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

  • To hold, or expect to achieve by 15 August, an Upper Second Class Honours (2:1) Degree or equivalent from a UK institution (or overseas award deemed to be equivalent via UK NARIC) in a related or cognate field.

Funding

    The University offers the following awards to support PhD study and applications are invited from UK, EU and overseas for the following levels of support:

    Vice Chancellors Research Studentship (VCRS)

    Full award (full-time PhD fees + DfE level of maintenance grant + RTSG for 3 years).

    This scholarship will cover full-time PhD tuition fees and provide the recipient with £15,000 maintenance grant 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.

    Vice-Chancellor’s Research Bursary (VCRB)

    Part award (full-time PhD fees + 50% DfE level of maintenance grant + RTSG for 3 years).

    This scholarship will cover full-time PhD tuition fees and provide the recipient with £7,500 maintenance grant 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.

    Vice-Chancellor’s Research Fees Bursary (VCRFB)

    Fees only award (PhD fees + RTSG for 3 years).

    This scholarship will cover full-time PhD tuition fees 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.

    Department for the Economy (DFE)

    The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £15,285 per annum for three years. EU applicants will only be eligible for the fee’s component of the studentship (no maintenance award is provided). For Non-EU nationals the candidate must be "settled" in the UK. 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.

    Due consideration should be given to financing your studies; for further information on cost of living etc. please refer to: www.ulster.ac.uk/doctoralcollege/postgraduate-research/fees-and-funding/financing-your-studies


Other information


The Doctoral College at Ulster University