This project is targeted towards the development of hardware accelerators for reduction in execution time of complex Artificial Intelligence (AI) algorithms in cardiology. AI has had a profound impact on our lives. Cardiac healthcare has highly benefited from the advances in AI and machine learning. AI in cardiology aids in identification of novel drug therapies, disease statistics, continuous remote monitoring and diagnostics, integration of multi-omic data, personalised medicine and in increasing physician efficiency. With the proliferation of wearable and mobile sensors, ubiquitous sensing has become a reality, leading a generation of large amounts of digital cardiac data.
AI has helped in detecting cardiovascular diseases like arrhythmias, left ventricular systolic dysfunction and congestive heart failure. Machine learning typically consists of two types of algorithms: Training and Inferencing. Machine learning training algorithms are very complex and are typically run on the cloud due to high computational demands. Neural networks have become one the most popularly used machine learning algorithms. In order to train these neural networks, lots of computation (several giga floating point operations) is required. These computations take a very long time typically ranging from days to weeks. Cloud service providers are adopting accelerators to satisfy computational demands and reduce the execution time of these complex algorithms (N. Normanet al. 2017).
Amazon Cloud provides multiple Field Programmable Gate Array (FPGAs) and multiple Graphics Processing Units (GPUs) to its users. Application Specific Integrated Circuit (ASICs) show 2x to 3x performance improvements in speed compared to other hardware accelerators like GPUs and FPGAs and up to 190x performance/watt when compared to CPUs. Microsoft executes many of their machine learning applications on FPGA Azure Cloud. Google’s Tensor Processing Units (TPUs) for accelerating machine learning applications is an ASIC. Inference is carried out on the edge (point of care) devices to identify any abnormalities/conditions where the main challenge is energy efficiency and training on the edge. Advancing the state-of-the-art in cardiac healthcare is highly dependent on reducing the execution time and interpreting results at real-time which is possible by development of novel reconfigurable accelerators.
The PhD Researcher will research development of reconfigurable hardware (FPGA) accelerators for reducing the computation time of cardiac AI algorithms. The Researcher will profile the software using profiling tools to identify parts (kernels) of the software which are taking up significant execution time. These Kernels will be implemented in hardware on FPGAs. The student will investigate modification of arithmetic precision of computations in order to get faster results with minimal loss of accuracy. However, precision reduction will be made tuneable so that users can choose between accuracy vs speed.
The Researcher will also have opportunities to collaborate and intern with researchers at Xilinx, Queens University Belfast and The University of Hong Kong.
This PhD project will be composed of challenging and timely research as well as bespoke training and mentoring that will equip the Researcher with technical and research skills needed to advance his/her career either in industry or academia.
If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.
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:
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.
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.
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.
The scholarship will cover tuition fees at the Home rate and a maintenance allowance of £ 15,009 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
Friday 7 February 2020
The largest of Ulster's campuses
When applying for this PhD opportunity please quote reference number: