北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2019, Vol. 42 ›› Issue (4): 126-132.doi: 10.13190/j.jbupt.2018-298

• 研究报告 • 上一篇    

基于机器学习的无线信道簇的提取与轨迹追踪

张嘉驰1,2, 刘留1, 周涛1, 王凯1, 朴哲岩2   

  1. 1. 北京交通大学 电子信息工程学院, 北京 100044;
    2. 山东交通学院 轨道交通学院, 济南 250357
  • 收稿日期:2018-11-28 出版日期:2019-08-28 发布日期:2019-08-26
  • 通讯作者: 刘留(1981-),男,教授,博士生导师,E-mail:liuliu@bjtu.edu.cn. E-mail:liuliu@bjtu.edu.cn
  • 作者简介:张嘉驰(1991-),男,博士生.
  • 基金资助:
    北京市自然科学基金-海淀原始创新联合基金项目(L172030);中央高校基本科研业务费专项资金项目(2018JBM003);泛网无线通信教育部重点实验室(北京邮电大学)基金项目KFKT-2018105

The Extraction and Tracking Trajectory of Wireless Channel Tap Clusters Based on Machine Learning

ZHANG Jia-chi1,2, LIU Liu1, ZHOU Tao1, WANG Kai1, PIAO Zhe-yan2   

  1. 1. School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing 100044, China;
    2. School of Rail Transportation, Shandong Jiaotong University, Jinan 250357, China
  • Received:2018-11-28 Online:2019-08-28 Published:2019-08-26

摘要: 针对时变无线信道抽头簇的提取和轨迹追踪提出了一种新方法:首先在时延-幅度维上采用反向传播(BP)神经网络对无线信道冲激响应(CIR)进行去噪,然后利用k-means聚类算法对有效抽头信号进行分簇,再用基于密度的空间聚类(DBSCAN)算法去除各个簇峰值抽头中的异常值,最后采用多项式拟合对去除异常值后的簇峰值抽头进行拟合,得到其时间变化轨迹.经过仿真和实测数据验证,该方法得到的簇峰值时间变化轨迹与根据几何关系得到的结果一致.

关键词: 无线信道, 神经网络, 基于密度的聚类, 抽头簇, 轨迹追踪

Abstract: A new method for extraction and tracking trajectory of dynamic wireless channel tap clusters is proposed. First, the channel impulse response (CIR) denoising is achieved by back propagation (BP) neural network in time delay-amplitude dimension. Then effective taps are clustered by k-means clustering algorithm. Next, density-based spatial clustering of applications with noise (DBSCAN) algorithm is applied to remove the abnormal peak taps for every cluster. Finally, the trajectory of cluster peak taps is obtained by polynomial fitting. The simulation result shows that trajectory obtained by proposed method is approximate to geometric calculation result. Moreover, the analysis result of high speed railway measured data is consistent with the actual observations.

Key words: wireless channel, neural network, density-based clustering, tap clusters, tracking trajectory

中图分类号: