Visual Analytics

Visual Analytics
The extraction and visualisation of information from complex datasets – such as those found in industry, the health sector and biological research – is an important area of research for the UK. Working in this area of information technology, the NCRG (the Non-linearity and Complexity Research Group) has become one of the leading international research groups in neural networks and their application to data analysis and visualisation.

The NCRG has established a unique capability through the development of new algorithms and the creation of software tools that implement those algorithms. This work came together in Netlab, a suite of open-source neural network software that provides a platform for continuing research, application development, and technology transfer. Netlab, written in the MATLAB mathematical programming environment, includes a wide range of pattern recognition algorithms. The Netlab toolbox, freely available through the Aston website, provides the core tools needed for simulating neural network algorithms and models in teaching, research and applications development. So far there have been more than 40,000 downloads of Netlab by the academic and business communities worldwide.

A number of companies have incorporated the data visualisation work of the NCRG into their business activities.
  • Pfizer Central Research has supported our work through funding the development of practical visualisation algorithms and methods, and has collaborated in writing joint papers. This culminated in the development of an interactive visualisation tool for Pfizer’s research chemists and biologists (rather than statisticians) to interpret and analyse screening results (e.g. biological activity, toxicity etc.).

  • Integrated Geochemical Interpretation Ltd (IGI Ltd), a petroleum geochemical consultancy company which operates world-wide, sells p:IGI, a software product for geochemical interpretation and basin modelling.  IGI co-funded a PhD CASE student who, after completing his thesis, worked for the company to implement our visualisation algorithms in the p:IGI tool.  This was released in August 2011 and is being be applied in the domains of environmental geochemistry.  The company are using this tool to drive their expansion into new business sectors: forensic geology and renewable energy.

  • Intelligence data visualisation: A prototype information visualisation system was delivered to DSTL (Defence Science and Technology Laboratory) under a contract on Collaborative Multi-source Intelligence related to integrating spatio-temporal and network analysis incorporating measures of uncertainty.

  • Thales are now exploring the use of topographic information visualisation using very high dimensional submarine sonar array data as part of a collaborative industrial CASE project in the mathematics Knowledge Transfer Network. The idea is to synthesis the vast amounts of information into a form suitable for human interpretation by skilled operators on board submarines.
Visual analytics (particularly with the use of the DVMS software) has also played an important role in collaborative industrial research projects  in order to understand data, detect outliers and select important features.
  • We worked with Daden, an SME on Birmingham Science Park Aston, on a £35k contract for dstl (the Cyber and Influence Centre, part of the Centre for Defence Enterprise) for immersive data visualisation and its application to defence intelligence analysis.

  • Ian Nabney has engaged with Select Research Ltd. to help them develop the data visualisation and analysis for an obesity metric based on volume measurements from a white-light scanner.  This led to the company launching the new obesity metric, the Body Volume Index, in November 2010 and trials for the NHS.

  • In a CASE studentship with AgustaWestland to develop a condition monitoring system for helicopter airframes, DVMS has been used to select frequency bands and sensors that will provide the best detection of faults.  The visual nature of the results has enabled us to explain the selection process to the engineers and demonstrate the transitions between different flight modes.