{"id":"https://openalex.org/W2990256517","doi":"https://doi.org/10.1145/3366624.3368170","title":"Dredging a data lake","display_name":"Dredging a data lake","publication_year":2019,"publication_date":"2019-11-27","ids":{"openalex":"https://openalex.org/W2990256517","doi":"https://doi.org/10.1145/3366624.3368170","mag":"2990256517"},"language":"en","primary_location":{"id":"doi:10.1145/3366624.3368170","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366624.3368170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","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/A5079278437","display_name":"Tyler J. Skluzacek","orcid":"https://orcid.org/0000-0003-2242-4931"},"institutions":[{"id":"https://openalex.org/I40347166","display_name":"University of Chicago","ror":"https://ror.org/024mw5h28","country_code":"US","type":"education","lineage":["https://openalex.org/I40347166"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Tyler J. Skluzacek","raw_affiliation_strings":["University of Chicago"],"affiliations":[{"raw_affiliation_string":"University of Chicago","institution_ids":["https://openalex.org/I40347166"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":["https://openalex.org/A5079278437"],"corresponding_institution_ids":["https://openalex.org/I40347166"],"apc_list":null,"apc_paid":null,"fwci":1.323,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.90889081,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":98},"biblio":{"volume":null,"issue":null,"first_page":"51","last_page":"53"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11986","display_name":"Scientific Computing and Data Management","score":0.9991000294685364,"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":0.9991000294685364,"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/T11719","display_name":"Data Quality and Management","score":0.9959999918937683,"subfield":{"id":"https://openalex.org/subfields/1803","display_name":"Management Science and Operations Research"},"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/T11181","display_name":"Advanced Data Storage Technologies","score":0.9954000115394592,"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/dredging","display_name":"Dredging","score":0.9128262996673584},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.45829448103904724},{"id":"https://openalex.org/keywords/environmental-science","display_name":"Environmental science","score":0.3861086368560791},{"id":"https://openalex.org/keywords/marine-engineering","display_name":"Marine engineering","score":0.37486398220062256},{"id":"https://openalex.org/keywords/oceanography","display_name":"Oceanography","score":0.3573870360851288},{"id":"https://openalex.org/keywords/hydrology","display_name":"Hydrology (agriculture)","score":0.32211604714393616},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.27168911695480347},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.260733962059021},{"id":"https://openalex.org/keywords/geotechnical-engineering","display_name":"Geotechnical engineering","score":0.170780211687088}],"concepts":[{"id":"https://openalex.org/C2781279111","wikidata":"https://www.wikidata.org/wiki/Q852170","display_name":"Dredging","level":2,"score":0.9128262996673584},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.45829448103904724},{"id":"https://openalex.org/C39432304","wikidata":"https://www.wikidata.org/wiki/Q188847","display_name":"Environmental science","level":0,"score":0.3861086368560791},{"id":"https://openalex.org/C199104240","wikidata":"https://www.wikidata.org/wiki/Q118291","display_name":"Marine engineering","level":1,"score":0.37486398220062256},{"id":"https://openalex.org/C111368507","wikidata":"https://www.wikidata.org/wiki/Q43518","display_name":"Oceanography","level":1,"score":0.3573870360851288},{"id":"https://openalex.org/C76886044","wikidata":"https://www.wikidata.org/wiki/Q2883300","display_name":"Hydrology (agriculture)","level":2,"score":0.32211604714393616},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.27168911695480347},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.260733962059021},{"id":"https://openalex.org/C187320778","wikidata":"https://www.wikidata.org/wiki/Q1349130","display_name":"Geotechnical engineering","level":1,"score":0.170780211687088}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/3366624.3368170","is_oa":false,"landing_page_url":"https://doi.org/10.1145/3366624.3368170","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 20th International Middleware Conference Doctoral Symposium","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"display_name":"Industry, innovation and infrastructure","id":"https://metadata.un.org/sdg/9","score":0.5}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":13,"referenced_works":["https://openalex.org/W2001818158","https://openalex.org/W2206826311","https://openalex.org/W2592114463","https://openalex.org/W2906830849","https://openalex.org/W2906841437","https://openalex.org/W2917576038","https://openalex.org/W2940974134","https://openalex.org/W2943761765","https://openalex.org/W2984976594","https://openalex.org/W3015860937","https://openalex.org/W3104388511","https://openalex.org/W3121991495","https://openalex.org/W4233717669"],"related_works":["https://openalex.org/W2999348011","https://openalex.org/W2156909292","https://openalex.org/W2301106095","https://openalex.org/W2041630996","https://openalex.org/W155941434","https://openalex.org/W2375034415","https://openalex.org/W2625371984","https://openalex.org/W2390564770","https://openalex.org/W2243600059","https://openalex.org/W2086797516"],"abstract_inverted_index":{"The":[0,19],"rapid":[1],"generation":[2],"of":[3,21,97],"data":[4,16,26,104],"from":[5,55],"distributed":[6,40,103],"IoT":[7],"devices,":[8],"scientific":[9],"instruments,":[10],"and":[11,24,85],"compute":[12,86],"clusters":[13],"presents":[14],"unique":[15],"management":[17],"challenges.":[18],"influx":[20],"large,":[22],"heterogeneous,":[23],"complex":[25],"causes":[27],"repositories":[28],"to":[29,52,69,80],"become":[30],"siloed":[31],"or":[32],"generally":[33],"unsearchable---both":[34],"problems":[35],"not":[36],"currently":[37],"well-addressed":[38],"by":[39],"file":[41,76],"systems.":[42],"In":[43,63],"this":[44,90],"work,":[45,66],"we":[46,67],"propose":[47],"Xtract,":[48],"a":[49,98],"serverless":[50],"middleware":[51],"extract":[53],"metadata":[54],"files":[56],"spread":[57],"across":[58,102],"heterogeneous":[59],"edge":[60],"computing":[61],"resources.":[62],"my":[64],"future":[65],"intend":[68],"study":[70],"how":[71],"Xtract":[72,92],"can":[73],"automatically":[74],"construct":[75],"extraction":[77],"workflows":[78],"subject":[79],"users'":[81],"cost,":[82],"time,":[83],"security,":[84],"allocation":[87],"constraints.":[88],"To":[89],"end,":[91],"will":[93],"enable":[94],"the":[95],"creation":[96],"searchable":[99],"centralized":[100],"index":[101],"collections.":[105]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":1},{"year":2024,"cited_by_count":2},{"year":2021,"cited_by_count":2},{"year":2019,"cited_by_count":1}],"updated_date":"2026-04-12T07:58:50.170612","created_date":"2025-10-10T00:00:00"}
