Limits...
Collaborative WiFi Fingerprinting Using Sensor-Based Navigation on Smartphones.

Zhang P, Zhao Q, Li Y, Niu X, Zhuang Y, Liu J - Sensors (Basel) (2015)

Bottom Line: Different middle-term navigation trajectories that move in and out of an indoor area are combined to make up the database.Furthermore, we evaluate the effect of WiFi database shifts on WiFi fingerprinting using the database generated by the proposed method.Results show that the fingerprinting errors will not increase linearly according to database (DB) errors in smartphone-based WiFi fingerprinting applications.

View Article: PubMed Central - PubMed

Affiliation: GNSS Research Center, Wuhan University, No.129 Luoyu Road, Wuhan 430079, China. fenix@whu.edu.cn.

ABSTRACT
This paper presents a method that trains the WiFi fingerprint database using sensor-based navigation solutions. Since micro-electromechanical systems (MEMS) sensors provide only a short-term accuracy but suffer from the accuracy degradation with time, we restrict the time length of available indoor navigation trajectories, and conduct post-processing to improve the sensor-based navigation solution. Different middle-term navigation trajectories that move in and out of an indoor area are combined to make up the database. Furthermore, we evaluate the effect of WiFi database shifts on WiFi fingerprinting using the database generated by the proposed method. Results show that the fingerprinting errors will not increase linearly according to database (DB) errors in smartphone-based WiFi fingerprinting applications.

No MeSH data available.


WiFi signal distribution in reference DB.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541948&req=5

sensors-15-17534-f008: WiFi signal distribution in reference DB.

Mentions: In addition, WiFi signal distribution in the reference DB was shown in Figure 8. The x- and y-axis indicate the length in the west-east and south-north directions, and the z-axis show the weighted AP number, which is calculated by(20)WAPi=∑j=1niai,j,  i∈IRPwhere is the weighted AP number at in the DB, is the number of WiFi signals received at, is the location index set of RPs in the DB. The value of is determine according to (i.e., the RSS of at) by the following rule: if > −60 dBm, = 1; else if −70 dBm < < −60 dBm, = 0.75; else if −85 dBm < < −70 dBm, = 0.25; else if < −85 dBm, = 0. Compared with Figure 7b, the available WiFi signals were abundant in the middle area of EEEL, lesser but still enough in the marginal indoor areas, and even less in outdoor areas.


Collaborative WiFi Fingerprinting Using Sensor-Based Navigation on Smartphones.

Zhang P, Zhao Q, Li Y, Niu X, Zhuang Y, Liu J - Sensors (Basel) (2015)

WiFi signal distribution in reference DB.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541948&req=5

sensors-15-17534-f008: WiFi signal distribution in reference DB.
Mentions: In addition, WiFi signal distribution in the reference DB was shown in Figure 8. The x- and y-axis indicate the length in the west-east and south-north directions, and the z-axis show the weighted AP number, which is calculated by(20)WAPi=∑j=1niai,j,  i∈IRPwhere is the weighted AP number at in the DB, is the number of WiFi signals received at, is the location index set of RPs in the DB. The value of is determine according to (i.e., the RSS of at) by the following rule: if > −60 dBm, = 1; else if −70 dBm < < −60 dBm, = 0.75; else if −85 dBm < < −70 dBm, = 0.25; else if < −85 dBm, = 0. Compared with Figure 7b, the available WiFi signals were abundant in the middle area of EEEL, lesser but still enough in the marginal indoor areas, and even less in outdoor areas.

Bottom Line: Different middle-term navigation trajectories that move in and out of an indoor area are combined to make up the database.Furthermore, we evaluate the effect of WiFi database shifts on WiFi fingerprinting using the database generated by the proposed method.Results show that the fingerprinting errors will not increase linearly according to database (DB) errors in smartphone-based WiFi fingerprinting applications.

View Article: PubMed Central - PubMed

Affiliation: GNSS Research Center, Wuhan University, No.129 Luoyu Road, Wuhan 430079, China. fenix@whu.edu.cn.

ABSTRACT
This paper presents a method that trains the WiFi fingerprint database using sensor-based navigation solutions. Since micro-electromechanical systems (MEMS) sensors provide only a short-term accuracy but suffer from the accuracy degradation with time, we restrict the time length of available indoor navigation trajectories, and conduct post-processing to improve the sensor-based navigation solution. Different middle-term navigation trajectories that move in and out of an indoor area are combined to make up the database. Furthermore, we evaluate the effect of WiFi database shifts on WiFi fingerprinting using the database generated by the proposed method. Results show that the fingerprinting errors will not increase linearly according to database (DB) errors in smartphone-based WiFi fingerprinting applications.

No MeSH data available.