This project is funded by:
Deep learning has been playing increasingly important roles in intelligence systems for our daily lives, such as computer vision, autonomous car driving, earth observation, etc. Deep learning is typically data driven, there is little domain knowledge utilised in constructing and training neural network models, and determining decision boundaries. Learning process mainly focuses on searching and optimizing network models by gradient descent functions, without accounting for inherent discriminant and dependent characteristics of data distribution. Such a learning paradigm often makes it more difficult to achieve the convergence of training models, and therefore the resulting network models are not easy to generalize, typically in machine translation. These observations have motivated the recent development of deep Transformer Networks.
Transformer Networks make extensive use of attention mechanisms to discriminate the representative parts of data distribution based on contextual information and fade out the rest, thereby devoting more learning processes to deal with that small but representative part of the data for classification, recognition or prediction tasks. Currently ‘the two most common attention techniques used are dot-product attention, which uses the scalar product between vectors to highlight important parts of data, and multi-head attention, which uses combined attention to direct the overall attention of a network or sub-network’.
The proposed project will study existing attention techniques and develop new attention mechanisms that will be used as heuristics in a transformer network model. The project will incorporate one of two application scenarios into the development of attention: (1) detecting abnormal change from images, and (2) anomaly detection in electromagnetic satellite signals, which are part of the ongoing work undertaken in the supervisory team. For the former case, the development of an attention mechanism could be inspired by human visual attention, in which humans often focus on an object of interest in an image with high resolution while perceiving the surrounding of the object at low resolution over time. Whereas for the latter case, as electromagnetic satellite signals might contain a range of events, not all parts of signals are equally relevant for a specific event. This observation could motivate development of an attention based on the contextual characteristics of an event to determine the relevant portions of signals.
The transformer networks developed may be applicable to various real world application scenarios, such as monitoring abnormal signal change in Earth Observation, detecting faults in assemble lines of manufacturing processes, or human’s health deterioration in the context of healthcare.
The School of Computing at Ulster University holds Athena Swan Bronze Award since 2016 and is committed to promote and advance gender equality in Higher Education. We particularly welcome female applicants, as they are under-represented within the School.
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.
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 is an equal opportunities employer and welcomes applicants from all sections of the community, particularly from those with disabilities.
Appointment will be made on merit.
This project is funded by:
Our fully funded PhD scholarships will cover tuition fees and provide a maintenance allowance of £19,237 (tbc) per annum for three years (subject to satisfactory academic performance). A Research Training Support Grant (RTSG) of £900 per annum is also available.
These scholarships, funded via the Department for the Economy (DfE) and the Vice Chancellor’s Research Scholarships (VCRS), are open to applicants worldwide, regardless of residency or domicile.
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.
1. Xiangzeng Kong, Yaxin Bi, David H. Glass. Detecting anomalies in sequential data augmented with new features. Artif. Intell. Rev. 53(1): 625-652 (2020)
2. Stuart J. Blair, Yaxin Bi, Maurice D. Mulvenna. Aggregated topic models for increasing social media topic coherence. Appl. Intell. 50(1): 138-156 (2020)
3. Vyron Christodoulou, Yaxin Bi, George Wilkie. A Fuzzy Shape-Based Anomaly Detection and Its Application to Electromagnetic Data. IEEE J. Sel. Top. Appl. Earth Obs. Remote. Sens. 11(9): 3366-3379 (2018)
4. Yaxin Bi, Jiwen Guan, David A. Bell. The combination of multiple classifiers using an evidential reasoning approach. Artif. Intell. 172(15): 1731-1751 (2008)
5. Lodhi, Bilal, and Jaewoo Kang. "Multipath-DenseNet: A Supervised ensemble architecture of densely connected convolutional networks." Information Sciences 482 (2019): 63-72.
6. Jung, Hwejin, Bilal Lodhi, and Jaewoo Kang. "An automatic nuclei segmentation method based on deep convolutional neural networks for histopathology images." BMC Biomedical Engineering 1 (2019): 1-12.
7. Imran, Sajida, Bilal Ahmed Lodhi, and Ali Alzahrani. "Unsupervised method to localize masses in mammograms." IEEE Access 9 (2021): 99327-99338.
Submission deadline
Monday 24 February 2025
04:00PM
Interview Date
April 2025
Preferred student start date
15 September 2025
Telephone
Contact by phone
Email
Contact by email