Date Added: Jan 2011
Indoor localization techniques using location fingerprints are gaining popularity because of their cost-effectiveness compared to other infrastructure-based location systems. However, their reported accuracy falls short of their counterparts. In this paper, the authors investigate many aspects of fingerprint-based location systems in order to enhance their accuracy. First, they derive analytically a robust location fingerprint definition, and then verify it experimentally as well. They also devise a way to facilitate under-trained location systems through simple linear regression technique.