Radio sensing, medical imaging and intelligent computing systems.
Doctoral research · Electronic Engineering
Wireless capsule endoscopy provides images of the gastrointestinal tract. My research investigates the accompanying localisation problem: using radio measurements and antenna positions to infer where the capsule is.
I explore machine learning and probabilistic approaches, including anchor-aware conditional flow matching, alongside software-defined radio and antenna systems.
Research Technician · Blizard Institute
CE-Track is a Queen Mary pre-spinout developing a wearable antenna-based system to locate and track capsule endoscopes. My contribution focuses on AI-based reconstruction and modelling of clinical imaging data.
I work with Professor Akram Alomainy, Dr Mohamed Adhnan Thaha and Dr Muhammad Qamar Satti, bringing together RF engineering, medical imaging and clinical expertise.
CE-Track was selected for the London Institute for Healthcare Engineering (LIHE) MedTech Venture Builder 2025–2026 cohort.
I investigate AI-based approaches to reconstructing gastrointestinal anatomy and describing variation in colon shape. This work is at the study-development stage.
CE-Track at a MedTech Venture Builder event: watch the video.
First-author publication · IEEE JBHI, 2024
Our paper investigates neural networks for tuberculosis prediction within a serverless e-health application. The deployment architecture uses Amazon EKS and AWS Fargate to serve image-prediction requests through scalable container-based inference.
Collaborative publications
My wider publications investigate edge AI, AI-enabled computing environments, container orchestration and healthcare applications. These collaborations connect machine learning methods with the systems in which they operate.
