{"id":"https://openalex.org/W2027355980","doi":"https://doi.org/10.1145/2133360.2133364","title":"A Modular Machine Learning System for Flow-Level Traffic Classification in Large Networks","display_name":"A Modular Machine Learning System for Flow-Level Traffic Classification in Large Networks","publication_year":2012,"publication_date":"2012-03-01","ids":{"openalex":"https://openalex.org/W2027355980","doi":"https://doi.org/10.1145/2133360.2133364","mag":"2027355980"},"language":"en","primary_location":{"id":"doi:10.1145/2133360.2133364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2133360.2133364","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-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/A5101683942","display_name":"Yu Jin","orcid":"https://orcid.org/0009-0005-1248-0798"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Yu Jin","raw_affiliation_strings":["University of Minnesota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota","institution_ids":["https://openalex.org/I2800403580"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5048558842","display_name":"Nick Duffield","orcid":"https://orcid.org/0000-0001-7211-1584"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Nick Duffield","raw_affiliation_strings":["AT&T Labs -- Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004860814","display_name":"Jeffrey Erman","orcid":null},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jeffrey Erman","raw_affiliation_strings":["AT&T Labs -- Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026605560","display_name":"Patrick Haffner","orcid":"https://orcid.org/0000-0002-2319-5109"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Patrick Haffner","raw_affiliation_strings":["AT&T Labs -- Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5114832181","display_name":"Subhabrata Sen","orcid":"https://orcid.org/0009-0005-5969-1023"},"institutions":[{"id":"https://openalex.org/I1283103587","display_name":"AT&T (United States)","ror":"https://ror.org/02bbd5539","country_code":"US","type":"company","lineage":["https://openalex.org/I1283103587"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Subhabrata Sen","raw_affiliation_strings":["AT&T Labs -- Research"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"AT&T Labs -- Research","institution_ids":["https://openalex.org/I1283103587"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100622098","display_name":"Zhili Zhang","orcid":"https://orcid.org/0000-0002-6709-9506"},"institutions":[{"id":"https://openalex.org/I2800403580","display_name":"University of Minnesota System","ror":"https://ror.org/03grvy078","country_code":"US","type":"education","lineage":["https://openalex.org/I2800403580"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Zhi-Li Zhang","raw_affiliation_strings":["University of Minnesota"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Minnesota","institution_ids":["https://openalex.org/I2800403580"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":14.353,"has_fulltext":false,"cited_by_count":102,"citation_normalized_percentile":{"value":0.98966883,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":97,"max":99},"biblio":{"volume":"6","issue":"1","first_page":"1","last_page":"34"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","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/T11598","display_name":"Internet Traffic Analysis and Secure E-voting","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/T10400","display_name":"Network Security and Intrusion Detection","score":0.9994999766349792,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9753000140190125,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.821134626865387},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.8079209327697754},{"id":"https://openalex.org/keywords/modular-design","display_name":"Modular design","score":0.6926783323287964},{"id":"https://openalex.org/keywords/traffic-classification","display_name":"Traffic classification","score":0.6552364826202393},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.561325192451477},{"id":"https://openalex.org/keywords/network-packet","display_name":"Network packet","score":0.5573413968086243},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5446734428405762},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5008523464202881},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.4883005619049072},{"id":"https://openalex.org/keywords/binary-classification","display_name":"Binary classification","score":0.44667574763298035},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15357112884521484},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.1476244032382965},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.10315307974815369}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.821134626865387},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.8079209327697754},{"id":"https://openalex.org/C101468663","wikidata":"https://www.wikidata.org/wiki/Q1620158","display_name":"Modular design","level":2,"score":0.6926783323287964},{"id":"https://openalex.org/C169988225","wikidata":"https://www.wikidata.org/wiki/Q7832484","display_name":"Traffic classification","level":3,"score":0.6552364826202393},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.561325192451477},{"id":"https://openalex.org/C158379750","wikidata":"https://www.wikidata.org/wiki/Q214111","display_name":"Network packet","level":2,"score":0.5573413968086243},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5446734428405762},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5008523464202881},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.4883005619049072},{"id":"https://openalex.org/C66905080","wikidata":"https://www.wikidata.org/wiki/Q17005494","display_name":"Binary classification","level":3,"score":0.44667574763298035},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15357112884521484},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.1476244032382965},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.10315307974815369},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2133360.2133364","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2133360.2133364","pdf_url":null,"source":{"id":"https://openalex.org/S41523882","display_name":"ACM Transactions on Knowledge Discovery from Data","issn_l":"1556-4681","issn":["1556-4681","1556-472X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319798","host_organization_name":"Association for Computing Machinery","host_organization_lineage":["https://openalex.org/P4310319798"],"host_organization_lineage_names":["Association for Computing Machinery"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"ACM Transactions on Knowledge Discovery from Data","raw_type":"journal-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.413.9023","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.413.9023","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www-users.cs.umn.edu/~zhzhang/Papers/A Modular Machine Learning System for Flow-Level Traffic Classification in Large Networks.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.46000000834465027,"display_name":"Industry, innovation and infrastructure"}],"awards":[{"id":"https://openalex.org/G6966764307","display_name":null,"funder_award_id":"CNS-0905037CNS-1017647","funder_id":"https://openalex.org/F4320337388","funder_display_name":"Division of Computer and Network Systems"}],"funders":[{"id":"https://openalex.org/F4320337388","display_name":"Division of Computer and Network Systems","ror":"https://ror.org/02rdzmk74"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W172040345","https://openalex.org/W1618905105","https://openalex.org/W1979759959","https://openalex.org/W1988790447","https://openalex.org/W2002151811","https://openalex.org/W2012095206","https://openalex.org/W2027262816","https://openalex.org/W2041855183","https://openalex.org/W2053463056","https://openalex.org/W2055261595","https://openalex.org/W2073089243","https://openalex.org/W2080222256","https://openalex.org/W2085092855","https://openalex.org/W2087405576","https://openalex.org/W2095815177","https://openalex.org/W2100062282","https://openalex.org/W2119895316","https://openalex.org/W2121250409","https://openalex.org/W2122226347","https://openalex.org/W2123504579","https://openalex.org/W2127058089","https://openalex.org/W2128567487","https://openalex.org/W2130598205","https://openalex.org/W2133473417","https://openalex.org/W2133864802","https://openalex.org/W2136695760","https://openalex.org/W2138798845","https://openalex.org/W2144098589","https://openalex.org/W2148346742","https://openalex.org/W2150884987","https://openalex.org/W2153959628","https://openalex.org/W2155620999","https://openalex.org/W2156123711","https://openalex.org/W2157349061","https://openalex.org/W2799061466","https://openalex.org/W4244728148","https://openalex.org/W4285719527","https://openalex.org/W6606298547"],"related_works":["https://openalex.org/W2378076731","https://openalex.org/W4286888643","https://openalex.org/W3210795196","https://openalex.org/W2012465643","https://openalex.org/W2773751105","https://openalex.org/W4293863212","https://openalex.org/W2050261031","https://openalex.org/W4382934300","https://openalex.org/W2121061354","https://openalex.org/W4285388059"],"abstract_inverted_index":{"The":[0],"ability":[1],"to":[2,13,136,280,290],"accurately":[3,159],"and":[4,28,37,55,109,119,131,178,187,195,211,270],"scalably":[5],"classify":[6,291],"network":[7],"traffic":[8,40,61,146,237,253,258,268,292],"is":[9,65],"of":[10,17,20,39,52,70,97,103,114,163,181,230,233],"critical":[11],"importance":[12],"a":[14,68,82,88,95,152,244,281],"wide":[15],"range":[16],"management":[18],"tasks":[19],"large":[21,43,153,182],"networks,":[22,44],"such":[23,220],"as":[24],"tier-1":[25],"ISP":[26,154,183],"networks":[27],"global":[29],"enterprise":[30],"networks.":[31,184],"Guided":[32],"by":[33,81,226,276],"the":[34,50,161,164,176,201,228,256],"practical":[35],"constraints":[36],"requirements":[38,180],"classification":[41,62,259],"in":[42,45,117,151],"this":[46],"article,":[47],"we":[48],"explore":[49],"design":[51],"an":[53,271],"accurate":[54],"scalable":[56],"machine":[57],"learning":[58],"based":[59],"flow-level":[60,71],"system,":[63],"which":[64,93,104,248],"trained":[66,110],"on":[67,111,170,266,293],"dataset":[69],"data":[72,116,133,147],"that":[73,156,190,219],"has":[74],"been":[75],"annotated":[76],"with":[77],"application":[78],"protocol":[79],"labels":[80,162],"packet-level":[83],"classifier.":[84],"Our":[85],"system":[86,158],"employs":[87],"lightweight":[89],"modular":[90],"architecture":[91],",":[92,130,135,239],"combines":[94],"series":[96],"simple":[98],"linear":[99],"binary":[100],"classifiers,":[101],"each":[102],"can":[105,223],"be":[106,224],"efficiently":[107],"implemented":[108],"vast":[112],"amounts":[113],"flow":[115,172,202],"parallel,":[118],"embraces":[120],"three":[121],"key":[122],"innovative":[123],"mechanisms,":[124],"weighted":[125],"threshold":[126],"sampling,":[127],"logistic":[128],"calibration":[129],"intelligent":[132],"partitioning":[134],"achieve":[137],"scalability":[138,177],"while":[139,174],"attaining":[140],"high":[141,282],"accuracy.":[142],"Evaluations":[143],"using":[144],"real":[145],"from":[148,197],"multiple":[149],"locations":[150],"show":[155,218],"our":[157,286],"reproduces":[160],"packet":[165],"level":[166],"classifier":[167],"when":[168],"runs":[169],"(unlabeled)":[171],"records,":[173],"meeting":[175],"stability":[179],"Using":[185],"training":[186],"test":[188],"datasets":[189],"are":[191,205],"two":[192,198],"months":[193],"apart":[194],"collected":[196],"different":[199],"locations,":[200],"error":[203,221,273],"rates":[204,222],"only":[206],"3%":[207],"for":[208,213],"TCP":[209],"flows":[210],"0.4%":[212],"UDP":[214],"flows.":[215],"We":[216,242],"further":[217],"reduced":[225],"combining":[227],"information":[229],"spatial":[231],"distributions":[232],"flows,":[234],"or":[235],"collective":[236,252],"statistics":[238,254],"during":[240],"classification.":[241],"propose":[243],"novel":[245],"two-step":[246],"model,":[247],"seamlessly":[249],"integrates":[250],"these":[251],"into":[255],"existing":[257],"system.":[260],"Experimental":[261],"results":[262],"display":[263],"performance":[264],"improvement":[265],"all":[267],"classes":[269],"overall":[272],"rate":[274],"reduction":[275],"15%.":[277],"In":[278],"addition":[279],"accuracy,":[283],"at":[284],"runtime,":[285],"implementation":[287],"easily":[288],"scales":[289],"10Gbps":[294],"links.":[295]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":5},{"year":2023,"cited_by_count":4},{"year":2022,"cited_by_count":7},{"year":2021,"cited_by_count":11},{"year":2020,"cited_by_count":10},{"year":2019,"cited_by_count":4},{"year":2018,"cited_by_count":5},{"year":2017,"cited_by_count":6},{"year":2016,"cited_by_count":9},{"year":2015,"cited_by_count":10},{"year":2014,"cited_by_count":12},{"year":2013,"cited_by_count":7},{"year":2012,"cited_by_count":4}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}