基于信号幅值分布的室内指纹定位算法Indoor fingerprint positioning algorithm based on signal amplitude distribution
丁承君,宇中强,朱志辉
摘要(Abstract)：
室内定位算法是基于位置服务领域研究的难点之一。针对室内定位应用场合和精度问题,提出了利用K-means和KNN融合算法对覆盖率广的WiFi信号进行指纹定位。WiFi指纹定位主要问题是前期指纹库数据的精确以及后期数据的匹配效果。首先,对WiFi信号的概率分布进行研究,弥补了一直以来由于K-means是无监督学习带来的k值的难以选取的缺陷,提高了指纹库的精确性,同时确保数据实时性。后期在线数据处理利用KNN分类算法进行后期在线定位过程的准确性。经多个实验场景测试结果表明,该算法在室内定位精度上3 m定位精度概率保持在78.4%,4 m精度保持在93.6%,基本上保证了室内定位精度的要求。
关键词(KeyWords)： 信号幅值;指纹定位;概率分布;K-means;KNN分类算法;WiFi信号
基金项目(Foundation): 天津市科技计划项目(14ZXCXGX00123);天津市科技计划项目(14ZCDZGX00811)~~
作者(Author): 丁承君,宇中强,朱志辉
DOI: 10.16652/j.issn.1004-373x.2018.10.010
参考文献(References)：
- [1]周傲英,杨彬,金澈清,等.基于位置的服务:架构与进展[J].计算机学报,2011,34(7):1155-1171.ZHOU Aoying,YANG Bin,JIN Cheqing,et al.Locationbased services:architecture and progress[J].Chinese journal of computers,2011,34(7):1155-1171.
- [2]席瑞,李玉军,侯孟书.室内定位方法综述[J].计算机科学,2016,43(4):1-6.XI Rui,LI Yujun,HOU Mengshu.Survey on indoor localization[J].Computer science,2016,43(4):1-6.
- [3]陆音,缪辉辉.复杂室内环境下的Wi Fi定位技术研究[J].计算机科学,2016,43(11):152-154.LU Yin,MIAO Huihui.Study on Wi Fi location technology under complex indoor environment[J].Computer science,2016,43(11):152-154.
- [4]江春冬,惠慧,陈云飞,等.与强度无关的位置指纹在线定位改进算法[J].电讯技术,2016,56(2):128-134.JIANG Chundong,HUI Hui,CHEN Yunfei,et al.An improved online position fingerprint algorithm for strength-independent interference source location[J].Telecommunication engineering,2016,56(2):128-134.
- [5]蔡朝晖,夏溪,胡波,等.室内信号强度指纹定位算法改进[J].计算机科学,2014,41(11):178-181.CAI Zhaohui,XIA Xi,HU Bo,et al.Improvements of indoor signal strength fingerprint location algorithm[J].Computer science,2014,41(11):178-181.
- [6]周瑞.应用室内结构布局提高Wi Fi定位精度和稳定性[J].电子科技大学学报,2013,42(2):295-299.ZHOU Rui.Improve the accuracy and stability of Wi Fi fingerprinting by applying the interior structure of buildings[J].Journal of University of Electronic Science and Technology of China,2013,42(2):295-299.
- [7]赵宇,周文刚.基于智能手机的室内定位[J].计算机应用与软件,2015,32(6):91-93.ZHAO Yu,ZHOU Wengang.Indoor localisation based on smartphone[J].Computer applications and software,2015,32(6):91-93.
- [8]唐洋,白勇,马跃,等.基于Wi Fi的指纹匹配算法在室内定位中的应用研究[J].计算机科学,2016,43(5):73-75.TANG Yang,BAI Yong,MA Yue,et al.Research of Wi Fibased fingerprinting matching algorithm in indoor positioning[J].Computer science,2016,43(5):73-75.
- [9]赵战营,成长生.基于聚类分析局部离群点挖掘改进算法的研究与实现[J].计算机应用与软件,2010,27(11):255-258.ZHAO Zhanying,CHENG Changsheng.On improved algorithm for local outlier mining based on cluster analysis and its implementation[J].Computer applications and software,2010,27(11):255-258.
- [10]华辉有,陈启买,刘海,等.一种融合K-means和KNN的网络入侵检测算法[J].计算机科学,2016,43(3):158-162.HUA Huiyou,CHEN Qimai,LIU Hai,et al.Hybrid K-meanswith KNN for network intrusion detection algorithm[J].Computer science,2016,43(3):158-162.
- [11]刘春燕,王坚.基于几何聚类指纹库的约束KNN室内定位模型[J].武汉大学学报(信息科学版),2014,39(11):1287-1292.LIU Chunyan,WANG Jian.A constrained KNN indoor positioning model based on a geometric clustering fingerprinting technique[J].Geomatics and information science of Wuhan University,2014,39(11):1287-1292.