Detecting and monitoring behavioural change through personalised ambient monitoring

Abstract

Bipolar disorder (BD) is one form of mental illness and is estimated to affect around
0.4{1.6% of the population. The disorder is characterised by recurrent episodes of mania
and depression and is estimated to cost the UK economy £5.21 billion a year. Many
people with BD self-monitor their behaviour to help them identify the early warning
signs of an affective episode. The Personalised Ambient Monitoring (PAM) project
has been conceived take ideas from existing telehealth systems and apply them to BD.
By using a distributed network of discreet, unobtrusive sensors, the user's behavioural
patterns can be monitored and deviations in their behaviour can be detected. In doing
so it is hoped that the early warning signs can be detected and that this can be used to
assist them in their self-monitoring.

The PAM system is being developed by a multi-disciplinary team based at the ISVR and
the School of Management at the University of Southampton, the School of Electrical
and Electronic Engineering at the University of Nottingham and the Department of
Computing Science and Mathematics at the University of Stirling.

This thesis presents the background and motivations for the PAM project, the approach
the project will take, a review of appropriate data analysis techniques and the experimental
work that has been undertaken in the investigation of accelerometry for activity
monitoring, the use of a wireless camera to monitor a complex environment and the use
of multiple sensors to capture behaviour patterns in a technical trial.

Results from the technical trial show that it is possible to process information from
a variety of sensors to identity activity signatures and behavioural patterns in normal
controls. When these activity patterns are trained on week-days, the results presented
show that it is possible to identify weekend days as being behaviourally different.

More information

Identifiers

Catalogue record

Export record