Automatic Device-Transparent RSS-Based Indoor Localization

Signal strength variation across diverse devices is a major problem with RSS-based indoor localization systems. This paper aims to solve this problem by considering two factors: the instability of collected RSS samples and linear shift of RSS patterns collected by different devices. We propose different techniques to handle the uncertainty of samples. Furthermore, we propose an automatic linear transformation algorithm that relies on the linear relationship across diverse devices. The algorithm finds the set of nearest neighbor fingerprints for an online point through a series of linear transformations. A localizer engine is then used to detect user's location. The proposed system is automatic, has low computational complexity and does not require any training period. Experimental results indicate the proposed system is reliable with very high positional accuracy.