{"id":"https://openalex.org/W2799132955","doi":"https://doi.org/10.1145/3183713.3196887","title":"RP-DBSCAN","display_name":"RP-DBSCAN","publication_year":2018,"publication_date":"2018-05-25","ids":{"openalex":"https://openalex.org/W2799132955","doi":"https://doi.org/10.1145/3183713.3196887","mag":"2799132955"},"language":"en","primary_location":{"id":"doi:10.1145/3183713.3196887","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3196887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","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/A5033909285","display_name":"Hwanjun Song","orcid":"https://orcid.org/0000-0002-1105-0818"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Hwanjun Song","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101805827","display_name":"Jae-Gil Lee","orcid":"https://orcid.org/0000-0002-8711-7732"},"institutions":[{"id":"https://openalex.org/I157485424","display_name":"Korea Advanced Institute of Science and Technology","ror":"https://ror.org/05apxxy63","country_code":"KR","type":"education","lineage":["https://openalex.org/I157485424"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Jae-Gil Lee","raw_affiliation_strings":["Korea Advanced Institute of Science and Technology, Daejeon, South Korea"],"affiliations":[{"raw_affiliation_string":"Korea Advanced Institute of Science and Technology, Daejeon, South Korea","institution_ids":["https://openalex.org/I157485424"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5033909285"],"corresponding_institution_ids":["https://openalex.org/I157485424"],"apc_list":null,"apc_paid":null,"fwci":5.8638,"has_fulltext":false,"cited_by_count":57,"citation_normalized_percentile":{"value":0.96853589,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":91,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1173","last_page":"1187"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11269","display_name":"Algorithms and Data Compression","score":0.9976999759674072,"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":0.9976999759674072,"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/T10627","display_name":"Advanced Image and Video Retrieval Techniques","score":0.9972000122070312,"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/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9929999709129333,"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":0.8816611170768738},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7557269334793091},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6251670718193054},{"id":"https://openalex.org/keywords/data-set","display_name":"Data set","score":0.5419460535049438},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.5153833627700806},{"id":"https://openalex.org/keywords/skewness","display_name":"Skewness","score":0.4824000597000122},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4327143132686615},{"id":"https://openalex.org/keywords/data-point","display_name":"Data point","score":0.4201362431049347},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.4200916290283203},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4047337472438812},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.21860811114311218},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.18767189979553223},{"id":"https://openalex.org/keywords/cure-data-clustering-algorithm","display_name":"CURE data clustering algorithm","score":0.1348665952682495},{"id":"https://openalex.org/keywords/correlation-clustering","display_name":"Correlation clustering","score":0.12833914160728455},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.09276503324508667}],"concepts":[{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.8816611170768738},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7557269334793091},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6251670718193054},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.5419460535049438},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.5153833627700806},{"id":"https://openalex.org/C122342681","wikidata":"https://www.wikidata.org/wiki/Q330828","display_name":"Skewness","level":2,"score":0.4824000597000122},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4327143132686615},{"id":"https://openalex.org/C21080849","wikidata":"https://www.wikidata.org/wiki/Q13611879","display_name":"Data point","level":2,"score":0.4201362431049347},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.4200916290283203},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4047337472438812},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.21860811114311218},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.18767189979553223},{"id":"https://openalex.org/C33704608","wikidata":"https://www.wikidata.org/wiki/Q5014717","display_name":"CURE data clustering algorithm","level":4,"score":0.1348665952682495},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.12833914160728455},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.09276503324508667},{"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/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3183713.3196887","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3183713.3196887","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2018 International Conference on Management of Data","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":38,"referenced_works":["https://openalex.org/W1126014701","https://openalex.org/W1484676273","https://openalex.org/W1489273657","https://openalex.org/W1496357020","https://openalex.org/W1507375662","https://openalex.org/W1527859964","https://openalex.org/W1547566968","https://openalex.org/W1768857938","https://openalex.org/W1989750313","https://openalex.org/W1991043239","https://openalex.org/W1992181154","https://openalex.org/W2008286666","https://openalex.org/W2030780826","https://openalex.org/W2033403400","https://openalex.org/W2048968215","https://openalex.org/W2054779505","https://openalex.org/W2080098453","https://openalex.org/W2092799168","https://openalex.org/W2109275473","https://openalex.org/W2111516947","https://openalex.org/W2116762767","https://openalex.org/W2119885577","https://openalex.org/W2122465391","https://openalex.org/W2134813265","https://openalex.org/W2141585940","https://openalex.org/W2143394441","https://openalex.org/W2160642098","https://openalex.org/W2293942356","https://openalex.org/W2380172038","https://openalex.org/W2477185808","https://openalex.org/W2542550679","https://openalex.org/W2562836854","https://openalex.org/W2570579522","https://openalex.org/W2600969903","https://openalex.org/W2613529642","https://openalex.org/W2744226525","https://openalex.org/W3105265400","https://openalex.org/W4247105055"],"related_works":["https://openalex.org/W2189529952","https://openalex.org/W3163639875","https://openalex.org/W2541415914","https://openalex.org/W3174008170","https://openalex.org/W4206465196","https://openalex.org/W4205730852","https://openalex.org/W2884473227","https://openalex.org/W3092265805","https://openalex.org/W4206278474","https://openalex.org/W2745792676"],"abstract_inverted_index":{"In":[0,89,188],"most":[1],"parallel":[2,15,121],"DBSCAN":[3,122],"algorithms,":[4],"neighboring":[5],"points":[6,70],"are":[7,195],"assigned":[8],"to":[9,17,112,146,156,225],"the":[10,21,24,69,83,100,143,162,212,220],"same":[11],"data":[12,27,39,45,55,79,84,102,148,179,190],"partition":[13,149],"for":[14,87],"processing":[16],"facilitate":[18],"calculation":[19],"of":[20,23,78,99,164],"density":[22],"neighbors.":[25],"This":[26],"partitioning":[28,56,60,132,191],"scheme":[29],"causes":[30],"a":[31,43,53,95,107,119,135,208],"few":[32],"critical":[33],"problems":[34],"including":[35],"load":[36,75],"imbalance":[37],"between":[38],"partitions,":[40],"especially":[41],"in":[42],"skewed":[44],"set.":[46],"To":[47,160],"remedy":[48],"these":[49,153],"problems,":[50],"we":[51,91,105,117,167],"propose":[52],"cell-based":[54],"scheme,":[57],"pseudo":[58,130],"random":[59,114,131],",":[61,111],"that":[62,128,216],"randomly":[63],"distributes":[64],"small":[65],"cells":[66],"rather":[67],"than":[68],"themselves.":[71],"It":[72],"achieves":[73],"high":[74],"balance":[76],"regardless":[77],"skewness":[80],"while":[81],"retaining":[82],"contiguity":[85],"required":[86],"DBSCAN.":[88],"addition,":[90],"build":[92],"and":[93,150,172,192,198],"broadcast":[94],"highly":[96],"compact":[97],"summary":[98],"entire":[101],"set,":[103],"which":[104],"call":[106],"two-level":[108,136],"cell":[109,137],"dictionary":[110],"supplement":[113],"partitions.":[115],"Then,":[116],"develop":[118],"novel":[120],"algorithm,":[123],"Random":[124],"Partitioning-DBSCAN":[125],"(shortly,":[126],"RP-DBSCAN),":[127],"uses":[129],"together":[133],"with":[134],"dictionary.":[138],"The":[139],"algorithm":[140],"simultaneously":[141],"finds":[142],"local":[144,154],"clusters":[145,155],"each":[147,201],"then":[151],"merges":[152],"obtain":[157],"global":[158],"clustering.":[159],"validate":[161],"merit":[163],"our":[165],"approach,":[166],"implement":[168],"RP-DBSCAN":[169,217],"on":[170,181,200],"Spark":[171],"conduct":[173],"extensive":[174],"experiments":[175],"using":[176],"various":[177],"real-world":[178],"sets":[180],"12":[182],"Microsoft":[183],"Azure":[184],"machines":[185],"(48":[186],"cores).":[187],"RP-DBSCAN,":[189],"cluster":[193],"merging":[194],"very":[196],"light,":[197],"clustering":[199],"split":[202],"is":[203],"not":[204],"dragged":[205],"out":[206],"by":[207,223],"specific":[209],"worker.":[210],"Therefore,":[211],"performance":[213],"results":[214],"show":[215],"significantly":[218],"outperforms":[219],"state-of-the-art":[221],"algorithms":[222],"up":[224],"180":[226],"times.":[227]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":4},{"year":2023,"cited_by_count":7},{"year":2022,"cited_by_count":10},{"year":2021,"cited_by_count":12},{"year":2020,"cited_by_count":13},{"year":2019,"cited_by_count":10}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2018-05-07T00:00:00"}