{"id":"https://openalex.org/W2912002037","doi":"https://doi.org/10.4149/cai_2018_6_1313","title":"FingerPrint Based Duplicate Detection in Streamed Data","display_name":"FingerPrint Based Duplicate Detection in Streamed Data","publication_year":2018,"publication_date":"2018-01-01","ids":{"openalex":"https://openalex.org/W2912002037","doi":"https://doi.org/10.4149/cai_2018_6_1313","mag":"2912002037"},"language":"en","primary_location":{"id":"doi:10.4149/cai_2018_6_1313","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_6_1313","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"diamond","oa_url":"https://doi.org/10.4149/cai_2018_6_1313","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5101705969","display_name":"Amritpal Singh","orcid":"https://orcid.org/0000-0002-6783-0960"},"institutions":[{"id":"https://openalex.org/I162030827","display_name":"Thapar Institute of Engineering & Technology","ror":"https://ror.org/00wdq3744","country_code":"IN","type":"education","lineage":["https://openalex.org/I162030827"]}],"countries":["IN"],"is_corresponding":true,"raw_author_name":"Amritpal Singh","raw_affiliation_strings":["Department of Computer Science and Engineering, Thapar University, Patiala, Punjab"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Thapar University, Patiala, Punjab","institution_ids":["https://openalex.org/I162030827"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5053714308","display_name":"Shalini Batra","orcid":"https://orcid.org/0000-0002-6800-0221"},"institutions":[{"id":"https://openalex.org/I162030827","display_name":"Thapar Institute of Engineering & Technology","ror":"https://ror.org/00wdq3744","country_code":"IN","type":"education","lineage":["https://openalex.org/I162030827"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Shalini Batra","raw_affiliation_strings":["Department of Computer Science and Engineering, Thapar University, Patiala, Punjab"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Thapar University, Patiala, Punjab","institution_ids":["https://openalex.org/I162030827"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5101705969"],"corresponding_institution_ids":["https://openalex.org/I162030827"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.20311181,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"37","issue":"6","first_page":"1313","last_page":"1338"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11478","display_name":"Caching and Content Delivery","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9983999729156494,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9940999746322632,"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/T11896","display_name":"Opportunistic and Delay-Tolerant Networks","score":0.9587000012397766,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/bloom-filter","display_name":"Bloom filter","score":0.9538369178771973},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.8143488168716431},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7872154712677002},{"id":"https://openalex.org/keywords/false-positive-paradox","display_name":"False positive paradox","score":0.6749399304389954},{"id":"https://openalex.org/keywords/fingerprint","display_name":"Fingerprint (computing)","score":0.6393178701400757},{"id":"https://openalex.org/keywords/data-structure","display_name":"Data structure","score":0.5130366086959839},{"id":"https://openalex.org/keywords/filter","display_name":"Filter (signal processing)","score":0.5098318457603455},{"id":"https://openalex.org/keywords/false-positives-and-false-negatives","display_name":"False positives and false negatives","score":0.45367783308029175},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4294394254684448},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3373849391937256},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.26964622735977173},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.24646922945976257},{"id":"https://openalex.org/keywords/computer-vision","display_name":"Computer vision","score":0.0949491560459137}],"concepts":[{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.9538369178771973},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.8143488168716431},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7872154712677002},{"id":"https://openalex.org/C64869954","wikidata":"https://www.wikidata.org/wiki/Q1859747","display_name":"False positive paradox","level":2,"score":0.6749399304389954},{"id":"https://openalex.org/C2777826928","wikidata":"https://www.wikidata.org/wiki/Q3745713","display_name":"Fingerprint (computing)","level":2,"score":0.6393178701400757},{"id":"https://openalex.org/C162319229","wikidata":"https://www.wikidata.org/wiki/Q175263","display_name":"Data structure","level":2,"score":0.5130366086959839},{"id":"https://openalex.org/C106131492","wikidata":"https://www.wikidata.org/wiki/Q3072260","display_name":"Filter (signal processing)","level":2,"score":0.5098318457603455},{"id":"https://openalex.org/C112789634","wikidata":"https://www.wikidata.org/wiki/Q18207010","display_name":"False positives and false negatives","level":3,"score":0.45367783308029175},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4294394254684448},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3373849391937256},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.26964622735977173},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.24646922945976257},{"id":"https://openalex.org/C31972630","wikidata":"https://www.wikidata.org/wiki/Q844240","display_name":"Computer vision","level":1,"score":0.0949491560459137},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4149/cai_2018_6_1313","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_6_1313","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"}],"best_oa_location":{"id":"doi:10.4149/cai_2018_6_1313","is_oa":true,"landing_page_url":"https://doi.org/10.4149/cai_2018_6_1313","pdf_url":null,"source":{"id":"https://openalex.org/S4210200093","display_name":"Computing and Informatics","issn_l":"1335-9150","issn":["1335-9150","2585-8807"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Computing and Informatics","raw_type":"journal-article"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/8","score":0.5699999928474426,"display_name":"Decent work and economic growth"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W1557094818","https://openalex.org/W4383553080","https://openalex.org/W2127784084","https://openalex.org/W2102140417","https://openalex.org/W4293879742","https://openalex.org/W4300824226","https://openalex.org/W2292926063","https://openalex.org/W2950578529","https://openalex.org/W2212047860","https://openalex.org/W2155669648"],"abstract_inverted_index":{"In":[0],"computing,":[1],"duplicate":[2,8,14,37,69,106],"data":[3,15,19,34,94,134,155],"detection":[4,38,136],"refers":[5],"to":[6],"identifying":[7],"copies":[9],"of":[10,42,114,117,122],"repeating":[11],"data.":[12,119],"Identifying":[13],"items":[16],"in":[17,95,110,153],"streamed":[18],"and":[20,80,102,107,137,142],"eliminating":[21],"them":[22],"before":[23],"storing,":[24],"is":[25],"a":[26,32,40],"complex":[27],"job.":[28],"This":[29],"paper":[30],"proposes":[31],"novel":[33],"structure":[35],"for":[36,68,132],"using":[39,98],"variant":[41],"stable":[43],"Bloom":[44,50,58,129],"filter":[45,59],"named":[46],"as":[47,85,87],"FingerPrint":[48],"Stable":[49],"Filter":[51],"(FP-SBF).":[52],"The":[53,120],"proposed":[54,147],"approach":[55,148],"uses":[56,72],"counting":[57],"with":[60,64,127,156],"fingerprint":[61],"bits":[62],"along":[63],"an":[65],"optimization":[66],"mechanism":[67],"detection.":[70],"FP-SBF":[71,90,123],"d-left":[73],"hashing":[74],"which":[75],"reduces":[76],"the":[77,82,115,146,151],"computational":[78],"time":[79],"decreases":[81],"false":[83,88],"positives":[84],"well":[86],"negatives.":[89],"can":[91],"process":[92],"unbounded":[93],"single":[96],"pass,":[97],"k":[99],"hash":[100],"functions,":[101],"successfully":[103],"differentiate":[104],"between":[105],"distinct":[108],"elements":[109],"O(k+1)":[111],"time,":[112],"independent":[113],"size":[116],"incoming":[118],"performance":[121],"has":[124,139],"been":[125,140],"compared":[126],"various":[128],"Filters":[130],"used":[131],"stream":[133],"duplication":[135],"it":[138],"theoretically":[141],"experimentally":[143],"proved":[144],"that":[145],"efficiently":[149],"detects":[150],"duplicates":[152],"streaming":[154],"less":[157],"memory":[158],"requirements.":[159]},"counts_by_year":[{"year":2023,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
