Mohammad Malekzadeh

Mohammad Malekzadeh is a Senior Research Scientist and Tech Lead at Nokia Bell Labs in Cambridge, UK. His team develops machine learning solutions for personal data, prioritizing multi-modality, data efficiency, individual privacy, and personalization. Previously, he was a Research Associate at Imperial College London, collaborating with Prof. Deniz Gunduz on Privacy-Preserving and Trustworthy Machine Learning. He earned his PhD in Computer Science at Queen Mary University of London while concurrently holding a Research Assistant position at Imperial College London, working with Prof. Hamed Haddadi, Dr. Richard G. Clegg, and Prof. Andrea Cavallaro. His PhD research focused on developing machine learning algorithms for privacy-preserving personal data analytics, particularly for data captured by mobile and wearable devices. Mohammad has published more than 20 papers in peer-reviewed conferences and journals and has filed several patents, all focusing on ubiquitous computing, data-centric machine learning, on-device machine learning, data privacy, and federated learning.

Talk Title

Elevating Health Awareness through Personalized Multimodal Sensing

Talk Summary

You likely view this text on a personal device—be it a laptop, smartphone, mixed-reality headset, smartwatch, or perhaps hearing it via AI-powered text-to-speech through your earbuds. With so many devices constantly with us, we can access information faster than ever. But these devices can offer more than just fast information access: they can provide us with a much deeper understanding of our physiological data, uniquely accessible through our personalised, multi-sensory devices. These devices can continuously sense our daily conditions, from deep sleep to intense exercise to hours of sitting at a desk. This creates a transformative opportunity to monitor, assess, and improve our health and well-being.

Join me as we explore how our personal devices can evolve into reliable tools for health awareness without compromising privacy or demanding excessive engagement and computational resources. I will discuss approaches like self-supervised learning from sensory data, leveraging data across various modalities, and developing algorithms to address data scarcity. Together, we will explore a vision for human-centered device intelligence that is adaptive, private, and efficient in advancing health monitoring and personal well-being.