{"id":"https://openalex.org/W3206779369","doi":"https://doi.org/10.1109/isc253183.2021.9562939","title":"An Unbiased Estimator for Hamming LSH Blocking","display_name":"An Unbiased Estimator for Hamming LSH Blocking","publication_year":2021,"publication_date":"2021-09-07","ids":{"openalex":"https://openalex.org/W3206779369","doi":"https://doi.org/10.1109/isc253183.2021.9562939","mag":"3206779369"},"language":"en","primary_location":{"id":"doi:10.1109/isc253183.2021.9562939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isc253183.2021.9562939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Smart Cities Conference (ISC2)","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/A5021354735","display_name":"Dimitrios Karapiperis","orcid":"https://orcid.org/0000-0002-3878-5988"},"institutions":[{"id":"https://openalex.org/I183898223","display_name":"International Hellenic University","ror":"https://ror.org/00708jp83","country_code":"GR","type":"education","lineage":["https://openalex.org/I183898223"]}],"countries":["GR"],"is_corresponding":true,"raw_author_name":"Dimitrios Karapiperis","raw_affiliation_strings":["International Hellenic University, Thermi, Greece"],"affiliations":[{"raw_affiliation_string":"International Hellenic University, Thermi, Greece","institution_ids":["https://openalex.org/I183898223"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5081141966","display_name":"Aris Gkoulalas-Divanis","orcid":"https://orcid.org/0000-0003-0011-6591"},"institutions":[{"id":"https://openalex.org/I1341412227","display_name":"IBM (United States)","ror":"https://ror.org/05hh8d621","country_code":"US","type":"company","lineage":["https://openalex.org/I1341412227"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Aris Gkoulalas-Divanis","raw_affiliation_strings":["IBM Watson Health,Cambridge,MA,USA"],"affiliations":[{"raw_affiliation_string":"IBM Watson Health,Cambridge,MA,USA","institution_ids":["https://openalex.org/I1341412227"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5021354735"],"corresponding_institution_ids":["https://openalex.org/I183898223"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18245757,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"4"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9358999729156494,"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/T11614","display_name":"Cloud Data Security Solutions","score":0.9236000180244446,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7070052027702332},{"id":"https://openalex.org/keywords/locality-sensitive-hashing","display_name":"Locality-sensitive hashing","score":0.7005484104156494},{"id":"https://openalex.org/keywords/record-linkage","display_name":"Record linkage","score":0.6138145327568054},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5860398411750793},{"id":"https://openalex.org/keywords/blocking","display_name":"Blocking (statistics)","score":0.5749297142028809},{"id":"https://openalex.org/keywords/estimator","display_name":"Estimator","score":0.5683825612068176},{"id":"https://openalex.org/keywords/probabilistic-logic","display_name":"Probabilistic logic","score":0.5431413650512695},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.5078781247138977},{"id":"https://openalex.org/keywords/sampling","display_name":"Sampling (signal processing)","score":0.4961932301521301},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.4391574561595917},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.40853530168533325},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.33936160802841187},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.31918710470199585},{"id":"https://openalex.org/keywords/hash-table","display_name":"Hash table","score":0.23578545451164246},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.21345919370651245},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.15735292434692383},{"id":"https://openalex.org/keywords/detector","display_name":"Detector","score":0.09117892384529114},{"id":"https://openalex.org/keywords/computer-security","display_name":"Computer security","score":0.08487269282341003}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7070052027702332},{"id":"https://openalex.org/C74270461","wikidata":"https://www.wikidata.org/wiki/Q1625299","display_name":"Locality-sensitive hashing","level":4,"score":0.7005484104156494},{"id":"https://openalex.org/C142210648","wikidata":"https://www.wikidata.org/wiki/Q1266546","display_name":"Record linkage","level":3,"score":0.6138145327568054},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5860398411750793},{"id":"https://openalex.org/C144745244","wikidata":"https://www.wikidata.org/wiki/Q4927286","display_name":"Blocking (statistics)","level":2,"score":0.5749297142028809},{"id":"https://openalex.org/C185429906","wikidata":"https://www.wikidata.org/wiki/Q1130160","display_name":"Estimator","level":2,"score":0.5683825612068176},{"id":"https://openalex.org/C49937458","wikidata":"https://www.wikidata.org/wiki/Q2599292","display_name":"Probabilistic logic","level":2,"score":0.5431413650512695},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.5078781247138977},{"id":"https://openalex.org/C140779682","wikidata":"https://www.wikidata.org/wiki/Q210868","display_name":"Sampling (signal processing)","level":3,"score":0.4961932301521301},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.4391574561595917},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.40853530168533325},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.33936160802841187},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.31918710470199585},{"id":"https://openalex.org/C67388219","wikidata":"https://www.wikidata.org/wiki/Q207440","display_name":"Hash table","level":3,"score":0.23578545451164246},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.21345919370651245},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.15735292434692383},{"id":"https://openalex.org/C94915269","wikidata":"https://www.wikidata.org/wiki/Q1834857","display_name":"Detector","level":2,"score":0.09117892384529114},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.08487269282341003},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C76155785","wikidata":"https://www.wikidata.org/wiki/Q418","display_name":"Telecommunications","level":1,"score":0.0},{"id":"https://openalex.org/C149923435","wikidata":"https://www.wikidata.org/wiki/Q37732","display_name":"Demography","level":1,"score":0.0},{"id":"https://openalex.org/C2908647359","wikidata":"https://www.wikidata.org/wiki/Q2625603","display_name":"Population","level":2,"score":0.0},{"id":"https://openalex.org/C144024400","wikidata":"https://www.wikidata.org/wiki/Q21201","display_name":"Sociology","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isc253183.2021.9562939","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isc253183.2021.9562939","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2021 IEEE International Smart Cities Conference (ISC2)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/9","score":0.4099999964237213,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W1724849505","https://openalex.org/W1932742904","https://openalex.org/W1998600401","https://openalex.org/W2024770506","https://openalex.org/W2038276547","https://openalex.org/W2056099894","https://openalex.org/W2109834209","https://openalex.org/W2111116800","https://openalex.org/W2117974736","https://openalex.org/W2154785834","https://openalex.org/W2289049650","https://openalex.org/W2790957175","https://openalex.org/W2796291475","https://openalex.org/W2804222599","https://openalex.org/W4234053595","https://openalex.org/W4254734767","https://openalex.org/W4254788633","https://openalex.org/W6749221066"],"related_works":["https://openalex.org/W2508614996","https://openalex.org/W2144265691","https://openalex.org/W3161390536","https://openalex.org/W1993530675","https://openalex.org/W2080622138","https://openalex.org/W2033383639","https://openalex.org/W3108918257","https://openalex.org/W1540269031","https://openalex.org/W2301752323","https://openalex.org/W154872207"],"abstract_inverted_index":{"Record":[0],"linkage":[1,131],"has":[2],"recently":[3],"received":[4],"much":[5],"attention":[6],"as":[7],"a":[8,39,94,101],"result":[9],"of":[10,33,41,69,82,85,98,119,126],"the":[11,31,57,66,70,80,83,115,124],"many":[12],"data":[13,27,47,91,111],"sources":[14],"that":[15,61],"are":[16],"nowadays":[17],"available":[18],"and":[19,37,100,117],"need":[20],"to":[21,24,49,65],"be":[22],"integrated":[23],"enable":[25],"large-scale":[26],"analyses.":[28],"Accurately":[29],"estimating":[30,123],"proportion":[32,81],"matching":[34,86,127],"record":[35,87,130],"pairs,":[36,43],"obtaining":[38],"sample":[40],"such":[42],"would":[44],"greatly":[45],"assist":[46],"custodians":[48],"compile":[50],"appropriate":[51],"business":[52],"plans.":[53],"This":[54,76],"paper":[55],"presents":[56],"first":[58],"sampling":[59,77],"method":[60,78],"is":[62],"specifically":[63],"tailored":[64],"particular":[67],"characteristics":[68],"Hamming":[71],"Locality-Sensitive":[72],"Hashing":[73],"(LSH)":[74],"Blocking.":[75],"estimates":[79],"number":[84,125],"pairs":[88,128],"between":[89],"two":[90],"sets,":[92,112],"with":[93],"specified":[95],"acceptable":[96],"level":[97],"error":[99],"certain":[102],"probabilistic":[103],"confidence.":[104],"Through":[105],"experimental":[106],"evaluation":[107],"using":[108],"four":[109],"real-world":[110],"we":[113],"show":[114],"effectiveness":[116],"efficiency":[118],"our":[120],"approach":[121],"in":[122,129],"tasks.":[132]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}