Open Access
ARTICLE
Intelligence-based Channel Equalization for 4x1 SFBC-OFDM Receiver
Divneet Singh Kapoor1,*, Amit Kumar Kohli2
1 Electronics and Communication Engineering Department, Chandigarh University, Mohali-140413, Punjab, India.
2 Electronics and Communication Engineering Department, Thapar Institute of Engineering and Technology, Patiala-147001, India.
* Corresponding Author: Divneet Singh Kapoor,
Intelligent Automation & Soft Computing 2020, 26(3), 439-446. https://doi.org/10.32604/iasc.2020.013920
Abstract
This research paper represents an intelligent receiver based on the artificial-neuralnetworks (ANNs) for a 4x1 space-frequency-block-coded orthogonal-frequencydivision-multiplexing (SFBC-OFDM) system, working under slow time-varying
frequency-selective fading channels. The proposed equalizer directly recovers
transmitted symbols from the received signal, without the explicit requirement of
the channel estimation. The ANN based equalizer is modelled by using feedforward
as well as the recurrent neural-network (NN) architectures, and is trained using
error backpropagation algorithms. The major focus is on efficiency and efficacy of
three different strategies, namely the gradient-descent with momentum (GDM),
resilient-propagation (RProp), and Levenberg-Marquardt (LM) algorithms. The
recurrent neural network architecture based SFBC-OFDM system is found to be an
appropriate choice in terms of the low bit-error-rate performance, while using
different quasi-orthogonal space-time block codes.
Keywords
Cite This Article
D. Singh Kapoor and A. Kumar Kohli, "Intelligence-based channel equalization for 4x1 sfbc-ofdm receiver,"
Intelligent Automation & Soft Computing, vol. 26, no.3, pp. 439–446, 2020.
Citations