{"id":"https://openalex.org/W4416514193","doi":"https://doi.org/10.1109/isncc66965.2025.11250467","title":"From Raw to Refined: A Data Preprocessing Pipeline for Robust Prediction","display_name":"From Raw to Refined: A Data Preprocessing Pipeline for Robust Prediction","publication_year":2025,"publication_date":"2025-10-27","ids":{"openalex":"https://openalex.org/W4416514193","doi":"https://doi.org/10.1109/isncc66965.2025.11250467"},"language":null,"primary_location":{"id":"doi:10.1109/isncc66965.2025.11250467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isncc66965.2025.11250467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Symposium on Networks, Computers and Communications (ISNCC)","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/A5120371989","display_name":"Noor Qussay AlShaikhli","orcid":null},"institutions":[{"id":"https://openalex.org/I56409017","display_name":"Nahrain University","ror":"https://ror.org/05v2p9075","country_code":"IQ","type":"education","lineage":["https://openalex.org/I56409017"]}],"countries":["IQ"],"is_corresponding":false,"raw_author_name":"Noor Qussay AlShaikhli","raw_affiliation_strings":["Al-Nahrain University,College of Information Engineering,Baghdad,Iraq"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Al-Nahrain University,College of Information Engineering,Baghdad,Iraq","institution_ids":["https://openalex.org/I56409017"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5048154258","display_name":"Hakan Koyuncu","orcid":"https://orcid.org/0000-0002-8444-1094"},"institutions":[{"id":"https://openalex.org/I42317466","display_name":"Alt\u0131nba\u015f University","ror":"https://ror.org/0145w8333","country_code":"TR","type":"education","lineage":["https://openalex.org/I42317466"]}],"countries":["TR"],"is_corresponding":false,"raw_author_name":"Hakan Koyuncu","raw_affiliation_strings":["Altinbas University,computer Engineering Department,Istanbul,Turkey,34217"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Altinbas University,computer Engineering Department,Istanbul,Turkey,34217","institution_ids":["https://openalex.org/I42317466"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.41322412,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"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/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.9363999962806702,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12120","display_name":"Air Quality Monitoring and Forecasting","score":0.9363999962806702,"subfield":{"id":"https://openalex.org/subfields/2305","display_name":"Environmental Engineering"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10190","display_name":"Air Quality and Health Impacts","score":0.007199999876320362,"subfield":{"id":"https://openalex.org/subfields/2307","display_name":"Health, Toxicology and Mutagenesis"},"field":{"id":"https://openalex.org/fields/23","display_name":"Environmental Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11479","display_name":"Smart Cities and Technologies","score":0.006200000178068876,"subfield":{"id":"https://openalex.org/subfields/2214","display_name":"Media Technology"},"field":{"id":"https://openalex.org/fields/22","display_name":"Engineering"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.6650999784469604},{"id":"https://openalex.org/keywords/outlier","display_name":"Outlier","score":0.6456000208854675},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.6370999813079834},{"id":"https://openalex.org/keywords/pipeline","display_name":"Pipeline (software)","score":0.6068000197410583},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.5997999906539917},{"id":"https://openalex.org/keywords/missing-data","display_name":"Missing data","score":0.5368000268936157},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.510200023651123},{"id":"https://openalex.org/keywords/air-quality-index","display_name":"Air quality index","score":0.4072999954223633}],"concepts":[{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.7143999934196472},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.6650999784469604},{"id":"https://openalex.org/C79337645","wikidata":"https://www.wikidata.org/wiki/Q779824","display_name":"Outlier","level":2,"score":0.6456000208854675},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.6370999813079834},{"id":"https://openalex.org/C43521106","wikidata":"https://www.wikidata.org/wiki/Q2165493","display_name":"Pipeline (software)","level":2,"score":0.6068000197410583},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.5997999906539917},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5978000164031982},{"id":"https://openalex.org/C9357733","wikidata":"https://www.wikidata.org/wiki/Q6878417","display_name":"Missing data","level":2,"score":0.5368000268936157},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.510200023651123},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.41589999198913574},{"id":"https://openalex.org/C126314574","wikidata":"https://www.wikidata.org/wiki/Q2364111","display_name":"Air quality index","level":2,"score":0.4072999954223633},{"id":"https://openalex.org/C175309249","wikidata":"https://www.wikidata.org/wiki/Q725864","display_name":"Pipeline transport","level":2,"score":0.3912000060081482},{"id":"https://openalex.org/C2781067378","wikidata":"https://www.wikidata.org/wiki/Q17027399","display_name":"Interpretability","level":2,"score":0.37630000710487366},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3725999891757965},{"id":"https://openalex.org/C2776356880","wikidata":"https://www.wikidata.org/wiki/Q5381206","display_name":"Environmental data","level":2,"score":0.36559998989105225},{"id":"https://openalex.org/C24756922","wikidata":"https://www.wikidata.org/wiki/Q1757694","display_name":"Data quality","level":3,"score":0.3562000095844269},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.3398999869823456},{"id":"https://openalex.org/C739882","wikidata":"https://www.wikidata.org/wiki/Q3560506","display_name":"Anomaly detection","level":2,"score":0.31850001215934753},{"id":"https://openalex.org/C63479239","wikidata":"https://www.wikidata.org/wiki/Q7353546","display_name":"Robustness (evolution)","level":3,"score":0.3077999949455261},{"id":"https://openalex.org/C49020025","wikidata":"https://www.wikidata.org/wiki/Q1059099","display_name":"Chaining","level":2,"score":0.28769999742507935},{"id":"https://openalex.org/C127413603","wikidata":"https://www.wikidata.org/wiki/Q11023","display_name":"Engineering","level":0,"score":0.28690001368522644},{"id":"https://openalex.org/C196083921","wikidata":"https://www.wikidata.org/wiki/Q7915758","display_name":"Variance (accounting)","level":2,"score":0.2766999900341034},{"id":"https://openalex.org/C46686674","wikidata":"https://www.wikidata.org/wiki/Q466303","display_name":"Boosting (machine learning)","level":2,"score":0.27219998836517334},{"id":"https://openalex.org/C2777767291","wikidata":"https://www.wikidata.org/wiki/Q1080291","display_name":"Sizing","level":2,"score":0.2685999870300293},{"id":"https://openalex.org/C138827492","wikidata":"https://www.wikidata.org/wiki/Q6661985","display_name":"Data processing","level":2,"score":0.25450000166893005}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/isncc66965.2025.11250467","is_oa":false,"landing_page_url":"https://doi.org/10.1109/isncc66965.2025.11250467","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2025 International Symposium on Networks, Computers and Communications (ISNCC)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":27,"referenced_works":["https://openalex.org/W2890098390","https://openalex.org/W2912376047","https://openalex.org/W2979417040","https://openalex.org/W2998862520","https://openalex.org/W3159260083","https://openalex.org/W3170657538","https://openalex.org/W3176644936","https://openalex.org/W3182465062","https://openalex.org/W3185330107","https://openalex.org/W3186428586","https://openalex.org/W3199638341","https://openalex.org/W4200457408","https://openalex.org/W4206086079","https://openalex.org/W4220722235","https://openalex.org/W4293242646","https://openalex.org/W4320884090","https://openalex.org/W4362586055","https://openalex.org/W4367598939","https://openalex.org/W4383503610","https://openalex.org/W4384283312","https://openalex.org/W4389674350","https://openalex.org/W4392941830","https://openalex.org/W4393141143","https://openalex.org/W4404847869","https://openalex.org/W4405755492","https://openalex.org/W4405907889","https://openalex.org/W4408241164"],"related_works":[],"abstract_inverted_index":{"Precise":[0],"air":[1,47,129],"quality":[2,17,48,130],"prediction":[3],"is":[4],"an":[5,46],"essential":[6],"criterion":[7],"for":[8,93,135,141],"smart":[9,150],"cities.":[10],"Prediction":[11],"accuracy":[12],"relies":[13],"heavily":[14],"on":[15,55],"the":[16,67],"of":[18,146],"input":[19],"data.":[20],"However,":[21],"raw":[22],"environmental":[23,136],"datasets":[24],"often":[25],"suffer":[26],"from":[27,50],"missing":[28,68],"values":[29,69],"and":[30,64,72,82,100,108,138],"outliers,":[31],"leading":[32],"to":[33,45,97,126],"reduced":[34],"model":[35],"performance.":[36],"This":[37],"paper":[38],"presents":[39],"a":[40,142],"systematic":[41],"preprocessing":[42,119],"framework":[43],"applied":[44],"dataset":[49],"Seoul,":[51],"South":[52],"Korea,":[53],"focusing":[54],"key":[56],"pollutants":[57],"including":[58],"$\\mathrm{SO}_{2},":[59],"\\mathrm{NO}_{2},":[60],"\\mathrm{O}_{3},":[61],"\\mathrm{CO}$,":[62],"PM10,":[63],"PM2.5.":[65],"First,":[66],"were":[70],"identified":[71],"addressed":[73],"using":[74,89],"method":[75],"chaining":[76],"operations":[77],"in":[78],"Python,":[79],"ensuring":[80],"efficient":[81],"reproducible":[83],"cleaning.":[84],"Outlier":[85],"detection":[86],"was":[87],"performed":[88],"multiple":[90],"strategies,":[91],"tailored":[92],"each":[94],"pollutant":[95],"according":[96],"its":[98,133],"nature":[99],"value":[101],"range.":[102],"Results":[103],"show":[104],"significant":[105],"variance":[106],"reduction":[107],"improved":[109],"data":[110],"consistency,":[111],"enabling":[112],"better":[113],"downstream":[114],"machine":[115],"learning":[116],"modeling.":[117],"The":[118],"approach":[120],"demonstrated":[121],"here":[122],"can":[123],"be":[124],"generalized":[125],"similar":[127],"urban":[128],"datasets,":[131],"highlighting":[132],"effectiveness":[134],"monitoring":[137],"prediction,":[139],"calling":[140],"more":[143],"sustainable":[144],"way":[145],"living":[147],"that":[148],"supports":[149],"cities":[151],"management.":[152]},"counts_by_year":[],"updated_date":"2026-07-29T14:22:42.915294","created_date":"2025-11-23T00:00:00"}