Coordinate-Based Clustering Method for Indoor Fingerprinting Localization in Dense Cluttered Environments

Abstract

Indoor positioning technologies has boomed recently because of the growing commercial interest in indoor location-based service (ILBS). Due to the absence of satellite signal in Global Navigation Satellite System (GNSS), various technologies have been proposed for indoor applications. Among them, Wi-Fi fingerprinting has been attracting much interest from researchers because of its pervasive deployment, flexibility and robustness to dense cluttered indoor environments. One challenge, however, is the deployment of Access Points (AP), which would bring a significant influence on the system positioning accuracy. This paper concentrates on WLAN based fingerprinting indoor location by analyzing the AP deployment influence, and studying the advantages of coordinate-based clustering compared to traditional RSS-based clustering. A coordinate-based clustering method for indoor fingerprinting location, named Smallest-Enclosing-Circle-based (SEC), is then proposed aiming at reducing the positioning error lying in the AP deployment and improving robustness to dense cluttered environments. All measurements are conducted in indoor public areas, such as the National Center For the Performing Arts (as Test-bed 1) and the XiDan Joy City (Floors 1 and 2, as Test-bed 2), and results show that SEC clustering algorithm can improve system positioning accuracy by about 32.7% for Test-bed 1, 71.7% for Test-bed 2 Floor 1 and 73.7% for Test-bed 2 Floor 2 compared with traditional RSS-based clustering algorithms such as K-means.

A Comprehensive and Reproducible Comparison of Clustering and Optimization Rules in Wi-Fi Fingerprinting

“…The methods based on grid-based clustering [74] using fix-sized square cells are Gridx and GridOverlx. The gridbased clustering was suggested for RSS-based clustering by Liu et al [58]. For the two methods, x refers to the size of the cell in meters.…”

“…Liu et al [58] explored location-based clustering, where clusters are determined using the minimal radius circles that enclose all RPs. The circles are then used to cluster the RP by their distance to the circles' centers.…”

An Improved WiFi Positioning Method Based on Fingerprint Clustering and Signal Weighted Euclidean Distance

“…However, the clustering criteria used in the above RSS-based clustering methods are only the signal distance, which makes the clustering result unable to reflect the position distribution of RPs well and lead to the existence of many RPs with similar RSS, but distant positions, in a cluster. In [12], a coordinate-based clustering method is proposed to reduce the influence of AP deployment and improve the robustness of the system in dense cluttered indoor environments. In [13], a hybrid distance of signal distance and position distance is used as the clustering feature for clustering in the offline stage.…”

CC-DTW: An Accurate Indoor Fingerprinting Localization Using Calibrated Channel State Information and Modified Dynamic Time Warping

“…Although widely used global navigation satellite systems (GNSS) could provide a relatively high positioning accuracy outdoors, it does not perform well indoors due to the coverage limitation of satellite signals. Therefore, various indoor positioning technologies have been proposed in order to enable high-accuracy localization in indoors over the past two decades, including infrared [4], ultrasonic [5], ultra-wideband (UWB) [6], pseudolite [7], acoustic signals [8], Wi-Fi [9,10], Bluetooth [11], etc. However, indoor high-accuracy positioning is still an open but challenging issue, which has been proved by the conclusion “the indoor location problem is not solved” from the recent indoor localization competitions hosted by Microsoft [12].…”