Neural-Network-Based Equalization and Detection for Underwater Acoustic Orthogonal Frequency Division Multiplexing Communications: A Low-Complexity Approach
The performance of the underwater acoustic (UWA) orthogonal frequency division multiplexing (OFDM) system is often restrained by time-varying channels with large delays. The existing frequency domain equalizers do not work well because of the high complexity and difficulty of finding the real-time s...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2023-07-01
|
Series: | Remote Sensing |
Subjects: | |
Online Access: | https://www.mdpi.com/2072-4292/15/15/3796 |
_version_ | 1797586069849374720 |
---|---|
author | Mingzhang Zhou Junfeng Wang Xiao Feng Haixin Sun Jie Qi Rongbin Lin |
author_facet | Mingzhang Zhou Junfeng Wang Xiao Feng Haixin Sun Jie Qi Rongbin Lin |
author_sort | Mingzhang Zhou |
collection | DOAJ |
description | The performance of the underwater acoustic (UWA) orthogonal frequency division multiplexing (OFDM) system is often restrained by time-varying channels with large delays. The existing frequency domain equalizers do not work well because of the high complexity and difficulty of finding the real-time signal-to-noise ratio. To solve these problems, we propose a low-complexity neural network (NN)-based scheme for joint equalization and detection. A simple NN structure is built to yield the detected symbols with the joint input of the segmented channel response and received symbol. The coherence bandwidth is investigated to find the optimal hyperparameters. By being completely trained offline with real channels, the proposed detector is applied independently in both simulations and sea trials. The results show that the proposed detector outperforms the ZF and MMSE equalizers and extreme learning machine (ELM)-based detectors in both the strongly reflected channels of the pool and time-variant channels of the shallow sea. The complexity of the proposed network is lower than the MMSE and ELM-based receiver. |
first_indexed | 2024-03-11T00:17:06Z |
format | Article |
id | doaj.art-0a7d75a7d228492c86ff9a85ade498a8 |
institution | Directory Open Access Journal |
issn | 2072-4292 |
language | English |
last_indexed | 2024-03-11T00:17:06Z |
publishDate | 2023-07-01 |
publisher | MDPI AG |
record_format | Article |
series | Remote Sensing |
spelling | doaj.art-0a7d75a7d228492c86ff9a85ade498a82023-11-18T23:30:56ZengMDPI AGRemote Sensing2072-42922023-07-011515379610.3390/rs15153796Neural-Network-Based Equalization and Detection for Underwater Acoustic Orthogonal Frequency Division Multiplexing Communications: A Low-Complexity ApproachMingzhang Zhou0Junfeng Wang1Xiao Feng2Haixin Sun3Jie Qi4Rongbin Lin5School of Informatics, Xiamen University, Xiamen 361005, ChinaKey Laboratory of Southeast Coast Marine Information Intelligent Perception and Application, Ministry of Natural Resources, Zhangzhou 363000, ChinaKey Laboratory of Broadband Wireless Communication and Sensor Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210023, ChinaSchool of Informatics, Xiamen University, Xiamen 361005, ChinaSchool of Electornic Science and Engineering (National Model Microelectronics College), Xiamen University, Xiamen 361005, ChinaSchool of Informatics, Xiamen University, Xiamen 361005, ChinaThe performance of the underwater acoustic (UWA) orthogonal frequency division multiplexing (OFDM) system is often restrained by time-varying channels with large delays. The existing frequency domain equalizers do not work well because of the high complexity and difficulty of finding the real-time signal-to-noise ratio. To solve these problems, we propose a low-complexity neural network (NN)-based scheme for joint equalization and detection. A simple NN structure is built to yield the detected symbols with the joint input of the segmented channel response and received symbol. The coherence bandwidth is investigated to find the optimal hyperparameters. By being completely trained offline with real channels, the proposed detector is applied independently in both simulations and sea trials. The results show that the proposed detector outperforms the ZF and MMSE equalizers and extreme learning machine (ELM)-based detectors in both the strongly reflected channels of the pool and time-variant channels of the shallow sea. The complexity of the proposed network is lower than the MMSE and ELM-based receiver.https://www.mdpi.com/2072-4292/15/15/3796underwater acoustic communicationsubcarrier multiplexingneural networkscoherence bandwidthequalizersdetectors |
spellingShingle | Mingzhang Zhou Junfeng Wang Xiao Feng Haixin Sun Jie Qi Rongbin Lin Neural-Network-Based Equalization and Detection for Underwater Acoustic Orthogonal Frequency Division Multiplexing Communications: A Low-Complexity Approach Remote Sensing underwater acoustic communication subcarrier multiplexing neural networks coherence bandwidth equalizers detectors |
title | Neural-Network-Based Equalization and Detection for Underwater Acoustic Orthogonal Frequency Division Multiplexing Communications: A Low-Complexity Approach |
title_full | Neural-Network-Based Equalization and Detection for Underwater Acoustic Orthogonal Frequency Division Multiplexing Communications: A Low-Complexity Approach |
title_fullStr | Neural-Network-Based Equalization and Detection for Underwater Acoustic Orthogonal Frequency Division Multiplexing Communications: A Low-Complexity Approach |
title_full_unstemmed | Neural-Network-Based Equalization and Detection for Underwater Acoustic Orthogonal Frequency Division Multiplexing Communications: A Low-Complexity Approach |
title_short | Neural-Network-Based Equalization and Detection for Underwater Acoustic Orthogonal Frequency Division Multiplexing Communications: A Low-Complexity Approach |
title_sort | neural network based equalization and detection for underwater acoustic orthogonal frequency division multiplexing communications a low complexity approach |
topic | underwater acoustic communication subcarrier multiplexing neural networks coherence bandwidth equalizers detectors |
url | https://www.mdpi.com/2072-4292/15/15/3796 |
work_keys_str_mv | AT mingzhangzhou neuralnetworkbasedequalizationanddetectionforunderwateracousticorthogonalfrequencydivisionmultiplexingcommunicationsalowcomplexityapproach AT junfengwang neuralnetworkbasedequalizationanddetectionforunderwateracousticorthogonalfrequencydivisionmultiplexingcommunicationsalowcomplexityapproach AT xiaofeng neuralnetworkbasedequalizationanddetectionforunderwateracousticorthogonalfrequencydivisionmultiplexingcommunicationsalowcomplexityapproach AT haixinsun neuralnetworkbasedequalizationanddetectionforunderwateracousticorthogonalfrequencydivisionmultiplexingcommunicationsalowcomplexityapproach AT jieqi neuralnetworkbasedequalizationanddetectionforunderwateracousticorthogonalfrequencydivisionmultiplexingcommunicationsalowcomplexityapproach AT rongbinlin neuralnetworkbasedequalizationanddetectionforunderwateracousticorthogonalfrequencydivisionmultiplexingcommunicationsalowcomplexityapproach |