{"id":"https://openalex.org/W4229333403","doi":"https://doi.org/10.1142/s1793962323500101","title":"Diabetes mellitus prediction: An efficient pipeline of data imputation and oversampling","display_name":"Diabetes mellitus prediction: An efficient pipeline of data imputation and oversampling","publication_year":2022,"publication_date":"2022-05-08","ids":{"openalex":"https://openalex.org/W4229333403","doi":"https://doi.org/10.1142/s1793962323500101"},"language":"en","primary_location":{"id":"doi:10.1142/s1793962323500101","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793962323500101","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"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":"International Journal of Modeling, Simulation, and Scientific Computing","raw_type":"journal-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/A5064610296","display_name":"Neha Rajawat","orcid":null},"institutions":[{"id":"https://openalex.org/I4210091899","display_name":"Career Point University","ror":"https://ror.org/00e2khh43","country_code":"IN","type":"education","lineage":["https://openalex.org/I4210091899"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Neha Rajawat","raw_affiliation_strings":["Department of Mathematics, Career Point University, Kota, India"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Career Point University, Kota, India","institution_ids":["https://openalex.org/I4210091899"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5035191475","display_name":"Bharat Singh Hada","orcid":null},"institutions":[{"id":"https://openalex.org/I4210139030","display_name":"Samsung (India)","ror":"https://ror.org/04cpx2569","country_code":"IN","type":"company","lineage":["https://openalex.org/I2250650973","https://openalex.org/I4210139030"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Bharat Singh Hada","raw_affiliation_strings":["Samsung R & D Institute, Noida, India"],"affiliations":[{"raw_affiliation_string":"Samsung R & D Institute, Noida, India","institution_ids":["https://openalex.org/I4210139030"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025901213","display_name":"Soniya Lalwani","orcid":null},"institutions":[],"countries":[],"is_corresponding":true,"raw_author_name":"Soniya Lalwani","raw_affiliation_strings":["Department of Mathematics, Bal Krishna Institute of Technology, Kota, India"],"affiliations":[{"raw_affiliation_string":"Department of Mathematics, Bal Krishna Institute of Technology, Kota, India","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5052848876","display_name":"Rajesh Kumar","orcid":"https://orcid.org/0000-0002-6019-0702"},"institutions":[{"id":"https://openalex.org/I83205935","display_name":"Malaviya National Institute of Technology Jaipur","ror":"https://ror.org/0077k1j32","country_code":"IN","type":"education","lineage":["https://openalex.org/I83205935"]}],"countries":["IN"],"is_corresponding":false,"raw_author_name":"Rajesh Kumar","raw_affiliation_strings":["Department of Electrical Engineering, Malaviya National Institute of Technology, Jaipur, India"],"affiliations":[{"raw_affiliation_string":"Department of Electrical Engineering, Malaviya National Institute of Technology, Jaipur, India","institution_ids":["https://openalex.org/I83205935"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5025901213"],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.2693,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.68440255,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":"14","issue":"03","first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9998000264167786,"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"}},"topics":[{"id":"https://openalex.org/T11396","display_name":"Artificial Intelligence in Healthcare","score":0.9998000264167786,"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"}},{"id":"https://openalex.org/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9761000275611877,"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/T13702","display_name":"Machine Learning in Healthcare","score":0.9523000121116638,"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/support-vector-machine","display_name":"Support vector machine","score":0.7166496515274048},{"id":"https://openalex.org/keywords/random-forest","display_name":"Random forest","score":0.691527247428894},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6567203998565674},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.6507889628410339},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.5067921280860901},{"id":"https://openalex.org/keywords/data-pre-processing","display_name":"Data pre-processing","score":0.4789300858974457},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.4689860939979553},{"id":"https://openalex.org/keywords/oversampling","display_name":"Oversampling","score":0.4500562846660614},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4425064027309418},{"id":"https://openalex.org/keywords/decision-tree","display_name":"Decision tree","score":0.4390451908111572},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.4353765547275543},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.43237465620040894},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.41397541761398315}],"concepts":[{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.7166496515274048},{"id":"https://openalex.org/C169258074","wikidata":"https://www.wikidata.org/wiki/Q245748","display_name":"Random forest","level":2,"score":0.691527247428894},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6567203998565674},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.6507889628410339},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.5067921280860901},{"id":"https://openalex.org/C10551718","wikidata":"https://www.wikidata.org/wiki/Q5227332","display_name":"Data pre-processing","level":2,"score":0.4789300858974457},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.4689860939979553},{"id":"https://openalex.org/C197323446","wikidata":"https://www.wikidata.org/wiki/Q331222","display_name":"Oversampling","level":3,"score":0.4500562846660614},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4425064027309418},{"id":"https://openalex.org/C84525736","wikidata":"https://www.wikidata.org/wiki/Q831366","display_name":"Decision tree","level":2,"score":0.4390451908111572},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.4353765547275543},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.43237465620040894},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.41397541761398315},{"id":"https://openalex.org/C2776257435","wikidata":"https://www.wikidata.org/wiki/Q1576430","display_name":"Bandwidth (computing)","level":2,"score":0.0},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1142/s1793962323500101","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s1793962323500101","pdf_url":null,"source":{"id":"https://openalex.org/S107361000","display_name":"Advances in Complex Systems","issn_l":"0219-5259","issn":["0219-5259","1793-6802","1793-9615","1793-9623"],"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":"International Journal of Modeling, Simulation, and Scientific Computing","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.4300000071525574,"display_name":"Life in Land","id":"https://metadata.un.org/sdg/15"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":7,"referenced_works":["https://openalex.org/W1991181258","https://openalex.org/W2123380119","https://openalex.org/W2139944275","https://openalex.org/W2414319411","https://openalex.org/W2807027008","https://openalex.org/W2884179193","https://openalex.org/W2898880747"],"related_works":["https://openalex.org/W2012117566","https://openalex.org/W1981856929","https://openalex.org/W2989490741","https://openalex.org/W4389954502","https://openalex.org/W138569904","https://openalex.org/W2367545121","https://openalex.org/W2771255398","https://openalex.org/W4248881655","https://openalex.org/W2482165163","https://openalex.org/W3010890513"],"abstract_inverted_index":{"Diabetes":[0,116],"is":[1,89,165,169,196],"a":[2,109,160],"chronic":[3],"disease":[4],"which":[5],"indicates":[6],"the":[7,16,50,99,122,172],"high":[8],"level":[9],"of":[10,41,101,112,115],"body":[11],"glucose":[12],"level.":[13],"As":[14],"per":[15],"World":[17],"Health":[18],"Organization":[19],"(WHO),":[20],"422":[21],"million":[22],"people":[23],"were":[24],"diabetic":[25],"until":[26],"2014.":[27],"This":[28],"paper":[29],"develops":[30],"an":[31,38],"accurate":[32],"classification":[33,83,140],"machine":[34],"learning":[35],"model":[36],"and":[37,77,85,94,117,119,132,153,167,179,187],"efficient":[39],"usage":[40],"data":[42,127,130,176],"pre-processing":[43],"pipeline":[44],"to":[45,147],"improve":[46],"overall":[47],"accuracy.":[48],"For":[49],"purpose,":[51],"six":[52],"algorithms:":[53],"Support":[54,61],"Vector":[55,62],"Machine":[56,63],"with":[57,64,183],"Linear":[58],"kernel":[59,66],"(Linear-SVM),":[60],"RBF":[65],"(RBF-SVM),":[67],"K-Nearest":[68],"Neighbor":[69],"(KNN),":[70],"Artificial":[71],"Neural":[72],"Network":[73],"(ANN),":[74],"Decision":[75],"Tree":[76],"Random":[78,150],"Forest":[79,151],"are":[80,98,106,181],"used":[81],"for":[82],"purpose":[84],"their":[86],"comparative":[87],"accuracy":[88,141],"analyzed.":[90],"Data":[91,102],"Imputation,":[92],"Oversampling":[93],"Feature":[95],"scaling":[96],"techniques":[97],"constituents":[100],"preprocessing":[103,128],"pipeline.":[104],"Experiments":[105],"performed":[107],"on":[108,144],"well-known":[110],"dataset":[111],"National":[113],"Institute":[114],"Digestive":[118],"Kidney":[120],"Diseases,":[121],"PIMA":[123],"diabetes":[124],"dataset.":[125],"The":[126,190],"techniques,":[129],"imputation":[131],"Synthetic":[133],"Minority":[134],"Oversample":[135],"Technique":[136],"(SMOTE)":[137],"analysis":[138],"improved":[139],"from":[142],"77%":[143],"raw":[145],"data,":[146],"88.12%":[148],"(on":[149,155],"Classifier)":[152],"91%":[154],"ANN":[156],"Classifier),":[157],"respectively.":[158,189],"Furthermore,":[159],"new":[161,184],"feature":[162],"generation":[163],"approach":[164],"applied":[166],"performance":[168],"analyzed":[170],"using":[171],"SVM":[173],"model.":[174],"Original":[175],"attributes":[177],"BMI":[178],"Insulin":[180],"replaced":[182],"features":[185],"BMI_NORMAL":[186],"INSULIN_NORMAL,":[188],"significant":[191],"improvement":[192],"by":[193,198,202],"proposed":[194],"technique":[195],"confirmed":[197],"statistical":[199],"testing":[200],"followed":[201],"post-hoc":[203],"analysis.":[204]},"counts_by_year":[{"year":2024,"cited_by_count":1}],"updated_date":"2026-04-17T18:11:37.981687","created_date":"2025-10-10T00:00:00"}