A Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR Conditions

The use of Low-Power Wide Area Network (LPWAN) technologies, such as Long Range (LoRa), Sigfox, and IEEE 802.15.4g (ZigBee), has grown significantly, addressing a wide range of applications including smart metering, agriculture, smart homes, and healthcare. These technologies are valued for their si...

Full description

Saved in:
Bibliographic Details
Main Authors: Ife Olalekan Ebo, Idowu Ajayi, Lina Mroueh, Youmni Ziade, Sylvain Azarian
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Access
Subjects:
Online Access:https://ieeexplore.ieee.org/document/10980283/
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849722153734242304
author Ife Olalekan Ebo
Idowu Ajayi
Lina Mroueh
Youmni Ziade
Sylvain Azarian
author_facet Ife Olalekan Ebo
Idowu Ajayi
Lina Mroueh
Youmni Ziade
Sylvain Azarian
author_sort Ife Olalekan Ebo
collection DOAJ
description The use of Low-Power Wide Area Network (LPWAN) technologies, such as Long Range (LoRa), Sigfox, and IEEE 802.15.4g (ZigBee), has grown significantly, addressing a wide range of applications including smart metering, agriculture, smart homes, and healthcare. These technologies are valued for their simplicity, flexible connectivity, low power consumption, efficient modulation techniques, and moderate data rates. As a result, they can coexist within the same environment, serving either similar or distinct applications. However, the increasing deployment of devices and technologies has amplified the likelihood of interference between them, leading to performance degradation, particularly in real-world scenarios under challenging conditions where noise power surpasses signal power. The rapid proliferation of these technologies, especially within unlicensed Industrial, Scientific, and Medical (ISM) frequency bands, underscores the need for effective techniques to ensure seamless coexistence without disrupting communication. To address this challenge, we investigate the role of data representation and propose a Channel Attention-based Denoising Autoencoder U-Net and Classifier (UNA-DAEC). This model is designed to denoise multi-label LPWAN signals affected by white Gaussian noise and accurately classify overlapping transmissions, specifically IEEE 802.15.4g, Sigfox, and LoRa signals, within the same environment. The primary objective of UNA-DAEC is to achieve reliable signal classification in low Signal-to-Noise Ratio (SNR) conditions. This is achieved by first denoising the noisy signals to obtain optimal representations, enabling high classification accuracy with a single forward and backward propagation. Our results further demonstrate that data representation plays a critical role in identifying and classifying LPWAN signals, particularly in challenging low-SNR environments, with a significant performance of 44%, 7%, and 26% over CNN-based IQ, CNN-based FFT and DAE+Classifier methods, respectively, at -10 dB SNR.
format Article
id doaj-art-28eff17fa53b4f2e95198ac46dc3b9e6
institution DOAJ
issn 2169-3536
language English
publishDate 2025-01-01
publisher IEEE
record_format Article
series IEEE Access
spelling doaj-art-28eff17fa53b4f2e95198ac46dc3b9e62025-08-20T03:11:25ZengIEEEIEEE Access2169-35362025-01-0113773177733310.1109/ACCESS.2025.356585310980283A Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR ConditionsIfe Olalekan Ebo0https://orcid.org/0000-0001-5105-7857Idowu Ajayi1https://orcid.org/0000-0002-3345-4442Lina Mroueh2https://orcid.org/0000-0002-3051-0760Youmni Ziade3Sylvain Azarian4Laboratoire d’Informatique, Signal et Image, Électronique et Télécommunications (LISITE), ISEP, Issy-les-Moulineaux, FranceLaboratoire d’Informatique, Signal et Image, Électronique et Télécommunications (LISITE), ISEP, Issy-les-Moulineaux, FranceLaboratoire d’Informatique, Signal et Image, Électronique et Télécommunications (LISITE), ISEP, Issy-les-Moulineaux, FranceL’Agence Nationale des Fréquences, Maisons-Alfort, FranceSDR Technologies, Rambouillet, FranceThe use of Low-Power Wide Area Network (LPWAN) technologies, such as Long Range (LoRa), Sigfox, and IEEE 802.15.4g (ZigBee), has grown significantly, addressing a wide range of applications including smart metering, agriculture, smart homes, and healthcare. These technologies are valued for their simplicity, flexible connectivity, low power consumption, efficient modulation techniques, and moderate data rates. As a result, they can coexist within the same environment, serving either similar or distinct applications. However, the increasing deployment of devices and technologies has amplified the likelihood of interference between them, leading to performance degradation, particularly in real-world scenarios under challenging conditions where noise power surpasses signal power. The rapid proliferation of these technologies, especially within unlicensed Industrial, Scientific, and Medical (ISM) frequency bands, underscores the need for effective techniques to ensure seamless coexistence without disrupting communication. To address this challenge, we investigate the role of data representation and propose a Channel Attention-based Denoising Autoencoder U-Net and Classifier (UNA-DAEC). This model is designed to denoise multi-label LPWAN signals affected by white Gaussian noise and accurately classify overlapping transmissions, specifically IEEE 802.15.4g, Sigfox, and LoRa signals, within the same environment. The primary objective of UNA-DAEC is to achieve reliable signal classification in low Signal-to-Noise Ratio (SNR) conditions. This is achieved by first denoising the noisy signals to obtain optimal representations, enabling high classification accuracy with a single forward and backward propagation. Our results further demonstrate that data representation plays a critical role in identifying and classifying LPWAN signals, particularly in challenging low-SNR environments, with a significant performance of 44%, 7%, and 26% over CNN-based IQ, CNN-based FFT and DAE+Classifier methods, respectively, at -10 dB SNR.https://ieeexplore.ieee.org/document/10980283/Autoencoderchannel attentionconvolutional neural networkdeep learningdenoising auto-encoderlow-power wireless area network
spellingShingle Ife Olalekan Ebo
Idowu Ajayi
Lina Mroueh
Youmni Ziade
Sylvain Azarian
A Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR Conditions
IEEE Access
Autoencoder
channel attention
convolutional neural network
deep learning
denoising auto-encoder
low-power wireless area network
title A Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR Conditions
title_full A Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR Conditions
title_fullStr A Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR Conditions
title_full_unstemmed A Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR Conditions
title_short A Channel Attention-Based Denoising Autoencoder U-Net and Classifier (UNA-DAEC) for Signal Identification Under Challenging SNR Conditions
title_sort channel attention based denoising autoencoder u net and classifier una daec for signal identification under challenging snr conditions
topic Autoencoder
channel attention
convolutional neural network
deep learning
denoising auto-encoder
low-power wireless area network
url https://ieeexplore.ieee.org/document/10980283/
work_keys_str_mv AT ifeolalekanebo achannelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT idowuajayi achannelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT linamroueh achannelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT youmniziade achannelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT sylvainazarian achannelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT ifeolalekanebo channelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT idowuajayi channelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT linamroueh channelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT youmniziade channelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions
AT sylvainazarian channelattentionbaseddenoisingautoencoderunetandclassifierunadaecforsignalidentificationunderchallengingsnrconditions