Lightweight Machine Learning for Efficient Frequency-Offset-Aware Demodulation

Siyari, P; Rahbari, H; Krunz, M

Lightweight Machine Learning for Efficient Frequency-Offset-Aware Demodulation

Siyari, P Rahbari, H Krunz, M

Permalink

Publication Type:: Journal Article
Citation:: IEEE Journal on Selected Areas in Communications, 2019, 37 (11), pp. 2544 - 2558
Issue Date:: 2019-11-01

Closed Access

	Filename	Description	Size
	08792186.pdf	Published Version	2.24 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Siyari, P	en_US
dc.contributor.author	Rahbari, H	en_US
dc.contributor.author	Krunz, M	en_US
dc.date.accessioned	2020-04-14T07:06:32Z
dc.date.available	2020-04-14T07:06:32Z
dc.date.issued	2019-11-01	en_US
dc.identifier.citation	IEEE Journal on Selected Areas in Communications, 2019, 37 (11), pp. 2544 - 2558	en_US
dc.identifier.issn	0733-8716	en_US
dc.identifier.uri	http://hdl.handle.net/10453/139989
dc.description.abstract	© 2019 IEEE. Carrier frequency offset (CFO) arises from the intrinsic mismatch between the oscillators of a wireless transmitter and the corresponding receiver, as well as their relative motion (i.e., Doppler effect). Despite advances in CFO estimation and tracking techniques, estimation errors are still present. Residual CFO creates a time-varying phase error, which degrades the decoder's performance by increasing the symbol error rate. The impact is particularly visible in dense constellation maps (e.g., high-order QAM modulation), often used in modern wireless systems such as 5G NR, 802.11ax, and mmWave, as well as in physical security techniques, such as modulation obfuscation (MO). In this paper, we first derive the probability distribution function for the residual CFO under Gaussian noise. Using this distribution, we compute the maximum-likelihood demodulation boundaries for OFDM signals in a non-closed form. For modulation schemes with unequal-amplitude reference constellation points (e.g., 16-QAM and higher, APSK, etc.), the 'optimal' boundaries have irregular shapes, and more importantly, they depend on the time since the last CFO correction instance, e.g., reception of frame preamble. To approximate the optimal boundaries and provide a practical (real-time) demodulation scheme, we explore machine learning techniques, specifically, support vector machine (SVM). Our SVM approach exhibits better accuracy and lower complexity in the test phase than other state-of-the-art machine-learning approaches. As a case study, we apply our CFO-aware demodulation to enhance the performance of a MO technique. Our analytical results show a gain of up to 3dB over conventional demodulation schemes, which exceeds 3dB in complete system simulations. Finally, we implement our scheme on USRPs and experimentally corroborate our analytic and simulation-based findings.	en_US
dc.relation.ispartof	IEEE Journal on Selected Areas in Communications	en_US
dc.relation.isbasedon	10.1109/JSAC.2019.2933956	en_US
dc.rights	info:eu-repo/semantics/closedAccess
dc.subject.classification	Networking & Telecommunications	en_US
dc.title	Lightweight Machine Learning for Efficient Frequency-Offset-Aware Demodulation	en_US
dc.type	Journal Article
utslib.citation.volume	11	en_US
utslib.citation.volume	37	en_US
utslib.for	0805 Distributed Computing	en_US
utslib.for	0906 Electrical and Electronic Engineering	en_US
utslib.for	1005 Communications Technologies	en_US
pubs.embargo.period	Not known	en_US
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Electrical and Data Engineering
utslib.copyright.status	closed_access	*
pubs.issue	11	en_US
pubs.publication-status	Published	en_US
pubs.volume	37	en_US

Abstract:

© 2019 IEEE. Carrier frequency offset (CFO) arises from the intrinsic mismatch between the oscillators of a wireless transmitter and the corresponding receiver, as well as their relative motion (i.e., Doppler effect). Despite advances in CFO estimation and tracking techniques, estimation errors are still present. Residual CFO creates a time-varying phase error, which degrades the decoder's performance by increasing the symbol error rate. The impact is particularly visible in dense constellation maps (e.g., high-order QAM modulation), often used in modern wireless systems such as 5G NR, 802.11ax, and mmWave, as well as in physical security techniques, such as modulation obfuscation (MO). In this paper, we first derive the probability distribution function for the residual CFO under Gaussian noise. Using this distribution, we compute the maximum-likelihood demodulation boundaries for OFDM signals in a non-closed form. For modulation schemes with unequal-amplitude reference constellation points (e.g., 16-QAM and higher, APSK, etc.), the 'optimal' boundaries have irregular shapes, and more importantly, they depend on the time since the last CFO correction instance, e.g., reception of frame preamble. To approximate the optimal boundaries and provide a practical (real-time) demodulation scheme, we explore machine learning techniques, specifically, support vector machine (SVM). Our SVM approach exhibits better accuracy and lower complexity in the test phase than other state-of-the-art machine-learning approaches. As a case study, we apply our CFO-aware demodulation to enhance the performance of a MO technique. Our analytical results show a gain of up to 3dB over conventional demodulation schemes, which exceeds 3dB in complete system simulations. Finally, we implement our scheme on USRPs and experimentally corroborate our analytic and simulation-based findings.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/139989