{"id":"https://openalex.org/W4318148061","doi":"https://doi.org/10.1109/bigdata55660.2022.10020438","title":"StreamFlow: A System for Summarizing and Learning Over Industrial Big Data Streams","display_name":"StreamFlow: A System for Summarizing and Learning Over Industrial Big Data Streams","publication_year":2022,"publication_date":"2022-12-17","ids":{"openalex":"https://openalex.org/W4318148061","doi":"https://doi.org/10.1109/bigdata55660.2022.10020438"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata55660.2022.10020438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020438","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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 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":"https://openalex.org/A5109625719","display_name":"Mariam Barry","orcid":null},"institutions":[{"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/I4210145102","https://openalex.org/I4210145102","https://openalex.org/I4210165912"]},{"id":"https://openalex.org/I95549939","display_name":"BNP Paribas (France)","ror":"https://ror.org/02v616z87","country_code":"FR","type":"company","lineage":["https://openalex.org/I95549939"]}],"countries":["FR"],"is_corresponding":true,"raw_author_name":"Mariam Barry","raw_affiliation_strings":["ITG Production Data, BNP Paribas,LTCI, Institut Polytechnique de Paris,Palaiseau,France"],"affiliations":[{"raw_affiliation_string":"ITG Production Data, BNP Paribas,LTCI, Institut Polytechnique de Paris,Palaiseau,France","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I95549939"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5070595978","display_name":"Saad El Jaouhari","orcid":"https://orcid.org/0000-0002-1938-9963"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Saad El Jaouhari","raw_affiliation_strings":["Ecole d’Ingénieur du Numérique,LISITE, ISEP,Paris,France"],"affiliations":[{"raw_affiliation_string":"Ecole d’Ingénieur du Numérique,LISITE, ISEP,Paris,France","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5080970505","display_name":"Albert Bifet","orcid":"https://orcid.org/0000-0002-8339-7773"},"institutions":[{"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/I4210145102","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":["AI Institute, University of Waikato,LTCI, Institut Polytechnique de Paris,Hamilton,New Zealand"],"affiliations":[{"raw_affiliation_string":"AI Institute, University of Waikato,LTCI, Institut Polytechnique de Paris,Hamilton,New Zealand","institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5042593186","display_name":"Jacob Montiel","orcid":"https://orcid.org/0000-0003-2245-0718"},"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":"Jacob Montiel","raw_affiliation_strings":["University of Waikato,AI Institute,Seattle,USA","University of Waikato [Hamilton] (Hillcrest, Hamilton 3216 - New Zealand)"],"affiliations":[{"raw_affiliation_string":"University of Waikato,AI Institute,Seattle,USA","institution_ids":["https://openalex.org/I52179390"]},{"raw_affiliation_string":"University of Waikato [Hamilton] (Hillcrest, Hamilton 3216 - New Zealand)","institution_ids":["https://openalex.org/I52179390"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5040314737","display_name":"Eric Guerizec","orcid":null},"institutions":[{"id":"https://openalex.org/I95549939","display_name":"BNP Paribas (France)","ror":"https://ror.org/02v616z87","country_code":"FR","type":"company","lineage":["https://openalex.org/I95549939"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Eric Guerizec","raw_affiliation_strings":["BNP Paribas,IT Group Production Data,Montreuil,France"],"affiliations":[{"raw_affiliation_string":"BNP Paribas,IT Group Production Data,Montreuil,France","institution_ids":["https://openalex.org/I95549939"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068533827","display_name":"Raja Chiky","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Raja Chiky","raw_affiliation_strings":["3DS OUTSCALE, France,ISEP, Ecole d’Ingénieur du Numérique,Paris,France"],"affiliations":[{"raw_affiliation_string":"3DS OUTSCALE, France,ISEP, Ecole d’Ingénieur du Numérique,Paris,France","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5109625719"],"corresponding_institution_ids":["https://openalex.org/I4210165912","https://openalex.org/I95549939"],"apc_list":null,"apc_paid":null,"fwci":0.3118,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.53926955,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":91,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"2198","last_page":"2205"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9990000128746033,"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":0.9990000128746033,"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":0.9984999895095825,"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/T11719","display_name":"Data Quality and Management","score":0.991100013256073,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7709212303161621},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7629872560501099},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.6937522292137146},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6049966216087341},{"id":"https://openalex.org/keywords/automatic-summarization","display_name":"Automatic summarization","score":0.5865786075592041},{"id":"https://openalex.org/keywords/stream-processing","display_name":"Stream processing","score":0.5802242755889893},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5129013061523438},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4931928515434265},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.47861188650131226},{"id":"https://openalex.org/keywords/feature-engineering","display_name":"Feature engineering","score":0.47219786047935486},{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.43435657024383545},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.4137773811817169},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3721635341644287},{"id":"https://openalex.org/keywords/deep-learning","display_name":"Deep learning","score":0.340467631816864},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.24473246932029724},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.17431896924972534}],"concepts":[{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7709212303161621},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7629872560501099},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.6937522292137146},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6049966216087341},{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.5865786075592041},{"id":"https://openalex.org/C107027933","wikidata":"https://www.wikidata.org/wiki/Q2006448","display_name":"Stream processing","level":2,"score":0.5802242755889893},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5129013061523438},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4931928515434265},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.47861188650131226},{"id":"https://openalex.org/C2778827112","wikidata":"https://www.wikidata.org/wiki/Q22245680","display_name":"Feature engineering","level":3,"score":0.47219786047935486},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.43435657024383545},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.4137773811817169},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3721635341644287},{"id":"https://openalex.org/C108583219","wikidata":"https://www.wikidata.org/wiki/Q197536","display_name":"Deep learning","level":2,"score":0.340467631816864},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.24473246932029724},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.17431896924972534},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata55660.2022.10020438","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata55660.2022.10020438","pdf_url":null,"source":{"id":"https://openalex.org/S4363607709","display_name":"2022 IEEE International Conference on Big Data (Big Data)","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 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:HAL:hal-04468397v1","is_oa":false,"landing_page_url":"https://hal.science/hal-04468397","pdf_url":null,"source":{"id":"https://openalex.org/S4406922461","display_name":"SPIRE - Sciences Po Institutional REpository","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":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE International Conference on Big Data, Big Data 2022, Osaka, Japan, December 17-20, 2022, Dec 2022, Osaka, Japan. pp.2198--2205, ⟨10.1109/BIGDATA55660.2022.10020438⟩","raw_type":"Conference papers"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.5899999737739563,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W2074144235","https://openalex.org/W2101234009","https://openalex.org/W2110990494","https://openalex.org/W2126490564","https://openalex.org/W2545001194","https://openalex.org/W2550505910","https://openalex.org/W2616271757","https://openalex.org/W2765312595","https://openalex.org/W2805197914","https://openalex.org/W2941833233","https://openalex.org/W2963306329","https://openalex.org/W2971134149","https://openalex.org/W3015539140","https://openalex.org/W3034987706","https://openalex.org/W3041297593","https://openalex.org/W3094421101","https://openalex.org/W3110709587","https://openalex.org/W3111828510","https://openalex.org/W3131298000","https://openalex.org/W4289764914"],"related_works":["https://openalex.org/W3190734578","https://openalex.org/W1595351371","https://openalex.org/W91065195","https://openalex.org/W3191523773","https://openalex.org/W2964556660","https://openalex.org/W2082671441","https://openalex.org/W2605169415","https://openalex.org/W180351855","https://openalex.org/W2538312128","https://openalex.org/W2904574017"],"abstract_inverted_index":{"The":[0,121,165],"growing":[1],"need":[2],"for":[3,71,101,155,162],"predictive":[4,30,240],"analytics":[5],"over":[6,104],"streaming":[7],"data":[8,19,24,45,57,95,106,222],"in":[9,141,173,208,227,235],"the":[10,125,133,186,213],"industry":[11],"requires":[12,52],"a":[13,128,174],"flexible":[14],"and":[15,41,48,62,136,158,188,206],"continuously":[16],"scalable":[17],"big":[18,23,72,105],"system.":[20],"In":[21,87,212],"real-time":[22,156],"applications":[25,149],"(cybersecurity,":[26],"AIOps,":[27],"anomaly":[28],"detection,":[29],"maintenance,":[31],"IoT":[32],"etc.),":[33],"efficient":[34],"machine":[35,142,160,203,217],"learning":[36,103,143,161,204,218],"models":[37,70,80],"must":[38],"be":[39],"trained":[40],"industrialized":[42],"within":[43,171],"existing":[44,83],"processing":[46,177],"plat-forms":[47],"industrial":[49,84,99,210],"tools.":[50],"This":[51],"interoperability":[53],"between":[54],"various":[55],"components:":[56],"collection,":[58],"processing,":[59,199],"summarization,":[60,200],"modelling":[61],"analytics.":[63],"Existing":[64],"works":[65],"focus":[66],"on":[67],"building":[68],"AI":[69],"data,":[73],"neglecting":[74],"real-world":[75,148],"challenges":[76,100],"when":[77],"integrating":[78],"such":[79,150],"into":[81],"an":[82,93,111,209],"production":[85,172],"framework.":[86],"this":[88],"paper,":[89],"we":[90,146],"propose":[91,110],"StreamFlow,":[92],"operational":[94],"pipeline":[96],"to":[97,117,139,229],"address":[98],"continuous":[102],"streams.":[107],"We":[108],"also":[109],"online":[112,159],"method":[113],"using":[114,220],"sliding":[115],"windows":[116],"summarize":[118],"high-velocity":[119],"data.":[120],"final":[122],"result":[123],"of":[124,179,190,202,215,232],"framework":[126],"is":[127,137],"feature":[129,153],"vector":[130],"that":[131],"describes":[132],"underlying":[134],"processes":[135],"ready":[138],"use":[140],"tasks.":[144],"Moreover,":[145],"showcase":[147],"as":[151],"automated":[152],"engineering":[154],"monitoring":[157],"event":[163],"classification.":[164],"proposed":[166],"system":[167],"has":[168],"been":[169],"deployed":[170],"banking":[175],"system,":[176],"billions":[178],"daily":[180],"traffic":[181],"operations.":[182],"Our":[183],"experiments":[184],"demonstrate":[185],"effectiveness":[187,207],"performance":[189,205],"our":[191],"approach":[192],"by":[193,224],"evaluating":[194],"it":[195],"at":[196],"different":[197],"levels:":[198],"improvement":[201],"setting.":[211],"case":[214],"downstream":[216],"tasks,":[219],"summarized":[221],"generated":[223],"StreamFlow":[225],"results":[226],"up":[228],"2":[230],"orders":[231],"magnitude":[233],"speedups":[234],"training":[236],"time":[237],"without":[238],"compromising":[239],"performance.":[241]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2023,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}