Journal of Computer Applications ›› 2016, Vol. 36 ›› Issue (2): 488-491.DOI: 10.11772/j.issn.1001-9081.2016.02.0488

Previous Articles     Next Articles

Wi-Fi fingerprinting clustering for indoor place of interest positioning

WANG Yufan1,2, AI Haojun1, TU Weiping1,2   

  1. 1. School of Computer Science, Wuhan University, Wuhan Hubei 430070, China;
    2. National Engineering Research Center for Multimedia Software, Wuhan University, Wuhan Hubei 430070, China
  • Received:2015-09-01 Revised:2015-10-10 Online:2016-02-10 Published:2016-02-03


王玙璠1,2, 艾浩军1, 涂卫平1,2   

  1. 1. 武汉大学 计算机学院, 武汉 430070;
    2. 武汉大学 国家多媒体软件工程技术研究中心, 武汉 430070
  • 通讯作者: 艾浩军(1972-),男,湖北汉川人,副教授,博士,CCF会员,主要研究方向:室内定位、无线感知、多媒体信号处理。
  • 作者简介:王玙璠(1991-),女,安徽合肥人,硕士研究生,主要研究方向:室内定位、物联网工程;涂卫平(1974-),女,湖北松滋人,副教授,博士,CCF会员,主要研究方向:多媒体信号处理、音频编码。
  • 基金资助:

Abstract: Wi-Fi fingerprint acquisition and modeling is a time-consuming work, while crowdsourcing is an effective way to solve this problem. The feasibility of unsupervised clustering was demonstrated for Place of Interest (POI) positioning, which is benefit to generate radio map by crowded source. At first, a framework of Wi-Fi fingerprint localization algorithm was given, then the k-means, affinity propagation and adaptive propagation were applied to this framework. Using BP neural network as a supervised learning reference, an evaluation was executed in a laboratory to analyze the relationship between indoor POI partition and spatial division, and the Radio Signal Strength Indications (RSSI) were collected in POI. Compared the clustering results in the POI spatial space, the recall and the precision of the three clustering algorithms were both over 90%. The experimental results show that the unsupervised clustering method is an effective solution for coarse-grained POI indoor positioning application.

Key words: Place Of Interest(POI), indoor positioning, unsupervised clustering, affinity propagation, Wi-Fi fingerprint

摘要: 针对广域室内位置服务中Wi-Fi指纹图谱构建与维护困难的问题,论证无监督聚类算法实现感兴趣区域(POI)定位的可行性,从而为众包模式生成POI关联定位指纹图谱提供依据。首先介绍Wi-Fi指纹定位算法的基本框架,并将k均值算法、近邻传播算法、自适应传播算法应用到Wi-Fi指纹定位;然后以一个实验室为例,分析室内POI划分与空间区域的关系,建立无线信号强度指示(RSSI)特征库,以BP神经网络算法作为对比,评价三类无监督聚类算法在POI定位的性能,其定位的平均精度和查全率均高于90%。实验结果表明,无监督聚类算法生成无线指纹图谱可以作为粗粒度的室内POI定位的解决方案。

关键词: 感兴趣区域, 室内定位, 无监督聚类, 近邻传播, Wi-Fi指纹

CLC Number: