Weighted Local Access Point based on Fine Matching k-Nearest Neighbor Algorithm for Indoor Positioning System

2019 ◽  
Author(s):  
Mohd Amiruddin Abd Rahman ◽  
Muhammad Khalis Abdul Karim ◽  
Caceja Elyca Anak Bundak
Keyword(s):  
Nearest Neighbor ◽  
Access Point ◽  
Indoor Positioning ◽  
Positioning System ◽  
K Nearest Neighbor ◽  
Nearest Neighbor Algorithm ◽  
Local Access ◽  
K Nearest Neighbor Algorithm ◽  
Indoor Positioning System

scholarly journals CAPTURE: A Mobile Based Indoor Positioning System using Wireless Indoor Positioning System

2018 ◽  
Vol 12 (1) ◽  
pp. 61 ◽  
Author(s):  
Yohanes Erwin Dari ◽  
Suyoto Suyoto Suyoto ◽  
Pranowo Pranowo Pranowo
Keyword(s):  
Nearest Neighbor ◽  
Access Point ◽  
Indoor Positioning ◽  
Location Based Services ◽  
Positioning System ◽  
K Nearest Neighbor ◽  
Indoor Location ◽  
Pointing Device ◽  
Accurate Position ◽  
Indoor Positioning System

The existence of mobile devices as a location pointing device using Global Positioning System (GPS) is a very common thing nowadays. The use of GPS as a tool to determine the location of course has a shortage when used indoors. Therefore, the used of indoor location-based services in a room that leverages the use of Access Point (AP) is very important. By using the information of the Received Signal Strength (RSS) obtained from AP, then the location of the device can be determined without the need to use GPS. This technique is called the location fingerprint technique using the characteristics of received RSS’s fingerprint, then use it to determine the position. To get a more accurate position then authors used the K-Nearest Neighbor (KNN) method. KNN will use some of the data that obtained from some AP to assist in positioning the device. This solution of course would be able to determine the position of the devices in a storied building.

Amp-Phi: A CSI-Based Indoor Positioning System

2018 ◽  
Vol 32 (09) ◽  
pp. 1858005 ◽  
Author(s):  
Tao-Yun Zhou ◽  
Bao-Wang Lian ◽  
Yi Zhang ◽  
Sen Liu
Keyword(s):  
Nearest Neighbor ◽  
Phase Error ◽  
Indoor Positioning ◽  
Location Based Services ◽  
Statistical Characteristics ◽  
Positioning System ◽  
Indoor Environments ◽  
K Nearest Neighbor ◽  
Error Mitigation ◽  
Indoor Positioning System

With rapid growth in the demand of location-based services (LBS) in indoor environments, localizations based on fingerprinting have attracted significant interest due to their convenience. Until now, most such methods were based on received signal strength indicator (RSSI), which is vulnerable to non-line-of-sight (NLOS). In order to realize high-precision indoor positioning, we propose a channel state information (CSI)-based Amp-Phi indoor-positioning system which exploits the amplitude and phase information of CSI at the same time to establish a fingerprinting database. Firstly, according to the characteristics of the raw CSI information collected at different positions under different environments, we build an NLOS mitigation model and a phase error mitigation model, respectively, to process the amplitude and phase of CSI. Secondly, we analyze the statistical characteristics of CSI carefully, including maximum, minimum, mean and variance. After being processed with the models, the CSI features can be used to distinguish different positions clearly, which provides a theoretical basis for the indoor positioning based on fingerprinting. Finally, we build a fingerprinting database based on the features of amplitude and phase, realize to locate the target’s position with the K-Nearest Neighbor (KNN) matching algorithm. Experiments implemented in different situations show that Amp-Pi system is reliable and robust, whose position accuracy is higher than that of PhaseFi, Horus and machine learning (ML) systems under the same condition. It can be used in many scenarios, such as the localization of robots in our daily life, by doctors or patients in the hospital, for people localization in large supermarkets or museums and so on.

Sign in / Sign up

Export Citation Format

Share Document