{"id":"https://openalex.org/W2583618789","doi":"https://doi.org/10.1109/bigdata.2016.7840859","title":"Building a research data science platform from industrial machines","display_name":"Building a research data science platform from industrial machines","publication_year":2016,"publication_date":"2016-12-01","ids":{"openalex":"https://openalex.org/W2583618789","doi":"https://doi.org/10.1109/bigdata.2016.7840859","mag":"2583618789"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata.2016.7840859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"},"type":"conference-paper","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/A5100453054","display_name":"Fang Liu","orcid":"https://orcid.org/0000-0002-3383-2191"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fang Cherry Liu","raw_affiliation_strings":["Partnership for An Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, Georgia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Partnership for An Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5037207405","display_name":"Fu Shen","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Fu Shen","raw_affiliation_strings":["School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5020153026","display_name":"Duen Horng Chau","orcid":"https://orcid.org/0000-0001-9824-3323"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Duen Horng Chau","raw_affiliation_strings":["School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"School of Computational Science and Engineering, Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5065154117","display_name":"Neil Bright","orcid":null},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Neil Bright","raw_affiliation_strings":["Partnership for An Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, Georgia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Partnership for An Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078584378","display_name":"Mehmet Belgin","orcid":"https://orcid.org/0000-0001-8613-3485"},"institutions":[{"id":"https://openalex.org/I130701444","display_name":"Georgia Institute of Technology","ror":"https://ror.org/01zkghx44","country_code":"US","type":"education","lineage":["https://openalex.org/I130701444"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mehmet Belgin","raw_affiliation_strings":["Partnership for An Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, Georgia"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Partnership for An Advanced Computing Environment (PACE), Georgia Institute of Technology, Atlanta, Georgia","institution_ids":["https://openalex.org/I130701444"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I130701444"],"apc_list":null,"apc_paid":null,"fwci":1.5723,"has_fulltext":false,"cited_by_count":6,"citation_normalized_percentile":{"value":0.8570133,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":97},"biblio":{"volume":null,"issue":null,"first_page":"2270","last_page":"2275"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10101","display_name":"Cloud Computing and Resource Management","score":0.9937999844551086,"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9937999844551086,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.972100019454956,"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/T12205","display_name":"Time Series Analysis and Forecasting","score":0.9681000113487244,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.8321921825408936},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7860195636749268},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7022842168807983},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.4894348680973053},{"id":"https://openalex.org/keywords/software","display_name":"Software","score":0.4618711769580841},{"id":"https://openalex.org/keywords/resource","display_name":"Resource (disambiguation)","score":0.4447143077850342},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4398655295372009},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.4173700511455536},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.27201831340789795},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.2408519983291626}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.8321921825408936},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7860195636749268},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7022842168807983},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.4894348680973053},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.4618711769580841},{"id":"https://openalex.org/C206345919","wikidata":"https://www.wikidata.org/wiki/Q20380951","display_name":"Resource (disambiguation)","level":2,"score":0.4447143077850342},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4398655295372009},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.4173700511455536},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.27201831340789795},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.2408519983291626},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"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.2016.7840859","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata.2016.7840859","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2016 IEEE International Conference on Big Data (Big Data)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6399999856948853,"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W4390608645","https://openalex.org/W4394895745","https://openalex.org/W2960264696","https://openalex.org/W3090563135","https://openalex.org/W2497432351","https://openalex.org/W2766461310","https://openalex.org/W4247566972","https://openalex.org/W4388692845","https://openalex.org/W3202731209","https://openalex.org/W3211874991"],"abstract_inverted_index":{"Data":[0,97],"Science":[1,98],"research":[2,96],"has":[3],"a":[4,82,95,140,148,169,178,186],"long":[5],"history":[6],"in":[7,75,218],"academia":[8,70],"which":[9,221],"spans":[10],"from":[11,23,69,88],"large-scale":[12],"data":[13,16,19,38,45,50,197],"management,":[14],"to":[15,121],"mining":[17],"and":[18,46,59,135,142,150,175,181,199,226],"analysis":[20],"using":[21,168],"technologies":[22,36],"database":[24],"management":[25],"systems":[26],"(DBMS's).":[27],"While":[28],"traditional":[29],"HPC":[30,117],"offers":[31],"tools":[32,60],"on":[33,62,185,207],"leveraging":[34],"existing":[35,116],"with":[37,177],"processing":[39],"needs,":[40,125],"the":[41,47,56,153],"large":[42],"volume":[43],"of":[44,49,64,79,84],"speed":[48],"generation":[51],"pose":[52],"significant":[53],"challenges.":[54],"Using":[55],"Hadoop":[57,141,182],"platform":[58],"built":[61],"top":[63],"it":[65,72,162],"drew":[66],"immense":[67],"interest":[68],"after":[71],"gained":[73,217],"success":[74],"industry.":[76],"Georgia":[77],"Institute":[78],"Technology":[80],"received":[81],"donation":[83],"200":[85],"compute":[86],"nodes":[87,133],"Yahoo.":[89],"Turning":[90],"these":[91],"industrial":[92],"machines":[93],"into":[94,115],"Platform":[99],"(DSP)":[100],"poses":[101],"unique":[102],"challenges,":[103],"such":[104],"as:":[105],"nontrivial":[106],"hardware":[107],"design":[108],"decisions,":[109],"configuration":[110],"tool":[111],"choices,":[112,128],"node":[113],"integration":[114],"infrastructure,":[118],"partitioning":[119],"resource":[120],"meet":[122],"different":[123],"application":[124],"software":[126],"stack":[127],"etc.":[129],"We":[130,159,204,212],"have":[131],"40":[132],"up":[134,209],"running,":[136],"24":[137],"running":[138,146,155],"as":[139,147,156],"Spark":[143,164,173],"cluster,":[144,152],"12":[145],"HBase":[149],"OpenTSDB":[151,190],"others":[154],"service":[157],"nodes.":[158,211],"successfully":[160],"tested":[161],"against":[163],"Machine":[165],"Learning":[166],"algorithms":[167],"88GB":[170],"image":[171],"dataset,":[172,180],"DataFrame":[174],"GraphFrame":[176],"Wikipedia":[179],"MapReduce":[183],"wordcount":[184],"300GB":[187],"dataset.":[188],"The":[189],"cluster":[191],"is":[192],"for":[193,201],"real-time":[194],"time":[195],"series":[196],"ingestion":[198],"storage":[200],"sensor":[202],"data.":[203],"are":[205],"working":[206],"bringing":[208],"more":[210],"share":[213],"our":[214,219],"first-hand":[215],"experience":[216],"journey,":[220],"we":[222],"believe":[223],"will":[224],"benefit":[225],"inspire":[227],"other":[228],"academic":[229],"institutions.":[230]},"counts_by_year":[{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}