{"id":"https://openalex.org/W3190900310","doi":null,"title":"Adaptive Effort Classifiers: A System Design For Partitioned Edge/Cloud Inference","display_name":"Adaptive Effort Classifiers: A System Design For Partitioned Edge/Cloud Inference","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3190900310","mag":"3190900310"},"language":"en","primary_location":{"id":"pmh:oai:academicworks.cuny.edu:cc_etds_theses-1975","doi":null,"is_oa":true,"landing_page_url":"https://academicworks.cuny.edu/cc_etds_theses/937","pdf_url":"https://academicworks.cuny.edu/cgi/viewcontent.cgi?article=1975&context=cc_etds_theses","source":{"id":"https://openalex.org/S4377196304","display_name":"CUNY Academic Works (City University of New York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I174216632","host_organization_name":"City University of New York","host_organization_lineage":["https://openalex.org/I174216632"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dissertations and Theses","raw_type":"thesis"},"volume":null,"type":"dissertation","is_traditional":true,"indexed_in":[],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://academicworks.cuny.edu/cgi/viewcontent.cgi?article=1975&context=cc_etds_theses","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5061989853","display_name":"Divya Sankar","orcid":"https://orcid.org/0009-0006-3209-4154","observed_orcids":["https://orcid.org/0009-0006-3209-4154"]},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Divya Sankar","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":["https://openalex.org/A5061989853"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9926999807357788,"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"}},"topics":[{"id":"https://openalex.org/T10273","display_name":"IoT and Edge/Fog Computing","score":0.9926999807357788,"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/T10036","display_name":"Advanced Neural Network Applications","score":0.00279999990016222,"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/T14098","display_name":"Energy Efficiency in Computing","score":0.0007999999797903001,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/deep-neural-network-inference","display_name":"deep neural network inference","score":0.46799999475479126},{"id":"https://openalex.org/keywords/energy-efficiency","display_name":"energy efficiency","score":0.5619999766349792},{"id":"https://openalex.org/keywords/confidence-threshold","display_name":"confidence threshold","score":0.4560000002384186},{"id":"https://openalex.org/keywords/classifier-chains","display_name":"classifier chains","score":0.652999997138977},{"id":"https://openalex.org/keywords/edge-computing","display_name":"edge computing","score":0.32899999618530273},{"id":"https://openalex.org/keywords/internet-of-things","display_name":"Internet of Things","score":0.8510000109672546},{"id":"https://openalex.org/keywords/data-transmission-reduction","display_name":"data transmission reduction","score":0.41200000047683716}],"concepts":[{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.7013897895812988},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6059918999671936},{"id":"https://openalex.org/C162307627","wikidata":"https://www.wikidata.org/wiki/Q204833","display_name":"Enhanced Data Rates for GSM Evolution","level":2,"score":0.5535988211631775},{"id":"https://openalex.org/C2776214188","wikidata":"https://www.wikidata.org/wiki/Q408386","display_name":"Inference","level":2,"score":0.5203689932823181},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3996109664440155},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.34484797716140747},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.32648134231567383},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.09056752920150757}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:academicworks.cuny.edu:cc_etds_theses-1975","doi":null,"is_oa":true,"landing_page_url":"https://academicworks.cuny.edu/cc_etds_theses/937","pdf_url":"https://academicworks.cuny.edu/cgi/viewcontent.cgi?article=1975&context=cc_etds_theses","source":{"id":"https://openalex.org/S4377196304","display_name":"CUNY Academic Works (City University of New York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I174216632","host_organization_name":"City University of New York","host_organization_lineage":["https://openalex.org/I174216632"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dissertations and Theses","raw_type":"thesis"},{"id":"mag:3190900310","doi":null,"is_oa":false,"landing_page_url":"https://academicworks.cuny.edu/cc_etds_theses/937/","pdf_url":null,"source":null,"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":null}],"best_oa_location":{"id":"pmh:oai:academicworks.cuny.edu:cc_etds_theses-1975","doi":null,"is_oa":true,"landing_page_url":"https://academicworks.cuny.edu/cc_etds_theses/937","pdf_url":"https://academicworks.cuny.edu/cgi/viewcontent.cgi?article=1975&context=cc_etds_theses","source":{"id":"https://openalex.org/S4377196304","display_name":"CUNY Academic Works (City University of New York)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I174216632","host_organization_name":"City University of New York","host_organization_lineage":["https://openalex.org/I174216632"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Dissertations and Theses","raw_type":"thesis"},"sustainable_development_goals":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3190900310.pdf","grobid_xml":"https://content.openalex.org/works/W3190900310.grobid-xml"},"referenced_works_count":31,"referenced_works":["https://openalex.org/W1532826273","https://openalex.org/W1583776211","https://openalex.org/W1598866093","https://openalex.org/W1605005685","https://openalex.org/W1845051632","https://openalex.org/W1922123711","https://openalex.org/W1935978687","https://openalex.org/W1980446076","https://openalex.org/W1998305460","https://openalex.org/W1998917233","https://openalex.org/W2048266589","https://openalex.org/W2060969833","https://openalex.org/W2114766824","https://openalex.org/W2119144962","https://openalex.org/W2125203716","https://openalex.org/W2136836265","https://openalex.org/W2167215970","https://openalex.org/W2172166488","https://openalex.org/W2396813586","https://openalex.org/W2489529491","https://openalex.org/W2495046539","https://openalex.org/W2610140147","https://openalex.org/W2626991402","https://openalex.org/W2883542588","https://openalex.org/W2893813411","https://openalex.org/W2895298874","https://openalex.org/W2950967261","https://openalex.org/W2962677625","https://openalex.org/W2963674932","https://openalex.org/W2964299589","https://openalex.org/W4243928383"],"related_works":["https://openalex.org/W6969084770","https://openalex.org/W4387968598","https://openalex.org/W7163401783","https://openalex.org/W4315629955","https://openalex.org/W4413952606","https://openalex.org/W7128613629","https://openalex.org/W4393186053","https://openalex.org/W4328030459","https://openalex.org/W7198549142","https://openalex.org/W7155405239"],"abstract_inverted_index":{"The":[0,460],"massive":[1],"growth":[2],"in":[3,20,90,227,315,357,385,457,479,541,546],"availability":[4,152],"of":[5,15,37,66,75,136,190,234,244,318,334,343,348,351,399,455,487,517],"real-world":[6],"data":[7,45,102,137,176,235,494,501],"from":[8,40],"connected":[9],"devices":[10,39,43,118],"and":[11,29,47,60,80,108,122,214,238,270,302,359,361,409,441,489,511,530],"the":[12,35,48,64,72,86,91,106,113,133,140,147,169,186,196,206,212,215,221,224,250,263,278,282,287,289,297,300,303,316,328,332,340,344,376,386,394,402,406,413,422,429,433,439,442,453,480,497],"overwhelming":[13],"success":[14],"Deep":[16],"Neural":[17],"Networks":[18],"(DNNs)":[19],"many":[21,228],"ArtificialIntelligence":[22],"(AI)":[23],"tasks":[24],"have":[25],"enabled":[26],"AI-based":[27],"applications":[28,95,129],"services":[30],"to":[31,44,112,139,161,173,185,194,249,254,288,310,330,375,401,451,465,508,539],"become":[32],"commonplace":[33],"across":[34,505],"spectrum":[36],"computing":[38,68],"edge/Internet-of-Things":[41],"(IoT)":[42],"centers":[46],"cloud.":[49,216],"However,":[50],"DNNs":[51,76,518],"incur":[52],"high":[53,157,187],"computational":[54,73,87,188,198,260],"cost":[55,189],"(compute":[56],"operations,":[57],"memory":[58],"footprint":[59],"bandwidth),which":[61],"far":[62],"outstrip":[63],"capabilities":[65],"modern":[67],"platforms.":[69],"Therefore":[70],"improving":[71],"efficiency":[74,88],"wide-spread":[77],"commercial":[78],"deployment":[79],"success.In":[81],"this":[82,295],"thesis,":[83],"we":[84],"address":[85,195],"challenge":[89,199],"context":[92,317],"ofAI":[93],"inference":[94,207,313],"executing":[96],"on":[97,146,168,262,339,363,374,428,438,520],"edge/cloud":[98,203,320],"systems,":[99],"where":[100],"conventionally":[101],"is":[103,178,200,209,223,236,246,253,398,445,503],"sensed":[104,138,237],"at":[105,277],"edge":[107,148,170,213,264,430],"then":[109],"transmitted":[110,286],"wirelessly":[111],"cloud":[114,141,290,440],"for":[115,291,500,526,533],"inference.":[116,321],"Edge":[117],"are":[119,123,285,325,383,410,426,436],"typically":[120],"battery-driven,":[121],"hence":[124],"energy":[125,144,360],"constrained.":[126],"In":[127,418],"always-on":[128],"(e.g.,remote":[130],"surveillance),":[131],"transmitting":[132],"large":[134,232],"amount":[135,233],"incurs":[142],"significant":[143],"penalty":[145],"device.":[149],"Further,":[150],"network":[151],"may":[153],"prohibit":[154],"sustaining":[155],"a":[156,181,231,241,307,349,364,448],"transmission":[158,177],"rate":[159],"required":[160],"meet":[162],"real-time":[163],"constraints.":[164],"Embedding":[165],"intelligence":[166,257],"completely":[167],"device":[171],"itself":[172],"eliminate":[174],"continuous":[175],"also":[179],"not":[180],"viable":[182],"solution":[183],"due":[184],"DNNs.A":[191],"promising":[192],"approach":[193,309],"aforementioned":[197],"through":[201,405],"partitioned":[202,319],"inference,":[204],"wherein":[205,476,496],"application":[208],"split":[210],"between":[211],"A":[217],"key":[218,252],"intuition":[219],"behind":[220],"idea":[222],"observation":[225],"that,":[226],"applications,":[229],"although":[230],"processed,":[239],"only":[240,281],"small":[242],"fraction":[243],"it":[245],"eventually":[247],"important":[248],"end-application.The":[251],"embed":[255],"limited":[256],"(with":[258],"low":[259,391],"cost)":[261],"device,":[265,431],"such":[266],"that":[267,354],"those":[268],"uninteresting":[269],"potentially":[271],"easy-to-classify":[272],"instances":[273],"can":[274],"be":[275],"filtered":[276],"edge,":[279],"while":[280],"interesting":[283],"ones":[284],"more":[292,414,485],"sophisticated":[293],"processing.To":[294],"end,":[296],"thesis":[298,461],"presents":[299],"concept":[301],"design":[304,466],"ofAdaptive":[305],"EffortClassifiers,":[306],"new":[308],"designing":[311],"AI":[312],"classifiers":[314,324],"Adaptive":[322],"effort":[323,335,468,515],"designed":[326],"with":[327,389,472,492,543],"ability":[329],"modulate":[331],"degree":[333],"they":[336],"expend":[337],"based":[338,362],"inherent":[341],"difficulty":[342],"input.":[345],"They":[346],"comprise":[347],"chain":[350,408,482],"classifier":[352,407,424,506],"stages":[353,388,425,435,507],"progressively":[355,484],"grow":[356],"complexity":[358,510],"confidence":[365,449],"threshold,":[366],"each":[367,458,477],"stage":[368,478],"either":[369],"gets":[370],"classified":[371,384,411],"or":[372],"passed":[373],"next":[377],"stage.":[378,459],"Easy":[379],"(or":[380],"uninteresting)":[381],"inputs":[382,396],"initial":[387,423],"very":[390],"effort,":[392],"whereas":[393,432],"harder":[395],"(which":[397],"interest":[400],"application)":[403],"progress":[404],"by":[412],"complex":[415],"final":[416,434],"stages.":[417],"our":[419],"system":[420],"design,":[421],"executed":[427,437],"class":[443],"probability":[444],"used":[446,499],"as":[447],"thresh-old":[450],"tune":[452],"aggressivity":[454],"classification":[456,481],"proposes":[462],"two":[463],"strategies":[464],"adaptive":[467,514],"classifiers:":[469],"(i)":[470],"Classifiers":[471,491],"progressive":[473,493],"feature":[474],"set,":[475],"uses":[483],"number":[486],"features,":[488],"(ii)":[490],"bit-width,":[495],"bit-width":[498],"representation":[502],"modulated":[504],"scale":[509],"accuracy.We":[512],"build":[513],"versions":[516],"trained":[519],"2":[521],"popular":[522],"datasets":[523],"viz.MNIST":[524],"dataset":[525,532],"handwritten":[527],"digit":[528],"recognition":[529],"CIFAR-10":[531],"object":[534],"recognition.":[535],"We":[536],"demonstrate":[537],"up":[538],"3.44\u00d7-11.29\u00d7improvement":[540],"ops":[542],"no":[544],"loss":[545],"accuracy.":[547]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-11-07T11:25:07.637180","created_date":"2021-08-16T00:00:00"}