王升志,
刘建航,
黄庭培,
张鑫
中国石油大学(华东)计算机与通信工程学院 青岛 ??266580
基金项目:国家自然科学基金(61972417, 61601519, 61872385)，中央高校基本科研业务费专项资金(18CX02134A, 18CX02137A, 18CX02133A,19CX05003A-4)
详细信息
作者简介:李世宝：男，1978年生，副教授，研究方向为移动计算、无线传感器网络、干扰对齐等
王升志：男，1994年生，硕士生，研究方向为无线定位技术
刘建航：男，1978年生，副教授、博士，研究方向为无线局域网、车联网
黄庭培：女，1980年生，讲师、博士，研究方向为无线传感器网络
张鑫：男，1993年生，硕士生，研究方向为无线定位技术
通讯作者:李世宝 lishibao@upc.edu.cn
中图分类号:TN929.5计量
文章访问数:2391
HTML全文浏览量:785
PDF下载量:64
被引次数:0
出版历程
收稿日期:2018-06-20
修回日期:2019-02-28
网络出版日期:2019-03-30
刊出日期:2019-10-01
Semi-supervised Indoor Fingerprint Database Construction Method Based on the Nonhomogeneous Distribution Characteristic of Received Signal Strength
Shibao LI,,Shengzhi WANG,
Jianhang LIU,
Tingpei HUANG,
Xin ZHANG
College of Computer and Communication Engineering, China University of Petroleum (East China), Qingdao 266580, China
Funds:The National Natural Science Foundation of China (61972417, 61601519, 61872385), The Fundamental Research Funds for the Central Universities (18CX02134A, 18CX02137A, 18CX02133A, 19CX05003A-4)
摘要
摘要:室内定位中半监督学习的指纹库构建方法能够降低人力开销，但忽略了高维接收信号强度(RSS)数据不均匀的非齐分布特点，影响定位精度，针对此问题该文提出一种基于RSS非齐性分布特征的半监督流形对齐指纹库构建方法。该算法运用局部RSS尺度参数以及共享近邻相似性构造权重矩阵，得到精确反映RSS数据流形结构的权重图，利用该权重图通过求解流形对齐的目标函数最优解，实现运用少量标记数据对大量未标记数据的位置标定。实验结果表明，该算法可以显著降低离线阶段数据采集的工作量，同时可以取得较高的定位精度。
关键词:无线局域网/
室内指纹定位/
半监督流形对齐/
非齐性分布/
指纹库构建
Abstract:The radio map construction is time consuming and labor intensive, and the conventional semi-supervised based methods usually ignore the influence of the uneven distribution of high-dimensional Received Signal Strength (RSS). In order to solve that problem, a semi-supervised radio map construction approach which is based on the nonhomogeneous distribution characteristic of RSS is proposed. The approach utilizes the RSS local scale and common neighbors similarities to calculate the weighted matrix. Thus, the weighted graph that reflects accurately the structure of RSS data manifold is presented. In addition, the weighted graph is used to find the optimal solution of the objective function to calibrate the locations of plenty of unlabeled data by a small number of labeled RSS. The extensive experiments demonstrate that the proposed method is capable of not only constructing an accurate radio map at a low manual cost, but also achieving a high localization accuracy.
Key words:Wireless Local Area Network (WLAN)/
Indoor fingerprinting localization/
Semi-supervised manifold alignment/
Nonhomogeneous distribution/
Radio map construction
PDF全文下载地址:
https://jeit.ac.cn/article/exportPdf?id=e20ae62b-8a5f-4739-b36d-da2d9928c2ea
