PhD Study : Advancements in Detection and Classification of Anomalies in Multidimensional Biomedical Signals Using Data-Driven Techniques

Summary

Problem Statement:

The use of modern techniques such as machine learning (ML) and artificial intelligence (AI) to analyse biomedical signals for monitoring and diagnosis has increased in recent years. These techniques help to enhance decision-making for more accurate diagnosis, hence improving healthcare services and treatments. As technologies advance, development of new sensors have been made available to improve diagnosis results. However, this also causes the dimensionality of the data to increase and it requires more computing power and time to process the data. For example, data from a 24-lead electrocardiogram (ECG) would provide more biomedical information about the patient compared to a 2-lead ECG dataset, but it would also consume more resources to analyse and extract critical information from those data. This so-called curse of dimensionality, remains as one of the open research questions for anomaly detection using machine learning, especially healthcare.

Proposed Innovative Solution:

Focussing on the anomaly detection and classification in ECG and electroencephalogram (EEG) signals, this project aims to overcome the curse of dimensionality. This project seeks to use advanced techniques to reduce the dimensionality of the data so that they can be visualised in lower dimensional forms, such as 2D or 3D plots, which could be more easily understood. In the process of doing so, the dimensionality reduction technique will also perform the first stage of segmentation and clustering of the data such that some of the anomalies can be detected and identified. The anomalies that will be the focus of this research include, but not necessarily limited to, epilepsic seizures in EEG signals, and arrhythmia episodes such as premature ventricular contractions (PVC) and atrial premature complexes (APC) in ECG signals.

Next, this project aims to perform early anomaly detection and accurate diagnosis using data from the biomedical signals. To do this, once the data have been reduced to lower dimensional representations, a second stage of feature extraction (anomaly detection) and regression (prediction) algorithms will be designed using hybrid machine learning approaches.

The hybrid machine learning approach consists of two or more generic machine learning algorithms augmenting one another. Through this hybrid approach, individual methods are able to complement one another by solving problems that others are not able to solve. As a result, this hybrid machine learning approach will be able to improve the prediction outputs, and hence enhancing the accuracy of diagnosis.

Finally, to verify this approach for real-time processing and analysis, the algorithms designed will be ported to the NVIDIA Jetson TX2 Development Kit platform, which is available at NIBEC.

The Jetson TX2 is a GPU-based mini supercomputer capable of fast processing of data using machine learning algorithms in real-time.

*Note: EEG and ECG data required for the project can be obtained from the PhysioNet online databases [URL: www.physionet.org].

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.

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