{"id":"https://openalex.org/W3008463620","doi":"https://doi.org/10.1109/bigdata47090.2019.9006217","title":"Semi-supervised Learning over Streaming Data using MOA","display_name":"Semi-supervised Learning over Streaming Data using MOA","publication_year":2019,"publication_date":"2019-12-01","ids":{"openalex":"https://openalex.org/W3008463620","doi":"https://doi.org/10.1109/bigdata47090.2019.9006217","mag":"3008463620"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata47090.2019.9006217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","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":null,"display_name":"Minh Huong Le Nguyen","orcid":null},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Minh Huong Le Nguyen","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris Institut Polytechnique de Paris, Paris, France"],"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris Institut Polytechnique de Paris, Paris, France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I12356871"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5071380196","display_name":"Heitor Murilo Gomes","orcid":"https://orcid.org/0000-0002-5276-637X"},"institutions":[{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Heitor Murilo Gomes","raw_affiliation_strings":["Department of Computer Science, University of Waikato, Hamilton, New Zealand"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Waikato, Hamilton, New Zealand","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080970505","display_name":"Albert Bifet","orcid":"https://orcid.org/0000-0002-8339-7773"},"institutions":[{"id":"https://openalex.org/I12356871","display_name":"T\u00e9l\u00e9com Paris","ror":"https://ror.org/01naq7912","country_code":"FR","type":"education","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102"]},{"id":"https://openalex.org/I4210165912","display_name":"Laboratoire Traitement et Communication de l\u2019Information","ror":"https://ror.org/057er4c39","country_code":"FR","type":"facility","lineage":["https://openalex.org/I12356871","https://openalex.org/I205703379","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I52179390","display_name":"University of Waikato","ror":"https://ror.org/013fsnh78","country_code":"NZ","type":"education","lineage":["https://openalex.org/I52179390"]}],"countries":["FR","NZ"],"is_corresponding":false,"raw_author_name":"Albert Bifet","raw_affiliation_strings":["LTCI, T\u00e9l\u00e9com Paris Institut Polytechnique de Paris, University of Waikato"],"affiliations":[{"raw_affiliation_string":"LTCI, T\u00e9l\u00e9com Paris Institut Polytechnique de Paris, University of Waikato","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I52179390","https://openalex.org/I12356871"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I12356871","https://openalex.org/I4210165912"],"apc_list":null,"apc_paid":null,"fwci":1.0116,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.83534857,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"553","last_page":"562"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":1.0,"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"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9890000224113464,"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"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","score":0.9832000136375427,"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/computer-science","display_name":"Computer science","score":0.8287749886512756},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.8053734302520752},{"id":"https://openalex.org/keywords/benchmark","display_name":"Benchmark (surveying)","score":0.6968730688095093},{"id":"https://openalex.org/keywords/labeled-data","display_name":"Labeled data","score":0.6432664394378662},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6400802135467529},{"id":"https://openalex.org/keywords/semi-supervised-learning","display_name":"Semi-supervised learning","score":0.6369794011116028},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6001826524734497},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5589350461959839},{"id":"https://openalex.org/keywords/supervised-learning","display_name":"Supervised learning","score":0.5237369537353516},{"id":"https://openalex.org/keywords/unsupervised-learning","display_name":"Unsupervised learning","score":0.5211808085441589},{"id":"https://openalex.org/keywords/data-stream","display_name":"Data stream","score":0.4933246672153473},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4801884889602661},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.47876039147377014},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.45912182331085205},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45470744371414185},{"id":"https://openalex.org/keywords/streaming-data","display_name":"Streaming data","score":0.447787344455719},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.4327133893966675},{"id":"https://openalex.org/keywords/strengths-and-weaknesses","display_name":"Strengths and weaknesses","score":0.412159264087677},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.18871045112609863}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8287749886512756},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.8053734302520752},{"id":"https://openalex.org/C185798385","wikidata":"https://www.wikidata.org/wiki/Q1161707","display_name":"Benchmark (surveying)","level":2,"score":0.6968730688095093},{"id":"https://openalex.org/C2776145971","wikidata":"https://www.wikidata.org/wiki/Q30673951","display_name":"Labeled data","level":2,"score":0.6432664394378662},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6400802135467529},{"id":"https://openalex.org/C58973888","wikidata":"https://www.wikidata.org/wiki/Q1041418","display_name":"Semi-supervised learning","level":2,"score":0.6369794011116028},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6001826524734497},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5589350461959839},{"id":"https://openalex.org/C136389625","wikidata":"https://www.wikidata.org/wiki/Q334384","display_name":"Supervised learning","level":3,"score":0.5237369537353516},{"id":"https://openalex.org/C8038995","wikidata":"https://www.wikidata.org/wiki/Q1152135","display_name":"Unsupervised learning","level":2,"score":0.5211808085441589},{"id":"https://openalex.org/C2778484313","wikidata":"https://www.wikidata.org/wiki/Q1172540","display_name":"Data stream","level":2,"score":0.4933246672153473},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4801884889602661},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.47876039147377014},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.45912182331085205},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45470744371414185},{"id":"https://openalex.org/C2777611316","wikidata":"https://www.wikidata.org/wiki/Q39045282","display_name":"Streaming data","level":2,"score":0.447787344455719},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.4327133893966675},{"id":"https://openalex.org/C63882131","wikidata":"https://www.wikidata.org/wiki/Q17122954","display_name":"Strengths and weaknesses","level":2,"score":0.412159264087677},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.18871045112609863},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C13280743","wikidata":"https://www.wikidata.org/wiki/Q131089","display_name":"Geodesy","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata47090.2019.9006217","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata47090.2019.9006217","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2019 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":28,"referenced_works":["https://openalex.org/W3540556","https://openalex.org/W92894758","https://openalex.org/W1521014365","https://openalex.org/W1562135275","https://openalex.org/W1977456486","https://openalex.org/W2021739900","https://openalex.org/W2028489411","https://openalex.org/W2032432384","https://openalex.org/W2068714596","https://openalex.org/W2101210369","https://openalex.org/W2107056945","https://openalex.org/W2108740451","https://openalex.org/W2122565017","https://openalex.org/W2129767422","https://openalex.org/W2135335717","https://openalex.org/W2136246134","https://openalex.org/W2140234018","https://openalex.org/W2153678935","https://openalex.org/W2170936641","https://openalex.org/W2434851943","https://openalex.org/W2470412537","https://openalex.org/W2602516395","https://openalex.org/W3003253354","https://openalex.org/W6603760306","https://openalex.org/W6631284376","https://openalex.org/W6677987841","https://openalex.org/W6680192438","https://openalex.org/W6719935260"],"related_works":["https://openalex.org/W4312414840","https://openalex.org/W2794908468","https://openalex.org/W4206276646","https://openalex.org/W2943467239","https://openalex.org/W1571801203","https://openalex.org/W101422005","https://openalex.org/W192740413","https://openalex.org/W3004135598","https://openalex.org/W2952937263","https://openalex.org/W2131153761"],"abstract_inverted_index":{"Machine":[0],"learning":[1,14,29,100,124,155],"algorithms":[2],"for":[3,13,98],"data":[4,10,22,40,53,57,102,127,157],"streams":[5,158],"usually":[6],"suppose":[7],"that":[8],"all":[9],"examples":[11,23],"available":[12],"are":[15,24,131],"strictly":[16],"labeled.":[17,27],"Unfortunately,":[18],"in":[19,49,60,101,126],"real-world":[20],"scenarios,":[21],"not":[25],"always":[26],"Semi-supervised":[28],"is":[30,46,58],"a":[31,119],"challenging":[32],"task":[33],"to":[34,69,94,117,121,146,149],"learn":[35],"using":[36],"labeled":[37],"and":[38,62,84,106,112],"unlabeled":[39],"at":[41],"the":[42,50,56,63,77,110,134],"same":[43],"time.":[44],"It":[45],"especially":[47],"relevant":[48],"context":[51],"of":[52,114],"streams,":[54,103],"where":[55],"generated":[59],"real-time,":[61],"labels":[64,97],"may":[65],"be":[66],"missing":[67,96],"due":[68],"various":[70],"factors":[71],"(e.g.,":[72],"network":[73],"delay,":[74],"errors":[75],"during":[76],"communication":[78],"between":[79],"sensors,":[80],"expensive":[81],"labeling":[82],"process,":[83],"others).":[85],"In":[86],"this":[87],"paper,":[88],"we":[89],"present":[90],"two":[91],"novel":[92],"approaches":[93],"handle":[95],"classification":[99],"namely":[104],"cluster-and-label":[105],"self-training.":[107],"We":[108],"discuss":[109],"strengths":[111],"weaknesses":[113],"each":[115],"solution":[116],"establish":[118],"baseline":[120],"evaluate":[122],"semi-supervised":[123,154],"techniques":[125],"streams.":[128],"These":[129],"methods":[130],"implemented":[132],"inside":[133],"MOA":[135],"(Massive":[136],"Online":[137],"Analysis)":[138],"open-source":[139],"software":[140],"as":[141],"an":[142],"internal":[143],"benchmark":[144],"component,":[145],"help":[147],"researchers":[148],"run":[150],"experimental":[151],"comparisons":[152],"on":[153,156],"easily.":[159]},"counts_by_year":[{"year":2025,"cited_by_count":5},{"year":2024,"cited_by_count":3},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":3},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-16T08:26:57.006410","created_date":"2025-10-10T00:00:00"}