52 lines
2.5 KiB
TeX
Executable File
52 lines
2.5 KiB
TeX
Executable File
\section{Related Work}
|
|
|
|
Indoor localization based on \docWIFI{} signal strengths dates back to the year
|
|
2000 and the work of Bahl and Padmanabhan \cite{radar}. During an offline-phase, a
|
|
multitude of reference measurements are conducted once. Those measurements are compared
|
|
against live readings during an online-phase. The pedestrian's location is inferred
|
|
using the $k$-nearest neighbor(s) based on the Euclidean distance between currently
|
|
received signal strengths and the readings during the offline phase.
|
|
|
|
Inspired by this initial work, Youssef et al. \cite{horus} proposed a more robust, probabilistic
|
|
approach. Fingerprints were placed every \SI{1.52}{\meter} and estimated by scanning each location
|
|
100 times. The resulting signal strength propagation for one location is hereafter denoted by a histogram.
|
|
The latter can be compared against live measurements to infer its matching-probability. The center
|
|
of mass among the $k$ highest probabilities, including their weight, describes the pedestrian's current location.
|
|
%
|
|
In \cite{ProbabilisticWlan}, a similar approach is used and compared against nearest neighbor and machine learning.
|
|
Furthermore, they mention potential issues of unseen transmitters and describe a simple heuristic of how to handle such cases.
|
|
|
|
Meng et al \cite{secureAndRobust} further discuss several fingerprinting issues like environmental changes
|
|
after the fingerprints were recorded. They propose an outlier detected based on RANSAC to remove potentially
|
|
distorted measurements and thus improve the matching process.
|
|
|
|
Despite a very high accuracy due to real-world comparisons, all approaches suffer from tremendous setup-
|
|
and maintainance times.
|
|
|
|
Therefore it makes sense to replace those time consuming fingerprints by model predictions.
|
|
Those are a well established research field, mainly used to determine the \docWIFI{}-coverage
|
|
for new installations. \cite{ANewPathLossPrediction, PredictingRFCoverage, empiricalPathLossModel}
|
|
|
|
|
|
einfach messen, ab und zu einen GPS fix und danach genetisch alles zuusammenoptimieren. also kein vorwissen
|
|
\cite{WithoutThePain}
|
|
|
|
das muesste noch was aehnliches sein:
|
|
\cite{crowdinside}
|
|
|
|
|
|
|
|
|
|
neben signalstärke gibt es noch viele andere methoden über laufzeiten wie beim gps etc.
|
|
diese erfordern meist aber spezial-hardware und laufen deshalb nicht so einfach auf dem smartphone [= ueberleitung!]
|
|
|
|
|
|
|
|
\cite{secureAndRobust}
|
|
|
|
|
|
andere methoden neben signalstärke
|
|
\cite{TimeDifferenceOfArrival1} \cite{TOAAOA}
|
|
|
|
\cite{Ebner-15}
|