Show simple item record

dc.contributor.authorGarcia Marti, Dolores 
dc.contributor.authorRuiz, Rafael 
dc.contributor.authorLacruz, Jesús Omar 
dc.contributor.authorWidmer, Joerg 
dc.date.accessioned2023-01-13T16:48:00Z
dc.date.available2023-01-13T16:48:00Z
dc.date.issued2023-05-17
dc.identifier.urihttps://hdl.handle.net/20.500.12761/1660
dc.description.abstractMachine Learning (ML) is a promising tool to design wireless physical layer (PHY) components. It is particularly interesting for millimeter-wave (mm-wave) frequencies and above, due to the more challenging hardware design and channel environment at these frequencies. Rather than building individual ML-components, in this paper, we design an entire ML-enhanced mm-wave receiver for frequency selective channels. Our ML-receiver jointly optimizes the channel estimation, equalization, phase correction and demapper using Convolutional Neural Networks. We also show that for mm-wave systems, the channel varies significantly even over short timescales, requiring frequent channel measurements, and this situation is exacerbated in mobile scenarios. To tackle this, we propose a new MLchannel estimation approach that refreshes the channel state information using the guard intervals (not intended for channel measurements) that are available for every block of symbols in communication packets. To the best of our knowledge, our MLreceiver is the first work to outperform conventional receivers in general scenarios, with simulation results showing up to 7dB gains. We also provide an experimental validation of the ML-enhanced receiver with a 60 GHz FPGA-based testbed with phased antenna arrays, which shows a throughput increase by a factor of up to 6 over baseline schemes in mobile scenarios.es
dc.description.sponsorshipMinistry of Economic Affairs and Digital Transformationes
dc.description.sponsorshipMinistry of Economic Affairs and Digital Transformationes
dc.description.sponsorshipMadrid Regional Governmentes
dc.language.isoenges
dc.titleHigh-speed Machine Learning-enhanced Receiver for Millimeter-Wave Systemses
dc.typeconference objectes
dc.conference.date17-20 May 2023es
dc.conference.placeNew York, United Stateses
dc.conference.titleIEEE International Conference on Computer Communications*
dc.event.typeconferencees
dc.pres.typepaperes
dc.type.hasVersionAMes
dc.rights.accessRightsopen accesses
dc.acronymINFOCOM*
dc.rankA**
dc.relation.projectIDTSI-063000-2021- 59es
dc.relation.projectIDTSI-063000-2021-63es
dc.relation.projectIDS2018/TCS4496es
dc.relation.projectNameRISC-6Ges
dc.relation.projectNameMAP-6Ges
dc.relation.projectNameTAPIR-CMes
dc.subject.keywordMachine Learninges
dc.subject.keywordMillimeter Wavees
dc.subject.keywordChannel Estimationes
dc.subject.keywordPhysical Layeres
dc.subject.keywordEqualizationes
dc.description.refereedTRUEes
dc.description.statusinpresses


Files in this item

This item appears in the following Collection(s)

Show simple item record