Accuracy performance ofWiFi fingerprinting positioning systems deteriorates severely when signal attenuations caused by human\nbody are not considered. Previous studies have proposedWiFi fingerprinting positioning based on user orientation using compasses\nbuilt in smartphones. However, compasses always cannot provide required accuracy of user orientation estimation due to the\nsevere indoormagnetic perturbations.More importantly, we discover that not only user orientations but also smartphone carrying\npositions may affect signal attenuations caused by human body greatly. Therefore, we propose a novel WiFi fingerprinting\npositioning approach considering both user orientations and smartphone carrying positions. For user orientation estimation, we\ndeploy Rotation Matrix and Principal Component Analysis (RMPCA) approach. For carrying position recognition, we propose a\nrobust Random Forest classifier based on the developed orientation invariant features. Experimental results show that the proposed\nWiFi positioning approach may improve positioning accuracy significantly.
Loading....