{"id":"https://openalex.org/W1768857938","doi":"https://doi.org/10.1109/hpcsim.2015.7237086","title":"DBSCAN on Resilient Distributed Datasets","display_name":"DBSCAN on Resilient Distributed Datasets","publication_year":2015,"publication_date":"2015-07-01","ids":{"openalex":"https://openalex.org/W1768857938","doi":"https://doi.org/10.1109/hpcsim.2015.7237086","mag":"1768857938"},"language":"en","primary_location":{"id":"doi:10.1109/hpcsim.2015.7237086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2015.7237086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on High Performance Computing & Simulation (HPCS)","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/A5074278702","display_name":"Irving Cordova","orcid":null},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Irving Cordova","raw_affiliation_strings":["Department of Computer Science, San Jos\u00e9 State University, San Jos\u00e9, California, U.S.A","Department of Computer Science, San Jos\u00e9 State University, California, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, San Jos\u00e9 State University, San Jos\u00e9, California, U.S.A","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"Department of Computer Science, San Jos\u00e9 State University, California, U.S.A","institution_ids":["https://openalex.org/I51504820"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5019298277","display_name":"Teng-Sheng Moh","orcid":"https://orcid.org/0000-0002-2726-102X"},"institutions":[{"id":"https://openalex.org/I51504820","display_name":"San Jose State University","ror":"https://ror.org/04qyvz380","country_code":"US","type":"education","lineage":["https://openalex.org/I51504820"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Teng-Sheng Moh","raw_affiliation_strings":["Department of Computer Science, San Jos\u00e9 State University, San Jos\u00e9, California, U.S.A","Department of Computer Science, San Jos\u00e9 State University, California, U.S.A"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, San Jos\u00e9 State University, San Jos\u00e9, California, U.S.A","institution_ids":["https://openalex.org/I51504820"]},{"raw_affiliation_string":"Department of Computer Science, San Jos\u00e9 State University, California, U.S.A","institution_ids":["https://openalex.org/I51504820"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I51504820"],"apc_list":null,"apc_paid":null,"fwci":3.3992,"has_fulltext":false,"cited_by_count":49,"citation_normalized_percentile":{"value":0.94491581,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"531","last_page":"540"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11106","display_name":"Data Management and Algorithms","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T11106","display_name":"Data Management and Algorithms","score":0.9980999827384949,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9976000189781189,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.995199978351593,"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/dbscan","display_name":"DBSCAN","score":0.9324750900268555},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8312058448791504},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.7313638925552368},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.5761228203773499},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.569640576839447},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5210732221603394},{"id":"https://openalex.org/keywords/computation","display_name":"Computation","score":0.4582899808883667},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2824603319168091},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.1847844421863556},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.09465700387954712},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.08490493893623352},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.07460552453994751}],"concepts":[{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.9324750900268555},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8312058448791504},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.7313638925552368},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.5761228203773499},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.569640576839447},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5210732221603394},{"id":"https://openalex.org/C45374587","wikidata":"https://www.wikidata.org/wiki/Q12525525","display_name":"Computation","level":2,"score":0.4582899808883667},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2824603319168091},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.1847844421863556},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.09465700387954712},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.08490493893623352},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.07460552453994751},{"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:10.1109/hpcsim.2015.7237086","is_oa":false,"landing_page_url":"https://doi.org/10.1109/hpcsim.2015.7237086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2015 International Conference on High Performance Computing & Simulation (HPCS)","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":19,"referenced_works":["https://openalex.org/W1484676273","https://openalex.org/W1673310716","https://openalex.org/W2008286666","https://openalex.org/W2028562168","https://openalex.org/W2044936152","https://openalex.org/W2048968215","https://openalex.org/W2061051181","https://openalex.org/W2065306205","https://openalex.org/W2101234009","https://openalex.org/W2109275473","https://openalex.org/W2111516947","https://openalex.org/W2131975293","https://openalex.org/W2173213060","https://openalex.org/W3150257885","https://openalex.org/W4245665133","https://openalex.org/W4300068876","https://openalex.org/W6637131181","https://openalex.org/W6675354045","https://openalex.org/W6679815717"],"related_works":["https://openalex.org/W2807508722","https://openalex.org/W3176449234","https://openalex.org/W2353158678","https://openalex.org/W2767235736","https://openalex.org/W4225278791","https://openalex.org/W2045002201","https://openalex.org/W2971352445","https://openalex.org/W4322502698","https://openalex.org/W4308507533","https://openalex.org/W2407107767"],"abstract_inverted_index":{"DBSCAN":[0,25,70,86],"is":[1,9,26],"a":[2,49,65,91],"well-known":[3],"density-based":[4],"data":[5,38,60],"clustering":[6],"algorithm":[7,67,87],"that":[8],"widely":[10],"used":[11],"due":[12],"to":[13,16,28],"its":[14,32],"ability":[15],"find":[17],"arbitrarily":[18],"shaped":[19],"clusters":[20],"in":[21,90],"noisy":[22],"data.":[23],"However,":[24],"hard":[27],"scale":[29],"which":[30],"limits":[31],"utility":[33],"when":[34],"working":[35],"with":[36],"large":[37,59],"sets.":[39,61],"Resilient":[40,73],"Distributed":[41,74],"Datasets":[42,75],"(RDDs),":[43],"on":[44,69],"the":[45,72,80,84,106],"other":[46],"hand,":[47],"are":[48],"fast":[50],"data-processing":[51],"abstraction":[52],"created":[53],"explicitly":[54],"for":[55],"in-memory":[56],"computation":[57],"of":[58,83,101],"This":[62],"paper":[63,96],"presents":[64],"new":[66],"based":[68],"using":[71,103],"approach:":[76],"RDD-DBSCAN.":[77],"RDD-DBSCAN":[78,102],"overcomes":[79],"scalability":[81],"limitations":[82],"traditional":[85],"by":[88],"operating":[89],"fully":[92],"distributed":[93],"fashion.":[94],"The":[95],"also":[97],"evaluates":[98],"an":[99],"implementation":[100],"Apache":[104],"Spark,":[105],"official":[107],"RDD":[108],"implementation.":[109]},"counts_by_year":[{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":5},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":4},{"year":2020,"cited_by_count":8},{"year":2019,"cited_by_count":10},{"year":2018,"cited_by_count":8},{"year":2017,"cited_by_count":3},{"year":2016,"cited_by_count":3}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}