Sort by
Refine Your Search
-
quantitative image analysis tools, integrating machine learning approaches to visualise and quantify structural features within Shelterin bound telomeric DNA. These biophysical approaches will be supported by
-
. To undertake this, we will first explore the use of machine learning to create models of the interactions between the spin and lattice in iron rhodium (FeRh) as a prototype anti-ferromagnet. Using
-
image the electrical properties of these materials alongside the surface topography on the nanoscale. Building on existing work in the Pyne Lab (TopoStats, https://github.com/AFM-SPM/TopoStats) we will
-
Develop a machine learning approach to multimodal imaging
-
existing materials in order to improve sustainability, reduce cost and reduce the risk of allergic reactions. The project will combine imaging and strain measurement techniques with mechanical and
-
, the conventional ML paradigm solves problems in isolation, and it requires building new models from scratch when adapting to multiple heterogeneous landscapes, which is resource-wasteful and time-costly
-
, environmental science, imaging and x-ray spectroscopic techniques. You will be part of a team working towards the safe disposal of the UK’s nuclear legacy. You will take your place in the next generation of
-
contacting either ambient air or the combustion gases of gas turbines with solvents used for CO2 capture. It uses a first of a kind prototype system to obtain experimental data, combine the data with process
-
Functional lung image synthesis using machine/deep learning: development, validation and application
-
Neurotransmitters, brain blood flow and functional brain imaging signals.r