Learning Enabled Human Activity Recognition and Tracking for Healthcare

The project will develop novel techniques, based on Artificial Intelligence/Machine Learning (AI/ML) and new sensors such as millimetrewave radars, for the non-invasive diagnosis for healthcare applications. A millimetrewave sensor can wirelessly and non-invasively detect vital signs including pulse rate and respiration rate of the human body. Routinely and continuously monitoring such signs is crucial and essential for prolonging independence and maintaining general wellness for elder people and those who live alone. While AI/ML has been successful in tasks such as image processing, new methods will be needed to deal with millimetrewave sensory input which contains significant noises and outliers. This is compounded by the challenges from the detection of minor – or even invisible -- human activities (such as heartbeat and respiration) and the medical context where the connection between human activities and illnesses needs to be established and clearly articulated.

Objectives

The objectives of this PhD project are to (1) develop novel automated techniques for non-invasive and unobtrusive diagnosis, based on AI/ML and sensing techniques, (2) develop the student into a future leader of this interdisciplinary area (AI/ML, sensing, and healthcare), and (3) foster the collaboration, and enable the two-way exchange of knowledge, between clinical and academic partners, in order to support the NHS and increase societal and economic impact.

Supervisory Arrangement

The supervisory team provides ideal support to this project. Dr Huang will provide supervision on AI/ML. Dr Zhou will provide supervision on sensing and signal processing technology, including the millimetrewave techniques. Prof Turner will provide supervision healthcare domain knowledge and the contextual information for this project. Moreover, the project will be supported by medical professionals in two local hospitals. 

Working Environment

The student will be placed at the Digital Innovation Facility, where the primary supervisor Dr Huang is the director of the Trustworthy Autonomous Cyberphysical Systems Lab. The lab has all the technical facilities needed for this project, including 3 GPU servers for computational needs, 10+ millimetrewave radars with data acquisition panels for sensing and data capturing, and 10+ mobile robots that can be used for this project. The co-supervisor Dr Zhou has a dedicated lab in EEE with radio frequency devices. The generous technical support from both sides will be sufficient for a PhD project from day one. The clinical experimental environment will be provided by our clinical partner in two local hospitals. 

The student is expected to have an undergraduate degree in either Computer Science or Electronic Engineering. Given this position will be competitive, a 1st class degree might be needed. 

Enquiries to: Dr Xiaowei Huang ([Email Address Removed]) and Dr Jiafeng Zhou ([Email Address Removed] ) and Prof Mark Turner ([Email Address Removed] )

To apply: please send your CV and a covering letter to [Email Address Removed] please put Technologies for Healthy Ageing in the subject line

Expected interviews in November 2021