project officer Chaitali Sinha.
Read more
Under Prof. Hur Jang-Wook’s supervision, I spearheaded this project between March 2019 and May 2021 as a requirement for fulfilling the requirements of masters (by research) at the Department of Mechanical Engineering (Department of Aeronautics, Mechanical and Electronic Convergence Engineering), Kumoh National Institute of Technology (KIT), Republic of Korea. 
Read more
Under Prof. Hur Jang-Wook’s supervision, I collaborated with a team member as part of his Masters (by research) requirements at the Department of Mechanical Engineering (Department of Aeronautics, Mechanical and Electronic Convergence Engineering), Kumoh National Institute of Technology (KIT), Republic of Korea. 
Read more
About 30% of greenhouse gas emissions come from diesel engines, which contribute to a variety of health and environmental problems. This project was motivated by the need to discover the optimal diesel emulsion to reduce fuel emmision, maintain engine efficiency and lower costs. 
Read more
The project proposed an informed decision-making framework for remaining compliant with domestic and international standards while also improving performance and extending the life cycles of proton-exchange membrane fuel cells (PEMFC) using Finite Element Analysis (FEA). 
Read more
The project aimed at developiing fault disgnostic frameworks for electrical motors. Supervised by Prof. Hur Jang Wook and spearheaded by myself, the team designed test beds, conducted experiments and authored a journal articles. 
Read more
The project aimed at developiing fault disgnostic frameworks for electronic (capacitors, etc) components. Supervised by Prof. Hur Jang Wook and spearheaded by myself, the team designed test beds, conducted experiments and authored a journal articles. 
Read more
About 30% of greenhouse gas emissions come from diesel engines, which contribute to a variety of health and environmental problems. This project was motivated by the need to discover the optimal diesel emulsion to reduce fuel emmision, maintain engine efficiency and lower costs. 
Read more
The project Explores different statistical and machine learning methods for estimating the remaining useful life (RUL) of Rolling Elemnet Bearings. 
Read more
Published in 5th International Conference on Materials and Reliability Jeju, Korea, 2019
This short paper proposes a kernel principal component analysis (KPCA) feature fusion technique for degradation assessment, and a deep learning model for prognostics of rolling element bearings. Read more
Recommended citation: U. E. Akpudo and J. H. Hur, “A Feature Fusion-based Prognostics Approach for Rolling Element Bearings,” 5th International Conference on Materials and Reliability Jeju, Korea, Nov. 27-29, 2019.
Download Paper | Download Slides
Published in IEEE Access, 2020
This study presents a robust approach for vibration-based failure diagnostics of electromagnetic/solenoid pumps which employ a multi-domain feature extraction procedure (statistical time-domain and frequency-domain features, Mel frequency cepstral coefficients, and continuous wavelet coefficients) for capturing linear and nonlinear properties from the signals. Read more
Recommended citation: U. E. Akpudo and H. Jang-Wook, "A Multi-Domain Diagnostics Approach for Solenoid Pumps Based on Discriminative Features," in IEEE Access, vol. 8, pp. 175020-175034, 2020, doi: 10.1109/ACCESS.2020.3025909..
Download Paper
Published in Journal of Mechanical Science and Technology (JMST), 2020
This study presents a methodology for constructing a reliable HI for bearing prognostics, choosing a reliable TSP, and provides a comparison between ML and DL methods for bearing prognostics. Read more
Recommended citation: Akpudo, U.E., Hur, JW. Towards bearing failure prognostics: a practical comparison between data-driven methods for industrial applications. Journal of Mechanical Science and Technology (JMST) 34, 4161–4172 (2020). https://doi.org/10.1007/s12206-020-0908-7
Download Paper
Published in IEEE Access, 2021
This study introduces a multi-sensor prognostics approach which merges highly prognosible statistical features from vibrational and pressure sensor measurements after a multi-level wavelet decomposition of the signals. Read more
Recommended citation: U. E. Akpudo and H. Jang-Wook, "An Automated Sensor Fusion Approach for the RUL Prediction of Electromagnetic Pumps," in IEEE Access, vol. 9, pp. 38920-38933, 2021, doi: 10.1109/ACCESS.2021.3063676.
Download Paper
Published in Electronics, 2021
This study proposes the use of common rail (CR) pressure differentials and a deep one-dimensional convolutional neural network (1D-CNN) with the local interpretable model-agnostic explanations (LIME) for empirical diagnostic evaluations (and validations) using a KIA Sorento 2004 four-cylinder line engine as a case study. Read more
Recommended citation: Akpudo, U.E.; Hur, J.-W. An Explainable DL-Based Condition Monitoring Framework for Water-Emulsified Diesel CR Systems. Electronics 2021, 10, 2522. https://doi.org/10.3390/electronics10202522.
Download Paper
Published in Energies, 2021
This study proposes a hybrid DNN and one-dimensional CNN diagnostics model (D-dCNN) which automatically extracts high-level discriminative features from vibration signals for fault detection and isolation (FDI). Read more
Recommended citation: Akpudo, U.E.; Hur, J.-W. D-dCNN: A Novel Hybrid Deep Learning-Based Tool for Vibration-Based Diagnostics. Energies 2021, 14, 5286. https://doi.org/10.3390/en14175286
Download Paper
Published in Algorithms, 2022
This study explores artificial intelligence-based models for learning the discriminant spectral information stored in the vibration signals and considers the accuracy and cost implications of spectral isolation of the critical spectral segments of the signals for accurate equipment monitoring. Read more
Recommended citation: Akpudo, U.E.; Hur, J.-W. Exploring the Efficiencies of Spectral Isolation for Intelligent Wear Monitoring of Micro Drill Bit Automatic Regrinding In-Line Systems. Algorithms 2022, 15, 194. https://doi.org/10.3390/a15060194.
Download Paper
Published in Data for Policy 2022, 2022
This brief unveils some vulnerabilities surrounding the use of AI in SSA and promotes equitable access to new technologies in SSA amidst the anxiety around AI and concerns about data governance. Read more
Recommended citation: J. O. Effoduh, U. E. Akpudo, and J. D. Kong, “Toward a trustworthy and inclusive data governance policy for the use of artificial intelligence in Africa,” Data & Policy, vol. 6, p. e34, 2024. doi:10.1017/dap.2024.26.
Download Paper | Download Slides
Published in 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA), 2023
This study explores and draws for the first time, qualitative insights into Ultra-FGVC images through saliency-based explanation methods that provide intuitive hints on where the models are looking at the images. Read more
Recommended citation: U. E. Akpudo, X. Yu, J. Zhou and Y. Gao, "What EXACTLY are We Looking at?: Investigating for Discriminance in Ultra-Fine-Grained Visual Categorization Tasks," 2023 International Conference on Digital Image Computing: Techniques and Applications (DICTA), Port Macquarie, Australia, 2023, pp. 129-136, doi: 10.1109/DICTA60407.2023.00026.
Download Paper
Published in 2024 IEEE International Conference on Multimedia and Expo (ICME), 2024
This paper extends the Invertible Concept-based Explainer (ICE) to introduce a new ingredient measuring concept consistency. Read more
Recommended citation: U. E. Akpudo, Y. Gao, J. Zhou and A. Lewis, "Coherentice: Invertible Concept-Based Explainability Framework for CNNs beyond Fidelity," 2024 IEEE International Conference on Multimedia and Expo (ICME), Niagara Falls, ON, Canada, 2024, pp. 1-6, doi: 10.1109/ICME57554.2024.10687699.
Download Paper | Download Slides
Published in , 2025
This paper addresses limitations in concept-based explainability with the novel transformative nonlinear concept explainer (TraNCE) for CNN explanation. Read more
Recommended citation: U. E. Akpudo, Y. Gao, J. Zhou and A. Lewis, "TraNCE: Transformative Nonlinear Concept Explainer for CNNs," in IEEE Transactions on Neural Networks and Learning Systems, vol. 36, no. 6, pp. 10156-10170, June 2025, doi: 10.1109/TNNLS.2025.3556019.
Download Paper
Published in , 2025
This paper addresses limitations in concept-based explainability with principles of cognition. CoPISan is a plug-in module designed to work seamlessly with unsupervised concept-based CNN explanation methods Read more
Recommended citation: U. E. Akpudo, Y. Gao, J. Zhou and A. Lewis, "CoPISan: Contrastive Perceptual Inference and Sanity Checks for Concept-Based CNN Explanations," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 47, no. 9, pp. 8193-8212, Sept. 2025, doi: 10.1109/TPAMI.2025.3576755.
Download Paper
Published:
I had the opportunity to present my insights on how Big Data-driven Prognostics and Health Management (PHM) is shaping the future of industrial reliability. Read more
Published:
Addressed AI’s role in early disaster warning systems, climate adaptation strategies, and risk mitigation. Showcased case studies on AI-driven sustainable urban water systems. Read more
Published:
Discussed how AI can enhance predictive flood monitoring, real-time water quality assessment, and smart irrigation systems. Explored machine learning applications in optimizing hydropower efficiency and water distribution networks. Read more
Published:
Anchored a one-week workshop organised by Defense Reliability Laboratory, Kumoh National Institute of Technology for graduate and undergraduate students for practical approaches to data-driven prognostics and health management of mechanical, electrical and electronic components. Read more
Published:
Anchored a one-week workshop organised by Defense Reliability Laboratory, Kumoh National Institute of Technology for graduate and undergraduate students for practical approaches to data-driven prognostics and health management of mechanical, electrical and electronic components. Read more
Published:
Honoured to pitch my research proposal to Hanwa Systems on Emulsified Diesel Injection Systems Monitoring using intelligent PHM frameworks Read more
Published:
Pitched my proposal Smart Factory Automation: A correlation-based GA-DNN Model for Smart AC Monitoring and Control at the Daewoong Foundation AI & Big Data Hackathon organised by Daewoong Foundation. Read more
Published:
This initiative provides a platform for fostering cultural awareness and inclusivity through structured dialogues, exhibitions, presentations, and interactive sessions amongst high and middle school children. Read more
Published:
Honoured to be on a panel discussion at the Data for Policy Conference on Towards an Inclusive Data Governance Policy for the use of AI in Africa alongside Africa-Canada Artificial Intelligence and Data Innovation Consortium (ACADIC) colleagues (Jude Kong and Jake Okechukwu Effoduh), moderated by the International Development Research Centre (IDRC) project officer Chaitali Sinha (she/her). Read more
Published:
Pitched my proposal to 3rd Smart Agriculture Symposium organised by the ARC Research Hub for Driving Farming Productivity and Disease Prevention, Griffith University Australia. Read more
Published:
Pitched my proposal to different talent groups at the Emerging Industry Leaders Program organised by Griffith University Australia. Read more
Published:
Pitched my proposal on Unveiling AI Concerns for Sub-Saharan Africa and Other Vulnerable Groups’ at the ICONIC 2024 Read more
Published:
I’m honoured to have played a small part in this pilot initiative—not just attending, but volunteering to support peers through facilitation, team engagement, and feedback. Read more
Workshop, Konigin Des Friedens College, 2014
At Königin des Friedens College, I delivered structured lessons in mathematics and science while fostering disciplined academic engagement. I developed lesson plans aligned with curriculum standards, simplified complex concepts for diverse learning levels, and prepared students for internal and external examinations. Read more
Workshop, Kumoh National Institute of Technology, 2021
At Kumoh National Institute of Technology, I served in a teaching and research support capacity, delivering tutorials and practical sessions in engineering and computational subjects. I guided undergraduate students through core concepts in signal processing, machine learning, and dynamic systems, simplifying complex theories into applied problem-solving exercises. I also mentored students on laboratory work, coding implementation (Python/MATLAB), and research projects, fostering analytical thinking and technical independence. My teaching approach emphasized clarity, structure, and real-world application, helping students bridge theory with hands-on engineering practice. Here are a few: Read more
Masters course, EIT, Brisbance Campus, 2026
I deliver instruction and support in engineering and technology programs, guiding students through practical and theoretical aspects of Mechanical Engineering. I facilitate workshops, tutorials, and project-based learning, helping students develop applied problem-solving skills and technical proficiency in tools like MATLAB and Python. My teaching emphasize real-world applications, fostering critical thinking, collaborative learning, and professional readiness. In detail, I do the following: Read more