Digital twin the daily life patterns using multi-modal data


Self-funded PhD


3.5 (full-time) 5 years (part-time)

Application deadline:

Applications accepted year-round

About this project

With advancement of wearables and wellness monitoring technologies, it’s feasible to continuously monitor elderly populations to effectively ensure their wellbeing without compromising privacy and maintaining the dignity while them being monitored. The vast amount of data are not only useful for abnormality detection or predicting early signs of health deterioration, they are also invaluable memories of people. Imagine someone being diagnosed with dementia, by learning the patterns of people’s daily life, their digital twin of their memory can be learnt and used to help them to respond, to react to environment, or to communicate in their usual manner to increase their life quality.

In this project, a demonstration system will be created to collect, store and recommend actions utilising a collection of wearables, smart devices, utility usages and surrounding living environment. It’s anticipated at least areas of multi-modal sensory data consensus and new progressive deep learning model are needed in this project to extract the ‘patterns of daily life’ and in return assist olderly in their daily routines. You’re also expected to work with the ethical implications related to this research.

How to apply

Apply online.

Please include the project title and proposed supervisor in your application.

Postgraduate student reading in the Brynmor Jones Library

Watch: find out more about postgraduate study at the University of Hull


Open to fully self-funded full time / part time students only.

Entry requirements

Applicants should have a minimum 2:1 degree in Computer Science or relevant subject. A taught MSc or Masters by Research in a relevant subject or relevant laboratory experience would be an advantage.