There is currently a great deal of interest in applying data analytic to real world problems characterized by imbalanced data, i.e., imbalanced learning, which are concerned across a wide range of research and application areas. For example, rare event detection, as these events occur with low frequency in daily life, but may cause far-reaching impact, including natural disaster, hazards and risks in finance and industry, and diseases. Although many methods have been proposed, there are still some key limitations. One limitation is that the learning performance is still relative low. Another limitation is the lack of an ability with most of machine learning system to explain its outputs, which has fuelled recent research in explainable AI.
This project will study knowledge-enhanced imbalanced learning, i.e., both knowledge and data are used in the process of learning, and how to structure relevant and reliable knowledge and incorporate them within the roadmap of imbalanced data analytic. The knowledge may be problem context, principles, guidelines, expert experience, or characterisation of objects. On the one hand, there is increasing recognition for utilizing knowledge whenever it is available or can be created purposefully to enhance the learning performance. On the other hand, it is expected that a knowledge-enhanced learning system will have innate capabilities for explanation and interpretability.
This project provides an opportunity to combine cutting edge research at the intersection of knowledge and machine learning to address the above key challenges.
The timeliness of this PhD project becomes also apparent in the potential of the above integration to contribute to the long-standing goal of explainable and interpretable AI in emerging real world applications. This project will investigate fundamental research questions about knowledge-enhanced imbalanced learning and will be guided by various application scenarios where rich domain knowledge exists, such as human activity recognition, telematic data analytics, risk/safety assessment, or medical decision making.
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 offers the following levels of support:
The following scholarship options are available to applicants worldwide:
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.
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.
Due consideration should be given to financing your studies. Further information on cost of living
H.X. Guo et al. (2017), Learning from class-imbalanced data: review of methods and applications, Expert Systems with Applications, DOI: 10.1016/j.eswa.2016.12.035.
Z. Chen, et al. (2021), A hybrid data-level ensemble to enable learning from highly imbalanced dataset, Information Sciences. DOI: 10.1016/j.ins.2020.12.023.
J. Liu, L. Martínez, A. Calzada, and H. Wang (2013), A novel belief rule base representation, generation and its inference methodology, Knowledge-Based Systems. DOI: 10.1016/j.knosys.2013.08.019.
L.H. Yang, J. Liu, Y.M. Wang, and L. Martínez (2018), A micro-extended belief rule-based system for big data multi-class classification problems, IEEE Transactions on Systems, Man, and Cybernetics: Systems. DOI: 10.1109/TSMC.2018.2872843.
L.H. Yang, J. Liu, F.F. Ye, Y.M. Wang, C. Nugent, H. Wang, and L. Martínez (2021), Highly explainable cumulative belief rule-based system with effective rule-base modelling and inference scheme, Knowledge-Based Systems, accepted and in press.
L.H. Yang, J. Liu, Y.M. Wang, C. Nugent, and L. Martínez (2021), Online updating extended belief rule-based system for sensor-based activity recognition expert systems with applications, Expert Systems with Applications. DOI: 10.1016/j.eswa.2021.115737.
Submission deadline
Monday 7 February 2022
12:00AM
Interview Date
March 2022
Preferred student start date
mid September 2022
Telephone
Contact by phone
Email
Contact by email