{"id":"https://openalex.org/W4392175333","doi":"https://doi.org/10.1109/globecom54140.2023.10437056","title":"Light Weight AI: Representing ML Inference as Efficient Mathematical Relations for Embedded RAN Devices","display_name":"Light Weight AI: Representing ML Inference as Efficient Mathematical Relations for Embedded RAN Devices","publication_year":2023,"publication_date":"2023-12-04","ids":{"openalex":"https://openalex.org/W4392175333","doi":"https://doi.org/10.1109/globecom54140.2023.10437056"},"language":"en","primary_location":{"id":"doi:10.1109/globecom54140.2023.10437056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom54140.2023.10437056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2023 - 2023 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/A5014172274","display_name":"Swaraj Kumar","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Swaraj Kumar","raw_affiliation_strings":["Samsung R& D India-Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R& D India-Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5052587258","display_name":"Vishal Murgai","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Vishal Murgai","raw_affiliation_strings":["Samsung R& D India-Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R& D India-Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037831505","display_name":"Sukhdeep Singh","orcid":"https://orcid.org/0000-0003-1553-3275"},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sukhdeep Singh","raw_affiliation_strings":["Samsung R& D India-Bangalore"],"affiliations":[{"raw_affiliation_string":"Samsung R& D India-Bangalore","institution_ids":["https://openalex.org/I4210139030"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5014172274"],"corresponding_institution_ids":["https://openalex.org/I4210139030"],"apc_list":null,"apc_paid":null,"fwci":0.1748,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.60280762,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":95},"biblio":{"volume":null,"issue":null,"first_page":"7333","last_page":"7338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10320","display_name":"Neural Networks and Applications","score":0.9936000108718872,"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":0.9936000108718872,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9908999800682068,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.9771000146865845,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/ran","display_name":"Ran","score":0.8422130346298218},{"id":"https://openalex.org/keywords/inference","display_name":"Inference","score":0.7377848029136658},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6444900035858154},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.48506394028663635},{"id":"https://openalex.org/keywords/c-ran","display_name":"C-RAN","score":0.431941956281662},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.3289789855480194},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.11035442352294922},{"id":"https://openalex.org/keywords/radio-access-network","display_name":"Radio access network","score":0.07086095213890076}],"concepts":[{"id":"https://openalex.org/C160704184","wikidata":"https://www.wikidata.org/wiki/Q18031028","display_name":"Ran","level":2,"score":0.8422130346298218},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.7377848029136658},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6444900035858154},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.48506394028663635},{"id":"https://openalex.org/C2779765720","wikidata":"https://www.wikidata.org/wiki/Q5005908","display_name":"C-RAN","level":5,"score":0.431941956281662},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.3289789855480194},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.11035442352294922},{"id":"https://openalex.org/C106365562","wikidata":"https://www.wikidata.org/wiki/Q3078360","display_name":"Radio access network","level":4,"score":0.07086095213890076},{"id":"https://openalex.org/C68649174","wikidata":"https://www.wikidata.org/wiki/Q1379116","display_name":"Base station","level":2,"score":0.0},{"id":"https://openalex.org/C207029474","wikidata":"https://www.wikidata.org/wiki/Q384018","display_name":"Mobile station","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/globecom54140.2023.10437056","is_oa":false,"landing_page_url":"https://doi.org/10.1109/globecom54140.2023.10437056","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"GLOBECOM 2023 - 2023 IEEE Global Communications Conference","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W2046376809","https://openalex.org/W2945086780","https://openalex.org/W2965757358","https://openalex.org/W3010109240","https://openalex.org/W3036160090","https://openalex.org/W4285503423","https://openalex.org/W4293690684","https://openalex.org/W4317796310"],"related_works":["https://openalex.org/W2885627391","https://openalex.org/W4401508502","https://openalex.org/W4324323655","https://openalex.org/W2922954044","https://openalex.org/W3037103914","https://openalex.org/W1982654631","https://openalex.org/W3018338683","https://openalex.org/W3197340217","https://openalex.org/W4288060126","https://openalex.org/W4294306393"],"abstract_inverted_index":{"Wireless":[0],"5G":[1],"and":[2,21,72,127,162,171,198,218],"beyond":[3],"(B5G)":[4],"technology":[5],"offers":[6],"multiple":[7],"of":[8,24,64,68,75,173,208],"machine":[9],"learning":[10,107],"(ML)":[11],"use":[12,26],"cases,":[13],"including":[14],"congestion":[15,191],"detection,":[16],"handover":[17],"prediction,":[18],"MAC":[19],"scheduling":[20],"more.":[22],"Many":[23],"these":[25,47,148],"cases":[27],"involve":[28],"solving":[29],"complex":[30],"problems":[31],"that":[32],"need":[33],"neural":[34],"networks":[35],"(NN)":[36],"or":[37],"classical":[38],"ML":[39,77,113,153,242],"algorithms":[40],"to":[41,93,115,144,189,221,225],"achieve":[42],"optimal":[43,163],"solutions.":[44],"However,":[45],"implementing":[46],"NN":[48,226],"inferences":[49],"on":[50,118,138,156,245],"resource-constraint":[51,246],"base":[52],"stations":[53],"(BS)":[54],"pose":[55],"significant":[56],"challenges.":[57],"BSs":[58,158],"has":[59],"several":[60],"limitations":[61],"in":[62,177,201],"terms":[63],"CPU":[65,216],"frequency,":[66],"number":[67],"cores,":[69],"memory":[70,220],"capacity,":[71],"the":[73,84,139,145,169,174,184,206],"absence":[74],"dedicated":[76],"hardware":[78],"(HW)":[79],"offloads.":[80],"In":[81],"this":[82],"paper,":[83],"authors,":[85],"propose":[86],"a":[87],"lightweight":[88],"artificial":[89],"intelligence":[90],"(LWAI)":[91],"method":[92],"derive":[94],"computationally":[95],"efficient":[96],"mathematical":[97],"relations":[98],"(EMR)":[99],"between":[100],"Key":[101],"Performance":[102],"Indicators":[103],"(KPIs)":[104],"using":[105,147],"reinforcement":[106],"(RL).":[108],"The":[109,132,181],"derived":[110],"EMR":[111],"enables":[112],"inference":[114,154,243],"be":[116],"implemented":[117],"resource-constrained":[119],"BSs.":[120],"LWAI":[121,175,210],"takes":[122],"KPIs":[123],"information":[124],"as":[125,130,223],"input":[126],"provides":[128],"EMRs":[129,134,212],"output.":[131],"generated":[133],"are":[135],"then":[136],"deployed":[137],"BS.":[140,202],"Inference":[141],"is":[142],"made":[143],"BS":[146],"relations.":[149],"This":[150],"approach":[151,188,235],"makes":[152],"realizable":[155],"embedded":[157,247],"with":[159],"commercial-grade":[160],"accuracy":[161],"real-time":[164],"prediction":[165,232],"latency.":[166],"We":[167],"demonstrate":[168],"effectiveness":[170],"applicability":[172],"framework":[176],"two":[178],"real-world":[179],"scenarios.":[180],"results":[182,204],"highlight":[183],"potential":[185],"for":[186,240],"our":[187],"detect":[190],"by":[192],"predicting":[193],"physical":[194],"resource":[195],"block":[196],"(PRB)":[197],"energy":[199],"savings":[200],"Our":[203,234],"show":[205],"efficacy":[207],"EMRs.":[209],"framework-derived":[211],"consume":[213],"around":[214],"10%":[215],"cycles":[217],"5%":[219],"execute":[222],"compared":[224],"models":[227],"while":[228],"maintaining":[229],"over":[230],"90%":[231],"accuracy.":[233],"opens":[236],"up":[237],"new":[238],"possibilities":[239],"realizing":[241],"ideas":[244],"devices.":[248]},"counts_by_year":[{"year":2025,"cited_by_count":1}],"updated_date":"2026-01-13T01:12:25.745995","created_date":"2025-10-10T00:00:00"}