Autism spectrum disorder (ASD) is a lifelong neurodevelopmental disorder that can be recognised at an early age, typically before the age of three. It is a spectrum of pervasive developmental disorders and is found across all ethnic cultures and economic groups. ASD is a condition that can be characterised by a constant deficit in social communication, social interaction and the presence of restrictive and repetitive behaviour. Children with ASD often demonstrate restrictive and repetitive behaviour known as motor stereotypies, which can be defined as “involuntary, coordinated, patterned, repetitive, rhythmic, and purposeless but seemingly purposeful movements” .
These stereotypic behaviours are as a result of difficulty with motor function and coordination, and often identified by abnormal gait, clumsiness and irregular motor signs . Abnormal gait is defined as an unusual style of walking from the normal walking pattern and this could cause deterioration in occupational and other substantial ranges of daily activities.
Children with ASD tend to augment their walking stability with a reduced stride length, increased step width and therefore wider base of support, and increased time in the stance phase. A number of studies have addressed various types of gait disturbance in children with ASD [1-3]. In many Low and Middle-Income Countries (LMIC), there is a shortage of Mental Health Specialists (MHS) to conduct ASD screening. This results in long wait times (years) for children, with many children never getting an opportunity to see a specialist at all. This challenge could be overcome if there could be an automated mechanism for conducting this screening. Automated classification of ASD gait could provide assistance in diagnosis and ensure rapid quantitative clinical judgment.
The use of machine learning classifiers for automated recognition of gait pattern deviations has grown enormously in the last decade [4-6]. However, the published literature focusing on automated classification on ASD gait patterns is still scarce. Even though the interest in gait analysis is becoming popular among researchers, very few quantitative studies have been conducted on children with autism. Thus, this project will harness this opportunity by proposing a biologically inspired approach for the automated classification of gait patterns of children with ASD based on video sequences using spatial-temporal parameters.
The project will focus on producing a low-cost solution, using technology such as mobile phones to allow parents in LMIC to capture video sequences that can be used for automated screening. This project is multidisciplinary in nature and will leverage existing research links with Dr Sudarshi Seneviratne, Lecturer in Child and Adolescent Psychiatry, University of Colombo, Sri Lanka, to provide a solution for early detection of ASD using an appropriate set of gait features along with biologically inspired machine learning approaches.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
Vice Chancellors Research Scholarships (VCRS)
The scholarships will cover tuition fees and a maintenance award of £14,777 per annum for three years (subject to satisfactory academic performance). Applications are invited from UK, European Union and overseas students.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £ 14,777 per annum for three years. EU applicants will only be eligible for the fees component of the studentship (no maintenance award is provided). For Non EU nationals the candidate must be "settled" in the UK.
As Senior Engineering Manager of Analytics at Seagate Technology I utilise the learning from my PhD ever day
Adrian Johnston - PhD in InformaticsWatch Video
Monday 18 February 2019
19 - 20 March 2019
A key player in the economy of the north west
Monday 25 November 2019
Computer Science and Informatics