{"id":"https://openalex.org/W7114787599","doi":"https://doi.org/10.1109/access.2025.3642938","title":"High-Efficiency FPGA-Based CNN Accelerator With Optimized Data Handling for Convolution and Fully Connected Layers","display_name":"High-Efficiency FPGA-Based CNN Accelerator With Optimized Data Handling for Convolution and Fully Connected Layers","publication_year":2025,"publication_date":"2025-01-01","ids":{"openalex":"https://openalex.org/W7114787599","doi":"https://doi.org/10.1109/access.2025.3642938"},"language":"en","primary_location":{"id":"doi:10.1109/access.2025.3642938","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3642938","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1109/access.2025.3642938","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Raziyeh Foroumandi","orcid":"https://orcid.org/0009-0000-1733-8508"},"institutions":[{"id":"https://openalex.org/I38476204","display_name":"Urmia University","ror":"https://ror.org/032fk0x53","country_code":"IR","type":"education","lineage":["https://openalex.org/I38476204"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Raziyeh Foroumandi","raw_affiliation_strings":["Microelectronic Research Laboratory, Urmia University, Urmia, Iran"],"raw_orcid":"https://orcid.org/0009-0000-1733-8508","affiliations":[{"raw_affiliation_string":"Microelectronic Research Laboratory, Urmia University, Urmia, Iran","institution_ids":["https://openalex.org/I38476204"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Behbood Mashoufi","orcid":"https://orcid.org/0000-0002-9472-6069"},"institutions":[{"id":"https://openalex.org/I38476204","display_name":"Urmia University","ror":"https://ror.org/032fk0x53","country_code":"IR","type":"education","lineage":["https://openalex.org/I38476204"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Behbood Mashoufi","raw_affiliation_strings":["Microelectronic Research Laboratory, Urmia University, Urmia, Iran"],"raw_orcid":"https://orcid.org/0000-0002-9472-6069","affiliations":[{"raw_affiliation_string":"Microelectronic Research Laboratory, Urmia University, Urmia, Iran","institution_ids":["https://openalex.org/I38476204"]}]},{"author_position":"last","author":{"id":null,"display_name":"Amir Fathi","orcid":"https://orcid.org/0000-0001-8420-9909"},"institutions":[{"id":"https://openalex.org/I38476204","display_name":"Urmia University","ror":"https://ror.org/032fk0x53","country_code":"IR","type":"education","lineage":["https://openalex.org/I38476204"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Amir Fathi","raw_affiliation_strings":["Microelectronic Research Laboratory, Urmia University, Urmia, Iran"],"raw_orcid":"https://orcid.org/0000-0001-8420-9909","affiliations":[{"raw_affiliation_string":"Microelectronic Research Laboratory, Urmia University, Urmia, Iran","institution_ids":["https://openalex.org/I38476204"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I38476204"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.54251072,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"13","issue":null,"first_page":"211235","last_page":"211250"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9261999726295471,"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":0.9261999726295471,"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/T14347","display_name":"Big Data and Digital Economy","score":0.008799999952316284,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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":0.007699999958276749,"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/reconfigurability","display_name":"Reconfigurability","score":0.8381999731063843},{"id":"https://openalex.org/keywords/field-programmable-gate-array","display_name":"Field-programmable gate array","score":0.6762999892234802},{"id":"https://openalex.org/keywords/convolutional-neural-network","display_name":"Convolutional neural network","score":0.6538000106811523},{"id":"https://openalex.org/keywords/dram","display_name":"Dram","score":0.5837000012397766},{"id":"https://openalex.org/keywords/convolution","display_name":"Convolution (computer science)","score":0.5521000027656555},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.5249000191688538},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.5145999789237976},{"id":"https://openalex.org/keywords/coprocessor","display_name":"Coprocessor","score":0.43549999594688416},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.36980000138282776}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8605999946594238},{"id":"https://openalex.org/C2780149590","wikidata":"https://www.wikidata.org/wiki/Q7302742","display_name":"Reconfigurability","level":2,"score":0.8381999731063843},{"id":"https://openalex.org/C42935608","wikidata":"https://www.wikidata.org/wiki/Q190411","display_name":"Field-programmable gate array","level":2,"score":0.6762999892234802},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6538000106811523},{"id":"https://openalex.org/C7366592","wikidata":"https://www.wikidata.org/wiki/Q1255620","display_name":"Dram","level":2,"score":0.5837000012397766},{"id":"https://openalex.org/C45347329","wikidata":"https://www.wikidata.org/wiki/Q5166604","display_name":"Convolution (computer science)","level":3,"score":0.5521000027656555},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.5249000191688538},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.5145999789237976},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.4943000078201294},{"id":"https://openalex.org/C9390403","wikidata":"https://www.wikidata.org/wiki/Q3966","display_name":"Computer hardware","level":1,"score":0.4756999909877777},{"id":"https://openalex.org/C86111242","wikidata":"https://www.wikidata.org/wiki/Q859595","display_name":"Coprocessor","level":2,"score":0.43549999594688416},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.41269999742507935},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.36980000138282776},{"id":"https://openalex.org/C118524514","wikidata":"https://www.wikidata.org/wiki/Q173212","display_name":"Computer architecture","level":1,"score":0.3418000042438507},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.3264000117778778},{"id":"https://openalex.org/C58013763","wikidata":"https://www.wikidata.org/wiki/Q5754574","display_name":"High-level synthesis","level":3,"score":0.32010000944137573},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.3107999861240387},{"id":"https://openalex.org/C74193536","wikidata":"https://www.wikidata.org/wiki/Q574844","display_name":"Kernel (algebra)","level":2,"score":0.30300000309944153},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2996000051498413},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.29829999804496765},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.2980000078678131},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.2856000065803528},{"id":"https://openalex.org/C142962650","wikidata":"https://www.wikidata.org/wiki/Q240838","display_name":"Reconfigurable computing","level":3,"score":0.2831000089645386},{"id":"https://openalex.org/C163258240","wikidata":"https://www.wikidata.org/wiki/Q25342","display_name":"Power (physics)","level":2,"score":0.2761000096797943},{"id":"https://openalex.org/C106515295","wikidata":"https://www.wikidata.org/wiki/Q26806595","display_name":"Parallel processing","level":2,"score":0.273499995470047},{"id":"https://openalex.org/C13164978","wikidata":"https://www.wikidata.org/wiki/Q600158","display_name":"Hardware acceleration","level":3,"score":0.2727000117301941},{"id":"https://openalex.org/C13926793","wikidata":"https://www.wikidata.org/wiki/Q3507155","display_name":"Group method of data handling","level":2,"score":0.27230000495910645},{"id":"https://openalex.org/C123593499","wikidata":"https://www.wikidata.org/wiki/Q6008583","display_name":"In-Memory Processing","level":5,"score":0.26190000772476196},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.25920000672340393},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.2572999894618988},{"id":"https://openalex.org/C459310","wikidata":"https://www.wikidata.org/wiki/Q117801","display_name":"Computational science","level":1,"score":0.2567000091075897}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/access.2025.3642938","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3642938","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:354e206a251f4d10ae5be1f7d6eb26d2","is_oa":true,"landing_page_url":"https://doaj.org/article/354e206a251f4d10ae5be1f7d6eb26d2","pdf_url":null,"source":{"id":"https://openalex.org/S4306401280","display_name":"DOAJ (DOAJ: Directory of Open Access Journals)","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":"repository"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 13, Pp 211235-211250 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.1109/access.2025.3642938","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2025.3642938","pdf_url":null,"source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"With":[0],"the":[1,40,57,106,141],"rapid":[2],"success":[3],"and":[4,39,43,69,99,152,166],"development":[5],"of":[6,45,78,108,159],"convolutional":[7],"neural":[8],"networks":[9],"(CNNs),":[10],"there":[11],"is":[12,124],"an":[13,52,91],"increasing":[14],"demand":[15],"for":[16,61,161,164,168],"hardware":[17],"accelerators":[18,27],"that":[19,85,96],"efficiently":[20],"perform":[21],"CNN":[22,25,54,177],"inference.":[23],"FPGA-based":[24,53,176],"inference":[26],"are":[28],"gaining":[29],"popularity":[30],"due":[31],"to":[32,104,126],"their":[33],"high":[34,71],"performance,":[35],"low":[36],"power":[37],"consumption,":[38],"inherent":[41],"reconfigurability":[42],"flexibility":[44],"FPGAs.":[46],"In":[47],"this":[48],"work,":[49],"we":[50],"present":[51],"accelerator":[55,137],"using":[56,146],"multi-computing":[58,113],"engine":[59,114,120],"method":[60],"convolution":[62],"operations,":[63],"focusing":[64],"on":[65,140],"improving":[66],"computing":[67,109,157],"efficiency":[68,158],"achieving":[70],"throughput.":[72],"The":[73,135,170],"architecture":[74],"incorporates":[75],"multiple":[76],"levels":[77],"parallelism,":[79],"a":[80,100,117,156],"cycle-aligned":[81],"data":[82,93,101],"reordering":[83],"unit":[84,123],"keeps":[86],"processing":[87],"elements":[88],"fully":[89,121,132],"utilized,":[90],"inter-layer":[92],"production":[94],"pattern":[95],"prevents":[97],"stalls,":[98],"buffer":[102],"structure,":[103],"address":[105],"causes":[107],"resource":[110],"underutilization":[111],"in":[112,130],"systems.":[115],"Additionally,":[116],"batch-based,":[118],"single-computing":[119],"connected":[122,133],"utilized":[125],"reduce":[127],"DRAM":[128],"accesses":[129],"memory-intensive":[131],"layers.":[134],"proposed":[136,171],"was":[138],"evaluated":[139],"Xilinx":[142],"XC7VX690T":[143],"FPGA":[144],"platform":[145],"three":[147],"benchmark":[148],"models,":[149],"VGG16,":[150,162],"ResNet18,":[151,165],"AlexNet.":[153,169],"It":[154],"achieved":[155],"98.92%":[160],"92.88%":[163],"71.6%":[167],"design":[172],"outperforms":[173],"existing":[174],"state-of-the-art":[175],"accelerators.":[178]},"counts_by_year":[],"updated_date":"2026-06-26T08:34:08.712188","created_date":"2025-12-11T00:00:00"}