Workshop Date: 20 July 2025
IEEE ICDCS Workshop on ‘Federated and Privacy Preserving AI in Biomedical Applications’
When: 20th of July, 13:45-17:15
Where: Radisson Blu Hotel (301 Argyle Street, Glasgow, G2 8DL, United Kingdom). For more information visit this link: https://icdcs2025.icdcs.org/venue/
Schedule:
13:45 – 14:30 – Keynote 1: Prof. Fahim Kawsar, University of Glasgow / Nokia Bell Labs
- Title: Edge AI at Human Scale: Building the Invisible Infrastructure of Pervasive Intelligence
- Abstract: What if your ears could become a window into your cardiovascular health? What if a child’s first encounter with AI didn’t come from YouTube, but from building and training their own models in the classroom? What if a $10 camera could detect industrial faults in milliseconds—without touching the cloud? This talk explores the reality of Edge AI at human scale: intelligent systems engineered to operate entirely on-device, under real-world constraints. OmniBuds is a clinically driven, ear-worn digital health platform that enables continuous, passive, and context-aware monitoring of hypertension and respiratory health, using multimodal sensing and microcontroller-optimised inference. Bella is a foundational AI education platform that introduces computing and artificial intelligence to children aged 6–12 through interactive, explainable, and offline model training—crafted specifically for safety, engagement, and accessibility in diverse classroom environments. CaaS is an edge-native camera platform for industrial automation, delivering low-latency, task-specific visual intelligence on low-power microcontrollers, without relying on external compute or connectivity. These platforms required targeted innovations in few-shot learning, self-supervised techniques, compiler-level optimisation, and event-driven inference—all while balancing efficiency, interpretability, and real-world resilience. I will conclude by outlining core principles for translating AI research into deployable, trustworthy, and domain-specific systems that scale—advancing the vision of pervasive intelligence across health, education, and industry.
14:30 - 15:15 – Keynote 2: Dr. Blesson Varghese, University of St. Andrews
- Title: Making Machine Learning Work on Edge Systems
- Abstract: Machine learning (ML) at the edge - where data is processed close to where it is generated - is a key enabler for many emerging applications of scientific and societal relevance. However, deploying ML in these resource-constrained environments presents significant challenges, particularly in terms of computation and communication efficiency.
This talk will highlight key challenges in making edge ML systems practical, using federated learning as a central example. I will present approaches developed in my lab to overcome these challenges, along with insights from experimental systems that have broader applicability across domains, including biomedical applications.
15:15- 15:45 Coffee Break
15:45 – 16:15 Keynote 3: Dr. Fani Deligianni University of Glasgow
- Title: Privacy-Preserved Human Motion Analysis for Healthcare Applications
- Abstract: Human motion analysis is critical for healthcare and activity recognition, yet privacy concerns pose significant deployment barriers. This talk presents comprehensive approaches to lightweight, privacy-preserving human motion analysis across visual and radar-based sensing modalities using Differential Privacy techniques.
16:15- 17:15 Paper Session
- 104: Federated Deep Reinforcement Learning for Privacy Preserving Robotic-Assisted Surgery, Sana Hafeez, Sundas Mulkana, Muhammad Imran and Michele Sevegnani
- 170: FedGraph: Probing-Based Personalized Federated Learning for Human Activity Recognition with Multimodal Physiological Signals, Pai Chet Ng, Arash Rasti-Meymandi, Seyed Mohammad Sheikholeslami and Konstantinos Plataniotis
- 150: (Late Abstract) Differentially Private Gradient Based Parameters Framework for Video Recognition, Idris Zakariyya, Kaushik Bhargav Sivangi and Fani Deligianni
- 212 (Late Abstract): Blockchain-Enabled Privacy-Preserving Machine Learning for Biomedical Applications in IoT, Shailendra Rathore