Skip to main content

Research Repository

Advanced Search

Browse


The inadvertently revealing statistic: A systemic gap in statistical training? (2024)
Journal Article
Derrick, B., Green, E., Ritchie, F., Smith, J., & White, P. (2024). The inadvertently revealing statistic: A systemic gap in statistical training?. Significance, 21(1), 24-27. https://doi.org/10.1093/jrssig/qmae009

While concerns around data privacy are well-known, there's a lack of awareness and training when it comes to the confidentiality risk of published statistics, argue Ben Derrick, Elizabeth Green, Felix Ritchie, Jim Smith, Paul White

Analyst-driven XAI for time series forecasting: Analytics for telecoms maintenance (2024)
Conference Proceeding
Barrett, J., Legg, P., Smith, J., & Boyle, C. (in press). Analyst-driven XAI for time series forecasting: Analytics for telecoms maintenance.

Time series forecasting facilitates real-time anomaly detection in telecom networks, predicting events that disrupt security and service. Current research efforts have been found to focus on new forecasting libraries, more rigorous data cleaning meth... Read More about Analyst-driven XAI for time series forecasting: Analytics for telecoms maintenance.

On Cooperative Coevolution and Global Crossover (2024)
Journal Article
Bull, L., & Liu, H. (2024). On Cooperative Coevolution and Global Crossover. IEEE Transactions on Evolutionary Computation, 1-1. https://doi.org/10.1109/tevc.2024.3355776

Cooperative coevolutionary algorithms (CCEAs) divide a given problem in to a number of subproblems and use an evolutionary algorithm to solve each subproblem. This letter is concerned with the scenario under which a single fitness measure exists. By... Read More about On Cooperative Coevolution and Global Crossover.

Evolving multi-valued regulatory networks on tuneable fitness landscapes (2023)
Journal Article
Bull, L. (2023). Evolving multi-valued regulatory networks on tuneable fitness landscapes. Complex Systems -Champaign-, 32(3), 289-307. https://doi.org/10.25088/ComplexSystems.32.3.289

Random Boolean networks have been used widely to explore aspects of gene regulatory networks. As the name implies, traditionally the model has used a binary representation scheme. This paper uses a modified form of the model to systematically explore... Read More about Evolving multi-valued regulatory networks on tuneable fitness landscapes.

Feature-based search space characterisation for data-driven adaptive operator selection (2023)
Journal Article
Aydin, M. E., Durgut, R., Rakib, A., & Ihshaish, H. (2024). Feature-based search space characterisation for data-driven adaptive operator selection. Evolving Systems, 15(1), 99-114. https://doi.org/10.1007/s12530-023-09560-7

Combinatorial optimisation problems are known as unpredictable and challenging due to their nature and complexity. One way to reduce the unpredictability of such problems is to identify features and the characteristics that can be utilised to guide t... Read More about Feature-based search space characterisation for data-driven adaptive operator selection.

Machine learning models in trusted research environments - Understanding operational risks (2023)
Journal Article
Ritchie, F., Tilbrook, A., Cole, C., Jefferson, E., Krueger, S., Mansouri-Benssassi, E., …Smith, J. (2023). Machine learning models in trusted research environments - Understanding operational risks. International Journal of Population Data Science, 8(1), Article 2165. https://doi.org/10.23889/ijpds.v8i1.2165

IntroductionTrusted research environments (TREs) provide secure access to very sensitive data for research. All TREs operate manual checks on outputs to ensure there is no residual disclosure risk. Machine learning (ML) models require very large amou... Read More about Machine learning models in trusted research environments - Understanding operational risks.

Evaluating data distribution strategies in federated learning: A trade-off analysis between privacy and performance for IoT security (2023)
Conference Proceeding
White, J., & Legg, P. (in press). Evaluating data distribution strategies in federated learning: A trade-off analysis between privacy and performance for IoT security.

Federated learning is an effective approach for training a global machine learning model. It uses locally acquired data without having to share local data with the centralised server. This method provides a machine learning model beneficial for all p... Read More about Evaluating data distribution strategies in federated learning: A trade-off analysis between privacy and performance for IoT security.

Multi-agent learning of asset maintenance plans through localised subnetworks (2023)
Journal Article
Pérez Hernández, M., Puchkova, A., & Parlikad, A. K. (2024). Multi-agent learning of asset maintenance plans through localised subnetworks. Engineering Applications of Artificial Intelligence, 127(Part B), Article 107362. https://doi.org/10.1016/j.engappai.2023.107362

Maintenance planning of networked multi-asset systems is a complex problem due to the inherent individual and collective asset constraints and dynamics as well as the size of the system and interdependencies among assets. Although multi-asset systems... Read More about Multi-agent learning of asset maintenance plans through localised subnetworks.

What will make misinformation spread: An XAI perspective (2023)
Conference Proceeding
Bo, H., Wu, Y., You, Z., McConville, R., Hong, J., & Liu, W. (2023). What will make misinformation spread: An XAI perspective. In L. Longo (Ed.), Explainable Artificial Intelligence (321-337). https://doi.org/10.1007/978-3-031-44067-0_17

Explainable Artificial Intelligence (XAI) techniques can provide explanations of how AI systems or models make decisions, or what factors AI considers when making the decisions. Online social networks have a problem with misinformation which is known... Read More about What will make misinformation spread: An XAI perspective.

SACRO: Semi-Automated Checking Of Research Outputs (2023)
Presentation / Conference
Smith, J., Preen, R., Albashir, M., Ritchie, F., Green, E., Davy, S., …Bacon, S. (2023, September). SACRO: Semi-Automated Checking Of Research Outputs. Paper presented at UNECE Expert meeting on Statistical Data Confidentiality, Wiesbaden, Germany

Output checking can require significant resources, acting as a barrier to scaling up the research use of confidential data. We report on a project, SACRO, that is developing a general-purpose, semi-automatic output checking systems that works across... Read More about SACRO: Semi-Automated Checking Of Research Outputs.

Reproducing "Show, attend and tell: Neural image caption generation with visual attention" (2023)
Journal Article
Liu, H., & Brailsford, T. (2023). Reproducing "Show, attend and tell: Neural image caption generation with visual attention". Journal of Physics: Conference Series, 2589(1), Article 012012. https://doi.org/10.1088/1742-6596/2589/1/012012

This paper replicates the experiment presented in the work of Xu et al. [1], and examines errors in the generated captions. The analysis of the identified errors aims to provide deeper insight into the underlying causes. This study also encompass... Read More about Reproducing "Show, attend and tell: Neural image caption generation with visual attention".

Listening to all the stakeholders? The UN Sustainable Development Goals as requirements in Systems Engineering (2023)
Presentation / Conference
Brooks, I. (2023, September). Listening to all the stakeholders? The UN Sustainable Development Goals as requirements in Systems Engineering. Presented at SustainabilITy2030: 2 Internationale Konferenz Für Digitalisierung Und Nachhaltigkeit, Brugg, Switzerland

The 17 UN Sustainable Development Goals (SDGs) represent a global agreement on 'the world we want' by 2030. Many businesses have identified SDGs that they contribute towards. Can we also use them as requirements in Systems Engineering? This talk will... Read More about Listening to all the stakeholders? The UN Sustainable Development Goals as requirements in Systems Engineering.

Understanding people's perceptions of their liveable neighbourhoods: A case study of East Bristol (2023)
Conference Proceeding
Covato, E., & Jeawak, S. (2023). Understanding people's perceptions of their liveable neighbourhoods: A case study of East Bristol. . https://doi.org/10.4230/LIPIcs.GIScience.2023.24

Liveable neighbourhoods are urban planning initiatives that aim to improve the quality of residential areas. In this paper, we focus on the East Bristol Liveable Neighbourhood (EBLN) to understand people’s perceptions of their neighbourhood’s urban r... Read More about Understanding people's perceptions of their liveable neighbourhoods: A case study of East Bristol.

Maintenance automation using deep learning methods: A case study from the aerospace industry (2023)
Conference Proceeding
Mayhew, P. J., Ihshaish, H., Deza, I., & Del Amo, A. (2023). Maintenance automation using deep learning methods: A case study from the aerospace industry. In Artificial Neural Networks and Machine Learning – ICANN 2023 (295-307). https://doi.org/10.1007/978-3-031-44204-9_25

In this study, state-of-the-art AI models are employed to classify aerospace maintenance records into categories based on the fault descriptions of avionic components. The classification is performed using short natural language text descriptions pro... Read More about Maintenance automation using deep learning methods: A case study from the aerospace industry.

Enhancing software fault prediction with deep neural networks: An empirical analysis of error-type metrics (2023)
Conference Proceeding
Phung, K., Ogunshile, E., & Aydin, M. E. (in press). Enhancing software fault prediction with deep neural networks: An empirical analysis of error-type metrics.

In the context of software quality assurance, Software Fault Prediction (SFP) serves as a critical technique to optimise costs and efforts by classifying software modules as faulty or not, using pertinent project characteristics. Despite considerable... Read More about Enhancing software fault prediction with deep neural networks: An empirical analysis of error-type metrics.

PP71 Emergency operation centre staff views on identifying patients at imminent risk of out-of-hospital cardiac arrest during the emergency medical service call for help (2023)
Presentation / Conference
Kirby, K., Voss, S., & Benger, J. (2023, June). PP71 Emergency operation centre staff views on identifying patients at imminent risk of out-of-hospital cardiac arrest during the emergency medical service call for help. Paper presented at 999 EMS Research Forum 2023 meeting abstracts, Manchester

Background Internationally, Emergency Medical Service (EMS) triage emergency calls so that healthcare resources can be allocated appropriately. Studies have indicated that call triage in EMS may trigger a suboptimal response to some patients with lif... Read More about PP71 Emergency operation centre staff views on identifying patients at imminent risk of out-of-hospital cardiac arrest during the emergency medical service call for help.

Digital twins in industry 4.0 cyber security (2023)
Conference Proceeding
Lo, C., Win, T. Y., Rezaeifar, Z., Khan, Z., & Legg, P. (in press). Digital twins in industry 4.0 cyber security. In IEEE Smart World Congress 2023 - IEEE SWC / UIC / ATC / ScalCom / Digital Twin / PCDS / Metaverse-2023

The increased adoption of sophisticated Cyber Physical Systems (CPS) in critical infrastructure and various aspects of Industry 4.0 has exposed vulnerabilities stemming from legacy CPS and Industrial Internet of Things (IIoT) devices. The interconnec... Read More about Digital twins in industry 4.0 cyber security.

Evaluating the graphics processing unit for digital audio synthesis and the development of HyperModels (2023)
Thesis
Renney, H. Evaluating the graphics processing unit for digital audio synthesis and the development of HyperModels. (Thesis). University of the West of England. Retrieved from https://uwe-repository.worktribe.com/output/9271061

The extraordinary growth in computation in single processors for almost half a century is becoming increasingly difficult to maintain. Future computational growth is expected from parallel processors, as seen in the increasing number of tightly coup... Read More about Evaluating the graphics processing unit for digital audio synthesis and the development of HyperModels.

Disclosure control of machine learning models from trusted research environments (TRE): New challenges and opportunities (2023)
Journal Article
Mansouri-Benssassi, E., Rogers, S., Reel, S., Malone, M., Smith, J., Ritchie, F., & Jefferson, E. (2023). Disclosure control of machine learning models from trusted research environments (TRE): New challenges and opportunities. Heliyon, 9(4), Article e15143. https://doi.org/10.1016/j.heliyon.2023.e15143

Introduction: Artificial intelligence (AI) applications in healthcare and medicine have increased in recent years. To enable access to personal data, Trusted Research Environments (TREs) (otherwise known as Safe Havens) provide safe and secure enviro... Read More about Disclosure control of machine learning models from trusted research environments (TRE): New challenges and opportunities.