In this paper we described how a smart phone can be used to perform
activity recognition, simply by keeping it in ones pocket.
We further showed that activity recognition can be highly accurate,
with most activities being recognized correctly over 90% of
the time. In addition, these activities can be recognized quickly,
since each example is generated from only 10 seconds worth of
data. We have several interesting applications in mind for activity
recognition and plan to implement some of these applications in
the near future.
Our work would not have been possible without establishing our
WISDM Android-based data collection platform, and we view this software and hardware architecture, where data is transmitted
by the phone to our Internet-based server, as a key resource produced
as a consequence of this work. By having this in place we
will be able to mine other mobile sensor data much more quickly.
This platform, as well as the data that we collected, will ultimately
be made public.