{"id":"https://openalex.org/W3044469091","doi":"https://doi.org/10.1145/3388440.3412460","title":"Collaborative Cloud Computing Framework for Health Data with Open Source Technologies","display_name":"Collaborative Cloud Computing Framework for Health Data with Open Source Technologies","publication_year":2020,"publication_date":"2020-09-21","ids":{"openalex":"https://openalex.org/W3044469091","doi":"https://doi.org/10.1145/3388440.3412460","mag":"3044469091"},"language":"en","primary_location":{"id":"doi:10.1145/3388440.3412460","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3388440.3412460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},"type":"article","indexed_in":["arxiv","crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://arxiv.org/pdf/2007.10498","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Fatemeh Rouzbeh","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Fatemeh Rouzbeh","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Ananth Grama","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ananth Grama","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"middle","author":{"id":null,"display_name":"Paul Griffin","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Paul Griffin","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]},{"author_position":"last","author":{"id":null,"display_name":"Mohammad Adibuzzaman","orcid":null},"institutions":[{"id":"https://openalex.org/I219193219","display_name":"Purdue University West Lafayette","ror":"https://ror.org/02dqehb95","country_code":"US","type":"education","lineage":["https://openalex.org/I219193219"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Mohammad Adibuzzaman","raw_affiliation_strings":["Purdue University, West Lafayette, USA"],"affiliations":[{"raw_affiliation_string":"Purdue University, West Lafayette, USA","institution_ids":["https://openalex.org/I219193219"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I219193219"],"apc_list":null,"apc_paid":null,"fwci":0.4581,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.80388616,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"10"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9952999949455261,"subfield":{"id":"https://openalex.org/subfields/1802","display_name":"Information Systems and Management"},"field":{"id":"https://openalex.org/fields/18","display_name":"Decision Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},{"id":"https://openalex.org/T13702","display_name":"Machine Learning in Healthcare","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"}},{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9891999959945679,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.6881999969482422},{"id":"https://openalex.org/keywords/flexibility","display_name":"Flexibility (engineering)","score":0.6345000267028809},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.5184999704360962},{"id":"https://openalex.org/keywords/architecture","display_name":"Architecture","score":0.45739999413490295},{"id":"https://openalex.org/keywords/set","display_name":"Set (abstract data type)","score":0.4049000144004822},{"id":"https://openalex.org/keywords/data-sharing","display_name":"Data sharing","score":0.3709000051021576},{"id":"https://openalex.org/keywords/data-type","display_name":"Data type","score":0.36059999465942383},{"id":"https://openalex.org/keywords/open-research","display_name":"Open research","score":0.34850001335144043},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.32499998807907104},{"id":"https://openalex.org/keywords/systems-architecture","display_name":"Systems architecture","score":0.31619998812675476}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7634000182151794},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.6881999969482422},{"id":"https://openalex.org/C2780598303","wikidata":"https://www.wikidata.org/wiki/Q65921492","display_name":"Flexibility (engineering)","level":2,"score":0.6345000267028809},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.6093999743461609},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.5184999704360962},{"id":"https://openalex.org/C123657996","wikidata":"https://www.wikidata.org/wiki/Q12271","display_name":"Architecture","level":2,"score":0.45739999413490295},{"id":"https://openalex.org/C177264268","wikidata":"https://www.wikidata.org/wiki/Q1514741","display_name":"Set (abstract data type)","level":2,"score":0.4049000144004822},{"id":"https://openalex.org/C2779965156","wikidata":"https://www.wikidata.org/wiki/Q5227350","display_name":"Data sharing","level":3,"score":0.3709000051021576},{"id":"https://openalex.org/C138958017","wikidata":"https://www.wikidata.org/wiki/Q190087","display_name":"Data type","level":2,"score":0.36059999465942383},{"id":"https://openalex.org/C2778464652","wikidata":"https://www.wikidata.org/wiki/Q309849","display_name":"Open research","level":2,"score":0.34850001335144043},{"id":"https://openalex.org/C115903868","wikidata":"https://www.wikidata.org/wiki/Q80993","display_name":"Software engineering","level":1,"score":0.33309999108314514},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.3319000005722046},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.32499998807907104},{"id":"https://openalex.org/C98025372","wikidata":"https://www.wikidata.org/wiki/Q477538","display_name":"Systems architecture","level":3,"score":0.31619998812675476},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.31119999289512634},{"id":"https://openalex.org/C3018397939","wikidata":"https://www.wikidata.org/wiki/Q3644502","display_name":"Open source","level":3,"score":0.29919999837875366},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.29179999232292175},{"id":"https://openalex.org/C133462117","wikidata":"https://www.wikidata.org/wiki/Q4929239","display_name":"Data collection","level":2,"score":0.28999999165534973},{"id":"https://openalex.org/C34165917","wikidata":"https://www.wikidata.org/wiki/Q188267","display_name":"Programming paradigm","level":2,"score":0.28529998660087585},{"id":"https://openalex.org/C70061542","wikidata":"https://www.wikidata.org/wiki/Q989016","display_name":"Distributed database","level":2,"score":0.2842999994754791},{"id":"https://openalex.org/C2778149293","wikidata":"https://www.wikidata.org/wiki/Q309823","display_name":"Open science","level":2,"score":0.2822999954223633},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.2816999852657318},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.2815999984741211},{"id":"https://openalex.org/C58489278","wikidata":"https://www.wikidata.org/wiki/Q1172284","display_name":"Data set","level":2,"score":0.2777000069618225},{"id":"https://openalex.org/C207267971","wikidata":"https://www.wikidata.org/wiki/Q120208","display_name":"Emerging technologies","level":2,"score":0.2736999988555908},{"id":"https://openalex.org/C1668388","wikidata":"https://www.wikidata.org/wiki/Q1149776","display_name":"Data management","level":2,"score":0.26440000534057617},{"id":"https://openalex.org/C3017977704","wikidata":"https://www.wikidata.org/wiki/Q18745135","display_name":"Health data","level":3,"score":0.2621999979019165},{"id":"https://openalex.org/C180198813","wikidata":"https://www.wikidata.org/wiki/Q121182","display_name":"Information system","level":2,"score":0.26109999418258667},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.2603999972343445},{"id":"https://openalex.org/C194739806","wikidata":"https://www.wikidata.org/wiki/Q66221","display_name":"Computer data storage","level":2,"score":0.25999999046325684},{"id":"https://openalex.org/C2780535194","wikidata":"https://www.wikidata.org/wiki/Q309901","display_name":"Open data","level":2,"score":0.259799987077713},{"id":"https://openalex.org/C123201435","wikidata":"https://www.wikidata.org/wiki/Q456632","display_name":"Information privacy","level":2,"score":0.25589999556541443},{"id":"https://openalex.org/C33762810","wikidata":"https://www.wikidata.org/wiki/Q461671","display_name":"Data integrity","level":2,"score":0.2508000135421753}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/3388440.3412460","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3388440.3412460","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 11th ACM International Conference on Bioinformatics, Computational Biology and Health Informatics","raw_type":"proceedings-article"},{"id":"pmh:oai:arXiv.org:2007.10498","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10498","pdf_url":"https://arxiv.org/pdf/2007.10498","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:2007.10498","is_oa":true,"landing_page_url":"http://arxiv.org/abs/2007.10498","pdf_url":"https://arxiv.org/pdf/2007.10498","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":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W202860122","https://openalex.org/W1776325840","https://openalex.org/W1952553890","https://openalex.org/W1973747955","https://openalex.org/W1983005394","https://openalex.org/W2011013830","https://openalex.org/W2053710796","https://openalex.org/W2068069008","https://openalex.org/W2081814119","https://openalex.org/W2104608657","https://openalex.org/W2104993419","https://openalex.org/W2120989936","https://openalex.org/W2131940722","https://openalex.org/W2149140091","https://openalex.org/W2215669148","https://openalex.org/W2396881363","https://openalex.org/W2572857085","https://openalex.org/W2597719243","https://openalex.org/W2754542821","https://openalex.org/W2757504960","https://openalex.org/W2774995705","https://openalex.org/W2798903611","https://openalex.org/W2891243993","https://openalex.org/W2982615798","https://openalex.org/W3036577874"],"related_works":[],"abstract_inverted_index":{"The":[0],"proliferation":[1],"of":[2,15,19,32,42,48,100,137,176],"sensor":[3],"technologies":[4,153],"and":[5,60,106,133,159],"advancements":[6],"in":[7,40,62,130,161],"data":[8,50,92,125,174],"collection":[9],"methods":[10],"have":[11],"enabled":[12],"the":[13,30,33,79,88,94,110,119,135,138,168],"accumulation":[14],"very":[16],"large":[17,172],"amounts":[18],"data.":[20],"Increasingly,":[21],"these":[22],"datasets":[23],"are":[24],"considered":[25],"for":[26,74,122,127,147],"scientific":[27,64,128],"research.":[28],"However,":[29],"design":[31],"system":[34,140,169],"architecture":[35,146],"to":[36,85,90],"achieve":[37],"high":[38],"performance":[39],"terms":[41],"parallelization,":[43],"query":[44],"processing":[45],"time,":[46],"aggregation":[47],"heterogeneous":[49],"types":[51],"(e.g.,":[52],"time":[53],"series,":[54],"images,":[55],"structured":[56],"data,":[57],"among":[58],"others),":[59],"difficulty":[61],"reproducing":[63],"research":[65,129],"remain":[66],"a":[67,144,162,171],"major":[68],"challenge.":[69],"This":[70],"is":[71],"specifically":[72],"true":[73],"health":[75,131],"sciences":[76,132],"research,":[77],"where":[78],"systems":[80,126],"must":[81],"be":[82],"i)":[83],"easy":[84],"use":[86],"with":[87,109],"flexibility":[89],"manipulate":[91],"at":[93],"most":[95],"granular":[96],"level,":[97],"ii)":[98],"agnostic":[99],"programming":[101],"language":[102],"kernel,":[103],"iii)":[104],"scalable,":[105],"iv)":[107],"compliant":[108],"HIPAA":[111],"privacy":[112],"law.":[113],"In":[114],"this":[115],"paper,":[116],"we":[117],"review":[118],"existing":[120],"literature":[121],"such":[123,154],"big":[124],"identify":[134],"gaps":[136],"current":[139],"landscape.":[141],"We":[142,165],"propose":[143],"novel":[145],"software-hardware-data":[148],"ecosystem":[149],"using":[150,170],"open":[151],"source":[152],"as":[155],"Apache":[156],"Hadoop,":[157],"Kubernetes":[158],"JupyterHub":[160],"distributed":[163],"environment.":[164],"also":[166],"evaluate":[167],"clinical":[173],"set":[175],"69M":[177],"patients.":[178]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2024,"cited_by_count":1},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-20T23:20:44.827607","created_date":"2020-07-29T00:00:00"}
