AI for Sustainable Agri-Food Systems and Food Integrity

Summary

Positioned within Ulster University’s School of Computing, this research theme focuses on harnessing artificial intelligence and spectral technologies to strengthen food integrity and sustainability in agri-food systems.

The work aligns with sectoral priorities in Digital Health, Food Security, and Responsible Innovation.

PhD researchers will investigate cutting-edge approaches that combine machine learning with spectral data to enable rapid, non-destructive detection of food adulteration and fraud.

Machine learning combined with spectral data can play a vital role in combating food fraud by enabling precise and rapid identification of adulteration. Spectral techniques generate unique chemical fingerprints of food items, which machine learning algorithms analyse to detect inconsistencies and verify authenticity.

This project is an exciting opportunity to work on the integration of machine learning and spectral techniques to allow for real-time, non-destructive testing, reducing reliance on traditional laboratory methods and increasing detection efficiency. Overall, leveraging machine learning techniques for non-linear, sparse and small data sizes analysis to enhance food safety, protect consumers, and help prevent economic losses.

The ubiquitousness of handheld spectrometers which is a consequence of their miniaturisation and cost effectiveness signalled a shift in the food fraud fight realm where the matter can swing from being tackled by professionals in labs to consumers at the forefront in the fight against food fraud. Such technology can identify the unique “fingerprint” in agri-food products and one can generate spectral data of a food sample at a quick rate beyond what can be managed by labs employing bulky spectrometers.

What the technology lacks in terms of prediction capabilities compared to expensive bulky lab spectrometers, it gets it back by exceling in data acquisition in sufficient amounts, hence rendering the matter of food fraud a classical ML problem. Nevertheless, few matters affecting the collected spectral data have been reported.

Data collected can be affected by background noise and environmental factors. And in a similar way to how multimodal data distributions are handled; clustering and sub-class predictions have been preferred for the creation of more interpretable and efficient models that may focus only on the most significant features and points. Unavoidably, by embedding clustering methods in classification, one has also to tackle sparsity and class unbalance issues.

Sparse ML focuses on building models where many parameters are zero; and unbalanced ML describes datasets where one class has significantly more points than others leading to poor performance on the minority class.

This project aims at presenting a ML solution that takes into consideration spectral data and tackles small data problems including sparsity, multimodality and unbalanced distributions to take a further step in the fight against food fraud.

Applying to Multiple Projects: Applications for more than one PhD studentship are welcome, however if you apply for more than one PhD project within Computing, your first application on the system will be deemed your first-choice preference and further applications will be ordered based on the sequential time of submission.

If you are successfully shortlisted, you will be interviewed only on your first-choice application and ranked accordingly. Those ranked highest will be offered a PhD studentship.

In the situation where you are ranked highly and your first-choice project is already allocated to someone who was ranked higher than you, you may be offered your 2nd or 3rd choice project depending on the availability of this project.

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.

Essential criteria

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.

• Clearly defined research proposal detailing background, research questions, aims and methodology

Desirable Criteria

If the University receives a large number of applicants for the project, the following desirable criteria may be applied to shortlist applicants for interview.

• First Class Honours (1st) Degree
• Masters at 70%
• Experience using research methods or other approaches relevant to the subject domain
• Work experience relevant to the proposed project
• Publications - peer-reviewed
• Experience of presentation of research findings

Equal Opportunities

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.

Funding and eligibility

This project is funded by:

• Department for the Economy (DfE)

This scholarship will cover tuition fees and provide a maintenance allowance of £21,000* (tbc) per annum for three years (subject to satisfactory academic performance).  A Research Training Support Grant (RTSG) of approximately £900 per annum is also available.

To be eligible for these scholarships, applicants must meet the following criteria:

• Be a UK National, or

• Have settled status, or

• Have pre-settled status, or

• Have indefinite leave to remain or enter, or

• be an Irish National

Applicants should also meet the residency criteria which requires that they have lived in the EEA, Switzerland, the UK or Gibraltar for at least the three years preceding the start date of the research degree programme.

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.

*Part time PhD scholarships may be available, based on 0.5 of the full time rate, and will require a six year registration period