{"id":"https://openalex.org/W2156131541","doi":"https://doi.org/10.1109/icde.2010.5447843","title":"Efficient and accurate discovery of patterns in sequence datasets","display_name":"Efficient and accurate discovery of patterns in sequence datasets","publication_year":2010,"publication_date":"2010-03-01","ids":{"openalex":"https://openalex.org/W2156131541","doi":"https://doi.org/10.1109/icde.2010.5447843","mag":"2156131541"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","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/A5020678151","display_name":"Avrilia Floratou","orcid":"https://orcid.org/0009-0007-5760-8657"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Avrilia Floratou","raw_affiliation_strings":["Computer Sciences Department, University of Wisconsin-Madison, USA","Computer Sciences Department, University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin-Madison, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5102945075","display_name":"Sandeep Tata","orcid":"https://orcid.org/0009-0007-7785-5516"},"institutions":[{"id":"https://openalex.org/I4210085935","display_name":"IBM Research - Almaden","ror":"https://ror.org/005w8dd04","country_code":"US","type":"facility","lineage":["https://openalex.org/I1341412227","https://openalex.org/I4210085935","https://openalex.org/I4210114115"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Sandeep Tata","raw_affiliation_strings":["IBM Almaden Research Center, CA, USA"],"affiliations":[{"raw_affiliation_string":"IBM Almaden Research Center, CA, USA","institution_ids":["https://openalex.org/I4210085935"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5069237428","display_name":"Jignesh M. Patel","orcid":"https://orcid.org/0000-0003-3653-2538"},"institutions":[{"id":"https://openalex.org/I135310074","display_name":"University of Wisconsin\u2013Madison","ror":"https://ror.org/01y2jtd41","country_code":"US","type":"education","lineage":["https://openalex.org/I135310074"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Jignesh M. Patel","raw_affiliation_strings":["Computer Sciences Department, University of Wisconsin-Madison, USA","Computer Sciences Department, University of Wisconsin, Madison, WI, USA"],"affiliations":[{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin-Madison, USA","institution_ids":["https://openalex.org/I135310074"]},{"raw_affiliation_string":"Computer Sciences Department, University of Wisconsin, Madison, WI, USA","institution_ids":["https://openalex.org/I135310074"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5020678151"],"corresponding_institution_ids":["https://openalex.org/I135310074"],"apc_list":null,"apc_paid":null,"fwci":2.2552,"has_fulltext":false,"cited_by_count":12,"citation_normalized_percentile":{"value":0.89819769,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"461","last_page":"472"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9993000030517578,"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/T11106","display_name":"Data Management and Algorithms","score":0.9900000095367432,"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/scalability","display_name":"Scalability","score":0.7887444496154785},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7572555541992188},{"id":"https://openalex.org/keywords/suffix-tree","display_name":"Suffix tree","score":0.644066572189331},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6192086338996887},{"id":"https://openalex.org/keywords/sequential-pattern-mining","display_name":"Sequential Pattern Mining","score":0.579746663570404},{"id":"https://openalex.org/keywords/trie","display_name":"Trie","score":0.46864837408065796},{"id":"https://openalex.org/keywords/sequence-database","display_name":"Sequence database","score":0.430440753698349},{"id":"https://openalex.org/keywords/suffix","display_name":"Suffix","score":0.418828547000885},{"id":"https://openalex.org/keywords/motif","display_name":"Motif (music)","score":0.416413277387619},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.4143674075603485},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.41225215792655945},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3317260146141052},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.32425254583358765},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.2260376513004303},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.0950499176979065}],"concepts":[{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7887444496154785},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7572555541992188},{"id":"https://openalex.org/C2781166958","wikidata":"https://www.wikidata.org/wiki/Q1426863","display_name":"Suffix tree","level":3,"score":0.644066572189331},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6192086338996887},{"id":"https://openalex.org/C149490388","wikidata":"https://www.wikidata.org/wiki/Q1718507","display_name":"Sequential Pattern Mining","level":2,"score":0.579746663570404},{"id":"https://openalex.org/C190290938","wikidata":"https://www.wikidata.org/wiki/Q387015","display_name":"Trie","level":3,"score":0.46864837408065796},{"id":"https://openalex.org/C41584329","wikidata":"https://www.wikidata.org/wiki/Q175902","display_name":"Sequence database","level":3,"score":0.430440753698349},{"id":"https://openalex.org/C2779804580","wikidata":"https://www.wikidata.org/wiki/Q102047","display_name":"Suffix","level":2,"score":0.418828547000885},{"id":"https://openalex.org/C32276052","wikidata":"https://www.wikidata.org/wiki/Q908349","display_name":"Motif (music)","level":2,"score":0.416413277387619},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.4143674075603485},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.41225215792655945},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3317260146141052},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.32425254583358765},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.2260376513004303},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.0950499176979065},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"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/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C24890656","wikidata":"https://www.wikidata.org/wiki/Q82811","display_name":"Acoustics","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/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icde.2010.5447843","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447843","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","score":0.4399999976158142,"display_name":"No poverty"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":69,"referenced_works":["https://openalex.org/W109758530","https://openalex.org/W151863654","https://openalex.org/W1484413656","https://openalex.org/W1502916507","https://openalex.org/W1518105754","https://openalex.org/W1580213736","https://openalex.org/W1583721307","https://openalex.org/W1583782919","https://openalex.org/W1584003909","https://openalex.org/W1592870802","https://openalex.org/W1608194207","https://openalex.org/W1676985236","https://openalex.org/W2006761268","https://openalex.org/W2009418433","https://openalex.org/W2009566340","https://openalex.org/W2017758253","https://openalex.org/W2023863508","https://openalex.org/W2025567828","https://openalex.org/W2028904582","https://openalex.org/W2032991899","https://openalex.org/W2033376980","https://openalex.org/W2047792838","https://openalex.org/W2054984882","https://openalex.org/W2056002855","https://openalex.org/W2066558394","https://openalex.org/W2066834853","https://openalex.org/W2086802511","https://openalex.org/W2087668094","https://openalex.org/W2089783852","https://openalex.org/W2096210973","https://openalex.org/W2097426120","https://openalex.org/W2103447044","https://openalex.org/W2105709740","https://openalex.org/W2108706843","https://openalex.org/W2115761267","https://openalex.org/W2118371392","https://openalex.org/W2122182354","https://openalex.org/W2124192284","https://openalex.org/W2125246942","https://openalex.org/W2128091972","https://openalex.org/W2129242777","https://openalex.org/W2129330015","https://openalex.org/W2134752891","https://openalex.org/W2136197452","https://openalex.org/W2139306337","https://openalex.org/W2141408320","https://openalex.org/W2142473132","https://openalex.org/W2143210482","https://openalex.org/W2147880780","https://openalex.org/W2149558335","https://openalex.org/W2154440943","https://openalex.org/W2158454296","https://openalex.org/W2161507796","https://openalex.org/W2162111678","https://openalex.org/W2162665632","https://openalex.org/W2164814636","https://openalex.org/W4231088442","https://openalex.org/W4239504300","https://openalex.org/W4254829975","https://openalex.org/W4300336601","https://openalex.org/W6606194391","https://openalex.org/W6628750762","https://openalex.org/W6629956336","https://openalex.org/W6634719314","https://openalex.org/W6634944405","https://openalex.org/W6635016272","https://openalex.org/W6635200387","https://openalex.org/W6678876942","https://openalex.org/W6679475434"],"related_works":["https://openalex.org/W3157818565","https://openalex.org/W2032737507","https://openalex.org/W2067956663","https://openalex.org/W2142644988","https://openalex.org/W2047168584","https://openalex.org/W2395836737","https://openalex.org/W2171073185","https://openalex.org/W435774925","https://openalex.org/W2138454694","https://openalex.org/W2076424561"],"abstract_inverted_index":{"Existing":[0],"sequence":[1],"mining":[2,7,26,47],"algorithms":[3,36,136],"mostly":[4],"focus":[5],"on":[6,137],"for":[8],"subsequences.":[9],"However,":[10],"a":[11,72,84,99,138],"large":[12],"class":[13],"of":[14,27,54,101,103,140],"applications,":[15],"such":[16,43],"as":[17,111],"biological":[18],"DNA":[19],"and":[20,60,78,123,133],"protein":[21],"motif":[22,104],"mining,":[23],"require":[24],"efficient":[25],"\u00bfapproximate\u00bf":[28],"patterns":[29,97],"that":[30,37,90,128,152],"are":[31],"contiguous.":[32],"The":[33],"few":[34],"existing":[35,135,159],"can":[38,91],"be":[39,92],"applied":[40],"to":[41,64,94,149],"find":[42,95,114],"contiguous":[44],"approximate":[45],"pattern":[46,116],"have":[48,154],"drawbacks":[49],"like":[50],"poor":[51],"scalability,":[52],"lack":[53],"guarantees":[55],"in":[56,62],"finding":[57],"the":[58,115],"pattern,":[59],"difficulty":[61],"adapting":[63],"other":[65],"applications.":[66],"In":[67],"this":[68],"paper,":[69],"we":[70,126],"present":[71],"new":[73],"algorithm":[74,89],"called":[75],"FLAME":[76,82,129],"(FLexible":[77],"Accurate":[79],"Motif":[80],"DEtector).":[81],"is":[83,108,130,146],"flexible":[85],"suffix":[86],"tree":[87],"based":[88],"used":[93],"frequent":[96],"with":[98,158],"variety":[100,139],"definitions":[102],"(pattern)":[105],"models.":[106],"It":[107],"also":[109],"accurate,":[110],"it":[112,118,145],"always":[113],"if":[117],"exists.":[119],"Using":[120,143],"both":[121],"real":[122],"synthetic":[124],"datasets,":[125],"demonstrate":[127],"fast,":[131],"scalable,":[132],"outperforms":[134],"performance":[141],"metrics.":[142],"FLAME,":[144],"now":[147],"possible":[148],"mine":[150],"datasets":[151],"would":[153],"been":[155],"prohibitively":[156],"difficult":[157],"tools.":[160]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":1},{"year":2014,"cited_by_count":3},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":2}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}