《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (12): 3947-3954.DOI: 10.11772/j.issn.1001-9081.2023010005

• 前沿与综合应用 • 上一篇    下一篇

基于测量报告信号聚类的指纹定位方法

张海永1,2, 方贤进1(), 张恩皖3, 李宝玉2, 彭超4, 穆健翔2   

  1. 1.安徽理工大学 计算机科学与工程学院, 安徽 淮南 232001
    2.科大国创云网科技有限公司, 合肥 230088
    3.中国移动通信集团安徽有限公司, 合肥 230088
    4.国防科技大学 电子对抗学院, 合肥 230037
  • 收稿日期:2023-01-04 修回日期:2023-04-23 接受日期:2023-04-24 发布日期:2023-06-06 出版日期:2023-12-10
  • 通讯作者: 方贤进
  • 作者简介:张海永(1992—),男,安徽合肥人,硕士研究生,主要研究方向:运营商大数据、机器学习
    张恩皖(1982—),男,安徽合肥人,硕士,主要研究方向:人工智能、运营商大数据
    李宝玉(1982—),男,安徽安庆人,硕士,主要研究方向:人工智能、运营商大数据
    彭超(1994—),男,安徽合肥人,硕士,主要研究方向:复杂网络、人工智能
    穆健翔(1993—),男,安徽阜阳人,主要研究方向:运营商大数据。
  • 基金资助:
    安徽理工大学创新基金资助项目(2022CX2129);安徽理工大学环境友好材料与职业健康研究院(芜湖)研发专项基金资助项目(ALW2021YF08)

Fingerprint positioning method based on measurement report signal clustering

Haiyong ZHANG1,2, Xianjin FANG1(), Enwan ZHANG3, Baoyu LI2, Chao PENG4, Jianxiang MU2   

  1. 1.School of Computer Science and Engineering,Anhui University of Science and Technology,Huainan Anhui 232001,China
    2.GuoChuang Cloud Technology Company Limited,Hefei Anhui 230088,China
    3.China Mobile Group Anhui Company Limited,Hefei Anhui 230088,China
    4.College of Electronic Countermeasure,National University of Defense Technology,Hefei Anhui 230037,China
  • Received:2023-01-04 Revised:2023-04-23 Accepted:2023-04-24 Online:2023-06-06 Published:2023-12-10
  • Contact: Xianjin FANG
  • About author:ZHANG Haiyong, born in 1992, M. S. candidate. His research interests include operator big data, machine learning.
    ZHANG Enwan, born in 1982, M. S. His research interests include artificial intelligence, operator big data.
    LI Baoyu, born in 1982, M. S. His research interests include artificial intelligence, operator big data.
    PENG Chao, born in 1994, M. S. His research interests include complex network, artificial intelligence.
    MU Jianxiang, born in 1993. His research interests include operator big data.
  • Supported by:
    Anhui University of Science and Technology Innovation Fund(2022CX2129);Research and Development Special Fund of Institute of Environment-friendly Materials and Occupational Health (Wuhu) of Anhui University of Science and Technology(ALW2021YF08)

摘要:

针对基于加权K最近邻(WKNN)和机器学习算法的指纹库定位方法存在精度和定位效率较低的问题,提出一种基于测量报告(MR)信号聚类的指纹定位方法。首先,把MR信号分为室内、道路和室外这3种属性;其次,利用地理信息系统(GIS)信息将栅格分为建筑物、道路和室外子区域,并将不同属性的MR数据落入对应的属性子区域;最后,借助K均值(K-Means)聚类算法对栅格内的MR信号进行聚类分析,以创建子区域下的虚拟子区域,并采用WKNN算法对MR测试样本进行匹配。此外,利用欧氏距离计算平均定位精度,并通过生产环境的一些MR数据测试了所提方法的定位性能。实验结果表明,所提方法的50 m定位误差占比为71.21%,相较于WKNN算法提升了2.64个百分点;平均定位定位误差为44.73 m,相较于WKNN算法降低了7.60 m。所提方法具备良好的定位精度和效率,可满足生产环境中MR数据的定位需求。

关键词: 测量报告, 定位, 信号聚类, 加权K最近邻算法, 欧氏距离

Abstract:

Aiming at the problems of low positioning precision and efficiency of fingerprint positioning methods based on Weighted K-Nearest Neighbor (WKNN) and machine learning algorithms, a fingerprint positioning method based on Measurement Report (MR) signal clustering was proposed. Firstly, MR signals were divided into three attributes: indoor, road and outdoor. Then, by using the Geographic Information System (GIS) information, the grids were divided into building, road and outdoor sub-regions, and MR data with different attributes were placed in the sub-regions with corresponding attributes. Finally, with the help of K-Means clustering algorithm, MR signals in the grid were clustered and analyzed to create virtual sub-regions under the sub-region, and WKNN algorithm was used to match MR test samples. Besides, the average positioning accuracy was calculated by using the Euclidean distance, and the positioning performance of the proposed method was tested by some MR data in the production environment. Experimental results show that the proportion of 50 m positioning error of the proposed method is 71.21%, which is 2.64 percentage points higher than that of WKNN algorithm, and the average positioning error of the proposed method is 44.73 m, which is 7.60 m lower than that of WKNN algorithm. It can be seen that the proposed method has good positioning precision and efficiency, and can meet the positioning requirements of MR data in the production environment.

Key words: Measurement Report (MR), positioning, signal clustering, Weighted K-Nearest Neighbor (WKNN) algorithm, Euclidean distance

中图分类号: