FHWS/OTHER2017
Archived
3
0
Fork 0
Code Issues 4 Pull Requests Releases Wiki Activity

latest version

Browse Source
This commit is contained in:
FrankE
2017-04-18 20:35:48 +02:00
parent 11cb939758
commit cb86c22f3d
4 changed files with 529 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

44
tex/chapters/experiments.tex
View File

@@ -74,10 +74,52 @@ kann man auch testen wenn man beim particle-filter das resampling ganz aus macht
mit grafik: exp-dist vergroesert teils den abstand zu anderen locations , der GT selbst wird also besser,
aber an anderen stellen geht dafür der fehler hoch und kann zu verlaufen führen (z.B. treppenhaus)
}
% -------------------------------- other distributions, unseen APs, etc -------------------------------- %
To reduce the amount of misclassifications, where other locations within the building are (almost)
as likely (see \refeq{eq:wifiProb}) as the pedestrians actual location, we examined various
approaches. Unfortunately, none of which provided a viable enhancement under all conditions within
the performed walks.
One possibility to dissolve an equal \docWIFI{}-likelihood between two (or more) locations within in the building
is, to not only consider the \docAPshort{}s seen by the Smartphone, but also the \docAPshort{}s not seen
by the Smartphone. Maybe there is an \docAP{} that should be visible at the other locations. However,
as the Smartphone did not see this \docAPshort{} the other location can be ruled out.
While this works in theory, evaluations revealed several issues:
There is a chance that an \docAPshort{} is unseen during a scan due to packet collisions or
temporal effects within the surrounding. It thus might make sense to opt-out other locations
only, if at least two \docAPshort{}s are missing. On the other hand, this obviously requires (at least)
two \docAPshort{}s to actually be different between the two locations, which might not always be
the case.
Also, this requires the signal strength prediction model to be fairly accurate. Within our testing
walks there are several places surrounded by concrete walls, which cause a harsh, local drop in signal strength.
The models used within this work will not accurately predict the signal strength for such locations.
Including \docAPshort{}s unseen by the Smartphone thus often increases the estimation error instead
of fixing the multimodality.
We therefore examined variations of the probability calculation from \refeq{eq:wifiProb}.
Removing the strongest/weakest \docAPshort{} from $\mRssiVecWiFi{}$ yielded similar results.
While some estimations were improved, the overall estimation error increased for our walks,
as there are many situations where only a handful \docAP{}s can be seen. Removing (valid)
information will highly increase the error for such situations.
Using a more strict exponential distribution for
\begin{figure}
\input{gfx/wifiCompare_normalVsExp_cross.tex}
\input{gfx/wifiCompare_normalVsExp_meter.tex}
\label{normal vs exponential}
\label{fig:normalVsExponential}
\caption{
Comparison between normal- (black) and exponential-distribution (red) for \refeq{eq:wifiProb}.
While misclassifications are slightly reduced (upper chart),
the error between ground-truth and estimation (lower chart) increases by
about \SI{1}{\meter} for the median.
}
\end{figure}
\todo{