This paper proposes a novel Deep Learning (DL)-based approach for classifying the radio-access technology (RAT) of wireless emitters. The approach improves computational efficiency and accuracy under harsh channel conditions with respect to existing approaches. Intelligent spectrum monitoring is a crucial enabler for emerging wireless access environments that supports sharing of (and dynamic access to) spectral resources between multiple RATs and user classes. Emitter classification enables monitoring the varying patterns of spectral occupancy across RATs, which is instrumental in optimizing spectral utilization and interference management and supporting efficient enforcement of access regulations. Existing emitter classification approaches successfully leverage convolutional neural networks (CNNs) to recognize RAT visual features in spectrograms and other time-frequency representations; however, the corresponding classification accuracy degrades severely under harsh propagation conditions, and the computational cost of CNNs may limit their adoption in resource-constrained network edge scenarios. In this work, we propose a novel emitter classification solution consisting of a Denoising Autoencoder (DAE), which feeds a CNN classifier with lower di-mensionality, denoised representations of channel-corrupted spectrograms. We demonstrate—using a standard-compliant simulation of various RATs including LTE and four latest Wi-Fi standards—that in harsh channel conditions including non-line-of-sight, large scale fading, and mobility-induced Doppler shifts, our proposed solution outperforms a wide range of standalone CNNs and other machine learning models while requiring significantly less computational resources. The maximum achieved accuracy of the emitter classifier is 100%, and the average accuracy is 91% across all the propagation conditions.

Robust computationally-efficient wireless emitter classification using autoencoders and convolutional neural networks / E. Almazrouei, G. Gianini, N. Almoosa, E. Damiani. - In: SENSORS. - ISSN 1424-8220. - 21:7(2021 Apr 01), p. 2414.2414.

Robust computationally-efficient wireless emitter classification using autoencoders and convolutional neural networks

G. Gianini
Secondo
;
E. Damiani
Ultimo
2021

Abstract

This paper proposes a novel Deep Learning (DL)-based approach for classifying the radio-access technology (RAT) of wireless emitters. The approach improves computational efficiency and accuracy under harsh channel conditions with respect to existing approaches. Intelligent spectrum monitoring is a crucial enabler for emerging wireless access environments that supports sharing of (and dynamic access to) spectral resources between multiple RATs and user classes. Emitter classification enables monitoring the varying patterns of spectral occupancy across RATs, which is instrumental in optimizing spectral utilization and interference management and supporting efficient enforcement of access regulations. Existing emitter classification approaches successfully leverage convolutional neural networks (CNNs) to recognize RAT visual features in spectrograms and other time-frequency representations; however, the corresponding classification accuracy degrades severely under harsh propagation conditions, and the computational cost of CNNs may limit their adoption in resource-constrained network edge scenarios. In this work, we propose a novel emitter classification solution consisting of a Denoising Autoencoder (DAE), which feeds a CNN classifier with lower di-mensionality, denoised representations of channel-corrupted spectrograms. We demonstrate—using a standard-compliant simulation of various RATs including LTE and four latest Wi-Fi standards—that in harsh channel conditions including non-line-of-sight, large scale fading, and mobility-induced Doppler shifts, our proposed solution outperforms a wide range of standalone CNNs and other machine learning models while requiring significantly less computational resources. The maximum achieved accuracy of the emitter classifier is 100%, and the average accuracy is 91% across all the propagation conditions.
Classification; Convolutional neural networks; Deep Learning; Denoising Autoencoders; IEEE Wi-Fi protocols; LTE; Spectrum management
Settore INF/01 - Informatica
Settore ING-INF/05 - Sistemi di Elaborazione delle Informazioni
1-apr-2021
Article (author)
File in questo prodotto:
File Dimensione Formato  
sensors-21-02414-v2.pdf

accesso aperto

Tipologia: Publisher's version/PDF
Dimensione 8.3 MB
Formato Adobe PDF
8.3 MB Adobe PDF Visualizza/Apri
Pubblicazioni consigliate

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2434/848839
Citazioni
  • ???jsp.display-item.citation.pmc??? 0
  • Scopus 7
  • ???jsp.display-item.citation.isi??? 4
social impact