A Modified KNN Indoor WiFi Localization Method With K-median Cluster

3rd International Conference on Aeronautical Materials and Aerospace Engineering

航空航天工程

Lan, Wei^1 ; Li, Hongxin^1

School of Information Science and Engineering, Lanzhou University, Lanzhou

730000, China^1

关键词: Fingerprint features;    Indoor environment;    K-nearest neighbors;    Outdoor positioning;    Positioning accuracy;    Similarity measure;    Wi-Fi localizations;    Wi-Fi Positioning;   

Others  :  https://iopscience.iop.org/article/10.1088/1757-899X/608/1/012008/pdf
DOI  :  10.1088/1757-899X/608/1/012008

学科分类：航空航天科学

来源: IOP

【 摘 要 】

Because of the serious attenuation and multi-path effect of GPS signal, outdoor-positioning technology can not be applied in complex indoor environment. Through the study of K-Nearest Neighbor applied in WiFi positioning, according to the problem that the time complexity of KNN algorithm increases linearly with the quantity of samples, this paper combined clustering algorithm with KNN optimized the similarity measure in fingerprint feature space and proposed a efficient indoor target location algorithm . Experimental results showed that the algorithm improved the positioning accuracy, had strong robustness to noise and more importantly, the positioning time was effectively shortened and it can meet the requirements of practical applications.