University of Hull Research Team Wins Third Place in Cambridge Edge AI Sustainability Challenge

University of Hull Research Team Wins Third Place in Cambridge Edge AI Sustainability Challenge

SustainGRF brings together researchers working on wearable AI and federated learning to explore more privacy-conscious and resource-efficient healthcare applications.

A research team from the University of Hull has secured third place in the Cambridge Edge AI Innovation for Sustainability Challenge 2026 with SustainGRF, a project exploring how smartwatch data and federated learning could support research into the relationship between everyday physical activity and bone health.

Led by PhD researcher Parvin Ghaffarzadeh, the team included Debarati Chakraborty, Koorosh Aslansefat, Yiannis Papadopoulos and Ali Dostan. Together, the team explored how AI models could learn collaboratively from wearable data while keeping raw data local to participating devices.

Bringing wearable AI closer to real-world healthcare

Smartwatches provide opportunities to study everyday physical activity and its potential relationship with health. However, training AI models across distributed devices can create challenges relating to personal data privacy, communication requirements and dependence on centralised computing infrastructure.

SustainGRF explores federated learning as an approach that allows AI models to learn collaboratively without requiring raw personal data to be transferred from local devices. By examining how distributed learning can operate within practical resource constraints, the project connects wearable technology with the wider challenge of developing more sustainable and privacy-conscious AI.

Recognising sustainable AI innovation

The Cambridge Edge AI Innovation for Sustainability Challenge 2026 brought together students and researchers from across the UK to develop AI systems that can collaborate while keeping data local and reducing unnecessary communication and reliance on energy-intensive data centres.

SustainGRF achieved third place, following HiveMind in first place and PyroWatch in second place. The finalist projects demonstrated how Edge AI could contribute to sustainability challenges across agriculture, environmental resilience and healthcare.

Reflecting on the achievement, Parvin Ghaffarzadeh said:

“I wanted to bring this project closer to real life, and this competition was the perfect opportunity. Being selected as one of the finalists, and coming third, gave me the chance to show my results, meet people from different companies and think about how this research could have a real-world impact.”

The result recognises the team’s contribution to exploring how collaborative AI can deliver practical benefits while taking data privacy and resource efficiency into account.

The challenge was organised in collaboration with MICROIP Inc., Arculus System and the University of Cambridge Institute for Sustainability Leadership (CISL).