Outputs (19)

Measuring AI Fairness in a Continuum Maintaining Nuances: A Robustness Case Study (2024)
Journal Article
Paxton, K., Aslansefat, K., Thakker, D., & Papadopoulos, Y. (2024). Measuring AI Fairness in a Continuum Maintaining Nuances: A Robustness Case Study. IEEE Internet Computing, 28(5), 11-19. https://doi.org/10.1109/MIC.2024.3450815

As machine learning is increasingly making decisions about hiring or healthcare, we want AI to treat ethnic and socioeconomic groups fairly. Fairness is currently measured by comparing the average accuracy of reasoning across groups. We argue that im... Read More about Measuring AI Fairness in a Continuum Maintaining Nuances: A Robustness Case Study.

Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance (2023)
Presentation / Conference Contribution
Walker, C., Rothon, C., Aslansefat, K., Papadopoulos, Y., & Dethlefs, N. (2024, February). Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance. Presented at Safety Critical Systems Symposium SSS'24, Bristol, UK

It has been forecasted that a quarter of the world's energy usage will be supplied from Offshore Wind (OSW) by 2050 (Smith 2023). Given that up to one third of Levelised Cost of Energy (LCOE) arises from Operations and Maintenance (O&M), the motive f... Read More about Safety Monitoring for Large Language Models: A Case Study of Offshore Wind Maintenance.

Addressing Complexity and Intelligence in Systems Dependability Evaluation (2023)
Thesis
Aslansefat, K. Addressing Complexity and Intelligence in Systems Dependability Evaluation. (Thesis). University of Hull. https://hull-repository.worktribe.com/output/4500562

Engineering and computing systems are increasingly complex, intelligent, and open adaptive. When it comes to the dependability evaluation of such systems, there are certain challenges posed by the characteristics of “complexity” and “intelligence”. T... Read More about Addressing Complexity and Intelligence in Systems Dependability Evaluation.

Safety Analysis Concept and Methodology for EDDI development (Initial Version) (2023)
Report
Aslansefat, K., Gerasimou, S., Michalodimi-trakis, E., Papoutsakis, M., Reich, J., Sorokos, I., Walker, M., & Papadopoulos, Y. (2023). Safety Analysis Concept and Methodology for EDDI development (Initial Version). European Comission

Executive Summary:
This deliverable describes the proposed safety analysis concept and accompanying methodology to be defined in the SESAME project. Three overarching challenges to the development of safe and secure multi-robot systems are identifie... Read More about Safety Analysis Concept and Methodology for EDDI development (Initial Version).

Safety-Security Co-Engineering Framework (2023)
Report
Aslansefat, K., Gerasimou, S., Hamibi, H., Matragkas, N., Michalodimitrakis, E., Papadopoulos, Y., Papoutsakis, M., & Walker, M. (2023). Safety-Security Co-Engineering Framework. European Commission

Executive Summary:
The advantages of a model-based approach for safety have been clear for many years now. However, security analysis is typically less formal and more ad-hoc; it may involve systematic processes but these are not generally tied into... Read More about Safety-Security Co-Engineering Framework.

Keep Your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring (2022)
Presentation / Conference Contribution
Farhad, A. H., Sorokos, I., Schmidt, A., Akram, M. N., Aslansefat, K., & Schneider, D. (2022, September). Keep Your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring. Presented at Model-Based Safety and Assessment, 8th International Symposium, IMBSA 2022, Munich, Germany

Machine Learning (ML) has provided promising results in recent years across different applications and domains. However, in many cases, qualities such as reliability or even safety need to be ensured. To this end, one important aspect is to determine... Read More about Keep Your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring.

A Deep Learning Framework for Wind Turbine Repair Action Prediction Using Alarm Sequences and Long Short Term Memory Algorithms (2022)
Journal Article
Walker, C., Rothon, C., Aslansefat, K., Papadopoulos, Y., & Dethlefs, N. (2022). A Deep Learning Framework for Wind Turbine Repair Action Prediction Using Alarm Sequences and Long Short Term Memory Algorithms. Lecture notes in computer science, 13525 LNCS, 189-203. https://doi.org/10.1007/978-3-031-15842-1_14

With an increasing emphasis on driving down the costs of Operations and Maintenance (O &M) in the Offshore Wind (OSW) sector, comes the requirement to explore new methodology and applications of Deep Learning (DL) to the domain. Condition-based monit... Read More about A Deep Learning Framework for Wind Turbine Repair Action Prediction Using Alarm Sequences and Long Short Term Memory Algorithms.

Towards Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems (2021)
Journal Article
Aslansefat, K., Kabir, S., Abdullatif, A., Vasudevan Nair, V., & Papadopoulos, Y. (2021). Towards Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems. Computer, 54(8), 66-76

The application of artificial intelligence (AI) and data-driven decision-making systems in autonomous vehicles is growing rapidly. As autonomous vehicles operate in dynamic environments, the risk that they can face an unknown observation is relativel... Read More about Towards Improving Confidence in Autonomous Vehicle Software: A Study on Traffic Sign Recognition Systems.

Hourly performance forecast of a dew point cooler using explainable Artificial Intelligence and evolutionary optimisations by 2050 (2020)
Journal Article
Golizadeh Akhlaghi, Y., Aslansefat, K., Zhao, X., Sadati, S., Badiei, A., Xiao, X., Shittu, S., Fan, Y., & Ma, X. (2021). Hourly performance forecast of a dew point cooler using explainable Artificial Intelligence and evolutionary optimisations by 2050. Applied energy, 281, Article 116062. https://doi.org/10.1016/j.apenergy.2020.116062

The empirical success of the Artificial Intelligence (AI), has enhanced importance of the transparency in black box Machine Learning (ML) models. This study pioneers in developing an explainable and interpretable Deep Neural Network (DNN) model for a... Read More about Hourly performance forecast of a dew point cooler using explainable Artificial Intelligence and evolutionary optimisations by 2050.

SafeML: Safety Monitoring of Machine Learning Classifiers Through Statistical Difference Measures (2020)
Presentation / Conference Contribution
Aslansefat, K., Sorokos, I., Whiting, D., Tavakoli Kolagari, R., & Papadopoulos, Y. SafeML: Safety Monitoring of Machine Learning Classifiers Through Statistical Difference Measures. Presented at IMBSA: International Symposium on Model-Based Safety and Assessment, Lisbon

Ensuring safety and explainability of machine learning (ML) is a topic of increasing relevance as data-driven applications venture into safety-critical application domains, traditionally committed to high safety standards that are not satisfied with... Read More about SafeML: Safety Monitoring of Machine Learning Classifiers Through Statistical Difference Measures.