Paper Info
Title
Smartphone- Based Indoor Fingerprinting Localization Using Channel State Information
Abstract
Indoor localization technology plays an important role in many indoor application scenarios. Existing WiFi-based indoor localization methods mainly obtain channel state information (CSI) through the personal computer, or obtain coarse-grained received signal strength (RSS) through the smartphone to finish the localization. Little work has been done on using smartphones to obtain fine-grained channel state information for localization. In this paper, we use the smartphone to collect fine-grained CSI that is more convenient and applicable, and propose a indoor fingerprinting localization. Compared with the CSI collected by the computer, the CSI signal collected by the smartphone fluctuates greatly. Hence, we corrects the CSI data through the signal processing technique and selects optimal subcarriers to obtain more stable and effective signals. In order to cope with the noisy WiFi environment, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) method is used to remove abnormal sample points to reduce environmental interference. Moreover, the support vector machine multi-classification method is used for training and classification to achieve localization. Finally, we use the Google Nexus 5 smartphone to conduct experiments in two typical indoor environments. The localization accuracy is 91% and 86%, respectively, and both average localization errors are less than 0.5m. Experimental results show that the proposed algorithm has higher localization accuracy compared with the typical algorithms.
Year
DOI
Venue
2019
10.1109/ACCESS.2019.2958957
IEEE ACCESS
Keywords
DocType
Volume
Indoor localization, smartphone, channel state information, support vector machine
Journal
7
ISSN
Citations 
PageRank 
2169-3536
0
0.34
References 
Authors
0
6
Name
Order
Citations
PageRank
Pengpeng Chen112317.75
Fen Liu200.34
Shouwan Gao302.37
Peihao Li412.73
Xu Yang522.09
Qiang Niu687.67