Sort by
Refine Your Search
-
the integrity of scientific information extracted from the scans. The successful candidate will join the AC/DC research team to develop an open-source compression solution tailored for the XCT community. While
-
early detection and predict adverse pregnancy outcomes. You will develop and validate a data-driven clinical decision support tool in collaboration with clinicians and industry partners. Pre-eclampsia is
-
(such as demand spikes) can threaten the power grid stability. The PhD project will identify and develop solutions to mitigate power grid instability caused by AI data center loads, ensuring resilient grid
-
reliable transmission of demanding multi-modal data such as haptic feedback, video, and 3D sensing data. This project will develop AI-driven predictive network intelligence to anticipate delay and network
-
details Supervisors: Dr Oksana Trushkevych and Prof Tony McNally Research area and project description: Develop scalable acoustic methods to structure advanced polymer composites for lightweight, low‑carbon
-
warning and adaptive control to ensure safe and reliable human–robot interaction. The PhD project will develop AI-empowered predictive models that anticipate network delay and instability using historical
-
sensors - if we can control and tune their properties. You will develop and use top-of-the-line machine learning models to predict the sensor response of these materials under realistic conditions
-
), where heat is stored/released through reversible chemical reactions. This project focuses on NaOH water TCES systems, which use cheap, abundant materials [1]. We will develop modelling tools that combine
-
that is still poorly understood. This project will develop advanced computational models to simulate a new imaging technique called electron ptychography, which can map magnetic fields in 3D at nanometre
-
Energy’s Natural Hazards R&D Team, this project will utilise and develop state-of-the-art space simulations to probe past, present and future events to constrain extreme value distributions spanning hundreds