The TDOA Algorithm Based on BP Neural Network Optimized by Cuckoo Search

被引：5

作者：

Li, Nan ^{[1
]}

Shen, Chong ^{[1
]}

Zhang, Kun ^{[1
,2
]}

Huang, Xing ^{[1
]}

机构：

[1] Hainan Univ, State Key Lab Marine Resources Utilizat South Chi, Haikou 570228, Hainan, Peoples R China

[2] Hainan Trop Ocean Univ, Educ Ctr MTA, Sanya 572022, Hainan, Peoples R China

来源：

2019 INTERNATIONAL CONFERENCE ON ROBOTS & INTELLIGENT SYSTEM (ICRIS 2019) | 2019年

基金：

中国国家自然科学基金;

关键词：

NLOS; CS; BP neural network; TDOA; SYSTEM;

D O I：

10.1109/ICRIS.2019.00138

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

In the UWB indoor positioning system, the Non Line of Sight (NLOS) error usually has a great influence on the positioning of the mobile platform. In order to reduce the influence of NLOS error on the positioning accuracy of mobile stations, this paper proposes a TDOA algorithm based on BP neural network optimized by Cuckoo Search (CS). The algorithm uses the cuckoo search to optimize and train the initial weights of the BP neural network, and then corrects the measured time difference of the Time Difference of Arrival (TDOA) after the training model. Finally, the Chan algorithm is used to perform the positioning calculation according to the corrected TDOA value. The simulation results show that the positioning accuracy of this algorithm is significantly improved compared with the traditional algorithm.

引用

页码：539 / 542

页数：4

共 11 条

[1] Real-Valued Sparse DOA Estimation for MIMO Array System Under Unknown Nonuniform Noise [J].