Title: Advanced Electronic Surveillance DSP and ML Techniques
Project supervisor: Dr Matthew Ritchie
Department: Electronic and Electrical Engineering, University College London
Start Date: Sept, 2023
Closing Date: None (the position will remain open until a suitable candidate is found)
OPEN TO UK NATIONALS ONLY
How to apply: Applications must be made using the UCL online application system by using the UCL postgraduate study application form. Please mark it to the attention of Dr. Matthew Ritchie
Please submit your CV, transcripts (both undergraduate and postgraduate), your latest thesis (and/or one of your publications if applicable), and a short (up to one page) cover letter explaining why you think you are a suitable candidate for this post. The short-listed candidates might be further required to provide contact info (no direct recommendation letters) for peers that can recommend them.
The electromagnetic environment (EME) is becoming increasingly congested and contested. Designers of both radar and communications systems are developing methods that are both more complicated and increasingly harder to detect. Electronic Surveillance (ES) is therefore facing an increasingly complex environment to operate within. As radar and communications systems develop in their adaptability the requirements on ES systems increase significantly.
Recently there have been attempts to bring the advances made in machine learning (ML) to the understanding of the EME. Several works have applied ML to modulation recognition in communications whilst others have attempted to classify individual radar transmitters from their radio frequency emissions (RF). ES could leverage these techniques to provide the operator with greater understanding of the complicated EME around them. Little academic research has been completed on real world applied problems considering low SNR, congested and contested environments.
Many open research questions exist in the application of ML to the Electromagnetic Environment (EME). These include:
- How to collect the training data with limited a priori information or ability to label it.
- Labelling is a significant challenge in general and a non-trivial task to undertake. This PhD develop methods for best practice in this area.
- How to pre-process RF data to get best performance from ML algorithms, e.g., best normalisation techniques to cope with varying power levels and the use of time-frequency transforms to provide more information.
- How to deal with specific ES challenges such as
- Fleeting signals, e.g., only a few examples of a signal/class are available to ML techniques.
- Erroneous data labelling and incomplete datasets
- Congested RF scenarios
- Interference and multi-path problems specific to ES problems.
- How to aggregate ML techniques across multiple distributed sensors
- Benchmarking of ML techniques against traditional methods and defining when methods break.
- How to deal with multiple signal types – one model or multiple models. Cutting edge solutions may implement hierarchical modelling solutions which can be investigated within this research programme.
- What real world limitations exist when porting algorithms onto hardware?
These questions are present across many of the problems within ES that ML could address. The PhD will therefore focus on a particular research area, detecting, counting and separating signals in a congested EME using ML.
The PhD will include elements of simulation, algorithm design and hardware implementations. The balance of this will be discussed during the research project depending on skill sets of the PhD and feedback from the sponsor.
The hardware opportunities include the use of cutting-edge equipment such as the Xilinx RFSoC system the AIR-T SDR, BladeRF SDR, LimeSDR and many more. These devices can be utilized to create datasets to apply newly generated ML techniques on. The AIR-T system can leverage GPU processing while also having a re-configurable SDR solution all within the same device. Examples that look to use CUDA GPU acceleration into ES applications are already obtainable and the PhD candidate can use these as starting points for the practical aspects of the research.
The convergence of electromagnetic, cyber, and information activities are critical to achieving UK Defence’s mission and requires coordination and integration across the joint force for success. As part of the Cyber and Information System Division, the purpose of Electronic Warfare Technology and Enterprise (EWTE) Group is to develop science and technology concepts to exploit the electromagnetic spectrum for inform and attack; provide specialist technical advice to support the development of electronic warfare and electromagnetic activities capabilities; and create the UK contribution to an electromagnetic activities enterprise. Specifically, the Group specialises in radio frequency (RF) electronic surveillance and electronic attack, as well as drawing together domain knowledge with specialist advice at the EW Enterprise level. We range from early career graduates, mid-career specialists, ex-academia and ex-military personnel through to the Fellows of Dstl and Chartered Institutes.
As part of the ICASE PhD the student can engage closely with the sponsor Dstl over the 4-year period. Dstl has a team of experts in the area of RF sensing and ES that will provide technical partnering on this research. As part of this ICASE award the PhD student will be able to take secondments at the Dstl site and work closely with expert engineers within this research topic. It is a strict requirement that the applicant must be a UK national, due to security requirements for on-site working with the sponsor.
The candidate should meet the entry requirements detailed here: https://www.ucl.ac.uk/prospective-students/graduate/research-degrees/electronic-and-electrical-engineering-mphil-phd for PhD programmes at UCL EEE.
They should have at least an upper second-class honours degree (2:1 or equivalent qualification) in Electrical Engineering, Computer Science, Applied Mathematics, or related fields.
Additional requirements include an outstanding academic record and strong Digital Signal Processing background.
Experience with research is not required but is a plus. Additional desirable skills include prior knowledge in Radar sensing, RF design, and machine learning.
If you fit these specifications, like challenging tasks, and are passionate about research, then we would love to hear from you.
For inquiries about the position, please contact Dr Matthew Ritchie email@example.com.
Further information regarding UCL may be found at www.ucl.ac.uk/. Information about the departments may be found at: www.ucl.ac.uk/eee.