基于WiFi的指纹匹配算法在室内定位中的应用研究  

Research of WiFi-based Fingerprinting Matching Algorithm in Indoor Positioning

作　　者：唐洋[1] 白勇[1] 马跃[2] 蓝章礼[3] 

机构地区：[1]重庆电力高等专科学校,重庆400053 [2]重庆大学软件学院,重庆401331 [3]重庆交通大学,重庆400074

出　　处：《计算机科学》2016年第5期73-75,共3页Computer Science

基　　金：国家电网重庆市电力公司科技研究资助项目(201566)资助

摘　　要：快速、准确地建立目标测定的接收信息强度(RSS)与指纹数据库的匹配,是提高指纹定位算法性能的关键。提出一种基于指纹簇匹配算法,以缩小搜索范围,优化搜索路径,通过减少搜索数目及计算量,达到快速、准确完成匹配的目的。考虑不同簇形对定位性能的影响,采用4组实验对算法的快速性、准确性进行评估。实验结果展示在保证定位精度的同时,指纹簇算法较传统算法至少减少了60%的搜索数目,并验证得出蜂窝簇形的性能是最优的。To enhance the performance of fingerprinting positioning,it is significantly necessary to rapidly and accurately match between the received signal strength（RSS）measured by the users and the pre-stored fingerprinting database.Therefore,a fingerprinting cluster algorithm was proposed to reduce the number of search points and optimize the search path,improving the performance of matching in rapidity and accuracy.Four different tests were designed to verify the proposed algorithm by evaluating the positioning accuracy and the rapidity,taking into consideration different shape of cluster.Our results show that the proposed algorithm reduces the number of search points by 60%,and has the same positioning accuracy with that of the traditional fingerprinting algorithm.By comparison of the performance of the different shape of clusters,the cellular cluster is optimal.

关 键 词：室内定位 RSS 指纹簇 蜂窝簇 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]