Machine Learning on Health Data from Wearables

Supervisory Team: Dr Zhiwu Huang, Dr Kate Farrahi

This PhD project focuses on developing advanced machine learning methods to transform wearable biosignal data, like heart rate, activity levels, and sleep patterns, into actionable health insights. With wearable technology collecting vast amounts of health data, this project aims to create algorithms that can predict health events, deliver personalized recommendations, and ultimately guide users toward healthier lifestyles.

The successful candidate will work on critical challenges, including data heterogeneity from various biosignal sources, real-time processing for immediate insights, and personalization to accommodate individual health variations. Methods will include multimodal machine learning for integrating diverse datasets, edge computing for efficient real-time analysis, and adaptive modeling to tailor insights to each user.

Joining this project provides an opportunity to work within a multidisciplinary team at the forefront of digital healthcare research, contributing to the creation of impactful, user-centered health monitoring solutions. Research directions may include federated learning to ensure user privacy, interpretability methods to enhance trust in machine learning models, and collaborations with health and technology experts for broader industry impact.

This project is ideal for candidates passionate about wearable health technology, machine learning, and personalized healthcare. Outcomes will contribute to better disease prediction, improved health management, and more responsive healthcare in a digital era.

Entry Requirements

You must have a UK 2:1 honours degree, or its international equivalent, with a strong foundation in mathematics.

You should have programming skills, and a passion for research. 

Experience with machine learning, computer vision, or healthcare technology will be beneficial.

How To Apply

Apply online: Search for a Postgraduate Programme of Study (soton.ac.uk).

You need to:  

• choose programme type (research), 2025/26, Faculty of Engineering and Physical Sciences

• please select if you will be full time or part time

• choose the relevant PhD in Computer Science

• add name of the supervisor in Section 2  

Applications should include:  

• research proposal

• CV (resumé) 

• 2 reference letters 

• degree transcripts to date