Share Email Print
cover

Proceedings Paper

WiFi location method based on TSNE-KNN
Author(s): Yanru Zhong; Qingbo Xie; Shuaijie Zhao; Xiaonan Luo
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Aiming at the problems of low positioning accuracy and high data dimension of traditional WIFI fingerprint locating method, propose the WIFI fingerprint indoor locating method based on TSNE-KNN method to solution the problem. In the offline stage, the WIFI fingerprint database is dimensionalized by using the TSNE (t-distributed embedding), and the TSNE parameters are adjusted to obtain the 2d(two-dimensional) WIFI fingerprint database with high differentiation. In the online phase: firstly, the real-time WIFI signal strength collected together with the original WIFI fingerprint database is used as the input of TSNE. The 2d WIFI fingerprint database obtained in the offline phase is used as the initial solution, and a set of arbitrary data is added as the initial solution. The TSNE parameters obtained in the offline phase are used to calculate the dimensionality reduction data. Then use KNN (k-nearestneighbor) algorithm to achieve WIFI location; Finally, the fingerprint database on the fourth floor of EE building of XJTLU north campus is used as input in the experiment. Experiments show that the TSNE-KNN can effectively display the characteristics of high-dimensional datas with low-dimensional datas, and improve the location accuracy also.

Paper Details

Date Published: 27 November 2019
PDF: 9 pages
Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113212X (27 November 2019); doi: 10.1117/12.2542190
Show Author Affiliations
Yanru Zhong, Guilin Univ. of Electronic Technology (China)
Qingbo Xie, Guilin Univ. of Electronic Technology (China)
Shuaijie Zhao, Guilin Univ. of Electronic Technology (China)
Xiaonan Luo, Guilin Univ. of Electronic Technology (China)


Published in SPIE Proceedings Vol. 11321:
2019 International Conference on Image and Video Processing, and Artificial Intelligence
Ruidan Su, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray