{"id":"https://openalex.org/W2063490473","doi":"https://doi.org/10.1145/1458082.1458211","title":"Real-time data pre-processing technique for efficient feature extraction in large scale datasets","display_name":"Real-time data pre-processing technique for efficient feature extraction in large scale datasets","publication_year":2008,"publication_date":"2008-10-26","ids":{"openalex":"https://openalex.org/W2063490473","doi":"https://doi.org/10.1145/1458082.1458211","mag":"2063490473"},"language":"en","primary_location":{"id":"doi:10.1145/1458082.1458211","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100414434","display_name":"Ying Liu","orcid":"https://orcid.org/0000-0003-2626-8403"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ying Liu","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111881156","display_name":"Lucian Vlad Lita","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Lucian V. Lita","raw_affiliation_strings":["Siemens Medical Solutions, Malven, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Medical Solutions, Malven, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5045516900","display_name":"Radu Stefan Niculescu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"R. Stefan Niculescu","raw_affiliation_strings":["Siemens Medical Solutions, Malven, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Siemens Medical Solutions, Malven, PA, USA","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5072519705","display_name":"Kun Bai","orcid":"https://orcid.org/0009-0008-8005-7424"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Kun Bai","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5009542542","display_name":"Prasenjit Mitra","orcid":"https://orcid.org/0000-0002-7530-9497"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Prasenjit Mitra","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5001294898","display_name":"C. Lee Giles","orcid":"https://orcid.org/0000-0002-1931-585X"},"institutions":[{"id":"https://openalex.org/I130769515","display_name":"Pennsylvania State University","ror":"https://ror.org/04p491231","country_code":"US","type":"education","lineage":["https://openalex.org/I130769515"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"C. Lee Giles","raw_affiliation_strings":["The Pennsylvania State University, University Park, PA, USA","The Pennsylvania State University , University Park, PA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"The Pennsylvania State University, University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]},{"raw_affiliation_string":"The Pennsylvania State University , University Park, PA, USA","institution_ids":["https://openalex.org/I130769515"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.5041,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.59871343,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"981","last_page":"990"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9986000061035156,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.9980000257492065,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8489183783531189},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6610894203186035},{"id":"https://openalex.org/keywords/exploit","display_name":"Exploit","score":0.6274593472480774},{"id":"https://openalex.org/keywords/block","display_name":"Block (permutation group theory)","score":0.5588309168815613},{"id":"https://openalex.org/keywords/knowledge-extraction","display_name":"Knowledge extraction","score":0.5294544100761414},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5209744572639465},{"id":"https://openalex.org/keywords/feature-extraction","display_name":"Feature extraction","score":0.488736629486084},{"id":"https://openalex.org/keywords/domain","display_name":"Domain (mathematical analysis)","score":0.44265368580818176},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.44173768162727356},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.3423658013343811},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.32546383142471313},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32276737689971924}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8489183783531189},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6610894203186035},{"id":"https://openalex.org/C165696696","wikidata":"https://www.wikidata.org/wiki/Q11287","display_name":"Exploit","level":2,"score":0.6274593472480774},{"id":"https://openalex.org/C2777210771","wikidata":"https://www.wikidata.org/wiki/Q4927124","display_name":"Block (permutation group theory)","level":2,"score":0.5588309168815613},{"id":"https://openalex.org/C120567893","wikidata":"https://www.wikidata.org/wiki/Q1582085","display_name":"Knowledge extraction","level":2,"score":0.5294544100761414},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5209744572639465},{"id":"https://openalex.org/C52622490","wikidata":"https://www.wikidata.org/wiki/Q1026626","display_name":"Feature extraction","level":2,"score":0.488736629486084},{"id":"https://openalex.org/C36503486","wikidata":"https://www.wikidata.org/wiki/Q11235244","display_name":"Domain (mathematical analysis)","level":2,"score":0.44265368580818176},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.44173768162727356},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.3423658013343811},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.32546383142471313},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32276737689971924},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":4,"locations":[{"id":"doi:10.1145/1458082.1458211","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1458082.1458211","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 17th ACM conference on Information and knowledge management","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.157.1447","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.157.1447","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.cmu.edu/~stefann/papers/cikm08.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.304.4538","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.304.4538","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://clgiles.ist.psu.edu/pubs/CIKM2008-real-time-preprocessing.pdf","raw_type":"text"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.365.3463","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.365.3463","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.personal.psu.edu/yzl127/CIKM2008_YingLiu_2.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W124244495","https://openalex.org/W182128760","https://openalex.org/W185052921","https://openalex.org/W1489835744","https://openalex.org/W1577337656","https://openalex.org/W1674877186","https://openalex.org/W1787230089","https://openalex.org/W1985108724","https://openalex.org/W2000982728","https://openalex.org/W2066055909","https://openalex.org/W2099964107","https://openalex.org/W2132791332","https://openalex.org/W2134826720","https://openalex.org/W2140977185","https://openalex.org/W2141233457","https://openalex.org/W2151888610","https://openalex.org/W2156577800","https://openalex.org/W2160196229","https://openalex.org/W4210896998","https://openalex.org/W6629295535"],"related_works":["https://openalex.org/W17155033","https://openalex.org/W3207760230","https://openalex.org/W1496222301","https://openalex.org/W4312814274","https://openalex.org/W1590307681","https://openalex.org/W2536018345","https://openalex.org/W4285370786","https://openalex.org/W2296488620","https://openalex.org/W2358353312","https://openalex.org/W2353836703"],"abstract_inverted_index":{"Due":[0],"to":[1,83,142],"the":[2,8,35,63,85,120,123,144],"continuous":[3],"and":[4,19,78,105,132,154],"rampant":[5],"increase":[6],"in":[7,25,70,76],"size":[9],"of":[10,37,65,88,122,136,148],"domain":[11,149],"specific":[12,150],"data":[13,67,80,95,151],"sources,":[14],"there":[15],"is":[16,61,81,116,139],"a":[17,110],"real":[18,161],"sustained":[20],"need":[21,97],"for":[22,42,152],"fast":[23],"processing":[24],"time-sensitive":[26],"applications,":[27,72],"such":[28,51,89,128],"as":[29,45,47,52,129],"medical":[30],"record":[31],"information":[32,103],"extraction":[33,41,104],"at":[34,62],"point":[36],"care,":[38],"genetic":[39],"feature":[40],"personalized":[43],"treatment,":[44],"well":[46],"off-line":[48,153],"knowledge":[49,90],"discovery":[50],"creating":[53],"evidence":[54],"based":[55],"medicine.":[56],"Since":[57],"parallel":[58,156],"multi-string":[59,125],"matching":[60,75,126],"core":[64],"most":[66],"mining":[68,96],"tasks":[69],"these":[71],"faster":[73],"on-line":[74],"static":[77],"streaming":[79],"needed":[82],"improve":[84],"overall":[86],"efficiency":[87],"discovery.":[91],"To":[92],"solve":[93],"this":[94],"not":[98],"efficiently":[99],"handled":[100],"by":[101],"traditional":[102],"retrieval":[106],"techniques,":[107],"we":[108],"propose":[109],"Block":[111],"Suffix":[112],"Shifting-based":[113],"approach,":[114],"which":[115],"an":[117],"improvement":[118],"over":[119],"state":[121],"art":[124],"algorithms":[127],"Aho-Corasick,":[130],"Commentz-Walter,":[131],"Wu-Manber.":[133],"The":[134],"strength":[135],"our":[137,166],"approach":[138,167],"its":[140],"ability":[141],"exploit":[143],"different":[145],"block":[146],"structures":[147],"online":[155],"matching.":[157],"Experiments":[158],"on":[159],"several":[160],"world":[162],"datasets":[163],"show":[164],"how":[165],"translates":[168],"into":[169],"significant":[170],"performance":[171],"improvements.":[172]},"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":1}],"updated_date":"2026-08-26T07:47:46.906454","created_date":"2025-10-10T00:00:00"}
