{"id":"https://openalex.org/W2782959932","doi":"https://doi.org/10.1109/bigdata.2017.8258338","title":"Big data machine learning using apache spark MLlib","display_name":"Big data machine learning using apache spark MLlib","publication_year":2017,"publication_date":"2017-12-01","ids":{"openalex":"https://openalex.org/W2782959932","doi":"https://doi.org/10.1109/bigdata.2017.8258338","mag":"2782959932"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2017.8258338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/A5084703739","display_name":"Mehdi Assefi","orcid":null},"institutions":[{"id":"https://openalex.org/I165733156","display_name":"University of Georgia","ror":"https://ror.org/00te3t702","country_code":"US","type":"education","lineage":["https://openalex.org/I165733156"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehdi Assefi","raw_affiliation_strings":["Department of Computer Science, University of Georgia, GA, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Department of Computer Science, University of Georgia, GA, USA","institution_ids":["https://openalex.org/I165733156"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5047873620","display_name":"Ehsun Behravesh","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ehsun Behravesh","raw_affiliation_strings":["IEEE Memebr, Kuala Lumpur, Malaysia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"IEEE Memebr, Kuala Lumpur, Malaysia","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5062122183","display_name":"Guangchi Liu","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Guangchi Liu","raw_affiliation_strings":["Stratifyd Inc., Charlotte, NC, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Stratifyd Inc., Charlotte, NC, USA","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5067918441","display_name":"Ahmad P. Tafti","orcid":"https://orcid.org/0000-0001-9650-2862"},"institutions":[{"id":"https://openalex.org/I1315135799","display_name":"Marshfield Clinic","ror":"https://ror.org/025chrz76","country_code":"US","type":"healthcare","lineage":["https://openalex.org/I1315135799"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ahmad P. Tafti","raw_affiliation_strings":["Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Biomedical Informatics Research Center, Marshfield Clinic Research Institute, WI, USA","institution_ids":["https://openalex.org/I1315135799"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":16.3812,"has_fulltext":false,"cited_by_count":105,"citation_normalized_percentile":{"value":0.99153891,"is_in_top_1_percent":true,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":100},"biblio":{"volume":null,"issue":null,"first_page":"3492","last_page":"3498"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11891","display_name":"Big Data and Business Intelligence","score":0.9987999796867371,"subfield":{"id":"https://openalex.org/subfields/1404","display_name":"Management Information Systems"},"field":{"id":"https://openalex.org/fields/14","display_name":"Business, Management and Accounting"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T12535","display_name":"Machine Learning and Data Classification","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"}},{"id":"https://openalex.org/T12761","display_name":"Data Stream Mining Techniques","score":0.9939000010490417,"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/computer-science","display_name":"Computer science","score":0.8143692016601562},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.8038244247436523},{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7752472162246704},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7657454013824463},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6357797980308533},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.5979924201965332},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.45436882972717285},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.41700229048728943},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.3376061022281647},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.30187249183654785},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.254249632358551}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8143692016601562},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.8038244247436523},{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7752472162246704},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7657454013824463},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6357797980308533},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.5979924201965332},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.45436882972717285},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.41700229048728943},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.3376061022281647},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.30187249183654785},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.254249632358551},{"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/bigdata.2017.8258338","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2017.8258338","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 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/9","score":0.4300000071525574,"display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":66,"referenced_works":["https://openalex.org/W410850256","https://openalex.org/W1763021057","https://openalex.org/W1874755017","https://openalex.org/W1966979133","https://openalex.org/W1985554463","https://openalex.org/W2036260704","https://openalex.org/W2057907879","https://openalex.org/W2074702228","https://openalex.org/W2078945459","https://openalex.org/W2082839002","https://openalex.org/W2089442574","https://openalex.org/W2097048552","https://openalex.org/W2114383418","https://openalex.org/W2120751691","https://openalex.org/W2125621954","https://openalex.org/W2131975293","https://openalex.org/W2140190241","https://openalex.org/W2142680014","https://openalex.org/W2147869723","https://openalex.org/W2157825442","https://openalex.org/W2180882458","https://openalex.org/W2189465200","https://openalex.org/W2256629785","https://openalex.org/W2257086086","https://openalex.org/W2261525379","https://openalex.org/W2284916459","https://openalex.org/W2295758551","https://openalex.org/W2309679942","https://openalex.org/W2313033407","https://openalex.org/W2399287554","https://openalex.org/W2408419917","https://openalex.org/W2414702969","https://openalex.org/W2416893335","https://openalex.org/W2437797956","https://openalex.org/W2480903369","https://openalex.org/W2518382532","https://openalex.org/W2527654716","https://openalex.org/W2533223174","https://openalex.org/W2541639660","https://openalex.org/W2542459869","https://openalex.org/W2546251482","https://openalex.org/W2586618089","https://openalex.org/W2588280690","https://openalex.org/W2592230399","https://openalex.org/W2600277774","https://openalex.org/W2625185938","https://openalex.org/W2727053942","https://openalex.org/W2735364069","https://openalex.org/W2743247826","https://openalex.org/W2761885575","https://openalex.org/W2772514355","https://openalex.org/W2783800533","https://openalex.org/W2955081412","https://openalex.org/W2963288913","https://openalex.org/W3103589224","https://openalex.org/W3189813533","https://openalex.org/W4285719527","https://openalex.org/W4293869929","https://openalex.org/W6614148910","https://openalex.org/W6679815717","https://openalex.org/W6687322159","https://openalex.org/W6714190092","https://openalex.org/W6733172388","https://openalex.org/W6733262946","https://openalex.org/W6765548864","https://openalex.org/W6799332892"],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991","https://openalex.org/W4308507533","https://openalex.org/W2407107767","https://openalex.org/W2901787049","https://openalex.org/W2792181990"],"abstract_inverted_index":{"Artificial":[0],"intelligence,":[1],"and":[2,22,31,47,53,62,71,130,135,161,180,197],"particularly":[3],"machine":[4,42,123,164,173,194],"learning,":[5],"has":[6],"been":[7],"used":[8],"in":[9,92,191],"many":[10],"ways":[11],"by":[12],"the":[13,88,106,144,147,151,178,184],"research":[14,196],"community":[15],"to":[16,36,133,176],"turn":[17],"a":[18,56,93,116],"variety":[19],"of":[20,60,105,118,150,183],"diverse":[21],"even":[23],"heterogeneous":[24],"data":[25,67,79,89,112,193],"sources":[26],"into":[27],"high":[28],"quality":[29],"facts":[30],"knowledge,":[32],"providing":[33],"premier":[34],"capabilities":[35],"accurate":[37],"pattern":[38],"discovery.":[39],"However,":[40],"applying":[41],"learning":[43,124,165,174,195],"strategies":[44],"on":[45],"big":[46,78,111,192],"complex":[48],"datasets":[49],"is":[50,81,103],"computationally":[51],"expensive,":[52],"it":[54],"consumes":[55],"very":[57],"large":[58],"amount":[59,90],"logical":[61],"physical":[63],"resources,":[64],"such":[65],"as":[66,87,156],"file":[68],"space,":[69],"CPU,":[70],"memory.":[72],"A":[73],"sophisticated":[74],"platform":[75,162],"for":[76,110,121,200],"efficient":[77],"analytics":[80],"becoming":[82],"more":[83],"important":[84],"these":[85],"days":[86],"generated":[91],"daily":[94],"basis":[95],"exceeds":[96],"over":[97],"quintillion":[98],"bytes.":[99],"Apache":[100,152],"Spark":[101,153],"MLlib":[102,154],"one":[104],"most":[107],"prominent":[108],"platforms":[109],"analysis":[113],"which":[114],"offers":[115],"set":[117],"excellent":[119],"functionalities":[120],"different":[122],"tasks":[125],"ranging":[126],"from":[127,143],"regression,":[128],"classification,":[129],"dimension":[131],"reduction":[132],"clustering":[134],"rule":[136],"extraction.":[137],"In":[138],"this":[139],"contribution,":[140],"we":[141,168,187],"explore,":[142],"computational":[145],"perspective,":[146],"expanding":[148],"body":[149],"2.0":[155],"an":[157],"open-source,":[158],"distributed,":[159],"scalable,":[160],"independent":[163],"library.":[166],"Specifically,":[167],"perform":[169],"several":[170],"real":[171],"world":[172],"experiments":[175],"examine":[177],"qualitative":[179],"quantitative":[181],"attributes":[182],"platform.":[185],"Furthermore,":[186],"highlight":[188],"current":[189],"trends":[190],"provide":[198],"insights":[199],"future":[201],"work.":[202]},"counts_by_year":[{"year":2026,"cited_by_count":2},{"year":2025,"cited_by_count":10},{"year":2024,"cited_by_count":12},{"year":2023,"cited_by_count":13},{"year":2022,"cited_by_count":11},{"year":2021,"cited_by_count":14},{"year":2020,"cited_by_count":22},{"year":2019,"cited_by_count":12},{"year":2018,"cited_by_count":8},{"year":2016,"cited_by_count":1}],"updated_date":"2026-06-11T09:08:48.828518","created_date":"2025-10-10T00:00:00"}