{"id":"https://openalex.org/W4241467715","doi":"https://doi.org/10.1504/ijart.2019.10020165","title":"QSJoin: a new string similarity join method based on Q-sample and statistical features","display_name":"QSJoin: a new string similarity join method based on Q-sample and statistical features","publication_year":2019,"publication_date":"2019-01-01","ids":{"openalex":"https://openalex.org/W4241467715","doi":"https://doi.org/10.1504/ijart.2019.10020165"},"language":"en","primary_location":{"id":"doi:10.1504/ijart.2019.10020165","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijart.2019.10020165","pdf_url":null,"source":{"id":"https://openalex.org/S86116553","display_name":"International Journal of Arts and Technology","issn_l":"1754-8853","issn":["1754-8853","1754-8861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Arts and Technology","raw_type":"journal-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/A5100360046","display_name":"Xiaoxia Wang","orcid":"https://orcid.org/0000-0003-2625-6816"},"institutions":[{"id":"https://openalex.org/I97009856","display_name":"Bohai University","ror":"https://ror.org/01kdzej58","country_code":"CN","type":"education","lineage":["https://openalex.org/I97009856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xiaoxia Wang","raw_affiliation_strings":["College of Information Science and Technology, Bohai University, Jinzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Bohai University, Jinzhou, China","institution_ids":["https://openalex.org/I97009856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5085261336","display_name":"Bo Wu","orcid":"https://orcid.org/0000-0002-1446-408X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Bo Wu","raw_affiliation_strings":["Dell EMC, No. 2, Hanzhong Road, Nanjing, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Dell EMC, No. 2, Hanzhong Road, Nanjing, China","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5059570868","display_name":"Decai Sun","orcid":"https://orcid.org/0000-0002-6664-4998"},"institutions":[{"id":"https://openalex.org/I97009856","display_name":"Bohai University","ror":"https://ror.org/01kdzej58","country_code":"CN","type":"education","lineage":["https://openalex.org/I97009856"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Decai Sun","raw_affiliation_strings":["College of Information Science and Technology, Bohai University, Jinzhou, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Information Science and Technology, Bohai University, Jinzhou, China","institution_ids":["https://openalex.org/I97009856"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5030278223","display_name":"Puzhao Ji","orcid":null},"institutions":[{"id":"https://openalex.org/I150229711","display_name":"University of Electronic Science and Technology of China","ror":"https://ror.org/04qr3zq92","country_code":"CN","type":"education","lineage":["https://openalex.org/I150229711"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Puzhao Ji","raw_affiliation_strings":["School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu, China","institution_ids":["https://openalex.org/I150229711"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.37551716,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"11","issue":"3","first_page":"285","last_page":"285"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11719","display_name":"Data Quality and Management","score":0.9957000017166138,"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":0.9957000017166138,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9916999936103821,"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/T10028","display_name":"Topic Modeling","score":0.9304999709129333,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.817623496055603},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.720981240272522},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.6875842809677124},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.6868584156036377},{"id":"https://openalex.org/keywords/join","display_name":"Join (topology)","score":0.6736901998519897},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.6628022193908691},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.6421114802360535},{"id":"https://openalex.org/keywords/bit-array","display_name":"Bit array","score":0.5149005651473999},{"id":"https://openalex.org/keywords/string-metric","display_name":"String metric","score":0.49976253509521484},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.45461782813072205},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3789583742618561},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.22531023621559143},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.188879132270813},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.17872074246406555},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.08118164539337158}],"concepts":[{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.817623496055603},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.720981240272522},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.6875842809677124},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.6868584156036377},{"id":"https://openalex.org/C2776124973","wikidata":"https://www.wikidata.org/wiki/Q3183033","display_name":"Join (topology)","level":2,"score":0.6736901998519897},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.6628022193908691},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.6421114802360535},{"id":"https://openalex.org/C150807984","wikidata":"https://www.wikidata.org/wiki/Q1992074","display_name":"Bit array","level":3,"score":0.5149005651473999},{"id":"https://openalex.org/C22820288","wikidata":"https://www.wikidata.org/wiki/Q9050568","display_name":"String metric","level":4,"score":0.49976253509521484},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.45461782813072205},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3789583742618561},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.22531023621559143},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.188879132270813},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.17872074246406555},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.08118164539337158},{"id":"https://openalex.org/C18903297","wikidata":"https://www.wikidata.org/wiki/Q7150","display_name":"Ecology","level":1,"score":0.0},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0},{"id":"https://openalex.org/C2777299769","wikidata":"https://www.wikidata.org/wiki/Q3707858","display_name":"Type (biology)","level":2,"score":0.0},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","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/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"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/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1504/ijart.2019.10020165","is_oa":false,"landing_page_url":"https://doi.org/10.1504/ijart.2019.10020165","pdf_url":null,"source":{"id":"https://openalex.org/S86116553","display_name":"International Journal of Arts and Technology","issn_l":"1754-8853","issn":["1754-8853","1754-8861"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310317825","host_organization_name":"Inderscience Publishers","host_organization_lineage":["https://openalex.org/P4310317825"],"host_organization_lineage_names":["Inderscience Publishers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Arts and Technology","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2393491644","https://openalex.org/W4206577045","https://openalex.org/W650102067","https://openalex.org/W3086237447","https://openalex.org/W2740404111","https://openalex.org/W1550806730","https://openalex.org/W1496672428","https://openalex.org/W2589740103","https://openalex.org/W1966967794","https://openalex.org/W2397450670"],"abstract_inverted_index":{"Similarity":[0],"joins":[1],"is":[2,58,86,102],"an":[3],"essential":[4],"operation":[5],"in":[6,41],"big":[7],"data":[8,12,15],"analytics,":[9],"such":[10],"as":[11],"integration":[13],"and":[14,38,67,96,126],"cleaning.":[16],"In":[17,49,80],"this":[18],"paper,":[19],"we":[20],"propose":[21],"a":[22,46,51,69,82],"new":[23,52],"algorithm,":[24],"called":[25],"QSJoin,":[26],"to":[27,60,88],"support":[28],"efficient":[29],"string":[30],"similarity":[31],"join":[32],"by":[33,104],"reducing":[34],"the":[35,62,98,105],"shuffle":[36],"cost":[37,40],"transmission":[39],"MapReduce.":[42],"Our":[43],"algorithm":[44,122],"employs":[45],"filter-verify":[47],"framework.":[48],"filtration,":[50],"signature":[53],"scheme":[54,85],"based":[55],"on":[56,116],"q-sample":[57],"adopted":[59,87],"decrease":[61],"number":[63,71],"of":[64,72,107],"generated":[65],"signatures,":[66],"then":[68,97],"large":[70],"dissimilar":[73,91],"pairs":[74,92,101,109],"are":[75],"discarded":[76],"with":[77,93,110],"Standard-Match":[78],"filter.":[79],"verification,":[81],"multi-vector":[83],"filter":[84],"eliminate":[89],"more":[90],"statistical":[94],"features,":[95],"final":[99],"true":[100],"extracted":[103],"verification":[106,112],"candidate":[108],"length-aware":[111],"method.":[113],"Experimental":[114],"result":[115],"real-world":[117],"datasets":[118],"shows":[119],"that":[120],"our":[121],"achieves":[123],"high":[124],"performance":[125],"outperforms":[127],"state-of-the-art":[128],"approaches.":[129]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}