Fingerprinting based enhanced indoor positioning system using multi wall propagation model

Abstract

Nowadays, demands for location-based services (LBS) are going to rise day by day for indoor environments. Due to the unavailability of the extensively used Global Positioning System (GPS) in indoor environments, many other technologies and techniques are followed to fulfil these demands. Amongst all Indoor positioning techniques, Wi-Fi fingerprinting technique has appealed significant interest due to its potential to achieve maximum accuracy at minimum cost. Efficient systems are important to minimize delays, complexity and the associated additional costs. Positioning accuracy of Wi-Fi indoor positioning systems highly depends upon offline databases. Therefore, Development of robust Wi-Fi fingerprints is performed to improve the positioning results. For this reason, improved Motely Keenan propagation model is used. Additionally, based on original implementation, an Indoor Positioning System (IPS) is developed by utilizing different matching algorithms e.g. k-Nearest-Neighbors (kNN) algorithm, Feature Scaling k-Nearest-Neighbors (FS-kNN) algorithm. And then performance of all matching algorithm is compared with each other. Moreover, a new positioning algorithm is proposed to improve the localization accuracy. The development of the proposed algorithm is mainly based on environmental dispersion. To mitigate the effect of that dispersion, a procedure named as ‘Deleting Outlier’ is used with existing technique i.e. FS-kNN. The simulation results show that proposed method is superior to some previous methods and achieves an exceptional accuracy with an average positioning error of approximately 1.45m in 30m × 33m area using an up-to-date fingerprint database. On the basis of the results of this research, it can be concluded that it is possible to use Wi-Fi fingerprinting for indoor positioning to obtain a state-of-the-art accuracy.