An indoor location method based on smart phone's RSS fingerprint in four directions
-
摘要: 针对传统位置指纹匹配算法只能表征单一维度指纹点特征的问题，提出了一种基于智能手机四向接收信号强度(RSS)指纹的室内定位方法. 该方法通过离线阶段的数据采集、特征提取、接入点(AP)权重分配三个步骤提取了更丰富的指纹点信息，在线阶段使用改进的K最近邻(KNN)分类算法将测试点与指纹点匹配. 在操作系统版本为Android 10的智能手机上使用蓝牙传感器进行实验验证，随机选取30个测试点，得到的实验结果表明：1)四向RSS指纹优于传统的单向RSS指纹，在相同的实验条件下使用四向RSS指纹最高可降低13.4%的定位误差；2)使用四向RSS指纹结合提出的算法，平均定位误差在1.61 m，且响应时间在毫秒级.
-
关键词:
- 室内定位 /
- Android系统 /
- 四向接收信号强度(RSS)指纹 /
- 接入点(AP)权重分配 /
- K最近邻(KNN)算法
Abstract: To address the problem that traditional location fingerprint matching algorithm can only represent the characteristics of single dimensional fingerprint points, an indoor locating method based on smartphone's received signal strength (RSS) fingerprint was proposed. In this methods richer fingerprint point information was extracted by data collection, feature extraction and access point (AP) weight assignment in the offline phase, and the improved K nearest neighbor (KNN) algorithm was used to match the test Point with the fingerprint Point in the online phase. In addition, a Bluetooth sensor was used for experimental verification on a smartphone with Android 10 as the operating system version, and 30 test points were randomly selected. Two conclusions can be drawn from the experiment. First, the four-way RSS fingerprint is better than the traditional one-way RSS fingerprint. Under the same experimental conditions, the four-way RSS fingerprint can reduce the positioning error by up to 13.4%. The second is the algorithm proposed by combining the four-way RSS fingerprint, with an average positioning error of about 1.61 meters and a response time of milliseconds. -
表 1 简化后的模糊规则表
IQR Smaller Small Med Big Bigger Noise Std-Dev Smaller Small Med Big Bigger Noise 经典权重 1 0.800 0.600 0.400 0.200 0 改进后的权重 1 0.935 0.526 0.283 0.047 0.001 
下载: 导出CSV
表 2 各方案下的平均定位误差对比
m 方案 K=3 K=4 单向KNN 1.94 1.92 单向WKNN 2.07 2.14 四向KNN 1.68 1.76 四向WKNN 1.83 1.94 本文算法 1.71 1.61
下载: 导出CSV
表 3 本文算法与经典算法的运行时间对比
ms 算法 算法平均耗时 传统NN算法 1.4 传统KNN算法 1.5 传统加权KNN算法 1.7 四向最近邻算法 4.9 四向KNN算法 5.1 四向加权KNN算法 5.4 本文四向算法 5.1
下载: 导出CSV
-
[1] 陈锐志, 陈亮. 基于智能手机的室内定位技术的发展现状和挑战[J]. 测绘学报, 2017, 46(10): 1316-1326. DOI: 10.11947/j.AGCS.2017.20170383 [2] 王睿, 赵方, 彭金华, 等. 基于WI-FI和蓝牙融合的室内定位算法[J]. 计算机研究与发展, 2011, 48(增刊2): 28-33. [3] 黄刚, 胡钊政, 蔡浩, 等. 基于Wi-Vi指纹的智能手机室内定位方法[J]. 自动化学报, 2020, 46(2): 320-331. [4] 杨凯, 郭英, 毕京学. 基于安卓平台的室内实时定位[J]. 测绘科学, 2015, 40(6): 125-128, 155. [5] 王晓亮, 徐恪, 杨铮, 等. TinyLoc: 一种面向能耗受限的可穿戴设备的室内定位算法[J]. 计算机学报, 2017, 40(8): 1813-1828. DOI: 10.11897/SP.J.1016.2017.01813 [6] 石欣, 印爱民, 陈曦. 基于RSSI的多维标度室内定位算法[J]. 仪器仪表学报, 2014, 35(2): 261-268. [7] 方震, 赵湛, 郭鹏, 等. 基于RSSI测距分析[J]. 传感技术学报, 2007, 20(11): 2526-2530. DOI: 10.3969/j.issn.1004-1699.2007.11.037 [8] 邓中亮, 余彦培, 徐连明, 等. 室内外无线定位与导航[M]. 北京: 北京邮电大学出版社, 2013. [9] 石柯, 陈洪生, 张仁同. 一种基于支持向量回归的802.11无线室内定位方法[J]. 软件学报, 2014, 25(11): 2636-2651. [10] 郭伟奇. 基于模糊推理的室内定位方法研究[D]. 成都: 电子科技大学, 2015. [11] ZADEH L A. Fuzzy sets[J]. Information and control, 1965, 8(3): 338-353. DOI: 10.1016/S0019-9958(65)90241-X [12] ZADEH L A. Outline of a new approach to the analysis of complex systems and decision processes[J]. IEEE transactions on systems, man, and cybernetics, 1973, 3(1): 28-44. DOI: 10.1109/TSMC.1973.5408575 [13] TAKAGI T, SUGENO M. Fuzzy identification o f systems and its applications to modeling and control[J]. IEEE transactions on sytems, man, and cybernetics, 1985, 15(1): 116-132. DOI: 10.1109/TSMC.1985.6313399 [14] 胡可, 廖兴宇, 余敏, 等. 基于GPS与Wi-Fi位置指纹的室内外无缝定位研究[J]. 计算机工程, 2016, 42(2): 98-103. DOI: 10.3969/j.issn.1000-3428.2016.02.018 [15] YU M, XUE F, RUAN C, et al. Floor positioning method indoors with smartphone ’s barometer[J]. Geo-spatial information science, 2019, 22(2): 138-148. DOI: 10.1080/10095020.2019.1631573 -
点击查看大图
图(7) / 表(3)
计量
- 文章访问数: 382
- HTML全文浏览量: 122
- PDF下载量: 28
- 被引次数: 0
