A pilot-aided neural network for modeling and identification of nonlinear satellite mobile channels

被引：0

作者：

Ibnkahla, Mohamed ^{[1
]}

Cao, Yu ^{[1
]}

机构：

[1] Queens Univ, Dept Elect & Comp Engn, Kingston, ON K7L 3N6, Canada

来源：

2008 CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, VOLS 1-4 | 2008年

关键词：

neural networks; satellite communications; MIMO systems;

D O I：

暂无

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

We propose a neural network pilot symbol-aided (NN-PSA) receiver for nonlinear satellite mobile channels. The NN-PSA receiver is composed of a two-layer memory-less neural network (NN) nonlinear identifier and a pilot symbol-aided (PSA) fading estimator. In comparison with traditional techniques, the main advantage of this receiver is that it is able to identify and track both the nonlinearity and the time-varying fading simultaneously without prior knowledge of them. The Natural Gradient (NG) descent is used for NN training, which shows superior performance in comparison to the classical back propagation (BP) algorithm. The paper is supported with simulation results for 16-QAM modulation in terms of symbol error rate (SER) and mean square error (MSE) performance.

引用

页码：1470 / 1473

页数：4

共 50 条

[21] Comparison of traditional and neural network approaches to stochastic nonlinear system identification [J].

Kil To Chong ;

Alexander G. Parlos .

KSME International Journal, 1997, 11 :267-278

[22] The Reiterated Neural Network Parametric Identification of Nonlinear Dynamic Models of Objects [J].

Volkov, A. V. ;

Semenov, A. D. ;

Staroverov, B. A. .

ADVANCES IN AUTOMATION III, 2022, 857 :34-42

[23] Comparison of traditional and neural network approaches to stochastic nonlinear system identification [J].

Chong, KT ;

Parlos, AG .

KSME INTERNATIONAL JOURNAL, 1997, 11 (03) :267-278

[24] More transparent neural network approach for modeling nonlinear hysteretic systems [J].

Pei, JS ;

Smyth, AW .

SMART STRUCTURES AND MATERIALS 2003: SMART SYSTEMS AND NONDESTRUCTIVE EVALUATION FOR CIVIL INFRASTRUCTURES, 2003, 5057 :516-523

[25] Nonlinear modeling and fault detection using fuzzy-neural network [J].

Taniguchi, S ;

Akhmetov, DF ;

Dote, Y ;

Ovaska, SJ .

INTELLIGENT SYSTEMS, 2000, :96-100

[26] State space neural network with nonlinear physics for mechanical system modeling [J].

Eischens, Reese ;

Li, Tao ;

Vogl, Gregory W. ;

Cai, Yi ;

Qu, Yongzhi .

RELIABILITY ENGINEERING & SYSTEM SAFETY, 2025, 259

[27] A Review of Neural Network Based Techniques for Nonlinear Microwave Device Modeling [J].

Liu, Wenyuan ;

Na, Weicong ;

Zhu, Lin ;

Zhang, Qi-Jun .

2016 IEEE MTT-S INTERNATIONAL CONFERENCE ON NUMERICAL ELECTROMAGNETIC AND MULTIPHYSICS MODELING AND OPTIMIZATION (NEMO), 2016,

[28] Adjoint recurrent neural network technique for nonlinear electronic component modeling [J].

Naghibi, Zohreh ;

Sadrossadat, Sayed Alireza ;

Safari, Saeed .

INTERNATIONAL JOURNAL OF CIRCUIT THEORY AND APPLICATIONS, 2022, 50 (04) :1119-1129

[29] Using Virtual Data Effects to Stabilize Pilot Run Neural Network Modeling [J].

Lin, Yao-San ;

Tsai, Tung-I .

JOURNAL OF GREY SYSTEM, 2014, 26 (02) :84-94

[30] Using Virtual Data Effects To Stabilize Pilot Run Neural Network Modeling [J].

Lin, Yao-San ;

Tsai, Tung-, I .

PROCEEDINGS OF 2013 IEEE INTERNATIONAL CONFERENCE ON GREY SYSTEMS AND INTELLIGENT SERVICES (GSIS), 2013, :463-468

← 1 2 3 4 5 →