Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification

Thien Huynh-The; Quoc Viet Pham; Thai Hoc Vu; Daniel Benevides Da Costa; Van Phuc Hoang

doi:10.1109/SSP53291.2023.10208054

Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification

Thien Huynh-The^*
, Quoc Viet Pham
, Thai Hoc Vu
, Daniel Benevides Da Costa
, Van Phuc Hoang

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

17 Scopus citations

Abstract

The paper presents an intelligent spectrum sensing approach for next-generation wireless networks by exploiting deep learning, in which we develop a deep convolutional network (ConvNet) to automatically identify Fifth Generation New Radio (5G NR) and Long-Term Evolution (LTE) signals under standards-specified channel models with diversified RF impairments. In particular, we design a semantic segmentation ConvNet to detect and localize the spectral content of 5G NR and LTE in a synthetic signal featured by spectrum occupancy. A received signal is first converted by a short-time Fourier transform and represented as a wideband spectrogram image which is then passed through the ConvNet, incorporated by DeepLabv3+ and ResNet18 to improve the accuracy of pixel-wise segmentation to further increase the accuracy of signal identification. In the simulations, our ConvNet achieves around 95% mean accuracy and 91% mean intersection-over-union (IoU) at medium SNR level and demonstrates robustness under various practical channel impairments.

Original language	English
Title of host publication	Proceedings of the 22nd IEEE Statistical Signal Processing Workshop, SSP 2023
Publisher	IEEE Computer Society
Pages	140-144
Number of pages	5
ISBN (Electronic)	9781665452458
DOIs	https://doi.org/10.1109/SSP53291.2023.10208054
State	Published - 2023
Externally published	Yes
Event	22nd IEEE Statistical Signal Processing Workshop, SSP 2023 - Hanoi, Viet Nam Duration: 2 Jul 2023 → 5 Jul 2023

Publication series

Name	IEEE Workshop on Statistical Signal Processing Proceedings
Volume	2023-July

Conference

Conference	22nd IEEE Statistical Signal Processing Workshop, SSP 2023
Country/Territory	Viet Nam
City	Hanoi
Period	2/07/23 → 5/07/23

Bibliographical note

Publisher Copyright:
© 2023 IEEE.

Keywords

5G NR
cognitive ration
deep learning
encoder-decoder architecture
signal identification
spectrum sensing

ASJC Scopus subject areas

Electrical and Electronic Engineering
Applied Mathematics
Signal Processing
Computer Science Applications

Access to Document

10.1109/SSP53291.2023.10208054

Cite this

Huynh-The, T., Pham, Q. V., Vu, T. H., Da Costa, D. B., & Hoang, V. P. (2023). Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification. In Proceedings of the 22nd IEEE Statistical Signal Processing Workshop, SSP 2023 (pp. 140-144). (IEEE Workshop on Statistical Signal Processing Proceedings; Vol. 2023-July). IEEE Computer Society. https://doi.org/10.1109/SSP53291.2023.10208054

@inproceedings{792b9214e6ea4a30aef251df532f69e6,

title = "Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification",

abstract = "The paper presents an intelligent spectrum sensing approach for next-generation wireless networks by exploiting deep learning, in which we develop a deep convolutional network (ConvNet) to automatically identify Fifth Generation New Radio (5G NR) and Long-Term Evolution (LTE) signals under standards-specified channel models with diversified RF impairments. In particular, we design a semantic segmentation ConvNet to detect and localize the spectral content of 5G NR and LTE in a synthetic signal featured by spectrum occupancy. A received signal is first converted by a short-time Fourier transform and represented as a wideband spectrogram image which is then passed through the ConvNet, incorporated by DeepLabv3+ and ResNet18 to improve the accuracy of pixel-wise segmentation to further increase the accuracy of signal identification. In the simulations, our ConvNet achieves around 95\% mean accuracy and 91\% mean intersection-over-union (IoU) at medium SNR level and demonstrates robustness under various practical channel impairments.",

keywords = "5G NR, cognitive ration, deep learning, encoder-decoder architecture, signal identification, spectrum sensing",

author = "Thien Huynh-The and Pham, \{Quoc Viet\} and Vu, \{Thai Hoc\} and \{Da Costa\}, \{Daniel Benevides\} and Hoang, \{Van Phuc\}",

note = "Publisher Copyright: {\textcopyright} 2023 IEEE.; 22nd IEEE Statistical Signal Processing Workshop, SSP 2023 ; Conference date: 02-07-2023 Through 05-07-2023",

year = "2023",

doi = "10.1109/SSP53291.2023.10208054",

language = "English",

series = "IEEE Workshop on Statistical Signal Processing Proceedings",

publisher = "IEEE Computer Society",

pages = "140--144",

booktitle = "Proceedings of the 22nd IEEE Statistical Signal Processing Workshop, SSP 2023",

address = "United States",

}

Huynh-The, T, Pham, QV, Vu, TH, Da Costa, DB & Hoang, VP 2023, Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification. in Proceedings of the 22nd IEEE Statistical Signal Processing Workshop, SSP 2023. IEEE Workshop on Statistical Signal Processing Proceedings, vol. 2023-July, IEEE Computer Society, pp. 140-144, 22nd IEEE Statistical Signal Processing Workshop, SSP 2023, Hanoi, Viet Nam, 2/07/23. https://doi.org/10.1109/SSP53291.2023.10208054

Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification. / Huynh-The, Thien; Pham, Quoc Viet; Vu, Thai Hoc et al.
Proceedings of the 22nd IEEE Statistical Signal Processing Workshop, SSP 2023. IEEE Computer Society, 2023. p. 140-144 (IEEE Workshop on Statistical Signal Processing Proceedings; Vol. 2023-July).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification

AU - Huynh-The, Thien

AU - Pham, Quoc Viet

AU - Vu, Thai Hoc

AU - Da Costa, Daniel Benevides

AU - Hoang, Van Phuc

PY - 2023

Y1 - 2023

N2 - The paper presents an intelligent spectrum sensing approach for next-generation wireless networks by exploiting deep learning, in which we develop a deep convolutional network (ConvNet) to automatically identify Fifth Generation New Radio (5G NR) and Long-Term Evolution (LTE) signals under standards-specified channel models with diversified RF impairments. In particular, we design a semantic segmentation ConvNet to detect and localize the spectral content of 5G NR and LTE in a synthetic signal featured by spectrum occupancy. A received signal is first converted by a short-time Fourier transform and represented as a wideband spectrogram image which is then passed through the ConvNet, incorporated by DeepLabv3+ and ResNet18 to improve the accuracy of pixel-wise segmentation to further increase the accuracy of signal identification. In the simulations, our ConvNet achieves around 95% mean accuracy and 91% mean intersection-over-union (IoU) at medium SNR level and demonstrates robustness under various practical channel impairments.

AB - The paper presents an intelligent spectrum sensing approach for next-generation wireless networks by exploiting deep learning, in which we develop a deep convolutional network (ConvNet) to automatically identify Fifth Generation New Radio (5G NR) and Long-Term Evolution (LTE) signals under standards-specified channel models with diversified RF impairments. In particular, we design a semantic segmentation ConvNet to detect and localize the spectral content of 5G NR and LTE in a synthetic signal featured by spectrum occupancy. A received signal is first converted by a short-time Fourier transform and represented as a wideband spectrogram image which is then passed through the ConvNet, incorporated by DeepLabv3+ and ResNet18 to improve the accuracy of pixel-wise segmentation to further increase the accuracy of signal identification. In the simulations, our ConvNet achieves around 95% mean accuracy and 91% mean intersection-over-union (IoU) at medium SNR level and demonstrates robustness under various practical channel impairments.

KW - 5G NR

KW - cognitive ration

KW - deep learning

KW - encoder-decoder architecture

KW - signal identification

KW - spectrum sensing

UR - https://www.scopus.com/pages/publications/85168917677

U2 - 10.1109/SSP53291.2023.10208054

DO - 10.1109/SSP53291.2023.10208054

M3 - Conference contribution

AN - SCOPUS:85168917677

T3 - IEEE Workshop on Statistical Signal Processing Proceedings

SP - 140

EP - 144

BT - Proceedings of the 22nd IEEE Statistical Signal Processing Workshop, SSP 2023

PB - IEEE Computer Society

T2 - 22nd IEEE Statistical Signal Processing Workshop, SSP 2023

Y2 - 2 July 2023 through 5 July 2023

ER -

Intelligent Spectrum Sensing with ConvNet for 5G and LTE Signals Identification

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Fingerprint

Cite this