PhD Study : Automatic detection of sleep arousals using deep learning and a visual representation of time-frequecny analysis of EEG signals

Summary

Any physiological condition that causes disturbance in the amount, quality and timing of sleep is categorised as a sleep disorder. Sleep disorders have wide range of negative impacts on mental and physical health which require treatment with or without pharmacological interventions. Arousals are one state of sleep disorders that are defined by any intrusion of wakefulness into sleep. Sleep arousals can be classified into apnea and non-apnea arousals. Sleep apnea is caused by abnormal breathing events during the night which in some cases may cause complete or almost complete block of airflows and consequently cardiovascular disorders, including coronary artery disease, stroke and atrial defibrillation as well as insulin resistance, neural injury, accelerated mortality, reduced cognitive function and poor work efficiency.  Any sleep disorder which cannot be included in sleep apnea is classified as a non-apnea sleep disorder. Non-apnea sleep disorders may increase the risks of type 2 diabetes mellitus (DM), chronic kidney disease (CKD), cardiovascular disease, stroke, menstrual irregularities, reproductive dysfunction, adverse pregnancy outcome, infertility and erectile dysfunction.

The diagnosis and classification of sleep arousals are traditionally done in sleep laboratory settings, where sleep experts study polysomnography (PSG) in order to detect sleep disorders. In this procedure a subject is monitored during an overnight stay in a sleep lab where their respiratory and neurophysiological signals are recorded. These records are then analysed by a specialist human observer. Since this monitoring takes place for a duration equivalent to one night of sleep, a relatively large amount of data is typically recorded. As a result, the process of arousal detection by the human observer is time consuming and there is an interest in finding more appropriate methods to detect and categorise sleep arousal states automatically.

Sleep arousals are often associated with a sudden shift in their electroencephalogram (EEG), therefore changes in the EEG signal is often a good indicator of the presence of sleep arousals.  Accordingly, many studies have used different signal processing techniques combined with machine learning to detect apnea arousals. However, few studies report investigations into the detection of non-apnea arousals. In this project, the PhD student will conduct research to develop a new model using a visual representation of time-frequency analysis and deep learning (e.g Convolutional Neural network) to detect both apnea and non-apnea arousals from bio-signals collected during a PSG study. During this project, the successful PhD candidate will have the opportunity to work on Ulster University’s HPC server to develop the model. Furthermore, the capability of the developed model to be used in a real-time analysis of EEG signals will be investigated. Developing a successful model with real-time applicability can potentially decrease the human observers’ errors as well as the analysis time.

Essential criteria

Applicants should hold, or expect to obtain, a First or Upper Second Class Honours Degree in a subject relevant to the proposed area of study.

We may also consider applications from those who hold equivalent qualifications, for example, a Lower Second Class Honours Degree plus a Master’s Degree with Distinction.

In exceptional circumstances, the University may consider a portfolio of evidence from applicants who have appropriate professional experience which is equivalent to the learning outcomes of an Honours degree in lieu of academic qualifications.

• Sound understanding of subject area as evidenced by a comprehensive research proposal

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

• First Class Honours (1st) Degree
• Masters at 65%
• Work experience relevant to the proposed project
• Publications - peer-reviewed

Funding and eligibility

The University offers the following levels of support:

Vice Chancellors Research Studentship (VCRS)

The following scholarship options are available to applicants worldwide:

• Full Award: (full-time tuition fees + £19,000 (tbc))
• Part Award: (full-time tuition fees + £9,500)
• Fees Only Award: (full-time tuition fees)

These scholarships will cover full-time PhD tuition fees for three years (subject to satisfactory academic performance) and will provide a £900 per annum research training support grant (RTSG) to help support the PhD researcher.

Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Please note: you will automatically be entered into the competition for the Full Award, unless you state otherwise in your application.

Department for the Economy (DFE)

The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £19,000 (tbc) per annum for three years (subject to satisfactory academic performance).

This scholarship also comes with £900 per annum for three years as a research training support grant (RTSG) allocation to help support the PhD researcher.

• Candidates with pre-settled or settled status under the EU Settlement Scheme, who also satisfy a three year residency requirement in the UK prior to the start of the course for which a Studentship is held MAY receive a Studentship covering fees and maintenance.
• Republic of Ireland (ROI) nationals who satisfy three years’ residency in the UK prior to the start of the course MAY receive a Studentship covering fees and maintenance (ROI nationals don’t need to have pre-settled or settled status under the EU Settlement Scheme to qualify).
• Other non-ROI EU applicants are ‘International’ are not eligible for this source of funding.
• Applicants who already hold a doctoral degree or who have been registered on a programme of research leading to the award of a doctoral degree on a full-time basis for more than one year (or part-time equivalent) are NOT eligible to apply for an award.

Due consideration should be given to financing your studies. Further information on cost of living