{"id":"https://openalex.org/W4391094988","doi":"https://doi.org/10.1109/bigdata59044.2023.10386969","title":"Ocean Data Quality Assessment through Outlier Detection-enhanced Active Learning","display_name":"Ocean Data Quality Assessment through Outlier Detection-enhanced Active Learning","publication_year":2023,"publication_date":"2023-12-15","ids":{"openalex":"https://openalex.org/W4391094988","doi":"https://doi.org/10.1109/bigdata59044.2023.10386969"},"language":"en","primary_location":{"id":"doi:10.1109/bigdata59044.2023.10386969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"http://arxiv.org/pdf/2312.10817","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100368028","display_name":"Na Li","orcid":"https://orcid.org/0000-0001-7799-876X"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Na Li","raw_affiliation_strings":["Informatics Institute, University of Amsterdam,Multiscale Networked System,Netherlands","Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam,Multiscale Networked System,Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5111116099","display_name":"Yiyang Qi","orcid":null},"institutions":[{"id":"https://openalex.org/I865915315","display_name":"Vrije Universiteit Amsterdam","ror":"https://ror.org/008xxew50","country_code":"NL","type":"education","lineage":["https://openalex.org/I865915315"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Yiyang Qi","raw_affiliation_strings":["Vrije Universiteit Amsterdam,Computer Science Department,Amsterdam,Netherlands","Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands","Computer Science Department, Vrije Universiteit Amsterdam, Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Vrije Universiteit Amsterdam,Computer Science Department,Amsterdam,Netherlands","institution_ids":["https://openalex.org/I865915315"]},{"raw_affiliation_string":"Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Computer Science Department, Vrije Universiteit Amsterdam, Amsterdam, Netherlands","institution_ids":["https://openalex.org/I865915315"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5073878572","display_name":"Ruyue Xin","orcid":"https://orcid.org/0000-0001-5821-4835"},"institutions":[{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Ruyue Xin","raw_affiliation_strings":["Informatics Institute, University of Amsterdam,Multiscale Networked System,Netherlands","Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam,Multiscale Networked System,Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5068341719","display_name":"Zhiming Zhao","orcid":"https://orcid.org/0000-0002-6717-9418"},"institutions":[{"id":"https://openalex.org/I4405260839","display_name":"LifeWatch ERIC","ror":"https://ror.org/04c04g438","country_code":"ES","type":"nonprofit","lineage":["https://openalex.org/I4405260839"]},{"id":"https://openalex.org/I887064364","display_name":"University of Amsterdam","ror":"https://ror.org/04dkp9463","country_code":"NL","type":"education","lineage":["https://openalex.org/I887064364"]}],"countries":["ES","NL"],"is_corresponding":false,"raw_author_name":"Zhiming Zhao","raw_affiliation_strings":["Informatics Institute, University of Amsterdam,Multiscale Networked System,Netherlands","LifeWatch ERIC Virtual Lab and Innovation Center (VLIC), Amsterdam, Netherlands","Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Informatics Institute, University of Amsterdam,Multiscale Networked System,Netherlands","institution_ids":["https://openalex.org/I887064364"]},{"raw_affiliation_string":"LifeWatch ERIC Virtual Lab and Innovation Center (VLIC), Amsterdam, Netherlands","institution_ids":["https://openalex.org/I4405260839"]},{"raw_affiliation_string":"Multiscale Networked System, Informatics Institute, University of Amsterdam, Netherlands","institution_ids":["https://openalex.org/I887064364"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"102","last_page":"107"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10876","display_name":"Fault Detection and Control Systems","score":0.998199999332428,"subfield":{"id":"https://openalex.org/subfields/2207","display_name":"Control and Systems Engineering"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11512","display_name":"Anomaly Detection Techniques and Applications","score":0.9890999794006348,"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/T10711","display_name":"Target Tracking and Data Fusion in Sensor Networks","score":0.986299991607666,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/anomaly-detection","display_name":"Anomaly detection","score":0.61826491355896},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6148762702941895},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.5923898220062256},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.521918535232544},{"id":"https://openalex.org/keywords/data-quality","display_name":"Data quality","score":0.42155811190605164},{"id":"https://openalex.org/keywords/remote-sensing","display_name":"Remote sensing","score":0.3874777853488922},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3665197491645813},{"id":"https://openalex.org/keywords/geology","display_name":"Geology","score":0.21247562766075134},{"id":"https://openalex.org/keywords/engineering","display_name":"Engineering","score":0.12671920657157898}],"concepts":[{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.61826491355896},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6148762702941895},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.5923898220062256},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.521918535232544},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.42155811190605164},{"id":"https://openalex.org/C62649853","wikidata":"https://www.wikidata.org/wiki/Q199687","display_name":"Remote sensing","level":1,"score":0.3874777853488922},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3665197491645813},{"id":"https://openalex.org/C127313418","wikidata":"https://www.wikidata.org/wiki/Q1069","display_name":"Geology","level":0,"score":0.21247562766075134},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.12671920657157898},{"id":"https://openalex.org/C21547014","wikidata":"https://www.wikidata.org/wiki/Q1423657","display_name":"Operations management","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C176217482","wikidata":"https://www.wikidata.org/wiki/Q860554","display_name":"Metric (unit)","level":2,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/bigdata59044.2023.10386969","is_oa":false,"landing_page_url":"https://doi.org/10.1109/bigdata59044.2023.10386969","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE International Conference on Big Data (BigData)","raw_type":"proceedings-article"},{"id":"pmh:oai:zenodo.org:10576019","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2312.10817v1","pdf_url":"http://arxiv.org/pdf/2312.10817","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BigData, IEEE BigData, Italy","raw_type":"info:eu-repo/semantics/conferencePaper"}],"best_oa_location":{"id":"pmh:oai:zenodo.org:10576019","is_oa":true,"landing_page_url":"https://arxiv.org/abs/arXiv:2312.10817v1","pdf_url":"http://arxiv.org/pdf/2312.10817","source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"BigData, IEEE BigData, Italy","raw_type":"info:eu-repo/semantics/conferencePaper"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/13","display_name":"Climate action","score":0.699999988079071}],"awards":[{"id":"https://openalex.org/G2300613588","display_name":"CLoud ARtificial Intelligence For pathologY","funder_award_id":"860627","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3912856170","display_name":"ENVironmental Research Infrastructures building Fair services Accessible for society, Innovation and Research","funder_award_id":"824068","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8072458336","display_name":"A federated European FAIR and Open Research Ecosystem for oceans, seas, coastal and inland waters","funder_award_id":"101094227","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8764417039","display_name":"smART socIal media eCOsytstem in a blockchaiN Federated environment","funder_award_id":"825134","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321800","display_name":"Nederlandse Organisatie voor Wetenschappelijk Onderzoek","ror":"https://ror.org/04jsz6e67"},{"id":"https://openalex.org/F4320325020","display_name":"LifeWatch \u2013 Niclas \u00d6berg Foundation","ror":null}],"has_content":{"grobid_xml":false,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W4391094988.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W160042716","https://openalex.org/W1967320885","https://openalex.org/W2105497548","https://openalex.org/W2116656765","https://openalex.org/W2150900085","https://openalex.org/W2170775563","https://openalex.org/W2289669588","https://openalex.org/W2295598076","https://openalex.org/W2296719434","https://openalex.org/W2549804226","https://openalex.org/W2768348081","https://openalex.org/W2887831728","https://openalex.org/W2964022491","https://openalex.org/W3031903852","https://openalex.org/W3094509504","https://openalex.org/W3158273053","https://openalex.org/W4254182148","https://openalex.org/W4316116055","https://openalex.org/W4362673537","https://openalex.org/W6745609711","https://openalex.org/W6750729320","https://openalex.org/W6756615331","https://openalex.org/W6776641763"],"related_works":["https://openalex.org/W3006513224","https://openalex.org/W2046456988","https://openalex.org/W2357409937","https://openalex.org/W2510582230","https://openalex.org/W2499612753","https://openalex.org/W3111802945","https://openalex.org/W2946096271","https://openalex.org/W2295423552","https://openalex.org/W1598471830","https://openalex.org/W3107369729"],"abstract_inverted_index":{"Ocean":[0],"and":[1,14,37,56,91,125,154],"climate":[2],"research":[3],"benefits":[4],"from":[5,34],"global":[6],"ocean":[7,21,73],"observation":[8],"initiatives":[9],"such":[10],"as":[11],"Argo,":[12],"GLOSS,":[13],"EMSO.":[15],"The":[16,131],"Argo":[17,109],"network,":[18],"dedicated":[19],"to":[20,52,81,111,143,151,161],"profiling,":[22],"generates":[23],"a":[24],"vast":[25],"volume":[26],"of":[27,121],"observatory":[28],"data.":[29],"However,":[30],"data":[31,55,74],"quality":[32,42,75,88,138],"issues":[33],"sensor":[35],"malfunctions":[36],"transmission":[38],"errors":[39],"necessitate":[40],"stringent":[41],"assessment.":[43],"Existing":[44],"methods,":[45],"including":[46,118],"machine":[47],"learning,":[48],"fall":[49],"short":[50],"due":[51],"limited":[53],"labeled":[54],"imbalanced":[57],"datasets.":[58],"To":[59],"address":[60],"these":[61],"challenges,":[62],"we":[63],"propose":[64],"an":[65],"Outlier":[66],"Detection-Enhanced":[67],"Active":[68,78],"Learning":[69,79],"(ODEAL)":[70],"framework":[71,136],"for":[72,96],"assessment,":[76],"employing":[77],"(AL)":[80],"reduce":[82],"human":[83],"experts\u2019":[84],"workload":[85],"in":[86],"the":[87,119,126,146,164],"assessment":[89,139],"workflow":[90],"leveraging":[92],"outlier":[93,169],"detection":[94],"algorithms":[95],"effective":[97],"model":[98],"initialization.":[99],"We":[100],"also":[101],"conduct":[102],"extensive":[103],"experiments":[104],"on":[105],"five":[106],"large-scale":[107],"realistic":[108],"datasets":[110],"gain":[112],"insights":[113],"into":[114],"our":[115,135],"proposed":[116],"method,":[117],"effectiveness":[120],"AL":[122],"query":[123,148],"strategies":[124],"initial":[127,165],"set":[128,166],"construction":[129],"approach.":[130],"results":[132],"suggest":[133],"that":[134],"enhances":[137],"efficiency":[140],"by":[141,159],"up":[142,160],"465.5%":[144],"with":[145,168],"uncertainty-based":[147],"strategy":[149],"compared":[150],"random":[152],"sampling":[153],"minimizes":[155],"overall":[156],"annotation":[157],"costs":[158],"76.9%":[162],"using":[163],"built":[167],"detectors.":[170]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":2},{"year":2024,"cited_by_count":1}],"updated_date":"2026-07-27T08:26:11.824852","created_date":"2025-10-10T00:00:00"}