{"id":"https://openalex.org/W1996130971","doi":"https://doi.org/10.1145/1376616.1376635","title":"Scalable regular expression matching on data streams","display_name":"Scalable regular expression matching on data streams","publication_year":2008,"publication_date":"2008-06-09","ids":{"openalex":"https://openalex.org/W1996130971","doi":"https://doi.org/10.1145/1376616.1376635","mag":"1996130971"},"language":"en","primary_location":{"id":"doi:10.1145/1376616.1376635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of 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/A5038929529","display_name":"Anirban Majumder","orcid":"https://orcid.org/0009-0002-3490-1395"},"institutions":[{"id":"https://openalex.org/I72090969","display_name":"Nokia (United States)","ror":"https://ror.org/038km2573","country_code":"US","type":"company","lineage":["https://openalex.org/I2738502077","https://openalex.org/I72090969"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Anirban Majumder","raw_affiliation_strings":["Bell Labs Research India, India","Bell Labs Research India, India#TAB#"],"affiliations":[{"raw_affiliation_string":"Bell Labs Research India, India","institution_ids":[]},{"raw_affiliation_string":"Bell Labs Research India, India#TAB#","institution_ids":["https://openalex.org/I72090969"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111717871","display_name":"Rajeev Rastogi","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Rajeev Rastogi","raw_affiliation_strings":["Yahoo!, Bangalore, India","Yahoo , Bangalore, India"],"affiliations":[{"raw_affiliation_string":"Yahoo!, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"Yahoo , Bangalore, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5040312135","display_name":"Sriram Vanama","orcid":null},"institutions":[{"id":"https://openalex.org/I24676775","display_name":"Indian Institute of Technology Madras","ror":"https://ror.org/03v0r5n49","country_code":"IN","type":"facility","lineage":["https://openalex.org/I24676775"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Sriram Vanama","raw_affiliation_strings":["Indian Institute of Technology, Madras, Chennai, India"],"affiliations":[{"raw_affiliation_string":"Indian Institute of Technology, Madras, Chennai, India","institution_ids":["https://openalex.org/I24676775"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5038929529"],"corresponding_institution_ids":["https://openalex.org/I72090969"],"apc_list":null,"apc_paid":null,"fwci":5.1991,"has_fulltext":false,"cited_by_count":36,"citation_normalized_percentile":{"value":0.95590527,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"161","last_page":"172"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":1.0,"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"}},"topics":[{"id":"https://openalex.org/T12326","display_name":"Network Packet Processing and Optimization","score":1.0,"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"}},{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9976999759674072,"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/T11567","display_name":"semigroups and automata theory","score":0.9955000281333923,"subfield":{"id":"https://openalex.org/subfields/1703","display_name":"Computational Theory and Mathematics"},"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":0.8071001172065735},{"id":"https://openalex.org/keywords/regular-expression","display_name":"Regular expression","score":0.7876118421554565},{"id":"https://openalex.org/keywords/deterministic-finite-automaton","display_name":"Deterministic finite automaton","score":0.7029882073402405},{"id":"https://openalex.org/keywords/dfa-minimization","display_name":"DFA minimization","score":0.6227443814277649},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5985147953033447},{"id":"https://openalex.org/keywords/nondeterministic-finite-automaton","display_name":"Nondeterministic finite automaton","score":0.5220506191253662},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5008704662322998},{"id":"https://openalex.org/keywords/automaton","display_name":"Automaton","score":0.48894965648651123},{"id":"https://openalex.org/keywords/cache","display_name":"Cache","score":0.4771541953086853},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.46922242641448975},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.45935559272766113},{"id":"https://openalex.org/keywords/finite-state-machine","display_name":"Finite-state machine","score":0.4188826084136963},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.41380608081817627},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26791495084762573},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.225468248128891},{"id":"https://openalex.org/keywords/automata-theory","display_name":"Automata theory","score":0.2249111533164978},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.12125781178474426},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.08583575487136841},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.08506211638450623}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8071001172065735},{"id":"https://openalex.org/C121329065","wikidata":"https://www.wikidata.org/wiki/Q185612","display_name":"Regular expression","level":2,"score":0.7876118421554565},{"id":"https://openalex.org/C104091681","wikidata":"https://www.wikidata.org/wiki/Q837528","display_name":"Deterministic finite automaton","level":3,"score":0.7029882073402405},{"id":"https://openalex.org/C65753522","wikidata":"https://www.wikidata.org/wiki/Q5204896","display_name":"DFA minimization","level":5,"score":0.6227443814277649},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5985147953033447},{"id":"https://openalex.org/C158008952","wikidata":"https://www.wikidata.org/wiki/Q617295","display_name":"Nondeterministic finite automaton","level":4,"score":0.5220506191253662},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5008704662322998},{"id":"https://openalex.org/C112505250","wikidata":"https://www.wikidata.org/wiki/Q787116","display_name":"Automaton","level":2,"score":0.48894965648651123},{"id":"https://openalex.org/C115537543","wikidata":"https://www.wikidata.org/wiki/Q165596","display_name":"Cache","level":2,"score":0.4771541953086853},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.46922242641448975},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.45935559272766113},{"id":"https://openalex.org/C167822520","wikidata":"https://www.wikidata.org/wiki/Q176452","display_name":"Finite-state machine","level":2,"score":0.4188826084136963},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.41380608081817627},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26791495084762573},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.225468248128891},{"id":"https://openalex.org/C116248031","wikidata":"https://www.wikidata.org/wiki/Q214526","display_name":"Automata theory","level":3,"score":0.2249111533164978},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.12125781178474426},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.08583575487136841},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.08506211638450623},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1376616.1376635","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1376616.1376635","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2008 ACM SIGMOD international conference on Management of 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":15,"referenced_works":["https://openalex.org/W124244495","https://openalex.org/W1577337656","https://openalex.org/W1968497507","https://openalex.org/W1969783316","https://openalex.org/W1973190970","https://openalex.org/W2002089154","https://openalex.org/W2006508099","https://openalex.org/W2030102079","https://openalex.org/W2096102629","https://openalex.org/W2096474000","https://openalex.org/W2099964107","https://openalex.org/W2111995392","https://openalex.org/W2126632912","https://openalex.org/W2147440220","https://openalex.org/W2171177618"],"related_works":["https://openalex.org/W3143588635","https://openalex.org/W2160879187","https://openalex.org/W2115419634","https://openalex.org/W1560450186","https://openalex.org/W2171377051","https://openalex.org/W2396272923","https://openalex.org/W2083002627","https://openalex.org/W1644613146","https://openalex.org/W1606484542","https://openalex.org/W2364615116"],"abstract_inverted_index":{"Regular":[0],"Expression":[1],"(RE)":[2],"matching":[3,30],"has":[4],"important":[5],"applications":[6],"in":[7,96,108,123],"the":[8,22,35,44,73,90,101,124,142],"areas":[9],"of":[10,25,38,47,56,72,93,126],"XML":[11],"content":[12],"distribution":[13],"and":[14],"network":[15],"security.":[16],"In":[17,58],"this":[18,85,134],"paper,":[19],"we":[20,67,111],"present":[21],"end-to-end":[23],"design":[24],"a":[26,70,79],"high":[27],"performance":[28],"RE":[29,62],"system.":[31],"Our":[32],"system":[33],"combines":[34],"processing":[36],"efficiency":[37,46],"Deterministic":[39],"Finite":[40,49],"Automata":[41,50],"(DFA)":[42],"with":[43,60],"space":[45],"Non-deterministic":[48],"(NFA)":[51],"to":[52,54,87,100,130,136],"scale":[53],"hundreds":[55],"REs.":[57],"experiments":[59],"real-life":[61],"data":[63,65],"on":[64],"streams,":[66],"found":[68],"that":[69,115],"bulk":[71],"DFA":[74,81,95,103,144],"transitions":[75],"are":[76,128],"concentrated":[77],"around":[78],"few":[80],"states.":[82],"We":[83],"exploit":[84],"fact":[86],"cache":[88,138],"only":[89],"frequent":[91],"core":[92],"each":[94],"memory":[97],"as":[98],"opposed":[99],"entire":[102],"(which":[104],"may":[105],"be":[106],"exponential":[107,121],"size).":[109],"Further,":[110],"cluster":[112],"REs":[113,116],"such":[114],"whose":[117],"interactions":[118],"cause":[119],"an":[120],"increase":[122],"number":[125],"states":[127],"assigned":[129],"separate":[131],"groups":[132],"--":[133],"helps":[135],"improve":[137],"hits":[139],"by":[140],"controlling":[141],"overall":[143],"size.":[145]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":2},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":1},{"year":2012,"cited_by_count":8}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
