Outline:
Traditional approaches to emitter geolocation in complex cluttered environments might use numerical methods such as ray tracing or finite element modelling to estimate radio channels, and such methods can be too computationally expensive and impractical for real use. Alternatively, statistical propagation models can be used, which are computationally low burden but will tend to be insufficiently accurate.
Modern deep learning architectures such as physics-informed neural networks are at the forefront of scientific research and offer the potential to model the evolution of physical systems both accurately and with significantly lower computational burden than traditional numerical methods.
Focus/Aim:
The overall objective therefore is to explore the potential benefit of modern deep learning architectures to address the challenge of emitter geolocation in complex environments. This is to be achieved through the development and application of relevant deep learning architectures and then comparing the performance (both accuracy and computational burden) against traditional numerical methods (which are computationally expensive) and statistical models (which are computationally light but low accuracy). Key aims are to identify suitable deep learning architectures, quantify the potential benefit of deep learning approaches and determine the key limits and constraints of the concept.
Unique Opportunities:
Cranfield Defence and Security (CDS) provide unique educational opportunities to the Defence and security sectors of both public and private sector organisations.
Based at the UK Defence Academy at Shrivenham in Oxfordshire, CDS is the academic provider to the UK Ministry of Defence for postgraduate education at the Defence Academy, training in engineering, science, acquisition, management and leadership.
You will work on a cutting-edge research project in collaboration with Plextek which is expected to deliver high impact results.
You will have the opportunity to work closely with our industrial partners at Plextek and to travel for meetings with our industrial partner and to conferences to present your results.
Transferable Skills:
You will gain strong independent thinking and research skills, both theoretical and experimental. A number of writing courses are available which will assist in report, scientific paper, presentation and thesis writing. You will gain experience in presenting work at workshops and conferences, and also in programming and signal processing. All of these are transferable skills enhancing employability.
Continue with Facebook
