{"id":"https://openalex.org/W7219929214","doi":null,"title":"Optimized Lightweight CNN Architectures for Real-Time Inference on Edge and Embedded Devices","display_name":"Optimized Lightweight CNN Architectures for Real-Time Inference on Edge and Embedded Devices","alternate_titles":[],"publication_year":2023,"publication_date":"2023-12-03","ids":{"openalex":"https://openalex.org/W7219929214"},"language":"en","primary_location":{"id":"pmh:oai:oai.eccsubmit.com:article/11","doi":null,"is_oa":true,"landing_page_url":"https://eccsubmit.com/index.php/congress/article/view/11","pdf_url":"https://eccsubmit.com/index.php/congress/article/download/11/231","source":{"id":"https://openalex.org/S7407075903","display_name":"Electronics, Communications, and Computing Summit","issn_l":"3107-8222","issn":["3107-8222"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3107-8222","raw_type":"info:eu-repo/semantics/article"},"parent_works":[],"lineage":["https://openalex.org/W7219929214"],"child_works_count":0,"type":"article","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://eccsubmit.com/index.php/congress/article/download/11/231","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5006253877","display_name":"Sarkhosh Seddighi Chaharborj","orcid":"https://orcid.org/0000-0001-5894-6622","observed_orcids":["https://orcid.org/0000-0001-5894-6622"]},"institutions":[{"id":"https://openalex.org/I130343225","display_name":"Universiti Putra Malaysia","ror":"https://ror.org/02e91jd64","country_code":"MY","type":"education","lineage":["https://openalex.org/I130343225"]},{"id":"https://openalex.org/I4392738327","display_name":"Nuclear Science and Technology Research Institute","ror":"https://ror.org/05cebxq10","country_code":"IR","type":"government","lineage":["https://openalex.org/I102962589","https://openalex.org/I4392738327"]}],"countries":["IR","MY"],"is_corresponding":true,"raw_author_name":"Sarkhosh Seddighi Chaharborj","raw_affiliation_strings":["Department of Mathematics, UPM, Malaysia. Nuclear Science Research School, Nuclear Science and Technology Research Institute (NSTRI), Iran"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Mathematics, UPM, Malaysia. Nuclear Science Research School, Nuclear Science and Technology Research Institute (NSTRI), Iran","institution_ids":["https://openalex.org/I130343225","https://openalex.org/I4392738327"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5006253877"],"corresponding_institution_ids":["https://openalex.org/I130343225","https://openalex.org/I4392738327"],"apc_list":null,"apc_paid":null,"fwci":0.128,"has_fulltext":true,"cited_by_count":2,"citation_normalized_percentile":{"value":0.2918536,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":94,"max":96},"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_pulled":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10036","display_name":"Advanced Neural Network Applications","score":0.9994999766349792,"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":0.9994999766349792,"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":0.0003000000142492354,"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/T11307","display_name":"Domain Adaptation and Few-Shot Learning","score":0.0,"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/lightweight-convolutional-neural-network","display_name":"lightweight convolutional neural network","score":0.949999988079071},{"id":"https://openalex.org/keywords/edge-computing","display_name":"edge computing","score":0.8080000281333923},{"id":"https://openalex.org/keywords/embedded-devices","display_name":"embedded devices","score":0.8059999942779541},{"id":"https://openalex.org/keywords/real-time-inference","display_name":"real-time inference","score":0.9359999895095825},{"id":"https://openalex.org/keywords/model-compression","display_name":"model compression","score":0.9509999752044678},{"id":"https://openalex.org/keywords/structured-pruning","display_name":"structured pruning","score":0.8690000176429749},{"id":"https://openalex.org/keywords/8-bit-quantization","display_name":"8-bit quantization","score":0.9990000128746033},{"id":"https://openalex.org/keywords/knowledge-distillation","display_name":"knowledge distillation","score":1.0},{"id":"https://openalex.org/keywords/depthwise-separable-convolution","display_name":"depthwise separable convolution","score":0.8980000019073486},{"id":"https://openalex.org/keywords/nvidia-jetson-nano","display_name":"Jetson Nano","score":0.7829999923706055},{"id":"https://openalex.org/keywords/raspberry-pi-4","display_name":"Raspberry Pi 4","score":0.9240000247955322},{"id":"https://openalex.org/keywords/latency-reduction","display_name":"latency reduction","score":0.6940000057220459},{"id":"https://openalex.org/keywords/energy-efficiency","display_name":"energy efficiency","score":0.9200000166893005},{"id":"https://openalex.org/keywords/object-detection","display_name":"object detection","score":0.7260000109672546},{"id":"https://openalex.org/keywords/surveillance","display_name":"surveillance","score":0.4959999918937683},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.7519999742507935}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7674000263214111},{"id":"https://openalex.org/C138236772","wikidata":"https://www.wikidata.org/wiki/Q25098575","display_name":"Edge device","level":3,"score":0.7222999930381775},{"id":"https://openalex.org/C81363708","wikidata":"https://www.wikidata.org/wiki/Q17084460","display_name":"Convolutional neural network","level":2,"score":0.6107000112533569},{"id":"https://openalex.org/C2778456923","wikidata":"https://www.wikidata.org/wiki/Q5337692","display_name":"Edge computing","level":3,"score":0.5300999879837036},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.4941999912261963},{"id":"https://openalex.org/C111335779","wikidata":"https://www.wikidata.org/wiki/Q3454686","display_name":"Reduction (mathematics)","level":2,"score":0.48649999499320984},{"id":"https://openalex.org/C113775141","wikidata":"https://www.wikidata.org/wiki/Q428691","display_name":"Computer engineering","level":1,"score":0.48489999771118164},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.45879998803138733},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.4481000006198883},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.4361000061035156},{"id":"https://openalex.org/C157764524","wikidata":"https://www.wikidata.org/wiki/Q1383412","display_name":"Throughput","level":3,"score":0.4323999881744385},{"id":"https://openalex.org/C177212765","wikidata":"https://www.wikidata.org/wiki/Q627335","display_name":"Workflow","level":2,"score":0.4138999879360199},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.41200000047683716},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.4050000011920929},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.3991999924182892},{"id":"https://openalex.org/C96324660","wikidata":"https://www.wikidata.org/wiki/Q205446","display_name":"Dataflow","level":2,"score":0.38420000672340393},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.3578000068664551},{"id":"https://openalex.org/C157170001","wikidata":"https://www.wikidata.org/wiki/Q4781507","display_name":"Applications of artificial intelligence","level":2,"score":0.35740000009536743},{"id":"https://openalex.org/C82876162","wikidata":"https://www.wikidata.org/wiki/Q17096504","display_name":"Latency (audio)","level":2,"score":0.34529998898506165},{"id":"https://openalex.org/C46637626","wikidata":"https://www.wikidata.org/wiki/Q6693015","display_name":"Low latency (capital markets)","level":2,"score":0.3434000015258789},{"id":"https://openalex.org/C105339364","wikidata":"https://www.wikidata.org/wiki/Q2297740","display_name":"Software deployment","level":2,"score":0.3400000035762787},{"id":"https://openalex.org/C2776151529","wikidata":"https://www.wikidata.org/wiki/Q3045304","display_name":"Object detection","level":3,"score":0.3084000051021576},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.30239999294281006},{"id":"https://openalex.org/C149635348","wikidata":"https://www.wikidata.org/wiki/Q193040","display_name":"Embedded system","level":1,"score":0.30219998955726624},{"id":"https://openalex.org/C79403827","wikidata":"https://www.wikidata.org/wiki/Q3988","display_name":"Real-time computing","level":1,"score":0.29660001397132874},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.2802000045776367},{"id":"https://openalex.org/C2742236","wikidata":"https://www.wikidata.org/wiki/Q924713","display_name":"Efficient energy use","level":2,"score":0.27459999918937683},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.2533000111579895}],"mesh":[],"locations_count":1,"locations":[{"id":"pmh:oai:oai.eccsubmit.com:article/11","doi":null,"is_oa":true,"landing_page_url":"https://eccsubmit.com/index.php/congress/article/view/11","pdf_url":"https://eccsubmit.com/index.php/congress/article/download/11/231","source":{"id":"https://openalex.org/S7407075903","display_name":"Electronics, Communications, and Computing Summit","issn_l":"3107-8222","issn":["3107-8222"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3107-8222","raw_type":"info:eu-repo/semantics/article"}],"best_oa_location":{"id":"pmh:oai:oai.eccsubmit.com:article/11","doi":null,"is_oa":true,"landing_page_url":"https://eccsubmit.com/index.php/congress/article/view/11","pdf_url":"https://eccsubmit.com/index.php/congress/article/download/11/231","source":{"id":"https://openalex.org/S7407075903","display_name":"Electronics, Communications, and Computing Summit","issn_l":"3107-8222","issn":["3107-8222"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"3107-8222","raw_type":"info:eu-repo/semantics/article"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W7219929214.pdf","grobid_xml":"https://content.openalex.org/works/W7219929214.grobid-xml"},"referenced_works_count":7,"referenced_works":["https://openalex.org/W1821462560","https://openalex.org/W2119144962","https://openalex.org/W2612445135","https://openalex.org/W2752037867","https://openalex.org/W2963125010","https://openalex.org/W2967733054","https://openalex.org/W4394670654"],"related_works":["https://openalex.org/W7219926051","https://openalex.org/W7155373200","https://openalex.org/W4415443973","https://openalex.org/W7153155350","https://openalex.org/W4413461801","https://openalex.org/W3214980411","https://openalex.org/W4414956863","https://openalex.org/W4377001532","https://openalex.org/W7165119474","https://openalex.org/W7115195140"],"abstract_inverted_index":{"The":[0,71,164,290,323],"edge":[1,55,240,269,335],"computing":[2],"paradigm":[3],"has":[4],"become":[5],"central":[6],"in":[7,30,47,268,282,302],"reversing":[8],"the":[9,17,39,42,54,78,89,93,126,138,149,191,233,245,262,294,298,334,337,342,345],"distance":[10],"between":[11,156],"artificial":[12],"intelligence":[13],"(AI)":[14],"application":[15,221],"and":[16,56,68,119,134,158,182,200,214,318],"data":[18],"source":[19],"by":[20,227,250],"bringing":[21],"them":[22],"near":[23],"to":[24,53,86,172,177,184,190,239,261,296,326,344],"one":[25],"another,":[26],"facilitating":[27],"quick":[28],"decisions":[29],"real":[31],"time":[32],"frameworks,":[33],"an":[34,74],"energy-efficient":[35],"decision-making":[36],"process.":[37],"Nevertheless,":[38],"deployment":[40],"of":[41,77,92,222,236,264,286,329],"traditional":[43],"deep":[44,287],"learning":[45,288],"models,":[46],"particular,":[48],"convolutional":[49],"neural":[50],"networks":[51],"(CNNs)":[52],"embedded":[57,347],"devices":[58,97],"is":[59,84,225,336],"a":[60,109,123,153,219,228,274,283],"major":[61,205],"challenge":[62,328],"since":[63],"they":[64],"require":[65],"high":[66],"computational":[67],"memory":[69,211],"capacities.":[70],"paper":[72],"develops":[73],"efficient":[75],"architecture":[76],"lightweight":[79],"CNN":[80],"whose":[81],"main":[82],"input":[83],"made":[85],"focus":[87],"on":[88,95,204,333],"real-time":[90,246],"interpretation":[91],"process":[94],"resource-limited":[96],"like":[98,141,304],"NVIDIA":[99],"Jetson":[100],"Nano":[101],"or":[102,143],"Raspberry":[103],"Pi":[104],"4.":[105],"Our":[106],"strategy":[107,112],"involves":[108],"multi-pronged":[110],"model-compression":[111],"that":[113,148,231,243,278,340],"incorporates":[114],"structured":[115],"pruning,":[116],"8-bit":[117],"quantization,":[118],"knowledge":[120],"distillation":[121],"into":[122],"combination":[124],"with":[125],"current":[127],"architectural":[128],"innovation":[129],"components":[130],"depth-wise":[131],"separable":[132],"convolutions":[133],"grouped":[135],"layers.":[136],"On":[137],"benchmark":[139],"datasets,":[140],"CIFAR-10":[142],"Tiny":[144],"ImageNet,":[145],"we":[146],"show":[147,152],"models":[150,238],"proposed":[151,338],"good":[154],"trade-off":[155],"efficiency":[157],"accuracy":[159,170],"through":[160],"wide":[161,284],"experimental":[162],"studies.":[163],"optimized":[165],"CNNs":[166,267],"achieve":[167,175],"competitive":[168],"classification":[169],"(up":[171],"90.1%),":[173],"but":[174,271],"up":[176,183,293],"65":[178],"percent":[179,186],"latency":[180,319],"reduction":[181,188],"45":[185],"energy":[187],"compared":[189],"uncompressed":[192],"CNNs.":[193],"We":[194],"also":[195,272],"perform":[196],"actual":[197],"device":[198],"validation":[199],"evaluate":[201],"performance":[202],"based":[203],"metrics":[206],"such":[207],"as":[208],"model":[209],"size,":[210],"footprint,":[212],"throughput":[213],"power":[215],"consumption.":[216],"In":[217],"addition,":[218],"real-world":[220],"machine":[223],"surveillance":[224],"provided":[226],"case":[229],"study":[230,256],"demonstrates":[232],"real-life":[234],"applicability":[235],"our":[237],"AI":[241,332],"applications":[242],"exceed":[244],"object":[247],"detection":[248],"capabilities":[249],"using":[251],"less":[252],"total":[253],"power.":[254],"This":[255],"does":[257],"not":[258],"only":[259],"point":[260],"viability":[263],"light":[265],"weight":[266],"inference":[270],"generates":[273],"scalable":[275],"optimization":[276],"pipeline":[277],"can":[279],"be":[280],"used":[281],"variety":[285],"architectures.":[289],"results":[291],"open":[292],"possibility":[295],"applying":[297],"robust":[299,330],"intelligent":[300],"systems":[301],"areas":[303,314],"health":[305],"tracking,":[306],"autonomous":[307],"platforms,":[308],"Internet-of-Things":[309],"(IoT)":[310],"setups,":[311],"among":[312],"other":[313],"where":[315],"performance,":[316],"energy,":[317],"are":[320],"key":[321],"factors.":[322],"tempting":[324],"solution":[325],"this":[327],"low-power":[331],"framework":[339],"paves":[341],"way":[343],"next-generation":[346],"intelligence.":[348]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W7219929214","counts_by_year":[{"year":2026,"cited_by_count":2}],"updated_date":"2026-11-16T12:05:36.265796","created_date":"2026-10-05T00:00:00"}
