Towards Holistic Activity Modeling and Behavioral Analyses

As the age profile of many societies continues to increase,
supporting health, both mental and physical, is of increasing importance
if independent living is to be maintained. Sensing and, ultimately, recognizing
activities of daily living has been perceived as a prerequisite
for detecting tasks that people avoid or find increasingly difficult to perform,
as well as being indicators of certain illnesses. To date, extensive
research efforts have been made on activity monitoring, recognition and
assistance in indoor scenarios, frequently through smart home initiatives.
However, the scenarios outside of the home have not received a similar
degree of attention from the research community. This paper advocates
a need for platforms that enable activity recognition in a range of environments,
thus enabling the construction of more complex yet realistic
activity models and behavior patterns. The design of a prototype supporting
an integrated approach to sensor data capture and activity model
construction is proposed. The application domain is that of dementia.