AbstractThis thesis focuses on the localization problem adapted to the constraints of araytracer simulated signal distribution for Wi-Fi capable mobile devices in indoorscenarios. The localization problem is defined as predicting the most probablelocations for an observed sequence of Wi-Fi signal strength readings. An accuratelyperforming solution is of high interest because Wi-Fi signals can be observedcheaply due to an already widespread deployment of Access Points. For an efficientanalysis of the problem, a framework is implemented that combines the raytracing,the localization and evaluation components. Based on this framework, it isinvestigated whether the raytracing tool provides an effective basis for an accurateWi-Fi localization system. Furthermore, the performance of a Hidden MarkovModel , a Particle Filter and a Nearest Neighbour based localization approach areevaluated on automatically trained raytracer models. Therefore, a representativecorpus of location annotated signal measurements is assembled and subsequentlyemployed for a thorough investigation of the algorithm properties with respect totracking the device in scenes of various complexity. The trained Wi-Fi signalstrength predictions diverge in average by 4 dBm from the real measurements.Under these predictions, the tracking algorithms reach a localization accuracy ofabout 1. 5 m on pathways and degrades up to 4 m in complex scenes like stairways.