Postgraduate Research Opportunities

Supervised at-home gait assessment for children with Cerebral Palsy using deep learning and data fusion techniques

Details

Title: SCH42: Supervised at-home gait assessment for children with Cerebral Palsy using deep learning and data fusion techniques

Funding: A full Home/EU fee waiver or equivalent fee discount for overseas students  (£5,103 in 2020-21) (further fee details - international students will need to pay the balance of their fees) plus a doctoral stipend equivalent to the RCUK Minimum Doctoral Stipend (£15,285 in 2020-21).

Application deadline: Tuesday 31 March 2020

Start date: October 2020

Duration: 3 years (full time)

Location: Colchester Campus

Based in: School of Computer Science and Electronic Engineering (in collaboration with School of Sport, Rehabilitation and Exercise Sciences)

Overview

This interdisciplinary studentship brings together the expertise of AI and machine learning with rehabilitation science also leveraging practical support from the Paediatric Physiotherapy Unit, Anglian Community Enterprise Community Interest Company, which could in turn enable a significant scientific impact potential for this timely research endeavour.

Therefore, we are looking for a highly motivated and interdisciplinary-minded student, who has an excellent computer science, electronics/biomedical/mechatronics engineering or other related UG/MSc degree and is keen to work on relevant research in the area of machine learning algorithms for rehabilitation of children with disability. More details about this project can be found as follows.

The project

The project is to develop a portable, marker-less motion capture system consisting of accelerometers and a video camera, and a gait assessment method using deep learning and data fusion techniques to automatically quantify the degree of walking impairment in children with Cerebral Palsy (CP).

Phase 1

The validity and reliability assessment. Walking biomechanics in children with/without CP will be captured using the developed system and the sensors’ data will be processed using deep learning to derive Lower limb kinematics.

Phase 2

Multivariate statistics will be used for dimension reduction of the high-dimensional kinematics.

A metric of impairment between the components loading of individuals with/without CP (e.g. Euclidean distance) will be calculated and compared for both methods. This will justify if walking impairment quantified using the new method is comparable to 3DGA.

Phase 3

The new gait analysis method will be used in children with CP to quantify the magnitude of walking improvement before and after intervention (e.g. orthosis), and this will be correlated with routine clinical outcome measures (e.g. subjective reports of improvement, walking speed).

Significance

A low-cost, accurate and automatic gait analysis platform will better enable clinicians to objectively quantify impairments, monitor improvements, and individualising treatment decision making.

Additional information

As this project involves working with minors the successful candidate will be need to undergo a Disclosure and Barring (DBS) check. Additional paperwork may be requested from the successful candidate as part of this process, and the university reserves the right to withdraw the studentship offer if the candidate fails these checks.

Funding

The award consists of a full Home/EU fee waiver or equivalent fee discount for overseas students (further fee details), a doctoral stipend equivalent to the Research Councils UK National Minimum Doctoral Stipend (£15,285 in 2020-21), plus £2,500 training bursary via Proficio funding, which may be used to cover the cost of advanced skills training including conference attendance and travel.

Supervisors

Dr Bernard Liew

Co-supervisor

School of Sport, Rehabilitation and Exercise Sciences, University of Essex

Dr Bernard Liew is a Lecturer in Biomechanics, where he is part of the Health, Exercise and Active Lifestyle (HEAL) research group. As a physiotherapist, his expertise lies at the nexus of rehabilitation, biomechanics, and machine learning. He has experience in applying biomechanical and machine learning techniques towards understanding fundamental mechanisms of healthy and impaired motor control. He has published 19 peer-reviewed papers in the fields of rehabilitation, pain, applied biomechanics and statistics.

Professor Huosheng Hu

Co-supervisor

School of Computer Science and Electronic Engineering, University of Essex

Prof. Huosheng Hu is head of Robotics and Mechatronics Group at Essex University. His research has been focused on the development of advanced robots and intelligent machines for industrial automation and healthcare, including autonomous robots, assistive technology, human-robot interaction, data fusion algorithm and wearable sensors. He has secured over £3 million research grants, as PI and Co-I, from EPSRC, EU, Charity, Innovate UK and Industry, with over 500 peer-reviewed papers in journals and conferences.

Dr Xiaojun Zhai

Co-supervisor

School of Computer Science and Electronic Engineering, University of Essex

Dr Xiaojun Zhai is a Lecturer in the EIS in CSEE, he has been part of the EPSRC or EU funded projects for developing Embedded System and System-on-Chip (SoC) solutions for healthcare, machine learning and pattern recognition applications. He has published more than 60 peer-reviewed papers in the area of connected health applications, machine learning, Internet of Things, image processing and their accelerations using multi-core and FPGAs/GPUs based systems during his career to date.

Criteria

  • BSc/MSc degree in computer science, electronic engineering, biomedical engineering, mechatronics engineering or other related subjects. An MSc with Merit or Distinction is desirable.
  • Good programming skills in C, Matlab, Python, or related software.
  • Good writing skills and good command of the English Language. Demonstrable effectiveness in disseminating scientific results (e.g. publications/talks in conferences) will be considered favourably.
  • Comfortable working with children, including those with a disability (such as cerebral palsy).
  • Comfortable working in a multidisciplinary team environment.
  • Additional experience in experimental methods (e.g. motion capture technology) and/or in machine learning research and development.

How to apply

You can apply for this postgraduate research opportunity online.

Please include your CV, covering letter, personal statement, and transcripts of UG and Masters degrees in your application.

The University has moved to requiring only one reference for PhD applications and these can be received after a conditional offer has been made so the absence of these will not hold up the recruitment process.

Instruction to applicants

When you apply online you will be prompted to fill out several boxes in the form:

  • For "Course title" please put "Computer Science", tick "postgraduate research" and hit "search". This will bring up a list of matching courses, select the one marked "full time" and "PhD".
  • For "Proposed research topic or area of research" please put the title of this studentship (SCH42: Supervised at-home gait assessment for children with Cerebral Palsy using deep learning and data fusion techniques)
  • For "If you have contacted a potential supervisor..." please put the name of the lead supervisor (Dr Liang Hu)

If you have any informal queries about this opportunity please email the lead supervisor, Dr Liang Hu (l.hu@essex.ac.uk).

You can find the terms and conditions of this studentship here (PDF).

Student and academic working at a board together
Postgraduate research opportunities

Thinking about postgraduate research at Essex? We advertise studentships and funded opportunities throughout the year.

View our latest opportunities