{"id":"https://openalex.org/W4410859373","doi":"https://doi.org/10.3390/fi17060241","title":"Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies","display_name":"Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies","publication_year":2025,"publication_date":"2025-05-29","ids":{"openalex":"https://openalex.org/W4410859373","doi":"https://doi.org/10.3390/fi17060241"},"language":"en","primary_location":{"id":"doi:10.3390/fi17060241","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17060241","pdf_url":"https://www.mdpi.com/1999-5903/17/6/241/pdf?version=1748525858","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"type":"article","indexed_in":["crossref","doaj"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://www.mdpi.com/1999-5903/17/6/241/pdf?version=1748525858","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5112353020","display_name":"Qi Liu","orcid":"https://orcid.org/0000-0002-1587-8524"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Qi Liu","raw_affiliation_strings":["Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation, Tongji University, Shanghai 200092, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation, Tongji University, Shanghai 200092, China","institution_ids":["https://openalex.org/I116953780"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5101764264","display_name":"Wanjing Ma","orcid":"https://orcid.org/0000-0003-4875-041X"},"institutions":[{"id":"https://openalex.org/I116953780","display_name":"Tongji University","ror":"https://ror.org/03rc6as71","country_code":"CN","type":"education","lineage":["https://openalex.org/I116953780"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Wanjing Ma","raw_affiliation_strings":["Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation, Tongji University, Shanghai 200092, China"],"affiliations":[{"raw_affiliation_string":"Key Laboratory of Road and Traffic Engineering of the Ministry of Education, College of Transportation, Tongji University, Shanghai 200092, China","institution_ids":["https://openalex.org/I116953780"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5112353020"],"corresponding_institution_ids":["https://openalex.org/I116953780"],"apc_list":{"value":1400,"currency":"CHF","value_usd":1515},"apc_paid":{"value":1400,"currency":"CHF","value_usd":1515},"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.06132667,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"17","issue":"6","first_page":"241","last_page":"241"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9958999752998352,"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"}},"topics":[{"id":"https://openalex.org/T10764","display_name":"Privacy-Preserving Technologies in Data","score":0.9958999752998352,"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/T11344","display_name":"Traffic Prediction and Management Techniques","score":0.9739000201225281,"subfield":{"id":"https://openalex.org/subfields/2215","display_name":"Building and Construction"},"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/T11704","display_name":"Mobile Crowdsensing and Crowdsourcing","score":0.9462000131607056,"subfield":{"id":"https://openalex.org/subfields/1706","display_name":"Computer Science Applications"},"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/computer-science","display_name":"Computer science","score":0.9152339696884155},{"id":"https://openalex.org/keywords/imputation","display_name":"Imputation (statistics)","score":0.6406641602516174},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.4609115719795227},{"id":"https://openalex.org/keywords/language-change","display_name":"Language change","score":0.45231926441192627},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.45033106207847595},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.44616007804870605},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.14751681685447693}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9152339696884155},{"id":"https://openalex.org/C58041806","wikidata":"https://www.wikidata.org/wiki/Q1660484","display_name":"Imputation (statistics)","level":3,"score":0.6406641602516174},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4609115719795227},{"id":"https://openalex.org/C2780027415","wikidata":"https://www.wikidata.org/wiki/Q524648","display_name":"Language change","level":2,"score":0.45231926441192627},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.45033106207847595},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.44616007804870605},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.14751681685447693},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0},{"id":"https://openalex.org/C124952713","wikidata":"https://www.wikidata.org/wiki/Q8242","display_name":"Literature","level":1,"score":0.0},{"id":"https://openalex.org/C142362112","wikidata":"https://www.wikidata.org/wiki/Q735","display_name":"Art","level":0,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.3390/fi17060241","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17060241","pdf_url":"https://www.mdpi.com/1999-5903/17/6/241/pdf?version=1748525858","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},{"id":"pmh:oai:doaj.org/article:f807eb71562e46dab04174cb5fa891b9","is_oa":true,"landing_page_url":"https://doaj.org/article/f807eb71562e46dab04174cb5fa891b9","pdf_url":null,"source":{"id":"https://openalex.org/S112646816","display_name":"SHILAP Revista de lepidopterolog\u00eda","issn_l":"0300-5267","issn":["0300-5267","2340-4078"],"is_oa":true,"is_in_doaj":true,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Future Internet, Vol 17, Iss 6, p 241 (2025)","raw_type":"article"}],"best_oa_location":{"id":"doi:10.3390/fi17060241","is_oa":true,"landing_page_url":"https://doi.org/10.3390/fi17060241","pdf_url":"https://www.mdpi.com/1999-5903/17/6/241/pdf?version=1748525858","source":{"id":"https://openalex.org/S34838331","display_name":"Future Internet","issn_l":"1999-5903","issn":["1999-5903"],"is_oa":true,"is_in_doaj":true,"is_core":true,"host_organization":"https://openalex.org/P4310310987","host_organization_name":"Multidisciplinary Digital Publishing Institute","host_organization_lineage":["https://openalex.org/P4310310987"],"host_organization_lineage_names":["Multidisciplinary Digital Publishing Institute"],"type":"journal"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Future Internet","raw_type":"journal-article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W4410859373.pdf"},"referenced_works_count":24,"referenced_works":["https://openalex.org/W1537066827","https://openalex.org/W2025768430","https://openalex.org/W2096863518","https://openalex.org/W2097381042","https://openalex.org/W2100358124","https://openalex.org/W2118502261","https://openalex.org/W2121092017","https://openalex.org/W2145339207","https://openalex.org/W2156267802","https://openalex.org/W2910166370","https://openalex.org/W2911964244","https://openalex.org/W2963523627","https://openalex.org/W2964010366","https://openalex.org/W2965373594","https://openalex.org/W2984869362","https://openalex.org/W3011411500","https://openalex.org/W3042609801","https://openalex.org/W3169283738","https://openalex.org/W3170657538","https://openalex.org/W4320013936","https://openalex.org/W4366548379","https://openalex.org/W6674600207","https://openalex.org/W6677939520","https://openalex.org/W6766673545"],"related_works":["https://openalex.org/W2961085424","https://openalex.org/W4306674287","https://openalex.org/W4387369504","https://openalex.org/W4394896187","https://openalex.org/W3170094116","https://openalex.org/W4386462264","https://openalex.org/W3107602296","https://openalex.org/W4364306694","https://openalex.org/W4312192474","https://openalex.org/W4283697347"],"abstract_inverted_index":{"Data":[0],"corruption,":[1],"including":[2],"missing":[3,84,99],"and":[4,20,31,53,112,127,162],"noisy":[5,166],"entries,":[6],"is":[7,123],"a":[8,69],"common":[9],"challenge":[10],"in":[11,87,165],"real-world":[12],"machine":[13],"learning.":[14],"This":[15,40,115],"paper":[16],"examines":[17],"its":[18,106],"impact":[19],"mitigation":[21],"strategies":[22,164],"through":[23],"two":[24],"experimental":[25],"setups:":[26],"supervised":[27],"NLP":[28],"tasks":[29,89,129],"(NLP-SL)":[30],"deep":[32],"reinforcement":[33],"learning":[34],"for":[35],"traffic":[36],"signal":[37],"control":[38],"(Signal-RL).":[39],"study":[41,116],"analyzes":[42],"how":[43],"varying":[44],"corruption":[45,60,110,138,146],"levels":[46],"affect":[47],"model":[48],"performance,":[49],"evaluate":[50],"imputation":[51,113,122,160],"strategies,":[52],"assess":[54],"whether":[55],"expanding":[56],"datasets":[57,136],"can":[58,102],"counteract":[59],"effects.":[61],"The":[62],"results":[63],"indicate":[64],"that":[65],"performance":[66,81],"degradation":[67],"follows":[68],"diminishing-return":[70],"pattern,":[71],"well":[72],"modeled":[73],"by":[74],"an":[75],"exponential":[76],"function.":[77],"Noisy":[78],"data":[79,100,158],"harm":[80],"more":[82],"than":[83],"data,":[85],"especially":[86],"sequential":[88],"like":[90],"Signal-RL":[91],"where":[92],"errors":[93],"may":[94],"compound.":[95],"Imputation":[96],"helps":[97],"recover":[98],"but":[101,140],"introduce":[103],"noise,":[104],"with":[105],"effectiveness":[107],"depending":[108],"on":[109],"severity":[111],"accuracy.":[114],"identifies":[117],"clear":[118],"boundaries":[119],"between":[120],"when":[121],"beneficial":[124],"versus":[125],"harmful,":[126],"classifies":[128],"as":[130],"either":[131],"noise-sensitive":[132],"or":[133],"noise-insensitive.":[134],"Larger":[135],"reduce":[137],"effects":[139],"offer":[141],"diminishing":[142],"gains":[143],"at":[144],"high":[145],"levels.":[147],"These":[148],"insights":[149],"guide":[150],"the":[151],"design":[152],"of":[153],"robust":[154],"systems,":[155],"emphasizing":[156],"smart":[157],"collection,":[159],"decisions,":[161],"preprocessing":[163],"environments.":[167]},"counts_by_year":[],"updated_date":"2026-02-27T16:54:17.756197","created_date":"2025-10-10T00:00:00"}