点击次数：

论文类型：会议论文

发表时间：2017-01-01

收录刊物：EI、CPCI-S

卷号：10559

页面范围：269-276

关键字：Fingerprint location algorithm; Positioning accuracy; Clustering; priori information

摘要：Fingerprint positioning is a common technique in the field of indoor positioning. As a result of avoiding and utilizing the complex indoor structure to block and reflect the signal effectively, it has the most necessary room-level positioning accuracy. Due to the large amount of data in the radio-map, the clustering algorithm has become a commonly used method to reduce the workload of the search. But the artificial clustering and automatic clustering have their own limitations. This paper proposes a predictive radio-map search strategy to accelerate the database search, which means taking the positioning results, predicted by the filtering algorithm, to be the priori information to accelerate the next positioning. The simulation results show that the algorithm is superior to the traditional clustering - localization strategy in positioning accuracy.