{"id":"https://openalex.org/W2751095725","doi":"https://doi.org/10.1109/nas.2017.8026864","title":"Kaleido: Enabling Efficient Scientific Data Processing on Big-Data Systems","display_name":"Kaleido: Enabling Efficient Scientific Data Processing on Big-Data Systems","publication_year":2017,"publication_date":"2017-08-01","ids":{"openalex":"https://openalex.org/W2751095725","doi":"https://doi.org/10.1109/nas.2017.8026864","mag":"2751095725"},"language":"en","primary_location":{"id":"doi:10.1109/nas.2017.8026864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2017.8026864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Networking, Architecture, and Storage (NAS)","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/A5012323110","display_name":"Saman Biookaghazadeh","orcid":null},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Saman Biookaghazadeh","raw_affiliation_strings":["Arizona State University, Tempe, Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona","institution_ids":["https://openalex.org/I55732556"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5103531132","display_name":"Shujia Zhou","orcid":null},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Shujia Zhou","raw_affiliation_strings":["Northrup Grumman, Baltimore, Maryland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Northrup Grumman, Baltimore, Maryland","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5018115197","display_name":"Ming Zhao","orcid":"https://orcid.org/0000-0002-1647-1769"},"institutions":[{"id":"https://openalex.org/I55732556","display_name":"Arizona State University","ror":"https://ror.org/03efmqc40","country_code":"US","type":"education","lineage":["https://openalex.org/I55732556"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Ming Zhao","raw_affiliation_strings":["Arizona State University, Tempe, Arizona"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Arizona State University, Tempe, Arizona","institution_ids":["https://openalex.org/I55732556"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.6473,"has_fulltext":false,"cited_by_count":4,"citation_normalized_percentile":{"value":0.69728388,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"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/T10101","display_name":"Cloud Computing and Resource Management","score":0.9987999796867371,"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":0.9987999796867371,"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/T11106","display_name":"Data Management and Algorithms","score":0.9973000288009644,"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"}},{"id":"https://openalex.org/T10715","display_name":"Distributed and Parallel Computing Systems","score":0.9962000250816345,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/netcdf","display_name":"NetCDF","score":0.9414015412330627},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8400972485542297},{"id":"https://openalex.org/keywords/big-data","display_name":"Big data","score":0.7737430334091187},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.5594381093978882},{"id":"https://openalex.org/keywords/dimension","display_name":"Dimension (graph theory)","score":0.5533360242843628},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.47981715202331543},{"id":"https://openalex.org/keywords/data-modeling","display_name":"Data modeling","score":0.4539879858493805},{"id":"https://openalex.org/keywords/speedup","display_name":"Speedup","score":0.4259878695011139},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.419491171836853},{"id":"https://openalex.org/keywords/data-processing","display_name":"Data processing","score":0.41728609800338745},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3310694694519043},{"id":"https://openalex.org/keywords/parallel-computing","display_name":"Parallel computing","score":0.10211583971977234},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.09143507480621338}],"concepts":[{"id":"https://openalex.org/C11090531","wikidata":"https://www.wikidata.org/wiki/Q1361922","display_name":"NetCDF","level":2,"score":0.9414015412330627},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8400972485542297},{"id":"https://openalex.org/C75684735","wikidata":"https://www.wikidata.org/wiki/Q858810","display_name":"Big data","level":2,"score":0.7737430334091187},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.5594381093978882},{"id":"https://openalex.org/C33676613","wikidata":"https://www.wikidata.org/wiki/Q13415176","display_name":"Dimension (graph theory)","level":2,"score":0.5533360242843628},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.47981715202331543},{"id":"https://openalex.org/C67186912","wikidata":"https://www.wikidata.org/wiki/Q367664","display_name":"Data modeling","level":2,"score":0.4539879858493805},{"id":"https://openalex.org/C68339613","wikidata":"https://www.wikidata.org/wiki/Q1549489","display_name":"Speedup","level":2,"score":0.4259878695011139},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.419491171836853},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.41728609800338745},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3310694694519043},{"id":"https://openalex.org/C173608175","wikidata":"https://www.wikidata.org/wiki/Q232661","display_name":"Parallel computing","level":1,"score":0.10211583971977234},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.09143507480621338},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.0},{"id":"https://openalex.org/C202444582","wikidata":"https://www.wikidata.org/wiki/Q837863","display_name":"Pure mathematics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/nas.2017.8026864","is_oa":false,"landing_page_url":"https://doi.org/10.1109/nas.2017.8026864","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2017 International Conference on Networking, Architecture, and Storage (NAS)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320306076","display_name":"National Science Foundation","ror":"https://ror.org/021nxhr62"}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":20,"referenced_works":["https://openalex.org/W1981420413","https://openalex.org/W2014830756","https://openalex.org/W2035355147","https://openalex.org/W2038412523","https://openalex.org/W2098994245","https://openalex.org/W2110086534","https://openalex.org/W2115583184","https://openalex.org/W2119565742","https://openalex.org/W2119738171","https://openalex.org/W2131975293","https://openalex.org/W2159825340","https://openalex.org/W2173213060","https://openalex.org/W2212383961","https://openalex.org/W2298833372","https://openalex.org/W2539603560","https://openalex.org/W2602692428","https://openalex.org/W4239670432","https://openalex.org/W6679815717","https://openalex.org/W6697540089","https://openalex.org/W6728835107"],"related_works":["https://openalex.org/W4393791361","https://openalex.org/W4393876146","https://openalex.org/W4393590023","https://openalex.org/W4393622966","https://openalex.org/W4393728971","https://openalex.org/W4393609815","https://openalex.org/W4393613575","https://openalex.org/W4393448036","https://openalex.org/W4394020292","https://openalex.org/W2258409311"],"abstract_inverted_index":{"Big-Data":[0],"systems":[1,20,57,74],"are":[2,34],"increasingly":[3],"important":[4],"for":[5,40,172,188],"solving":[6],"the":[7,23,52,113,137,185],"data-driven":[8],"problems":[9],"in":[10,96],"many":[11],"science":[12,59],"domains":[13],"including":[14],"geosciences.":[15],"However,":[16],"existing":[17,170],"big-":[18,72],"data":[19,28,41,73,90,177],"cannot":[21],"support":[22,106],"efficient":[24,128],"processing":[25,175],"of":[26,55,130,136,147],"self-describing":[27],"formats":[29],"such":[30],"as":[31],"NetCDF":[32,89,109,176],"which":[33,126],"commonly":[35],"used":[36],"by":[37,58,70],"scientific":[38,80,121,193],"communities":[39],"distribution":[42],"and":[43,78,93,165,174,180],"sharing.":[44],"This":[45,61],"limitation":[46],"presents":[47,63,143],"a":[48,65,144,153],"serious":[49],"hurdle":[50],"to":[51,67,75,86,105,112,120,169],"further":[53],"adoption":[54],"big-data":[56],"domains.":[60],"paper":[62,142],"Kaleido,":[64],"solution":[66],"this":[68],"problem":[69],"enabling":[71],"efficiently":[76],"store":[77,88],"process":[79,94],"data.":[81,140,194],"Specifically,":[82],"it":[83,116,181],"enables":[84,103],"Hadoop":[85],"directly":[87],"on":[91,108,152,178,192],"HDFS,":[92],"them":[95],"MapReduce":[97],"using":[98,149],"convenient":[99],"APIs.":[100],"It":[101],"also":[102,182],"Hive":[104],"queries":[107,132,151,191],"data,":[110,122],"transparent":[111],"users.":[114],"Moreover,":[115],"employs":[117],"optimizations":[118],"tailored":[119],"particularly":[123],"dimension-aware":[124],"layout":[125],"allows":[127],"execution":[129],"subset":[131,190],"targeting":[133],"any":[134],"dimension":[135],"multi-":[138],"dimensional":[139],"The":[141,157],"comprehensive":[145],"evaluation":[146],"Kaleido":[148,161],"representative":[150],"typical":[154],"geoscientific":[155],"dataset.":[156],"results":[158],"show":[159],"that":[160],"achieves":[162],"substantial":[163],"speedup":[164],"space":[166],"saving":[167],"compared":[168],"solutions":[171,187],"storing":[173],"Hadoop,":[179],"substantially":[183],"outperforms":[184],"state-of-the-art":[186],"supporting":[189]},"counts_by_year":[{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-10-10T00:00:00"}