Journal of Computer Applications ›› 2012, Vol. 32 ›› Issue (09): 2426-2428.DOI: 10.3724/SP.J.1087.2012.02426

• Network and communications • Previous Articles     Next Articles

Location algorithm based on BP neural network in OFDM system

MAO Yong-yi1,LI Cheng1*,ZHANG Hong-jun2   

  1. 1.School of Electronic Engineering,Xi'an University of Posts and Telecommunications,Xi'an Shaanxi 710061,China;
    2.School of Communication and Information Engineering,Xi'an University of Posts and Telecommunications,Xi'an Shaanxi 710061,China
  • Received:2012-03-23 Revised:2012-05-03 Online:2012-09-01 Published:2012-09-01
  • Contact: Cheng LI



  1. 1.西安邮电学院 电子工程学院,西安710061;
    2.西安邮电学院 通信与信息工程学院,西安710061
  • 通讯作者: 李成
  • 作者简介:毛永毅(1969-),男,湖南长沙人,教授,博士,主要研究方向:通信信号处理、移动台定位; 李成(1987-),男,江苏盐城人,硕士研究生,主要研究方向:通信信号处理、移动台定位; 张宏君(1987-),男,陕西渭南人,硕士研究生,主要研究方向:通信信号处理、移动台定位。
  • 基金资助:


Abstract: For the purpose of reducing multi-path interference for positioning accuracy in Orthogonal Frequency Division Multiplexing (OFDM) systems, a location algorithm based on Back Propagation (BP) neural networks was proposed. MUltiple SIgnal Classification (MUSIC) algorithm was used to estimate the Time Of Arrival (TOA) of the first arrival path and calculate the Time Difference Of Arrival (TDOA). Then BP neural network was used to correct the TDOA. Finally Chan algorithm was used to determine the location of the mobile station. The location algorithm was simulated in multi-path environment. The simulation results show that this algorithm can effectively reduce the effect of the multi-path interference and the performance is better than Least Square (LS) algorithm, Chan algorithm and Taylor algorithm.

Key words: Orthogonal Frequency Division Multiplexing (OFDM), Time Difference Of Arrival (TDOA), neural network, MUltiple SIgnal Classification (MUSIC) algorithm, multi-path interference

摘要: 为了减小正交频分复用(OFDM)系统中多径干扰对定位精度的影响,提出一种基于后向传播(BP)神经网络的定位算法。该算法采用多重信号分类(MUSIC)算法估计OFDM信号首径的到达时间(TOA),再计算出到达时间差(TDOA),然后利用BP神经网络对其进行修正,最后使用Chan算法确定移动台的位置。在多径环境下对算法进行仿真,仿真结果表明该算法能够有效地降低多径干扰的影响,性能优于最小二乘(LS)算法、Chan算法和泰勒算法。

关键词: 正交频分复用, 到达时间差, 神经网络, 多重信号分类算法, 多径干扰

CLC Number: