Indoor Localization for Fingerprint using RF Based on SSD

Fingerprint-based methods are widely adopted for indoor localization as compared to other infrastructure based positioning systems. The popular location fingerprint Received Signal Strength (RSS) is observed to vary a fingerprint significantly across from different devices. The experiment result is done with both Wi-Fi and Bluetooth devices as well as both Access-Point (AP) based localization and Mobile Node (MN) assisted localization. A robust location fingerprint is a analytical definition of Signal Strength Difference (SSD) and verify the performance experimental using a number of different mobile devices with heterogeneous hardware. The results of two well-known localization algorithms are K Nearest Neighbor and Bayesian Inference. Our proposed fingerprint is used to demonstrate its robustness when the testing device differs from the training device. And also compare these SSD based localization algorithms performance against with two other approaches to mitigate the effect of mobile node hardware variations. And the SSD-based algorithms have better accuracy.