Matthias Omotayo Oladele is a PhD researcher in Information Technology at the Durban University of Technology, South Africa. His research focuses on artificial intelligence for healthcare, computer vision, facial analysis, and medical image processing.
His current doctoral research centres on the development of deep learning models for automated eye disease detection using retinal fundus images. His work covers multi-label disease classification, retinal vessel segmentation, domain adaptation, pseudo-label generation, ensemble learning, and explainable artificial intelligence. The research seeks to improve the accuracy, interpretability, and practical use of AI-based diagnostic systems, particularly where labelled medical data are limited.
He also has experience in facial age prediction, convolutional neural networks, advanced facial image preprocessing, and hybrid optimisation methods such as Differential Evolution and Reinforcement Learning. His work combines model development, performance evaluation, interpretability, and practical deployment through user-friendly applications.
His broader interests include machine learning, deep learning, healthcare diagnostics, cybersecurity, intelligent decision-support systems, and the application of AI to real-world social and medical challenges. He welcomes research collaboration in artificial intelligence, medical image analysis, computer vision, explainable AI, and digital security.
Matthias Omotayo Oladele is a PhD researcher in Information Technology at the Durban University of Technology, South Africa. His research focuses on artificial intelligence for healthcare, computer vision, facial analysis, and medical image processing.
His current doctoral research centres on the development of deep learning models for automated eye disease detection using retinal fundus images. His work covers multi-label disease classification, retinal vessel segmentation, domain adaptation, pseudo-label generation, ensemble learning, and explainable artificial intelligence. The research seeks to improve the accuracy, interpretability, and practical use of AI-based diagnostic systems, particularly where labelled medical data are limited.
He also has experience in facial age prediction, convolutional neural networks, advanced facial image preprocessing, and hybrid optimisation methods such as Differential Evolution and Reinforcement Learning. His work combines model development, performance evaluation, interpretability, and practical deployment through user-friendly applications.
His broader interests include machine learning, deep learning, healthcare diagnostics, cybersecurity, intelligent decision-support systems, and the application of AI to real-world social and medical challenges. He welcomes research collaboration in artificial intelligence, medical image analysis, computer vision, explainable AI, and digital security.