current TeX

switched to acm-large

tex/chapters/relatedwork.tex

@@ -1,51 +1,58 @@
 \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.
+	Indoor localization based on received \docWIFI{} signal strengths (RSSI) dates back to the year
+	2000 and the work of Bahl and Padmanabhan \cite{radar}. During an one-time offline-phase, a
+	multitude of reference measurements are conducted. During the online-phase, where the pedestrian
+	walks along the building, those prior measurements are compared against live readings.
+	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.
+	approach. Their fingerprints were placed every \SI{1.52}{\meter} and estimated by scanning each location 
+	100 times. The resulting signal strength distribution for each location is hereafter encoded 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.
+	In \cite{ProbabilisticWlan}, a similar approach is used and compared against nearest neighbor, kernel-density-estimation and machine learning.
+	Furthermore, they mention potential issues of (temporarily) invisible 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
+	Meng et al. \cite{secureAndRobust} further discuss several fingerprinting issues like environmental changes 
+	after the fingerprints were recorded. They propose an outlier detection 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. 
+	Despite a very high accuracy due to real-world comparisons, aforementioned approaches suffer from tremendous setup-
+	and maintainance times.
+	Using robots instead of human workforce to accurately gather the necessary
+	fingerprints might thus be a viable choice \cite{robotFingerprinting}.
+	Being cheaper and more accurate, this technique can also
+	be combined with SLAM for cases where the floorplan is unavailable.
 	
-	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}
+	Besides using real world measurements via fingerprinting, model predictions can be used to determine
+	signal strengths for arbitrary locations. Propagation models are a well established field of research,
+	initially used to determine the \docWIFI{}-coverage for new installations.
+	While many of them are intended for outdoor and line-of-sight purposes, they are often applied to indoor use-cases as well
+	\cite{ANewPathLossPrediction, PredictingRFCoverage, empiricalPathLossModel}.
+	
+	The model-based approach presented by Chintalapudi et al. \cite{WithoutThePain} works without any prior knowledge.
+	During a setup phase, pedestrians just walk within the building and transmit all observations to a central 
+	server. Some GPS fixes with well known position (e.g. entering and leaving the building) observed by the pedestrians
+	are used as reference points. A genetic optimization algorithm hereafter estimates both, the parameters for a
+	signal strength prediction model and the pedestrian's locations during the walk. The estimated parameters
+	can be refined using additional walks and may hereafter be used for the indoor localization process.
+	Likewise, it is possible to apply a global optimization that also determines a vague floorplan for the building \cite{crowdinside}.
 	
 	
-	einfach messen, ab und zu einen GPS fix und danach genetisch alles zuusammenoptimieren. also kein vorwissen
-	\cite{WithoutThePain}
+	As described in previous works, signal strength propagation strongly depends on the transmitter's surroundings and thus on the buildings
+	architecture. 
+	%This induces both, the need for more complex prediction models and the need for filtering approaches
+	%to limit the impact of potentially erroneous readings.
+	%
+	Approaches based on timing like TOA and TDOA as used within the GPS or methods estimating the signal's angle-of-arrival (AOA)
+	are more accurate, and mostly invariant to architectural obstacles \cite{TimeDifferenceOfArrival1, TOAAOA}.
+	However, each of those requires special hardware to work.
+	%
+	We therefore focus on the well-known RSSI that is available on each commodity smartphone and use a 
+	a simple signal strength prediction model to estimate the most probable location given the phone's observations.
+	To reduce the prediction error, we propose a new model based on multiple simple ones.
+	Several strategies to optimize such a model and the to-be-expected accuracy are hereafter discussed and evaluated.
 	
-	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}