{"id":"https://openalex.org/W2608289103","doi":"https://doi.org/10.1109/icpr.2016.7899683","title":"Distributed data augmented support vector machine on Spark","display_name":"Distributed data augmented support vector machine on Spark","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2608289103","doi":"https://doi.org/10.1109/icpr.2016.7899683","mag":"2608289103"},"language":"en","primary_location":{"id":"doi:10.1109/icpr.2016.7899683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7899683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://figshare.com/articles/conference_contribution/Distributed_data_augmented_support_vector_machine_on_spark/20850769","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5103252932","display_name":"Tu Dinh Nguyen","orcid":"https://orcid.org/0000-0002-9281-8613"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":true,"raw_author_name":"Tu Dinh Nguyen","raw_affiliation_strings":["Center for Pattern Recognition and Data Analytics, Deakin University, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101775198","display_name":"Vu Nguyen","orcid":"https://orcid.org/0000-0002-0294-4561"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Vu Nguyen","raw_affiliation_strings":["Center for Pattern Recognition and Data Analytics, Deakin University, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102780660","display_name":"Trung Le","orcid":"https://orcid.org/0000-0003-0414-9067"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Trung Le","raw_affiliation_strings":["Center for Pattern Recognition and Data Analytics, Deakin University, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036447132","display_name":"Dinh Phung","orcid":"https://orcid.org/0000-0002-9977-8247"},"institutions":[{"id":"https://openalex.org/I149704539","display_name":"Deakin University","ror":"https://ror.org/02czsnj07","country_code":"AU","type":"education","lineage":["https://openalex.org/I149704539"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Dinh Phung","raw_affiliation_strings":["Center for Pattern Recognition and Data Analytics, Deakin University, Australia"],"affiliations":[{"raw_affiliation_string":"Center for Pattern Recognition and Data Analytics, Deakin University, Australia","institution_ids":["https://openalex.org/I149704539"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5103252932"],"corresponding_institution_ids":["https://openalex.org/I149704539"],"apc_list":null,"apc_paid":null,"fwci":3.1039,"has_fulltext":false,"cited_by_count":9,"citation_normalized_percentile":{"value":0.93429124,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":"10","issue":null,"first_page":"498","last_page":"503"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9998999834060669,"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":0.9998999834060669,"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":0.9994000196456909,"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":0.9959999918937683,"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/spark","display_name":"SPARK (programming language)","score":0.8795437216758728},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.8790585994720459},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8371686935424805},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7900371551513672},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6026203036308289},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5654904246330261},{"id":"https://openalex.org/keywords/scale","display_name":"Scale (ratio)","score":0.4934503138065338},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4883689284324646},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.4373801350593567},{"id":"https://openalex.org/keywords/structured-support-vector-machine","display_name":"Structured support vector machine","score":0.4283289313316345},{"id":"https://openalex.org/keywords/term","display_name":"Term (time)","score":0.41191965341567993},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2219003438949585}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8795437216758728},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.8790585994720459},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8371686935424805},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7900371551513672},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6026203036308289},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5654904246330261},{"id":"https://openalex.org/C2778755073","wikidata":"https://www.wikidata.org/wiki/Q10858537","display_name":"Scale (ratio)","level":2,"score":0.4934503138065338},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4883689284324646},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.4373801350593567},{"id":"https://openalex.org/C125168437","wikidata":"https://www.wikidata.org/wiki/Q7625184","display_name":"Structured support vector machine","level":3,"score":0.4283289313316345},{"id":"https://openalex.org/C61797465","wikidata":"https://www.wikidata.org/wiki/Q1188986","display_name":"Term (time)","level":2,"score":0.41191965341567993},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2219003438949585},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icpr.2016.7899683","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icpr.2016.7899683","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 23rd International Conference on Pattern Recognition (ICPR)","raw_type":"proceedings-article"},{"id":"pmh:oai:dro.deakin.edu.au:DU:30097143","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402457","display_name":"Deakin Research Online (Deakin University)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I149704539","host_organization_name":"Deakin University","host_organization_lineage":["https://openalex.org/I149704539"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"},{"id":"pmh:oai:figshare.com:article/20850769","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Distributed_data_augmented_support_vector_machine_on_spark/20850769","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"}],"best_oa_location":{"id":"pmh:oai:figshare.com:article/20850769","is_oa":true,"landing_page_url":"https://figshare.com/articles/conference_contribution/Distributed_data_augmented_support_vector_machine_on_spark/20850769","pdf_url":null,"source":{"id":"https://openalex.org/S4377196282","display_name":"Figshare","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I4210132348","host_organization_name":"Figshare (United Kingdom)","host_organization_lineage":["https://openalex.org/I4210132348"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Text"},"sustainable_development_goals":[{"score":0.6200000047683716,"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":23,"referenced_works":["https://openalex.org/W64238590","https://openalex.org/W410850256","https://openalex.org/W1512098439","https://openalex.org/W1552828154","https://openalex.org/W1838330068","https://openalex.org/W1964357740","https://openalex.org/W1973682096","https://openalex.org/W2028870622","https://openalex.org/W2059503458","https://openalex.org/W2089442574","https://openalex.org/W2173213060","https://openalex.org/W2189465200","https://openalex.org/W2214123151","https://openalex.org/W2575676263","https://openalex.org/W2585527639","https://openalex.org/W3102221121","https://openalex.org/W4239510810","https://openalex.org/W6602547664","https://openalex.org/W6630527977","https://openalex.org/W6638807358","https://openalex.org/W6673375266","https://openalex.org/W6687322159","https://openalex.org/W6732337159"],"related_works":["https://openalex.org/W2891888092","https://openalex.org/W2889616422","https://openalex.org/W2900588685","https://openalex.org/W2782700877","https://openalex.org/W2101819884","https://openalex.org/W4200331753","https://openalex.org/W2974335793","https://openalex.org/W2539163683","https://openalex.org/W1996541855","https://openalex.org/W4361795583"],"abstract_inverted_index":{"Support":[0],"vector":[1,111],"machines":[2],"(SVMs)":[3],"are":[4,53,197],"widely-used":[5],"for":[6,44,63,80,91],"classification":[7,117,146],"in":[8,99,104],"machine":[9,112],"learning":[10],"and":[11,42,56,88,118],"data":[12,32,66,77,125,138,150,184],"mining":[13],"tasks.":[14],"However,":[15],"they":[16],"traditionally":[17],"have":[18,153,156],"been":[19,70,96],"applied":[20],"to":[21,23,28,38,46,135],"small":[22],"medium":[24],"datasets.":[25],"Recent":[26],"need":[27],"scale":[29],"up":[30],"with":[31,65,139,178],"size":[33],"has":[34,68,95],"attracted":[35],"research":[36,100],"attention":[37],"develop":[39,132],"new":[40,55,140,149],"methods":[41],"implementation":[43,62,79,109],"SVM":[45,64,81],"perform":[47],"tasks":[48,120],"at":[49,212],"scale.":[50],"Distributed":[51],"SVMs":[52],"relatively":[54],"studied":[57],"recently,":[58],"but":[59],"the":[60,124,137,169,191,206],"distributed":[61,76,92],"augmentation":[67,78],"not":[69,157],"developed.":[71],"This":[72],"paper":[73],"introduces":[74],"a":[75,85,133,161],"on":[82,175],"Apache":[83],"Spark,":[84],"recent":[86],"advanced":[87],"popular":[89],"platform":[90],"computing":[93],"that":[94,155,190],"employed":[97],"widely":[98],"as":[101,103],"well":[102],"industry.":[105],"We":[106,167],"term":[107,164],"our":[108,172,195],"sparkling":[110],"(SkVM)":[113],"which":[114],"supports":[115],"both":[116],"regression":[119],"by":[121],"scanning":[122],"through":[123],"exactly":[126],"once.":[127],"In":[128],"addition,":[129],"we":[130,163],"further":[131],"framework":[134],"handle":[136],"classes":[141],"arriving":[142],"under":[143],"an":[144,213],"online":[145],"setting":[147],"where":[148],"points":[151],"can":[152],"labels":[154],"previously":[158],"seen":[159],"-":[160],"problem":[162],"label-drift":[165],"classification.":[166],"demonstrate":[168],"scalability":[170],"of":[171,194,203,215],"proposed":[173],"method":[174,196],"large-scale":[176],"datasets":[177],"more":[179],"than":[180,201],"one":[181],"hundred":[182],"million":[183],"points.":[185],"The":[186],"experimental":[187],"results":[188],"show":[189],"predictive":[192],"performances":[193],"comparable":[198],"or":[199],"better":[200],"those":[202],"baselines":[204],"whilst":[205],"execution":[207],"time":[208],"is":[209],"much":[210],"faster":[211],"order":[214],"magnitude.":[216]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}