A fine-grained indoor fingerprinting localization based on magnetic field strength and channel state information

With the popularity of wireless networks and smart devices, indoor localization gets developed rapidly. The location-based information services have attracted more and more attentions and the accurate location information has played an important role in the practical application. However, a large position measurement error in the unique indoor environment brings some challenges for accurate indoor localization. In this paper, we propose a hybrid fingerprint localization algorithm by synthetically utilizing Channel State Information (CSI) and magnetic field strength. Firstly, we give an improved Line of Sight (LOS) identification algorithm to narrow down the matching area that localization requires. Then, we combine CSI with magnetic field information to construct a fusion fingerprint database and provide a Multi-Dimensional Scaling k-Nearest Neighbor (MDS-KNN) method to achieve the fingerprint matching. Experiment result reveals that our proposed localization algorithm has better robustness and higher positioning accuracy than traditional fingerprint location methods.