A new programme aims to extract useful information from huge, complex datasets. Bath mathematicians will be building models to identify big dataset anomalies.
A new UK-wide research programme that aims to extract useful information from huge, complex datasets has been launched. As part of the programme, mathematicians from the University of Bath will be developing tools to identify dataset anomalies that point to serious problems that might otherwise go undetected.
In the field of neuroscience, for instance, the new mathematical models being developed at Bath may flag up anomalies on a brain scan that suggest a heightened risk of Alzheimer’s disease.
Explaining, Bath mathematician Dr Matthew Nunes said: -People at risk of Alzheimer’s display particular brain-function patterns, so we-ll be trying to characterise that brain function using statistical methods so a scan can give a better indication of a person’s susceptibility to the disease.-
Dr Nunes is confident that the new method being developed at Bath will also find applications in the fields of cybersecurity, communications, biology, finance and logistics - among others.
Making computer networks more resilient to cyberattacks is a major objective.
-The data that computers in a network use when talking to each other have certain patterns, and when these patterns change, it suggests something is going wrong, such as a cyberattack,- said Dr Nunes, who is coordinating the Bath project from the Department of Mathematical Sciences.
A better way to analyse complex data
The Network Stochastic Processes and Time Series (NeST) partnership will run over six years and will involve six UK universities- Bath, Bristol, Imperial College, Oxford, York and the London School of Economics and Political Science - and a range of companies and government organisations.*
The overarching aim of NeST is to achieve a step change in the modelling and analysis of vast banks of ever-growing, often interconnected data relating to customer needs and behaviour, and the performance of systems and equipment.
The programme will run across many sectors, making it easier to pinpoint problems and opportunities, make accurate predictions and plan robustly. It will dovetail leading-edge expertise in statistics, probability theory and data science, and is being funded by the Engineering and Physical Sciences Research Council (EPSRC), part of UK Research and Innovation (UKRI).
-This programme represents an important push in a direction where the UK risks lagging behind,- said Dr Nunes. -It’s the first serious attempt in the UK to find new methods to analyse complex datasets.-
Pinpointing problems
NeST has been split into eight overlapping projects. One project will focus on creating more secure, greener power grids. Another will improve mail services by matching resources to changing demand and better utilising the service’s distribution infrastructure and vehicle fleets.
A third project will analyse data from social media networks to better understand how fake news spreads, how influencers grow their audiences and how criminal networks operate online.
-If we can better use data to identify the big players in criminal rings, we can either stop their communications or intervene to combat human trafficking,- said Dr Nunes.
Jane Nicholson, EPSRC Director for Research Base, said: -The NeST programme demonstrates the fundamental importance of the mathematical sciences to important sectors such as energy, transport and cybersecurity.
-The team’s work in establishing itself as a leader in the study and exploitation of dynamic networks, which will reflect the fact that the data which underpin these critical sectors is constantly changing, will deliver benefits for industry and key services which impact on our daily lives.-
Professor Marina Knight of the University of York, one of the NeST Deputy Directors, said: -Everyone involved is tremendously excited to have the opportunity to undertake this timely research into such an important, growing area.
-We aim to build a national centre showcasing our work and harnessing the skills of a highly diverse team with backgrounds in statistics, probability and data science.
-Demonstrating that maths is directly relevant to real-world issues impacting everyone’s lives will be at the heart of NeST.-