WiFi location method based on TSNE-KNN

Yanru Zhong; Qingbo Xie; Shuaijie Zhao; Xiaonan Luo

doi:10.1117/12.2542190

27 November 2019 WiFi location method based on TSNE-KNN

Yanru Zhong, Qingbo Xie, Shuaijie Zhao, Xiaonan Luo

Proceedings Volume 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence; 113212X (2019) https://doi.org/10.1117/12.2542190
Event: The Second International Conference on Image, Video Processing and Artifical Intelligence, 2019, Shanghai, China

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.

Citation Download Citation

Yanru Zhong, Qingbo Xie, Shuaijie Zhao, and Xiaonan Luo "WiFi location method based on TSNE-KNN", Proc. SPIE 11321, 2019 International Conference on Image and Video Processing, and Artificial Intelligence, 113212X (27 November 2019); https://doi.org/10.1117/12.2542190

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available