BEM-ANN receiver with linear complexity for severe doubly-selective fading channels
In orthogonal frequency division multiplexing (OFDM) communication over fast time-varying frequency-selective fading channels, also known as doubly-selective channels (DSC), channel estimation (CE) and OFDM demodulation are challenging tasks. This is because high Doppler spread in DSC introduces sev...
| Main Authors: | , , , , |
|---|---|
| Other Authors: | |
| Format: | Journal Article |
| Language: | English |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/182827 |
| _version_ | 1826134345054683136 |
|---|---|
| author | Liu, Xiaobei Guan, Yong Liang Xie, Yihang Qin, Yan Teh, Kah Chan |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Liu, Xiaobei Guan, Yong Liang Xie, Yihang Qin, Yan Teh, Kah Chan |
| author_sort | Liu, Xiaobei |
| collection | NTU |
| description | In orthogonal frequency division multiplexing (OFDM) communication over fast time-varying frequency-selective fading channels, also known as doubly-selective channels (DSC), channel estimation (CE) and OFDM demodulation are challenging tasks. This is because high Doppler spread in DSC introduces severe inter-carrier interference (ICI) that distorts the OFDM data, and spreads the pilot tones away from their designated frequency positions to make channel estimation inaccurate. In this paper, we present a robust OFDM communication receiver for severe DSC, which incorporates a novel deep learning (DL) based channel estimator (CE) and a two-stage equalization architecture named 2s-BEM-ANN. The proposed 2s-BEM-ANN architecture operates in two stages. In the first stage, a pilot-aided CE is performed using an attention neural network (ANN) known as BEM-ANN, followed by equalization using a banded-minimum mean square error (BMMSE) algorithm. In the second stage, data-aided CE is carried out using another BEM-ANN, followed by maximum-likelihood (ML) equalization. Both channel estimators model the DSC using a complex-exponential basis expansion model (CX-BEM), and two training strategies are proposed for the pilot-aided and data-aided BEM-ANNs. Simulation results show that the proposed 2-stage basis expansion model attention neural network (2s-BEM-ANN) receiver significantly improves the bit-error rate (BER) performance over the conventional CE and equalization techniques. Furthermore, the BER performance of the proposed 2s-BEM-ANN approaches very close to the BER lower bound, and without requiring any turbo iteration between the CE and equalization modules. The proposed 2s-BEM-ANN is also robust against signal-to-noise ratio (SNR) and Doppler uncertainties, as well as variations in the channel power-delay profile. Finally, the computational complexity of the proposed 2s-BEM-ANN grows only linearly with the OFDM block length N. |
| first_indexed | 2025-03-09T16:23:43Z |
| format | Journal Article |
| id | ntu-10356/182827 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-03-09T16:23:43Z |
| publishDate | 2025 |
| record_format | dspace |
| spelling | ntu-10356/1828272025-03-07T15:45:33Z BEM-ANN receiver with linear complexity for severe doubly-selective fading channels Liu, Xiaobei Guan, Yong Liang Xie, Yihang Qin, Yan Teh, Kah Chan School of Electrical and Electronic Engineering Temasek Laboratories @ NTU Engineering Doubly-selective channels Orthogonal frequency division multiplexing Deep neural network Attention neural network In orthogonal frequency division multiplexing (OFDM) communication over fast time-varying frequency-selective fading channels, also known as doubly-selective channels (DSC), channel estimation (CE) and OFDM demodulation are challenging tasks. This is because high Doppler spread in DSC introduces severe inter-carrier interference (ICI) that distorts the OFDM data, and spreads the pilot tones away from their designated frequency positions to make channel estimation inaccurate. In this paper, we present a robust OFDM communication receiver for severe DSC, which incorporates a novel deep learning (DL) based channel estimator (CE) and a two-stage equalization architecture named 2s-BEM-ANN. The proposed 2s-BEM-ANN architecture operates in two stages. In the first stage, a pilot-aided CE is performed using an attention neural network (ANN) known as BEM-ANN, followed by equalization using a banded-minimum mean square error (BMMSE) algorithm. In the second stage, data-aided CE is carried out using another BEM-ANN, followed by maximum-likelihood (ML) equalization. Both channel estimators model the DSC using a complex-exponential basis expansion model (CX-BEM), and two training strategies are proposed for the pilot-aided and data-aided BEM-ANNs. Simulation results show that the proposed 2-stage basis expansion model attention neural network (2s-BEM-ANN) receiver significantly improves the bit-error rate (BER) performance over the conventional CE and equalization techniques. Furthermore, the BER performance of the proposed 2s-BEM-ANN approaches very close to the BER lower bound, and without requiring any turbo iteration between the CE and equalization modules. The proposed 2s-BEM-ANN is also robust against signal-to-noise ratio (SNR) and Doppler uncertainties, as well as variations in the channel power-delay profile. Finally, the computational complexity of the proposed 2s-BEM-ANN grows only linearly with the OFDM block length N. Nanyang Technological University Submitted/Accepted version This work was supported by the Temasek Laboratories@NTU Signal Research Programme Phase 4. 2025-03-03T04:04:10Z 2025-03-03T04:04:10Z 2024 Journal Article Liu, X., Guan, Y. L., Xie, Y., Qin, Y. & Teh, K. C. (2024). BEM-ANN receiver with linear complexity for severe doubly-selective fading channels. IEEE Transactions On Vehicular Technology, 73(12), 19005-19018. https://dx.doi.org/10.1109/TVT.2024.3441559 0018-9545 https://hdl.handle.net/10356/182827 10.1109/TVT.2024.3441559 2-s2.0-85201284071 12 73 19005 19018 en DSOCL22291 IEEE Transactions on Vehicular Technology © 2024 IEEE. All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at http://doi.org/10.1109/TVT.2024.3441559 application/pdf |
| spellingShingle | Engineering Doubly-selective channels Orthogonal frequency division multiplexing Deep neural network Attention neural network Liu, Xiaobei Guan, Yong Liang Xie, Yihang Qin, Yan Teh, Kah Chan BEM-ANN receiver with linear complexity for severe doubly-selective fading channels |
| title | BEM-ANN receiver with linear complexity for severe doubly-selective fading channels |
| title_full | BEM-ANN receiver with linear complexity for severe doubly-selective fading channels |
| title_fullStr | BEM-ANN receiver with linear complexity for severe doubly-selective fading channels |
| title_full_unstemmed | BEM-ANN receiver with linear complexity for severe doubly-selective fading channels |
| title_short | BEM-ANN receiver with linear complexity for severe doubly-selective fading channels |
| title_sort | bem ann receiver with linear complexity for severe doubly selective fading channels |
| topic | Engineering Doubly-selective channels Orthogonal frequency division multiplexing Deep neural network Attention neural network |
| url | https://hdl.handle.net/10356/182827 |
| work_keys_str_mv | AT liuxiaobei bemannreceiverwithlinearcomplexityforseveredoublyselectivefadingchannels AT guanyongliang bemannreceiverwithlinearcomplexityforseveredoublyselectivefadingchannels AT xieyihang bemannreceiverwithlinearcomplexityforseveredoublyselectivefadingchannels AT qinyan bemannreceiverwithlinearcomplexityforseveredoublyselectivefadingchannels AT tehkahchan bemannreceiverwithlinearcomplexityforseveredoublyselectivefadingchannels |