Here you can find a list of all projects which the Research Engineering Group have worked on.
Search
REG Projects
AI for control problems
Using a competition platform to accelerate progress in data-driven control problems
AI for multiple long-term conditions: Research Support Facility
Developing data standards, best practice and community around AI for multiple long term conditions research
AI for Numerical Weather Prediction (NWP): AI4NWP
Developing artificial intelligence algorithms to fundamentally transform weather forecasting and the prediction of local and global weather events
AMBER (AI-assisted Monitoring of Biodiversity using Edge-processing and Remote sensors)
Automated biodiversity monitoring of insects, bats and birds
Analysing humanities books and newspapers data
Text analysis using Cray's supercomputing analytics platform Urika-GX
Analysing social and geographic datasets
Mapping the available tools and techniques for qualitatively understanding human behaviour, in the context of social dynamics
App-based information governance for trustworthy research environments
Delivering an open source 'information governance system in a box' to support data protection in trustworthy research environments
Artificial intelligence for data analytics (AIDA)
Drawing on new advances in AI and machine learning to address data wrangling issues, and help to automate the data analytics process
Automating data visualisation
Researching algorithms for visualising data in digital twins, including automating the layout of large scale data and visualising the uncertainty of data values
Automating translation by determining text difficulty
Building a model to determine the features of text which make it more difficult for machine translation
Building a 'Google Maps' for molecular and cellular biology
The goal is to develop and deploy new computational methods to resolve the three-dimensional spatial distribution of the entire proteome of molecules inside whole cells, to provide an unprecedented view of the organisation of living matter.
Chronotopic cartographies for literature
Mapping fictional worlds from literary texts to advance understanding and interpretation of literature in entirely new ways
CROP: the Crop Research Observation Platform
A prototype digital twin of the Growing Underground underground farm operated by Zero Carbon Farms Ltd
Data safe havens in the cloud
Developing a policy and process framework for secure environments for productive data science research projects at scale
Data science toolkit for explorable data visualisations
Helping scientists understand data analyses by connecting parts of visualisations to the data they depend on
Data science tools for high-performance computing
Enabling the provision of popular data science packages within a managed, multi-user, academic high performance computing (HPC) environment
Demoland
Spatial modelling for (urban) land management predicting the impact of large-scale planning and land use changes.
Detecting and understanding harmful content online
Developing benchmarks and datasets for online harms researchers, and guidance for practitioners using tools to detect online harms
Digital twin of the world’s first 3D printed stainless steel bridge
A revolutionary project to create the world’s first 3D printed steel pedestrian bridge and understand how infrastructure can act as a living object
Enabling meta-learning in Shogun.ML
Allowing data scientists to exchange and analyse their workflows more easily
Environmental monitoring: blending satellite and surface data
Intelligent fusion of data from satellite and in-situ surface sensors to help understand our changing planet
Evaluating homomorphic encryption
Exploring different ways of encrypting sensitive data that can allow for secure, outsourced computation in the cloud
Global urban analytics for resilient defence
Understanding the mechanics that cause conflict and identifying multi-scale population areas that are at risk of conflict
Improving Android game recommendations
Creating a deep learning based tool to improve game recommendations on Samsung Galaxy devices
Input-output analytics for urban systems
Investigating inter-city trade flows in contemporary and historical contexts
Integrating information visualisation with machine learning
Integrating interactive data and information visualisation with machine learning technologies for learning for large datasets
Investigating industrial CT scanner damage
Gathering community-sourced data on damage to x‑ray detectors in industrial CT scanners, to inform cost-effective maintenance
Language models for quantitative science studies
Developing models to represent the use of language in research and improve performance of specific tasks, including the retrieval and summarisation of literature
Learning machines – infrastructure for augmented intelligence
Developing infrastructure and methods for supporting continuous use of machine learning algorithms
Living with Machines
A five-year research project that takes a fresh look at the well-known history of the Industrial Revolution using data-driven approaches
London air quality
Developing machine learning algorithms and data science platforms to understand and improve air quality over London
Machine learning in Julia
Developing a machine learning toolbox for the Julia programming language, emphasising ease of use, reproducibility, high performance, rapid development and advanced interoperability.
Managing uncertainty in government modelling
Developing practical methods and tools for managing uncertainty in government modelling
Network modelling of the UK's urban skill base
Modelling networks of locally embedded knowledge and skills to investigate the future diversification potential of individual UK cities
Nocell: Probabilistic programming for spreadsheet experts
Developing a programming language for probabilistic model-building, for organisations that produce spreadsheets as output
Optimising analysis of network graphs
Investigating how to optimise software that allows for the analysis of complex data networks on state-of-the-art processors
Optimising flow within mobility systems with AI
Using interactive data visualisation, mathematical and computer modelling, and machine learning to transform the way cities are planned and urban traffic is managed
Posterior bootstrap: A scalable approach to Bayesian non-parametric learning
Providing an open-source tool to make non-parametric statistical inference faster and more accurate
QUIPP – Quantifying utility and preserving privacy in synthetic data sets
Understanding the balance between utility, privacy and the uncertainty associated with synthetic data sets
Raphtory: A practical system for the analysis of dynamic graphs
Developing an open source system for dynamic graph analysis of datasets
Robust inference for air quality monitoring
Developing new computational and statistical tools to better understand and predict urban air quality
Role of synthetic data in financial systems
Investigating the role and use of synthetic data in financial systems
Scalable regression: Tools and techniques
Developing techniques for regression models to scale at large data volumes, incorporating regression model power into big data analytics engines
Scalable topological data analysis
Developing software that enables meaningful conclusions to be drawn from the shape of massive, noisy, and potentially incomplete datasets
Scivision
The Scivision project aims to connect computer vision model developers to image data providers from diverse scientific fields.
Security in the cloud
Investigating and prototyping the secure software components needed to enable data sharing without compromising data privacy.
sktime: A toolbox for data science with time series
A unified toolbox for time series in the Python programming language
Solar nowcasting with machine vision
Enabling worldwide solar photovoltaic (PV) nowcasting via machine vision and open data
Statistical secret sharing
Developing methodology for multiple parties to securely share and unify their statistical inference, without having to reveal their inference or underlying data
Supporting Pangeo: the community-driven platform for Big Data geoscience
Aligning efforts with the environmental data science community, the Met Office and Microsoft to support Pangeo, the growing international platform for Big Data geoscience
Synthetic data and privacy preservation
Exploring the use of synthetic data generators, which offer a naturally private way to generate high-quality data that preserves the statistical features of the original dataset
Synthetic data generation for finance and economics
Generating artificial business, finance, and economic data to enable data sharing, scenario simulation, and model validation
Technical advice for the NHS COVID-19 app
Informing the NHS Test and Trace programme’s understanding of the spread of the virus and helping to optimise the performance of the app
The (mis)informed citizen
Using computational approaches to evaluate the quality of online news and studying its impacts
The Gamma: democratising data science
Democratising data science by building tools that encourage everyone to understand data better
The Turing Way
An open source, open-collaboration and community-led project for reproducible, ethical and collaborative data science
Time-sensitive sensing of language and user-generated content
Developing methods for understanding changes in behaviour over time, with applications in mental health
Trustworthy Digital Infrastructure for Identity Systems
Enhancing the privacy and security of national digital identity systems
Trustworthy synthetic data in practice
Building a toolbox to generate and evaluate the trustworthiness, scalability, and usability of synthetic data, and co-ordinating synthetic data research
Turing benchmarking framework
Developing a cross-architecture benchmarking framework for data science algorithms
UK Biobank activity recognition
Using deep learning to find new connections between patterns of physical activity and health outcomes
Visual diagnostics for Markov Chain Monte Carlo (MCMC)
Designing visual diagnostics that articulate the concepts underlying robust MCMC computational algorithms
