|
|
Nonlinear Data Analysis and Modelling of
Complex Systems:
Applications
to Healthcare and Finance
Analysis of real life complex systems is concerned with recognising
patterns within the randomness they display, essentially finding the
fingerprints in their behaviours as a basis for learning and
prediction. Typically in such
data-rich but model-weak environments, this is done by non-parametric
nonlinear modelling based on nonlinear dynamics theory or machine learning
typified by neural networks. The
strength of these methods accrues from the fact that they need no a
priori assumption of a model and from their capability to infer
complex, nonlinear underlying relationships.
This programme undertakes front-line research of modelling, simulation
and prediction of real-world complex systems using advanced tools of
nonlinear dynamics theory and neural networks. The purpose of this work is to develop
new strategies and methodology in critical areas within risk assessment in
the areas of Healthcare and Finance.
This programme is partially supported by a University initiative and
has strong interaction and collaboration with specialists in hospitals,
companies and financial houses within Edinburgh and worldwide. This programme has lead to the
establishment of the Edinburgh Multidisciplinary Consortium for Advanced
Nonlinear Analysis of Complex Systems, funded by the Scottish Higher Education Funding Council
(SHEFC) Research Development Grant, and in partnership with the Royal Infirmary of Edinburgh, Laerdal Medical Ltd and Standard Life.
This new methodology has been applied with effect to several critical
areas within Healthcare, in particular modelling, prediction, and
determining outcome of the lethal arrhythmia ventricular fibrillation, and
also for more accurate classification of breast cancer through neural net
analysis. In collaboration with the Center for Disease Control in Atlanta, this procedure has been successfully used in
areas of behavioural science; for identifying world health inequalities and
health care promotion direction for countries, and within the US
identifying the evolution of health status among its states. In Finance, nonlinear data analysis in
conjunction with wavelets, and neural networks has led to improved
prediction accuracy; and techniques derived from this work have been
incorporated into neural network and data analysis procedures at Standard Life. In the three years since its creation the
Consortium has established a world-wide network of collaborators, been
highly productive in its output and attracted substantial media coverage of
its work resulting in increased public awareness of this new field of
analysis.
Back to Research Reviews'
Page
|
|
