Show simple item record

dc.contributor.authorSiyari, Peyman
dc.contributor.authorRahbari, Hanif
dc.contributor.authorKrunz, Marwan
dc.date.accessioned2020-01-13T18:16:13Z
dc.date.available2020-01-13T18:16:13Z
dc.date.issued2019-11
dc.identifier.citationSiyari, P., Rahbari, H., & Krunz, M. (2019). Lightweight Machine Learning for Efficient Frequency-Offset-Aware Demodulation. IEEE Journal on Selected Areas in Communications, 37(11), 2544-2558.en_US
dc.identifier.issn0733-8716
dc.identifier.doi10.1109/jsac.2019.2933956
dc.identifier.urihttp://hdl.handle.net/10150/636459
dc.description.abstractCarrier 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 3 dB over conventional demodulation schemes, which exceeds 3 dB in complete system simulations. Finally, we implement our scheme on USRPs and experimentally corroborate our analytic and simulation-based findings.en_US
dc.description.sponsorshipNational Science Foundation (NSF) [CNS-1409172, IIP-1822071, CNS-1513649, CNS-1731164]; Broadband Wireless Access & Applications Center (BWAC) [18091319]; RIT [18091319]en_US
dc.language.isoenen_US
dc.publisherInstitute of Electrical and Electronics Engineers (IEEE)en_US
dc.rights© 2019 IEEE.en_US
dc.subjectCarrier frequency offseten_US
dc.subjectdemodulationen_US
dc.subjectsupport vector machineen_US
dc.subjectmodulation obfuscationen_US
dc.subjectUSRP experimentsen_US
dc.titleLightweight Machine Learning for Efficient Frequency-Offset-Aware Demodulationen_US
dc.typeArticleen_US
dc.identifier.eissn1558-0008
dc.contributor.departmentUniv Arizona, Dept Elect & Comp Engnen_US
dc.identifier.journalIEEE Journal on Selected Areas in Communicationsen_US
dc.description.collectioninformationThis item from the UA Faculty Publications collection is made available by the University of Arizona with support from the University of Arizona Libraries. If you have questions, please contact us at repository@u.library.arizona.edu.en_US
dc.eprint.versionFinal accepted manuscripten_US
dc.source.volume37
dc.source.issue11
dc.source.beginpage2544-2558
refterms.dateFOA2020-01-13T18:16:14Z


Files in this item

Thumbnail
Name:
1570514640-2.pdf
Size:
2.799Mb
Format:
PDF
Description:
Final Accepted Manuscript

This item appears in the following Collection(s)

Show simple item record