基于相似指纹特征的室内定位机制研究  

Indoor Positioning Mechanism Research Based on Similar Fingerprint Characteristics

作　　者：陈永乐[1] 于丹[1] 王泽[1] 

机构地区：[1]太原理工大学计算机科学与技术学院,太原030024

出　　处：《太原理工大学学报》2015年第3期336-340,共5页Journal of Taiyuan University of Technology

基　　金：国家自然科学基金项目:基于移动感知的室内指纹定位可通用性问题研究(61401300);山西省教育厅科技创新基金(2014124);太原理工大学校青年基金(2013Z060);太原理工大学校基金项目(2014TD054)

摘　　要：针对指纹定位结果中存在较大定位误差问题,分析了离线相似指纹对应采集点的分布特征,发现存在部分相似指纹对应的采集点位置距离较远的特征,这导致了较大定位误差的出现。据此提出了一种基于阈值的Dynamic-kNN的算法来实现指纹的匹配,并进一步针对相似指纹的聚类特征设计了基于K-Means的聚类优化算法,从而大大减少了定位结果中较大误差的存在。实验表明,该算法能够将最大定位误差缩小到5m以内,同时4m以上的较大定位误差所占比例也明显下降。本研究与其他算法相比,在定位性能和算法开销上具有明显优势。For big errors of fingerprint positioning, we analyzed corresponding position distri bution of off-line similar fingerprints and found the long distance of sampling positions of some similar fingerprints. Accordingly, we proposed a Dynamic kNN algorithm to achieve the finger- print matching based on a setting threshold. Moreover, a clustering algorithm on K Means was proposed with the clustering characteristics of similar fingerprints, which greatly reduced larger errors in the positioning results. Experiment results show that the algorithm can reduce the maxi- mum positioning errors to less than 5 m. Meanwhile, the proportion of the large positioning er- rors greater than 4 m also decreases, which has clear advantages in the positioning performance and overhead in comparison with other algorithms.

关 键 词：WiFi信号 信号强度 指纹定位 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]