{"id":"https://openalex.org/W3215372595","doi":"https://doi.org/10.1109/swc50871.2021.00022","title":"Feasibility Analysis of Machine Learning Optimization on GPU-based Low-cost Edges","display_name":"Feasibility Analysis of Machine Learning Optimization on GPU-based Low-cost Edges","publication_year":2021,"publication_date":"2021-10-01","ids":{"openalex":"https://openalex.org/W3215372595","doi":"https://doi.org/10.1109/swc50871.2021.00022","mag":"3215372595"},"language":"en","primary_location":{"id":"doi:10.1109/swc50871.2021.00022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/swc50871.2021.00022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/IOP/SCI)","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/A5029600448","display_name":"Jiashun Suo","orcid":"https://orcid.org/0000-0002-5360-353X"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Jiashun Suo","raw_affiliation_strings":["Engineering Research Center of Cyberspace, Yunnan University, Kunming, China","School of Software, Yunnan University, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Cyberspace, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]},{"raw_affiliation_string":"School of Software, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5019902081","display_name":"Xingzhou Zhang","orcid":"https://orcid.org/0000-0002-8404-7302"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]},{"id":"https://openalex.org/I4210090176","display_name":"Institute of Computing Technology","ror":"https://ror.org/0090r4d87","country_code":"CN","type":"facility","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210090176"]},{"id":"https://openalex.org/I19820366","display_name":"Chinese Academy of Sciences","ror":"https://ror.org/034t30j35","country_code":"CN","type":"funder","lineage":["https://openalex.org/I19820366"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xingzhou Zhang","raw_affiliation_strings":["Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210090176","https://openalex.org/I19820366"]},{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5032367559","display_name":"Shilei Zhang","orcid":"https://orcid.org/0000-0001-8169-0098"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Shilei Zhang","raw_affiliation_strings":["Engineering Research Center of Cyberspace, Yunnan University, Kunming, China","School of Software, Yunnan University, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Cyberspace, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]},{"raw_affiliation_string":"School of Software, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051349066","display_name":"Wei Zhou","orcid":"https://orcid.org/0000-0002-5881-9436"},"institutions":[{"id":"https://openalex.org/I189210763","display_name":"Yunnan University","ror":"https://ror.org/0040axw97","country_code":"CN","type":"education","lineage":["https://openalex.org/I189210763"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wei Zhou","raw_affiliation_strings":["Engineering Research Center of Cyberspace, Yunnan University, Kunming, China","School of Software, Yunnan University, Kunming, China"],"affiliations":[{"raw_affiliation_string":"Engineering Research Center of Cyberspace, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]},{"raw_affiliation_string":"School of Software, Yunnan University, Kunming, China","institution_ids":["https://openalex.org/I189210763"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100651611","display_name":"Weisong Shi","orcid":"https://orcid.org/0000-0001-5864-4675"},"institutions":[{"id":"https://openalex.org/I185443292","display_name":"Wayne State University","ror":"https://ror.org/01070mq45","country_code":"US","type":"education","lineage":["https://openalex.org/I185443292"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Weisong Shi","raw_affiliation_strings":["Department of Computer Science, Wayne State University, Detroit, MI, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, Wayne State University, Detroit, MI, USA","institution_ids":["https://openalex.org/I185443292"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5029600448"],"corresponding_institution_ids":["https://openalex.org/I189210763"],"apc_list":null,"apc_paid":null,"fwci":0.6725,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.71893791,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"89","last_page":"96"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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"}},"topics":[{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9995999932289124,"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"}},{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9993000030517578,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11775","display_name":"COVID-19 diagnosis using AI","score":0.9933000206947327,"subfield":{"id":"https://openalex.org/subfields/2741","display_name":"Radiology, Nuclear Medicine and Imaging"},"field":{"id":"https://openalex.org/fields/27","display_name":"Medicine"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8317579627037048},{"id":"https://openalex.org/keywords/edge-computing","display_name":"Edge computing","score":0.6553205251693726},{"id":"https://openalex.org/keywords/edge-device","display_name":"Edge device","score":0.6340439915657043},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.6287251114845276},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5483619570732117},{"id":"https://openalex.org/keywords/computer-engineering","display_name":"Computer engineering","score":0.5279873013496399},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4992384910583496},{"id":"https://openalex.org/keywords/enhanced-data-rates-for-gsm-evolution","display_name":"Enhanced Data Rates for GSM Evolution","score":0.48008471727371216},{"id":"https://openalex.org/keywords/cuda","display_name":"CUDA","score":0.4290473759174347},{"id":"https://openalex.org/keywords/general-purpose-computing-on-graphics-processing-units","display_name":"General-purpose computing on graphics processing units","score":0.4280466139316559},{"id":"https://openalex.org/keywords/quantization","display_name":"Quantization (signal processing)","score":0.4194122552871704},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.32916128635406494},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.3226172626018524},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.3214643895626068},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.2325032651424408},{"id":"https://openalex.org/keywords/computer-graphics","display_name":"Computer graphics (images)","score":0.09566852450370789},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.0901760458946228}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8317579627037048},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.6553205251693726},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.6340439915657043},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.6287251114845276},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5483619570732117},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.5279873013496399},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4992384910583496},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.48008471727371216},{"id":"https://openalex.org/C2778119891","wikidata":"https://www.wikidata.org/wiki/Q477690","display_name":"CUDA","level":2,"score":0.4290473759174347},{"id":"https://openalex.org/C50630238","wikidata":"https://www.wikidata.org/wiki/Q971505","display_name":"General-purpose computing on graphics processing units","level":3,"score":0.4280466139316559},{"id":"https://openalex.org/C28855332","wikidata":"https://www.wikidata.org/wiki/Q198099","display_name":"Quantization (signal processing)","level":2,"score":0.4194122552871704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.32916128635406494},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.3226172626018524},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.3214643895626068},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.2325032651424408},{"id":"https://openalex.org/C121684516","wikidata":"https://www.wikidata.org/wiki/Q7600677","display_name":"Computer graphics (images)","level":1,"score":0.09566852450370789},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0901760458946228},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C205649164","wikidata":"https://www.wikidata.org/wiki/Q1071","display_name":"Geography","level":0,"score":0.0},{"id":"https://openalex.org/C21442007","wikidata":"https://www.wikidata.org/wiki/Q1027879","display_name":"Graphics","level":2,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/swc50871.2021.00022","is_oa":false,"landing_page_url":"https://doi.org/10.1109/swc50871.2021.00022","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE SmartWorld, Ubiquitous Intelligence & Computing, Advanced & Trusted Computing, Scalable Computing & Communications, Internet of People and Smart City Innovation (SmartWorld/SCALCOM/UIC/ATC/IOP/SCI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1864199185","https://openalex.org/W2402144811","https://openalex.org/W2416799949","https://openalex.org/W2744316982","https://openalex.org/W2770587725","https://openalex.org/W2796347433","https://openalex.org/W2883863832","https://openalex.org/W2950865323","https://openalex.org/W2953384591","https://openalex.org/W2982650630","https://openalex.org/W2982656930","https://openalex.org/W2998802733","https://openalex.org/W3003643108","https://openalex.org/W4293584584","https://openalex.org/W6713134421","https://openalex.org/W6750227808","https://openalex.org/W6772261133","https://openalex.org/W6773095222"],"related_works":["https://openalex.org/W1963859303","https://openalex.org/W2364044215","https://openalex.org/W2389600408","https://openalex.org/W240129890","https://openalex.org/W3048701459","https://openalex.org/W2149078538","https://openalex.org/W2080146221","https://openalex.org/W2546223573","https://openalex.org/W2370314112","https://openalex.org/W1912958759"],"abstract_inverted_index":{"Many":[0],"AI":[1,30,83,144,200],"algorithms":[2,31,201],"have":[3],"been":[4],"deployed":[5],"on":[6,58,119,131,179,202],"edge":[7,10,26,44,63,140,203],"devices":[8,27],"as":[9,79],"computing":[11,148],"has":[12],"the":[13,38,50,80,104,138,165,174,195],"advantages":[14],"of":[15,43,52,92,124,169,176,189],"reducing":[16],"latency,":[17,87],"saving":[18],"network":[19],"bandwidth,":[20],"and":[21,40,89,99,116,160,167,172],"protecting":[22],"data":[23],"privacy.":[24],"Whether":[25],"can":[28,142],"run":[29,143],"is":[32,69,76],"an":[33],"important":[34],"challenge":[35],"due":[36],"to":[37,129,163,191,198],"low-power":[39],"low-cost":[41,62],"characteristics":[42],"devices.":[45,204],"Therefore,":[46],"this":[47],"paper":[48],"analyzed":[49],"performance":[51,106],"optimization":[53,109,170],"techniques":[54,171],"by":[55],"running":[56,122],"YOLOv3":[57,68,125],"a":[59,70,152,187],"typical":[60],"GPU-based":[61],"device,":[64],"NVIDIA":[65,132,180],"Jetson":[66,133,181],"Nano.":[67,134],"representative":[71],"object":[72],"detection":[73],"algorithm,":[74],"which":[75],"widely":[77],"used":[78],"benchmark":[81],"in":[82,151],"scenarios.":[84],"We":[85,184],"compared":[86],"memory,":[88],"power":[90,149],"consumption":[91],"three":[93],"deep":[94],"learning":[95],"frameworks,":[96],"TensorFlow,":[97],"PyTorch,":[98],"TensorRT.":[100,120],"Then":[101],"we":[102,156],"squeezed":[103],"extreme":[105],"using":[107],"multiple":[108],"techniques,":[110],"including":[111],"model":[112,114],"quantization,":[113],"parallelization,":[115],"image":[117],"scaling":[118],"The":[121],"speed":[123],"increases":[126],"from":[127],"3.9FPS":[128],"13.1FPS":[130],"It":[135],"proves":[136],"that":[137],"resource-limited":[139],"device":[141],"applications":[145],"with":[146],"high":[147],"requirements":[150],"real-time":[153],"manner.":[154],"Moreover,":[155],"summarized":[157],"nine":[158],"observations":[159],"five":[161],"insights":[162],"guide":[164],"selection":[166],"design":[168],"verified":[173],"generalization":[175],"these":[177],"rules":[178],"Xavier":[182],"NX.":[183],"also":[185],"provided":[186],"series":[188],"suggestions":[190],"help":[192],"developers":[193],"choose":[194],"appropriate":[196],"method":[197],"deploy":[199]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}