{"id":"https://openalex.org/W2885730538","doi":"https://doi.org/10.1109/icc.2018.8422284","title":"A Data-Deduplication-Based Matching Mechanism for URL Filtering","display_name":"A Data-Deduplication-Based Matching Mechanism for URL Filtering","publication_year":2018,"publication_date":"2018-05-01","ids":{"openalex":"https://openalex.org/W2885730538","doi":"https://doi.org/10.1109/icc.2018.8422284","mag":"2885730538"},"language":"en","primary_location":{"id":"doi:10.1109/icc.2018.8422284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc.2018.8422284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Communications (ICC)","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/A5072653222","display_name":"Yuhai Lu","orcid":null},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Yuhai Lu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5101651401","display_name":"Yanbing Liu","orcid":"https://orcid.org/0000-0001-8068-8316"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yanbing Liu","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100350829","display_name":"Chunyan Zhang","orcid":"https://orcid.org/0000-0001-8937-1307"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Chunyan Zhang","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5100533815","display_name":"Jianlong Tan","orcid":"https://orcid.org/0009-0001-4558-560X"},"institutions":[{"id":"https://openalex.org/I4210165038","display_name":"University of Chinese Academy of Sciences","ror":"https://ror.org/05qbk4x57","country_code":"CN","type":"education","lineage":["https://openalex.org/I19820366","https://openalex.org/I4210165038"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Jianlong Tan","raw_affiliation_strings":["University of Chinese Academy of Sciences, Beijing, China"],"affiliations":[{"raw_affiliation_string":"University of Chinese Academy of Sciences, Beijing, China","institution_ids":["https://openalex.org/I4210165038"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5072653222"],"corresponding_institution_ids":["https://openalex.org/I4210165038"],"apc_list":null,"apc_paid":null,"fwci":0.3258,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.67072509,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":94},"biblio":{"volume":"46","issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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"}},"topics":[{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9994999766349792,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9983999729156494,"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/T12326","display_name":"Network Packet Processing and Optimization","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/1708","display_name":"Hardware and Architecture"},"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/data-deduplication","display_name":"Data deduplication","score":0.8468931913375854},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.822172999382019},{"id":"https://openalex.org/keywords/hash-function","display_name":"Hash function","score":0.7084097862243652},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.6558534502983093},{"id":"https://openalex.org/keywords/string-searching-algorithm","display_name":"String searching algorithm","score":0.6451194286346436},{"id":"https://openalex.org/keywords/bloom-filter","display_name":"Bloom filter","score":0.5581018924713135},{"id":"https://openalex.org/keywords/approximate-string-matching","display_name":"Approximate string matching","score":0.5089197158813477},{"id":"https://openalex.org/keywords/string","display_name":"String (physics)","score":0.48095908761024475},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4560950994491577},{"id":"https://openalex.org/keywords/dbm","display_name":"dBm","score":0.4464501738548279},{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.4391050934791565},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.38311895728111267},{"id":"https://openalex.org/keywords/pattern-matching","display_name":"Pattern matching","score":0.31150275468826294},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.2515879273414612},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.16780513525009155},{"id":"https://openalex.org/keywords/computer-network","display_name":"Computer network","score":0.08495017886161804},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.07210195064544678}],"concepts":[{"id":"https://openalex.org/C32587265","wikidata":"https://www.wikidata.org/wiki/Q1182260","display_name":"Data deduplication","level":2,"score":0.8468931913375854},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.822172999382019},{"id":"https://openalex.org/C99138194","wikidata":"https://www.wikidata.org/wiki/Q183427","display_name":"Hash function","level":2,"score":0.7084097862243652},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.6558534502983093},{"id":"https://openalex.org/C7757238","wikidata":"https://www.wikidata.org/wiki/Q374040","display_name":"String searching algorithm","level":3,"score":0.6451194286346436},{"id":"https://openalex.org/C147224247","wikidata":"https://www.wikidata.org/wiki/Q885373","display_name":"Bloom filter","level":2,"score":0.5581018924713135},{"id":"https://openalex.org/C32610155","wikidata":"https://www.wikidata.org/wiki/Q1798621","display_name":"Approximate string matching","level":3,"score":0.5089197158813477},{"id":"https://openalex.org/C157486923","wikidata":"https://www.wikidata.org/wiki/Q1376436","display_name":"String (physics)","level":2,"score":0.48095908761024475},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4560950994491577},{"id":"https://openalex.org/C94105702","wikidata":"https://www.wikidata.org/wiki/Q777017","display_name":"dBm","level":4,"score":0.4464501738548279},{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.4391050934791565},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.38311895728111267},{"id":"https://openalex.org/C68859911","wikidata":"https://www.wikidata.org/wiki/Q1503724","display_name":"Pattern matching","level":2,"score":0.31150275468826294},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.2515879273414612},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.16780513525009155},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.08495017886161804},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.07210195064544678},{"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/C194257627","wikidata":"https://www.wikidata.org/wiki/Q211554","display_name":"Amplifier","level":3,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"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/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/icc.2018.8422284","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icc.2018.8422284","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2018 IEEE International Conference on Communications (ICC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":16,"referenced_works":["https://openalex.org/W124244495","https://openalex.org/W1595313252","https://openalex.org/W1972418517","https://openalex.org/W1973990666","https://openalex.org/W1977467261","https://openalex.org/W1981409766","https://openalex.org/W2084566754","https://openalex.org/W2092587157","https://openalex.org/W2099964107","https://openalex.org/W2159070959","https://openalex.org/W2916086000","https://openalex.org/W3004084820","https://openalex.org/W3145042860","https://openalex.org/W6605045863","https://openalex.org/W6671729338","https://openalex.org/W7058537420"],"related_works":["https://openalex.org/W3008420177","https://openalex.org/W2942719460","https://openalex.org/W2371981271","https://openalex.org/W2806950186","https://openalex.org/W3113874423","https://openalex.org/W2054173104","https://openalex.org/W2257399947","https://openalex.org/W2051764263","https://openalex.org/W2935705348","https://openalex.org/W2358632292"],"abstract_inverted_index":{"URL":[0,11,67,89,126,142,149],"filtering":[1,12,90,127,143,150],"plays":[2],"an":[3],"important":[4],"role":[5],"in":[6,77,97,116,167],"various":[7],"network":[8],"security":[9],"applications.":[10],"usually":[13],"requires":[14],"high":[15],"matching":[16,26,63,103,113,122,160],"performance,":[17],"but":[18],"the":[19,22,41,74,119,121,125,139,158],"performance":[20],"of":[21,51,73,124,141,148,157],"classical":[23],"multiple":[24,101,111],"string":[25,102,112],"algorithms":[27],"have":[28],"been":[29],"difficult":[30],"to":[31,44,55,81],"be":[32,45,95,130,164],"significantly":[33,137],"improved.":[34],"In":[35],"this":[36,56],"article,":[37],"we":[38,58],"found":[39],"that":[40,108],"online":[42],"URLs":[43,76,84],"filtered":[46],"contain":[47],"a":[48,60,78,110,154],"large":[49],"number":[50],"duplicate":[52,75,83],"URLs.":[53],"According":[54],"observation,":[57],"propose":[59],"novel":[61],"deduplication-based":[62],"mechanism":[64,155],"(DBM)":[65],"for":[66],"filtering.":[68],"The":[69,92],"DBM":[70,93,135,152],"caches":[71],"information":[72],"hash":[79],"table":[80],"avoid":[82],"being":[85],"repeatedly":[86],"scanned":[87],"by":[88,132],"system.":[91,144],"can":[94,129,136,163],"used":[96,115,166],"conjunction":[98,117],"with":[99,118],"any":[100],"algorithms.":[104],"Experimental":[105],"results":[106],"show":[107],"when":[109],"algorithm":[114,161],"DBM,":[120],"speed":[123,140,147],"system":[128],"increased":[131],"9\\%-68\\%.":[133],"So":[134],"accelerate":[138],"Besides":[145],"increasing":[146],"system,":[151],"is":[153],"independent":[156],"specific":[159],"and":[162],"easily":[165],"other":[168],"field.":[169]},"counts_by_year":[{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}