Modeling individual healthy behavior using home automation sensor data: Results from a field trial
Steen, Enno-Edzard and Frenken, Thomas and Eichelberg, Marco and Frenken, Melina and Hein, Andreas
Journal of Ambient Intelligence and Smart Environments
A technical system for unobtrusive presence measurement and two novel models for describing user behavior indomestic environments are presented. Within the developed models user behavior is either described as the probability of beingpresent at a certain location within an environment at a certain time on a day of the week or being present at a location for acertain number of times with a certain duration. The models are called timeslot-based and duration-based. Both models havebeen applied to presence information gathered by a technical system using home automation sensors. The system was installedinto two flats of older people during a field trial for eight months. Results of the experiment show that the two models canbe applied to describe user behavior. The influence of data structure and model quality on the detection of anomalies and thegeneration of alarms is discussed. On the long-term, the approach aims at detecting cutbacks in self-care ability and changesin health state by autonomously learning typical user behavior from presence information in a spatial model and by detectinguntypical behavior, called anomalies, and generating alarms for caretakers. Such automatic assessment of self-care ability andhealth state is required in order to meet the increased challenges imposed to the decreasing number of care personal during theprogress of the demographic change.
11 / 2013
article
503–523
5
