{"id":"https://openalex.org/W2020970220","doi":"https://doi.org/10.1145/1281192.1281200","title":"On string classification in data streams","display_name":"On string classification in data streams","publication_year":2007,"publication_date":"2007-08-12","ids":{"openalex":"https://openalex.org/W2020970220","doi":"https://doi.org/10.1145/1281192.1281200","mag":"2020970220"},"language":"en","primary_location":{"id":"doi:10.1145/1281192.1281200","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","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/A5028089542","display_name":"Char\u0173 C. Aggarwal","orcid":"https://orcid.org/0000-0003-2579-7581"},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Charu C. Aggarwal","raw_affiliation_strings":["IBM T. J. Watson Research Center"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5036357902","display_name":"Philip S. Yu","orcid":"https://orcid.org/0000-0002-3491-5968"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Philip S. Yu","raw_affiliation_strings":["IBM T. J. Watson Research Center"],"affiliations":[{"raw_affiliation_string":"IBM T. J. Watson Research Center","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5028089542"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.483,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.75129474,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"36","last_page":"45"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9997000098228455,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9966999888420105,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9866999983787537,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7582300901412964},{"id":"https://openalex.org/keywords/substring","display_name":"Substring","score":0.7208770513534546},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6942858695983887},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.6180114150047302},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.5514305233955383},{"id":"https://openalex.org/keywords/generalization","display_name":"Generalization","score":0.5410183668136597},{"id":"https://openalex.org/keywords/data-stream-mining","display_name":"Data stream mining","score":0.5144177079200745},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.4709257483482361},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4101129174232483},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.36376428604125977},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.33269140124320984},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2973700761795044},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.1840168535709381},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1681746542453766},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.11021816730499268},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08965012431144714}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7582300901412964},{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.7208770513534546},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6942858695983887},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.6180114150047302},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.5514305233955383},{"id":"https://openalex.org/C177148314","wikidata":"https://www.wikidata.org/wiki/Q170084","display_name":"Generalization","level":2,"score":0.5410183668136597},{"id":"https://openalex.org/C89198739","wikidata":"https://www.wikidata.org/wiki/Q3079880","display_name":"Data stream mining","level":2,"score":0.5144177079200745},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.4709257483482361},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4101129174232483},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.36376428604125977},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.33269140124320984},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2973700761795044},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.1840168535709381},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1681746542453766},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.11021816730499268},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08965012431144714},{"id":"https://openalex.org/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/1281192.1281200","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1281192.1281200","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 13th ACM SIGKDD international conference on Knowledge discovery and data mining","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.135.5133","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.135.5133","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://charuaggarwal.net/frp430-aggarwal.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.550000011920929}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":17,"referenced_works":["https://openalex.org/W1484413656","https://openalex.org/W1506285740","https://openalex.org/W1524940515","https://openalex.org/W1539117683","https://openalex.org/W1971912858","https://openalex.org/W1990061958","https://openalex.org/W1991133427","https://openalex.org/W2005120335","https://openalex.org/W2010657328","https://openalex.org/W2029873015","https://openalex.org/W2052331661","https://openalex.org/W2068714596","https://openalex.org/W2075457099","https://openalex.org/W2099919278","https://openalex.org/W2102122585","https://openalex.org/W2140244239","https://openalex.org/W2610179052"],"related_works":["https://openalex.org/W2298204719","https://openalex.org/W152351265","https://openalex.org/W52396946","https://openalex.org/W3042295250","https://openalex.org/W2549495077","https://openalex.org/W2748704845","https://openalex.org/W1564013439","https://openalex.org/W3175353343","https://openalex.org/W2119057313","https://openalex.org/W3112977702"],"abstract_inverted_index":{"String":[0],"data":[1,179,182,193,196],"has":[2],"recently":[3],"become":[4],"important":[5,52],"because":[6],"of":[7,13,36,54,62,80,93,112,120,131,191],"its":[8],"use":[9],"in":[10,83],"a":[11,33,55,63,68,88,117,140,155,189],"number":[12,190],"applications":[14],"such":[15,48,67],"as":[16,148],"computational":[17],"and":[18,23,78,181,195],"molecular":[19],"biology,":[20],"protein":[21],"analysis,":[22],"market":[24],"basket":[25],"data.":[26,85],"In":[27,66],"many":[28],"cases,":[29],"these":[30],"strings":[31,103],"contain":[32],"wide":[34],"variety":[35],"substructures":[37,49],"which":[38,144],"may":[39],"have":[40],"physical":[41],"significance":[42],"for":[43,163,176],"that":[44,81],"application.":[45],"For":[46],"example,":[47],"could":[50],"represent":[51],"fragments":[53,115],"DNA":[56],"string":[57,114,173],"or":[58],"an":[59],"interesting":[60],"portion":[61],"fraudulent":[64],"transaction.":[65],"case,":[69],"it":[70],"is":[71,87],"desirable":[72],"to":[73,147,169],"determine":[74],"the":[75,84,94,98,108,149,171],"identity,":[76],"location,":[77],"extent":[79],"substructure":[82],"This":[86],"much":[89],"more":[90,109,126],"difficult":[91],"generalization":[92],"classification":[95,151,174],"problem,":[96],"since":[97],"latter":[99],"problem":[100,123,143],"labels":[101],"entire":[102],"rather":[104],"than":[105],"deal":[106],"with":[107,116],"complex":[110],"task":[111],"determining":[113],"particular":[118],"kind":[119],"behavior.":[121],"The":[122],"becomes":[124],"even":[125],"complicated":[127,134],"when":[128],"different":[129,142],"kinds":[130],"substrings":[132],"show":[133,167],"nesting":[135],"patterns.":[136],"Therefore,":[137],"we":[138,145],"define":[139],"somewhat":[141],"refer":[146],"generalized":[150,172],"problem.":[152,165],"We":[153,166,184],"propose":[154],"scalable":[156],"approach":[157],"based":[158],"on":[159],"hidden":[160],"markov":[161],"models":[162],"this":[164],"how":[168],"implement":[170],"procedure":[175],"very":[177],"large":[178,192],"bases":[180],"streams.":[183,197],"present":[185],"experimental":[186],"results":[187],"over":[188],"sets":[194]},"counts_by_year":[{"year":2018,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}