{"id":"https://openalex.org/W7160240844","doi":"https://doi.org/10.48550/arxiv.2605.01931","title":"SwiftChannel: Algorithm-Hardware Co-Design for Deep Learning-Based 5G Channel Estimation","display_name":"SwiftChannel: Algorithm-Hardware Co-Design for Deep Learning-Based 5G Channel Estimation","publication_year":2026,"publication_date":"2026-05-03","ids":{"openalex":"https://openalex.org/W7160240844","doi":"https://doi.org/10.48550/arxiv.2605.01931"},"language":null,"primary_location":{"id":"doi:10.48550/arxiv.2605.01931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01931","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"type":"preprint","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.48550/arxiv.2605.01931","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5108948085","display_name":"Shengzhe Lyu","orcid":"https://orcid.org/0009-0004-7331-7700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lyu, Shengzhe","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5006271768","display_name":"Yuhan She","orcid":"https://orcid.org/0000-0003-3748-577X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"She, Yuhan","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5041177357","display_name":"Di Duan","orcid":"https://orcid.org/0000-0003-4184-0762"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Duan, Di","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135332398","display_name":"Tao Ni","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ni, Tao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102540010","display_name":"Yu Hin Chan","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chan, Yu Hin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060564734","display_name":"Chengwen Luo","orcid":"https://orcid.org/0000-0003-0293-0781"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Luo, Chengwen","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5135299225","display_name":"Ray C. C. Cheung","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Cheung, Ray C. C.","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5036424879","display_name":"Weitao Xu","orcid":"https://orcid.org/0000-0001-9741-5912"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xu, Weitao","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10936","display_name":"Millimeter-Wave Propagation and Modeling","score":0.5284000039100647,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10936","display_name":"Millimeter-Wave Propagation and Modeling","score":0.5284000039100647,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12131","display_name":"Wireless Signal Modulation Classification","score":0.29170000553131104,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10148","display_name":"Advanced MIMO Systems Optimization","score":0.02199999988079071,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6664999723434448},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.6083999872207642},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5782999992370605},{"id":"https://openalex.org/keywords/dataflow","display_name":"Dataflow","score":0.5708000063896179},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.5473999977111816},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.5163999795913696},{"id":"https://openalex.org/keywords/transmission","display_name":"Transmission (telecommunications)","score":0.46720001101493835},{"id":"https://openalex.org/keywords/mimo","display_name":"MIMO","score":0.42649999260902405},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.37299999594688416},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.3686999976634979}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7373999953269958},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6664999723434448},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.6083999872207642},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5782999992370605},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.5708000063896179},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5615000128746033},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.5473999977111816},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.5163999795913696},{"id":"https://openalex.org/C761482","wikidata":"https://www.wikidata.org/wiki/Q118093","display_name":"Transmission (telecommunications)","level":2,"score":0.46720001101493835},{"id":"https://openalex.org/C207987634","wikidata":"https://www.wikidata.org/wiki/Q176862","display_name":"MIMO","level":3,"score":0.42649999260902405},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.39329999685287476},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.37299999594688416},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.3686999976634979},{"id":"https://openalex.org/C78548338","wikidata":"https://www.wikidata.org/wiki/Q2493","display_name":"Data compression","level":2,"score":0.36390000581741333},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.36160001158714294},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.35589998960494995},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3508000075817108},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.3492000102996826},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.3452000021934509},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3188999891281128},{"id":"https://openalex.org/C19275194","wikidata":"https://www.wikidata.org/wiki/Q222903","display_name":"Multiplexing","level":2,"score":0.311599999666214},{"id":"https://openalex.org/C206588197","wikidata":"https://www.wikidata.org/wiki/Q846574","display_name":"Reuse","level":2,"score":0.3093999922275543},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.3068999946117401},{"id":"https://openalex.org/C89600930","wikidata":"https://www.wikidata.org/wiki/Q1423946","display_name":"Segmentation","level":2,"score":0.30399999022483826},{"id":"https://openalex.org/C2780513914","wikidata":"https://www.wikidata.org/wiki/Q18210350","display_name":"Bottleneck","level":2,"score":0.28949999809265137},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.288100004196167},{"id":"https://openalex.org/C13944312","wikidata":"https://www.wikidata.org/wiki/Q7512748","display_name":"Signal-to-noise ratio (imaging)","level":2,"score":0.287200003862381},{"id":"https://openalex.org/C163294075","wikidata":"https://www.wikidata.org/wiki/Q581861","display_name":"Noise reduction","level":2,"score":0.27970001101493835},{"id":"https://openalex.org/C20136886","wikidata":"https://www.wikidata.org/wiki/Q749647","display_name":"Interoperability","level":2,"score":0.2745000123977661},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.2741999924182892},{"id":"https://openalex.org/C104267543","wikidata":"https://www.wikidata.org/wiki/Q208163","display_name":"Signal processing","level":3,"score":0.2678000032901764},{"id":"https://openalex.org/C49289754","wikidata":"https://www.wikidata.org/wiki/Q2267081","display_name":"Side channel attack","level":3,"score":0.2558000087738037},{"id":"https://openalex.org/C57654395","wikidata":"https://www.wikidata.org/wiki/Q1097775","display_name":"Compression artifact","level":5,"score":0.2524999976158142},{"id":"https://openalex.org/C24326235","wikidata":"https://www.wikidata.org/wiki/Q126095","display_name":"Electronic engineering","level":1,"score":0.25119999051094055},{"id":"https://openalex.org/C40409654","wikidata":"https://www.wikidata.org/wiki/Q375889","display_name":"Orthogonal frequency-division multiplexing","level":3,"score":0.250900000333786}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.48550/arxiv.2605.01931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01931","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"doi:10.48550/arxiv.2605.01931","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2605.01931","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"Preprint"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/7","score":0.7542784810066223,"display_name":"Affordable and clean energy"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Channel":[0],"estimation":[1,36,217],"is":[2],"crucial":[3],"in":[4,28,33,112,168],"5G":[5,29,220],"communication":[6],"networks":[7,30],"for":[8,219],"optimizing":[9],"transmission":[10],"parameters":[11],"and":[12,22,25,108,128,144,164,189],"ensuring":[13],"reliable,":[14],"high-speed":[15],"communication.":[16],"However,":[17],"the":[18,125,129,154,179],"use":[19],"of":[20,197],"multiple-input":[21],"multiple-output":[23],"(MIMO)":[24],"millimeter-wave":[26],"(mmWave)":[27],"presents":[31,213],"challenges":[32],"achieving":[34],"accurate":[35],"under":[37],"strict":[38],"latency":[39],"requirements":[40],"on":[41,132,149],"resource-limited":[42],"hardware":[43,122],"platforms.":[44],"To":[45],"address":[46],"these":[47],"challenges,":[48],"we":[49],"propose":[50],"SwiftChannel,":[51],"an":[52],"algorithm-hardware":[53],"co-design":[54],"framework":[55],"that":[56,178],"integrates":[57],"a":[58,65,71,77,98,140,150,195,214],"hardware-friendly":[59],"deep":[60],"learning-based":[61],"channel":[62,87,199,216],"estimator":[63,131],"with":[64,76,117,208],"dedicated":[66],"accelerator.":[67],"Our":[68],"approach":[69],"employs":[70],"convolutional":[72],"neural":[73],"network":[74],"enhanced":[75],"parameter-free":[78],"attention":[79],"mechanism,":[80],"which":[81],"effectively":[82],"reconstructs":[83],"full-resolution":[84],"spatial-frequency":[85],"domain":[86],"matrices":[88],"from":[89],"low-resolution":[90],"least":[91],"squares":[92],"(LS)":[93],"estimates.":[94],"We":[95],"further":[96],"develop":[97],"multi-stage":[99],"model":[100,114,127],"compression":[101],"pipeline":[102,142],"combining":[103],"knowledge":[104],"distillation,":[105],"convolution":[106],"re-parameterization,":[107],"quantization-aware":[109],"training,":[110],"resulting":[111],"substantial":[113],"size":[115],"reduction":[116],"negligible":[118],"accuracy":[119],"loss.":[120],"The":[121],"accelerator,":[123],"implementing":[124],"compressed":[126],"LS":[130],"FPGA":[133],"platforms":[134],"using":[135],"High-level":[136],"Synthesis":[137],"(HLS),":[138],"features":[139],"fine-grained":[141],"architecture":[143],"optimized":[145],"dataflow":[146],"strategies.":[147],"Tested":[148],"Zynq":[151],"UltraScale+":[152],"RFSoC,":[153],"accelerator":[155],"achieves":[156],"sub-millisecond":[157],"latency,":[158],"providing":[159],"up":[160],"to":[161,172,194],"24x":[162],"speed-up":[163],"over":[165],"33x":[166],"improvement":[167],"energy":[169],"efficiency":[170],"compared":[171],"GPU-based":[173],"solutions.":[174],"Extensive":[175],"evaluations":[176],"demonstrate":[177],"proposed":[180],"design":[181],"generalizes":[182],"not":[183],"only":[184],"across":[185],"various":[186],"noise":[187],"levels":[188],"user":[190],"mobilities,":[191],"but":[192],"also":[193],"variety":[196],"unseen":[198],"profiles,":[200],"outperforming":[201],"state-of-the-art":[202],"baselines.":[203],"By":[204],"unifying":[205],"algorithmic":[206],"innovation":[207],"hardware-aware":[209],"design,":[210],"our":[211],"work":[212],"future-proof":[215],"solution":[218],"MIMO":[221],"systems.":[222]},"counts_by_year":[],"updated_date":"2026-07-01T06:00:48.157686","created_date":"2026-05-06T00:00:00"}