A. Parnandi, K. Le, P. Vaghela, A. Kolli, K. Dantu, S. Poduri, and G. Sukhatme. Mobile Computing, Applications, and Services, volume 35 of Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, Springer Berlin Heidelberg, 10.1007/978-3-642-12607-9_25.(2010)
Geographic location of a person is important contextual information that can be used in a variety of scenarios like disaster relief, directional assistance, context-based advertisements, etc. GPS provides accurate localization outdoors but is not useful inside buildings. We propose an coarse indoor localization approach that exploits the ubiquity of smart phones with embedded sensors. GPS is used to find the building in which the user is present. The Accelerometers are used to recognize the user’s dynamic activities (going up or down stairs or an elevator) to determine his/her location within the building. We demonstrate the ability to estimate the floor-level of a user. We compare two techniques for activity classification, one is naive Bayes classifier and the other is based on dynamic time warping. The design and implementation of a localization application on the HTC G1 platform running Google Android is also presented.