Improvement of fingerprint location method based on KNN-PF algorithm

Xinyi Xue; Hao Wang; Haidong Hu; Chenkai Ma

doi:10.1117/12.2652192

10 November 2022 Improvement of fingerprint location method based on KNN-PF algorithm

Xinyi Xue, Hao Wang, Haidong Hu, Chenkai Ma

Proceedings Volume 12331, International Conference on Mechanisms and Robotics (ICMAR 2022); 1233134 (2022) https://doi.org/10.1117/12.2652192
Event: International Conference on Mechanisms and Robotics (ICMAR 2022), 2022, Zhuhai, China

Abstract

Fingerprint positioning is a common method of indoor positioning. The matching algorithm is an important part of determining the final positioning accuracy. How to choose a better algorithm to improve the positioning accuracy is the focus of this article. The traditional KNN algorithm is a common matching algorithm, but its positioning accuracy is not very high. Therefore, this paper proposes to select the optimal hyperparameter K through cross-validation, align to perform KNN regression, and then pass PF (particle filter) Method to optimize its results, its average positioning accuracy is improved by 23%, which has certain practical significance.

Citation Download Citation

Xinyi Xue, Hao Wang, Haidong Hu, and Chenkai Ma "Improvement of fingerprint location method based on KNN-PF algorithm", Proc. SPIE 12331, International Conference on Mechanisms and Robotics (ICMAR 2022), 1233134 (10 November 2022); https://doi.org/10.1117/12.2652192

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