{"id":"https://openalex.org/W4317382648","doi":"https://doi.org/10.1109/rivf55975.2022.10013887","title":"A Low-cost High-performance 2D-Convolution Accelerator for Deep Neural Networks in IoT","display_name":"A Low-cost High-performance 2D-Convolution Accelerator for Deep Neural Networks in IoT","publication_year":2022,"publication_date":"2022-12-20","ids":{"openalex":"https://openalex.org/W4317382648","doi":"https://doi.org/10.1109/rivf55975.2022.10013887"},"language":"en","primary_location":{"id":"doi:10.1109/rivf55975.2022.10013887","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rivf55975.2022.10013887","pdf_url":null,"source":{"id":"https://openalex.org/S4363608274","display_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","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/A5112891251","display_name":"Hung K. Nguyen","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Hung K. Nguyen","raw_affiliation_strings":["VNU University of Engineering and Technology,Key Laboratory for Smart Integrated System (SISLAB),HaNoi,VietNam","Key Laboratory for Smart Integrated System (SISLAB), VNU University of Engineering and Technology, HaNoi, VietNam"],"affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology,Key Laboratory for Smart Integrated System (SISLAB),HaNoi,VietNam","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory for Smart Integrated System (SISLAB), VNU University of Engineering and Technology, HaNoi, VietNam","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100631109","display_name":"Anh Tu\u1ea5n Nguy\u1ec5n","orcid":"https://orcid.org/0000-0003-3551-1700"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Anh T. Nguyen","raw_affiliation_strings":["VNU University of Engineering and Technology,Key Laboratory for Smart Integrated System (SISLAB),HaNoi,VietNam","Key Laboratory for Smart Integrated System (SISLAB), VNU University of Engineering and Technology, HaNoi, VietNam"],"affiliations":[{"raw_affiliation_string":"VNU University of Engineering and Technology,Key Laboratory for Smart Integrated System (SISLAB),HaNoi,VietNam","institution_ids":[]},{"raw_affiliation_string":"Key Laboratory for Smart Integrated System (SISLAB), VNU University of Engineering and Technology, HaNoi, VietNam","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112891251"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0599,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.34714102,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"440","last_page":"445"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9998000264167786,"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":0.9998000264167786,"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/T11992","display_name":"CCD and CMOS Imaging Sensors","score":0.9994000196456909,"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/T10502","display_name":"Advanced Memory and Neural Computing","score":0.9965000152587891,"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/computer-science","display_name":"Computer science","score":0.8087037801742554},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6916087865829468},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6311461925506592},{"id":"https://openalex.org/keywords/firmware","display_name":"Firmware","score":0.6085377335548401},{"id":"https://openalex.org/keywords/computer-hardware","display_name":"Computer hardware","score":0.5972617864608765},{"id":"https://openalex.org/keywords/kernel","display_name":"Kernel (algebra)","score":0.5115369558334351},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.4819188416004181},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4785507321357727},{"id":"https://openalex.org/keywords/embedded-system","display_name":"Embedded system","score":0.44943276047706604},{"id":"https://openalex.org/keywords/hardware-acceleration","display_name":"Hardware acceleration","score":0.4483816921710968},{"id":"https://openalex.org/keywords/bandwidth","display_name":"Bandwidth (computing)","score":0.4224685728549957},{"id":"https://openalex.org/keywords/throughput","display_name":"Throughput","score":0.4164176881313324},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.38328754901885986},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.3342568278312683},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.17342430353164673},{"id":"https://openalex.org/keywords/wireless","display_name":"Wireless","score":0.12224066257476807}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8087037801742554},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6916087865829468},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6311461925506592},{"id":"https://openalex.org/C67212190","wikidata":"https://www.wikidata.org/wiki/Q104851","display_name":"Firmware","level":2,"score":0.6085377335548401},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.5972617864608765},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.5115369558334351},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.4819188416004181},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4785507321357727},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.44943276047706604},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.4483816921710968},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.4224685728549957},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4164176881313324},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.38328754901885986},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3342568278312683},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.17342430353164673},{"id":"https://openalex.org/C555944384","wikidata":"https://www.wikidata.org/wiki/Q249","display_name":"Wireless","level":2,"score":0.12224066257476807},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/rivf55975.2022.10013887","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/rivf55975.2022.10013887","pdf_url":null,"source":{"id":"https://openalex.org/S4363608274","display_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2022 RIVF International Conference on Computing and Communication Technologies (RIVF)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Affordable and clean energy","score":0.8999999761581421,"id":"https://metadata.un.org/sdg/7"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":9,"referenced_works":["https://openalex.org/W2910121883","https://openalex.org/W2945146780","https://openalex.org/W3004127905","https://openalex.org/W3037261029","https://openalex.org/W3090500501","https://openalex.org/W3091546705","https://openalex.org/W3100321043","https://openalex.org/W4210842700","https://openalex.org/W4280500999"],"related_works":["https://openalex.org/W4389238932","https://openalex.org/W3034421924","https://openalex.org/W2982536526","https://openalex.org/W4386858688","https://openalex.org/W4380302312","https://openalex.org/W4390971171","https://openalex.org/W4385338604","https://openalex.org/W3081626085","https://openalex.org/W2518118925","https://openalex.org/W3159273459"],"abstract_inverted_index":{"This":[0],"paper":[1,66],"presents":[2],"an":[3],"hardware-":[4],"and":[5,37,57,99,109,137,155,165,192],"bandwidth-efficient":[6],"high-performance":[7],"2D":[8,20,43,82,89,131],"convolution":[9,21,44,83,90,132],"accelerator":[10,22,45],"for":[11],"convolutional":[12],"neural":[13],"networks":[14],"(CNNs)":[15],"in":[16,64,158,163],"IoT":[17],"applications.":[18],"The":[19,42,61,81,102,130],"is":[23,85,153],"made":[24],"up":[25],"of":[26,70,95,121],"three":[27],"main":[28],"components":[29],"including":[30],"a":[31,34,38,47,186],"dedicated":[32,176],"Loader,":[33],"Circle":[35],"Buffer,":[36],"MAC":[39],"(Multiplier-Accumulator)":[40],"unit.":[41],"has":[46,134],"2-stage":[48],"pipeline":[49],"structure":[50],"that":[51,150],"reduces":[52,58],"latency,":[53],"increases":[54],"processing":[55],"throughput,":[56],"power":[59,110],"consumption.":[60],"architecture":[62,103],"proposed":[63],"the":[65,68,72,77,118,122,161],"eliminates":[67],"reloading":[69],"both":[71],"weights":[73],"as":[74,76,111,113],"well":[75,112],"input":[78,96,124],"image":[79,97],"data.":[80],"unit":[84,133],"configurable":[86],"to":[87,117,143],"support":[88],"operations":[91],"with":[92],"different":[93],"sizes":[94],"matrix":[98],"kernel":[100],"filter.":[101],"can":[104],"reduce":[105],"memory":[106],"access":[107],"time":[108,115],"execution":[114],"thanks":[116],"efficient":[119],"reuse":[120],"preloaded":[123,181],"data,":[125,182],"while":[126],"simplifying":[127],"hardware":[128,170,177],"implementation.":[129],"been":[135],"simulated":[136],"implemented":[138],"on":[139],"Xilinx's":[140],"FPGA":[141],"platform":[142],"evaluate":[144],"its":[145],"superiority.":[146],"Experimental":[147],"results":[148],"show":[149],"our":[151,183],"design":[152,162,184],"1.54\u00d7":[154],"13.6\u00d7":[156],"faster":[157],"performance":[159],"than":[160],"[7]":[164],"[8],":[166],"respectively,":[167],"at":[168],"lower":[169],"cost":[171],"without":[172],"using":[173],"any":[174],"FPGA's":[175],"blocks.":[178],"By":[179],"reusing":[180],"achieves":[185],"bandwidth":[187],"reduction":[188],"ratio":[189],"between":[190],"66.4%":[191],"90.5%.":[193]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1}],"updated_date":"2026-02-14T06:23:00.392402","created_date":"2025-10-10T00:00:00"}