Research on Indoor Location Algorithm Based on Wi-Fi
Junjie Guo
College of Information Science and
Engineering
Guilin university of Technology
Jiangan Road 12,Guilin,China
86-13986555190
johnguo888@163.com
Hongxiang Xiao
*
College of Information Science and
Engineering
Guilin University of Technology
Jiangan Road 12,Guilin,China
86-13768916556
xhx0601@qq.com
Chaoqun Zhang
College of Information Science and
Engineering
Guilin University of Technology
Jiangan Road 12,Guilin,China
86-15998983897
1063660212@qq.com
ABSTRACT
Only one localization algorithm indoor environment has certain
error, and the change of localization environment will cause
instability of positioning system. The fusion of the position
fingerprint matching algorithm and the polynomial distribution
model can reduce the influence of the low positioning accuracy
caused by the shortcomings of the polynomial distribution model
and the position fingerprint matching model. In this paper, the
position fingerprint matching algorithm and the polynomial
distribution algorithm are respectively used to locate in different
environments, and the same parameter is used to quantify the
positioning results of the two different algorithms on the same
environment. According to the selection coefficient, the optimal
algorithm is selected for indoor positioning. In the online
positioning stage, an algorithm that can be selected according to
the selection coefficient to adapt to the environment can be used
to locate. This adaptive algorithm can solve the respective defects
of the fingerprint matching algorithm and the polynomial
distribution model, and improve the indoor positioning accuracy.
CCS Concepts
•Networks → Network services → Location based services.
Keywords
Indoor positioning, Dual-mode Complementary, Adaptive, Select
Coefficient
1. INTRODUCTION
The most widely used is the Global Positioning System (GPS) in
outdoor navigation positioning, which has good outdoor
navigation and positioning capabilities. Despite it’s widely range
of application, the disadvantage of GPS is needed to maintain line
of sight with satellites. In the environment where is an obstacle
between the satellite and the equipment terminal holder, that is,
the positioning service in the closed indoor environment can’t be
completed. The indoor positioning technology based on Wi-Fi is
the key to the future indoor positioning, and the algorithm used by
the positioning system will directly affect the positioning result.
The fusion of multiple algorithms for positioning can make indoor
positioning more accurate and adaptable, which is the
development direction of indoor positioning technology.
2. Indoor Position Algorithm Model
2.1 Polynomial Distribution Model
There are various interferences such as reflection and refraction in
the propagation of wireless signals in indoor environments. The
wireless signal strength is not simply reduced by the exponential
decay rule, but instead of the local convergence but overall
monotonous complex situation
[1]
. In order to reflect the signal
distribution more realistically, the distribution equation of the
wireless signal can be considered as a surface equation. From the
characteristics of the surface, it can be know the any
two-dimensional surface can be described by a polynomial, and a
two-dimensional can be proposed:
0 0 1, 1
,
N N N
i i m n
i i nm
i i m n
f x y C x D y E x y F
Formula (1.1)
In the formula (1. 1): (x, y) is the position of the reference node,
N is the order of the distribution model, 、 、 、 F is
an unknown parameter to be calculated
2.2 Fingerprint matching model
Location-based fingerprint matching positioning algorithm
includes two steps: the reference point feature information
collection phase and the location fingerprinting stage. The
reference point feature information collection stage mainly saves
the signal intensity and other feature information of each
reference point under the experimental environment in the
position fingerprint database. Offline data collection is represent
by
,which means the q wireless signal
reception strength values of the AP detected at the i-th feature
information collection point in the specified experimental
environment.
indicates the average wireless network
strength of the
detected at the i-th reference point in the
location area. It is known from the relevant research of the
reference, when
, the average strength of wireless
network reception returns to a certain value. And when the
fingerprint feature information is collected for each selected
reference point in the positioning area, the format of the
fingerprint data may be defined and denoted by R:
Permission to make digital or hard copies of all or part of this work for
personal or classroom use is granted without fee provided that copies are
not made or distributed for profit or commercial advantage and that
copies bear this notice and the full citation on the first page. Copyrights
for components of this work owned by others than ACM must be
honored. Abstracting with credit is permitted. To copy otherwise, or
republish, to post on servers or to redistribute to lists, requires prior
specific permission and/or a fee. Request permissions from
Permissions@acm.org.
ICIIP '18, May 19–20, 2018, Guilin, China
© 2018 Association for computing Machinery, ACM ISBN
978-1-4503-6496-6/18/05…$15.00
https://doi.org/10.1145/3232116.3232133