Wirelessly Indoor Positioning System based on RSS Signal

Abstract

Indoor positioning (IPS) detection is a research area, presently undergoing development, mainly due to its applicability in the construction of different system types. Because it is, the Smartphone has become an integrated part of human daily life with its capability of connecting to Wireless Fidelity (Wi-Fi) network, which can be used as a tool in positioning systems. The idea of the proposed system is to use the Wi-Fi access points, inside the building, together with a Smartphone Wi-Fi sensor for constructing an accurate and reliable indoor positioning system which lets the building administrator locate those carrying smartphones, wherever they exist inside the building. The proposed system uses fingerprinting technique it is consists of the two-stage the first is a testing phase (or preparation phase) and therefore, the second is the training phase (or positioning phase). Three types of intelligent classifier algorithms are used; these algorithms are KNearest Neighbor (K-NN), Multilayer Perceptron neural network (MLP), and Support Vector Machine (SVM). The performance results of the suggested classifiers based on the detection of the location of the target demonstrate that the detection accuracy for MLP is 94.38% and SVM is 90.91%. The best success rate is obtained when using KNN classifiers, which is 96.8595% and the mean error rate (m) is 1.2m when used KNN classifier.