This research develops a machine learning system that automatically assesses the quality of wearable sensor data before it is used for clinical decision-making. By filtering unreliable signals and distinguishing noise from genuine health events, the approach aims to improve diagnostic accuracy, reduce false alarms, and enable trustworthy medical use of wearable technologies.

This research explores how redesigning onboarding experiences for contact tracing apps can improve public understanding, trust, and adoption. Through co-design workshops with experts and smartphone users, it identifies strategies that better explain privacy practices, personalise user choices, and reinforce community participation to strengthen future pandemic responses.

This project developed AI Care, a voice-based caregiving system for people with early-stage Alzheimer's disease. Unlike conventional voice assistants, it uses caregiver-maintained medical records to provide personalised, safety-aware support. By adapting to users rather than requiring users to adapt to technology, AI Care aims to extend safe, independent living at home.

This research evaluates electronic case reporting (ECR), an automated disease surveillance system that alerts public health agencies as soon as diagnoses are recorded. By analyzing surveillance data and clinician experiences, the work aims to improve outbreak detection speed, accuracy, and usability—helping public health respond earlier and save lives.