Citation: Zhou, R.; Meng, F.; Zhou, J.;
Teng, J. A Wi-Fi Indoor Positioning
Method Based on an Integration of
EMDT and WKNN. Sensors 2022, 22,
5411. https://doi.org/10.3390/
s22145411
Academic Editor: Andrzej Stateczny
Received: 19 May 2022
Accepted: 15 July 2022
Published: 20 July 2022
Publisher’s Note: MDPI stays neutral
with regard to jurisdictional claims in
published maps and institutional affil-
iations.
Copyright: © 2022 by the authors.
Licensee MDPI, Basel, Switzerland.
This article is an open access article
distributed under the terms and
conditions of the Creative Commons
Attribution (CC BY) license (https://
creativecommons.org/licenses/by/
4.0/).
Article
A Wi-Fi Indoor Positioning Method Based on an Integration of
EMDT and WKNN
Rong Zhou, Fengying Meng, Jing Zhou * and Jing Teng
School of Control and Computer Engineering, North China Electric Power University, Beijing 102206, China;
zhourong@ncepu.edu.cn (R.Z.); 120202227098@ncepu.edu.cn (F.M.); jing.teng@ncepu.edu.cn (J.T.)
* Correspondence: zhoujing108@ncepu.edu.cn
Abstract:
In indoor positioning, signal fluctuation is one of the main factors affecting positioning
accuracy. To solve this problem, a new method based on an integration of the empirical mode
decomposition threshold smoothing method (EMDT) and improved weighted K nearest neighbor
(WKNN), named EMDT-WKNN, is proposed in this paper. First, the nonlinear and non-stationary
received signal strength indication (RSSI) sequences are constructed. Secondly, intrinsic mode
functions (IMF) selection criteria based on energy analysis method and fluctuation coefficients is
proposed. Thirdly, the EMDT method is employed to smooth the RSSI fluctuation. Finally, to further
avoid the influence of RSSI fluctuation on the positioning accuracy, the deviated matching points are
removed, and more precise combined weights are constructed by combining the geometric distance
of the matching points and the Euclidean distance of fingerprints in the positioning method-WKNN.
The experimental results show that, on an underground parking dataset, the positioning accuracy
based on EMDT-WKNN can reach 1.73 m in the 75th percentile positioning error, which is 27.6%
better than 2.39 m of the original RSSI positioning method.
Keywords: RSSI fluctuation; EMD; WKNN; indoor positioning
1. Introduction
Due to non-line-of-sight obstacles such as roofs and walls, the global navigation
satellite system (GNSS) fails to achieve desirable positioning in indoor environments [
1
].
With the emergence of a large number of indoor applications, scholars have conducted
numerous studies. Indoor positioning technologies can be divided into two categories
according to whether it requires dedicated infrastructure. Indoor positioning technologies
that require dedicated infrastructures are radio frequency identification (RFID) [
2
], Blue-
tooth low energy (BLE) [
3
], light (invisible and infrared light [
4
]), sund (audible sound and
ultrasonic [
5
]), ultra-wide band (UWB) [
6
] and others. Indoor positioning technologies
that do not require dedicated infrastructures include wi-fi [
7
], computer vision [
8
], motion
sensors [
9
], and so on. The type of positioning technology determines the method to obtain
location. The common methods include the path loss distance model, angle of arrival (AOA),
time of arrival (TOA), and fingerprint [
10
]. In infrared, the user transmits an infrared signal to
an infrared receiver, and the TOA of the ultrasonic pulse can estimate the location from the
transmitter to the receiver. In wi-fi, based on the received signal strength indication (RSSI)
from wi-fi access points (AP), the location can be easily estimated by using the path loss
distance model or the fingerprint methods. In addition, motion sensors can provide informa-
tion about direction, speed, and acceleration. The location can be continuously updated by
integrating the motion sensor information. Computer vision captures images from the user’s
perspective and compares them with database images to estimate the user’s location.
Among these wireless systems, wi-fi fingerprint positioning is favored in indoor
positioning because most mobile devices have the function of receiving wi-fi signals,
and APs are widely deployed indoors. The wi-fi fingerprint positioning method has its
Sensors 2022, 22, 5411. https://doi.org/10.3390/s22145411 https://www.mdpi.com/journal/sensors
