{"id":"https://openalex.org/W3031244230","doi":"https://doi.org/10.1109/access.2020.2996945","title":"Optimized Signature Selection for Efficient String Similarity Search","display_name":"Optimized Signature Selection for Efficient String Similarity Search","publication_year":2020,"publication_date":"2020-01-01","ids":{"openalex":"https://openalex.org/W3031244230","doi":"https://doi.org/10.1109/access.2020.2996945","mag":"3031244230"},"language":"en","primary_location":{"id":"doi:10.1109/access.2020.2996945","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2996945","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09099253.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09099253.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5047242010","display_name":"Taegyoung Lee","orcid":null},"institutions":[{"id":"https://openalex.org/I200769079","display_name":"Hong Kong University of Science and Technology","ror":"https://ror.org/00q4vv597","country_code":"HK","type":"education","lineage":["https://openalex.org/I200769079"]}],"countries":["HK"],"is_corresponding":true,"raw_author_name":"Taegyoung Lee","raw_affiliation_strings":["Department of Computer Science and Engineering, The Hong Kong University of Science and Technology (HKUST), Hong Kong"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, The Hong Kong University of Science and Technology (HKUST), Hong Kong","institution_ids":["https://openalex.org/I200769079"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5044985062","display_name":"Tae\u2010Sun Chung","orcid":"https://orcid.org/0000-0001-5992-1136"},"institutions":[{"id":"https://openalex.org/I57664883","display_name":"Ajou University","ror":"https://ror.org/03tzb2h73","country_code":"KR","type":"education","lineage":["https://openalex.org/I57664883"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Tae-Sun Chung","raw_affiliation_strings":["Department of Computer Engineering, Ajou University, Suwon, South Korea"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Ajou University, Suwon, South Korea","institution_ids":["https://openalex.org/I57664883"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5010897170","display_name":"Jongik Kim","orcid":"https://orcid.org/0000-0002-5857-6091"},"institutions":[{"id":"https://openalex.org/I80611190","display_name":"Jeonbuk National University","ror":"https://ror.org/05q92br09","country_code":"KR","type":"education","lineage":["https://openalex.org/I80611190"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jongik Kim","raw_affiliation_strings":["Division of Computer Science and Engineering, Jeonbuk National University, Jeonju, South Korea"],"affiliations":[{"raw_affiliation_string":"Division of Computer Science and Engineering, Jeonbuk National University, Jeonju, South Korea","institution_ids":["https://openalex.org/I80611190"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5047242010"],"corresponding_institution_ids":["https://openalex.org/I200769079"],"apc_list":{"value":1850,"currency":"USD","value_usd":1850},"apc_paid":{"value":1850,"currency":"USD","value_usd":1850},"fwci":0.1857,"has_fulltext":true,"cited_by_count":1,"citation_normalized_percentile":{"value":0.55792246,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"8","issue":null,"first_page":"98193","last_page":"98204"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.998199999332428,"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":0.9804999828338623,"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":0.8022032380104065},{"id":"https://openalex.org/keywords/edit-distance","display_name":"Edit distance","score":0.7512794733047485},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.7112168669700623},{"id":"https://openalex.org/keywords/overhead","display_name":"Overhead (engineering)","score":0.5934792757034302},{"id":"https://openalex.org/keywords/inverted-index","display_name":"Inverted index","score":0.592806339263916},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.5791205763816833},{"id":"https://openalex.org/keywords/node","display_name":"Node (physics)","score":0.5731010437011719},{"id":"https://openalex.org/keywords/signature","display_name":"Signature (topology)","score":0.548564612865448},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5240359902381897},{"id":"https://openalex.org/keywords/nearest-neighbor-search","display_name":"Nearest neighbor search","score":0.4861690402030945},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4390362501144409},{"id":"https://openalex.org/keywords/selection","display_name":"Selection (genetic algorithm)","score":0.4334656894207001},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.42827707529067993},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.4264230728149414},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.3767543435096741},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3758176565170288},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.25559744238853455},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16799089312553406},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.14873582124710083},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1485091745853424}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8022032380104065},{"id":"https://openalex.org/C44359876","wikidata":"https://www.wikidata.org/wiki/Q5338467","display_name":"Edit distance","level":2,"score":0.7512794733047485},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.7112168669700623},{"id":"https://openalex.org/C2779960059","wikidata":"https://www.wikidata.org/wiki/Q7113681","display_name":"Overhead (engineering)","level":2,"score":0.5934792757034302},{"id":"https://openalex.org/C130590232","wikidata":"https://www.wikidata.org/wiki/Q1671754","display_name":"Inverted index","level":3,"score":0.592806339263916},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.5791205763816833},{"id":"https://openalex.org/C62611344","wikidata":"https://www.wikidata.org/wiki/Q1062658","display_name":"Node (physics)","level":2,"score":0.5731010437011719},{"id":"https://openalex.org/C2779696439","wikidata":"https://www.wikidata.org/wiki/Q7512811","display_name":"Signature (topology)","level":2,"score":0.548564612865448},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5240359902381897},{"id":"https://openalex.org/C116738811","wikidata":"https://www.wikidata.org/wiki/Q608751","display_name":"Nearest neighbor search","level":2,"score":0.4861690402030945},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4390362501144409},{"id":"https://openalex.org/C81917197","wikidata":"https://www.wikidata.org/wiki/Q628760","display_name":"Selection (genetic algorithm)","level":2,"score":0.4334656894207001},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.42827707529067993},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.4264230728149414},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.3767543435096741},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3758176565170288},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.25559744238853455},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16799089312553406},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.14873582124710083},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1485091745853424},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"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/C37914503","wikidata":"https://www.wikidata.org/wiki/Q156495","display_name":"Mathematical physics","level":1,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"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/C66938386","wikidata":"https://www.wikidata.org/wiki/Q633538","display_name":"Structural engineering","level":1,"score":0.0},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/access.2020.2996945","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2996945","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09099253.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:4f82ae9831ce44e0aea3789c5a6c6893","is_oa":true,"landing_page_url":"https://doaj.org/article/4f82ae9831ce44e0aea3789c5a6c6893","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by-sa","license_id":"https://openalex.org/licenses/cc-by-sa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"IEEE Access, Vol 8, Pp 98193-98204 (2020)","raw_type":"article"},{"id":"pmh:oai:repository.ust.hk:1783.1-104081","is_oa":false,"landing_page_url":"http://repository.ust.hk/ir/Record/1783.1-104081","pdf_url":null,"source":{"id":"https://openalex.org/S4306401796","display_name":"Rare & Special e-Zone (The Hong Kong University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I200769079","host_organization_name":"Hong Kong University of Science and Technology","host_organization_lineage":["https://openalex.org/I200769079"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":{"id":"doi:10.1109/access.2020.2996945","is_oa":true,"landing_page_url":"https://doi.org/10.1109/access.2020.2996945","pdf_url":"https://ieeexplore.ieee.org/ielx7/6287639/8948470/09099253.pdf","source":{"id":"https://openalex.org/S2485537415","display_name":"IEEE Access","issn_l":"2169-3536","issn":["2169-3536"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Access","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[{"id":"https://openalex.org/G1568672042","display_name":null,"funder_award_id":"2019R1F1A1058548","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G342704958","display_name":null,"funder_award_id":"funded","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G4445624639","display_name":null,"funder_award_id":"105979","funder_id":"https://openalex.org/F4320320671","funder_display_name":"National Research Foundation"},{"id":"https://openalex.org/G6202940033","display_name":null,"funder_award_id":"2019R1F1A1059795","funder_id":"https://openalex.org/F4320322120","funder_display_name":"National Research Foundation of Korea"},{"id":"https://openalex.org/G7685055460","display_name":null,"funder_award_id":"Grant","funder_id":"https://openalex.org/F4320328359","funder_display_name":"Ministry of Science and ICT, South Korea"}],"funders":[{"id":"https://openalex.org/F4320320671","display_name":"National Research Foundation","ror":"https://ror.org/05s0g1g46"},{"id":"https://openalex.org/F4320322120","display_name":"National Research Foundation of Korea","ror":"https://ror.org/013aysd81"},{"id":"https://openalex.org/F4320328359","display_name":"Ministry of Science and ICT, South Korea","ror":"https://ror.org/01wpjm123"}],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3031244230.pdf","grobid_xml":"https://content.openalex.org/works/W3031244230.grobid-xml"},"referenced_works_count":61,"referenced_works":["https://openalex.org/W58646613","https://openalex.org/W1502619761","https://openalex.org/W1536525420","https://openalex.org/W1583471564","https://openalex.org/W1768336749","https://openalex.org/W1780567500","https://openalex.org/W1970026646","https://openalex.org/W1973001156","https://openalex.org/W1983578042","https://openalex.org/W1987869189","https://openalex.org/W1989383714","https://openalex.org/W2010392031","https://openalex.org/W2010541316","https://openalex.org/W2012459404","https://openalex.org/W2038361443","https://openalex.org/W2073112656","https://openalex.org/W2074231493","https://openalex.org/W2083235381","https://openalex.org/W2087829218","https://openalex.org/W2096598900","https://openalex.org/W2097184821","https://openalex.org/W2097776316","https://openalex.org/W2099225351","https://openalex.org/W2100548092","https://openalex.org/W2101798015","https://openalex.org/W2105423800","https://openalex.org/W2105436061","https://openalex.org/W2107293766","https://openalex.org/W2111192396","https://openalex.org/W2117831564","https://openalex.org/W2119057313","https://openalex.org/W2121269638","https://openalex.org/W2121516976","https://openalex.org/W2123020735","https://openalex.org/W2125980212","https://openalex.org/W2127675794","https://openalex.org/W2130825214","https://openalex.org/W2133299088","https://openalex.org/W2150916025","https://openalex.org/W2152407760","https://openalex.org/W2161443453","https://openalex.org/W2161936973","https://openalex.org/W2167439683","https://openalex.org/W2167847032","https://openalex.org/W2433194246","https://openalex.org/W2486424789","https://openalex.org/W2562696781","https://openalex.org/W2745750801","https://openalex.org/W2795589160","https://openalex.org/W2911030582","https://openalex.org/W2928374578","https://openalex.org/W2931927337","https://openalex.org/W2951438725","https://openalex.org/W4213169074","https://openalex.org/W6630171628","https://openalex.org/W6638104246","https://openalex.org/W6674576723","https://openalex.org/W6677631532","https://openalex.org/W6683401941","https://openalex.org/W6722837056","https://openalex.org/W6761368745"],"related_works":["https://openalex.org/W2399644331","https://openalex.org/W2187092961","https://openalex.org/W2131677984","https://openalex.org/W2405436873","https://openalex.org/W1516985461","https://openalex.org/W2527905720","https://openalex.org/W52396946","https://openalex.org/W1973578339","https://openalex.org/W1824878879","https://openalex.org/W2043481183"],"abstract_inverted_index":{"In":[0,105],"this":[1,106],"paper,":[2,107],"we":[3,33,108,166],"study":[4],"the":[5,29,48,52,70,135,169,186,191,195],"problem":[6],"of":[7,54,67,151,158,171],"string":[8,22],"similarity":[9,30],"search":[10],"to":[11,19,46,61,116,155],"retrieve":[12],"in":[13,69,129,174],"a":[14,20,24,43,64,97,102,122,140,144,163],"database":[15],"all":[16],"strings":[17],"similar":[18],"query":[21],"within":[23],"given":[25,103],"threshold.":[26,104],"To":[27,50,87],"measure":[28],"between":[31],"strings,":[32],"use":[34],"edit":[35,55],"distance.":[36],"Many":[37],"algorithms":[38],"have":[39],"been":[40,80],"proposed":[41,81,187],"under":[42],"filtering-and-verification":[44],"framework":[45],"solve":[47],"problem.":[49],"reduce":[51,168],"overhead":[53,170],"distance":[56],"verification,":[57],"it":[58],"is":[59],"crucial":[60],"efficiently":[62,83],"generate":[63,88],"small":[65],"number":[66],"candidates":[68],"filtering":[71],"phase.":[72],"Recently,":[73],"an":[74,130,152],"index":[75,172],"structure":[76],"named":[77,143],"HSTree":[78,94,118,127,153,175],"has":[79],"for":[82],"generating":[84],"candidate":[85],"strings.":[86],"candidates,":[89],"they":[90],"select":[91,117],"and":[92,120],"utilize":[93],"nodes":[95,128,176],"at":[96],"specific":[98],"level":[99],"calculated":[100],"from":[101],"observe":[109],"that":[110,125,185],"there":[111],"are":[112],"many":[113],"alternative":[114],"ways":[115],"nodes,":[119],"propose":[121,139],"novel":[123],"technique":[124,188,193],"selects":[126],"optimized":[131],"way":[132],"based":[133],"on":[134],"observation.":[136],"We":[137],"also":[138],"modified":[141],"HSTree,":[142,146,165],"threaded":[145,164],"which":[147],"connects":[148],"inverted":[149,156],"lists":[150,157],"node":[154],"its":[159],"child":[160],"nodes.":[161,181],"With":[162],"can":[167],"lookups":[173],"while":[177],"selecting":[178],"optimal":[179],"tree":[180],"Experimental":[182],"results":[183],"show":[184],"significantly":[189],"outperforms":[190],"existing":[192],"using":[194],"HSTree.":[196]},"counts_by_year":[{"year":2020,"cited_by_count":1}],"updated_date":"2026-04-10T15:06:20.359241","created_date":"2025-10-10T00:00:00"}