{"id":"https://openalex.org/W1603793496","doi":"https://doi.org/10.1109/icaci.2015.7184772","title":"Hamming distance based approximate similarity text search algorithm","display_name":"Hamming distance based approximate similarity text search algorithm","publication_year":2015,"publication_date":"2015-03-01","ids":{"openalex":"https://openalex.org/W1603793496","doi":"https://doi.org/10.1109/icaci.2015.7184772","mag":"1603793496"},"language":"en","primary_location":{"id":"doi:10.1109/icaci.2015.7184772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaci.2015.7184772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Seventh International Conference on Advanced Computational Intelligence (ICACI)","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/A5101788068","display_name":"Haifeng Hu","orcid":"https://orcid.org/0000-0002-6585-3106"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]},{"id":"https://openalex.org/I76569877","display_name":"Southeast University","ror":"https://ror.org/04ct4d772","country_code":"CN","type":"education","lineage":["https://openalex.org/I76569877"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Haifeng Hu","raw_affiliation_strings":["Department of Telecommunication and Information Engineering, Southeast University, Nanjing, China","Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, 210003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunication and Information Engineering, Southeast University, Nanjing, China","institution_ids":["https://openalex.org/I76569877"]},{"raw_affiliation_string":"Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, 210003, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5115589479","display_name":"Liang Zhang","orcid":"https://orcid.org/0000-0002-5220-4748"},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Liang Zhang","raw_affiliation_strings":["Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, 210003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, 210003, China","institution_ids":["https://openalex.org/I41198531"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100872849","display_name":"Jianshen Wu","orcid":null},"institutions":[{"id":"https://openalex.org/I41198531","display_name":"Nanjing University of Posts and Telecommunications","ror":"https://ror.org/043bpky34","country_code":"CN","type":"education","lineage":["https://openalex.org/I41198531"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianshen Wu","raw_affiliation_strings":["Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, 210003, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China","institution_ids":["https://openalex.org/I41198531"]},{"raw_affiliation_string":"Department of Telecommunication and Information Engineering, Nanjing University of Posts and Telecommunications, 210003, China","institution_ids":["https://openalex.org/I41198531"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/1707","display_name":"Computer Vision and Pattern Recognition"},"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":0.9987000226974487,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9973000288009644,"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/substring","display_name":"Substring","score":0.843025267124176},{"id":"https://openalex.org/keywords/hamming-distance","display_name":"Hamming distance","score":0.8108799457550049},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7401791214942932},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.5686780214309692},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.5562381148338318},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.546031653881073},{"id":"https://openalex.org/keywords/hamming-code","display_name":"Hamming code","score":0.5095370411872864},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3392181396484375},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21554598212242126},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.09281793236732483},{"id":"https://openalex.org/keywords/decoding-methods","display_name":"Decoding methods","score":0.07463976740837097}],"concepts":[{"id":"https://openalex.org/C182407805","wikidata":"https://www.wikidata.org/wiki/Q2626534","display_name":"Substring","level":3,"score":0.843025267124176},{"id":"https://openalex.org/C193319292","wikidata":"https://www.wikidata.org/wiki/Q272172","display_name":"Hamming distance","level":2,"score":0.8108799457550049},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7401791214942932},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.5686780214309692},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.5562381148338318},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.546031653881073},{"id":"https://openalex.org/C73150493","wikidata":"https://www.wikidata.org/wiki/Q853922","display_name":"Hamming code","level":4,"score":0.5095370411872864},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3392181396484375},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21554598212242126},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.09281793236732483},{"id":"https://openalex.org/C57273362","wikidata":"https://www.wikidata.org/wiki/Q576722","display_name":"Decoding methods","level":2,"score":0.07463976740837097},{"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/C157125643","wikidata":"https://www.wikidata.org/wiki/Q884707","display_name":"Block code","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icaci.2015.7184772","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icaci.2015.7184772","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 Seventh International Conference on Advanced Computational Intelligence (ICACI)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W1502916507","https://openalex.org/W1541459201","https://openalex.org/W1967408872","https://openalex.org/W1993530675","https://openalex.org/W2040855741","https://openalex.org/W2048779798","https://openalex.org/W2073880961","https://openalex.org/W2132069633","https://openalex.org/W2142058655","https://openalex.org/W2145349611","https://openalex.org/W2147717514","https://openalex.org/W2162006472","https://openalex.org/W2162530156","https://openalex.org/W2170037597","https://openalex.org/W2397770138","https://openalex.org/W6629956336","https://openalex.org/W6632397832","https://openalex.org/W6680793065","https://openalex.org/W6685012337"],"related_works":["https://openalex.org/W1674453943","https://openalex.org/W2985943250","https://openalex.org/W2945511280","https://openalex.org/W1540916738","https://openalex.org/W3127593639","https://openalex.org/W2062696773","https://openalex.org/W4287814113","https://openalex.org/W3016364484","https://openalex.org/W2122887143","https://openalex.org/W2020935936"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2],"Hamming":[3,70],"distance":[4,71],"based":[5],"approximate":[6],"similarity":[7],"text":[8,20,49,78,126],"search":[9,110],"(HASTS)":[10],"algorithm":[11,24,102,118],"to":[12,48,51,89],"improve":[13],"the":[14,31,36,41,53,56,60,69,73,77,81,91,100,108,116,121],"quality":[15],"of":[16,55,93,99],"queries":[17],"in":[18,80,124],"massive":[19,125],"data.":[21],"The":[22,112],"HASTS":[23,101,117],"first":[25],"constructs":[26],"an":[27],"index":[28],"table":[29],"with":[30,107,128],"substrings":[32],"extracted":[33],"randomly":[34],"from":[35],"feature":[37],"fingerprints":[38],"generated":[39],"by":[40,67],"SimHash":[42],"algorithm.":[43,111],"Then,":[44],"it":[45],"assigns":[46],"weights":[47],"terms":[50,79],"reduce":[52],"size":[54],"candidate":[57,82],"set.":[58,83],"Furthermore,":[59],"final":[61],"query":[62,74,97,122],"result":[63],"can":[64,119],"be":[65],"obtained":[66],"comparing":[68],"between":[72],"term":[75],"and":[76,103],"Finally,":[84],"Extensive":[85],"simulations":[86],"are":[87],"conducted":[88],"analysis":[90],"influence":[92],"different":[94],"parameters":[95],"on":[96],"performance":[98,106],"compare":[104],"its":[105],"existing":[109],"results":[113],"show":[114],"that":[115],"satisfy":[120],"requirements":[123],"data":[127],"relatively":[129],"low":[130],"overheads.":[131]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2020,"cited_by_count":3},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":3},{"year":2017,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}