Institution: Ulster University — Faculty of Computing, Engineering and the Built Environment
Supervisors: Dr Bryan Gardiner, Dr Vimal Dwivedi, Dr Barry Dillon, Dr Xuemei Ding
Closing date: Friday, January 08, 2027
Competition Funded PhD Project (UK Students Only)
Location: Belfast, United Kingdom
Subjects: Applied Mathematics, Artificial Intelligence, Computational Mathematics, Data Science, Health Informatics, Human Computer Interaction, Machine Learning, Quantum Computing
About the Project
OPEN TO HOME AND REPUBLIC OF IRELAND STUDENTS ONLY
Artificial intelligence (AI) is increasingly required to inform decisions in critical systems, where an error is costly, an unexplained output is unusable, and the answer is often needed within microseconds or under strict governance. This thematic PhD pursues one question across three different domains: how do we build machine learning that is interpretable, auditable and efficient in automated decision-making?
The candidate will pursue one of the three complementary strands, each sharing a methodological core of responsible AI:
Strand 1:
“An Intelligent Multimodal Data Fusion and Predictive Modelling Framework for Early Detection of Neurodegenerative Diseases”, led by Dr Xuemei Ding, develops an AI framework for early diagnosis and risk prediction by fusing clinical records, cognitive assessments, medical imaging, physiological signals and lifestyle data, with clinical expertise and data support provided by a collaborating neurologist. The emphasis is on models that are accurate and efficient, but also interpretable and ethical enough to support evidence-based clinical decision-making.
or Strand 2:
“A Trustworthy AI-Assisted Digital Twin for Climate-Resilient Planning in Belfast”, led by Dr Vimal Dwivedi, builds a versioned decision-support digital twin of selected Belfast neighbourhoods, integrating geospatial, environmental, infrastructure, social and planning data so that green-blue infrastructure options can be compared. A deliberately bounded agentic AI assistant will help users locate approved evidence and produce plain-English, source-linked explanations, without accessing the open web, altering authoritative data or making planning decisions. Belfast City Council officers retain control throughout.
or Strand 3:
“FastML for Scalable and Fault-Tolerant Quantum Computing”, led by Dr Barry Dillon, investigates how fast machine-learning techniques can enable scalable and fault-tolerant quantum computing, with applications in qubit readout, quantum error correction, noise modelling and anomaly detection, where accurate decisions must be made under strict latency and resource constraints. It will use hls4ml to translate models into efficient FPGA implementations for real-time deployment close to quantum-control hardware, and explore the co-design of algorithms and specialised hardware.
Across the strands the research addresses heterogeneous, high-dimensional and longitudinal data; latency- and resource-constrained inference; uncertainty quantification; and AI assurance with meaningful human oversight. Depending on the selected strand, candidates may gain expertise in areas such as ML/DL, hardware-aware model design, multimodal data fusion, interpretability and human-centred evaluation.
Applicants should have a strong quantitative background, for example in computer science, machine learning, data science, engineering, physics or mathematics, and an interest in making AI trustworthy within critical systems.
Funding Notes
OPEN TO HOME AND REPUBLIC OF IRELAND STUDENTS ONLY
References
- National Institute of Standards and Technology (2023) Artificial Intelligence Risk Management Framework (AI RMF 1.0), NIST AI 100-1. https://nvlpubs.nist.gov/nistpubs/ai/nist.ai.100-1.pdf
- Duarte, J., Han, S., Harris, P., et al. (2018) Fast inference of deep neural networks in FPGAs for particle physics. Journal of Instrumentation, 13, P07027. https://doi.org/10.1088/1748-0221/13/07/P07027
- Bausch, J., Senior, A.W., Heras, F.J.H., et al. (2024) Learning high-accuracy error decoding for quantum processors. Nature, 635, 834–840. https://doi.org/10.1038/s41586-024-08148-8
- Lienhard, B., Vepsäläinen, A., Govia, L.C.G., et al. (2022) Deep-neural-network discrimination of multiplexed superconducting-qubit states. Physical Review Applied, 17, 014024. https://doi.org/10.1103/PhysRevApplied.17.014024
- Xue, C., Kowshik, S.S., Lteif, D., et al. (2024) AI-based differential diagnosis of dementia etiologies on multimodal data. Nature Medicine. https://doi.org/10.1038/s41591-024-03118-z
- Elazab, A., Wang, C., Abdelaziz, M., et al. (2024) Alzheimer’s disease diagnosis from single and multimodal data using machine and deep learning models: Achievements and future directions. Expert Systems with Applications. https://doi.org/10.1016/j.eswa.2024.124780
- Hlal, M., Munyaka, J.-C.B., Chenal, J., et al. (2025) Digital Twin Technology for Urban Flood Risk Management: A Systematic Review of Remote Sensing Applications and Early Warning Systems. Remote Sensing, 17(17), 3104. https://doi.org/10.3390/rs17173104
- Bibri, S.E., Huang, J., Jagatheesaperumal, S.K. and Krogstie, J. (2024) The synergistic interplay of artificial intelligence and digital twin in environmentally planning sustainable smart cities: A comprehensive systematic review. Environmental Science and Ecotechnology, 20, 100433. https://doi.org/10.1016/j.ese.2024.100433
- Wang, L., Ma, C., Feng, X., et al. (2024) A survey on large language model based autonomous agents. Frontiers of Computer Science, 18, 186345. https://doi.org/10.1007/s11704-024-40231-1