Senior Lecturer
I am currently accepting PhDs in Computing Science.
- Overview
-
Dr Georgios Leontidis Contact Details
- Telephone
- work +44 (0)1224 272299
- georgios.leontidis@abdn.ac.uk
- Address
- The University of Aberdeen Meston 230
- Other Profiles
-
ORCiD
-
Twitter
-
ResearchGate
-
Google Scholar
-
Linkedin
Biography
George is an Associate Professor in Machine Learning and also the Programme Director of the highly successful and innovative MSc AI programme. George has a strong interest in both theoretical aspects of Machine/Deep Learning, e.g. capsule networks, domain adaptation, self-supervised learning etc., as well as applications, e.g. data imputation in environmental data of COSMOS-UK network (PI in NERC/EPSRC project ENTRAIN), homomorphic encryption with deep learning for enabling data sharing and analytics in food industry (PI - IoFT network plus EPSRC project), anomaly detection in nuclear reactors (Co-PI in H2020 project Cortex - 20 EU partners in total), Optimising retail refrigeration systems with machine learning (Co-PI-IUK project with Tesco), forecasting yield in strawberries and tomatoes (Co-PI-EU Interreg project SmartGreen and PhD studentship), Gas Turbine availability and fault prediction with Siemens Lincoln, etc.
Previously I was a Senior Lecturer at the University of Lincoln, before that a Senior Data Scientist at IBA Dosimetry in Germany and a Marie Curie FP7-ITN Fellow.
I am serving as programme committe in various tier 1 venues, such as NeurIPS, ICML, AAAI, ICLR, IJCAI, etc. and am participating in the UK AI Council’s Data Working Group ecosystem. I am also a member of the Full College of EPSRC and have been a college member of the UKRI FLF scheme, serving as interview and sift panel member. I am also serving as External Examiner at Cranfield University (MSc applied AI) and University of Hull. I have also served as external panel member for programme validation events.
My publication record includes more than 30 articles in leading venues, covering theoretical aspects on machine/deep learning as well as some highly impactful applications on nuclear reactors, refrigerations systems, agri-food, gas turbines and healthcare.
I have successfully supervised PhD students and have served as PhD viva examiner.
I am currently supervising 7 PhD students.
Latest Publications
-
-
Lightweight deep learning models for detecting COVID-19 from chest X-ray images
-
Multi-source domain adaptation for quality control in retail food packaging
-
Using Deep Learning to Predict Plant Growth and Yield in Greenhouse Environments
-
Introducing Routing Uncertainty in Capsule Networks
Memberships and Affiliations
- Internal
-
Director of the MSc Artificial Intelligence
- External
-
External Examiner of the MSc in Applied AI at Cranfield University
External Examiner of the BSc in Computer Science, Hull University
Sift and Interview panel member of the UKRI Future Leaders Fellowship scheme
Full College of EPSRC - member
AI Council’s Data Working Group ecosystem - member
- Research
-
Research Areas
Please get in touch if you would like to discuss your research ideas further.
- Computing Science Accepting PhDs View Research Area
Specialisms
- Artificial Intelligence
- Computer Vision
- Machine Learning
- Neural Computing
Research Overview
I am interested in problems revolving around deep learning and machine learning, more speficially on domain adaptation, variational inference and self-supervised learning. I am also working on novel neural network architectures, such as Capsule Networks.
In terms of application areas, I have a strong interest in problems that ML can provide solutions primarily in environmental, industrial, food and healthcare settings.
My past and current activity involves working with national and international collaborators on nuclear reactor perturbation analysis, optimising retail refrigeration systems, gap filling in environmental time-series, domain adaptation for food retail packaging image quality detection, disease detection, and yield forecasting for strawberries and tomatoes
Current Research
I am currently working on the following problems across a several funded projects:
a) Detecting various types of perturbations via neutron noise modelling and deep learning. We are using simulated and real data for various types of nuclear reactors. The data are provided by our EU partners (EU-H2020, 2017-2021, http://cortex-h2020.eu/)
b) Gap filling in environmental time-series, specifically for the Cosmos-UK network. We are developing new data imputation techniques in order to fill the gaps in the time series using historical data from most of the Cosmos-UK sites across the UK (https://www.ceh.ac.uk/our-science/projects/entrain)
c) New routing algorithms for Capsule Networks in order to improve their run time and performance, whilst reducing the number of parameters
d) Yield forecasting for strawberries - we use mobile robots to collect data in a setting that our collaborators at the Univeristy of Lincoln have in the Riseholme campus. We collect time-series, image, depth and video data, so that we can develop new machine learning techniques that can accurately and robustly forecast yield in 1-, 2- and 3- weeks ahead
e) Predicting availability of gas turbines, a collaboration with Siemens Gas Turbines
Collaborations
UK:
a) Centre for Ecology and Hydrology, Wallingford, with Matt Fry, Jon Evans, Steve Cole, Mike Bowes and John Wallbank
b) British Geological Survey, Keyworth, with Andy Kingdon and john Bloomfield
c) Sheffield University, Mike Mangan
d) University of Lincoln, MLearn group, LIAT and LCAS groups
International:
a) Chalmers University of Technology, Sweden with Christophe Demaziere and Paolo Vinai
b) Paul Scherrer Insitute, Switzerland with Hamid Dokhane
c) National Technical University of Athens, Greece with Andreas Stafylopatis and Georgios Alexandridis
d) Technical University of Madrid, Spain with Cristina Montalvo
e) Nuclear plant, UJV/Rez, Czech Republic, with Petr Stulik
Supervision
My current supervision areas are: Computing Science.
Internal Supervision
Primary supervisor
a) Aiden Durrant - third year: working on deep learning (Self-supervised Learning and nuclear reactors)
b) Miles Everett - first year: working on deep learning (Capsule networks and self-supervised learning)
Second Supervisor
a) Chris Moorhead - third year: working on deep learning for sonar images
External Supervision
Primary Supervisor
a) George Onoufriou - third year: working on deep learning for soft fruit yield forecasting
b) Mamatha Thota - third year: working on deep learning (domain adaptation in computer vision)
Research Funding and Grants
- Data Management and Interoperability for Data Trusts - Internet of Food Things EPSRC Network Plus - £50K – Principal Investigator (with Glasgow University) - 09/2020 to 03/2021
- NEXTGEN: Neural-network Encryption; eXploration of Techniques for secure aGricultural data processing – Internet of Food Things EPSRC Network Plus - £50K – Principal Investigator (Led by the Scotland’s Rural College) – 03/2020 to 09/2020
- Engineering Transformation for the Integration of Sensor Networks - Natural Environment Research Council (NERC) - £114K – non-lead Principal Investigator for UoL – (£340£ in total led by NERC Centre for Ecology and Hydrology) – 02/2019 to 04/2020
- BerryPredictor: Improving harvest forecasts, yield predictions and crop productivity by optimising zonal phytoclimates in covered strawberry production – Innovate UK – £80K - Co- Principal Investigator – 2019 to 2022 (Pearson, Leontidis)
- CORe monitoring Techniques and Experimental validation and demonstration (Cortex) – EU H2020 - 155K£ - Principal Investigator (~5M£ in total, coordinated by Chalmers University, Sweden) – 09/2017 to 08/2021
- SmartGreen–Big Data and Eco-Innovative resource use in the NSR Greenhouse Industry – EU Interreg – 530K£ (50% match funding) for UoL (~3M£ in total) – 09/2017 to 08/2021 – Co-I
- The Development of Dynamic Energy Control Mechanisms for Food Retailing Refrigeration Systems – Innovate UK – 845,510£ for UoL (~3.5M in total) – 09/2016 to 11/2018 – Co-I (https://tinyurl.com/y9sj5tdp)
- ReACT Refrigeration AI Control Technologies – BBSRC seeding catalyst – 35,000£ - 10/2018 to 04/2019 – Co-I
- The augmented agronomist: Synthesis of AI, ML and robotics to assist decision support. BBSRC-CTP-NPIF 4-year PhD Studentship - National Institute of Agricultural Botany – £99,300 - 2018
- Teaching
-
Teaching Responsibilities
Course Coordinator: Data Mining & Visualisation - MSc Artificial Intelligence
- Publications
-
Publications
Currently viewing:Page 1 of 4 Results 1 to 10 of 36
-
How might technology rise to the challenge of data sharing in agri-food?
Global Food Security, vol. 28, pp. 1-8
Contributions to Journals: Articles
- Digital Object Identifier
- https://doi.org/10.1016/j.gfs.2021.100493
- Additional Links
- personalised share link
-
Lightweight deep learning models for detecting COVID-19 from chest X-ray images
Computers in Biology and Medicine, vol. 130, 104181
Contributions to Journals: Articles
- Digital Object Identifier
- https://doi.org/10.1016/j.compbiomed.2020.104181
- Open Access
- http://aura.abdn.ac.uk/bitstream/2164/15586/1/Leontidis_cbm_cov_pre.pdf
- Additional Links
- View publication in Scopus
-
Multi-source domain adaptation for quality control in retail food packaging
Computers in Industry, vol. 123, 103293
Contributions to Journals: Articles
- Digital Object Identifier
- https://doi.org/10.1016/j.compind.2020.103293
- Additional Links
- View publication in Scopus
-
Using Deep Learning to Predict Plant Growth and Yield in Greenhouse Environments
Acta Horticulturae. International Society for Horticultural Science pp. 425-431, 7 pages.
Chapters in Books, Reports and Conference Proceedings: Conference Proceedings
- Digital Object Identifier
- https://doi.org/10.17660/ActaHortic.2020.1296.55
- Open Access
- https://pure.abdn.ac.uk/ws/files/163638324/1907.00624.pdf
- Additional Links
- View publication in Scopus
-
Introducing Routing Uncertainty in Capsule Networks
Contributions to Conferences: Papers
-
Imputation of missing sub-hourly precipitation data in a large sensor network: a machine learning approach
Journal of Hydrology, vol. 588, 125126
Contributions to Journals: Articles
- Digital Object Identifier
- https://doi.org/10.1016/j.jhydrol.2020.125126
- Additional Links
- View publication in Scopus
-
Introducing Multi-Source Domain Adaptation for Quality Control in Retail Food Packaging
Contributions to Conferences: Other Contributions
-
Neutron Noise-based Anomaly Classification and Localization using Machine Learning
Contributions to Conferences: Papers
-
Deep Bayesian Self-Training
Neural Computing and Applications, vol. 32, pp. 4275-4291
Contributions to Journals: Articles
- Digital Object Identifier
- https://doi.org/10.1007/s00521-019-04332-4
- Open Access
- http://aura.abdn.ac.uk/bitstream/2164/14476/1/SousaRibeiro_et_al_NCA_DeepBayesianSelfTraining_VoR.pdf
- Additional Links
- View publication in Scopus
-
The Augmented Agronomist Pipeline and Time Series Forecasting
3rd UK Robotics & Autonomous Systems Conference (UK-RAS)
Contributions to Conferences: Posters
- Digital Object Identifier
- https://doi.org/10.31256/Qm1Fu7L
-