{"id":"https://openalex.org/W4408325054","doi":"https://doi.org/10.1109/globecom52923.2024.10900969","title":"Enhancing LMMSE Performance with Modest Complexity Increase via Neural Network Equalizers","display_name":"Enhancing LMMSE Performance with Modest Complexity Increase via Neural Network Equalizers","publication_year":2024,"publication_date":"2024-12-08","ids":{"openalex":"https://openalex.org/W4408325054","doi":"https://doi.org/10.1109/globecom52923.2024.10900969"},"language":"en","primary_location":{"id":"doi:10.1109/globecom52923.2024.10900969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom52923.2024.10900969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2024 - 2024 IEEE Global Communications Conference","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5114637469","display_name":"Vadim Rozenfeld","orcid":null},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":true,"raw_author_name":"Vadim Rozenfeld","raw_affiliation_strings":["Tel-Aviv University,Israel"],"affiliations":[{"raw_affiliation_string":"Tel-Aviv University,Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5036838465","display_name":"Dan Raphaeli","orcid":"https://orcid.org/0000-0003-3563-1067"},"institutions":[{"id":"https://openalex.org/I16391192","display_name":"Tel Aviv University","ror":"https://ror.org/04mhzgx49","country_code":"IL","type":"education","lineage":["https://openalex.org/I16391192"]}],"countries":["IL"],"is_corresponding":false,"raw_author_name":"Dan Raphaeli","raw_affiliation_strings":["Tel-Aviv University,Israel"],"affiliations":[{"raw_affiliation_string":"Tel-Aviv University,Israel","institution_ids":["https://openalex.org/I16391192"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076874228","display_name":"Oded Bialer","orcid":"https://orcid.org/0000-0001-8521-3416"},"institutions":[{"id":"https://openalex.org/I4210135317","display_name":"General Motors (Poland)","ror":"https://ror.org/03n3nz506","country_code":"PL","type":"company","lineage":["https://openalex.org/I118136607","https://openalex.org/I4210135317"]}],"countries":["PL"],"is_corresponding":false,"raw_author_name":"Oded Bialer","raw_affiliation_strings":["General Motors"],"affiliations":[{"raw_affiliation_string":"General Motors","institution_ids":["https://openalex.org/I4210135317"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5114637469"],"corresponding_institution_ids":["https://openalex.org/I16391192"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.25315225,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"2365","last_page":"2370"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7918000221252441,"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"}},"topics":[{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.7918000221252441,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6958116292953491},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.5552183389663696},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.26005131006240845}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6958116292953491},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.5552183389663696},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.26005131006240845}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom52923.2024.10900969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom52923.2024.10900969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2024 - 2024 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":15,"referenced_works":["https://openalex.org/W2045407304","https://openalex.org/W2080918425","https://openalex.org/W2107959360","https://openalex.org/W2134938338","https://openalex.org/W2156434076","https://openalex.org/W2164839258","https://openalex.org/W2962782499","https://openalex.org/W2963852693","https://openalex.org/W3006643426","https://openalex.org/W3081045327","https://openalex.org/W4315630053","https://openalex.org/W6630607823","https://openalex.org/W6631190155","https://openalex.org/W6746713790","https://openalex.org/W6747916894"],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W4391913857","https://openalex.org/W2358668433","https://openalex.org/W4396701345","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W4396696052"],"abstract_inverted_index":{"The":[0],"BCJR":[1,83,145],"algorithm":[2],"is":[3,157],"renowned":[4],"for":[5],"its":[6,20],"optimal":[7],"equalization,":[8],"minimizing":[9],"bit":[10],"error":[11,40],"rate":[12],"(BER)":[13],"over":[14],"intersymbol":[15],"interference":[16],"(ISI)":[17],"channels.":[18],"However,":[19,85],"complexity":[21,130],"grows":[22],"exponentially":[23],"with":[24,49,114,129,150,180,201],"the":[25,35,54,72,82,104,109,144],"channel":[26],"memory,":[27],"posing":[28],"a":[29,44,89,115,126,139,153,175,181],"significant":[30,148],"computational":[31],"burden.":[32],"In":[33],"contrast,":[34],"linear":[36],"minimum":[37],"mean":[38],"square":[39],"(LMMSE)":[41],"equalizer":[42,128,178],"offers":[43],"notably":[45],"simpler":[46],"solution,":[47],"albeit":[48],"reduced":[50,116],"performance":[51,79,136,141],"compared":[52],"to":[53,68,71,81,99,132,160,162,166],"BCJR.":[55,105],"Recently,":[56],"Neural":[57],"Network":[58],"(NN)":[59],"based":[60,185],"equalizers":[61],"have":[62],"emerged":[63],"as":[64],"promising":[65],"alternatives.":[66],"Trained":[67],"map":[69],"observations":[70],"original":[73],"transmitted":[74],"symbols,":[75],"these":[76],"NNs":[77,151],"demonstrate":[78],"similar":[80],"algorithm.":[84],"they":[86],"often":[87],"entail":[88],"high":[90],"number":[91,117],"of":[92,111,118],"learnable":[93,119],"parameters,":[94],"resulting":[95],"in":[96],"complexities":[97],"comparable":[98,131],"or":[100],"even":[101],"larger":[102],"than":[103],"This":[106,188],"paper":[107],"explores":[108],"potential":[110],"NN-based":[112],"equalization":[113],"parameters":[120],"and":[121,137,195,202],"low":[122],"complexity.":[123],"We":[124],"introduce":[125],"NN":[127,177],"LMMSE,":[133],"surpassing":[134],"LMMSE":[135,197],"achieving":[138],"modest":[140],"gap":[142],"from":[143],"equalizer.":[146],"A":[147],"challenge":[149],"featuring":[152],"limited":[154],"parameter":[155],"count":[156],"their":[158],"susceptibility":[159],"converging":[161],"local":[163],"minima,":[164],"leading":[165],"suboptimal":[167],"performance.":[168],"To":[169],"address":[170],"this":[171],"challenge,":[172],"we":[173],"propose":[174],"novel":[176],"architecture":[179],"unique":[182],"initialization":[183],"approach":[184],"on":[186],"LMMSE.":[187],"innovative":[189],"method":[190],"effectively":[191],"overcomes":[192],"optimization":[193],"challenges":[194],"enhances":[196],"performance,":[198],"applicable":[199],"both":[200],"without":[203],"turbo":[204],"decoding.":[205]},"counts_by_year":[],"updated_date":"2025-12-28T23:10:05.387466","created_date":"2025-10-10T00:00:00"}