Gerka, Alexander and Bayer, Finn and Eichelberg, Marco and Frenken, Melina and Hein, Andreas
Global Internet of Things Summit
Dementia patients, like most older adults, prefer
to live in their own home as long as possible. This requires,
however, that they are able to perform activities of daily living
(ADL). Therefore, many research projects install different sensor
setups to identify ADLs. Though the water usage correlates with
many ADLs (i.e.: bathing, cooking) only few of these systems
use water usage sensors. The reason is that there is no water
usage sensor available that is unobtrusive, ambient and precise.
In this article, we propose a water usage sensor that is based
on a piezoelectric element that fulﬁlls these requirements. We
describe the implementation of the sensor system in a living lab.
Additionally, we discuss different features that were extracted
from the sensor signal and different machine learning algorithms
that were used to classify the data. Finally, we present the results
to several tests we performed to determine the accuracy of our
sensor system under different environmental conditions.