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.

Smartphone-Based Indoor Localization Systems: A Systematic Literature Review

“…In order to improve accuracy, there must be a dataset that offers RSSI in a variety of settings and device configurations, along with the precision of location points [81], because it offers acceptable accuracy in office buildings with Wi-Fi access points [17]. However, RSS fingerprint positioning technology dismisses a huge amount of parameters from estimation [63,124]. The smartphone-based acoustic approaches are used to improve indoor tracking performance by increasing the precision of position estimates [102] or by combining the horizontal and vertical (HV) magnetic fingerprinting model with the magnetic density fingerprinting model [113].…”

“…The smartphone-based acoustic approaches are used to improve indoor tracking performance by increasing the precision of position estimates [102] or by combining the horizontal and vertical (HV) magnetic fingerprinting model with the magnetic density fingerprinting model [113]. The indoor localization technique based on channel state information is widely used due to its excellent processing performance and better localization accuracy [124]. The method enhances overall location accuracy, especially in areas where anchor nodes are limited [20], by using particle filter formulation, estimates of PDR movement, and map data [113].…”

Survey on WiFi‐based indoor positioning techniques

“…The implementation process of fingerprint technology is generally divided into offline phase and online phase [44]. (i) Offline phase: establishing a wireless map that matches the RSS value of each AP and location information in the corresponding area; (ii) online phase: comparing the RSS value received by the mobile receiver carried by the target with the information of the wireless map to estimate the position and the trajectory of the target.…”

Multiview Variational Deep Learning With Application to Practical Indoor Localization

“…However, in the radio localization, it is preferable that the system be capable of packet-by-packet processing, rather than batch processing. References [18] and [19] introduced SVM based classification and regression, respectively. Reference [20] adopted transfer learning to reconstruct CSI data and applied the enhanced k-nearest neighbor (KNN) approach for localization.…”