Research degree opportunities in Computing Science

A PhD in computing can be the first step into an academic career and a passport to some of the most interesting technology jobs in the world. We are welcoming students for study towards a PhD or MPhil degree in data science, artificial intelligence and other areas of computer science.

We have a limited number of funded places each year, and these are advertised on FindAPhD.

We also welcome students from the UK and abroad who have their own funding or who wish to develop a proposal to apply for a scholarship. We will help you develop your research question and your proposal with a view to you studying at Stirling. You may have your own ideas for a research question and we would be happy to help you shape them into a high quality PhD proposal. Alternatively, you may find one of our existing research projects the perfect fit for your own interests. We also offer a professional doctorate programme, in which you can work on a project for your employer (who covers the costs) and earn a PhD at the same time.

The list below describes some PhD opportunities that are available right now. If you have a scholarship opportunity or private funding, please contact the supervisor listed for the project that interests you.

Title: Fair artificial intelligence for reducing peak electricity consumption

Supervisor: Dr Simon Powers

The UK and the EU have both recently updated their legislation to put net zero emissions targets in place for 2050. This requires moving away from using fossil fuels for energy generation, and moving towards renewable sources such as photovoltaic cells and wind turbines. To exploit these renewable energy sources effectively, we need to reduce the peak demand for electricity. Traditional approaches to this have been based on time of use pricing – a utility company sets peak and off-peak hours, and charges households more to use their appliances in peak hours, with the aim of discouraging them from doing this. However, this approach has not been successful in the UK in widely shifting energy usage patterns (e.g. we are still facing the prospect of blackouts this winter because peak consumption is too high). And moreover, time of use pricing inherently discriminates against households on lower incomes.

This project will develop alternative approaches, drawing on theory from social science to develop agent-based protocols for reducing peak electricity consumption in a way that people perceive as treating them fairly. These are based on the idea that each household can have an agent running on their smart meter, into which they can input their preferences for when they would like to run their appliances. Their agent then negotiates with the agents of other households to come up with an allocation of times that satisfies each household’s preferences as far as possible, while reducing peak consumption. The project will develop and test several such protocols in simulation, and perform online user studies to test how fair people find them.

Title: Do trustworthy AI techniques actually have an effect on people's trust?

Supervisor: Dr Simon Powers

Why do people trust or distrust artificial intelligence (AI)? To predict the effects that different techniques for trustworthy AI, such as explainable AI, might have on people's trust, we need to be able to objectively measure this. But current work is very limited because it relies either on subjective survey results, or measures of trust that only apply to one application of AI. This limits our ability to generalise and build predictive models. To address this, we will use game theory to model the trust decision a person takes when they interact with various AI systems, including recommender systems and machine learning models. 

By using game theory, we will be able to account for the fact that the interests of AI system designers and the people using the AI systems are often not fully aligned (indeed, if they were there would be little need for regulations such as the EU AI Act).  For example, an AI recommender tool designed by a retailer might recommend more expensive products than the user wants or needs, or might use an end user’s data in ways that are not in the user’s best interest. Likewise, conversational AI tools such as ChatGPT benefit from gaining as many users as possible, and may do this by trying to please the user by providing answers on a vast range of topics, even when these answers are incorrect. This strategic nature of human-AI interactions is likely to have a large effect on whether people trust different applications of AI, and what signals of trustworthiness affect their decision, but has been ignored in previous behavioural experiments that measure trust in applications of AI. And crucially, by accounting for the potential for misalignment of interests, we can determine which signals of trustworthiness may mislead people to trust systems that are untrustworthy. 

Title: Multimodal Generative AI in Medical Imaging

Supervisor: Dr Hazrat Ali

Large Language Models (LLMs) are revolutionizing the field of Medical Artificial Intelligence, primarily through their advanced capabilities in processing textual and tabular data within healthcare. Despite these advancements, the application of LLMs in the Medical Imaging domain remains underexplored. There exists significant potential to harness the multimodal data processing capabilities of LLMs to develop innovative AI tools for medical imaging while integrating diverse forms of data, which could lead to enhanced diagnostic accuracy and improved patient outcomes. This research seeks to develop novel AI-driven solutions that can more accurately analyze and interpret complex medical images. The outcomes of this research have the potential to significantly advance the field, offering new tools that can support clinicians in making more informed decisions, ultimately leading to better patient care and outcomes.

Title: Generative AI for synthetic aperture radar (SAR) data processing

Supervisor: Dr Vahid Akbari

The project aims to develop generative AI methods, such as Generative Adversarial Networks (GANs) and Variational Auto-Encoders (VAE), for synthetic aperture radar (SAR) data processing including image synthesis and resolution enhancement, and noise reduction. These relatively new techniques have shown impressive results in the optical image field, enabling, for instance, the generation of very convincing fake images. Thus, the student has to investigate how these methods can be used or adapted for similar data generation in radar imaging. The student will follow the progressive development path of GANs and VAEs and explore some applications for SAR image domains transformations, while monitoring their expected performances for monitoring purposes.

Title: Language models for synthetic aperture radar data

Supervisor: Dr Vahid Akbari

This research will explore the application of large language models (LLMs) to understand scattering mechanisms in synthetic aperture radar (SAR) data. By leveraging the advanced capabilities of LLMs, the research aims to improve the interpretation of SAR images and the identification of diverse scattering phenomena. This innovative approach has the potential to significantly advance SAR data analysis, leading to more accurate environmental monitoring and remote sensing applications.

Title: Synthetic Data for Trustworthy AI

Supervisor: Dr Paulius Stankaitis

Synthetic data has great potential in addressing data scarcity issues in the AI domain. One challenge of generating good synthetic data using physics-simulators for training deep learning models is ensuring that the generated synthetic data sufficiently captures the complexity and variability of real-world scenarios to effectively train the neural networks. This project would investigate the use of realistic synthetic data and optimisation techniques for improving the trustworthiness of AI models.

Title: Deepfake and Fake news detection

Supervisor: Dr Leonardo Bezerra

Due to the growing presence of social media or social networking sites people are digitally connected more than ever. This also empowers citizens to express their views in multitude of topics ranging from Government policies, events in everyday life to just sharing their emotions. However, the growing influence experience by the propaganda of fake news is now cause for concern for all walks of life. Election results are argued on some occasions to have been manipulated through the circulation of unfounded and sometime doctored stories on social media. In addition to fake text, there has been huge growth of AI based image/media manipulation algorithms commonly known as ‘deepfake’. Near realistic fake videos are being generated that contributes significantly to spreading misinformation. This project will research on developing new algorithms that combines deep learning based Natural Language Processing (NLP) and Computer Vision (CV) techniques to detect fake news and prevent misinformation spreading.

Title: Predicting the Performance of Backtracking While Backtracking

Supervisor: Dr Patrick Maier

Backtracking is a generic algorithm for computing optimal solutions of many combinatorial optimisation problems such as travelling salesman or vehicle routing. Unfortunately, the time a backtracking solver requires to find an optimal solution, to prove optimality, or to prove infeasibility is very hard to predict, which limits the practicality of such solvers for real-world problems.

Research in algorithms has mainly focused on specific problem classes and on identifying characteristic features of hard problem instances. Instead, this project aims to mine a generic backtracking solver for performance data at runtime (that is, while solving a particular problem instance) and to build statistical models that can be used to estimate the future performance of the solver on the current problem. Interesting estimates include: How likely is it that the current solution is optimal? Assuming the current solution is optimal, how long will it take to prove optimality? Can the search be parallelised, and if so, how many CPUs would be required to get the answer in one hour?

Topic: The application of cognitive computational methods to enhance vocational rehabilitation

Supervisor: Dr Sæmundur Haraldsson

Vocational Rehabilitation (VR) is a field within healthcare which aims to assist long term sick-listed and unemployed individuals to enter the workforce or education [2]. VR has yet to fully embrace the use of cognitive computer systems, including Artificial Intelligence (AI) approaches. As such it offers indefinite avenues of research for inquisitive minds, e.g., predicting future regional demand for VR, optimising VR pathways for maximum probability of success, and many more. Potential PhD candidates would collaborate with international partners of the ADAPT consortium to exploit state-of-the-art AI and Data Science methods to improve decision making and planning in VR. The projects would form the foundation for the field of VR informatics with international real-world impact on people's health and wellbeing as well as current societal issues.

Topic: Bio inspired Peer-to-Peer Overlay algorithms

Supervisor: Dr Mario Kolberg

Peer-to-Peer (P2P) overlay networks are self-organising, self-managing, and hugely scalable networks without the need for a centralised server component. Utilizing inspiration from biological processes to construct and maintain P2P overlays has attracted some research interest to date. The majority of related solutions focus on providing efficient resource discovery mechanisms using swarm intelligence techniques. In fact such techniques have proven performance benefits in regard to routing and scheduling in dynamic networks, while they have also inherent support for adaptability and robustness in light of node failures. Conversely, except for very few examples, using such techniques for topology management has not really been exploited. This project will investigate the use of bio-inspired solutions for topology management addressing some of the techniques’ challenges such as relatively high computational and messaging complexity.

Topic: Machine Learning approaches to tackle Cyber Attacks

Supervisor: Dr Mario Kolberg

The range of internet services has increased dramatically in recent years, however, at the same time cyber-attacks have grown both in number and sophistication endangering user trust and uptake of such services. Thus there is a need for researchers to  develop solutions to these evolving cyber-attacks. However, these attacks are evolving as attackers keep changing their approaches.

Security measures such as firewalls are put in place as the first line of network defense to safeguard these networks but attackers are still able to exploit vulnerabilities in these networks. Intrusion Detection Systems (IDS) have shown potential to be a successful counter measure against potential attacks. However, there are still many open issues, such as their efficiency and effectiveness in the presence of large amount of network traffic. Several IDS have been proposed that can differentiate between attacks and benign network traffic and raise an alarm when a potential threat is detected. However, these systems must be able to analyse large quantity of data in real time to be applicable in modern networks. Unfortunately the larger the data quantity, the more irrelevant information stored. One solution may be to extract key features and apply Machine Learning (ML) techniques to detect attacks. This project will investigate using ML approaches to detect intrusion attacks at runtime.

Topic: Understanding and Visualising the Landscape of Multi-objective Optimisation Problems

Supervisor: Prof. Gabriela Ochoa

In commerce, industry and science, optimisation is a crosscutting, ubiquitous activity. Optimisation problems arise in real-world situations where resources are constrained and multiple criteria are required or desired such as in logistics, manufacturing, transportation, energy, healthcare, food production, biotechnology and others. Most real-world optimisation problems are inherently multi-objective. For example, when evaluating potential solutions, cost or price is one of the main criteria, and some measure of quality is another criterion, often in conflict with the cost.  The analysis of multi-objective optimisation surfaces is thus of paramount importance, yet it is not well developed.  This project will look at developing and applying network-based models of fitness landscapes and search trajectories to multi-objective optimisation problems. The ultimate goal is to provide a better understanding of algorithms and problems and demonstrate that better knowledge leads to better optimisation across a number of domains

Topic: Artificial Intelligence Sight Loss Assistant

Supervisor: Dr Kevin Swingler

The Artificial Intelligence Sight Loss Assistant (AISLA) project aims to use state of the art computer vision and artificial intelligence to develop personal assistant technology for people with sight loss. Topics within the project include computer vision, natural language processing and human-AI interfaces. A PhD in AI and computer vision can lead to an academic career or jobs in industries such as automotive, building self driving cars, digital assistant design or security. Companies like Google, Amazon and Facebook are at the forefront of commercial AI.

Topic: Interpretable Machine Learning for Time Series Analysis

Supervisor: Dr Yuanlin Gu

In challenging scenarios marked by strong uncertainty or limited data size, the performance and reliability of predictive model can be negatively affected. This project aims to develop interpretable machine learning models along with method for generating and selecting explainable features. This will uncover the relationship between system outputs and the complex changing impacts of inputs, facilitating easier model fine-tuning based on the insights and knowledge gained. The developed methods will be applied in multidisciplinary areas such as engineering, finance, environment, etc

Topic: Efficient search techniques for large-scale global optimisation problems in the real world

Supervisor: Dr Sandy Brownlee

Optimisation problems become very difficult at the large scales: like allocating thousands of skilled engineers to jobs, or prioritising where to spend public money in improving energy efficiency of thousands of homes. This project will look at how to learn the structure of these problems, allowing us to intelligently divide them up so they can be solved efficiently, and how to present the outcomes intuitively to decision makers so they can make informed choices.

Topic: Search-based software improvement

Supervisor: Dr Sandy Brownlee

Software is everywhere, and more efficient software has enormous benefits (i.e., more responsive mobile apps; reducing environmental impact of datacentres). In many cases there is even a trade-off between functionality and efficiency, yet improving existing code is difficult because it is easy to break functionality and there is a lot of noise when we measure performance, whether run time, memory consumption, or energy use. This project will explore how search-based approaches like genetic algorithms can be integrated with the latest large language models and best practice from software engineering to improve the efficiency of code, accounting for these difficulties.

Topic: Building Smaller but More Efficient Language Models

Supervisor: Dr Burcu Can Buglalilar

Large Language Models (LLMs) are data hungry and require massive computational and energy resources. This has two implications. First, they are less effective when applied to low-resource languages that lack data resources for building Natural Language Processing (NLP) models, leaving out a large part of the world's population. Second, training such LLMs is currently extremely energy intensive, which has a negative impact on the environment. In this research, we aim to build smaller but more efficient small language models using theories from other fields, including but not limited to linguistics, psycholinguistics and cognitive science.