MobiUK 2024 Conference Programme

Event Location:  Building 100, Room - 4011 and 4013. Registration in Level 4 foyer.

Dates: 8th-9th July 2024

Venue: Highfield Campus, University of Southampton

Note that this is a tentative program subject to minor changes close to the event.


Each paper talk is of 15 minutes including Q&A.


Day 1: 8th July 2024, Room location – 4011/4013





Welcome from Jagmohan Chauhan and Kate Farrahi


Using wearables in large-scale biobanks to transform our understanding of health


Opening and Invited Speaker: Aiden Doherty (University of Oxford)

Session Chair: Jagmohan Chauhan


I will discuss the story behind the collection of wrist-worn accelerometer data in over 150,000 research participants across the UK and China, while also describing efforts to collect complementary open human activity recognition validation datasets to further enhance these resources. I will share the development of machine learning methods for sleep, sedentary behaviour, physical activity behaviours and steps, referring to open software tools and data resources of relevance to others in the field.


Session 1: Biosensing and Health Monitoring

Session Chair: Shelly Vishwakarma


Respiratory Rate Monitoring from Earables Yang Liu, Kayla-Jade Butkow, Jake Stuchbury-Wass, Dong Ma, and Cecilia



Smartphone Pupilometry for Identifying Aphantasia and Hyperphantasia Reuben Hellier and Sarah Clinch


Enhancing Pulmonary Rehabilitation Exercises Analysis with Acoustics and Pose Estimation Mohammed Mosuily, Jagmohan Chauhan


Video-Based Pulse Estimation through Spatiotemporal Meta-Learning Eirini Kateri, Katayoun Farrahi


Lunch Break in B100


Federating everything with Flower


Invited speaker: Javier Fernandez-Marques (Flower Labs)

Session Chair: Sarah Clinch


Federated Learning has quickly become the preferred form of training AI models when the data cannot be moved to a centralised location due to privacy reasons, legal reasons, logistical reasons, or combinations of these. This talk will be divided into two parts: first, an overview of how a typical Federated Learning pipeline works, followed up by several real-world scenarios where FL has proven to be indispensable. We’ll close this first part of the talk by covering the current open research questions in FL with a special focus on those that arise in cross-device setups. The second part of the talk will be in the form of a tutorial where you will learn how to get started with FL using Flower. You will learn how to federate your existing ML projects and how to make the most out of Flower.


Session 2: Privacy and Security in Mobile Systems

Session Chair:  Mirco Musolesi


Surveying Developers on Effects and Awareness of Modded Apps Luis A. Saavedra, Alastair R. Beresford, Hridoy S. Dutta, Alice Hutchings


Building Trust in Peer-to-peer Trusted Execution Environment (TEE) Networks Ceren Kocaogullar


Safeguarding Privacy and Security in Mobile Systems with

Personalised Decentralised Machine Learning Qilei Li, Ahmed M. Abdelmoniem


Towards Building Better Context-Aware Smart Homes for Security and Privacy Weijia He, Jingjie Li



Tea/Coffee Break in B100 Level 4


Session 3: Applications and Implications of Mobile, Wearable, Sensing, and Ubiquitous Systems

Session Chair: Katayoun Farrahi


Exploring the Potential of Radar Technology for Tumour Detection Keniel Peart, Indu Bodala, Shelly Vishwakarma


IMChew: Chewing Analysis using Earphone Inertial Measurement Units Tamisa Ketmalasiri, Yu Yvonne Wu, Kayla-Jade Butkow, Cecilia Mascolo, Yang Liu


AudioDent: Toothbrushing Monitoring with In-ear Microphones

 Qiang Yang, Yang Liu, Jake-Stuchbury-Wass, Kayla-Jade Butkow

Emeli Panariti, Dong Ma, Cecilia Mascolo


Future Directions in Pervasive Display Systems for Care Homes Andrea Baumann, Nigel Davies

18:00 - 21:00

Dinner at Centenary Restaurant



Tuesday 9th July

Event Location:  Building 100, Room - 4011 and 4013  



E-Textiles – a New Platform for Wearable Technology


Invited speaker: Steve Beeby (University of Southampton)

Session Chair: Nigel Davis


This talk will introduce electronic textiles (e-textiles or smart fabrics) and describe the progression of the technology towards becoming a viable platform for wearables. The ultimate vision of the technology is to enable user to engage with their wearable technologies by simply getting dress with the electronic functionality being imperceptible to the wearer. However, combining electronics with textiles is not straightforward due to the particular mechanical characteristics that enable fabrics to drape and flex as well as being very strong and soft and able to survive very harsh conditions. The talk will discuss the fabrication of E-textiles through the Steve Beeby holds a prestigious Royal Academy of Engineering Chair in Emerging Technologies on e-textile engineering. He completed his PhD studies in MEMS Resonant Sensors at the University of Southampton, in 1996 and he is a Professor at the University of Southampton since 2011. His research interests include the application of flexible electronics, smart printable materials, and energy-harvesting technologies to electronic textiles (e-textiles). He leads the E-Textiles Network and has established the E-Textiles International Conference series. He is a Fellow of the IEEE, IET and IoP. use of printed smart materials or the integration of flexible electronics and discuss the challenges of suppling power, scaling up towards mass manufacture and surviving the rigours of use.


Tea/Coffee Break at Level 4 in B100


Edge-Powered Dynamic and Secure Swarm Networking 


Invited speaker: Noa Zilberman (University of Oxford)

Session Chair: Cecilia Mascolo


Smart environments managing dynamic swarms of mobile nodes often face strong requirements on latency, resilience, security and scalability.  In this talk, I will present our work on SmartEdge, enabling decentralized edge intelligence for smart IoT applications in near real-time, and utilizing hardware-accelerated in-network operations for context-aware swarm networking. The talk will focus on the provision of ultra-low latency, ML driven in-network defence against emerging threats in dynamic swarm environments. It will introduce Planter, an open source framework for in-network ML, and the provision of distributed, federated and hybrid deployment of attack detection and mitigation within resource constrained network devices. Using examples from  smart transportation and smart manufacturing, the talk will discuss some of the challenges and solutions to future development of smart mobile environments. 


Session 4: Resource-efficient Machine Learning for Embedded and Mobile Platforms

Session Chair: Nicholas Lane  


SparseFedPP: Sparse Federated Learning for Hardware-Constrained Edge-Devices Adriano Guastella, Lorenzo Sani, Alexandru-Andrei Iacob, Alessio Mora, Paolo Bellavista, and Nicholas D. Lane


Epileptic Seizure Detection with Tiny Machine Learning - A Preliminary Study  Loic Lemoine, Nhat Pham


Adaptive Continual Learning Tsetlin Machines Chong Tang, Neelam Singh, Jagmohan Chauhan


Federated Learning with Tsetlin Machine Shannon How Shi Qi, Jagmohan Chauhan, Geoff V Merrett, Jonathan Hare


A Call to Rethink AI Computing at the Consumer Edge: New Challenges and Systems Considerations


Invited speaker: Stylianos I. Venieris (Samsung AI Center, Cambridge, UK)

Session Chair: Alastair Beresford


In the last few years, the rapid progress of deep learning and deep neural networks (DNNs) has enabled the embedding of intelligence across consumer devices, be it voice assistants, smart cameras, or home robots. Nonetheless, recent trends strongly indicate that the next decade of consumer intelligence will require unprecedented levels of computational resources in order to cope with the demands of the new AI use-cases. In this talk, we argue for a paradigm shift towards the next generation of Consumer Edge-AI Computing. We'll start by discussing the new computational challenges of next-generation AI systems. Next, we'll introduce the notion of among-device intelligence, where multiple devices collaborate with each other through the fluid sharing of both context information and computational resources. Finally, we'll discuss how novel components, such as adaptive neural models, multi-DNN accelerators and fluid batching schemes, can be the key towards bringing performant and efficient intelligence to the consumer edge.


Lunch in B100/Level 4


Session 5: Advanced Networking and Identification Strategies for Mobile Systems

Session Chair: Jagmohan Chauhan


Advancing Device Uniqueness through Physical-Layer Identification: A High-Resolution Strategy Qingrui Pan, Zhenlin An, Xiaopeng Zhao, Lei Yang

Unveiling the Thrilling Realities of Mobile 5G in London and the Pivotal Role of Ecosystem and Energy Efficiency Peixuan Song, JunKyu Lee, Lev Mukhanov


Hardware-Accelerated Intelligent Roadside Unit Hongyi Chen, Noa Zilberman


Session 6: Innovations in Federated Learning and Health Monitoring for Mobile Systems

Session Chair: Katayoun Farrahi


Worldwide Edge-SILO Federated Learning of Language Models Alex Iacob, Lorenzo Sani, Bill Marino, Preslav Aleksandrov, William F. Shen, Nicholas Donald Lane

Sheaf HyperNetworks for Personalized Federated Learning Bao Nguyen, Lorenzo Sani, Xinchi Qiu, Pietro Li`o & Nicholas D. Lane


A Large-Scale Respiratory Audio Pre-trained Representation Model for Mobile Respiratory Health Yuwei Zhang, Tong Xia, Cecilia Mascolo



Close and Announcement of MobiUK 2025 (Cecilia Mascolo)