Smart Hallway - The use of AI in patient monitoring
PhDs and postgraduate research
Funded (UK/EU/International students)
School of Computing
23 February 2020
The PhD will be based in the Faculty of Technology, and will be supervised by Professor Honghai Liu, and Professor Peter Kyberd.
This PhD studentship is one of six PhD studentships funded by the University of Portsmouth in the area of biomaterials and bioengineering. These studentships will support the University’s strategic plan engaging with clinicians working in Portsmouth Hospital Trust to solve real-life medical problems. The successful applicants would be part of a cross-faculty research cluster in medical technologies.
This programme of research involves several Schools based in the Faculty of Science and Health and the Faculty of Technology. The vision of the cluster is to train a cohort of PhD students who contribute to the academic environment, some of whom would be expected to develop academic careers in this expanding area whilst others would be employed in the growing international medical technologies industry. Training would be enhanced by extended visits to other institutions involved in similar research and by visits to hospitals to meet with clinicians involved in the research project.
The scholarship covers tuition fees and an annual maintenance grant of £15,009 (UKRI 2019/20 rate) for three years. Scholarship recipients will also receive up to £3,000 for research project costs/consumables during the duration of the programme.
The work on this project could involve:
- Setting up a Smart Hallway
- Taking data from unimpaired persons
- Analyzing the video data
- Producing reports based on the findings
We're developing a new approach that uses AI to automatically identify a person’s body and limbs as they walk along an institutional hallway, calculating movement-related measures, and describing a person’s current mobility level. This information could be used to determine fall risk, identify changes in dementia level, or help determine if a person is ready to be discharged after surgery.
Since the Smart Hallway does not require sensors on the person, vision based walking analysis can be efficient and unobtrusive. Outcome reports to the clinician could be made immediately after the person moves through the Smart Hallway, enabling real-time reporting, or they could be available in reports on the person’s current status, as desired. Additionally, the movement outcomes can be used to generate new AI models that better link the person’s quality of movement to disease and mental health progression, effects of medication changes, or recovery after a healthcare interventions.
This project will use AI tools such as deep learning to extract key determinants of the walking cycle from video data of people walking along a corridor. The successful candidate will need to work out the best positioning for the cameras to get usable data. You will then use deep learning techniques to work out how a person is walking. The longer-term aim is to use data obtained from our partners in the UK and Canada to look at persons with impairments to detect differences between them and the unimpaired population.
The nature of the work is to gather substantial amounts of data and then analyse it, initially manually dividing the data into blocks (segmenting) based on context, so that the computer can be trained on it. Additionally, you'll write and test the software needed to perform the analysis.
You must be able to determine the best set up for the cameras to take useable data. The cameras must be above head height so that the eventual tool is unobtrusive. Once they have established this through taking data on unimpaired subjects and performing simple analysis on the data. You will then have to take larger datasets in order to process the data and see which of the important variables of the walking cycle can detect reliably.
Jointly based in our schools of Computing and Electronics, you'll work with colleagues in disciplines as diverse as Sport and Exercise Science and Biology to understand the problems and facilitate solutions.
You will need a good first degree from an internationally recognised university (minimum upper second class or equivalent, depending on your chosen course) or a Master’s degree in an appropriate subject. In exceptional cases, we may consider equivalent professional experience and/or Qualifications. English language proficiency at a minimum of IELTS band 6.5 with no component score below 6.0.
A first degree or Master’s in Mechanical engineering, Biomedical engineering, Data Analysis, Biomedical Engineering or Mechanical Engineering is desirable.
How to apply
We’d encourage you to contact Professor Peter Kyberd at email@example.com to discuss your interest before you apply, quoting the project code.
When you are ready to apply, you can use our online application form. Make sure you submit a personal statement, proof of your degrees and grades, details of two referees, proof of your English language proficiency and an up-to-date CV.
Our ‘How to Apply’ page offers further guidance on the PhD application process.
If you want to be considered for this funded PhD opportunity you must quote the project code COMP5040120 when applying.