摘要
位置指纹定位的K-均值聚类算法将参考点分为K个子类,将相似对象聚集在一起,从而减少指纹搜索空间,提高效率。本文在K-均值聚类算法的基础上对选取的子类中邻近点进行加权计算,提高高相关性参考点的计算比重,从而达到提高定位精度的目的。实验结果表明,改进后的算法具有更高定位精度,其精度提高了18.5%。
K-mean clustering algorithm based on fingerprint is divided the reference point into K subclass.The similar objects are clustered together to reduce the search space and improve the efficiency.In this paper,we weighted the nearest neighbor of the choose subclass based on the K-means clustering algorithm.Increase the proportion of high correlation reference point while calculating,so as to achieve the purpose of improving the accuracy of location.The experimental results show that the accuracy of the new algorithm has improved18.5percent.
出处
《全球定位系统》
CSCD
2016年第5期89-92,共4页
Gnss World of China
关键词
指纹定位
K-均值聚类
加权
Fingerprint localization
K-means clustering
weighting
