Nature of Research
The centre specialises in the application of artificial intelligence
(AI) to problems affecting the natural environment. Projects to
date have concentrated on the development of intelligent systems
for the biological monitoring of river quality. The Centre’s expertise
in this field has grown out of the pioneering work carried out
by Bill Walley and Bert Hawkes in the early 1990s. Although biomonitoring
will remain the principal application domain of the group, some
diversification into other environmental applications is envisaged.
The AI methods used by the group stem from the belief that experts
use two complementary mental processes when diagnosing or predicting
problems in their domain of expertise. These are: a) probabilistic
reasoning based upon their scientific knowledge; and b) pattern
recognition based upon their experience of previous cases. Consequently,
the group is following two lines of AI research in parallel -
probabilistic reasoning based on Bayesian methods and pattern
recognition based on neural networks and information theory. The
Bayesian methods range from simple ‘naive’ Bayesian models to
complex Bayesian belief networks (BBN). The neural networks that
have been used include both supervised-learning networks (e.g.
multi-layered perceptrons) and unsupervised-learning networks
(e.g. self-organising maps). Recently the group has developed
its own pattern recognition system (MIR-max) based upon information
theory. This is now central to the groups pattern recognition
systems.
|
