Original scientific paper
https://doi.org/10.24138/jcomss.v15i1.612
An Enhanced Indoor Positioning Method Based on Wi-Fi RSS Fingerprinting
Marwan Alfakih
orcid.org/0000-0001-8893-6388
; Laboratoire Signaux et Images, Département d’Electronique, Université des Sciences et de la Technologie d’Oran, Algérie
Mokhtar Keche
; Laboratoire Signaux et Images, Département d’Electronique, Université des Sciences et de la Technologie d’Oran, Algérie
Abstract
In WiFi-based indoor positioning, the received signal strength (RSS) measurements are commonly used to estimate the mobile user location. However, these measurements significantly fluctuate over time and are susceptible to human movement, multipath and Non-Line-of-Sight (NLOS) propagation, which reduce the location accuracy. In this paper, an enhancement positioning method based on the nearest neighbor algorithm is proposed. The distribution of the RSS samples recorded from several Access Points (APs) are used rather than their average, for reducing the location errors introduced by the RSS variations and the multipath problem. The proposed algorithm, named the Nearest Kth Nearest Neighbor (NK-NN) is experimentally evaluated and compared to other powerful methods. The results show that the proposed method outperforms these methods.
Keywords
Indoor localization; nearest neighbor; received signal strength; Wi-Fi fingerprinting; wireless communication.
Hrčak ID:
216309
URI
Publication date:
1.3.2019.
Visits: 1.456 *