{"id":"https://openalex.org/W2913195718","doi":"https://doi.org/10.1109/bigdata.2018.8622005","title":"Achieving Horizontal Scalability in Density-based Clustering for URLs","display_name":"Achieving Horizontal Scalability in Density-based Clustering for URLs","publication_year":2018,"publication_date":"2018-12-01","ids":{"openalex":"https://openalex.org/W2913195718","doi":"https://doi.org/10.1109/bigdata.2018.8622005","mag":"2913195718"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2018.8622005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622005","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 Big Data (Big Data)","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://ieeexplore.ieee.org/document/8622005","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5019477068","display_name":"Azadeh Faroughi","orcid":"https://orcid.org/0000-0002-9945-8075"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":true,"raw_author_name":"Azadeh Faroughi","raw_affiliation_strings":["Politecnico di Torino"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5058428827","display_name":"Reza Javidan","orcid":"https://orcid.org/0000-0002-7788-6597"},"institutions":[{"id":"https://openalex.org/I177477856","display_name":"Polytechnic University of Turin","ror":"https://ror.org/00bgk9508","country_code":"IT","type":"education","lineage":["https://openalex.org/I177477856"]}],"countries":["IT"],"is_corresponding":false,"raw_author_name":"Reza Javidan","raw_affiliation_strings":["Politecnico di Torino"],"affiliations":[{"raw_affiliation_string":"Politecnico di Torino","institution_ids":["https://openalex.org/I177477856"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060087704","display_name":"Marco Mellia","orcid":"https://orcid.org/0000-0003-1859-6693"},"institutions":[{"id":"https://openalex.org/I204490172","display_name":"Shiraz University of Technology","ror":"https://ror.org/04bxa3v83","country_code":"IR","type":"education","lineage":["https://openalex.org/I204490172"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Marco Mellia","raw_affiliation_strings":["Shiraz University of Technology"],"affiliations":[{"raw_affiliation_string":"Shiraz University of Technology","institution_ids":["https://openalex.org/I204490172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5088062736","display_name":"Andrea Morichetta","orcid":"https://orcid.org/0000-0003-3765-3067"},"institutions":[{"id":"https://openalex.org/I204490172","display_name":"Shiraz University of Technology","ror":"https://ror.org/04bxa3v83","country_code":"IR","type":"education","lineage":["https://openalex.org/I204490172"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Andrea Morichetta","raw_affiliation_strings":["Shiraz University of Technology"],"affiliations":[{"raw_affiliation_string":"Shiraz University of Technology","institution_ids":["https://openalex.org/I204490172"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5075022804","display_name":"Francesca Soro","orcid":"https://orcid.org/0000-0001-6738-8634"},"institutions":[{"id":"https://openalex.org/I204490172","display_name":"Shiraz University of Technology","ror":"https://ror.org/04bxa3v83","country_code":"IR","type":"education","lineage":["https://openalex.org/I204490172"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Francesca Soro","raw_affiliation_strings":["Shiraz University of Technology"],"affiliations":[{"raw_affiliation_string":"Shiraz University of Technology","institution_ids":["https://openalex.org/I204490172"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061815649","display_name":"Martino Trevisan","orcid":"https://orcid.org/0000-0002-4258-4679"},"institutions":[{"id":"https://openalex.org/I204490172","display_name":"Shiraz University of Technology","ror":"https://ror.org/04bxa3v83","country_code":"IR","type":"education","lineage":["https://openalex.org/I204490172"]}],"countries":["IR"],"is_corresponding":false,"raw_author_name":"Martino Trevisan","raw_affiliation_strings":["Shiraz University of Technology"],"affiliations":[{"raw_affiliation_string":"Shiraz University of Technology","institution_ids":["https://openalex.org/I204490172"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":6,"corresponding_author_ids":["https://openalex.org/A5019477068"],"corresponding_institution_ids":["https://openalex.org/I177477856"],"apc_list":null,"apc_paid":null,"fwci":0.6761,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.78875121,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":"2018","issue":null,"first_page":"3841","last_page":"3846"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991999864578247,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9991999864578247,"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/T10064","display_name":"Complex Network Analysis Techniques","score":0.9990000128746033,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9954000115394592,"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/computer-science","display_name":"Computer science","score":0.7955799102783203},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7760869264602661},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.7115083932876587},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3428710103034973},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.27553731203079224},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.11804023385047913}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7955799102783203},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7760869264602661},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.7115083932876587},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3428710103034973},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.27553731203079224},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.11804023385047913}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/bigdata.2018.8622005","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2018.8622005","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 Big Data (Big Data)","raw_type":"proceedings-article"},{"id":"pmh:oai:arts.units.it:11368/3025228","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/8622005","pdf_url":null,"source":{"id":"https://openalex.org/S4306400480","display_name":"ArTS Archivio della ricerca di Trieste (University of Trieste https://www.units.it/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142444530","host_organization_name":"University of Trieste","host_organization_lineage":["https://openalex.org/I142444530"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},{"id":"mag:3044269971","is_oa":false,"landing_page_url":"https://jglobal.jst.go.jp/en/detail?JGLOBAL_ID=201902270588193503","pdf_url":null,"source":{"id":"https://openalex.org/S4306512817","display_name":"IEEE Conference Proceedings","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"conference"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":"IEEE Conference Proceedings","raw_type":null}],"best_oa_location":{"id":"pmh:oai:arts.units.it:11368/3025228","is_oa":true,"landing_page_url":"https://ieeexplore.ieee.org/document/8622005","pdf_url":null,"source":{"id":"https://openalex.org/S4306400480","display_name":"ArTS Archivio della ricerca di Trieste (University of Trieste https://www.units.it/)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I142444530","host_organization_name":"University of Trieste","host_organization_lineage":["https://openalex.org/I142444530"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"info:eu-repo/semantics/conferenceObject"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":36,"referenced_works":["https://openalex.org/W151377110","https://openalex.org/W1507388815","https://openalex.org/W1531910981","https://openalex.org/W1647671624","https://openalex.org/W1673310716","https://openalex.org/W1768857938","https://openalex.org/W1775772884","https://openalex.org/W1827212170","https://openalex.org/W1987971958","https://openalex.org/W1990396441","https://openalex.org/W2027966202","https://openalex.org/W2079207448","https://openalex.org/W2088134864","https://openalex.org/W2092799168","https://openalex.org/W2137313854","https://openalex.org/W2160642098","https://openalex.org/W2268474745","https://openalex.org/W2477185808","https://openalex.org/W2484813563","https://openalex.org/W2542550679","https://openalex.org/W2569665589","https://openalex.org/W2570579522","https://openalex.org/W2597306771","https://openalex.org/W2619824656","https://openalex.org/W2775192194","https://openalex.org/W2810669459","https://openalex.org/W2897206998","https://openalex.org/W3144750446","https://openalex.org/W4235539094","https://openalex.org/W6606062967","https://openalex.org/W6630161724","https://openalex.org/W6636915900","https://openalex.org/W6637131181","https://openalex.org/W6638021444","https://openalex.org/W6638623425","https://openalex.org/W6693780431"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2389214306","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W3151146928"],"abstract_inverted_index":{"Clustering":[0],"has":[1],"become":[2,109],"an":[3],"important":[4],"means":[5],"to":[6,42,74,135,142,195],"analyze":[7],"large":[8],"datasets":[9,108],"when":[10,107],"labeled":[11],"data":[12,19,55],"is":[13,172],"not":[14],"available.":[15],"The":[16],"volume":[17],"of":[18,112,121,128,158,169,182,200],"and":[20,78,190,203],"its":[21],"variety":[22],"however":[23],"challenge":[24],"classical":[25],"clustering":[26,45,73,114,184],"algorithms,":[27],"with":[28,176],"density-based":[29,44,113],"ones":[30],"suffering":[31],"from":[32,144],"severe":[33],"scalability":[34,51],"issues.In":[35],"this":[36,150],"paper,":[37],"we":[38,133,152],"propose":[39,134],"a":[40,103,206],"way":[41],"perform":[43],"efficiently":[46],"by":[47,53,64,118],"exploiting":[48],"the":[49,94,119,123,137,145,156,170,180,183,188,191,198,201],"horizontal":[50],"offered":[52],"big":[54],"solution":[56],"such":[57,87],"as":[58,88,100],"Apache":[59,162],"Spark.":[60],"We":[61,81],"are":[62,116],"motivated":[63],"recent":[65],"techniques":[66],"for":[67],"Internet":[68],"monitoring":[69],"that":[70],"rely":[71],"on":[72,84],"group":[75],"similar":[76],"events":[77],"spot":[79],"anomalies.":[80],"focus":[82],"specifically":[83],"textual":[85],"data,":[86],"URLs":[89],"or":[90,164],"server":[91],"logs.":[92],"Computing":[93],"distance":[95,138],"between":[96,125],"points,":[97],"here":[98],"represented":[99],"strings,":[101],"becomes":[102],"major":[104],"issue.":[105],"Indeed,":[106],"large,":[110],"most":[111],"algorithms":[115,171],"bottlenecked":[117],"computation":[120],"all":[122],"distances":[124],"any":[126],"pairs":[127],"elements.":[129],"To":[130],"overcome":[131],"this,":[132],"decouple":[136],"computation,":[139],"easily":[140,154],"amenable":[141],"parallelization,":[143],"algorithm":[146],"execution.":[147],"By":[148],"using":[149],"approach,":[151],"can":[153],"exploit":[155],"benefits":[157],"distributed":[159],"platforms":[160],"like":[161],"Spark":[163],"MapReduce.":[165],"A":[166],"faster":[167],"execution":[168],"thus":[173],"guaranteed,":[174],"together":[175],"more":[177],"flexibility":[178],"in":[179],"choice":[181],"method.We":[185],"make":[186],"both":[187,196],"code":[189],"dataset":[192],"publicly":[193],"available,":[194],"guarantee":[197],"repeatability":[199],"experiments,":[202],"possibly":[204],"offering":[205],"new":[207],"benchmark":[208],"dataset.":[209]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2022,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-04T16:13:02.066488","created_date":"2025-10-10T00:00:00"}