Linear coding scheme for wireless indoor localization of heterogeneous wireless devices

As a convenient and low-cost wireless technology, WiFi has been widely used for indoor localization, usually based on the Received Signal Strength (RSS) and the fingerprinting algorithms. However, heterogeneous wireless devices measure RSS differently, and impact the localization accuracy significantly. In this paper, we will present a novel linear coding scheme performed on the RSS measurements and implemented by the fingerprinting algorithm. It is shown by analysis that the proposed algorithm can remove the RSS difference due to the device heterogeneity. Simulation results show that, compared with the classic kNN algorithm, the proposed algorithm can achieve better localization accuracy than the kNN algorithm.