To be considered for the project, candidates must:
- Possess, or be about to obtain, an upper second (2.1) UK BEng Hons, MEng or postgraduate MSc degree in a relevant engineering or physics related subject
- Have experience or a keen interest in one or more of the following: hyperspectral imaging/signal and Image Processing/machine learning and data analysis
- Have skills and understanding of Matlab and its use in data analysis
- Adhere to Research Council (RCUK) eligibility criteria for UK and EU nationals
Eligibility for RCUK studentships
- Research Council (RC) fees and stipend can only be awarded to UK and EU students and not to EEA or International students.
- EU students are only eligible for RC stipend if they have been resident in the UK for 3 years, including for study purposes, immediately prior to starting their PhD.
- If an EU student cannot fulfil this condition then they are eligible for a fees only studentship.
- International students cannot be funded from RC funds unless they are ‘settled’ in the UK. ‘Settled’ means being ordinarily resident in the UK without any immigration restrictions on the length of stay in the UK. To be ‘settled’ a student must either have the Right to Abode or Indefinite leave to remain in the UK or have the right of permanent residence in the UK under EC law. If the student’s passport describes them as a British citizen they have the Right of Abode.
- Students with full Refugee status are eligible for fees and stipend.
This PhD project will introduce new Hyperspectral Image (HSI) analysis tools based on state-of-the-art innovations in Artificial Intelligence (AI). Specifically, this research will aim to create new tools using deep learning for analysing HSI data for application in the agri-tech sector to detect the early onset of plant disease.
Unlike conventional cameras which sample Red, Green and Blue regions of the spectrum, hyperspectral imaging systems capture hundreds or thousands of images, each at a different wavelength of the electromagnetic spectrum. Recent reductions in the cost and size of HSI systems has made them increasingly more accessible for everyday applications in industry and research. However, HSI data is inherently large and its multidimensional nature makes it challenging to interpret and analyse. Fundamental research is therefore required to create new, intelligent data compression and analysis techniques in order to make the output of HSI systems more useful and accessible to non-expert end users.
In parallel with recent advances in HSI sensor technology and the reduction in their size and cost, recent developments in Deep Learning research has created major advances in the field of Artificial Intelligence. In this project, deep learning systems will be designed and used initially for analysing HSI data in the agri-tech sector for detecting the early onset of disease in high value crops. However, the application of the fundamental techniques for analysing HSI data will be wide ranging and could be applied in a number of impactful areas beyond this.
The objectives of this PhD studentship are as follows:
- To capture a sufficient amount of labelled HSI data of diseased and healthy crops for algorithm development and evaluation
- To design new data compression and band selection strategies based on deep neural networks to extract features from the HSI data which can be used for compression and classification
- To design, train and evaluate new Deep Learning algorithms and architectures to differentiate between healthy and various disease classes for various crops
- To extend the proposed Deep Learning architecture for other applications in e.g. defence, pharmaceuticals, and food & drink.
The studentship will commence on 1 October 2018.
For UK & eligible EU nationals - Funding is provided for full tuition fees and a high-spec PC for data analysis. There may be additional funding available for travel to one international conference during the PhD programme.
For International (Non-EU) applicants - Funding is available for tuition fees, but additional funding sources will need to be identified to cover the stipend and associated costs of the PhD programme.
The primary supervisor will be Dr Paul Murray, a Lecturer within the Institute for Sensors, Signals and Communications (InstSSC) in the Department of Electronic & Electrical Engineering. Dr Murray's research interests include Hyperspectral imaging and Image Processing.
The secondary supervisor will be Dr Jinchang Ren, a Reader in InstSSC. Dr Ren’s research expertise is in Hyperspectral data analysis.
How to apply
Candidates interested in applying should first email Dr Paul Murray or tel: +44 (0)141 548 2527 for an informal discussion. Thereafter, they should submit their CV, academic transcript, and a covering letter outlining their suitability for the position, to him.
Following review of the application submissions, selected candidates will be invited for interview.
Application submission deadline is 30th June 2018.
The project will start on 1st October 2018.