This research develops machine learning techniques to improve fibre-optic access networks, enabling faster, more reliable, and lower-cost internet connections. By allowing transmitters to adapt using receiver feedback, it reduces signal distortion, equipment complexity, and power consumption, helping build resilient communication networks capable of supporting future digital societies.

This research uses artificial intelligence to analyse immune-system data and predict vaccine effectiveness. By identifying early biological signals associated with strong, long-lasting immunity, the work aims to improve vaccine design, personalise vaccination strategies, and support development of universal vaccines capable of protecting against rapidly evolving infectious diseases.

This research explores how heterogeneous AI agents can establish common ground during collaboration. By separating communication and action into distinct decision-making policies, agents can engage in micro-conversations that create shared understanding. The work aims to improve teamwork among diverse robots and support future human-AI collaboration in complex environments.

This research uses artificial intelligence and machine learning to analyze light from distant exoplanets. By interpreting atmospheric spectral signatures, it aims to identify potentially habitable worlds and search for signs of life beyond Earth. The work supports future space missions designed to answer one of humanity’s oldest questions: Are we alone?

This research investigates tropical atmospheric waves that influence rainfall, storms, and seasonal weather patterns. Using satellite observations and machine learning, the study shows that wave propagation depends on geographic location, upper-level winds, and topography. The findings can improve weather forecasting models and help communities better prepare for extreme rainfall events.

This research examines whether changes in walking patterns can predict frailty before serious health events occur. Using smart insoles, GPS tracking, and machine learning, mobility data from older adults is analyzed to identify early warning signs of decline. The goal is to enable proactive interventions and support healthier aging.

This PhD defense presents research at the intersection of machine learning, reinforcement learning, social learning, affective computing, and human-AI interaction. The thesis is that social learning is a powerful mechanism for intelligence and explores how AI agents can learn from one another and from humans. Projects include intrinsic social influence rewards for multi-agent coordination, communication protocols emerging through influence, conversational agents trained from implicit human feedback such as sentiment, generative models improved through facial-expression feedback, and personalized well-being prediction from behavioral and physiological data. The thesis concludes that socially informed learning can improve coordination, adaptability, and human alignment.

This research uses artificial intelligence and astronomical data to search for signs of extraterrestrial intelligence. By applying anomaly-detection techniques to telescope images, the project identifies unusual signals or patterns that may indicate intelligent activity, with the ultimate goal of detecting and decoding potential messages from civilizations beyond Earth.

This research applies fluid mechanics, numerical simulations, and machine learning to model the brain’s waste-clearance system during sleep. By investigating how fluid moves through brain tissue and how aging or injury affect this process, the work aims to identify strategies for preventing or slowing neurodegenerative diseases such as Alzheimer's.

This research develops an AI model that combines thyroid ultrasound imaging with genetic testing to improve diagnosis of indeterminate thyroid nodules. By integrating molecular and imaging data, the model helps distinguish benign from cancerous nodules more accurately, reducing unnecessary surgeries and improving clinical decision-making for thyroid cancer patients.