Selected work
Applied machine learning, medical imaging and decision systems. Explore the approach, evidence and limitations behind each project.
Combining convolutional networks to explore MRI tumour classification, calibration and model attention.
Model comparison, probability calibration and Grad-CAM visualisations.
An ensemble pipeline exploring chest X-ray classification, model comparison and evaluation.
A documented pipeline covering preprocessing, model comparison and recall/F1 evaluation.
Grid-based path-planning system implementing A*, BFS, and DFS with an interactive GUI for visualising environments, tuning parameters, and running batch experiments.
Fully functional cross-platform GUI with batch experiment runner, CSV export, and real-time path visualisation.
Formal Markov Decision Process model for hospital drug inventory management. Applies value iteration and policy iteration to derive optimal ordering policies under demand uncertainty, with simulation-based evaluation.
Reported simulation result: approximately 8.6% lower mean cost than a baseline heuristic across 50 runs (2280.8 versus 2495.6).
Applied machine-learning coursework using UK AutoTrader vehicle listing data to explore price modelling. Covers data preprocessing, feature engineering, EDA, and comparative regression models.
End-to-end ML pipeline with structured discussion of bias–variance trade-offs, scaling effects, and validation strategy.
Participated in live research to annotate newly created datasets for ongoing AI training projects at MMU, focusing on high-quality data delivery and peer review.
Explored sustainable design methodologies and materials in additive manufacturing through collaboration with industry partners.
Built natural language processing models exploring sentiment analysis and text generation using modern transformer architectures.
Independent civic tool enabling the Kurdish community in the UK to find and communicate with their MPs, councillors, and local representatives by postcode.
Tabular Q-learning with discretised states for buy, hold and sell decisions.
An Android meal-planning and food-tracking application built with .NET MAUI.