Projects Led by Dr Allan Tucker
- Estimating Uncertainty in Deep Learning for Reporting Confidence: An Application on Protein Cell Type Prediction (Human Protein Atlas, Uppsala)
- Sub-categories of disease for patient-specific diagnosis
- Latent variable modelling of disease progression (Pavia)
- High Fidelity Synthetic Data for Primary Care Research (MHRA)
- Joint Baltic Sea Research and Development Programme BONUS (EU)
- Pseudo time-series trajectory modelling for integrating longitudinal and cross-sectional data (EPSRC)
- Biodiversity informatics for heterogeneous data (Royal Botanical Gardens, Kew)
- Extreme events in a changing climate: a Big Data perspective (NERC)
- Concept Drift in Medical Data (MHRA + Pioneer)
- A multi-dimensional environment-health risk analysis system for Kazakhstan (British Council)
- A global canonical image data set for automatic species classification (NERC, ZSL, Google & Royal Society)
Led by Dr Stephen Swift
- An investigation into the application of CNN’s to classify Leukemia subtypes from blood stain images
- The use of Consensus techniques to predict the number of groups within data clustering
- Mining GitHub project meta-data to improve the software modularisation problem
- An improved Iterated Local Search for discrete combinatorial optimization
- Sentiment analysis ensembles to predict the trajectory of online hate forums
Led by Professor Xiaohui Liu
- EC Horizon 2020, INTEGRADDE: “Intelligent data-driven pipeline for the manufacturing of certified metal parts through direct energy deposition processes”, CI
- EC Horizon 2020, Z-BRE4K: “Real-Time Adaptable Machine Simulation models wrapped around Physical Systems for accurate predictive maintenance, towards zero-unexpected-breakdowns and increased operating life of Factories”, CI
- EC 7th Framework, EWATUS: “An Integrated Support System for Efficient Water Usage and Resources Management”, CI
- GSK/EPSRC CASE Award, “Predicting chromatin status from differential expression profiles”, PI
Led by Profesor Zidong Wang
- Liu / Wang: EC Horizon 2020 [2020-2024], DIG_IT: “A Human centred Internet of Things Platform for the Sustainable Digital Mine of the Future”
- Liu / Wang: EC Horizon 2020 [2018-2022], INTEGRADDE: “Intelligent Data-Driven Pipeline for the Manufacturing of Certified Metal Parts through Direct Energy Deposition Processes”
- Liu / Wang: EC Horizon 2020 [2017-2021], Z-BRE4K: “Real-Time Adaptable Machine Simulation Models Wrapped around Physical Systems for Accurate Predictive Maintenance, towards Zero-unexpected-Breakdowns and Increased Operating Life of Factories”
- Deep learning techniques with applications to healthcare data (Royal Society, Royal Academy of Engineering, European Union)
- Advanced algorithm development for big data analysis in social networks (Royal Society, European Union)
- Big data learning-based QoS analysis and estimation of cloud-services (Royal Society, National Science Foundation of China)
- Dynamic state estimation for power grids with unconventional measurements (Royal Society, Royal Academy of Engineering, European Union)
- Mathematical challenges in complex networks (Royal Society, China Scholarship Council)
Led by Dr Annette Payne
- What Works for Well Being (ESRC)
- Identifying risk factors associated with student failure and poor performance using learning analytics
Led by Dr Stainslao Lauria
- INTEGRADDE (EU Horizon2020 2019-2023)
- DIG_IT (EU Horizon2020 2020-2023)
Led by Dr Isabel Sassoon
Led by Dr Alaa Marshan
Led by Nadine Aburumman
- Learning to Care: the Early Development of Empathy in Brain and Behaviour (VR CAVE and Eye Tracking device) with the ToddlerLab, Birkbeck, University of London.
- Exploring the Effect of Vibration Feedback in VR Training Settings with my PhD student Rania Xanthidou.
Led by Dr Yongmin Li
- Retinal image analysis
- Personalised re-marketing
- AI-assisted tax assessment
Led by Dr Lianghao Han
- Software Environment for Actionable & VVUQ-evaluated Exascale Applications (SEAVEA)
Led by Dr Keming Yu
- Weibull regression for dispersion and lifetime data
- Predicting coating defect size on pipelines
- Bayesian discrete quantile regression
- Online remote condition monitoring using statistical analysis
- Novel extreme regression analysis for material failure and corrosion
- Quantile regression for modelling the remaining life of buried pipelines