Residual learning based convolution neural network for improved channel estimation for VehA channel

Abstract Accurate channel estimation is crucial for reliable communication in orthogonal frequency division multiplexing (OFDM) systems, especially in high-mobility scenarios. Traditional channel estimation techniques, such as least squares (LS) and linear minimum mean square error (LMMSE), face lim...

Full description

Saved in:
Bibliographic Details
Main Authors: Sunita Khichar, Yahui Meng, Abhishek Sharma, Muhammad Saadi, Amir Parniarifard, Sushank Chaudhary
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-07139-7
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849399721252093952
author Sunita Khichar
Yahui Meng
Abhishek Sharma
Muhammad Saadi
Amir Parniarifard
Sushank Chaudhary
author_facet Sunita Khichar
Yahui Meng
Abhishek Sharma
Muhammad Saadi
Amir Parniarifard
Sushank Chaudhary
author_sort Sunita Khichar
collection DOAJ
description Abstract Accurate channel estimation is crucial for reliable communication in orthogonal frequency division multiplexing (OFDM) systems, especially in high-mobility scenarios. Traditional channel estimation techniques, such as least squares (LS) and linear minimum mean square error (LMMSE), face limitations in terms of estimation accuracy and computational complexity. To address these challenges, this paper proposes a novel convolutional neural network (CNN)-based channel estimation framework utilizing residual learning and iterative refinement. The residual learning approach mitigates vanishing gradient issues and enhances convergence speed, while iterative refinement progressively improves the channel estimates. Comprehensive simulations using the VehicularA (VehA) channel model demonstrate that the proposed method achieves up to 30% lower mean squared error (MSE) compared to LS estimation and 15% lower MSE compared to ChannelNet at an SNR of 12 dB. Furthermore, the proposed framework shows an MSE reduction of over 20% compared to FSRCNN at low pilot densities, while maintaining robustness across a wide range of SNRs. With its reduced computational complexity and superior performance, the proposed CNN-based framework is suitable for real-time implementation in next-generation wireless systems, including 5G and beyond.
format Article
id doaj-art-d22aa3fd168840528e868ffa337d4196
institution Kabale University
issn 2045-2322
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-d22aa3fd168840528e868ffa337d41962025-08-20T03:38:15ZengNature PortfolioScientific Reports2045-23222025-07-0115111310.1038/s41598-025-07139-7Residual learning based convolution neural network for improved channel estimation for VehA channelSunita Khichar0Yahui Meng1Abhishek Sharma2Muhammad Saadi3Amir Parniarifard4Sushank Chaudhary5Department of Electrical Engineering, Chulalongkorn UniversitySchool of Science, Guangdong University of Petrochemical TechnologyDepartment of Electronics and Communication Engineering, National Institute of TechnologySchool of Science and Technology, Department of Computer Science, Nottingham Trent UniversityGlasgow College, University of Electronic Science and Technology of ChinaSchool of Computer, Guangdong University of Petrochemical TechnologyAbstract Accurate channel estimation is crucial for reliable communication in orthogonal frequency division multiplexing (OFDM) systems, especially in high-mobility scenarios. Traditional channel estimation techniques, such as least squares (LS) and linear minimum mean square error (LMMSE), face limitations in terms of estimation accuracy and computational complexity. To address these challenges, this paper proposes a novel convolutional neural network (CNN)-based channel estimation framework utilizing residual learning and iterative refinement. The residual learning approach mitigates vanishing gradient issues and enhances convergence speed, while iterative refinement progressively improves the channel estimates. Comprehensive simulations using the VehicularA (VehA) channel model demonstrate that the proposed method achieves up to 30% lower mean squared error (MSE) compared to LS estimation and 15% lower MSE compared to ChannelNet at an SNR of 12 dB. Furthermore, the proposed framework shows an MSE reduction of over 20% compared to FSRCNN at low pilot densities, while maintaining robustness across a wide range of SNRs. With its reduced computational complexity and superior performance, the proposed CNN-based framework is suitable for real-time implementation in next-generation wireless systems, including 5G and beyond.https://doi.org/10.1038/s41598-025-07139-7Channel estimationConvolutional neural networkResidual learningDeep learning5G wireless networks
spellingShingle Sunita Khichar
Yahui Meng
Abhishek Sharma
Muhammad Saadi
Amir Parniarifard
Sushank Chaudhary
Residual learning based convolution neural network for improved channel estimation for VehA channel
Scientific Reports
Channel estimation
Convolutional neural network
Residual learning
Deep learning
5G wireless networks
title Residual learning based convolution neural network for improved channel estimation for VehA channel
title_full Residual learning based convolution neural network for improved channel estimation for VehA channel
title_fullStr Residual learning based convolution neural network for improved channel estimation for VehA channel
title_full_unstemmed Residual learning based convolution neural network for improved channel estimation for VehA channel
title_short Residual learning based convolution neural network for improved channel estimation for VehA channel
title_sort residual learning based convolution neural network for improved channel estimation for veha channel
topic Channel estimation
Convolutional neural network
Residual learning
Deep learning
5G wireless networks
url https://doi.org/10.1038/s41598-025-07139-7
work_keys_str_mv AT sunitakhichar residuallearningbasedconvolutionneuralnetworkforimprovedchannelestimationforvehachannel
AT yahuimeng residuallearningbasedconvolutionneuralnetworkforimprovedchannelestimationforvehachannel
AT abhisheksharma residuallearningbasedconvolutionneuralnetworkforimprovedchannelestimationforvehachannel
AT muhammadsaadi residuallearningbasedconvolutionneuralnetworkforimprovedchannelestimationforvehachannel
AT amirparniarifard residuallearningbasedconvolutionneuralnetworkforimprovedchannelestimationforvehachannel
AT sushankchaudhary residuallearningbasedconvolutionneuralnetworkforimprovedchannelestimationforvehachannel