{"id":"https://openalex.org/W3010894680","doi":"https://doi.org/10.1142/s0219649220400146","title":"Data Imbalance in Autism Pre-Diagnosis Classification Systems: An Experimental Study","display_name":"Data Imbalance in Autism Pre-Diagnosis Classification Systems: An Experimental Study","publication_year":2020,"publication_date":"2020-03-01","ids":{"openalex":"https://openalex.org/W3010894680","doi":"https://doi.org/10.1142/s0219649220400146","mag":"3010894680"},"language":"en","primary_location":{"id":"doi:10.1142/s0219649220400146","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219649220400146","pdf_url":null,"source":{"id":"https://openalex.org/S30163770","display_name":"Journal of Information & Knowledge Management","issn_l":"0219-6492","issn":["0219-6492","1793-6926"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information & Knowledge Management","raw_type":"journal-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://pure.hud.ac.uk/en/publications/10c77c49-82f9-40af-a67f-6265484523b2","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5052862524","display_name":"Neda Abdelhamid","orcid":"https://orcid.org/0000-0003-3638-8919"},"institutions":[{"id":"https://openalex.org/I1336277565","display_name":"Auckland Institute of Studies","ror":"https://ror.org/0090kax79","country_code":"NZ","type":"education","lineage":["https://openalex.org/I1336277565"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Neda Abdelhamid","raw_affiliation_strings":["IT Programme, Auckland Institute of Studies, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"IT Programme, Auckland Institute of Studies, Auckland, New Zealand","institution_ids":["https://openalex.org/I1336277565"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5022648171","display_name":"Arun Padmavathy","orcid":null},"institutions":[{"id":"https://openalex.org/I125931852","display_name":"Manukau Institute of Technology","ror":"https://ror.org/002r67t24","country_code":"NZ","type":"education","lineage":["https://openalex.org/I125931852","https://openalex.org/I4387152882"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Arun Padmavathy","raw_affiliation_strings":["Digital Technologies, Manukau Institute of Technology, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"Digital Technologies, Manukau Institute of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I125931852"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5054687784","display_name":"David Peebles","orcid":"https://orcid.org/0000-0003-1008-9275"},"institutions":[{"id":"https://openalex.org/I133837150","display_name":"University of Huddersfield","ror":"https://ror.org/05t1h8f27","country_code":"GB","type":"education","lineage":["https://openalex.org/I133837150"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"David Peebles","raw_affiliation_strings":["Department of Psychology, University of Huddersfield, Queensgate, Huddersfield HD1 3DH, UK"],"affiliations":[{"raw_affiliation_string":"Department of Psychology, University of Huddersfield, Queensgate, Huddersfield HD1 3DH, UK","institution_ids":["https://openalex.org/I133837150"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5057725721","display_name":"Fadi Thabtah","orcid":null},"institutions":[{"id":"https://openalex.org/I125931852","display_name":"Manukau Institute of Technology","ror":"https://ror.org/002r67t24","country_code":"NZ","type":"education","lineage":["https://openalex.org/I125931852","https://openalex.org/I4387152882"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Fadi Thabtah","raw_affiliation_strings":["Digital Technologies, Manukau Institute of Technology, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"Digital Technologies, Manukau Institute of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I125931852"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5046075754","display_name":"Daymond Goulder-Horobin","orcid":null},"institutions":[{"id":"https://openalex.org/I125931852","display_name":"Manukau Institute of Technology","ror":"https://ror.org/002r67t24","country_code":"NZ","type":"education","lineage":["https://openalex.org/I125931852","https://openalex.org/I4387152882"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Daymond Goulder-Horobin","raw_affiliation_strings":["Digital Technologies, Manukau Institute of Technology, Auckland, New Zealand"],"affiliations":[{"raw_affiliation_string":"Digital Technologies, Manukau Institute of Technology, Auckland, New Zealand","institution_ids":["https://openalex.org/I125931852"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":5,"corresponding_author_ids":["https://openalex.org/A5052862524"],"corresponding_institution_ids":["https://openalex.org/I1336277565"],"apc_list":null,"apc_paid":null,"fwci":2.1942,"has_fulltext":true,"cited_by_count":21,"citation_normalized_percentile":{"value":0.89947844,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"19","issue":"01","first_page":"2040014","last_page":"2040014"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9983000159263611,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9983000159263611,"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/T13429","display_name":"Electricity Theft Detection Techniques","score":0.9749000072479248,"subfield":{"id":"https://openalex.org/subfields/2208","display_name":"Electrical and Electronic 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/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9448000192642212,"subfield":{"id":"https://openalex.org/subfields/3605","display_name":"Health Information Management"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/undersampling","display_name":"Undersampling","score":0.9661425352096558},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.8745570182800293},{"id":"https://openalex.org/keywords/overfitting","display_name":"Overfitting","score":0.8032888174057007},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7477138042449951},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.6947105526924133},{"id":"https://openalex.org/keywords/autism","display_name":"Autism","score":0.6917296648025513},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6442996263504028},{"id":"https://openalex.org/keywords/autism-spectrum-disorder","display_name":"Autism spectrum disorder","score":0.6028004884719849},{"id":"https://openalex.org/keywords/class","display_name":"Class (philosophy)","score":0.5616593360900879},{"id":"https://openalex.org/keywords/neurotypical","display_name":"Neurotypical","score":0.5546389222145081},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.5002586841583252},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.4629979729652405},{"id":"https://openalex.org/keywords/feature-selection","display_name":"Feature selection","score":0.4236033260822296},{"id":"https://openalex.org/keywords/popularity","display_name":"Popularity","score":0.4147932827472687},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3584679961204529},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.22126886248588562},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.21229931712150574},{"id":"https://openalex.org/keywords/psychology","display_name":"Psychology","score":0.177756667137146}],"concepts":[{"id":"https://openalex.org/C136536468","wikidata":"https://www.wikidata.org/wiki/Q1225894","display_name":"Undersampling","level":2,"score":0.9661425352096558},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.8745570182800293},{"id":"https://openalex.org/C22019652","wikidata":"https://www.wikidata.org/wiki/Q331309","display_name":"Overfitting","level":3,"score":0.8032888174057007},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7477138042449951},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.6947105526924133},{"id":"https://openalex.org/C205778803","wikidata":"https://www.wikidata.org/wiki/Q38404","display_name":"Autism","level":2,"score":0.6917296648025513},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6442996263504028},{"id":"https://openalex.org/C2778538070","wikidata":"https://www.wikidata.org/wiki/Q1436063","display_name":"Autism spectrum disorder","level":3,"score":0.6028004884719849},{"id":"https://openalex.org/C2777212361","wikidata":"https://www.wikidata.org/wiki/Q5127848","display_name":"Class (philosophy)","level":2,"score":0.5616593360900879},{"id":"https://openalex.org/C2778391849","wikidata":"https://www.wikidata.org/wiki/Q1079090","display_name":"Neurotypical","level":4,"score":0.5546389222145081},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.5002586841583252},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.4629979729652405},{"id":"https://openalex.org/C148483581","wikidata":"https://www.wikidata.org/wiki/Q446488","display_name":"Feature selection","level":2,"score":0.4236033260822296},{"id":"https://openalex.org/C2780586970","wikidata":"https://www.wikidata.org/wiki/Q1357284","display_name":"Popularity","level":2,"score":0.4147932827472687},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3584679961204529},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.22126886248588562},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.21229931712150574},{"id":"https://openalex.org/C15744967","wikidata":"https://www.wikidata.org/wiki/Q9418","display_name":"Psychology","level":0,"score":0.177756667137146},{"id":"https://openalex.org/C138496976","wikidata":"https://www.wikidata.org/wiki/Q175002","display_name":"Developmental psychology","level":1,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C77805123","wikidata":"https://www.wikidata.org/wiki/Q161272","display_name":"Social psychology","level":1,"score":0.0},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1142/s0219649220400146","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0219649220400146","pdf_url":null,"source":{"id":"https://openalex.org/S30163770","display_name":"Journal of Information & Knowledge Management","issn_l":"0219-6492","issn":["0219-6492","1793-6926"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Information & Knowledge Management","raw_type":"journal-article"},{"id":"pmh:oai:pure.atira.dk:publications/10c77c49-82f9-40af-a67f-6265484523b2","is_oa":true,"landing_page_url":"https://pure.hud.ac.uk/en/publications/10c77c49-82f9-40af-a67f-6265484523b2","pdf_url":"https://pure.hud.ac.uk/en/publications/10c77c49-82f9-40af-a67f-6265484523b2","source":{"id":"https://openalex.org/S4306402508","display_name":"Huddersfield Research Portal (University of Huddersfield)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I133837150","host_organization_name":"University of Huddersfield","host_organization_lineage":["https://openalex.org/I133837150"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Abdelhamid, N, Padmavathy, A, Peebles, D, Thabtah, F & Goulder-Horobin, D 2020, 'Data Imbalance in Autism Pre-Diagnosis Classification Systems : An Experimental Study', Journal of Information and Knowledge Management, vol. 19, no. 1, 2040014. https://doi.org/10.1142/S0219649220400146","raw_type":"info:eu-repo/semantics/publishedVersion"},{"id":"pmh:oai:RePEc:wsi:jikmxx:v:19:y:2020:i:01:n:s0219649220400146","is_oa":false,"landing_page_url":"https://www.worldscientific.com/doi/abs/10.1142/S0219649220400146","pdf_url":null,"source":{"id":"https://openalex.org/S4306401271","display_name":"RePEc: Research Papers in Economics","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I77793887","host_organization_name":"Federal Reserve Bank of St. Louis","host_organization_lineage":["https://openalex.org/I77793887"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"}],"best_oa_location":{"id":"pmh:oai:pure.atira.dk:publications/10c77c49-82f9-40af-a67f-6265484523b2","is_oa":true,"landing_page_url":"https://pure.hud.ac.uk/en/publications/10c77c49-82f9-40af-a67f-6265484523b2","pdf_url":"https://pure.hud.ac.uk/en/publications/10c77c49-82f9-40af-a67f-6265484523b2","source":{"id":"https://openalex.org/S4306402508","display_name":"Huddersfield Research Portal (University of Huddersfield)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I133837150","host_organization_name":"University of Huddersfield","host_organization_lineage":["https://openalex.org/I133837150"],"host_organization_lineage_names":[],"type":"repository"},"license":"other-oa","license_id":"https://openalex.org/licenses/other-oa","version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Abdelhamid, N, Padmavathy, A, Peebles, D, Thabtah, F & Goulder-Horobin, D 2020, 'Data Imbalance in Autism Pre-Diagnosis Classification Systems : An Experimental Study', Journal of Information and Knowledge Management, vol. 19, no. 1, 2040014. https://doi.org/10.1142/S0219649220400146","raw_type":"info:eu-repo/semantics/publishedVersion"},"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/16","display_name":"Peace, Justice and strong institutions","score":0.7099999785423279}],"awards":[],"funders":[],"has_content":{"grobid_xml":true,"pdf":true},"content_urls":{"pdf":"https://content.openalex.org/works/W3010894680.pdf","grobid_xml":"https://content.openalex.org/works/W3010894680.grobid-xml"},"referenced_works_count":35,"referenced_works":["https://openalex.org/W1670263352","https://openalex.org/W1981837223","https://openalex.org/W1994118694","https://openalex.org/W2023639956","https://openalex.org/W2033184625","https://openalex.org/W2070808135","https://openalex.org/W2100429511","https://openalex.org/W2122111042","https://openalex.org/W2124776405","https://openalex.org/W2125055259","https://openalex.org/W2133506114","https://openalex.org/W2137839571","https://openalex.org/W2148143831","https://openalex.org/W2169105308","https://openalex.org/W2334028018","https://openalex.org/W2521504039","https://openalex.org/W2549616881","https://openalex.org/W2593875029","https://openalex.org/W2736661778","https://openalex.org/W2761291515","https://openalex.org/W2790175216","https://openalex.org/W2800394774","https://openalex.org/W2809960885","https://openalex.org/W2901423801","https://openalex.org/W2911964244","https://openalex.org/W2940437698","https://openalex.org/W2947139752","https://openalex.org/W2989219518","https://openalex.org/W2992822050","https://openalex.org/W2995959774","https://openalex.org/W3099414278","https://openalex.org/W4239510810","https://openalex.org/W4244630340","https://openalex.org/W4247665917","https://openalex.org/W4380488575"],"related_works":["https://openalex.org/W4206583062","https://openalex.org/W3176807344","https://openalex.org/W4385625096","https://openalex.org/W4206325870","https://openalex.org/W4292869357","https://openalex.org/W4366768903","https://openalex.org/W4375930479","https://openalex.org/W4321499019","https://openalex.org/W3193372619","https://openalex.org/W3176795340"],"abstract_inverted_index":{"Machine":[0],"learning":[1],"(ML)":[2],"is":[3,10,103,112],"a":[4,67],"branch":[5],"of":[6,45,100,141,148,193,198,204],"computer":[7],"science":[8],"that":[9,30,213,228,233,248],"rapidly":[11],"gaining":[12],"popularity":[13],"within":[14],"the":[15,43,92,98,109,115,127,132,139,146,163,191,196,199,224,252],"healthcare":[16],"arena":[17],"due":[18],"to":[19,22,26,189,218,245],"its":[20],"ability":[21],"explore":[23],"large":[24],"datasets":[25,154],"discover":[27],"useful":[28],"patterns":[29],"can":[31],"be":[32],"interepreted":[33],"for":[34,42,51,223],"decision-making":[35],"and":[36,48,55,57,60,117,130,176,186,208,231],"prediction.":[37],"ML":[38],"techniques":[39,215,241],"are":[40,85,160,216],"used":[41],"analysis":[44],"clinical":[46],"parameters":[47],"their":[49],"combinations":[50],"prognosis,":[52],"therapy":[53],"planning":[54],"support":[56],"patient":[58],"management":[59],"wellbeing.":[61],"In":[62,94],"this":[63,118],"research,":[64],"we":[65,229],"investigate":[66],"crucial":[68],"problem":[69],"associated":[70],"with":[71,105,178,242],"medical":[72],"applications":[73],"such":[74,123,170],"as":[75,124,171],"autism":[76,95,153,226],"spectrum":[77],"disorder":[78],"(ASD)":[79],"data":[80,157],"imbalances":[81],"in":[82,91,162,202],"which":[83],"cases":[84],"far":[86],"more":[87],"than":[88,114],"just":[89],"controls":[90],"dataset.":[93,253],"diagnosis":[96],"data,":[97],"number":[99],"possible":[101],"instances":[102],"linked":[104],"one":[106],"class,":[107],"i.e.":[108],"no":[110],"ASD":[111],"larger":[113],"ASD,":[116],"may":[119],"cause":[120],"performance":[121,147,197],"issues":[122],"models":[125,200,247],"favouring":[126],"majority":[128],"class":[129,142],"undermining":[131],"minority":[133],"class.":[134],"This":[135],"research":[136],"experimentally":[137],"measures":[138],"impact":[140,192],"imbalance":[143,158],"issue":[144],"on":[145,151,195],"different":[149,179],"classifiers":[150,180],"real":[152],"when":[155],"various":[156],"approaches":[159],"utilised":[161],"pre-processing":[164],"phase.":[165],"We":[166],"employ":[167],"oversampling":[168,214],"techniques,":[169,220],"Synthetic":[172],"Minority":[173],"Oversampling":[174],"(SMOTE),":[175],"undersampling":[177,219],"including":[181],"Naive":[182],"Bayes,":[183],"RIPPER,":[184],"C4.5":[185],"Random":[187],"Forest":[188],"measure":[190],"these":[194],"derived":[201],"terms":[203],"area":[205],"under":[206],"curve":[207],"other":[209],"metrics.":[210],"Results":[211],"pinpoint":[212],"superior":[217],"at":[221,238],"least":[222],"toddlers\u2019":[225],"dataset":[227],"consider,":[230],"suggest":[232],"further":[234],"work":[235],"should":[236],"look":[237],"incorporating":[239],"sampling":[240],"feature":[243],"selection":[244],"generate":[246],"do":[249],"not":[250],"overfit":[251]},"counts_by_year":[{"year":2026,"cited_by_count":1},{"year":2025,"cited_by_count":3},{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":9},{"year":2022,"cited_by_count":6},{"year":2021,"cited_by_count":1}],"updated_date":"2026-03-17T17:19:04.345684","created_date":"2025-10-10T00:00:00"}