Deep Multi-Object Characterization of Convolutive Signals
Dr M Yaghoobi
Prof Sotirios Tsaftaris
No more applications being accepted
Funded PhD Project (European/UK Students Only)
Machine learning (ML) and artificial intelligence (AI) are changing the future of defence and security. This project investigates deep neural networks (DNN), i.e. a successful class of ML and AI modeling approaches, for the sensor machine learning, where the objective is to develop and analyse a broad range of complex sensor signals with convolutive natures. In particular, DNNs have shown great performances in discriminating and generating isolated individual objects. Isolated objects are often generated using bounding boxes or masking other objects. On the other hand, deep generative models (GM), e.g. GAN and VAE, generate realistic “single” object signals and images. However, assuming a single-object per signal can be a fundamental restriction in some non-electro-optical and unconventional defence and security measurements. In such cases, the superposition of multi objects fundamentally changes the structure of inputs. Some examples of such scenarios are RF electronic surveillance, hyperspectral imagery, spectroscopic hazardous-mixture analysis and x-ray baggage screening.
Few separate attempts for compensation of overlapping and superposition of objects, particularly in image domain, have been recently reported, e.g. multi-label classification and background plus foreground image generation, but a universal approach for the multi-object/multi-label deep learning, does not exist. Multi-object signals and images characterization by deep discriminators and generators for anomaly detection and inverse problems, is the main subject of this project.
The ideal candidate for this post should have some background in signal processing and/or machine learning, with a solid mathematical knowledge and willing to work in a team. Some familiarity with Python programming and deep learning tools are desirable, but not essential.
The University Defence Research Collaboration are pleased to invite applications for PhD studentships to work as part of a leading team of experts in signal processing.
The project will be hosted by the Institute for Digital Communications at the School of Engineering at the University of Edinburgh and the student will work on the University Defence Research Collaboration (UDRC). The UDRC is a leading research partnership for signal processing for defence and develops new techniques to better transform data across many domains into actionable information, and meet the requirements for improved situational awareness, information superiority, and autonomy. This collaboration, sponsored by Dstl and the EPSRC, is academia-led and has commenced its third phase of research focusing on "Signal Processing in the Information Age". The Consortium is made up of the University of Edinburgh, Heriot-Watt University, Queen’s University Belfast and University of Strathclyde and there are currently PhD opportunities available across the four universities to work on diverse topics in signal processing, as part of a collaborative team. The work will involve strong links with industry and the UK defence sector. The PhD student will be expected to work closely with other research team members and to attend regular meetings to present project updates to the sponsors and partners of this project.
Minimum entry qualification - an Honours degree at 2:1 or above (or International equivalent) in a relevant science or engineering discipline, possibly supported by an MSc Degree.
Further information on English language requirements for EU/Overseas applicants can be found here - https://www.ed.ac.uk/studying/international/english/postgraduate
Tuition fees + stipend are available for Home/EU students (International students can apply, but the funding only covers the Home/EU fee rate).
Applications are welcomed from self-funded students, or students who are applying for scholarships from the University of Edinburgh or elsewhere.
How good is research at University of Edinburgh in General Engineering?
(joint submission with Heriot-Watt University)
FTE Category A staff submitted: 91.80
Research output data provided by the Research Excellence Framework (REF)
Click here to see the results for all UK universities