Enhancing structural health monitoring with eXplainable Artificial Intelligence

After a fire incident, analysing post-fire images and videos plays a critical role in assessing structural damage, identifying potential collapse risks, and enhancing the efficiency of rescue operations. By scrutinising these visual data sources, structural engineers can closely examine the extent of damage to buildings, bridges, or other structures, allowing for a thorough assessment of their stability and integrity. This analysis provides invaluable insights into areas where the structural integrity may have been compromised, such as weakened support beams or damaged load-bearing walls, helping to identify immediate risks of collapse. Moreover, leveraging Artificial Intelligence (AI) and Computer Vision techniques, can automate and expedite this process, enabling rapid assessment of largescale damage scenarios. As a result, rescue teams can make informed decisions about where to focus their efforts, prioritising areas with the highest risks and potentially saving lives by intervening promptly. This PhD project aims to leverage the capabilities of the eXplainable Vision Transformer (ViT) architectures, an innovative model in the field of artificial intelligence and computer vision, to identify structural damage from fire data and predict the behaviour of buildings during fires, ultimately leading to the construction of safer and more fire-resistant structures. The data required for this project will be supplied by an external Canadian partner. The datasets will comprise images and videos demonstrating the testing of a new blue light technique that enhances the clarity of images/videos taken during fire situations. This project provides an interdisciplinary training opportunity for integrating structural engineering with computer science. The student would attend modules in both disciplines to establish a strong foundational understanding and collaborate on research projects merging computational AI techniques with structural analysis and design, gain hands-on experience through real-world projects, participate in workshops and seminars to stay abreast of advancements, and receive mentorship from experts in both fields. This holistic approach aims to equip the student with the skills, knowledge, and experience necessary to tackle complex challenges at the intersection of structural engineering and computer science, facilitating contributions to both academic research and practical applications.

Research Context: Computer Science and Structural Engineering. The research will be supervised by Dr Baidaa Al-Bander in the Centre for Computer Science Research at Keele University and Dr Rwayda Al Hamd in School of Applied Sciences at Abertay University.

Applications are welcomed from Computer Science/Engineering graduates with (or anticipating) at least a 2.1 honours degree or equivalent. Applicants should have good computing skills and an enthusiasm for coding, designing, and testing. They should be self-motivated and able to work independently and as part of a team.

This opportunity is open to UK/EU and overseas students. The collaborative and presentation aspects of the research require good English language and communication skills. Overseas applicants would, therefore, require an English IELTS (or equivalent) of 6.0 overall with no less than 5.5 in any subtest. (For applicants starting from August 2024 English IELTS (or equivalent) of 6.5 overall with no less than 6.0 in any subtest).

Informal enquiries about the project are very welcome by email to Dr Baidaa Al-Bander (b.al-bander@keele.ac.uk) and Dr Rwayda Al Hamd (r.al-hamd@abertay.ac.uk ). Please see this website for further information and to submit a formal application https://www.keele.ac.uk/study/postgraduateresearch/studentships/enchancingstructuralhealthmonitoringwithexplainableartificialintelligence/

Please ensure you quote FNS_BAlBander_Feb 24 on your application.