{"id":"https://openalex.org/W2804722575","doi":"https://doi.org/10.1145/3208352.3208354","title":"Extending Apache Spark with a Mediation Layer","display_name":"Extending Apache Spark with a Mediation Layer","publication_year":2018,"publication_date":"2018-05-14","ids":{"openalex":"https://openalex.org/W2804722575","doi":"https://doi.org/10.1145/3208352.3208354","mag":"2804722575"},"language":"en","primary_location":{"id":"doi:10.1145/3208352.3208354","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3208352.3208354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic 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/A5015466855","display_name":"Dimitris Stripelis","orcid":"https://orcid.org/0000-0003-3343-8335"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Dimitris Stripelis","raw_affiliation_strings":["Information Sciences Institute, USC Viterbi School of Engineering, Marina Del Rey, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, USC Viterbi School of Engineering, Marina Del Rey, California","institution_ids":[]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5082460181","display_name":"Chrysovalantis Anastasiou","orcid":"https://orcid.org/0000-0003-4966-5129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Chrysovalantis Anastasiou","raw_affiliation_strings":["Integrated Media Systems Center, USC Viterbi School of Engineering, Los Angeles, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Integrated Media Systems Center, USC Viterbi School of Engineering, Los Angeles, California","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5033175043","display_name":"Jos\u00e9 Luis Ambite","orcid":"https://orcid.org/0000-0003-0087-080X"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Jos\u00e9 Luis Ambite","raw_affiliation_strings":["Information Sciences Institute, USC Viterbi School of Engineering, Marina Del Rey, California"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Information Sciences Institute, USC Viterbi School of Engineering, Marina Del Rey, California","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"6"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983999729156494,"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"}},"topics":[{"id":"https://openalex.org/T10317","display_name":"Advanced Database Systems and Queries","score":0.9983999729156494,"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/T12761","display_name":"Data Stream Mining Techniques","score":0.9968000054359436,"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/T11986","display_name":"Scientific Computing and Data Management","score":0.9919999837875366,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/spark","display_name":"SPARK (programming language)","score":0.7785011529922485},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7579202055931091},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.6459406614303589},{"id":"https://openalex.org/keywords/scalability","display_name":"Scalability","score":0.6185342669487},{"id":"https://openalex.org/keywords/schema","display_name":"Schema (genetic algorithms)","score":0.5382352471351624},{"id":"https://openalex.org/keywords/data-integration","display_name":"Data integration","score":0.5228902697563171},{"id":"https://openalex.org/keywords/analytics","display_name":"Analytics","score":0.4534882605075836},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.4421424865722656},{"id":"https://openalex.org/keywords/data-virtualization","display_name":"Data virtualization","score":0.4353697597980499},{"id":"https://openalex.org/keywords/distributed-computing","display_name":"Distributed computing","score":0.3284105658531189},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.31178364157676697},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.21911892294883728},{"id":"https://openalex.org/keywords/cloud-computing","display_name":"Cloud computing","score":0.18979677557945251},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.1710658073425293},{"id":"https://openalex.org/keywords/operating-system","display_name":"Operating system","score":0.15794500708580017}],"concepts":[{"id":"https://openalex.org/C2781215313","wikidata":"https://www.wikidata.org/wiki/Q3493345","display_name":"SPARK (programming language)","level":2,"score":0.7785011529922485},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7579202055931091},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.6459406614303589},{"id":"https://openalex.org/C48044578","wikidata":"https://www.wikidata.org/wiki/Q727490","display_name":"Scalability","level":2,"score":0.6185342669487},{"id":"https://openalex.org/C52146309","wikidata":"https://www.wikidata.org/wiki/Q7431116","display_name":"Schema (genetic algorithms)","level":2,"score":0.5382352471351624},{"id":"https://openalex.org/C72634772","wikidata":"https://www.wikidata.org/wiki/Q386824","display_name":"Data integration","level":2,"score":0.5228902697563171},{"id":"https://openalex.org/C79158427","wikidata":"https://www.wikidata.org/wiki/Q485396","display_name":"Analytics","level":2,"score":0.4534882605075836},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.4421424865722656},{"id":"https://openalex.org/C80344994","wikidata":"https://www.wikidata.org/wiki/Q5227369","display_name":"Data virtualization","level":4,"score":0.4353697597980499},{"id":"https://openalex.org/C120314980","wikidata":"https://www.wikidata.org/wiki/Q180634","display_name":"Distributed computing","level":1,"score":0.3284105658531189},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.31178364157676697},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.21911892294883728},{"id":"https://openalex.org/C79974875","wikidata":"https://www.wikidata.org/wiki/Q483639","display_name":"Cloud computing","level":2,"score":0.18979677557945251},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.1710658073425293},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.15794500708580017},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C513985346","wikidata":"https://www.wikidata.org/wiki/Q270471","display_name":"Virtualization","level":3,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3208352.3208354","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3208352.3208354","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the International Workshop on Semantic Big Data","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.6200000047683716,"id":"https://metadata.un.org/sdg/9","display_name":"Industry, innovation and infrastructure"}],"awards":[],"funders":[{"id":"https://openalex.org/F4320332161","display_name":"National Institutes of Health","ror":"https://ror.org/01cwqze88"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":35,"referenced_works":["https://openalex.org/W67656603","https://openalex.org/W361253298","https://openalex.org/W1223193434","https://openalex.org/W1562548864","https://openalex.org/W1870305865","https://openalex.org/W1967928013","https://openalex.org/W1988979669","https://openalex.org/W2011853314","https://openalex.org/W2038412523","https://openalex.org/W2101654853","https://openalex.org/W2102521965","https://openalex.org/W2102729564","https://openalex.org/W2108395352","https://openalex.org/W2113640782","https://openalex.org/W2119046278","https://openalex.org/W2141824507","https://openalex.org/W2162520370","https://openalex.org/W2164287735","https://openalex.org/W2166631541","https://openalex.org/W2167265771","https://openalex.org/W2168605051","https://openalex.org/W2172549414","https://openalex.org/W2189465200","https://openalex.org/W2260616469","https://openalex.org/W2299839756","https://openalex.org/W2323506184","https://openalex.org/W2397216586","https://openalex.org/W2473419855","https://openalex.org/W2521416656","https://openalex.org/W2585438896","https://openalex.org/W2585641484","https://openalex.org/W2613536717","https://openalex.org/W2616561403","https://openalex.org/W3017602685","https://openalex.org/W6687322159"],"related_works":["https://openalex.org/W3191926225","https://openalex.org/W2949279097","https://openalex.org/W4216703","https://openalex.org/W2020045149","https://openalex.org/W4285502407","https://openalex.org/W1968076388","https://openalex.org/W3019007971","https://openalex.org/W2157176736","https://openalex.org/W2080078336","https://openalex.org/W4387639963"],"abstract_inverted_index":{"With":[0],"the":[1,74,88,94],"recent":[2],"growth":[3],"of":[4,10,36,79,90,96],"data":[5,29,76,99,104],"volumes":[6],"in":[7],"many":[8,15],"disciplines":[9],"both":[11],"industry":[12],"and":[13,32,52,100],"academia":[14],"new":[16],"Big":[17],"Data":[18],"Management":[19],"systems":[20,38],"have":[21],"emerged":[22],"to":[23,93],"provide":[24],"scalable":[25],"tools":[26],"for":[27,42],"efficient":[28],"storing,":[30],"processing":[31],"analysis.":[33],"However,":[34],"most":[35],"these":[37],"offer":[39],"little":[40],"support":[41],"efficiently":[43],"integrating":[44],"multiple":[45],"external":[46],"sources":[47],"under":[48],"a":[49,53,70,83],"uniform":[50],"schema":[51],"single":[54],"query":[55],"access":[56],"point,":[57],"which":[58],"greatly":[59],"simplifies":[60],"further":[61],"analytics.":[62],"In":[63],"this":[64],"work,":[65],"we":[66,86],"present":[67],"Spark":[68,91],"Mediator,":[69],"system":[71],"that":[72],"extends":[73],"logical":[75],"integration":[77,95,105],"capabilities":[78],"Apache":[80],"Spark.":[81],"As":[82],"use":[84],"case,":[85],"show":[87],"application":[89],"Mediator":[92],"schizophrenia":[97],"neuroimaging":[98],"compare":[101],"with":[102],"previous":[103],"systems.":[106]},"counts_by_year":[{"year":2023,"cited_by_count":2},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
