Improving indoor localization by user feedback

In this paper we introduce a new method to incorporate the user as an additional information source for the purpose of indoor localization. Therefore, the user is interrogated about certain characteristics in his/her environment. The questions are generated by a knowledge-based system built on ontologies. We provide a new statistical model to evaluate the user's answer and integrate it into the particle filter, which is used for the localization system. Our results show that the user's feedback significantly improves localization results.