{"id":"https://openalex.org/W4404570820","doi":"https://doi.org/10.48550/arxiv.2411.11421","title":"Enabling DBSCAN for Very Large-Scale High-Dimensional Spaces","display_name":"Enabling DBSCAN for Very Large-Scale High-Dimensional Spaces","publication_year":2024,"publication_date":"2024-11-18","ids":{"openalex":"https://openalex.org/W4404570820","doi":"https://doi.org/10.48550/arxiv.2411.11421"},"language":"en","primary_location":{"id":"pmh:oai:arXiv.org:2411.11421","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.11421","pdf_url":"https://arxiv.org/pdf/2411.11421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"volume":null,"type":"preprint","indexed_in":["arxiv","datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2411.11421","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5102891100","display_name":"Yongyu Wang","orcid":"https://orcid.org/0000-0003-2483-3114","observed_orcids":["https://orcid.org/0000-0003-2483-3114"]},"institutions":[{"id":"https://openalex.org/I4210103986","display_name":"Jingdong (China)","ror":"https://ror.org/01dkjkq64","country_code":"CN","type":"company","lineage":["https://openalex.org/I4210103986"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Wang, Yongyu","raw_affiliation_strings":["JD Logistics , Beijing 101111 , China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"JD Logistics , Beijing 101111 , China","institution_ids":["https://openalex.org/I4210103986"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5102891100"],"corresponding_institution_ids":["https://openalex.org/I4210103986"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10637","display_name":"Advanced Clustering Algorithms Research","score":0.9926999807357788,"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":0.9926999807357788,"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/T11106","display_name":"Data Management and Algorithms","score":0.003000000026077032,"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/T12535","display_name":"Machine Learning and Data Classification","score":0.0007999999797903001,"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":0.9990000128746033},{"id":"https://openalex.org/keywords/density-based-clustering","display_name":"density-based clustering","score":0.75},{"id":"https://openalex.org/keywords/high-dimensional-data","display_name":"high-dimensional data","score":0.8610000014305115},{"id":"https://openalex.org/keywords/spectral-data-compression","display_name":"spectral data compression","score":0.9110000133514404},{"id":"https://openalex.org/keywords/computational-complexity","display_name":"computational complexity","score":0.5230000019073486},{"id":"https://openalex.org/keywords/outlier-detection","display_name":"outlier detection","score":0.6959999799728394},{"id":"https://openalex.org/keywords/noise-reduction","display_name":"noise reduction","score":0.49000000953674316},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"dimensionality reduction","score":0.6290000081062317},{"id":"https://openalex.org/keywords/large-scale-datasets","display_name":"large-scale datasets","score":0.6190000176429749}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5461796522140503},{"id":"https://openalex.org/C180016635","wikidata":"https://www.wikidata.org/wiki/Q2712821","display_name":"Compression (physics)","level":2,"score":0.5391339063644409},{"id":"https://openalex.org/C156778621","wikidata":"https://www.wikidata.org/wiki/Q1365748","display_name":"Spectrum (functional analysis)","level":2,"score":0.5216489434242249},{"id":"https://openalex.org/C46576248","wikidata":"https://www.wikidata.org/wiki/Q1114630","display_name":"DBSCAN","level":5,"score":0.48923492431640625},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2778348922729492},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.13615688681602478},{"id":"https://openalex.org/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.09669917821884155},{"id":"https://openalex.org/C104047586","wikidata":"https://www.wikidata.org/wiki/Q5033439","display_name":"Canopy clustering algorithm","level":4,"score":0.0},{"id":"https://openalex.org/C94641424","wikidata":"https://www.wikidata.org/wiki/Q5172845","display_name":"Correlation clustering","level":3,"score":0.0},{"id":"https://openalex.org/C62520636","wikidata":"https://www.wikidata.org/wiki/Q944","display_name":"Quantum mechanics","level":1,"score":0.0},{"id":"https://openalex.org/C97355855","wikidata":"https://www.wikidata.org/wiki/Q11473","display_name":"Thermodynamics","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"pmh:oai:arXiv.org:2411.11421","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.11421","pdf_url":"https://arxiv.org/pdf/2411.11421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},{"id":"doi:10.48550/arxiv.2411.11421","doi":"https://doi.org/10.48550/arxiv.2411.11421","is_oa":true,"landing_page_url":"https://doi.org/10.48550/arxiv.2411.11421","pdf_url":null,"source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"Preprint"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:2411.11421","doi":null,"is_oa":true,"landing_page_url":"http://arxiv.org/abs/2411.11421","pdf_url":"https://arxiv.org/pdf/2411.11421","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":"2331-8422","issn":["2331-8422"],"is_oa":true,"is_in_doaj":false,"is_core":false,"listed_in":[],"host_organization":"https://openalex.org/I205783295","host_organization_name":"Cornell University","host_organization_lineage":["https://openalex.org/I205783295"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"text"},"sustainable_development_goals":[],"sustainable_development_goals_aurora":[],"study_designs":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4404570820.pdf","grobid_xml":"https://content.openalex.org/works/W4404570820.grobid-xml"},"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4391375266","https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W3163639875","https://openalex.org/W2364999035","https://openalex.org/W4226497289","https://openalex.org/W2966681114","https://openalex.org/W4386078164","https://openalex.org/W2553918434","https://openalex.org/W2369356834"],"abstract_inverted_index":{"DBSCAN":[0,14,46,74,91,140],"is":[1,48,53,141],"one":[2],"of":[3,44,56,67,99,107,139],"the":[4,38,41,45,54,65,68,118,124,136],"most":[5,119],"important":[6],"non-parametric":[7],"unsupervised":[8],"data":[9,27,57,69,96,108],"analysis":[10],"tools.":[11],"By":[12,115],"applying":[13],"to":[15],"a":[16,72,90,104],"dataset,":[17],"two":[18],"key":[19],"analytical":[20],"results":[21],"can":[22],"be":[23],"obtained:":[24],"(1)":[25],"clustering":[26],"points":[28,58,109],"based":[29,93],"on":[30,94],"density":[31],"distribution":[32],"and":[33,59,81,111,133,147],"(2)":[34],"identifying":[35],"outliers":[36],"in":[37],"dataset.":[39],"However,":[40],"time":[42],"complexity":[43],"algorithm":[47],"$O(n^2":[49],"\u03b2)$,":[50],"where":[51],"$n$":[52,80],"number":[55,106],"$\u03b2=":[60],"O(D)$,":[61],"with":[62,103],"$D$":[63,82],"representing":[64],"dimensionality":[66,113],"space.":[70],"As":[71],"result,":[73],"becomes":[75],"computationally":[76],"infeasible":[77],"when":[78],"both":[79],"are":[83],"large.":[84],"In":[85],"this":[86],"paper,":[87],"we":[88],"propose":[89],"method":[92,128],"spectral":[95],"compression,":[97],"capable":[98],"efficiently":[100],"processing":[101],"datasets":[102],"large":[105],"($n$)":[110],"high":[112],"($D$).":[114],"preserving":[116],"only":[117],"critical":[120],"structural":[121],"information":[122],"during":[123],"compression":[125],"process,":[126],"our":[127],"effectively":[129],"removes":[130],"substantial":[131],"redundancy":[132],"noise.":[134],"Consequently,":[135],"solution":[137],"quality":[138],"significantly":[142],"improved,":[143],"enabling":[144],"more":[145],"accurate":[146],"reliable":[148],"results.":[149]},"counts_by_year":[],"updated_date":"2026-09-30T09:27:27.532063","created_date":"2024-11-21T00:00:00"}