Developing Deep Learning Intelligence for Forecasting Effects from Engineering Big Data PhD
- Mechanical, Electrical and Manufacturing Engineering
- Entry requirements:
- 2:1 +
- Not available
- Reference number:
- UK/EU fees:
- International fees:
- Application deadline:
- February 2018
in the UK for research quality
in the UK for Mechanical Engineering
The Complete University Guide 2018
of 2 Queen's Anniversary Prizes
Loughborough University is a top-ten rated university in England for research intensity (REF2014) and an outstanding 66% of the work of Loughborough’s academic staff who were eligible to be submitted to the REF was judged as ‘world-leading’ or ‘internationally excellent’, compared to a national average figure of 43%.
In choosing Loughborough for your research, you’ll work alongside academics who are leaders in their field. You will benefit from comprehensive support and guidance from our Doctoral College, including tailored careers advice, to help you succeed in your research and future career.
Deep Learning is a disruptive technology that has made remarkable forward leaps in the analysis of large and generic public image datasets. The proposed research will be focused on the entirely new application of Deep Learning to engineering data with a more diverse range of parameters and highly specific domain-knowledge. The research challenge is to devise a procedure to curate data in terms of quality, quantity and meta-data to enable data-fusion, abstraction and generalisation by means of Deep Learning algorithms.
This studentship will focus on developing underpinning Deep Learning abstraction architectures to interpret real-time multivariate and heterogenous engineering data. This is a new branch of analytical engineering science that involves a multi-disciplinary working. There are three research components: 1) devise and assemble multivariate and heterogenous engineering datasets for machine learning; 2) develop and deploy Deep Learning intelligence algorithms on the datasets; 3) develop and test visual analytic tools for interactive human-in-the-loop learning processes.
The studentship willdevelop Deep Learning interactively with the aid of visual analytics and visual abstractions. This research will lead to entirely new interactive visualization tools to enable exploration of high-dimensional data, scalability of models, model based design, coupled models and distributed datasets. Complimentary Deep Learning algorithms, coupled with interactive visualization, are foreseen to achieve a significant increase in accuracy and abstraction from the combination of multidisciplinary human expertise large amounts of data. The human-machine interaction is essential for Big Data Analytics where raw data is largely un-labelled and un-categorised. Engineering inspired case studies will be used to train and validate the research.
Primary supervisor: Prof Roy S. Kalawsky
Find out more
Applicants should have, or expect to achieve, at least a 2:1 Honours degree (or equivalent) in Engineering or Computer Science related subject. A relevant Master’s degree and/or experience in these subjects would also be advantageous.
All students must also meet the minimum English Language requirements.
Fees and funding
Tuition fees cover the cost of your teaching, assessment and operating University facilities such as the library, IT equipment and other support services. University fees and charges can be paid in advance and there are several methods of payment, including online payments and payment by instalment. Special arrangements are made for payments by part-time students.
This is an open call for candidates who are sponsored or who have their own funding. If you do not have funding, you may still apply, however Institutional funding is not guaranteed. Outstanding candidates (UK/EU/International) without funding will be considered for funding opportunities which may become available in the School.
How to apply
All applications should be made online. Under programme name select Electronic, Electrical & Systems Engineering. Please quote reference number: SFRK012017