{"id":"https://openalex.org/W2773612851","doi":"https://doi.org/10.1109/tii.2019.2912723","title":"Random Sample Partition: A Distributed Data Model for Big Data Analysis","display_name":"Random Sample Partition: A Distributed Data Model for Big Data Analysis","publication_year":2019,"publication_date":"2019-05-07","ids":{"openalex":"https://openalex.org/W2773612851","doi":"https://doi.org/10.1109/tii.2019.2912723","mag":"2773612851"},"language":"en","primary_location":{"id":"doi:10.1109/tii.2019.2912723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2019.2912723","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/1712.04146","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5064798504","display_name":"Salman Salloum","orcid":"https://orcid.org/0000-0002-6750-003X"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Salman Salloum","raw_affiliation_strings":["Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6750-003X","affiliations":[{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5003347359","display_name":"Joshua Zhexue Huang","orcid":"https://orcid.org/0000-0002-6797-2571"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Joshua Zhexue Huang","raw_affiliation_strings":["Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"raw_orcid":"https://orcid.org/0000-0002-6797-2571","affiliations":[{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5076542236","display_name":"Yulin He","orcid":"https://orcid.org/0000-0002-3415-0686"},"institutions":[{"id":"https://openalex.org/I180726961","display_name":"Shenzhen University","ror":"https://ror.org/01vy4gh70","country_code":"CN","type":"education","lineage":["https://openalex.org/I180726961"]},{"id":"https://openalex.org/I4210099586","display_name":"Shenzhen Research Institute of Big Data","ror":"https://ror.org/00z1gwf89","country_code":"CN","type":"education","lineage":["https://openalex.org/I4210099586"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yulin He","raw_affiliation_strings":["Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Big Data Institute, College of Computer Science and Software Engineering, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961","https://openalex.org/I4210099586"]},{"raw_affiliation_string":"National Engineering Laboratory for Big Data System Computing Technology, Shenzhen University, Shenzhen, China","institution_ids":["https://openalex.org/I180726961"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":13.4657,"has_fulltext":false,"cited_by_count":111,"citation_normalized_percentile":{"value":0.99121045,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":"15","issue":"11","first_page":"5846","last_page":"5854"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9975000023841858,"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"}},"topics":[{"id":"https://openalex.org/T10054","display_name":"Parallel Computing and Optimization Techniques","score":0.9975000023841858,"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"}},{"id":"https://openalex.org/T11181","display_name":"Advanced Data Storage Technologies","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"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/T12292","display_name":"Graph Theory and Algorithms","score":0.9950000047683716,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6030299663543701},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6016831398010254},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.5399622321128845},{"id":"https://openalex.org/keywords/sample","display_name":"Sample (material)","score":0.5101611614227295},{"id":"https://openalex.org/keywords/partition","display_name":"Partition (number theory)","score":0.45398467779159546},{"id":"https://openalex.org/keywords/distributed-database","display_name":"Distributed database","score":0.4160851538181305},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3771926760673523},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.19852551817893982},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.16574984788894653},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.15473201870918274}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6030299663543701},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6016831398010254},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.5399622321128845},{"id":"https://openalex.org/C198531522","wikidata":"https://www.wikidata.org/wiki/Q485146","display_name":"Sample (material)","level":2,"score":0.5101611614227295},{"id":"https://openalex.org/C42812","wikidata":"https://www.wikidata.org/wiki/Q1082910","display_name":"Partition (number theory)","level":2,"score":0.45398467779159546},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.4160851538181305},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3771926760673523},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.19852551817893982},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.16574984788894653},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.15473201870918274},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C43617362","wikidata":"https://www.wikidata.org/wiki/Q170050","display_name":"Chromatography","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":2,"locations":[{"id":"doi:10.1109/tii.2019.2912723","is_oa":false,"landing_page_url":"https://doi.org/10.1109/tii.2019.2912723","pdf_url":null,"source":{"id":"https://openalex.org/S184777250","display_name":"IEEE Transactions on Industrial Informatics","issn_l":"1551-3203","issn":["1551-3203","1941-0050"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319808","host_organization_name":"Institute of Electrical and Electronics Engineers","host_organization_lineage":["https://openalex.org/P4310319808"],"host_organization_lineage_names":["Institute of Electrical and Electronics Engineers"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"IEEE Transactions on Industrial Informatics","raw_type":"journal-article"},{"id":"pmh:oai:arXiv.org:1712.04146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.04146","pdf_url":"https://arxiv.org/pdf/1712.04146","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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"}],"best_oa_location":{"id":"pmh:oai:arXiv.org:1712.04146","is_oa":true,"landing_page_url":"http://arxiv.org/abs/1712.04146","pdf_url":"https://arxiv.org/pdf/1712.04146","source":{"id":"https://openalex.org/S4306400194","display_name":"arXiv (Cornell University)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"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":[],"awards":[{"id":"https://openalex.org/G5485717919","display_name":null,"funder_award_id":"61473194","funder_id":"https://openalex.org/F4320321001","funder_display_name":"National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320321001","display_name":"National Natural Science Foundation of China","ror":"https://ror.org/01h0zpd94"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":38,"referenced_works":["https://openalex.org/W845171161","https://openalex.org/W1164259208","https://openalex.org/W1547205936","https://openalex.org/W1975184797","https://openalex.org/W1995945562","https://openalex.org/W2002791618","https://openalex.org/W2036816792","https://openalex.org/W2051685933","https://openalex.org/W2071989194","https://openalex.org/W2084071276","https://openalex.org/W2119125655","https://openalex.org/W2119738171","https://openalex.org/W2126623642","https://openalex.org/W2131975293","https://openalex.org/W2146774335","https://openalex.org/W2150915951","https://openalex.org/W2151065878","https://openalex.org/W2155806188","https://openalex.org/W2173213060","https://openalex.org/W2212660284","https://openalex.org/W2265166184","https://openalex.org/W2339488751","https://openalex.org/W2429510775","https://openalex.org/W2530314904","https://openalex.org/W2542459869","https://openalex.org/W2559572207","https://openalex.org/W2563173212","https://openalex.org/W2572060670","https://openalex.org/W2607929867","https://openalex.org/W2766944931","https://openalex.org/W2788617251","https://openalex.org/W2794386528","https://openalex.org/W2808726866","https://openalex.org/W2949432502","https://openalex.org/W6632659161","https://openalex.org/W6677623120","https://openalex.org/W6679815717","https://openalex.org/W6730369149"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4247566972","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W4206777497","https://openalex.org/W4281381431","https://openalex.org/W2153883657","https://openalex.org/W1977025641"],"abstract_inverted_index":{"With":[0],"the":[1,28,41,76,87,91,99,105,108,135,141,149],"ever-increasing":[2],"volume":[3],"of":[4,27,58,75,90,107,144,151],"data,":[5],"alternative":[6],"strategies":[7],"are":[8],"required":[9],"to":[10,49,73,85,131],"divide":[11],"big":[12,33,52,114,124,145],"data":[13,17,30,34,47,53,60,78,92,101,115,125,146,152],"into":[14],"statistically":[15],"consistent":[16],"blocks":[18,81],"that":[19,74],"can":[20,82,128],"be":[21,83,129],"used":[22,84],"directly":[23],"as":[24,55],"representative":[25],"samples":[26],"entire":[29,77,100],"set":[31,54,57],"in":[32,134],"analysis.":[35],"In":[36],"this":[37],"paper,":[38],"we":[39],"propose":[40],"Random":[42],"Sample":[43],"Partition":[44],"(RSP)":[45],"distributed":[46],"model":[48,110],"represent":[50],"a":[51,56,69,118],"disjoint":[59],"blocks,":[61],"called":[62],"RSP":[63,66,80,109],"blocks.":[64],"Each":[65],"block":[67],"has":[68],"probability":[70],"distribution":[71],"similar":[72],"set.":[79,102],"estimate":[86],"statistical":[88],"properties":[89],"and":[93,116,147],"build":[94],"predictive":[95],"models":[96],"without":[97],"computing":[98],"We":[103],"demonstrate":[104],"implications":[106],"on":[111],"sampling":[112],"from":[113],"introduce":[117],"new":[119],"RSP-based":[120],"method":[121,138],"for":[122],"approximate":[123],"analysis":[126],"which":[127],"applied":[130],"different":[132],"scenarios":[133],"industry.":[136],"This":[137],"significantly":[139],"reduces":[140],"computational":[142],"burden":[143],"increases":[148],"productivity":[150],"scientists.":[153]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":12},{"year":2024,"cited_by_count":17},{"year":2023,"cited_by_count":27},{"year":2022,"cited_by_count":22},{"year":2021,"cited_by_count":16},{"year":2020,"cited_by_count":9},{"year":2019,"cited_by_count":5},{"year":2018,"cited_by_count":1}],"updated_date":"2026-07-22T07:51:19.307946","created_date":"2017-12-22T00:00:00"}