{"id":"https://openalex.org/W3139252201","doi":"https://doi.org/10.1109/bigdata50022.2020.9378399","title":"Extending the R Language with a Scalable Matrix Summarization Operator","display_name":"Extending the R Language with a Scalable Matrix Summarization Operator","publication_year":2020,"publication_date":"2020-12-10","ids":{"openalex":"https://openalex.org/W3139252201","doi":"https://doi.org/10.1109/bigdata50022.2020.9378399","mag":"3139252201"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata50022.2020.9378399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big 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/A5019842397","display_name":"Sikder Tahsin Al-Amin","orcid":null},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Sikder Tahsin Al-Amin","raw_affiliation_strings":["Department of Computer Science, University of Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5060389201","display_name":"Siva Uday Sampreeth Chebolu","orcid":"https://orcid.org/0000-0001-6206-0760"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Siva Uday Sampreeth Chebolu","raw_affiliation_strings":["Department of Computer Science, University of Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5031610238","display_name":"Carlos Ordo\u0144\u1ebdz","orcid":"https://orcid.org/0009-0005-1135-9726"},"institutions":[{"id":"https://openalex.org/I44461941","display_name":"University of Houston","ror":"https://ror.org/048sx0r50","country_code":"US","type":"education","lineage":["https://openalex.org/I44461941"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Carlos Ordonez","raw_affiliation_strings":["Department of Computer Science, University of Houston, TX, USA"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Houston, TX, USA","institution_ids":["https://openalex.org/I44461941"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5019842397"],"corresponding_institution_ids":["https://openalex.org/I44461941"],"apc_list":null,"apc_paid":null,"fwci":0.8007,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.82098024,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":96,"max":97},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9882000088691711,"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/T13398","display_name":"Data Analysis with R","score":0.9706000089645386,"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/automatic-summarization","display_name":"Automatic summarization","score":0.8102536201477051},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6846596598625183},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5433484315872192},{"id":"https://openalex.org/keywords/operator","display_name":"Operator (biology)","score":0.5274878740310669},{"id":"https://openalex.org/keywords/matrix","display_name":"Matrix (chemical analysis)","score":0.4234147369861603},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.37508460879325867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3403620719909668},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.10189256072044373},{"id":"https://openalex.org/keywords/materials-science","display_name":"Materials science","score":0.05954679846763611}],"concepts":[{"id":"https://openalex.org/C170858558","wikidata":"https://www.wikidata.org/wiki/Q1394144","display_name":"Automatic summarization","level":2,"score":0.8102536201477051},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6846596598625183},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5433484315872192},{"id":"https://openalex.org/C17020691","wikidata":"https://www.wikidata.org/wiki/Q139677","display_name":"Operator (biology)","level":5,"score":0.5274878740310669},{"id":"https://openalex.org/C106487976","wikidata":"https://www.wikidata.org/wiki/Q685816","display_name":"Matrix (chemical analysis)","level":2,"score":0.4234147369861603},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.37508460879325867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3403620719909668},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.10189256072044373},{"id":"https://openalex.org/C192562407","wikidata":"https://www.wikidata.org/wiki/Q228736","display_name":"Materials science","level":0,"score":0.05954679846763611},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C158448853","wikidata":"https://www.wikidata.org/wiki/Q425218","display_name":"Repressor","level":4,"score":0.0},{"id":"https://openalex.org/C86339819","wikidata":"https://www.wikidata.org/wiki/Q407384","display_name":"Transcription factor","level":3,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C159985019","wikidata":"https://www.wikidata.org/wiki/Q181790","display_name":"Composite material","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/bigdata50022.2020.9378399","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata50022.2020.9378399","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2020 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.4099999964237213,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W585085135","https://openalex.org/W2013373704","https://openalex.org/W2030638006","https://openalex.org/W2044490410","https://openalex.org/W2050213988","https://openalex.org/W2088083083","https://openalex.org/W2089442574","https://openalex.org/W2119738171","https://openalex.org/W2246319860","https://openalex.org/W2317943859","https://openalex.org/W2584070953","https://openalex.org/W2807483599","https://openalex.org/W2911419447","https://openalex.org/W2963534552","https://openalex.org/W2967826790","https://openalex.org/W3006804578","https://openalex.org/W3006889321","https://openalex.org/W3084904702"],"related_works":["https://openalex.org/W2366403280","https://openalex.org/W1495108544","https://openalex.org/W2091301346","https://openalex.org/W3148229873","https://openalex.org/W2150160875","https://openalex.org/W4242223894","https://openalex.org/W1517524280","https://openalex.org/W4323520239","https://openalex.org/W4389760904","https://openalex.org/W4306886878"],"abstract_inverted_index":{"Analysts":[0],"prefer":[1],"simpler":[2],"interpreted":[3],"languages":[4,10],"to":[5,22,41,177],"program":[6],"their":[7],"computations.":[8,45],"Prominent":[9],"include":[11],"R,":[12],"Python,":[13],"and":[14,82,124,135],"Matlab.":[15],"On":[16],"the":[17,63,102,109,146,151,178,208,227],"other":[18],"hand,":[19],"analysts":[20],"aim":[21],"compute":[23],"mathematical":[24],"models":[25],"as":[26,28],"fast":[27],"possible,":[29],"especially":[30],"with":[31,193],"large":[32,73],"data":[33,204,229],"sets.":[34],"Data":[35],"summarization":[36,54,70,92,152],"remains":[37],"a":[38,52,58,72,87,128],"fundamental":[39],"technique":[40],"accelerate":[42],"machine":[43],"learning":[44],"Based":[46],"on":[47,168],"this":[48],"motivation,":[49],"we":[50,188,201,222],"propose":[51],"novel":[53],"mechanism":[55],"computed":[56],"via":[57],"single":[59],"matrix":[60,96,112,130],"multiplication":[61,113,131],"in":[62,98,195,207,218,226],"statistical":[64],"R":[65,104,111,123,179],"language.":[66],"We":[67,85,100,154],"show":[68],"our":[69,140,160,186,191,199],"benefits":[71],"family":[74],"of":[75,150],"linear":[76],"models,":[77],"including":[78],"Linear":[79],"Regression,":[80],"PCA,":[81],"Naive":[83],"Bayes.":[84],"present":[86,155],"subsystem":[88,161,192],"that":[89,203],"enables":[90],"exploiting":[91],"by":[93,107],"detecting":[94],"Gramian":[95],"products":[97],"R.":[99],"optimize":[101],"existing":[103],"source":[105,169],"code":[106,170],"overriding":[108],"internal":[110],"algorithm":[114],"using":[115],"ours.":[116],"Our":[117,214],"solution":[118,141,215],"can":[119,142,205,223],"be":[120,143,206],"plugged":[121],"into":[122],"help":[125],"solving":[126],"where":[127],"similar":[129],"appears,":[132],"much":[133,173],"faster":[134,174],"without":[136],"RAM":[137],"limitations.":[138],"Moreover,":[139],"benefited":[144],"from":[145],"parallel":[147,196],"processing":[148],"ability":[149],"matrix.":[153],"an":[156],"experimental":[157],"validation":[158],"showing":[159],"incurs":[162],"little":[163],"overhead":[164],"since":[165],"it":[166],"works":[167],"while":[171],"providing":[172],"speeds":[175],"compared":[176],"language":[180],"built-in":[181],"functions.":[182],"To":[183],"round":[184],"up":[185],"comparisons,":[187],"also":[189,224],"compare":[190],"Spark":[194,217],"machines.":[197],"For":[198],"solution,":[200],"assume":[202],"HDFS,":[209],"disk,":[210],"or":[211],"already":[212],"partitioned.":[213],"triumphs":[216],"most":[219],"cases":[220],"proving":[221],"compete":[225],"big":[228],"space.":[230]},"counts_by_year":[{"year":2022,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}